diff options
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/Makefile | 2 | ||||
-rw-r--r-- | net/core/datagram.c | 14 | ||||
-rw-r--r-- | net/core/dev.c | 1001 | ||||
-rw-r--r-- | net/core/drop_monitor.c | 33 | ||||
-rw-r--r-- | net/core/dst.c | 41 | ||||
-rw-r--r-- | net/core/ethtool.c | 203 | ||||
-rw-r--r-- | net/core/fib_rules.c | 37 | ||||
-rw-r--r-- | net/core/filter.c | 226 | ||||
-rw-r--r-- | net/core/flow.c | 91 | ||||
-rw-r--r-- | net/core/gen_estimator.c | 17 | ||||
-rw-r--r-- | net/core/gen_stats.c | 14 | ||||
-rw-r--r-- | net/core/iovec.c | 32 | ||||
-rw-r--r-- | net/core/link_watch.c | 1 | ||||
-rw-r--r-- | net/core/neighbour.c | 486 | ||||
-rw-r--r-- | net/core/net-sysfs.c | 78 | ||||
-rw-r--r-- | net/core/net-sysfs.h | 4 | ||||
-rw-r--r-- | net/core/net-traces.c | 1 | ||||
-rw-r--r-- | net/core/net_namespace.c | 4 | ||||
-rw-r--r-- | net/core/netevent.c | 5 | ||||
-rw-r--r-- | net/core/netpoll.c | 186 | ||||
-rw-r--r-- | net/core/pktgen.c | 261 | ||||
-rw-r--r-- | net/core/rtnetlink.c | 50 | ||||
-rw-r--r-- | net/core/scm.c | 33 | ||||
-rw-r--r-- | net/core/skbuff.c | 115 | ||||
-rw-r--r-- | net/core/sock.c | 68 | ||||
-rw-r--r-- | net/core/stream.c | 14 | ||||
-rw-r--r-- | net/core/sysctl_net_core.c | 3 | ||||
-rw-r--r-- | net/core/timestamping.c | 126 | ||||
-rw-r--r-- | net/core/utils.c | 18 |
29 files changed, 1975 insertions, 1189 deletions
diff --git a/net/core/Makefile b/net/core/Makefile index 51c3eec850ef..8a04dd22cf77 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -18,4 +18,4 @@ obj-$(CONFIG_NET_DMA) += user_dma.o obj-$(CONFIG_FIB_RULES) += fib_rules.o obj-$(CONFIG_TRACEPOINTS) += net-traces.o obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o - +obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o diff --git a/net/core/datagram.c b/net/core/datagram.c index f5b6f43a4c2e..cd1e039c8755 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -219,6 +219,7 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned flags, return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), &peeked, err); } +EXPORT_SYMBOL(skb_recv_datagram); void skb_free_datagram(struct sock *sk, struct sk_buff *skb) { @@ -242,6 +243,7 @@ void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb) unlock_sock_fast(sk, slow); /* skb is now orphaned, can be freed outside of locked section */ + trace_kfree_skb(skb, skb_free_datagram_locked); __kfree_skb(skb); } EXPORT_SYMBOL(skb_free_datagram_locked); @@ -288,7 +290,6 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) return err; } - EXPORT_SYMBOL(skb_kill_datagram); /** @@ -373,6 +374,7 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, fault: return -EFAULT; } +EXPORT_SYMBOL(skb_copy_datagram_iovec); /** * skb_copy_datagram_const_iovec - Copy a datagram to an iovec. @@ -716,6 +718,7 @@ csum_error: fault: return -EFAULT; } +EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); /** * datagram_poll - generic datagram poll @@ -744,13 +747,12 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) mask |= POLLERR; if (sk->sk_shutdown & RCV_SHUTDOWN) - mask |= POLLRDHUP; + mask |= POLLRDHUP | POLLIN | POLLRDNORM; if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= POLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || - (sk->sk_shutdown & RCV_SHUTDOWN)) + if (!skb_queue_empty(&sk->sk_receive_queue)) mask |= POLLIN | POLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -770,8 +772,4 @@ unsigned int datagram_poll(struct file *file, struct socket *sock, return mask; } - EXPORT_SYMBOL(datagram_poll); -EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec); -EXPORT_SYMBOL(skb_copy_datagram_iovec); -EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index 1f466e82ac33..35dfb8318483 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -101,8 +101,6 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/stat.h> -#include <linux/if_bridge.h> -#include <linux/if_macvlan.h> #include <net/dst.h> #include <net/pkt_sched.h> #include <net/checksum.h> @@ -130,7 +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" @@ -373,6 +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 @@ -388,16 +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); @@ -416,15 +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) { @@ -435,7 +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); @@ -803,35 +802,31 @@ struct net_device *dev_getfirstbyhwtype(struct net *net, unsigned short