diff options
Diffstat (limited to 'net/core/dev.c')
| -rw-r--r-- | net/core/dev.c | 1046 |
1 files changed, 643 insertions, 403 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index 660dd41aaaa6..8ae6631abcc2 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -128,7 +128,10 @@ #include <linux/jhash.h> #include <linux/random.h> #include <trace/events/napi.h> +#include <trace/events/net.h> +#include <trace/events/skb.h> #include <linux/pci.h> +#include <linux/inetdevice.h> #include "net-sysfs.h" @@ -371,6 +374,14 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) * --ANK (980803) */ +static inline struct list_head *ptype_head(const struct packet_type *pt) +{ + if (pt->type == htons(ETH_P_ALL)) + return &ptype_all; + else + return &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; +} + /** * dev_add_pack - add packet handler * @pt: packet type declaration @@ -386,16 +397,11 @@ static inline void netdev_set_addr_lockdep_class(struct net_device *dev) void dev_add_pack(struct packet_type *pt) { - int hash; + struct list_head *head = ptype_head(pt); - spin_lock_bh(&ptype_lock); - if (pt->type == htons(ETH_P_ALL)) - list_add_rcu(&pt->list, &ptype_all); - else { - hash = ntohs(pt->type) & PTYPE_HASH_MASK; - list_add_rcu(&pt->list, &ptype_base[hash]); - } - spin_unlock_bh(&ptype_lock); + spin_lock(&ptype_lock); + list_add_rcu(&pt->list, head); + spin_unlock(&ptype_lock); } EXPORT_SYMBOL(dev_add_pack); @@ -414,15 +420,10 @@ EXPORT_SYMBOL(dev_add_pack); */ void __dev_remove_pack(struct packet_type *pt) { - struct list_head *head; + struct list_head *head = ptype_head(pt); struct packet_type *pt1; - spin_lock_bh(&ptype_lock); - - if (pt->type == htons(ETH_P_ALL)) - head = &ptype_all; - else - head = &ptype_base[ntohs(pt->type) & PTYPE_HASH_MASK]; + spin_lock(&ptype_lock); list_for_each_entry(pt1, head, list) { if (pt == pt1) { @@ -433,7 +434,7 @@ void __dev_remove_pack(struct packet_type *pt) printk(KERN_WARNING "dev_remove_pack: %p not found.\n", pt); out: - spin_unlock_bh(&ptype_lock); + spin_unlock(&ptype_lock); } EXPORT_SYMBOL(__dev_remove_pack); @@ -742,34 +743,32 @@ 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 or RTNL. + * 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) { @@ -1224,52 +1223,93 @@ 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) +{ + int retval; + LIST_HEAD(single); + + list_add(&dev->unreg_list, &single); + retval = __dev_close_many(&single); + list_del(&single); + return retval; +} - dev->flags &= ~IFF_UP; +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_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; } @@ -1284,17 +1324,11 @@ 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); - - /* - * Tell people we are down - */ - rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); - call_netdevice_notifiers(NETDEV_DOWN, dev); + LIST_HEAD(single); + list_add(&dev->unreg_list, &single); + dev_close_many(&single); + list_del(&single); return 0; } EXPORT_SYMBOL(dev_close); @@ -1484,8 +1518,9 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) skb_orphan(skb); nf_reset(skb); - if (!(dev->flags & IFF_UP) || - (skb->len > (dev->mtu + dev->hard_header_len))) { + if (unlikely(!(dev->flags & IFF_UP) || + (skb->len > (dev->mtu + dev->hard_header_len + VLAN_HLEN)))) { + atomic_long_inc(&dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } @@ -1497,6 +1532,14 @@ 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. @@ -1505,13 +1548,8 @@ 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) { @@ -1521,10 +1559,18 @@ 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. @@ -1543,9 +1589,11 @@ 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(); } @@ -1553,21 +1601,63 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) * Routine to help set real_num_tx_queues. To avoid skbs mapped to queues * greater then real_num_tx_queues stale skbs on the qdisc must be flushed. */ -void netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) +int netif_set_real_num_tx_queues(struct net_device *dev, unsigned int txq) { - unsigned int real_num = dev->real_num_tx_queues; + 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 (unlikely(txq > dev->num_tx_queues)) - ; - else if (txq > real_num) - dev->real_num_tx_queues = txq; - else if (txq < real_num) { - dev->real_num_tx_queues = txq; - qdisc_reset_all_tx_gt(dev, txq); + if (txq < dev->real_num_tx_queues) + qdisc_reset_all_tx_gt(dev, txq); } + + dev->real_num_tx_queues = txq; + return 0; } EXPORT_SYMBOL(netif_set_real_num_tx_queues); +#ifdef CONFIG_RPS +/** + * netif_set_real_num_rx_queues - set actual number of RX queues used + * @dev: Network device + * @rxq: Actual number of RX queues + * + * This must be called either with the rtnl_lock held or before + * registration of the net device. Returns 0 on success, or a + * negative error code. If called before registration, it always + * succeeds. + */ +int netif_set_real_num_rx_queues(struct net_device *dev, unsigned int rxq) +{ + int rc; + + if (rxq < 1 || rxq > dev->num_rx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); + + rc = net_rx_queue_update_kobjects(dev, dev->real_num_rx_queues, + rxq); + if (rc) + return rc; + } + + dev->real_num_rx_queues = rxq; + return 0; +} +EXPORT_SYMBOL(netif_set_real_num_rx_queues); +#endif + static inline void __netif_reschedule(struct Qdisc *q) { struct softnet_data *sd; @@ -1646,32 +1736,6 @@ void netif_device_attach(struct net_device *dev) } EXPORT_SYMBOL(netif_device_attach); -static bool can_checksum_protocol(unsigned long features, __be16 protocol) -{ - return ((features & NETIF_F_GEN_CSUM) || - ((features & NETIF_F_IP_CSUM) && - protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_IPV6_CSUM) && - protocol == htons(ETH_P_IPV6)) || - ((features & NETIF_F_FCOE_CRC) && - protocol == htons(ETH_P_FCOE))); -} - -static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) -{ - if (can_checksum_protocol(dev->features, skb->protocol)) - return true; - - if (skb->protocol == htons(ETH_P_8021Q)) { - struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; - if (can_checksum_protocol(dev->features & dev->vlan_features, - veh->h_vlan_encapsulated_proto)) - return true; - } - - return false; -} - /** * skb_dev_set -- assign a new device to a buffer * @skb: buffer for the new device @@ -1719,7 +1783,7 @@ 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); @@ -1756,8 +1820,20 @@ 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; + while (type == htons(ETH_P_8021Q)) { + struct vlan_hdr *vh; + + if (unlikely(!pskb_may_pull(skb, vlan_depth + VLAN_HLEN))) + return ERR_PTR(-EINVAL); + + vh = (struct vlan_hdr *)(skb->data + vlan_depth); + type = vh->h_vlan_encapsulated_proto; + vlan_depth += VLAN_HLEN; + } + skb_reset_mac_header(skb); skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); @@ -1769,8 +1845,7 @@ 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); @@ -1873,16 +1948,14 @@ static void dev_gso_skb_destructor(struct sk_buff *skb) /** * dev_gso_segment - Perform emulated hardware segmentation on skb. * @skb: buffer to segment + * @features: device features as applicable to this skb * * This function segments the given skb and stores the list of segments * in skb->next. */ -static int dev_gso_segment(struct sk_buff *skb) +static int dev_gso_segment(struct sk_buff *skb, int features) { - struct net_device *dev = skb->dev; struct sk_buff *segs; - int features = dev->features & ~(illegal_highdma(dev, skb) ? - NETIF_F_SG : 0); segs = skb_gso_segment(skb, features); @@ -1902,14 +1975,14 @@ static int dev_gso_segment(struct sk_buff *skb) /* * Try to orphan skb early, right before transmission by the device. - * We cannot orphan skb if tx timestamp is requested, since - * drivers need to call skb_tstamp_tx() to send the timestamp. + * 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_tx(skb)->flags) { + if (sk && !skb_shinfo(skb)->tx_flags) { /* skb_tx_hash() wont be able to get sk. * We copy sk_hash into skb->rxhash */ @@ -1919,6 +1992,53 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } +static bool can_checksum_protocol(unsigned long features, __be16 protocol) +{ + return ((features & NETIF_F_GEN_CSUM) || + ((features & NETIF_F_V4_CSUM) && + protocol == htons(ETH_P_IP)) || + ((features & NETIF_F_V6_CSUM) && + protocol == htons(ETH_P_IPV6)) || + ((features & NETIF_F_FCOE_CRC) && + protocol == htons(ETH_P_FCOE))); +} + +static int harmonize_features(struct sk_buff *skb, __be16 protocol, int features) +{ + if (!can_checksum_protocol(features, protocol)) { + features &= ~NETIF_F_ALL_CSUM; + features &= ~NETIF_F_SG; + } else if (illegal_highdma(skb->dev, skb)) { + features &= ~NETIF_F_SG; + } + + return features; +} + +int netif_skb_features(struct sk_buff *skb) +{ + __be16 protocol = skb->protocol; + int features = skb->dev->features; + + if (protocol == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh = (struct vlan_ethhdr *)skb->data; + protocol = veh->h_vlan_encapsulated_proto; + } else if (!vlan_tx_tag_present(skb)) { + return harmonize_features(skb, protocol, features); + } + + features &= (skb->dev->vlan_features | NETIF_F_HW_VLAN_TX); + + if (protocol != htons(ETH_P_8021Q)) { + return harmonize_features(skb, protocol, features); + } else { + features &= NETIF_F_SG | NETIF_F_HIGHDMA | NETIF_F_FRAGLIST | + NETIF_F_GEN_CSUM | NETIF_F_HW_VLAN_TX; + return harmonize_features(skb, protocol, features); + } +} +EXPORT_SYMBOL(netif_skb_features); + /* * Returns true if either: * 1. skb has frag_list and the device doesn't support FRAGLIST, or @@ -1927,12 +2047,13 @@ static inline void skb_orphan_try(struct sk_buff *skb) * support DMA from it. */ static inline int skb_needs_linearize(struct sk_buff *skb, - struct net_device *dev) + int features) { return skb_is_nonlinear(skb) && - ((skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) || - illegal_highdma(dev, skb)))); + ((skb_has_frag_list(skb) && + !(features & NETIF_F_FRAGLIST)) || + (skb_shinfo(skb)->nr_frags && + !(features & NETIF_F_SG))); } int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, @@ -1942,8 +2063,7 @@ 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); + int features; /* * If device doesnt need skb->dst, release it right now while @@ -1952,15 +2072,29 @@ 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 (netif_needs_gso(dev, skb)) { - if (unlikely(dev_gso_segment(skb))) + features = netif_skb_features(skb); + + if (vlan_tx_tag_present(skb) && + !(features & NETIF_F_HW_VLAN_TX)) { + skb = __vlan_put_tag(skb, vlan_tx_tag_get(skb)); + if (unlikely(!skb)) + goto out; + + skb->vlan_tci = 0; + } + + if (netif_needs_gso(skb, features)) { + if (unlikely(dev_gso_segment(skb, features))) goto out_kfree_skb; if (skb->next) goto gso; } else { - if (skb_needs_linearize(skb, dev) && + if (skb_needs_linearize(skb, features) && __skb_linearize(skb)) goto out_kfree_skb; @@ -1969,15 +2103,16 @@ 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)); - if (!dev_can_checksum(dev, skb) && + skb_set_transport_header(skb, + skb_checksum_start_offset(skb)); + if (!(features & NETIF_F_ALL_CSUM) && skb_checksum_help(skb)) goto out_kfree_skb; } } rc = ops->ndo_start_xmit(skb, dev); + trace_net_dev_xmit(skb, rc); if (rc == NETDEV_TX_OK) txq_trans_update(txq); return rc; @@ -1998,6 +2133,7 @@ gso: skb_dst_drop(nskb); rc = ops->ndo_start_xmit(nskb, dev); + trace_net_dev_xmit(nskb, rc); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) goto out_kfree_gso_skb; @@ -2015,19 +2151,25 @@ out_kfree_gso_skb: skb->destructor = DEV_GSO_CB(skb)->destructor; out_kfree_skb: kfree_skb(skb); +out: return rc; } 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; } @@ -2037,9 +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) { @@ -2054,26 +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 = 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); @@ -2115,7 +2301,10 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, */ if (!(dev->priv_flags & IFF_XMIT_DST_RELEASE)) skb_dst_force(skb); - __qdisc_update_bstats(q, skb->len); + + qdisc_skb_cb(skb)->pkt_len = skb->len; + qdisc_bstats_update(q, skb); + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { if (unlikely(contended)) { spin_unlock(&q->busylock); @@ -2143,6 +2332,9 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, return rc; } +static DEFINE_PER_CPU(int, xmit_recursion); +#define RECURSION_LIMIT 10 + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -2186,6 +2378,7 @@ int dev_queue_xmit(struct sk_buff *skb) #ifdef CONFIG_NET_CLS_ACT skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); #endif + trace_net_dev_queue(skb); if (q->enqueue) { rc = __dev_xmit_skb(skb, q, dev, txq); goto out; @@ -2208,10 +2401,15 @@ int dev_queue_xmit(struct sk_buff *skb) if (txq->xmit_lock_owner != cpu) { + if (__this_cpu_read(xmit_recursion) > RECURSION_LIMIT) + goto recursion_alert; + HARD_TX_LOCK(dev, txq, cpu); if (!netif_tx_queue_stopped(txq)) { + __this_cpu_inc(xmit_recursion); rc = dev_hard_start_xmit(skb, dev, txq); + __this_cpu_dec(xmit_recursion); if (dev_xmit_complete(rc)) { HARD_TX_UNLOCK(dev, txq); goto out; @@ -2223,7 +2421,9 @@ int dev_queue_xmit(struct sk_buff *skb) "queue packet!\n", dev->name); } else { /* Recursion is detected! It is possible, - * unfortunately */ + * unfortunately + */ +recursion_alert: if (net_ratelimit()) printk(KERN_CRIT "Dead loop on virtual device " "%s, fix it urgently!