diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/datagram.c | 2 | ||||
-rw-r--r-- | net/core/dev.c | 383 | ||||
-rw-r--r-- | net/core/ethtool.c | 21 | ||||
-rw-r--r-- | net/core/fib_rules.c | 3 | ||||
-rw-r--r-- | net/core/filter.c | 533 | ||||
-rw-r--r-- | net/core/neighbour.c | 1 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 430 | ||||
-rw-r--r-- | net/core/net-sysfs.h | 4 | ||||
-rw-r--r-- | net/core/netpoll.c | 6 | ||||
-rw-r--r-- | net/core/pktgen.c | 44 | ||||
-rw-r--r-- | net/core/request_sock.c | 1 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 166 | ||||
-rw-r--r-- | net/core/scm.c | 10 | ||||
-rw-r--r-- | net/core/skbuff.c | 36 | ||||
-rw-r--r-- | net/core/sock.c | 60 | ||||
-rw-r--r-- | net/core/timestamping.c | 10 |
16 files changed, 1247 insertions, 463 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index cd1e039c875..18ac112ea7a 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -177,7 +177,7 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned flags, * interrupt level will suddenly eat the receive_queue. * * Look at current nfs client by the way... - * However, this function was corrent in any case. 8) + * However, this function was correct in any case. 8) */ unsigned long cpu_flags; diff --git a/net/core/dev.c b/net/core/dev.c index 0dd54a69dac..a215269d2e3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -743,34 +743,31 @@ struct net_device *dev_get_by_index(struct net *net, int ifindex) EXPORT_SYMBOL(dev_get_by_index); /** - * dev_getbyhwaddr - find a device by its hardware address + * dev_getbyhwaddr_rcu - find a device by its hardware address * @net: the applicable net namespace * @type: media type of device * @ha: hardware address * * Search for an interface by MAC address. Returns NULL if the device - * is not found or a pointer to the device. The caller must hold the - * rtnl semaphore. The returned device has not had its ref count increased + * is not found or a pointer to the device. The caller must hold RCU + * The returned device has not had its ref count increased * and the caller must therefore be careful about locking * - * BUGS: - * If the API was consistent this would be __dev_get_by_hwaddr */ -struct net_device *dev_getbyhwaddr(struct net *net, unsigned short type, char *ha) +struct net_device *dev_getbyhwaddr_rcu(struct net *net, unsigned short type, + const char *ha) { struct net_device *dev; - ASSERT_RTNL(); - - for_each_netdev(net, dev) + for_each_netdev_rcu(net, dev) if (dev->type == type && !memcmp(dev->dev_addr, ha, dev->addr_len)) return dev; return NULL; } -EXPORT_SYMBOL(dev_getbyhwaddr); +EXPORT_SYMBOL(dev_getbyhwaddr_rcu); struct net_device *__dev_getfirstbyhwtype(struct net *net, unsigned short type) { @@ -1225,52 +1222,90 @@ int dev_open(struct net_device *dev) } EXPORT_SYMBOL(dev_open); -static int __dev_close(struct net_device *dev) +static int __dev_close_many(struct list_head *head) { - const struct net_device_ops *ops = dev->netdev_ops; + struct net_device *dev; ASSERT_RTNL(); might_sleep(); - /* - * Tell people we are going down, so that they can - * prepare to death, when device is still operating. - */ - call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); + list_for_each_entry(dev, head, unreg_list) { + /* + * Tell people we are going down, so that they can + * prepare to death, when device is still operating. + */ + call_netdevice_notifiers(NETDEV_GOING_DOWN, dev); - clear_bit(__LINK_STATE_START, &dev->state); + clear_bit(__LINK_STATE_START, &dev->state); - /* Synchronize to scheduled poll. We cannot touch poll list, - * it can be even on different cpu. So just clear netif_running(). - * - * dev->stop() will invoke napi_disable() on all of it's - * napi_struct instances on this device. - */ - smp_mb__after_clear_bit(); /* Commit netif_running(). */ + /* Synchronize to scheduled poll. We cannot touch poll list, it + * can be even on different cpu. So just clear netif_running(). + * + * dev->stop() will invoke napi_disable() on all of it's + * napi_struct instances on this device. + */ + smp_mb__after_clear_bit(); /* Commit netif_running(). */ + } - dev_deactivate(dev); + dev_deactivate_many(head); - /* - * Call the device specific close. This cannot fail. - * Only if device is UP - * - * We allow it to be called even after a DETACH hot-plug - * event. - */ - if (ops->ndo_stop) - ops->ndo_stop(dev); + list_for_each_entry(dev, head, unreg_list) { + const struct net_device_ops *ops = dev->netdev_ops; - /* - * Device is now down. - */ + /* + * Call the device specific close. This cannot fail. + * Only if device is UP + * + * We allow it to be called even after a DETACH hot-plug + * event. + */ + if (ops->ndo_stop) + ops->ndo_stop(dev); + + /* + * Device is now down. + */ + + dev->flags &= ~IFF_UP; + + /* + * Shutdown NET_DMA + */ + net_dmaengine_put(); + } + + return 0; +} + +static int __dev_close(struct net_device *dev) +{ + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + return __dev_close_many(&single); +} + +int dev_close_many(struct list_head *head) +{ + struct net_device *dev, *tmp; + LIST_HEAD(tmp_list); + + list_for_each_entry_safe(dev, tmp, head, unreg_list) + if (!(dev->flags & IFF_UP)) + list_move(&dev->unreg_list, &tmp_list); - dev->flags &= ~IFF_UP; + __dev_close_many(head); /* - * Shutdown NET_DMA + * Tell people we are down */ - net_dmaengine_put(); + list_for_each_entry(dev, head, unreg_list) { + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_DOWN, dev); + } + /* rollback_registered_many needs the complete original list */ + list_splice(&tmp_list, head); return 0; } @@ -1285,16 +1320,10 @@ static int __dev_close(struct net_device *dev) */ int dev_close(struct net_device *dev) { - if (!(dev->flags & IFF_UP)) - return 0; - - __dev_close(dev); + LIST_HEAD(single); - /* - * Tell people we are down - */ - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); - call_netdevice_notifiers(NETDEV_DOWN, dev); + list_add(&dev->unreg_list, &single); + dev_close_many(&single); return 0; } @@ -1499,6 +1528,14 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) } EXPORT_SYMBOL_GPL(dev_forward_skb); +static inline int deliver_skb(struct sk_buff *skb, + struct packet_type *pt_prev, + struct net_device *orig_dev) +{ + atomic_inc(&skb->users); + return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); +} + /* * Support routine. Sends outgoing frames to any network * taps currently in use. @@ -1507,13 +1544,8 @@ EXPORT_SYMBOL_GPL(dev_forward_skb); static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) { struct packet_type *ptype; - -#ifdef CONFIG_NET_CLS_ACT - if (!(skb->tstamp.tv64 && (G_TC_FROM(skb->tc_verd) & AT_INGRESS))) - net_timestamp_set(skb); -#else - net_timestamp_set(skb); -#endif + struct sk_buff *skb2 = NULL; + struct packet_type *pt_prev = NULL; rcu_read_lock(); list_for_each_entry_rcu(ptype, &ptype_all, list) { @@ -1523,10 +1555,18 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if ((ptype->dev == dev || !ptype->dev) && (ptype->af_packet_priv == NULL || (struct sock *)ptype->af_packet_priv != skb->sk)) { - struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (pt_prev) { + deliver_skb(skb2, pt_prev, skb->dev); + pt_prev = ptype; + continue; + } + + skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) break; + net_timestamp_set(skb2); + /* skb->nh should be correctly set by sender, so that the second statement is just protection against buggy protocols. @@ -1545,9 +1585,11 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) skb2->transport_header = skb2->network_header; skb2->pkt_type = PACKET_OUTGOING; - ptype->func(skb2, skb->dev, ptype, skb->dev); + pt_prev = ptype; } } + if (pt_prev) + pt_prev->func(skb2, skb->dev, pt_prev, skb->dev); rcu_read_unlock(); } @@ -1557,12 +1599,19 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) */ int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { + int rc; + if (txq < 1 || txq > dev->num_tx_queues) return -EINVAL; if (dev->reg_state == NETREG_REGISTERED) { ASSERT_RTNL(); + rc = netdev_queue_update_kobjects(dev, dev->real_num_tx_queues, + txq); + if (rc) + return rc; + if (txq < dev->real_num_tx_queues) qdisc_reset_all_tx_gt(dev, txq); } @@ -1757,7 +1806,7 @@ int skb_checksum_help(struct sk_buff *skb) goto out_set_summed; } - offset = skb->csum_start - skb_headroom(skb); + offset = skb_checksum_start_offset(skb); BUG_ON(offset >= skb_headlen(skb)); csum = skb_checksum(skb, offset, skb->len - offset, 0); @@ -1794,16 +1843,18 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) struct sk_buff *segs = ERR_PTR(-EPROTONOSUPPORT); struct packet_type *ptype; __be16 type = skb->protocol; + int vlan_depth = ETH_HLEN; int err; - if (type == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh; + while (type == htons(ETH_P_8021Q)) { + struct vlan_hdr *vh; - if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) + if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) return ERR_PTR(-EINVAL); - veh = (struct vlan_ethhdr *)skb->data; - type = veh->h_vlan_encapsulated_proto; + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; } skb_reset_mac_header(skb); @@ -1817,8 +1868,7 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) if (dev && dev->ethtool_ops && dev->ethtool_ops->get_drvinfo) dev->ethtool_ops->get_drvinfo(dev, &info); - WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d " - "ip_summed=%d", + WARN(1, "%s: caps=(0x%lx, 0x%lx) len=%d data_len=%d ip_summed=%d\n", info.driver, dev ? dev->features : 0L, skb->sk ? skb->sk->sk_route_caps : 0L, skb->len, skb->data_len, skb->ip_summed); @@ -1967,6 +2017,23 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } +int netif_get_vlan_features(struct sk_buff *skb, struct net_device *dev) +{ + __be16 protocol = skb->protocol; + + if (protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else if (!skb->vlan_tci) + return dev->features; + + if (protocol != htons(ETH_P_8021Q)) + return dev->features & dev->vlan_features; + else + return 0; +} +EXPORT_SYMBOL(netif_get_vlan_features); + /* * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or @@ -1977,15 +2044,20 @@ static inline void skb_orphan_try(struct sk_buff *skb) static inline int skb_needs_linearize(struct sk_buff *skb, struct net_device *dev) { - int features = dev->features; + if (skb_is_nonlinear(skb)) { + int features = dev->features; - if (skb->protocol == htons(ETH_P_8021Q) || vlan_tx_tag_present(skb)) - features &= dev->vlan_features; + if (vlan_tx_tag_present(skb)) + features &= dev->vlan_features; - return skb_is_nonlinear(skb) && - ((skb_has_frag_list(skb) && !(features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && (!(features & NETIF_F_SG) || - illegal_highdma(dev, skb)))); + return (skb_has_frag_list(skb) && + !(features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && + (!(features & NETIF_F_SG) || + illegal_highdma(dev, skb))); + } + + return 0; } int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -1995,9 +2067,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, int rc = NETDEV_TX_OK; if (likely(!skb->next)) { - if (!list_empty(&ptype_all)) - dev_queue_xmit_nit(skb, dev); - /* * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache @@ -2005,6 +2074,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (dev->priv_flags & IFF_XMIT_DST_RELEASE) skb_dst_drop(skb); + if (!list_empty(&ptype_all)) + dev_queue_xmit_nit(skb, dev); + skb_orphan_try(skb); if (vlan_tx_tag_present(skb) && @@ -2031,8 +2103,8 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, * checksumming here. */ if (skb->ip_summed == CHECKSUM_PARTIAL) { - skb_set_transport_header(skb, skb->csum_start - - skb_headroom(skb)); + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); if (!dev_can_checksum(dev, skb) && skb_checksum_help(skb)) goto out_kfree_skb; @@ -2085,14 +2157,19 @@ out: static u32 hashrnd __read_mostly; -u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) +/* + * Returns a Tx hash based on the given packet descriptor a Tx queues' number + * to be used as a distribution range. + */ +u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, + unsigned int num_tx_queues) { u32 hash; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); - while (unlikely(hash >= dev->real_num_tx_queues)) - hash -= dev->real_num_tx_queues; + while (unlikely(hash >= num_tx_queues)) + hash -= num_tx_queues; return hash; } @@ -2102,9 +2179,9 @@ u16 skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb) hash = (__force u16) skb->protocol ^ skb->rxhash; hash = jhash_1word(hash, hashrnd); - return (u16) (((u64) hash * dev->real_num_tx_queues) >> 32); + return (u16) (((u64) hash * num_tx_queues) >> 32); } -EXPORT_SYMBOL(skb_tx_hash); +EXPORT_SYMBOL(__skb_tx_hash); static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) { @@ -2119,26 +2196,70 @@ static inline u16 dev_cap_txqueue(struct net_device *dev, u16 queue_index) return queue_index; } +static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb) +{ +#ifdef CONFIG_XPS + struct xps_dev_maps *dev_maps; + struct xps_map *map; + int queue_index = -1; + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + map = rcu_dereference( + dev_maps->cpu_map[raw_smp_processor_id()]); + if (map) { + if (map->len == 1) + queue_index = map->queues[0]; + else { + u32 hash; + if (skb->sk && skb->sk->sk_hash) + hash = skb->sk->sk_hash; + else + hash = (__force u16) skb->protocol ^ + skb->rxhash; + hash = jhash_1word(hash, hashrnd); + queue_index = map->queues[ + ((u64)hash * map->len) >> 32]; + } + if (unlikely(queue_index >= dev->real_num_tx_queues)) + queue_index = -1; + } + } + rcu_read_unlock(); + + return queue_index; +#else + return -1; +#endif +} + static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { int queue_index; const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_select_queue) { + if (dev->real_num_tx_queues == 1) + queue_index = 0; + else if (ops->ndo_select_queue) { queue_index = ops->ndo_select_queue(dev, skb); queue_index = dev_cap_txqueue(dev, queue_index); } else { struct sock *sk = skb->sk; queue_index = sk_tx_queue_get(sk); - if (queue_index < 0 || queue_index >= dev->real_num_tx_queues) { - queue_index = 0; - if (dev->real_num_tx_queues > 1) + if (queue_index < 0 || skb->ooo_okay || + queue_index >= dev->real_num_tx_queues) { + int old_index = queue_index; + + queue_index = get_xps_queue(dev, skb); + if (queue_index < 0) queue_index = skb_tx_hash(dev, skb); - if (sk) { - struct dst_entry *dst = rcu_dereference_check(sk->sk_dst_cache, 1); + if (queue_index != old_index && sk) { + struct dst_entry *dst = + rcu_dereference_check(sk->sk_dst_cache, 1); if (dst && skb_dst(skb) == dst) sk_tx_queue_set(sk, queue_index); @@ -2712,14 +2833,6 @@ static void net_tx_action(struct softirq_action *h) } } -static inline int deliver_skb(struct sk_buff *skb, - struct packet_type *pt_prev, - struct net_device *orig_dev) -{ - atomic_inc(&skb->users); - return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); -} - #if (defined(CONFIG_BRIDGE) || defined(CONFIG_BRIDGE_MODULE)) && \ (defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE)) /* This hook is defined here for ATM LANE */ @@ -4887,10 +5000,12 @@ static void rollback_registered_many(struct list_head *head) } 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_many(head); + list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ unlist_netdevice(dev); @@ -4967,10 +5082,13 @@ unsigned long netdev_fix_features(unsigned long features, const char *name) } if (features & NETIF_F_UFO) { - if (!(features & NETIF_F_GEN_CSUM)) { + /* maybe split UFO into V4 and V6? */ + if (!((features & NETIF_F_GEN_CSUM) || + (features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) { if (name) printk(KERN_ERR "%s: Dropping NETIF_F_UFO " - "since no NETIF_F_HW_CSUM feature.\n", + "since no checksum offload features.\n", name); features &= ~NETIF_F_UFO; } @@ -5014,9 +5132,9 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); +#ifdef CONFIG_RPS static int netif_alloc_rx_queues(struct net_device *dev) { -#ifdef CONFIG_RPS unsigned int i, count = dev->num_rx_queues; struct netdev_rx_queue *rx; @@ -5029,15 +5147,22 @@ static int netif_alloc_rx_queues(struct net_device *dev) } dev->_rx = rx; - /* - * Set a pointer to first element in the array which holds the - * reference count. - */ for (i = 0; i < count; i++) - rx[i].first = rx; -#endif + rx[i].dev = dev; return 0; } +#endif + +static void netdev_init_one_queue(struct net_device *dev, + struct netdev_queue *queue, void *_unused) +{ + /* Initialize queue lock */ + spin_lock_init(&queue->_xmit_lock); + netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); + queue->xmit_lock_owner = -1; + netdev_queue_numa_node_write(queue, NUMA_NO_NODE); + queue->dev = dev; +} static int netif_alloc_netdev_queues(struct net_device *dev) { @@ -5053,25 +5178,11 @@ static int netif_alloc_netdev_queues(struct net_device *dev) return -ENOMEM; } dev->_tx = tx; - return 0; -} -static void netdev_init_one_queue(struct net_device *dev, - struct netdev_queue *queue, - void *_unused) -{ - queue->dev = dev; - - /* Initialize queue lock */ - spin_lock_init(&queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&queue->_xmit_lock, dev->type); - queue->xmit_lock_owner = -1; -} - -static void netdev_init_queues(struct