type) EXPORT_SYMBOL(dev_getfirstbyhwtype); /** - * dev_get_by_flags - find any device with given flags + * dev_get_by_flags_rcu - find any device with given flags * @net: the applicable net namespace * @if_flags: IFF_* values * @mask: bitmask of bits in if_flags to check * * Search for any interface with the given flags. Returns NULL if a device - * is not found or a pointer to the device. The device returned has - * had a reference added and the pointer is safe until the user calls - * dev_put to indicate they have finished with it. + * is not found or a pointer to the device. Must be called inside + * rcu_read_lock(), and result refcount is unchanged. */ -struct net_device *dev_get_by_flags(struct net *net, unsigned short if_flags, +struct net_device *dev_get_by_flags_rcu(struct net *net, unsigned short if_flags, unsigned short mask) { struct net_device *dev, *ret; ret = NULL; - rcu_read_lock(); for_each_netdev_rcu(net, dev) { if (((dev->flags ^ if_flags) & mask) == 0) { - dev_hold(dev); ret = dev; break; } } - rcu_read_unlock(); return ret; } -EXPORT_SYMBOL(dev_get_by_flags); +EXPORT_SYMBOL(dev_get_by_flags_rcu); /** * dev_valid_name - check if name is okay for network device @@ -1490,8 +1485,9 @@ 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; } @@ -1542,7 +1538,8 @@ static void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) if (net_ratelimit()) printk(KERN_CRIT "protocol %04x is " "buggy, dev %s\n", - skb2->protocol, dev->name); + ntohs(skb2->protocol), + dev->name); skb_reset_network_header(skb2); } @@ -1558,21 +1555,56 @@ 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; + if (txq < 1 || txq > dev->num_tx_queues) + return -EINVAL; + + if (dev->reg_state == NETREG_REGISTERED) { + ASSERT_RTNL(); - 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; @@ -1653,10 +1685,10 @@ 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) && + return ((features & NETIF_F_NO_CSUM) || + ((features & NETIF_F_V4_CSUM) && protocol == htons(ETH_P_IP)) || - ((features & NETIF_F_IPV6_CSUM) && + ((features & NETIF_F_V6_CSUM) && protocol == htons(ETH_P_IPV6)) || ((features & NETIF_F_FCOE_CRC) && protocol == htons(ETH_P_FCOE))); @@ -1664,17 +1696,18 @@ static bool can_checksum_protocol(unsigned long features, __be16 protocol) static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) { - if (can_checksum_protocol(dev->features, skb->protocol)) - return true; + __be16 protocol = skb->protocol; + int features = dev->features; - if (skb->protocol == htons(ETH_P_8021Q)) { + if (vlan_tx_tag_present(skb)) { + features &= dev->vlan_features; + } else if (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; + protocol = veh->h_vlan_encapsulated_proto; + features &= dev->vlan_features; } - return false; + return can_checksum_protocol(features, protocol); } /** @@ -1763,6 +1796,16 @@ struct sk_buff *skb_gso_segment(struct sk_buff *skb, int features) __be16 type = skb->protocol; int err; + if (type == htons(ETH_P_8021Q)) { + struct vlan_ethhdr *veh; + + if (unlikely(!pskb_may_pull(skb, VLAN_ETH_HLEN))) + return ERR_PTR(-EINVAL); + + veh = (struct vlan_ethhdr *)skb->data; + type = veh->h_vlan_encapsulated_proto; + } + skb_reset_mac_header(skb); skb->mac_len = skb->network_header - skb->mac_header; __skb_pull(skb, skb->mac_len); @@ -1907,14 +1950,14 @@ 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 */ @@ -1924,6 +1967,27 @@ static inline void skb_orphan_try(struct sk_buff *skb) } } +/* + * Returns true if either: + * 1. skb has frag_list and the device doesn't support FRAGLIST, or + * 2. skb is fragmented and the device does not support SG, or if + * at least one of fragments is in highmem and device does not + * support DMA from it. + */ +static inline int skb_needs_linearize(struct sk_buff *skb, + struct net_device *dev) +{ + int features = dev->features; + + if (skb->protocol == htons(ETH_P_8021Q) || 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)))); +} + int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, struct netdev_queue *txq) { @@ -1943,14 +2007,40 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, skb_orphan_try(skb); + if (vlan_tx_tag_present(skb) && + !