\n", dev->name); @@ -2259,69 +2459,44 @@ static inline void ____napi_schedule(struct softnet_data *sd, __raise_softirq_irqoff(NET_RX_SOFTIRQ); } -#ifdef CONFIG_RPS - -/* One global table that all flow-based protocols share. */ -struct rps_sock_flow_table *rps_sock_flow_table __read_mostly; -EXPORT_SYMBOL(rps_sock_flow_table); - /* - * get_rps_cpu is called from netif_receive_skb and returns the target - * CPU from the RPS map of the receiving queue for a given skb. - * rcu_read_lock must be held on entry. + * __skb_get_rxhash: calculate a flow hash based on src/dst addresses + * and src/dst port numbers. Returns a non-zero hash number on success + * and 0 on failure. */ -static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, - struct rps_dev_flow **rflowp) +__u32 __skb_get_rxhash(struct sk_buff *skb) { + int nhoff, hash = 0, poff; struct ipv6hdr *ip6; struct iphdr *ip; - struct netdev_rx_queue *rxqueue; - struct rps_map *map; - struct rps_dev_flow_table *flow_table; - struct rps_sock_flow_table *sock_flow_table; - int cpu = -1; u8 ip_proto; - u16 tcpu; u32 addr1, addr2, ihl; union { u32 v32; u16 v16[2]; } ports; - if (skb_rx_queue_recorded(skb)) { - u16 index = skb_get_rx_queue(skb); - if (unlikely(index >= dev->num_rx_queues)) { - WARN_ONCE(dev->num_rx_queues > 1, "%s received packet " - "on queue %u, but number of RX queues is %u\n", - dev->name, index, dev->num_rx_queues); - goto done; - } - rxqueue = dev->_rx + index; - } else - rxqueue = dev->_rx; - - if (!rxqueue->rps_map && !rxqueue->rps_flow_table) - goto done; - - if (skb->rxhash) - goto got_hash; /* Skip hash computation on packet header */ + nhoff = skb_network_offset(skb); switch (skb->protocol) { case __constant_htons(ETH_P_IP): - if (!pskb_may_pull(skb, sizeof(*ip))) + if (!pskb_may_pull(skb, sizeof(*ip) + nhoff)) goto done; - ip = (struct iphdr *) skb->data; - ip_proto = ip->protocol; + ip = (struct iphdr *) (skb->data + nhoff); + if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + ip_proto = 0; + else + ip_proto = ip->protocol; addr1 = (__force u32) ip->saddr; addr2 = (__force u32) ip->daddr; ihl = ip->ihl; break; case __constant_htons(ETH_P_IPV6): - if (!pskb_may_pull(skb, sizeof(*ip6))) + if (!pskb_may_pull(skb, sizeof(*ip6) + nhoff)) goto done; - ip6 = (struct ipv6hdr *) skb->data; + ip6 = (struct ipv6hdr *) (skb->data + nhoff); ip_proto = ip6->nexthdr; addr1 = (__force u32) ip6->saddr.s6_addr32[3]; addr2 = (__force u32) ip6->daddr.s6_addr32[3]; @@ -2330,33 +2505,82 @@ static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, default: goto done; } - switch (ip_proto) { - case IPPROTO_TCP: - case IPPROTO_UDP: - case IPPROTO_DCCP: - case IPPROTO_ESP: - case IPPROTO_AH: - case IPPROTO_SCTP: - case IPPROTO_UDPLITE: - if (pskb_may_pull(skb, (ihl * 4) + 4)) { - ports.v32 = * (__force u32 *) (skb->data + (ihl * 4)); + + ports.v32 = 0; + poff = proto_ports_offset(ip_proto); + if (poff >= 0) { + nhoff += ihl * 4 + poff; + if (pskb_may_pull(skb, nhoff + 4)) { + ports.v32 = * (__force u32 *) (skb->data + nhoff); if (ports.v16[1] < ports.v16[0]) swap(ports.v16[0], ports.v16[1]); - break; } - default: - ports.v32 = 0; - break; } /* get a consistent hash (same value on both flow directions) */ if (addr2 < addr1) swap(addr1, addr2); - skb->rxhash = jhash_3words(addr1, addr2, ports.v32, hashrnd); - if (!skb->rxhash) - skb->rxhash = 1; -got_hash: + hash = jhash_3words(addr1, addr2, ports.v32, hashrnd); + if (!hash) + hash = 1; + +done: + return hash; +} +EXPORT_SYMBOL(__skb_get_rxhash); + +#ifdef CONFIG_RPS + +/* One global table that all flow-based protocols share. */ +struct rps_sock_flow_table __rcu *rps_sock_flow_table __read_mostly; +EXPORT_SYMBOL(rps_sock_flow_table); + +/* + * get_rps_cpu is called from netif_receive_skb and returns the target + * CPU from the RPS map of the receiving queue for a given skb. + * rcu_read_lock must be held on entry. + */ +static int get_rps_cpu(struct net_device *dev, struct sk_buff *skb, + struct rps_dev_flow **rflowp) +{ + struct netdev_rx_queue *rxqueue; + struct rps_map *map; + struct rps_dev_flow_table *flow_table; + struct rps_sock_flow_table *sock_flow_table; + int cpu = -1; + u16 tcpu; + + if (skb_rx_queue_recorded(skb)) { + u16 index = skb_get_rx_queue(skb); + if (unlikely(index >= dev->real_num_rx_queues)) { + WARN_ONCE(dev->real_num_rx_queues > 1, + "%s received packet on queue %u, but number " + "of RX queues is %u\n", + dev->name, index, dev->real_num_rx_queues); + goto done; + } + rxqueue = dev->_rx + index; + } else + rxqueue = dev->_rx; + + map = rcu_dereference(rxqueue->rps_map); + if (map) { + if (map->len == 1 && + !rcu_dereference_raw(rxqueue->rps_flow_table)) { + tcpu = map->cpus[0]; + if (cpu_online(tcpu)) + cpu = tcpu; + goto done; + } + } else if (!rcu_dereference_raw(rxqueue->rps_flow_table)) { + goto done; + } + + skb_reset_network_header(skb); + if (!skb_get_rxhash(skb)) + goto