diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 149 |
1 files changed, 109 insertions, 40 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index cd0981977f5c..a39354ee1432 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1055,6 +1055,8 @@ rollback: */ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) { + char *new_ifalias; + ASSERT_RTNL(); if (len >= IFALIASZ) @@ -1068,9 +1070,10 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return 0; } - dev->ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); - if (!dev->ifalias) + new_ifalias = krealloc(dev->ifalias, len + 1, GFP_KERNEL); + if (!new_ifalias) return -ENOMEM; + dev->ifalias = new_ifalias; strlcpy(dev->ifalias, alias, len+1); return len; @@ -1136,8 +1139,8 @@ void dev_load(struct net *net, const char *name) no_module = request_module("netdev-%s", name); if (no_module && capable(CAP_SYS_MODULE)) { if (!request_module("%s", name)) - pr_err("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", - name); + pr_warn("Loading kernel module for a network device with CAP_SYS_MODULE (deprecated). Use CAP_NET_ADMIN and alias netdev-%s instead.\n", + name); } } EXPORT_SYMBOL(dev_load); @@ -1172,6 +1175,7 @@ static int __dev_open(struct net_device *dev) net_dmaengine_get(); dev_set_rx_mode(dev); dev_activate(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); } return ret; @@ -1632,6 +1636,8 @@ static inline int deliver_skb(struct sk_buff *skb, struct packet_type *pt_prev, struct net_device *orig_dev) { + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + return -ENOMEM; atomic_inc(&skb->users); return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } @@ -1691,7 +1697,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_unlock(); } -/* netif_setup_tc - Handle tc mappings on real_num_tx_queues change +/** + * netif_setup_tc - Handle tc mappings on real_num_tx_queues change * @dev: Network device * @txq: number of queues available * @@ -1793,6 +1800,18 @@ int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) EXPORT_SYMBOL(netif_set_real_num_rx_queues); #endif +/** + * netif_get_num_default_rss_queues - default number of RSS queues + * + * This routine should set an upper limit on the number of RSS queues + * used by default by multiqueue devices. + */ +int netif_get_num_default_rss_queues(void) +{ + return min_t(int, DEFAULT_MAX_NUM_RSS_QUEUES, num_online_cpus()); +} +EXPORT_SYMBOL(netif_get_num_default_rss_queues); + static inline void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; @@ -2089,25 +2108,6 @@ static int dev_gso_segment(struct sk_buff *skb, netdev_features_t features) return 0; } -/* - * Try to orphan skb early, right before transmission by the device. - * We cannot orphan skb if tx timestamp is requested or the sk-reference - * is needed on driver level for other reasons, e.g. see net/can/raw.c - */ -static inline void skb_orphan_try(struct sk_buff *skb) -{ - struct sock *sk = skb->sk; - - if (sk && !skb_shinfo(skb)->tx_flags) { - /* skb_tx_hash() wont be able to get sk. - * We copy sk_hash into skb->rxhash - */ - if (!skb->rxhash) - skb->rxhash = sk->sk_hash; - skb_orphan(skb); - } -} - static bool can_checksum_protocol(netdev_features_t features, __be16 protocol) { return ((features & NETIF_F_GEN_CSUM) || @@ -2137,6 +2137,9 @@ netdev_features_t netif_skb_features(struct sk_buff *skb) __be16 protocol = skb->protocol; netdev_features_t features = skb->dev->features; + if (skb_shinfo(skb)->gso_segs > skb->dev->gso_max_segs) + features &= ~NETIF_F_GSO_MASK; + if (protocol == htons(ETH_P_8021Q)) { struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; protocol = veh->h_vlan_encapsulated_proto; @@ -2193,8 +2196,6 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, if (!list_empty(&ptype_all)) dev_queue_xmit_nit(skb, dev); - skb_orphan_try(skb); - features = netif_skb_features(skb); if (vlan_tx_tag_present(skb) && @@ -2304,7 +2305,7 @@ u16 __skb_tx_hash(const struct net_device *dev, const struct sk_buff *skb, if (skb->sk && skb->sk->sk_hash) hash = skb->sk->sk_hash; else - hash = (__force u16) skb->protocol ^ skb->rxhash; + hash = (__force u16) skb->protocol; hash = jhash_1word(hash, hashrnd); return (u16) (((u64) hash * qcount) >> 32) + qoffset; @@ -2465,8 +2466,12 @@ static void skb_update_prio(struct sk_buff *skb) { struct netprio_map *map = rcu_dereference_bh(skb->dev->priomap); - if ((!skb->priority) && (skb->sk) && map) - skb->priority = map->priomap[skb->sk->sk_cgrp_prioidx]; + if (!skb->priority && skb->sk && map) { + unsigned int prioidx = skb->sk->sk_cgrp_prioidx; + + if (prioidx < map->priomap_len) + skb->priority = map->priomap[prioidx]; + } } #else #define skb_update_prio(skb) @@ -2476,6 +2481,23 @@ static DEFINE_PER_CPU(int, xmit_recursion); #define RECURSION_LIMIT 10 /** + * dev_loopback_xmit - loop back @skb + * @skb: buffer to transmit + */ +int dev_loopback_xmit(struct sk_buff *skb) +{ + skb_reset_mac_header(skb); + __skb_pull(skb, skb_network_offset(skb)); + skb->pkt_type = PACKET_LOOPBACK; + skb->ip_summed = CHECKSUM_UNNECESSARY; + WARN_ON(!skb_dst(skb)); + skb_dst_force(skb); + netif_rx_ni(skb); + return 0; +} +EXPORT_SYMBOL(dev_loopback_xmit); + +/** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit * @@ -3140,6 +3162,23 @@ void netdev_rx_handler_unregister(struct net_device *dev) } EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); +/* + * Limit the use of PFMEMALLOC reserves to those protocols that implement + * the special handling of PFMEMALLOC skbs. + */ +static bool skb_pfmemalloc_protocol(struct sk_buff *skb) +{ + switch (skb->protocol) { + case __constant_htons(ETH_P_ARP): + case __constant_htons(ETH_P_IP): + case __constant_htons(ETH_P_IPV6): + case __constant_htons(ETH_P_8021Q): + return true; + default: + return false; + } +} + static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; @@ -3149,17 +3188,28 @@ static int __netif_receive_skb(struct sk_buff *skb) bool deliver_exact = false; int ret = NET_RX_DROP; __be16 type; + unsigned long pflags = current->flags; net_timestamp_check(!netdev_tstamp_prequeue, skb); trace_netif_receive_skb(skb); + /* + * PFMEMALLOC skbs are special, they should + * - be delivered to SOCK_MEMALLOC sockets only + * - stay away from userspace + * - have bounded memory usage + * + * Use PF_MEMALLOC as this saves us from propagating the allocation + * context down to all allocation sites. + */ + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + current->flags |= PF_MEMALLOC; + /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) - return NET_RX_DROP; + goto out; - if (!skb->skb_iif) - skb->skb_iif = skb->dev->ifindex; orig_dev = skb->dev; skb_reset_network_header(skb); @@ -3171,13 +3221,14 @@ static int __netif_receive_skb(struct sk_buff *skb) rcu_read_lock(); another_round: + skb->skb_iif = skb->dev->ifindex; __this_cpu_inc(softnet_data.processed); if (skb->protocol == cpu_to_be16(ETH_P_8021Q)) { skb = vlan_untag(skb); if (unlikely(!skb)) - goto out; + goto unlock; } #ifdef CONFIG_NET_CLS_ACT @@ -3187,6 +3238,9 @@ another_round: } #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb)) + goto skip_taps; + list_for_each_entry_rcu(ptype, &ptype_all, list) { if (!ptype->dev || ptype->dev == skb->dev) { if (pt_prev) @@ -3195,13 +3249,18 @@ another_round: } } +skip_taps: #ifdef CONFIG_NET_CLS_ACT skb = handle_ing(skb, &pt_prev, &ret, orig_dev); if (!skb) - goto out; + goto unlock; ncls: #endif + if (sk_memalloc_socks() && skb_pfmemalloc(skb) + && !skb_pfmemalloc_protocol(skb)) + goto drop; + rx_handler = rcu_dereference(skb->dev->rx_handler); if (vlan_tx_tag_present(skb)) { if (pt_prev) { @@ -3211,7 +3270,7 @@ ncls: if (vlan_do_receive(&skb, !rx_handler)) goto another_round; else if (unlikely(!skb)) - goto out; + goto unlock; } if (rx_handler) { @@ -3221,7 +3280,7 @@ ncls: } switch (rx_handler(&skb)) { case RX_HANDLER_CONSUMED: - goto out; + goto unlock; case RX_HANDLER_ANOTHER: goto another_round; case RX_HANDLER_EXACT: @@ -3249,8 +3308,12 @@ ncls: } if (pt_prev) { - ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); + if (unlikely(skb_orphan_frags(skb, GFP_ATOMIC))) + ret = -ENOMEM; + else + ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { +drop: atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining @@ -3259,8 +3322,10 @@ ncls: ret = NET_RX_DROP; } -out: +unlock: rcu_read_unlock(); +out: + tsk_restore_flags(current, pflags, PF_MEMALLOC); return ret; } @@ -4784,6 +4849,7 @@ int dev_set_mac_address(struct net_device *dev, struct sockaddr *sa) err = ops->ndo_set_mac_address(dev, sa); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); + add_device_randomness(dev->dev_addr, dev->addr_len); return err; } EXPORT_SYMBOL(dev_set_mac_address); @@ -5562,6 +5628,7 @@ int register_netdevice(struct net_device *dev) dev_init_scheduler(dev); dev_hold(dev); list_netdevice(dev); + add_device_randomness(dev->dev_addr, dev->addr_len); /* Notify protocols, that a new device appeared. */ ret = call_netdevice_notifiers(NETDEV_REGISTER, dev); @@ -5663,7 +5730,7 @@ int netdev_refcnt_read(const struct net_device *dev) } EXPORT_SYMBOL(netdev_refcnt_read); -/* +/** * netdev_wait_allrefs - wait until all references are gone. * * This is called when unregistering network devices. @@ -5925,6 +5992,7 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev_net_set(dev, &init_net); dev->gso_max_size = GSO_MAX_SIZE; + dev->gso_max_segs = GSO_MAX_SEGS; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@ -6300,7 +6368,8 @@ static struct hlist_head *netdev_create_hash(void) /* Initialize per network namespace state */ static int __net_init netdev_init(struct net *net) { - INIT_LIST_HEAD(&net->dev_base_head); + if (net != &init_net) + INIT_LIST_HEAD(&net->dev_base_head); net->dev_name_head = netdev_create_hash(); if (net->dev_name_head == NULL) |