(dev->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(dev, skb)) { if (unlikely(dev_gso_segment(skb))) goto out_kfree_skb; if (skb->next) goto gso; + } else { + if (skb_needs_linearize(skb, dev) && + __skb_linearize(skb)) + goto out_kfree_skb; + + /* If packet is not checksummed and device does not + * support checksumming for this protocol, complete + * 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_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; @@ -1971,6 +2061,7 @@ 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; @@ -1988,6 +2079,7 @@ out_kfree_gso_skb: skb->destructor = DEV_GSO_CB(skb)->destructor; out_kfree_skb: kfree_skb(skb); +out: return rc; } @@ -2031,16 +2123,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { int queue_index; - struct sock *sk = skb->sk; + const struct net_device_ops *ops = dev->netdev_ops; - queue_index = sk_tx_queue_get(sk); - if (queue_index < 0) { - const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + struct sock *sk = skb->sk; + queue_index = sk_tx_queue_get(sk); + if (queue_index < 0) { - if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { queue_index = 0; if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); @@ -2063,14 +2155,24 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, struct netdev_queue *txq) { spinlock_t *root_lock = qdisc_lock(q); + bool contended = qdisc_is_running(q); int rc; + /* + * Heuristic to force contended enqueues to serialize on a + * separate lock before trying to get qdisc main lock. + * This permits __QDISC_STATE_RUNNING owner to get the lock more often + * and dequeue packets faster. + */ + if (unlikely(contended)) + spin_lock(&q->busylock); + spin_lock(root_lock); if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, &q->state))) { kfree_skb(skb); rc = NET_XMIT_DROP; } else if ((q->flags & TCQ_F_CAN_BYPASS) && !qdisc_qlen(q) && - !test_and_set_bit(__QDISC_STATE_RUNNING, &q->state)) { + qdisc_run_begin(q)) { /* * This is a work-conserving queue; there are no old skbs * waiting to be sent out; and the qdisc is not running - @@ -2079,36 +2181,35 @@ 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); - if (sch_direct_xmit(skb, q, dev, txq, root_lock)) + if (sch_direct_xmit(skb, q, dev, txq, root_lock)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } __qdisc_run(q); - else - clear_bit(__QDISC_STATE_RUNNING, &q->state); + } else + qdisc_run_end(q); rc = NET_XMIT_SUCCESS; } else { skb_dst_force(skb); rc = qdisc_enqueue_root(skb, q); - qdisc_run(q); + if (qdisc_run_begin(q)) { + if (unlikely(contended)) { + spin_unlock(&q->busylock); + contended = false; + } + __qdisc_run(q); + } } spin_unlock(root_lock); - + if (unlikely(contended)) + spin_unlock(&q->busylock); return rc; } -/* - * Returns true if either: - * 1. skb has frag_list and the device doesn't support FRAGLIST, or - * 2. skb is fragmented and the device does not support SG, or if - * at least one of fragments is in highmem and device does not - * support DMA from it. - */ -static inline int skb_needs_linearize(struct sk_buff *skb, - struct net_device *dev) -{ - return (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST)) || - (skb_shinfo(skb)->nr_frags && (!(dev->features & NETIF_F_SG) || - illegal_highdma(dev, skb))); -} +static DEFINE_PER_CPU(int, xmit_recursion); +#define RECURSION_LIMIT 10 /** * dev_queue_xmit - transmit a buffer @@ -2142,25 +2243,6 @@ int dev_queue_xmit(struct sk_buff *skb) struct Qdisc *q; int rc = -ENOMEM; - /* GSO will handle the following emulations directly. */ - if (netif_needs_gso(dev, skb)) - goto gso; - - /* Convert a paged skb to linear, if required */ - if (skb_needs_linearize(skb, dev) && __skb_linearize(skb)) - goto out_kfree_skb; - - /* If packet is not checksummed and device does not support - * checksumming for this protocol, complete 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_checksum_help(skb)) - goto out_kfree_skb; - } - -gso: /* Disable soft irqs for various locks below. Also * stops preemption for RCU. */ @@ -2172,6 +2254,7 @@ gso: #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; @@ -2194,10 +2277,15 @@ gso: 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; @@ -2209,7 +2297,9 @@ gso: "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); @@ -2219,7 +2309,6 @@ gso: rc = -ENETDOWN; rcu_read_unlock_bh(); -out_kfree_skb: kfree_skb(skb); return rc; out: @@ -2246,69 +2335,44 @@ 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]; @@ -2317,33 +2381,81 @@ 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) { + 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) { @@ -2383,7 +2495,6 @@ got_hash: } } - map = rcu_dereference(rxqueue->rps_map); if (map) { tcpu = map->cpus[((u64) skb->rxhash * map->len) >> 32]; @@ -2469,6 +2580,7 @@ enqueue: local_irq_restore(flags); + atomic_long_inc(&skb->dev->rx_dropped); kfree_skb(skb); return NET_RX_DROP; } @@ -2499,11 +2611,13 @@ 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; int cpu; + preempt_disable(); rcu_read_lock(); cpu = get_rps_cpu(skb->dev, skb, &rflow); @@ -2513,6 +2627,7 @@ int netif_rx(struct sk_buff *skb) ret = enqueue_to_backlog(skb, cpu, &rflow->last_qtail); rcu_read_unlock(); + preempt_enable(); } #else { @@ -2556,6 +2671,7 @@ 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); } } @@ -2604,70 +2720,14 @@ static inline int deliver_skb(struct sk_buff *skb, return pt_prev->func(skb, skb->dev, pt_prev, orig_dev); } -#if defined(CONFIG_BRIDGE) || defined (CONFIG_BRIDGE_MODULE) - -#if defined(CONFIG_ATM_LANE) || defined(CONFIG_ATM_LANE_MODULE) +#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 */ int (*br_fdb_test_addr_hook)(struct net_device *dev, unsigned char *addr) __read_mostly; EXPORT_SYMBOL_GPL(br_fdb_test_addr_hook); #endif -/* - * If bridge module is loaded call bridging hook. - * returns NULL if packet was consumed. - */ -struct sk_buff *(*br_handle_frame_hook)(struct net_bridge_port *p, - struct sk_buff *skb) __read_mostly; -EXPORT_SYMBOL_GPL(br_handle_frame_hook); - -static inline struct sk_buff *handle_bridge(struct sk_buff *skb, - struct packet_type **pt_prev, int *ret, - struct net_device *orig_dev) -{ - struct net_bridge_port *port; - - if (skb->pkt_type == PACKET_LOOPBACK || - (port = rcu_dereference(skb->dev->br_port)) == NULL) - return skb; - - if (*pt_prev) { - *ret = deliver_skb(skb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - - return br_handle_frame_hook(port, skb); -} -#else -#define handle_bridge(skb, pt_prev, ret, orig_dev) (skb) -#endif - -#if defined(CONFIG_MACVLAN) || defined(CONFIG_MACVLAN_MODULE) -struct sk_buff *(*macvlan_handle_frame_hook)(struct macvlan_port *p, - struct sk_buff *skb) __read_mostly; -EXPORT_SYMBOL_GPL(macvlan_handle_frame_hook); - -static inline struct sk_buff *handle_macvlan(struct sk_buff *skb, - struct packet_type **pt_prev, - int *ret, - struct net_device *orig_dev) -{ - struct macvlan_port *port; - - port = rcu_dereference(skb->dev->macvlan_port); - if (!port) - return skb; - - if (*pt_prev) { - *ret = deliver_skb(skb, *pt_prev, orig_dev); - *pt_prev = NULL; - } - return macvlan_handle_frame_hook(port, skb); -} -#else -#define handle_macvlan(skb, pt_prev, ret, orig_dev) (skb) -#endif - #ifdef CONFIG_NET_CLS_ACT /* TODO: Maybe we should just force sch_ingress to be compiled in * when CONFIG_NET_CLS_ACT is? otherwise some useless instructions @@ -2677,26 +2737,23 @@ static inline struct sk_buff *handle_macvlan(struct sk_buff *skb, * 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; - if (MAX_RED_LOOP < ttl++) { - printk(KERN_WARNING - "Redir loop detected Dropping packet (%d->%d)\n", - skb->skb_iif, dev->ifindex); + if (unlikely(MAX_RED_LOOP < ttl++)) { + if (net_ratelimit()) + pr_warning( "Redir loop detected Dropping packet (%d->%d)\n", + skb->skb_iif, dev->ifindex); return TC_ACT_SHOT; } 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)); @@ -2712,18 +2769,17 @@ 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) { *ret = deliver_skb(skb, *pt_prev, orig_dev); *pt_prev = NULL; - } else { - /* Huh? Why does turning on AF_PACKET affect this? */ - skb->tc_verd = SET_TC_OK2MUNGE(skb->tc_verd); } - switch (ing_filter(skb)) { + switch (ing_filter(skb, rxq)) { case TC_ACT_SHOT: case TC_ACT_STOLEN: kfree_skb(skb); @@ -2736,32 +2792,50 @@ out: } #endif -/* - * netif_nit_deliver - deliver received packets to network taps - * @skb: buffer +/** + * netdev_rx_handler_register - register receive handler + * @dev: device to register a handler for + * @rx_handler: receive handler to register + * @rx_handler_data: data pointer that is used by rx handler + * + * Register a receive hander for a device. This handler will then be + * called from __netif_receive_skb. A negative errno code is returned + * on a failure. * - * 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. + * The caller must hold the rtnl_mutex. */ -void netif_nit_deliver(struct sk_buff *skb) +int netdev_rx_handler_register(struct net_device *dev, + rx_handler_func_t *rx_handler, + void *rx_handler_data) { - struct packet_type *ptype; + ASSERT_RTNL(); - if (list_empty(&ptype_all)) - return; + if (dev->rx_handler) + return -EBUSY; - skb_reset_network_header(skb); - skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + rcu_assign_pointer(dev->rx_handler_data, rx_handler_data); + rcu_assign_pointer(dev->rx_handler, rx_handler); - 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(); + return 0; +} +EXPORT_SYMBOL_GPL(netdev_rx_handler_register); + +/** + * netdev_rx_handler_unregister - unregister receive handler + * @dev: device to unregister a handler from + * + * Unregister a receive hander from a device. + * + * The caller must hold the rtnl_mutex. + */ +void netdev_rx_handler_unregister(struct net_device *dev) +{ + + ASSERT_RTNL(); + rcu_assign_pointer(dev->rx_handler, NULL); + rcu_assign_pointer(dev->rx_handler_data, NULL); } +EXPORT_SYMBOL_GPL(netdev_rx_handler_unregister); static inline void skb_bond_set_mac_by_master(struct sk_buff *skb, struct net_device *master) @@ -2784,7 +2858,8 @@ int __skb_bond_should_drop(struct sk_buff *skb, struct net_device *master) if (master->priv_flags & IFF_MASTER_ARPMON) dev->last_rx = jiffies; - if ((master->priv_flags & IFF_MASTER_ALB) && master->br_port) { + if ((master->priv_flags & IFF_MASTER_ALB) && + (master->priv_flags & IFF_BRIDGE_PORT)) { /* Do address unmangle. The local destination address * will be always the one master has. Provides the right * functionality in a bridge. @@ -2815,6 +2890,7 @@ EXPORT_SYMBOL(__skb_bond_should_drop); static int __netif_receive_skb(struct sk_buff *skb) { struct packet_type *ptype, *pt_prev; + rx_handler_func_t *rx_handler; struct net_device *orig_dev; struct net_device *master; struct net_device *null_or_orig; @@ -2825,8 +2901,7 @@ 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)) @@ -2840,8 +2915,7 @@ 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; @@ -2856,8 +2930,7 @@ static int __netif_receive_skb(struct sk_buff *skb) skb->dev = master; } - __get_cpu_var(softnet_data).processed++; - + __this_cpu_inc(softnet_data.processed); skb_reset_network_header(skb); skb_reset_transport_header(skb); skb->mac_len = skb->network_header - skb->mac_header; @@ -2889,12 +2962,29 @@ static int __netif_receive_skb(struct sk_buff *skb) ncls: #endif - skb = handle_bridge(skb, &pt_prev, &ret, orig_dev); - if (!skb) - goto out; - skb = handle_macvlan(skb, &pt_prev, &ret, orig_dev); - if (!skb) - goto out; + /* Handle special case of bridge or macvlan */ + rx_handler = rcu_dereference(skb->dev->rx_handler); + if (rx_handler) { + if (pt_prev) { + ret = deliver_skb(skb, pt_prev, orig_dev); + pt_prev = NULL; + } + skb = rx_handler(skb); + if (!skb) + 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 @@ -2923,6 +3013,7 @@ 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. :-) @@ -2955,6 +3046,9 @@ int netif_receive_skb(struct sk_buff *skb) if (netdev_tstamp_prequeue) net_timestamp_check(skb); + if (skb_defer_rx_timestamp(skb)) + return NET_RX_SUCCESS; + #ifdef CONFIG_RPS { struct rps_dev_flow voidflow, *rflow = &voidflow; @@ -3040,7 +3134,7 @@ 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; @@ -3053,6 +3147,7 @@ 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) { @@ -3064,10 +3159,10 @@ enum gro_result dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) int mac_len; enum gro_result ret; - if (!(skb->dev->features & NETIF_F_GRO)) + 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(); @@ -3133,7 +3228,7 @@ pull: put_page(skb_shinfo(skb)->frags[0].page); memmove(skb_shinfo(skb)->frags, skb_shinfo(skb)->frags + 1, - --skb_shinfo(skb)->nr_frags); + --skb_shinfo(skb)->nr_frags * sizeof(skb_frag_t)); } } @@ -3146,19 +3241,19 @@ 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; - if (netpoll_rx_on(skb)) - return GRO_NORMAL; - for (p = napi->gro_list; p; p = p->next) { - NAPI_GRO_CB(p)->same_flow = - (p->dev == skb->dev) && - !compare_ether_header(skb_mac_header(p), + 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; } @@ -3211,14 +3306,14 @@ 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; napi->skb = skb; } -EXPORT_SYMBOL(napi_reuse_skb); struct sk_buff *napi_get_frags(struct napi_struct *napi) { @@ -3719,10 +3814,11 @@ void dev_seq_stop(struct seq_file *seq, void *v) static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { - const struct net_device_stats *stats = dev_get_stats(dev); + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); - seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " - "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", + seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu " + "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, stats->rx_dropped + stats->rx_missed_errors, @@ -4837,7 +4933,7 @@ static void rollback_registered_many(struct list_head *head) dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); - synchronize_net(); + rcu_barrier(); list_for_each_entry(dev, head, unreg_list) dev_put(dev); @@ -4851,21 +4947,6 @@ static void rollback_registered(struct net_device *dev) 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); -} - unsigned long netdev_fix_features(unsigned long features, const char *name) { /* Fix illegal SG+CSUM combinations. */ @@ -4933,6 +5014,66 @@ void netif_stacked_transfer_operstate(const struct net_device *rootdev, } EXPORT_SYMBOL(netif_stacked_transfer_operstate); +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; + + 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; + + /* + * 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 + return 0; +} + +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; + 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); +} + /** * register_netdevice - register a network device * @dev: device to register @@ -4966,28 +5107,19 @@ 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 - */ + ret = netif_alloc_rx_queues(dev); + if (ret) + goto out; - dev->_rx = kzalloc(sizeof(struct netdev_rx_queue), GFP_KERNEL); - if (!dev->_rx) { - ret = -ENOMEM; - goto out; - } + ret = netif_alloc_netdev_queues(dev); + if (ret) + goto out; + + netdev_init_queues(dev); - 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); @@ -5027,6 +5159,12 @@ 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) @@ -5097,9 +5235,6 @@ 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); @@ -5107,6 +5242,11 @@ 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); @@ -5148,6 +5288,16 @@ 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. * @@ -5162,11 +5312,14 @@ 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(); @@ -5193,11 +5346,13 @@ 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; } } @@ -5255,9 +5410,9 @@ 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) @@ -5271,20 +5426,22 @@ void netdev_run_todo(void) /** * dev_txq_stats_fold - fold tx_queues stats * @dev: device to get statistics from - * @stats: struct net_device_stats to hold results + * @stats: struct rtnl_link_stats64 to hold results */ void dev_txq_stats_fold(const struct net_device *dev, - struct net_device_stats *stats) + struct rtnl_link_stats64 *stats) { - unsigned long tx_bytes = 0, tx_packets = 0, tx_dropped = 0; + 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; @@ -5294,38 +5451,72 @@ void dev_txq_stats_fold(const struct net_device *dev, } 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. + */ +static void netdev_stats_to_stats64(struct rtnl_link_stats64 *stats64, + const struct net_device_stats *netdev_stats) +{ +#if BITS_PER_LONG == 64 + BUILD_BUG_ON(sizeof(*stats64) != sizeof(*netdev_stats)); + memcpy(stats64, netdev_stats, sizeof(*stats64)); +#else + size_t i, n = sizeof(*stats64) / sizeof(u64); + const unsigned long *src = (const unsigned long *)netdev_stats; + u64 *dst = (u64 *)stats64; + + BUILD_BUG_ON(sizeof(*netdev_stats) / sizeof(unsigned long) != + sizeof(*stats64) / sizeof(u64)); + for (i = 0; i < n; i++) + dst[i] = src[i]; +#endif +} + /** * dev_get_stats - get network device statistics * @dev: device to get statistics from + * @storage: place to store stats * - * Get network statistics from device. The device driver may provide - * its own method by setting dev->netdev_ops->get_stats; otherwise - * the internal statistics structure is used. + * Get network statistics from device. Return @storage. + * The device driver may provide its own method by setting + * dev->netdev_ops->get_stats64 or dev->netdev_ops->get_stats; + * otherwise the internal statistics structure is used. */ -const struct net_device_stats *dev_get_stats(struct net_device *dev) +struct rtnl_link_stats64 *dev_get_stats(struct net_device *dev, + struct rtnl_link_stats64 *storage) { const struct net_device_ops *ops = dev->netdev_ops; - if (ops->ndo_get_stats) - return ops->ndo_get_stats(dev); - - dev_txq_stats_fold(dev, &dev->stats); - return &dev->stats; + if (ops->ndo_get_stats64) { + memset(storage, 0, sizeof(*storage)); + ops->ndo_get_stats64(dev, storage); + } else if (ops->ndo_get_stats) { + netdev_stats_to_stats64(storage, ops->ndo_get_stats(dev)); + } else { + 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; } /** @@ -5342,17 +5533,18 @@ static void netdev_init_queues(struct net_device *dev) struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, void (*setup)(struct net_device *), unsigned int queue_count) { - 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 (queue_count < 1) { + pr_err("alloc_netdev: Unable to allocate device " + "with zero queues.