done; + flow_table = rcu_dereference(rxqueue->rps_flow_table); sock_flow_table = rcu_dereference(rps_sock_flow_table); if (flow_table && sock_flow_table) { @@ -2396,7 +2620,6 @@ got_hash: } } - map = rcu_dereference(rxqueue->rps_map); if (map) { tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; @@ -2482,6 +2705,7 @@ enqueue: local_irq_restore(flags); + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } @@ -2512,6 +2736,7 @@ int netif_rx(struct sk_buff *skb) if (netdev_tstamp_prequeue) net_timestamp_check(skb); + trace_netif_rx(skb); #ifdef CONFIG_RPS { struct rps_dev_flow voidflow, *rflow = &voidflow; @@ -2571,6 +2796,7 @@ static void net_tx_action(struct softirq_action *h) clist = clist->next; WARN_ON(atomic_read(&skb->users)); + trace_kfree_skb(skb, net_tx_action); __kfree_skb(skb); } } @@ -2611,14 +2837,6 @@ 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 */ @@ -2636,11 +2854,10 @@ EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); * the ingress scheduler, you just cant add policies on ingress. * */ -static int ing_filter(struct sk_buff *skb) +static int ing_filter(struct sk_buff *skb, struct netdev_queue *rxq) { struct net_device *dev = skb->dev; u32 ttl = G_TC_RTTL(skb->tc_verd); - struct netdev_queue *rxq; int result = TC_ACT_OK; struct Qdisc *q; @@ -2654,8 +2871,6 @@ static int ing_filter(struct sk_buff *skb) skb->tc_verd = SET_TC_RTTL(skb->tc_verd, ttl); skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_INGRESS); - rxq = &dev->rx_queue; - q = rxq->qdisc; if (q != &noop_qdisc) { spin_lock(qdisc_lock(q)); @@ -2671,7 +2886,9 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, struct packet_type **pt_prev, int *ret, struct net_device *orig_dev) { - if (skb->dev->rx_queue.qdisc == &noop_qdisc) + struct netdev_queue *rxq = rcu_dereference(skb->dev->ingress_queue); + + if (!rxq || rxq->qdisc == &noop_qdisc) goto out; if (*pt_prev) { @@ -2679,7 +2896,7 @@ static inline struct sk_buff *handle_ing(struct sk_buff *skb, *pt_prev = NULL; } - switch (ing_filter(skb)) { + switch (ing_filter(skb, rxq)) { case TC_ACT_SHOT: case TC_ACT_STOLEN: kfree_skb(skb); @@ -2692,33 +2909,6 @@ out: } #endif -/* - * netif_nit_deliver - deliver received packets to network taps - * @skb: buffer - * - * This function is used to deliver incoming packets to network - * taps. It should be used when the normal netif_receive_skb path - * is bypassed, for example because of VLAN acceleration. - */ -void netif_nit_deliver(struct sk_buff *skb) -{ - struct packet_type *ptype; - - if (list_empty(&ptype_all)) - return; - - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; - - rcu_read_lock(); - list_for_each_entry_rcu(ptype, &ptype_all, list) { - if (!ptype->dev || ptype->dev == skb->dev) - deliver_skb(skb, ptype, skb->dev); - } - rcu_read_unlock(); -} - /** * netdev_rx_handler_register - register receive handler * @dev: device to register a handler for @@ -2828,8 +3018,7 @@ static int __netif_receive_skb(struct sk_buff *skb) if (!netdev_tstamp_prequeue) net_timestamp_check(skb); - if (vlan_tx_tag_present(skb) && vlan_hwaccel_do_receive(skb)) - return NET_RX_SUCCESS; + trace_netif_receive_skb(skb); /* if we've gotten here through NAPI, check netpoll */ if (netpoll_receive_skb(skb)) @@ -2843,8 +3032,7 @@ static int __netif_receive_skb(struct sk_buff *skb) * be delivered to pkt handlers that are exact matches. Also * the deliver_no_wcard flag will be set. If packet handlers * are sensitive to duplicate packets these skbs will need to - * be dropped at the handler. The vlan accel path may have - * already set the deliver_no_wcard flag. + * be dropped at the handler. */ null_or_orig = NULL; orig_dev = skb->dev; @@ -2903,6 +3091,18 @@ ncls: goto out; } + if (vlan_tx_tag_present(skb)) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + if (vlan_hwaccel_do_receive(&skb)) { + ret = __netif_receive_skb(skb); + goto out; + } else if (unlikely(!skb)) + goto out; + } + /* * Make sure frames received on VLAN interfaces stacked on * bonding interfaces still make their way to any base bonding @@ -2930,6 +3130,7 @@ ncls: if (pt_prev) { ret = pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } else { + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); /* Jamal, now you will not able to escape explaining * me how you were going to use this. :-) @@ -3050,7 +3251,7 @@ out: return netif_receive_skb(skb); } -static void napi_gro_flush(struct napi_struct *napi) +inline void napi_gro_flush(struct napi_struct *napi) { struct sk_buff *skb, *next; @@ -3063,6 +3264,7 @@ static void napi_gro_flush(struct napi_struct *napi) napi->gro_count = 0; napi->gro_list = NULL; } +EXPORT_SYMBOL(napi_gro_flush); enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { @@ -3077,7 +3279,7 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) if (!