net_device *dev) -{ netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); spin_lock_init(&dev->tx_global_lock); + + return 0; } /** @@ -5110,16 +5221,6 @@ int register_netdevice(struct net_device *dev) dev->iflink = -1; - ret = netif_alloc_rx_queues(dev); - if (ret) - goto out; - - ret = netif_alloc_netdev_queues(dev); - if (ret) - goto out; - - netdev_init_queues(dev); - /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5577,10 +5678,14 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, dev->num_tx_queues = queue_count; dev->real_num_tx_queues = queue_count; + if (netif_alloc_netdev_queues(dev)) + goto free_pcpu; #ifdef CONFIG_RPS dev->num_rx_queues = queue_count; dev->real_num_rx_queues = queue_count; + if (netif_alloc_rx_queues(dev)) + goto free_pcpu; #endif dev->gso_max_size = GSO_MAX_SIZE; @@ -5597,6 +5702,11 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, free_pcpu: free_percpu(dev->pcpu_refcnt); + kfree(dev->_tx); +#ifdef CONFIG_RPS + kfree(dev->_rx); +#endif + free_p: kfree(p); return NULL; @@ -5618,6 +5728,9 @@ void free_netdev(struct net_device *dev) release_net(dev_net(dev)); kfree(dev->_tx); +#ifdef CONFIG_RPS + kfree(dev->_rx); +#endif kfree(rcu_dereference_raw(dev->ingress_queue)); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 956a9f4971c..17741782a34 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -891,6 +891,20 @@ static int ethtool_nway_reset(struct net_device *dev) return dev->ethtool_ops->nway_reset(dev); } +static int ethtool_get_link(struct net_device *dev, char __user *useraddr) +{ + struct ethtool_value edata = { .cmd = ETHTOOL_GLINK }; + + if (!dev->ethtool_ops->get_link) + return -EOPNOTSUPP; + + edata.data = netif_running(dev) && dev->ethtool_ops->get_link(dev); + + if (copy_to_user(useraddr, &edata, sizeof(edata))) + return -EFAULT; + return 0; +} + static int ethtool_get_eeprom(struct net_device *dev, void __user *useraddr) { struct ethtool_eeprom eeprom; @@ -1171,7 +1185,9 @@ static int ethtool_set_ufo(struct net_device *dev, char __user *useraddr) return -EFAULT; if (edata.data && !(dev->features & NETIF_F_SG)) return -EINVAL; - if (edata.data && !(dev->features & NETIF_F_HW_CSUM)) + if (edata.data && !((dev->features & NETIF_F_GEN_CSUM) || + (dev->features & (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM)) + == (NETIF_F_IP_CSUM|NETIF_F_IPV6_CSUM))) return -EINVAL; return dev->ethtool_ops->set_ufo(dev, edata.data); } @@ -1528,8 +1544,7 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) rc = ethtool_nway_reset(dev); break; case ETHTOOL_GLINK: - rc = ethtool_get_value(dev, useraddr, ethcmd, - dev->ethtool_ops->get_link); + rc = ethtool_get_link(dev, useraddr); break; case ETHTOOL_GEEPROM: rc = ethtool_get_eeprom(dev, useraddr); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 82a4369ae15..a20e5d3bbfa 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -181,8 +181,7 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->iifindex && (rule->iifindex != fl->iif) && - !(fl->flags & FLOWI_FLAG_MATCH_ANY_IIF)) + if (rule->iifindex && (rule->iifindex != fl->iif)) goto out; if (rule->oifindex && (rule->oifindex != fl->oif)) diff --git a/net/core/filter.c b/net/core/filter.c index c1ee800bc08..2b27d4efdd4 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -37,9 +37,69 @@ #include <asm/uaccess.h> #include <asm/unaligned.h> #include <linux/filter.h> +#include <linux/reciprocal_div.h> + +enum { + BPF_S_RET_K = 1, + BPF_S_RET_A, + BPF_S_ALU_ADD_K, + BPF_S_ALU_ADD_X, + BPF_S_ALU_SUB_K, + BPF_S_ALU_SUB_X, + BPF_S_ALU_MUL_K, + BPF_S_ALU_MUL_X, + BPF_S_ALU_DIV_X, + BPF_S_ALU_AND_K, + BPF_S_ALU_AND_X, + BPF_S_ALU_OR_K, + BPF_S_ALU_OR_X, + BPF_S_ALU_LSH_K, + BPF_S_ALU_LSH_X, + BPF_S_ALU_RSH_K, + BPF_S_ALU_RSH_X, + BPF_S_ALU_NEG, + BPF_S_LD_W_ABS, + BPF_S_LD_H_ABS, + BPF_S_LD_B_ABS, + BPF_S_LD_W_LEN, + BPF_S_LD_W_IND, + BPF_S_LD_H_IND, + BPF_S_LD_B_IND, + BPF_S_LD_IMM, + BPF_S_LDX_W_LEN, + BPF_S_LDX_B_MSH, + BPF_S_LDX_IMM, + BPF_S_MISC_TAX, + BPF_S_MISC_TXA, + BPF_S_ALU_DIV_K, + BPF_S_LD_MEM, + BPF_S_LDX_MEM, + BPF_S_ST, + BPF_S_STX, + BPF_S_JMP_JA, + BPF_S_JMP_JEQ_K, + BPF_S_JMP_JEQ_X, + BPF_S_JMP_JGE_K, + BPF_S_JMP_JGE_X, + BPF_S_JMP_JGT_K, + BPF_S_JMP_JGT_X, + BPF_S_JMP_JSET_K, + BPF_S_JMP_JSET_X, + /* Ancillary data */ + BPF_S_ANC_PROTOCOL, + BPF_S_ANC_PKTTYPE, + BPF_S_ANC_IFINDEX, + BPF_S_ANC_NLATTR, + BPF_S_ANC_NLATTR_NEST, + BPF_S_ANC_MARK, + BPF_S_ANC_QUEUE, + BPF_S_ANC_HATYPE, + BPF_S_ANC_RXHASH, + BPF_S_ANC_CPU, +}; /* No hurry in this branch */ -static void *__load_pointer(struct sk_buff *skb, int k) +static void *__load_pointer(const struct sk_buff *skb, int k, unsigned int size) { u8 *ptr = NULL; @@ -48,21 +108,17 @@ static void *__load_pointer(struct sk_buff *skb, int k) else if (k >= SKF_LL_OFF) ptr = skb_mac_header(skb) + k - SKF_LL_OFF; - if (ptr >= skb->head && ptr < skb_tail_pointer(skb)) + if (ptr >= skb->head && ptr + size <= skb_tail_pointer(skb)) return ptr; return NULL; } -static inline void *load_pointer(struct sk_buff *skb, int k, +static inline void *load_pointer(const struct sk_buff *skb, int k, unsigned int size, void *buffer) { if (k >= 0) return skb_header_pointer(skb, k, size, buffer); - else { - if (k >= SKF_AD_OFF) - return NULL; - return __load_pointer(skb, k); - } + return __load_pointer(skb, k, size); } /** @@ -89,7 +145,7 @@ int sk_filter(struct sock *sk, struct sk_buff *skb) rcu_read_lock_bh(); filter = rcu_dereference_bh(sk->sk_filter); if (filter) { - unsigned int pkt_len = sk_run_filter(skb, filter->insns, filter->len); + unsigned int pkt_len = sk_run_filter(skb, filter->insns); err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } @@ -103,50 +159,52 @@ EXPORT_SYMBOL(sk_filter); * sk_run_filter - run a filter on a socket * @skb: buffer to run the filter on * @filter: filter to apply - * @flen: length of filter * * Decode and apply filter instructions to the skb->data. - * Return length to keep, 0 for none. skb is the data we are - * filtering, filter is the array of filter instructions, and - * len is the number of filter blocks in the array. + * Return length to keep, 0 for none. @skb is the data we are + * filtering, @filter is the array of filter instructions. + * Because all jumps are guaranteed to be before last instruction, + * and last instruction guaranteed to be a RET, we dont need to check + * flen. (We used to pass to this function the length of filter) */ -unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int flen) +unsigned int sk_run_filter(const struct sk_buff *skb, + const struct sock_filter *fentry) { void *ptr; u32 A = 0; /* Accumulator */ u32 X = 0; /* Index Register */ u32 mem[BPF_MEMWORDS]; /* Scratch Memory Store */ - unsigned long memvalid = 0; u32 tmp; int k; - int pc; - BUILD_BUG_ON(BPF_MEMWORDS > BITS_PER_LONG); /* * Process array of filter instructions. */ - for (pc = 0; pc < flen; pc++) { - const struct sock_filter *fentry = &filter[pc]; - u32 f_k = fentry->k; + for (;; fentry++) { +#if defined(CONFIG_X86_32) +#define K (fentry->k) +#else + const u32 K = fentry->k; +#endif switch (fentry->code) { case BPF_S_ALU_ADD_X: A += X; continue; case BPF_S_ALU_ADD_K: - A += f_k; + A += K; continue; case BPF_S_ALU_SUB_X: A -= X; continue; case BPF_S_ALU_SUB_K: - A -= f_k; + A -= K; continue; case BPF_S_ALU_MUL_X: A *= X; continue; case BPF_S_ALU_MUL_K: - A *= f_k; + A *= K; continue; case BPF_S_ALU_DIV_X: if (X == 0) @@ -154,89 +212,89 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int A /= X; continue; case BPF_S_ALU_DIV_K: - A /= f_k; + A = reciprocal_divide(A, K); continue; case BPF_S_ALU_AND_X: A &= X; continue; case BPF_S_ALU_AND_K: - A &= f_k; + A &= K; continue; case BPF_S_ALU_OR_X: A |= X; continue; case BPF_S_ALU_OR_K: - A |= f_k; + A |= K; continue; case BPF_S_ALU_LSH_X: A <<= X; continue; case BPF_S_ALU_LSH_K: - A <<= f_k; + A <<= K; continue; case BPF_S_ALU_RSH_X: A >>= X; continue; case BPF_S_ALU_RSH_K: - A >>= f_k; + A >>= K; continue; case BPF_S_ALU_NEG: A = -A; continue; case BPF_S_JMP_JA: - pc += f_k; + fentry += K; continue; case BPF_S_JMP_JGT_K: - pc += (A > f_k) ? fentry->jt : fentry->jf; + fentry += (A > K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGE_K: - pc += (A >= f_k) ? fentry->jt : fentry->jf; + fentry += (A >= K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JEQ_K: - pc += (A == f_k) ? fentry->jt : fentry->jf; + fentry += (A == K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JSET_K: - pc += (A & f_k) ? fentry->jt : fentry->jf; + fentry += (A & K) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGT_X: - pc += (A > X) ? fentry->jt : fentry->jf; + fentry += (A > X) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JGE_X: - pc += (A >= X) ? fentry->jt : fentry->jf; + fentry += (A >= X) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JEQ_X: - pc += (A == X) ? fentry->jt : fentry->jf; + fentry += (A == X) ? fentry->jt : fentry->jf; continue; case BPF_S_JMP_JSET_X: - pc += (A & X) ? fentry->jt : fentry->jf; + fentry += (A & X) ? fentry->jt : fentry->jf; continue; case BPF_S_LD_W_ABS: - k = f_k; + k = K; load_w: ptr = load_pointer(skb, k, 4, &tmp); if (ptr != NULL) { A = get_unaligned_be32(ptr); continue; } - break; + return 0; case BPF_S_LD_H_ABS: - k = f_k; + k = K; load_h: ptr = load_pointer(skb, k, 2, &tmp); if (ptr != NULL) { A = get_unaligned_be16(ptr); continue; } - break; + return 0; case BPF_S_LD_B_ABS: - k = f_k; + k = K; load_b: ptr = load_pointer(skb, k, 1, &tmp); if (ptr != NULL) { A = *(u8 *)ptr; continue; } - break; + return 0; case BPF_S_LD_W_LEN: A = skb->len; continue; @@ -244,34 +302,32 @@ load_b: X = skb->len; continue; case BPF_S_LD_W_IND: - k = X + f_k; + k = X + K; goto load_w; case BPF_S_LD_H_IND: - k = X + f_k; + k = X + K; goto load_h; case BPF_S_LD_B_IND: - k = X + f_k; + k = X + K; goto load_b; case BPF_S_LDX_B_MSH: - ptr = load_pointer(skb, f_k, 1, &tmp); + ptr = load_pointer(skb, K, 1, &tmp); if (ptr != NULL) { X = (*(u8 *)ptr & 0xf) << 2; continue; } return 0; case BPF_S_LD_IMM: - A = f_k; + A = K; continue; case BPF_S_LDX_IMM: - X = f_k; + X = K; continue; case BPF_S_LD_MEM: - A = (memvalid & (1UL << f_k)) ? - mem[f_k] : 0; + A = mem[K]; continue; case BPF_S_LDX_MEM: - X = (memvalid & (1UL << f_k)) ? - mem[f_k] : 0; + X = mem[K]; continue; case BPF_S_MISC_TAX: X = A; @@ -280,50 +336,44 @@ load_b: A = X; continue; case BPF_S_RET_K: - return f_k; + return K; case BPF_S_RET_A: return A; case BPF_S_ST: - memvalid |= 1UL << f_k; - mem[f_k] = A; + mem[K] = A; continue; case BPF_S_STX: - memvalid |= 1UL << f_k; - mem[f_k] = X; + mem[K] = X; continue; - default: - WARN_ON(1); - return 0; - } - - /* - * Handle ancillary data, which are impossible - * (or very difficult) to get parsing packet contents. - */ - switch (k-SKF_AD_OFF) { - case SKF_AD_PROTOCOL: + case BPF_S_ANC_PROTOCOL: A = ntohs(skb->protocol); continue; - case SKF_AD_PKTTYPE: + case BPF_S_ANC_PKTTYPE: A = skb->pkt_type; continue; - case SKF_AD_IFINDEX: + case BPF_S_ANC_IFINDEX: if (!skb->dev) return 0; A = skb->dev->ifindex; continue; - case SKF_AD_MARK: + case BPF_S_ANC_MARK: A = skb->mark; continue; - case SKF_AD_QUEUE: + case BPF_S_ANC_QUEUE: A = skb->queue_mapping; continue; - case SKF_AD_HATYPE: + case BPF_S_ANC_HATYPE: if (!skb->dev) return 0; A = skb->dev->type; continue; - case SKF_AD_NLATTR: { + case BPF_S_ANC_RXHASH: + A = skb->rxhash; + continue; + case BPF_S_ANC_CPU: + A = raw_smp_processor_id(); + continue; + case BPF_S_ANC_NLATTR: { struct nlattr *nla; if (skb_is_nonlinear(skb)) @@ -339,7 +389,7 @@ load_b: A = 0; continue; } - case SKF_AD_NLATTR_NEST: { + case BPF_S_ANC_NLATTR_NEST: { struct nlattr *nla; if (skb_is_nonlinear(skb)) @@ -359,6 +409,7 @@ load_b: continue; } default: + WARN_ON(1); return 0; } } @@ -367,6 +418,66 @@ load_b: } EXPORT_SYMBOL(sk_run_filter); +/* + * Security : + * A BPF program is able to use 16 cells of memory to store intermediate + * values (check u32 mem[BPF_MEMWORDS] in sk_run_filter()) + * As we dont want to clear mem[] array for each packet going through + * sk_run_filter(), we check that filter loaded by user never try to read + * a cell if not previously written, and we check all branches to be sure + * a malicious user doesnt try to abuse us. + */ +static int check_load_and_stores(struct sock_filter *filter, int flen) +{ + u16 *masks, memvalid = 0; /* one bit per cell, 16 cells */ + int pc, ret = 0; + + BUILD_BUG_ON(BPF_MEMWORDS > 16); + masks = kmalloc(flen * sizeof(*masks), GFP_KERNEL); + if (!masks) + return -ENOMEM; + memset(masks, 0xff, flen * sizeof(*masks)); + + for (pc = 0; pc < flen; pc++) { + memvalid &= masks[pc]; + + switch (filter[pc].code) { + case BPF_S_ST: + case BPF_S_STX: + memvalid |= (1 << filter[pc].k); + break; + case BPF_S_LD_MEM: + case BPF_S_LDX_MEM: + if (!(memvalid & (1 << filter[pc].k))) { + ret = -EINVAL; + goto error; + } + break; + case BPF_S_JMP_JA: + /* a jump must set masks on target */ + masks[pc + 1 + filter[pc].k] &= memvalid; + memvalid = ~0; + break; + case BPF_S_JMP_JEQ_K: + case BPF_S_JMP_JEQ_X: + case BPF_S_JMP_JGE_K: + case BPF_S_JMP_JGE_X: + case BPF_S_JMP_JGT_K: + case BPF_S_JMP_JGT_X: + case BPF_S_JMP_JSET_X: + case BPF_S_JMP_JSET_K: + /* a jump must set masks on targets */ + masks[pc + 1 + filter[pc].jt] &= memvalid; + masks[pc + 1 + filter[pc].jf] &= memvalid; + memvalid = ~0; + break; + } + } +error: + kfree(masks); + return ret; +} + /** * sk_chk_filter - verify socket filter code * @filter: filter to verify @@ -383,7 +494,57 @@ EXPORT_SYMBOL(sk_run_filter); */ int sk_chk_filter(struct sock_filter *filter, int flen) { - struct sock_filter *ftest; + /* + * Valid instructions are initialized to non-0. + * Invalid instructions are initialized to 0. + */ + static const u8 codes[] = { + [BPF_ALU|BPF_ADD|BPF_K] = BPF_S_ALU_ADD_K, + [BPF_ALU|BPF_ADD|BPF_X] = BPF_S_ALU_ADD_X, + [BPF_ALU|BPF_SUB|BPF_K] = BPF_S_ALU_SUB_K, + [BPF_ALU|BPF_SUB|BPF_X] = BPF_S_ALU_SUB_X, + [BPF_ALU|BPF_MUL|BPF_K] = BPF_S_ALU_MUL_K, + [BPF_ALU|BPF_MUL|BPF_X] = BPF_S_ALU_MUL_X, + [BPF_ALU|BPF_DIV|BPF_X] = BPF_S_ALU_DIV_X, + [BPF_ALU|BPF_AND|BPF_K] = BPF_S_ALU_AND_K, + [BPF_ALU|BPF_AND|BPF_X] = BPF_S_ALU_AND_X, + [BPF_ALU|BPF_OR|BPF_K] = BPF_S_ALU_OR_K, + [BPF_ALU|BPF_OR|BPF_X] = BPF_S_ALU_OR_X, + [BPF_ALU|BPF_LSH|BPF_K] = BPF_S_ALU_LSH_K, + [BPF_ALU|BPF_LSH|BPF_X] = BPF_S_ALU_LSH_X, + [BPF_ALU|BPF_RSH|BPF_K] = BPF_S_ALU_RSH_K, + [BPF_ALU|BPF_RSH|BPF_X] = BPF_S_ALU_RSH_X, + [BPF_ALU|BPF_NEG] = BPF_S_ALU_NEG, + [BPF_LD|BPF_W|BPF_ABS] = BPF_S_LD_W_ABS, + [BPF_LD|BPF_H|BPF_ABS] = BPF_S_LD_H_ABS, + [BPF_LD|BPF_B|BPF_ABS] = BPF_S_LD_B_ABS, + [BPF_LD|BPF_W|BPF_LEN] = BPF_S_LD_W_LEN, + [BPF_LD|BPF_W|BPF_IND] = BPF_S_LD_W_IND, + [BPF_LD|BPF_H|BPF_IND] = BPF_S_LD_H_IND, + [BPF_LD|BPF_B|BPF_IND] = BPF_S_LD_B_IND, + [BPF_LD|BPF_IMM] = BPF_S_LD_IMM, + [BPF_LDX|BPF_W|BPF_LEN] = BPF_S_LDX_W_LEN, + [BPF_LDX|BPF_B|BPF_MSH] = BPF_S_LDX_B_MSH, + [BPF_LDX|BPF_IMM] = BPF_S_LDX_IMM, + [BPF_MISC|BPF_TAX] = BPF_S_MISC_TAX, + [BPF_MISC|BPF_TXA] = BPF_S_MISC_TXA, + [BPF_RET|BPF_K] = BPF_S_RET_K, + [BPF_RET|BPF_A] = BPF_S_RET_A, + [BPF_ALU|BPF_DIV|BPF_K] = BPF_S_ALU_DIV_K, + [BPF_LD|BPF_MEM] = BPF_S_LD_MEM, + [BPF_LDX|BPF_MEM] = BPF_S_LDX_MEM, + [BPF_ST] = BPF_S_ST, + [BPF_STX] = BPF_S_STX, + [BPF_JMP|BPF_JA] = BPF_S_JMP_JA, + [BPF_JMP|BPF_JEQ|BPF_K] = BPF_S_JMP_JEQ_K, + [BPF_JMP|BPF_JEQ|BPF_X] = BPF_S_JMP_JEQ_X, + [BPF_JMP|BPF_JGE|BPF_K] = BPF_S_JMP_JGE_K, + [BPF_JMP|BPF_JGE|BPF_X] = BPF_S_JMP_JGE_X, + [BPF_JMP|BPF_JGT|BPF_K] = BPF_S_JMP_JGT_K, + [BPF_JMP|BPF_JGT|BPF_X] = BPF_S_JMP_JGT_X, + [BPF_JMP|BPF_JSET|BPF_K] = BPF_S_JMP_JSET_K, + [BPF_JMP|BPF_JSET|BPF_X] = BPF_S_JMP_JSET_X, + }; int pc; if (flen == 0 || flen > BPF_MAXINSNS) @@ -391,136 +552,31 @@ int sk_chk_filter(struct sock_filter *filter, int flen) /* check the filter code now */ for (pc = 0; pc < flen; pc++) { - ftest = &filter[pc]; - - /* Only allow valid instructions */ - switch (ftest->code) { - case BPF_ALU|BPF_ADD|BPF_K: - ftest->code = BPF_S_ALU_ADD_K; - break; - case BPF_ALU|BPF_ADD|BPF_X: - ftest->code = BPF_S_ALU_ADD_X; - break; - case BPF_ALU|BPF_SUB|BPF_K: - ftest->code = BPF_S_ALU_SUB_K; - break; - case BPF_ALU|BPF_SUB|BPF_X: - ftest->code = BPF_S_ALU_SUB_X; - break; - case BPF_ALU|BPF_MUL|BPF_K: - ftest->code = BPF_S_ALU_MUL_K; - break; - case BPF_ALU|BPF_MUL|BPF_X: - ftest->code = BPF_S_ALU_MUL_X; - break; - case BPF_ALU|BPF_DIV|BPF_X: - ftest->code = BPF_S_ALU_DIV_X; - break; - case BPF_ALU|BPF_AND|BPF_K: - ftest->code = BPF_S_ALU_AND_K; - break; - case BPF_ALU|BPF_AND|BPF_X: - ftest->code = BPF_S_ALU_AND_X; - break; - case BPF_ALU|BPF_OR|BPF_K: - ftest->code = BPF_S_ALU_OR_K; - break; - case BPF_ALU|BPF_OR|BPF_X: - ftest->code = BPF_S_ALU_OR_X; - break; - case BPF_ALU|BPF_LSH|BPF_K: - ftest->code = BPF_S_ALU_LSH_K; - break; - case BPF_ALU|BPF_LSH|BPF_X: - ftest->code = BPF_S_ALU_LSH_X; - break; - case BPF_ALU|BPF_RSH|BPF_K: - ftest->code = BPF_S_ALU_RSH_K; - break; - case BPF_ALU|BPF_RSH|BPF_X: - ftest->code = BPF_S_ALU_RSH_X; - break; - case BPF_ALU|BPF_NEG: - ftest->code = BPF_S_ALU_NEG; - break; - case BPF_LD|BPF_W|BPF_ABS: - ftest->code = BPF_S_LD_W_ABS; - break; - case BPF_LD|BPF_H|BPF_ABS: - ftest->code = BPF_S_LD_H_ABS; - break; - case BPF_LD|BPF_B|BPF_ABS: - ftest->code = BPF_S_LD_B_ABS; - break; - case BPF_LD|BPF_W|BPF_LEN: - ftest->code = BPF_S_LD_W_LEN; - break; - case BPF_LD|BPF_W|BPF_IND: - ftest->code = BPF_S_LD_W_IND; - break; - case BPF_LD|BPF_H|BPF_IND: - ftest->code = BPF_S_LD_H_IND; - break; - case BPF_LD|BPF_B|BPF_IND: - ftest->code = BPF_S_LD_B_IND; - break; - case BPF_LD|BPF_IMM: - ftest->code = BPF_S_LD_IMM; - break; - case BPF_LDX|BPF_W|BPF_LEN: - ftest->code = BPF_S_LDX_W_LEN; - break; - case BPF_LDX|BPF_B|BPF_MSH: - ftest->code = BPF_S_LDX_B_MSH; - break; - case BPF_LDX|BPF_IMM: - ftest->code = BPF_S_LDX_IMM; - break; - case BPF_MISC|BPF_TAX: - ftest->code = BPF_S_MISC_TAX; - break; - case BPF_MISC|BPF_TXA: - ftest->code = BPF_S_MISC_TXA; - break; - case BPF_RET|BPF_K: - ftest->code = BPF_S_RET_K; - break; - case BPF_RET|BPF_A: - ftest->code = BPF_S_RET_A; - break; + struct sock_filter *ftest = &filter[pc]; + u16 code = ftest->code; + if (code >= ARRAY_SIZE(codes)) + return -EINVAL; + code = codes[code]; + if (!code) + return -EINVAL; /* Some instructions need special checks */ - + switch (code) { + case BPF_S_ALU_DIV_K: /* check for division by zero */ - case BPF_ALU|BPF_DIV|BPF_K: if (ftest->k == 0) return -EINVAL; - ftest->code = BPF_S_ALU_DIV_K; - break; - - /* check for invalid memory addresses */ - case BPF_LD|BPF_MEM: - if (ftest->k >= BPF_MEMWORDS) - return -EINVAL; - ftest->code = BPF_S_LD_MEM; + ftest->k = reciprocal_value(ftest->k); break; - case BPF_LDX|BPF_MEM: - if (ftest->k >= BPF_MEMWORDS) - return -EINVAL; - ftest->code = BPF_S_LDX_MEM; - break; - case BPF_ST: - if (ftest->k >= BPF_MEMWORDS) - return -EINVAL; - ftest->code = BPF_S_ST; - break; - case BPF_STX: + case BPF_S_LD_MEM: + case BPF_S_LDX_MEM: + case BPF_S_ST: + case BPF_S_STX: + /* check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; - ftest->code = BPF_S_STX; break; - - case BPF_JMP|BPF_JA: + case BPF_S_JMP_JA: /* * Note, the large ftest->k might cause loops. * Compare this with conditional jumps below, @@ -528,40 +584,7 @@ int sk_chk_filter(struct sock_filter *filter, int flen) */ if (ftest->k >= (unsigned)(flen-pc-1)) return -EINVAL; - ftest->code = BPF_S_JMP_JA; - break; - - case BPF_JMP|BPF_JEQ|BPF_K: - ftest->code = BPF_S_JMP_JEQ_K; - break; - case BPF_JMP|BPF_JEQ|BPF_X: - ftest->code = BPF_S_JMP_JEQ_X; - break; - case BPF_JMP|BPF_JGE|BPF_K: - ftest->code = BPF_S_JMP_JGE_K; - break; - case BPF_JMP|BPF_JGE|BPF_X: - ftest->code = BPF_S_JMP_JGE_X; break; - case BPF_JMP|BPF_JGT|BPF_K: - ftest->code = BPF_S_JMP_JGT_K; - break; - case BPF_JMP|BPF_JGT|BPF_X: - ftest->code = BPF_S_JMP_JGT_X; - break; - case BPF_JMP|BPF_JSET|BPF_K: - ftest->code = BPF_S_JMP_JSET_K; - break; - case BPF_JMP|BPF_JSET|BPF_X: - ftest->code = BPF_S_JMP_JSET_X; - break; - - default: - return -EINVAL; - } - - /* for conditionals both must be safe */ - switch (ftest->code) { case BPF_S_JMP_JEQ_K: case BPF_S_JMP_JEQ_X: case BPF_S_JMP_JGE_K: @@ -570,42 +593,54 @@ int sk_chk_filter(struct sock_filter *filter, int flen) case BPF_S_JMP_JGT_X: case BPF_S_JMP_JSET_X: case BPF_S_JMP_JSET_K: + /* for conditionals both must be safe */ if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; + break; + case BPF_S_LD_W_ABS: + case BPF_S_LD_H_ABS: + case BPF_S_LD_B_ABS: +#define ANCILLARY(CODE) case SKF_AD_OFF + SKF_AD_##CODE: \ + code = BPF_S_ANC_##CODE; \ + break + switch (ftest->k) { + ANCILLARY(PROTOCOL); + ANCILLARY(PKTTYPE); + ANCILLARY(IFINDEX); + ANCILLARY(NLATTR); + ANCILLARY(NLATTR_NEST); + ANCILLARY(MARK); + ANCILLARY(QUEUE); + ANCILLARY(HATYPE); + ANCILLARY(RXHASH); + ANCILLARY(CPU); + } } + ftest->code = code; } /* last instruction must be a RET code */ switch (filter[flen - 1].code) { case BPF_S_RET_K: case BPF_S_RET_A: - return 0; - break; - default: - return -EINVAL; - } + return check_load_and_stores(filter, flen); + } + return -EINVAL; } EXPORT_SYMBOL(sk_chk_filter); /** - * sk_filter_rcu_release - Release a socket filter by rcu_head + * sk_filter_release_rcu - Release a socket filter by rcu_head * @rcu: rcu_head that contains the sk_filter to free */ -static void sk_filter_rcu_release(struct rcu_head *rcu) +void sk_filter_release_rcu(struct rcu_head *rcu) { struct sk_filter *fp = container_of(rcu, struct sk_filter, rcu); - sk_filter_release(fp); -} - -static void sk_filter_delayed_uncharge(struct sock *sk, struct sk_filter *fp) -{ - unsigned int size = sk_filter_len(fp); - - atomic_sub(size, &sk->sk_omem_alloc); - call_rcu_bh(&fp->rcu, sk_filter_rcu_release); + kfree(fp); } +EXPORT_SYMBOL(sk_filter_release_rcu); /** * sk_attach_filter - attach a socket filter @@ -649,7 +684,7 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) rcu_assign_pointer(sk->sk_filter, fp); if (old_fp) - sk_filter_delayed_uncharge(sk, old_fp); + sk_filter_uncharge(sk, old_fp); return 0; } EXPORT_SYMBOL_GPL(sk_attach_filter); @@ -663,7 +698,7 @@ int sk_detach_filter(struct sock *sk) sock_owned_by_user(sk)); if (filter) { rcu_assign_pointer(sk->sk_filter, NULL); - sk_filter_delayed_uncharge(sk, filter); + sk_filter_uncharge(sk, filter); ret = 0; } return ret; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 8cc8f9a79db..60a90291342 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -41,7 +41,6 @@ #define NEIGH_PRINTK(x...) printk(x) #define NEIGH_NOPRINTK(x...) do { ; } while(0) -#define NEIGH_PRINTK0 NEIGH_PRINTK #define NEIGH_PRINTK1 NEIGH_NOPRINTK #define NEIGH_PRINTK2 NEIGH_NOPRINTK diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 7f902cad10f..e23c01be5a5 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -706,7 +706,6 @@ static struct attribute *rx_queue_default_attrs[] = { static void rx_queue_release(struct kobject *kobj) { struct netdev_rx_queue *queue = to_rx_queue(kobj); - struct netdev_rx_queue *first = queue->first; struct rps_map *map; struct rps_dev_flow_table *flow_table; @@ -723,10 +722,8 @@ static void rx_queue_release(struct kobject *kobj) call_rcu(&flow_table->rcu, rps_dev_flow_table_release); } - if (atomic_dec_and_test(&first->count)) - kfree(first); - else - memset(kobj, 0, sizeof(*kobj)); + memset(kobj, 0, sizeof(*kobj)); + dev_put(queue->dev); } static struct kobj_type rx_queue_ktype = { @@ -738,7 +735,6 @@ static struct kobj_type rx_queue_ktype = { static int rx_queue_add_kobject(struct net_device *net, int index) { struct netdev_rx_queue *queue = net->_rx + index; - struct netdev_rx_queue *first = queue->first; struct kobject *kobj = &queue->kobj; int error = 0; @@ -751,14 +747,16 @@ static int rx_queue_add_kobject(struct net_device *net, int index) } kobject_uevent(kobj, KOBJ_ADD); - atomic_inc(&first->count); + dev_hold(queue->dev); return error; } +#endif /* CONFIG_RPS */ int net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { +#ifdef CONFIG_RPS int i; int error = 0; @@ -774,23 +772,423 @@ net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) kobject_put(&net->_rx[i].kobj); return error; +#else + return 0; +#endif +} + +#ifdef CONFIG_XPS +/* + * netdev_queue sysfs structures and functions. + */ +struct netdev_queue_attribute { + struct attribute attr; + ssize_t (*show)(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, char *buf); + ssize_t (*store)(struct netdev_queue *queue, + struct netdev_queue_attribute *attr, const char *buf, size_t len); +}; +#define to_netdev_queue_attr(_attr) container_of(_attr, \ + struct netdev_queue_attribute, attr) + +#define to_netdev_queue(obj) container_of(obj, struct netdev_queue, kobj) + +static ssize_t netdev_queue_attr_show(struct kobject *kobj, + struct attribute *attr, char *buf) +{ + struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + struct netdev_queue *queue = to_netdev_queue(kobj); + + if (!attribute->show) + return -EIO; + + return attribute->show(queue, attribute, buf); } -static int rx_queue_register_kobjects(struct net_device *net) +static ssize_t netdev_queue_attr_store(struct kobject *kobj, + struct attribute *attr, + const char *buf, size_t count) { + struct netdev_queue_attribute *attribute = to_netdev_queue_attr(attr); + struct netdev_queue *queue = to_netdev_queue(kobj); + + if (!attribute->store) + return -EIO; + + return attribute->store(queue, attribute, buf, count); +} + +static const struct sysfs_ops netdev_queue_sysfs_ops = { + .show = netdev_queue_attr_show, + .store = netdev_queue_attr_store, +}; + +static inline unsigned int get_netdev_queue_index(struct netdev_queue *queue) +{ + struct net_device *dev = queue->dev; + int i; + + for (i = 0; i < dev->num_tx_queues; i++) + if (queue == &dev->_tx[i]) + break; + + BUG_ON(i >= dev->num_tx_queues); + + return i; +} + + +static ssize_t show_xps_map(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, char *buf) +{ + struct net_device *dev = queue->dev; + struct xps_dev_maps *dev_maps; + cpumask_var_t mask; + unsigned long index; + size_t len = 0; + int i; + + if (!zalloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + rcu_read_lock(); + dev_maps = rcu_dereference(dev->xps_maps); + if (dev_maps) { + for_each_possible_cpu(i) { + struct xps_map *map = + rcu_dereference(dev_maps->cpu_map[i]); + if (map) { + int j; + for (j = 0; j < map->len; j++) { + if (map->queues[j] == index) { + cpumask_set_cpu(i, mask); + break; + } + } + } + } + } + rcu_read_unlock(); + + len += cpumask_scnprintf(buf + len, PAGE_SIZE, mask); + if (PAGE_SIZE - len < 3) { + free_cpumask_var(mask); + return -EINVAL; + } + + free_cpumask_var(mask); + len += sprintf(buf + len, "\n"); + return len; +} + +static void xps_map_release(struct rcu_head *rcu) +{ + struct xps_map *map = container_of(rcu, struct xps_map, rcu); + + kfree(map); +} + +static void xps_dev_maps_release(struct rcu_head *rcu) +{ + struct xps_dev_maps *dev_maps = + container_of(rcu, struct xps_dev_maps, rcu); + + kfree(dev_maps); +} + +static DEFINE_MUTEX(xps_map_mutex); +#define xmap_dereference(P) \ + rcu_dereference_protected((P), lockdep_is_held(&xps_map_mutex)) + +static ssize_t store_xps_map(struct netdev_queue *queue, + struct netdev_queue_attribute *attribute, + const char *buf, size_t len) +{ + struct net_device *dev = queue->dev; + cpumask_var_t mask; + int err, i, cpu, pos, map_len, alloc_len, need_set; + unsigned long index; + struct xps_map *map, *new_map; + struct xps_dev_maps *dev_maps, *new_dev_maps; + int nonempty = 0; + int numa_node = -2; + + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + + if (!alloc_cpumask_var(&mask, GFP_KERNEL)) + return -ENOMEM; + + index = get_netdev_queue_index(queue); + + err = bitmap_parse(buf, len, cpumask_bits(mask), nr_cpumask_bits); + if (err) { + free_cpumask_var(mask); + return err; + } + + new_dev_maps = kzalloc(max_t(unsigned, + XPS_DEV_MAPS_SIZE, L1_CACHE_BYTES), GFP_KERNEL); + if (!new_dev_maps) { + free_cpumask_var(mask); + return -ENOMEM; + } + + mutex_lock(&xps_map_mutex); + + dev_maps = xmap_dereference(dev->xps_maps); + + for_each_possible_cpu(cpu) { + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; + new_map = map; + if (map) { + for (pos = 0; pos < map->len; pos++) + if (map->queues[pos] == index) + break; + map_len = map->len; + alloc_len = map->alloc_len; + } else + pos = map_len = alloc_len = 0; + + need_set = cpu_isset(cpu, *mask) && cpu_online(cpu); +#ifdef CONFIG_NUMA + if (need_set) { + if (numa_node == -2) + numa_node = cpu_to_node(cpu); + else if (numa_node != cpu_to_node(cpu)) + numa_node = -1; + } +#endif + if (need_set && pos >= map_len) { + /* Need to add queue to this CPU's map */ + if (map_len >= alloc_len) { + alloc_len = alloc_len ? + 2 * alloc_len : XPS_MIN_MAP_ALLOC; + new_map = kzalloc_node(XPS_MAP_SIZE(alloc_len), + GFP_KERNEL, + cpu_to_node(cpu)); + if (!new_map) + goto error; + new_map->alloc_len = alloc_len; + for (i = 0; i < map_len; i++) + new_map->queues[i] = map->queues[i]; + new_map->len = map_len; + } + new_map->queues[new_map->len++] = index; + } else if (!need_set && pos < map_len) { + /* Need to remove queue from this CPU's map */ + if (map_len > 1) + new_map->queues[pos] = + new_map->queues[--new_map->len]; + else + new_map = NULL; + } + RCU_INIT_POINTER(new_dev_maps->cpu_map[cpu], new_map); + } + + /* Cleanup old maps */ + for_each_possible_cpu(cpu) { + map = dev_maps ? + xmap_dereference(dev_maps->cpu_map[cpu]) : NULL; + if (map && xmap_dereference(new_dev_maps->cpu_map[cpu]) != map) + call_rcu(&map->rcu, xps_map_release); + if (new_dev_maps->cpu_map[cpu]) + nonempty = 1; + } + + if (nonempty) + rcu_assign_pointer(dev->xps_maps, new_dev_maps); + else { + kfree(new_dev_maps); + rcu_assign_pointer(dev->xps_maps, NULL); + } + + if (dev_maps) + call_rcu(&dev_maps->rcu, xps_dev_maps_release); + + netdev_queue_numa_node_write(queue, (numa_node >= 0) ? numa_node : + NUMA_NO_NODE); + + mutex_unlock(&xps_map_mutex); + + free_cpumask_var(mask); + return len; + +error: + mutex_unlock(&xps_map_mutex); + + if (new_dev_maps) + for_each_possible_cpu(i) + kfree(rcu_dereference_protected( + new_dev_maps->cpu_map[i], + 1)); + kfree(new_dev_maps); + free_cpumask_var(mask); + return -ENOMEM; +} + +static struct netdev_queue_attribute xps_cpus_attribute = + __ATTR(xps_cpus, S_IRUGO | S_IWUSR, show_xps_map, store_xps_map); + +static struct attribute *netdev_queue_default_attrs[] = { + &xps_cpus_attribute.attr, + NULL +}; + +static void netdev_queue_release(struct kobject *kobj) +{ + struct netdev_queue *queue = to_netdev_queue(kobj); + struct net_device *dev = queue->dev; + struct xps_dev_maps *dev_maps; + struct xps_map *map; + unsigned long index; + int i, pos, nonempty = 0; + + index = get_netdev_queue_index(queue); + + mutex_lock(&xps_map_mutex); + dev_maps = xmap_dereference(dev->xps_maps); + + if (dev_maps) { + for_each_possible_cpu(i) { + map = xmap_dereference(dev_maps->cpu_map[i]); + if (!map) + continue; + + for (pos = 0; pos < map->len; pos++) + if (map->queues[pos] == index) + break; + + if (pos < map->len) { + if (map->len > 1) + map->queues[pos] = + map->queues[--map->len]; + else { + RCU_INIT_POINTER(dev_maps->cpu_map[i], + NULL); + call_rcu(&map->rcu, xps_map_release); + map = NULL; + } + } + if (map) + nonempty = 1; + } + + if (!nonempty) { + RCU_INIT_POINTER(dev->xps_maps, NULL); + call_rcu(&dev_maps->rcu, xps_dev_maps_release); + } + } + + mutex_unlock(&xps_map_mutex); + + memset(kobj, 0, sizeof(*kobj)); + dev_put(queue->dev); +} + +static struct kobj_type netdev_queue_ktype = { + .sysfs_ops = &netdev_queue_sysfs_ops, + .release = netdev_queue_release, + .default_attrs = netdev_queue_default_attrs, +}; + +static int netdev_queue_add_kobject(struct net_device *net, int index) +{ + struct netdev_queue *queue = net->_tx + index; + struct kobject *kobj = &queue->kobj; + int error = 0; + + kobj->kset = net->queues_kset; + error = kobject_init_and_add(kobj, &netdev_queue_ktype, NULL, + "tx-%u", index); + if (error) { + kobject_put(kobj); + return error; + } + + kobject_uevent(kobj, KOBJ_ADD); + dev_hold(queue->dev); + + return error; +} +#endif /* CONFIG_XPS */ + +int +netdev_queue_update_kobjects(struct net_device *net, int old_num, int new_num) +{ +#ifdef CONFIG_XPS + int i; + int error = 0; + + for (i = old_num; i < new_num; i++) { + error = netdev_queue_add_kobject(net, i); + if (error) { + new_num = old_num; + break; + } + } + + while (--i >= new_num) + kobject_put(&net->_tx[i].kobj); + + return error; +#else + return 0; +#endif +} + +static int register_queue_kobjects(struct net_device *net) +{ + int error = 0, txq = 0, rxq = 0, real_rx = 0, real_tx = 0; + +#if defined(CONFIG_RPS) || defined(CONFIG_XPS) net->queues_kset = kset_create_and_add("queues", NULL, &net->dev.kobj); if (!net->queues_kset) return -ENOMEM; - return net_rx_queue_update_kobjects(net, 0, net->real_num_rx_queues); +#endif + +#ifdef CONFIG_RPS + real_rx = net->real_num_rx_queues; +#endif + real_tx = net->real_num_tx_queues; + + error = net_rx_queue_update_kobjects(net, 0, real_rx); + if (error) + goto error; + rxq = real_rx; + + error = netdev_queue_update_kobjects(net, 0, real_tx); + if (error) + goto error; + txq = real_tx; + + return 0; + +error: + netdev_queue_update_kobjects(net, txq, 0); + net_rx_queue_update_kobjects(net, rxq, 0); + return error; } -static void rx_queue_remove_kobjects(struct net_device *net) +static void remove_queue_kobjects(struct net_device *net) { - net_rx_queue_update_kobjects(net, net->real_num_rx_queues, 0); + int real_rx = 0, real_tx = 0; + +#ifdef CONFIG_RPS + real_rx = net->real_num_rx_queues; +#endif + real_tx = net->real_num_tx_queues; + + net_rx_queue_update_kobjects(net, real_rx, 0); + netdev_queue_update_kobjects(net, real_tx, 0); +#if defined(CONFIG_RPS) || defined(CONFIG_XPS) kset_unregister(net->queues_kset); +#endif } -#endif /* CONFIG_RPS */ static const void *net_current_ns(void) { @@ -889,9 +1287,7 @@ void netdev_unregister_kobject(struct net_device * net) kobject_get(&dev->kobj); -#ifdef CONFIG_RPS - rx_queue_remove_kobjects(net); -#endif + remove_queue_kobjects(net); device_del(dev); } @@ -930,13 +1326,11 @@ int netdev_register_kobject(struct net_device *net) if (error) return error; -#ifdef CONFIG_RPS - error = rx_queue_register_kobjects(net); + error = register_queue_kobjects(net); if (error) { device_del(dev); return error; } -#endif return error; } diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 778e1571548..bd7751ec1c4 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -4,8 +4,8 @@ int netdev_kobject_init(void); int netdev_register_kobject(struct net_device *); void netdev_unregister_kobject(struct net_device *); -#ifdef CONFIG_RPS int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num); -#endif +int netdev_queue_update_kobjects(struct net_device *net, + int old_num, int new_num); #endif diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 4e98ffac3af..02dc2cbcbe8 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -35,7 +35,6 @@ #define MAX_UDP_CHUNK 1460 #define MAX_SKBS 32 -#define MAX_QUEUE_DEPTH (MAX_SKBS / 2) static struct sk_buff_head skb_pool; @@ -76,8 +75,7 @@ static void queue_process(struct work_struct *work) local_irq_save(flags); __netif_tx_lock(txq, smp_processor_id()); - if (netif_tx_queue_stopped(txq) || - netif_tx_queue_frozen(txq) || + if (netif_tx_queue_frozen_or_stopped(txq) || ops->ndo_start_xmit(skb, dev) != NETDEV_TX_OK) { skb_queue_head(&npinfo->txq, skb); __netif_tx_unlock(txq); @@ -925,7 +923,7 @@ void __netpoll_cleanup(struct netpoll *np) skb_queue_purge(&npinfo->arp_tx); skb_queue_purge(&npinfo->txq); - cancel_rearming_delayed_work(&npinfo->tx_work); + cancel_delayed_work_sync(&npinfo->tx_work); /* clean after last, unfinished work */ __skb_queue_purge(&npinfo->txq); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 33bc3823ac6..a9e7fc4c461 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -378,6 +378,7 @@ struct pktgen_dev { u16 queue_map_min; u16 queue_map_max; + __u32 skb_priority; /* skb priority field */ int node; /* Memory node */ #ifdef CONFIG_XFRM @@ -394,6 +395,8 @@ struct pktgen_hdr { __be32 tv_usec; }; +static bool pktgen_exiting __read_mostly; + struct pktgen_thread { spinlock_t if_lock; /* for list of devices */ struct list_head if_list; /* All device here */ @@ -547,6 +550,10 @@ static int pktgen_if_show(struct seq_file *seq, void *v) pkt_dev->queue_map_min, pkt_dev->queue_map_max); + if (pkt_dev->skb_priority) + seq_printf(seq, " skb_priority: %u\n", + pkt_dev->skb_priority); + if (pkt_dev->flags & F_IPV6) { char b1[128], b2[128], b3[128]; fmt_ip6(b1, pkt_dev->in6_saddr.s6_addr); @@ -1711,6 +1718,18 @@ static ssize_t pktgen_if_write(struct file *file, return count; } + if (!strcmp(name, "skb_priority")) { + len = num_arg(&user_buffer[i], 9, &value); + if (len < 0) + return len; + + i += len; + pkt_dev->skb_priority = value; + sprintf(pg_result, "OK: skb_priority=%i", + pkt_dev->skb_priority); + return count; + } + sprintf(pkt_dev->result, "No such parameter \"%s\"", name); return -EINVAL; } @@ -2641,6 +2660,7 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, datalen); @@ -2671,6 +2691,8 @@ static struct sk_buff *fill_packet_ipv4(struct net_device *odev, skb->transport_header = skb->network_header + sizeof(struct iphdr); skb_put(skb, sizeof(struct iphdr) + sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); + skb->priority = pkt_dev->skb_priority; + iph = ip_hdr(skb); udph = udp_hdr(skb); @@ -2986,6 +3008,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, sprintf(pkt_dev->result, "No memory"); return NULL; } + prefetchw(skb->data); skb_reserve(skb, 16); @@ -3016,6 +3039,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, skb->transport_header = skb->network_header + sizeof(struct ipv6hdr); skb_put(skb, sizeof(struct ipv6hdr) + sizeof(struct udphdr)); skb_set_queue_mapping(skb, queue_map); + skb->priority = pkt_dev->skb_priority; iph = ipv6_hdr(skb); udph = udp_hdr(skb); @@ -3431,11 +3455,6 @@ static void pktgen_rem_thread(struct pktgen_thread *t) remove_proc_entry(t->tsk->comm, pg_proc_dir); - mutex_lock(&pktgen_thread_lock); - - list_del(&t->th_list); - - mutex_unlock(&pktgen_thread_lock); } static void pktgen_resched(struct pktgen_dev *pkt_dev) @@ -3510,7 +3529,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) __netif_tx_lock_bh(txq); - if (unlikely(netif_tx_queue_stopped(txq) || netif_tx_queue_frozen(txq))) { + if (unlikely(netif_tx_queue_frozen_or_stopped(txq))) { ret = NETDEV_TX_BUSY; pkt_dev->last_ok = 0; goto unlock; @@ -3534,8 +3553,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) break; default: /* Drivers are not supposed to return other values! */ if (net_ratelimit()) - pr_info("pktgen: %s xmit error: %d\n", - pkt_dev->odevname, ret); + pr_info("%s xmit error: %d\n", pkt_dev->odevname, ret); pkt_dev->errors++; /* fallthru */ case NETDEV_TX_LOCKED: @@ -3582,6 +3600,8 @@ static int pktgen_thread_worker(void *arg) pkt_dev = next_to_run(t); if (unlikely(!pkt_dev && t->control == 0)) { + if (pktgen_exiting) + break; wait_event_interruptible_timeout(t->queue, t->control != 0, HZ/10); @@ -3634,6 +3654,13 @@ static int pktgen_thread_worker(void *arg) pr_debug("%s removing thread\n", t->tsk->comm); pktgen_rem_thread(t); + /* Wait for kthread_stop */ + while (!kthread_should_stop()) { + set_current_state(TASK_INTERRUPTIBLE); + schedule(); + } + __set_current_state(TASK_RUNNING); + return 0; } @@ -3908,6 +3935,7 @@ static void __exit pg_cleanup(void) struct list_head *q, *n; /* Stop all interfaces & threads */ + pktgen_exiting = true; list_for_each_safe(q, n, &pktgen_threads) { t = list_entry(q, struct pktgen_thread, th_list); diff --git a/net/core/request_sock.c b/net/core/request_sock.c index fceeb37d716..182236b2510 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -33,6 +33,7 @@ * Note : Dont forget somaxconn that may limit backlog too. */ int sysctl_max_syn_backlog = 256; +EXPORT_SYMBOL(sysctl_max_syn_backlog); int reqsk_queue_alloc(struct request_sock_queue *queue, unsigned int nr_table_entries) diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 841c287ef40..750db57f3bb 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -362,6 +362,95 @@ static size_t rtnl_link_get_size(const struct net_device *dev) return size; } +static LIST_HEAD(rtnl_af_ops); + +static const struct rtnl_af_ops *rtnl_af_lookup(const int family) +{ + const struct rtnl_af_ops *ops; + + list_for_each_entry(ops, &rtnl_af_ops, list) { + if (ops->family == family) + return ops; + } + + return NULL; +} + +/** + * __rtnl_af_register - Register rtnl_af_ops with rtnetlink. + * @ops: struct rtnl_af_ops * to register + * + * The caller must hold the rtnl_mutex. + * + * Returns 0 on success or a negative error code. + */ +int __rtnl_af_register(struct rtnl_af_ops *ops) +{ + list_add_tail(&ops->list, &rtnl_af_ops); + return 0; +} +EXPORT_SYMBOL_GPL(__rtnl_af_register); + +/** + * rtnl_af_register - Register rtnl_af_ops with rtnetlink. + * @ops: struct rtnl_af_ops * to register + * + * Returns 0 on success or a negative error code. + */ +int rtnl_af_register(struct rtnl_af_ops *ops) +{ + int err; + + rtnl_lock(); + err = __rtnl_af_register(ops); + rtnl_unlock(); + return err; +} +EXPORT_SYMBOL_GPL(rtnl_af_register); + +/** + * __rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. + * @ops: struct rtnl_af_ops * to unregister + * + * The caller must hold the rtnl_mutex. + */ +void __rtnl_af_unregister(struct rtnl_af_ops *ops) +{ + list_del(&ops->list); +} +EXPORT_SYMBOL_GPL(__rtnl_af_unregister); + +/** + * rtnl_af_unregister - Unregister rtnl_af_ops from rtnetlink. + * @ops: struct rtnl_af_ops * to unregister + */ +void rtnl_af_unregister(struct rtnl_af_ops *ops) +{ + rtnl_lock(); + __rtnl_af_unregister(ops); + rtnl_unlock(); +} +EXPORT_SYMBOL_GPL(rtnl_af_unregister); + +static size_t rtnl_link_get_af_size(const struct net_device *dev) +{ + struct rtnl_af_ops *af_ops; + size_t size; + + /* IFLA_AF_SPEC */ + size = nla_total_size(sizeof(struct nlattr)); + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->get_link_af_size) { + /* AF_* + nested data */ + size += nla_total_size(sizeof(struct nlattr)) + + af_ops->get_link_af_size(dev); + } + } + + return size; +} + static int rtnl_link_fill(struct sk_buff *skb, const struct net_device *dev) { const struct rtnl_link_ops *ops = dev->rtnl_link_ops; @@ -671,7 +760,8 @@ static noinline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_NUM_VF */ + rtnl_vfinfo_size(dev) /* IFLA_VFINFO_LIST */ + rtnl_port_size(dev) /* IFLA_VF_PORTS + IFLA_PORT_SELF */ - + rtnl_link_get_size(dev); /* IFLA_LINKINFO */ + + rtnl_link_get_size(dev) /* IFLA_LINKINFO */ + + rtnl_link_get_af_size(dev); /* IFLA_AF_SPEC */ } static int rtnl_vf_ports_fill(struct sk_buff *skb, struct net_device *dev) @@ -757,7 +847,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct nlmsghdr *nlh; struct rtnl_link_stats64 temp; const struct rtnl_link_stats64 *stats; - struct nlattr *attr; + struct nlattr *attr, *af_spec; + struct rtnl_af_ops *af_ops; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); if (nlh == NULL) @@ -866,6 +957,36 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, goto nla_put_failure; } + if (!