\n"); + return NULL; + } + alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ @@ -5368,55 +5560,31 @@ 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; + dev->real_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); @@ -5427,12 +5595,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, strcpy(dev->name, name); return dev; -free_rx: -#ifdef CONFIG_RPS - kfree(rx); -free_tx: -#endif - kfree(tx); +free_pcpu: + free_percpu(dev->pcpu_refcnt); free_p: kfree(p); return NULL; @@ -5455,6 +5619,8 @@ void free_netdev(struct net_device *dev) kfree(dev->_tx); + kfree(rcu_dereference_raw(dev->ingress_queue)); + /* Flush device addresses */ dev_addr_flush(dev); @@ -5464,6 +5630,9 @@ 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); @@ -5618,6 +5787,10 @@ 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); @@ -5815,6 +5988,68 @@ char *netdev_drivername(const struct net_device *dev, char *buffer, int len) return buffer; } +static int __netdev_printk(const char *level, const struct net_device *dev, + struct va_format *vaf) +{ + int r; + + if (dev && dev->dev.parent) + r = dev_printk(level, dev->dev.parent, "%s: %pV", + netdev_name(dev), vaf); + else if (dev) + r = printk("%s%s: %pV", level, netdev_name(dev), vaf); + else + r = printk("%s(NULL net_device): %pV", level, vaf); + + return r; +} + +int netdev_printk(const char *level, const struct net_device *dev, + const char *format, ...) +{ + struct va_format vaf; + va_list args; + int r; + + va_start(args, format); + + vaf.fmt = format; + vaf.va = &args; + + r = __netdev_printk(level, dev, &vaf); + va_end(args); + + return r; +} +EXPORT_SYMBOL(netdev_printk); + +#define define_netdev_printk_level(func, level) \ +int func(const struct net_device *dev, const char *fmt, ...) \ +{ \ + int r; \ + struct va_format vaf; \ + va_list args; \ + \ + va_start(args, fmt); \ + \ + vaf.fmt = fmt; \ + vaf.va = &args; \ + \ + r = __netdev_printk(level, dev, &vaf); \ + va_end(args); \ + \ + return r; \ +} \ +EXPORT_SYMBOL(func); + +define_netdev_printk_level(netdev_emerg, KERN_EMERG); +define_netdev_printk_level(netdev_alert, KERN_ALERT); +define_netdev_printk_level(netdev_crit, KERN_CRIT); +define_netdev_printk_level(netdev_err, KERN_ERR); +define_netdev_printk_level(netdev_warn, KERN_WARNING); +define_netdev_printk_level(netdev_notice, KERN_NOTICE); +define_netdev_printk_level(netdev_info, KERN_INFO); + static void __net_exit netdev_exit(struct net *net) { kfree(net->dev_name_head); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index ad41529fb60f..36e603c78ce9 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -223,6 +223,11 @@ static int set_all_monitor_traces(int state) spin_lock(&trace_state_lock); + if (state == trace_state) { + rc = -EAGAIN; + goto out_unlock; + } + switch (state) { case TRACE_ON: rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL); @@ -251,11 +256,12 @@ static int set_all_monitor_traces(int state) if (!rc) trace_state = state; + else + rc = -EINPROGRESS; +out_unlock: spin_unlock(&trace_state_lock); - if (rc) - return -EINPROGRESS; return rc; } @@ -341,9 +347,9 @@ static struct notifier_block dropmon_net_notifier = { static int __init init_net_drop_monitor(void) { - int cpu; - int rc, i, ret; struct per_cpu_dm_data *data; + int cpu, rc; + printk(KERN_INFO "Initalizing network drop monitor service\n"); if (sizeof(void *) > 8) { @@ -351,21 +357,12 @@ static int __init init_net_drop_monitor(void) return -ENOSPC; } - if (genl_register_family(&net_drop_monitor_family) < 0) { + rc = genl_register_family_with_ops(&net_drop_monitor_family, + dropmon_ops, + ARRAY_SIZE(dropmon_ops)); + if (rc) { printk(KERN_ERR "Could not create drop monitor netlink family\n"); - return -EFAULT; - } - - rc = -EFAULT; - - for (i = 0; i < ARRAY_SIZE(dropmon_ops); i++) { - ret = genl_register_ops(&net_drop_monitor_family, - &dropmon_ops[i]); - if (ret) { - printk(KERN_CRIT "Failed to register operation %d\n", - dropmon_ops[i].cmd); - goto out_unreg; - } + return rc; } rc = register_netdevice_notifier(&dropmon_net_notifier); diff --git a/net/core/dst.c b/net/core/dst.c index 