(skb->dev->features & NETIF_F_GRO) || netpoll_rx_on(skb)) goto normal; - if (skb_is_gso(skb) || skb_has_frags(skb)) + if (skb_is_gso(skb) || skb_has_frag_list(skb)) goto normal; rcu_read_lock(); @@ -3156,16 +3358,19 @@ normal: } EXPORT_SYMBOL(dev_gro_receive); -static gro_result_t +static inline gro_result_t __napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) { struct sk_buff *p; for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = - (p->dev == skb->dev) && - !compare_ether_header(skb_mac_header(p), + unsigned long diffs; + + diffs = (unsigned long)p->dev ^ (unsigned long)skb->dev; + diffs |= p->vlan_tci ^ skb->vlan_tci; + diffs |= compare_ether_header(skb_mac_header(p), skb_gro_mac_header(skb)); + NAPI_GRO_CB(p)->same_flow = !diffs; NAPI_GRO_CB(p)->flush = 0; } @@ -3218,14 +3423,16 @@ gro_result_t napi_gro_receive(struct napi_struct *napi, struct sk_buff *skb) } EXPORT_SYMBOL(napi_gro_receive); -void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) +static void napi_reuse_skb(struct napi_struct *napi, struct sk_buff *skb) { __skb_pull(skb, skb_headlen(skb)); skb_reserve(skb, NET_IP_ALIGN - skb_headroom(skb)); + skb->vlan_tci = 0; + skb->dev = napi->dev; + skb->skb_iif = 0; napi->skb = skb; } -EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { @@ -4799,10 +5006,12 @@ 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); @@ -4857,21 +5066,7 @@ static void rollback_registered(struct net_device *dev) list_add(&dev->unreg_list, &single); rollback_registered_many(&single); -} - -static void __netdev_init_queue_locks_one(struct net_device *dev, - struct netdev_queue *dev_queue, - void *_unused) -{ - spin_lock_init(&dev_queue->_xmit_lock); - netdev_set_xmit_lockdep_class(&dev_queue->_xmit_lock, dev->type); - dev_queue->xmit_lock_owner = -1; -} - -static void netdev_init_queue_locks(struct net_device *dev) -{ - netdev_for_each_tx_queue(dev, __netdev_init_queue_locks_one, NULL); - __netdev_init_queue_locks_one(dev, &dev->rx_queue, NULL); + list_del(&single); } unsigned long netdev_fix_features(unsigned long features, const char *name) @@ -4894,10 +5089,13 @@ 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; } @@ -4941,6 +5139,59 @@ 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) +{ + unsigned int i, count = dev->num_rx_queues; + struct netdev_rx_queue *rx; + + BUG_ON(count < 1); + + rx = kcalloc(count, sizeof(struct netdev_rx_queue), GFP_KERNEL); + if (!rx) { + pr_err("netdev: Unable to allocate %u rx queues.\n", count); + return -ENOMEM; + } + dev->_rx = rx; + + for (i = 0; i < count; i++) + 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) +{ + unsigned int count = dev->num_tx_queues; + struct netdev_queue *tx; + + BUG_ON(count < 1); + + tx = kcalloc(count, sizeof(struct netdev_queue), GFP_KERNEL); + if (!tx) { + pr_err("netdev: Unable to allocate %u tx queues.\n", + count); + return -ENOMEM; + } + dev->_tx = tx; + + netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); + spin_lock_init(&dev->tx_global_lock); + + return 0; +} + /** * register_netdevice - register a network device * @dev: device to register @@ -4974,28 +5225,9 @@ int register_netdevice(struct net_device *dev) spin_lock_init(&dev->addr_list_lock); netdev_set_addr_lockdep_class(dev); - netdev_init_queue_locks(dev); dev->iflink = -1; -#ifdef CONFIG_RPS - if (!dev->num_rx_queues) { - /* - * Allocate a single RX queue if driver never called - * alloc_netdev_mq - */ - - dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!dev->_rx) { - ret = -ENOMEM; - goto out; - } - - dev->_rx->first = dev->_rx; - atomic_set(&dev->_rx->count, 1); - dev->num_rx_queues = 1; - } -#endif /* Init, if this function is available */ if (dev->netdev_ops->ndo_init) { ret = dev->netdev_ops->ndo_init(dev); @@ -5035,6 +5267,12 @@ int register_netdevice(struct net_device *dev) if (dev->features & NETIF_F_SG) dev->features |= NETIF_F_GSO; + /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, + * vlan_dev_init() will do the dev->features check, so these features + * are enabled only if supported by underlying device. + */ + dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); if (ret) @@ -5105,9 +5343,6 @@ int init_dummy_netdev(struct net_device *dev) */ dev->reg_state = NETREG_DUMMY; - /* initialize the ref count */ - atomic_set(&dev->refcnt, 1); - /* NAPI wants