(af_spec = nla_nest_start(skb, IFLA_AF_SPEC))) + goto nla_put_failure; + + list_for_each_entry(af_ops, &rtnl_af_ops, list) { + if (af_ops->fill_link_af) { + struct nlattr *af; + int err; + + if (!(af = nla_nest_start(skb, af_ops->family))) + goto nla_put_failure; + + err = af_ops->fill_link_af(skb, dev); + + /* + * Caller may return ENODATA to indicate that there + * was no data to be dumped. This is not an error, it + * means we should trim the attribute header and + * continue. + */ + if (err == -ENODATA) + nla_nest_cancel(skb, af); + else if (err < 0) + goto nla_put_failure; + + nla_nest_end(skb, af); + } + } + + nla_nest_end(skb, af_spec); + return nlmsg_end(skb, nlh); nla_put_failure: @@ -924,6 +1045,7 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_VFINFO_LIST] = {. type = NLA_NESTED }, [IFLA_VF_PORTS] = { .type = NLA_NESTED }, [IFLA_PORT_SELF] = { .type = NLA_NESTED }, + [IFLA_AF_SPEC] = { .type = NLA_NESTED }, }; EXPORT_SYMBOL(ifla_policy); @@ -985,6 +1107,28 @@ static int validate_linkmsg(struct net_device *dev, struct nlattr *tb[]) return -EINVAL; } + if (tb[IFLA_AF_SPEC]) { + struct nlattr *af; + int rem, err; + + nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { + const struct rtnl_af_ops *af_ops; + + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + return -EAFNOSUPPORT; + + if (!af_ops->set_link_af) + return -EOPNOTSUPP; + + if (af_ops->validate_link_af) { + err = af_ops->validate_link_af(dev, + tb[IFLA_AF_SPEC]); + if (err < 0) + return err; + } + } + } + return 0; } @@ -1225,6 +1369,24 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, goto errout; modified = 1; } + + if (tb[IFLA_AF_SPEC]) { + struct nlattr *af; + int rem; + + nla_for_each_nested(af, tb[IFLA_AF_SPEC], rem) { + const struct rtnl_af_ops *af_ops; + + if (!(af_ops = rtnl_af_lookup(nla_type(af)))) + BUG(); + + err = af_ops->set_link_af(dev, af); + if (err < 0) + goto errout; + + modified = 1; + } + } err = 0; errout: diff --git a/net/core/scm.c b/net/core/scm.c index 413cab89017..bbe45445080 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -79,10 +79,11 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) return -ENOMEM; *fplp = fpl; fpl->count = 0; + fpl->max = SCM_MAX_FD; } fpp = &fpl->fp[fpl->count]; - if (fpl->count + num > SCM_MAX_FD) + if (fpl->count + num > fpl->max) return -EINVAL; /* @@ -331,11 +332,12 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) if (!fpl) return NULL; - new_fpl = kmalloc(sizeof(*fpl), GFP_KERNEL); + new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]), + GFP_KERNEL); if (new_fpl) { - for (i=fpl->count-1; i>=0; i--) + for (i = 0; i < fpl->count; i++) get_file(fpl->fp[i]); - memcpy(new_fpl, fpl, sizeof(*fpl)); + new_fpl->max = new_fpl->count; } return new_fpl; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 104f8444754..19d6c21220f 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -778,6 +778,28 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, size = SKB_DATA_ALIGN(size); + /* Check if we can avoid taking references on fragments if we own + * the last reference on skb->head. (see skb_release_data()) + */ + if (!skb->cloned) + fastpath = true; + else { + int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; + + fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; + } + + if (fastpath && + size + sizeof(struct skb_shared_info) <= ksize(skb->head)) { + memmove(skb->head + size, skb_shinfo(skb), + offsetof(struct skb_shared_info, + frags[skb_shinfo(skb)->nr_frags])); + memmove(skb->head + nhead, skb->head, + skb_tail_pointer(skb) - skb->head); + off = nhead; + goto adjust_others; + } + data = kmalloc(size + sizeof(struct skb_shared_info), gfp_mask); if (!data) goto nodata; @@ -791,17 +813,6 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, skb_shinfo(skb), offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); - /* Check if we can avoid taking references on fragments if we own - * the last reference on skb->head. (see skb_release_data()) - */ - if (!skb->cloned) - fastpath = true; - else { - int delta = skb->nohdr ? (1 << SKB_DATAREF_SHIFT) + 1 : 1; - - fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; - } - if (fastpath) { kfree(skb->head); } else { @@ -816,6 +827,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, off = (data + nhead) - skb->head; skb->head = data; +adjust_others: skb->data += off; #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->end = size; @@ -1812,7 +1824,7 @@ void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to) long csstart; if (skb->ip_summed == CHECKSUM_PARTIAL) - csstart = skb->csum_start - skb_headroom(skb); + csstart = skb_checksum_start_offset(skb); else csstart = skb_headlen(skb); diff --git a/net/core/sock.c b/net/core/sock.c index fb608011146..a658aeb6d55 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -992,23 +992,54 @@ static inline void sock_lock_init(struct sock *sk) /* * Copy all fields from osk to nsk but nsk->sk_refcnt must not change yet, * even temporarly, because of RCU lookups. sk_node should also be left as is. + * We must not copy fields between sk_dontcopy_begin and sk_dontcopy_end */ static void sock_copy(struct sock *nsk, const struct sock *osk) { #ifdef CONFIG_SECURITY_NETWORK 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_tx_queue_mapping)); - memcpy(&nsk->sk_copy_start, &osk->sk_copy_start, - osk->sk_prot->obj_size - offsetof(struct sock, sk_copy_start)); + memcpy(nsk, osk, offsetof(struct sock, sk_dontcopy_begin)); + + memcpy(&nsk->sk_dontcopy_end, &osk->sk_dontcopy_end, + osk->sk_prot->obj_size - offsetof(struct sock, sk_dontcopy_end)); + #ifdef CONFIG_SECURITY_NETWORK nsk->sk_security = sptr; security_sk_clone(osk, nsk); #endif } +/* + * caches using SLAB_DESTROY_BY_RCU should let .next pointer from nulls nodes + * un-modified. Special care is taken when initializing object to zero. + */ +static inline void sk_prot_clear_nulls(struct sock *sk, int size) +{ + if (offsetof(struct sock, sk_node.next) != 0) + memset(sk, 0, offsetof(struct sock, sk_node.next)); + memset(&sk->sk_node.pprev, 0, + size - offsetof(struct sock, sk_node.pprev)); +} + +void sk_prot_clear_portaddr_nulls(struct sock *sk, int size) +{ + unsigned long nulls1, nulls2; + + nulls1 = offsetof(struct sock, __sk_common.skc_node.next); + nulls2 = offsetof(struct sock, __sk_common.skc_portaddr_node.next); + if (nulls1 > nulls2) + swap(nulls1, nulls2); + + if (nulls1 != 0) + memset((char *)sk, 0, nulls1); + memset((char *)sk + nulls1 + sizeof(void *), 0, + nulls2 - nulls1 - sizeof(void *)); + memset((char *)sk + nulls2 + sizeof(void *), 0, + size - nulls2 - sizeof(void *)); +} +EXPORT_SYMBOL(sk_prot_clear_portaddr_nulls); + static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, int family) { @@ -1021,19 +1052,12 @@ static struct sock *sk_prot_alloc(struct proto *prot, gfp_t priority, if (!sk) return sk; if (priority & __GFP_ZERO) { - /* - * caches using SLAB_DESTROY_BY_RCU should let - * sk_node.next un-modified. Special care is taken - * when initializing object to zero. - */ - if (offsetof(struct sock, sk_node.next) != 0) - memset(sk, 0, offsetof(struct sock, sk_node.next)); - memset(&sk->sk_node.pprev, 0, - prot->obj_size - offsetof(struct sock, - sk_node.pprev)); + if (prot->clear_sk) + prot->clear_sk(sk, prot->obj_size); + else + sk_prot_clear_nulls(sk, prot->obj_size); } - } - else + } else sk = kmalloc(prot->obj_size, priority); if (sk != NULL) { @@ -1884,7 +1908,7 @@ static void sock_def_readable(struct sock *sk, int len) rcu_read_lock(); wq = rcu_dereference(sk->sk_wq); if (wq_has_sleeper(wq)) - wake_up_interruptible_sync_poll(&wq->wait, POLLIN | + wake_up_interruptible_sync_poll(&wq->wait, POLLIN | POLLPRI | POLLRDNORM | POLLRDBAND); sk_wake_async(sk, SOCK_WAKE_WAITD, POLL_IN); rcu_read_unlock(); diff --git a/net/core/timestamping.c b/net/core/timestamping.c index 0ae6c22da85..7e7ca375d43 100644 --- a/net/core/timestamping.c +++ b/net/core/timestamping.c @@ -26,12 +26,12 @@ static struct sock_filter ptp_filter[] = { PTP_FILTER }; -static unsigned int classify(struct sk_buff *skb) +static unsigned int classify(const struct sk_buff *skb) { if (likely(skb->dev && skb->dev->phydev && skb->dev->phydev->drv)) - return sk_run_filter(skb, ptp_filter, ARRAY_SIZE(ptp_filter)); + return sk_run_filter(skb, ptp_filter); else return PTP_CLASS_NONE; } @@ -96,11 +96,13 @@ bool skb_defer_rx_timestamp(struct sk_buff *skb) struct phy_device *phydev; unsigned int type; - skb_push(skb, ETH_HLEN); + if (skb_headroom(skb) < ETH_HLEN) + return false; + __skb_push(skb, ETH_HLEN); type = classify(skb); - skb_pull(skb, ETH_HLEN); + __skb_pull(skb, ETH_HLEN); switch (type) { case PTP_CLASS_V1_IPV4: |