this */ INIT_LIST_HEAD(&dev->napi_list); @@ -5115,6 +5350,11 @@ int init_dummy_netdev(struct net_device *dev) set_bit(__LINK_STATE_PRESENT, &dev->state); set_bit(__LINK_STATE_START, &dev->state); + /* Note : We dont allocate pcpu_refcnt for dummy devices, + * because users of this 'device' dont need to change + * its refcount. + */ + return 0; } EXPORT_SYMBOL_GPL(init_dummy_netdev); @@ -5156,6 +5396,16 @@ out: } EXPORT_SYMBOL(register_netdev); +int netdev_refcnt_read(const struct net_device *dev) +{ + int i, refcnt = 0; + + for_each_possible_cpu(i) + refcnt += *per_cpu_ptr(dev->pcpu_refcnt, i); + return refcnt; +} +EXPORT_SYMBOL(netdev_refcnt_read); + /* * netdev_wait_allrefs - wait until all references are gone. * @@ -5170,11 +5420,14 @@ EXPORT_SYMBOL(register_netdev); static void netdev_wait_allrefs(struct net_device *dev) { unsigned long rebroadcast_time, warning_time; + int refcnt; linkwatch_forget_dev(dev); rebroadcast_time = warning_time = jiffies; - while (atomic_read(&dev->refcnt) != 0) { + refcnt = netdev_refcnt_read(dev); + + while (refcnt != 0) { if (time_after(jiffies, rebroadcast_time + 1 * HZ)) { rtnl_lock(); @@ -5201,11 +5454,13 @@ static void netdev_wait_allrefs(struct net_device *dev) msleep(250); + refcnt = netdev_refcnt_read(dev); + if (time_after(jiffies, warning_time + 10 * HZ)) { printk(KERN_EMERG "unregister_netdevice: " "waiting for %s to become free. Usage " "count = %d\n", - dev->name, atomic_read(&dev->refcnt)); + dev->name, refcnt); warning_time = jiffies; } } @@ -5263,9 +5518,9 @@ void netdev_run_todo(void) netdev_wait_allrefs(dev); /* paranoia */ - BUG_ON(atomic_read(&dev->refcnt)); - WARN_ON(dev->ip_ptr); - WARN_ON(dev->ip6_ptr); + BUG_ON(netdev_refcnt_read(dev)); + WARN_ON(rcu_dereference_raw(dev->ip_ptr)); + WARN_ON(rcu_dereference_raw(dev->ip6_ptr)); WARN_ON(dev->dn_ptr); if (dev->destructor) @@ -5276,34 +5531,6 @@ void netdev_run_todo(void) } } -/** - * dev_txq_stats_fold - fold tx_queues stats - * @dev: device to get statistics from - * @stats: struct rtnl_link_stats64 to hold results - */ -void dev_txq_stats_fold(const struct net_device *dev, - struct rtnl_link_stats64 *stats) -{ - u64 tx_bytes = 0, tx_packets = 0, tx_dropped = 0; - unsigned int i; - struct netdev_queue *txq; - - for (i = 0; i < dev->num_tx_queues; i++) { - txq = netdev_get_tx_queue(dev, i); - spin_lock_bh(&txq->_xmit_lock); - tx_bytes += txq->tx_bytes; - tx_packets += txq->tx_packets; - tx_dropped += txq->tx_dropped; - spin_unlock_bh(&txq->_xmit_lock); - } - if (tx_bytes || tx_packets || tx_dropped) { - stats->tx_bytes = tx_bytes; - stats->tx_packets = tx_packets; - stats->tx_dropped = tx_dropped; - } -} -EXPORT_SYMBOL(dev_txq_stats_fold); - /* Convert net_device_stats to rtnl_link_stats64. They have the same * fields in the same order, with only the type differing. */ @@ -5342,57 +5569,71 @@ struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, if (ops->ndo_get_stats64) { memset(storage, 0, sizeof(*storage)); - return ops->ndo_get_stats64(dev, storage); - } - if (ops->ndo_get_stats) { + ops->ndo_get_stats64(dev, storage); + } else if (ops->ndo_get_stats) { netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); - return storage; + } else { + netdev_stats_to_stats64(storage, &dev->stats); } - netdev_stats_to_stats64(storage, &dev->stats); - dev_txq_stats_fold(dev, storage); + storage->rx_dropped += atomic_long_read(&dev->rx_dropped); return storage; } EXPORT_SYMBOL(dev_get_stats); -static void netdev_init_one_queue(struct net_device *dev, - struct netdev_queue *queue, - void *_unused) +struct netdev_queue *dev_ingress_queue_create(struct net_device *dev) { - queue->dev = dev; -} + struct netdev_queue *queue = dev_ingress_queue(dev); -static void netdev_init_queues(struct net_device *dev) -{ - netdev_init_one_queue(dev, &dev->rx_queue, NULL); - netdev_for_each_tx_queue(dev, netdev_init_one_queue, NULL); - spin_lock_init(&dev->tx_global_lock); +#ifdef CONFIG_NET_CLS_ACT + if (queue) + return queue; + queue = kzalloc(sizeof(*queue), GFP_KERNEL); + if (!queue) + return NULL; + netdev_init_one_queue(dev, queue, NULL); + queue->qdisc = &noop_qdisc; + queue->qdisc_sleeping = &noop_qdisc; + rcu_assign_pointer(dev->ingress_queue, queue); +#endif + return queue; } /** - * alloc_netdev_mq - allocate network device + * alloc_netdev_mqs - allocate network device * @sizeof_priv: size of private data to allocate space for * @name: device name format string * @setup: callback to initialize device - * @queue_count: the number of subqueues to allocate + * @txqs: the number of TX subqueues to allocate + * @rxqs: the number of RX subqueues to allocate * * Allocates a struct net_device with private data area for driver use * and performs basic initialization. Also allocates subquue structs - * for each queue on the device at the end of the netdevice. + * for each queue on the device. */ -struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, - void (*setup)(struct net_device *), unsigned int queue_count) +struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, + void (*setup)(struct net_device *), + unsigned int txqs, unsigned int rxqs) { - struct netdev_queue *tx; struct net_device *dev; size_t alloc_size; struct net_device *p; -#ifdef CONFIG_RPS - struct netdev_rx_queue *rx; - int i; -#endif BUG_ON(strlen(name) >= sizeof(dev->name)); + if (txqs < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero queues.\n"); + return NULL; + } + +#ifdef CONFIG_RPS + if (rxqs < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero RX queues.\n"); + return NULL; + } +#endif + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5408,55 +5649,23 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, return NULL; } - tx = kcalloc(queue_count, sizeof(struct netdev_queue), GFP_KERNEL); - if (!tx) { - printk(KERN_ERR "alloc_netdev: Unable to allocate " - "tx qdiscs.\n"); - goto free_p; - } - -#ifdef CONFIG_RPS - rx = kcalloc(queue_count, sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!rx) { - printk(KERN_ERR "alloc_netdev: Unable to allocate " - "rx queues.\n"); - goto free_tx; - } - - atomic_set(&rx->count, queue_count); - - /* - * Set a pointer to first element in the array which holds the - * reference count. - */ - for (i = 0; i < queue_count; i++) - rx[i].first = rx; -#endif - dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; + dev->pcpu_refcnt = alloc_percpu(int); + if (!dev->pcpu_refcnt) + goto free_p; + if (dev_addr_init(dev)) - goto free_rx; + goto free_pcpu; dev_mc_init(dev); dev_uc_init(dev); dev_net_set(dev, &init_net); - dev->_tx = tx; - dev->num_tx_queues = queue_count; - dev->real_num_tx_queues = queue_count; - -#ifdef CONFIG_RPS - dev->_rx = rx; - dev->num_rx_queues = queue_count; -#endif - dev->gso_max_size = GSO_MAX_SIZE; - netdev_init_queues(dev); - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); @@ -5464,20 +5673,38 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, INIT_LIST_HEAD(&dev->link_watch_list); dev->priv_flags = IFF_XMIT_DST_RELEASE; setup(dev); + + dev->num_tx_queues = txqs; + dev->real_num_tx_queues = txqs; + if (netif_alloc_netdev_queues(dev)) + goto free_all; + +#ifdef CONFIG_RPS + dev->num_rx_queues = rxqs; + dev->real_num_rx_queues = rxqs; + if (netif_alloc_rx_queues(dev)) + goto free_all; +#endif + strcpy(dev->name, name); return dev; -free_rx: +free_all: + free_netdev(dev); + return NULL; + +free_pcpu: + free_percpu(dev->pcpu_refcnt); + kfree(dev->_tx); #ifdef CONFIG_RPS - kfree(rx); -free_tx: + kfree(dev->_rx); #endif - kfree(tx); + free_p: kfree(p); return NULL; } -EXPORT_SYMBOL(alloc_netdev_mq); +EXPORT_SYMBOL(alloc_netdev_mqs); /** * free_netdev - free network device @@ -5494,6 +5721,11 @@ 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)); /* Flush device addresses */ dev_addr_flush(dev); @@ -5504,6 +5736,9 @@ void free_netdev(struct net_device *dev) list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); + free_percpu(dev->pcpu_refcnt); + dev->pcpu_refcnt = NULL; + /* Compatibility with error handling in drivers */ if (dev->reg_state == NETREG_UNINITIALIZED) { kfree((char *)dev - dev->padded); @@ -5658,6 +5893,10 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* Notify protocols, that we are about to destroy this device. They should clean all the things. + + Note that dev->reg_state stays at NETREG_REGISTERED. + This is wanted because this way 8021q and macvlan know + the device is just moving and can keep their slaves up. */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); @@ -5963,7 +6202,7 @@ static void __net_exit default_device_exit(struct net *net) static void __net_exit default_device_exit_batch(struct list_head *net_list) { /* At exit all network devices most be removed from a network - * namespace. Do this in the reverse order of registeration. + * namespace. Do this in the reverse order of registration. * Do this across as many network namespaces as possible to * improve batching efficiency. */ @@ -5981,6 +6220,7 @@ static void __net_exit default_device_exit_batch(struct list_head *net_list) } } unregister_netdevice_many(&dev_kill_list); + list_del(&dev_kill_list); rtnl_unlock(); } |