9920722cc82b..8abe628b79f1 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -168,7 +168,7 @@ void *dst_alloc(struct dst_ops *ops) { struct dst_entry *dst; - if (ops->gc && atomic_read(&ops->entries) > ops->gc_thresh) { + if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { if (ops->gc(ops)) return NULL; } @@ -183,7 +183,7 @@ void *dst_alloc(struct dst_ops *ops) #if RT_CACHE_DEBUG >= 2 atomic_inc(&dst_total); #endif - atomic_inc(&ops->entries); + dst_entries_add(ops, 1); return dst; } EXPORT_SYMBOL(dst_alloc); @@ -197,7 +197,6 @@ static void ___dst_free(struct dst_entry *dst) dst->input = dst->output = dst_discard; dst->obsolete = 2; } -EXPORT_SYMBOL(__dst_free); void __dst_free(struct dst_entry *dst) { @@ -213,6 +212,7 @@ void __dst_free(struct dst_entry *dst) } spin_unlock_bh(&dst_garbage.lock); } +EXPORT_SYMBOL(__dst_free); struct dst_entry *dst_destroy(struct dst_entry * dst) { @@ -228,15 +228,15 @@ again: child = dst->child; dst->hh = NULL; - if (hh && atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); + if (hh) + hh_cache_put(hh); if (neigh) { dst->neighbour = NULL; neigh_release(neigh); } - atomic_dec(&dst->ops->entries); + dst_entries_add(dst->ops, -1); if (dst->ops->destroy) dst->ops->destroy(dst); @@ -271,13 +271,40 @@ void dst_release(struct dst_entry *dst) if (dst) { int newrefcnt; - smp_mb__before_atomic_dec(); newrefcnt = atomic_dec_return(&dst->__refcnt); WARN_ON(newrefcnt < 0); + if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt) { + dst = dst_destroy(dst); + if (dst) + __dst_free(dst); + } } } EXPORT_SYMBOL(dst_release); +/** + * skb_dst_set_noref - sets skb dst, without a reference + * @skb: buffer + * @dst: dst entry + * + * Sets skb dst, assuming a reference was not taken on dst + * skb_dst_drop() should not dst_release() this dst + */ +void skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst) +{ + WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held()); + /* If dst not in cache, we must take a reference, because + * dst_release() will destroy dst as soon as its refcount becomes zero + */ + if (unlikely(dst->flags & DST_NOCACHE)) { + dst_hold(dst); + skb_dst_set(skb, dst); + } else { + skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF; + } +} +EXPORT_SYMBOL(skb_dst_set_noref); + /* Dirty hack. We did it in 2.2 (in __dst_free), * we have _very_ good reasons not to repeat * this mistake in 2.3, but we have no choice diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 75e4ffeb8cc9..956a9f4971cb 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -19,6 +19,7 @@ #include <linux/netdevice.h> #include <linux/bitops.h> #include <linux/uaccess.h> +#include <linux/vmalloc.h> #include <linux/slab.h> /* @@ -131,7 +132,8 @@ EXPORT_SYMBOL(ethtool_op_set_ufo); * NETIF_F_xxx values in include/linux/netdevice.h */ static const u32 flags_dup_features = - (ETH_FLAG_LRO | ETH_FLAG_NTUPLE | ETH_FLAG_RXHASH); + (ETH_FLAG_LRO | ETH_FLAG_RXVLAN | ETH_FLAG_TXVLAN | ETH_FLAG_NTUPLE | + ETH_FLAG_RXHASH); u32 ethtool_op_get_flags(struct net_device *dev) { @@ -144,31 +146,13 @@ u32 ethtool_op_get_flags(struct net_device *dev) } EXPORT_SYMBOL(ethtool_op_get_flags); -int ethtool_op_set_flags(struct net_device *dev, u32 data) +int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) { - const struct ethtool_ops *ops = dev->ethtool_ops; - unsigned long features = dev->features; - - if (data & ETH_FLAG_LRO) - features |= NETIF_F_LRO; - else - features &= ~NETIF_F_LRO; - - if (data & ETH_FLAG_NTUPLE) { - if (!ops->set_rx_ntuple) - return -EOPNOTSUPP; - features |= NETIF_F_NTUPLE; - } else { - /* safe to clear regardless */ - features &= ~NETIF_F_NTUPLE; - } - - if (data & ETH_FLAG_RXHASH) - features |= NETIF_F_RXHASH; - else - features &= ~NETIF_F_RXHASH; + if (data & ~supported) + return -EINVAL; - dev->features = features; + dev->features = ((dev->features & ~flags_dup_features) | + (data & flags_dup_features)); return 0; } EXPORT_SYMBOL(ethtool_op_set_flags); @@ -223,18 +207,24 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo info; const struct ethtool_ops *ops = dev->ethtool_ops; - if (!ops->get_drvinfo) - return -EOPNOTSUPP; - memset(&info, 0, sizeof(info)); info.cmd = ETHTOOL_GDRVINFO; - ops->get_drvinfo(dev, &info); + if (ops && ops->get_drvinfo) { + ops->get_drvinfo(dev, &info); + } else if (dev->dev.parent && dev->dev.parent->driver) { + strlcpy(info.bus_info, dev_name(dev->dev.parent), + sizeof(info.bus_info)); + strlcpy(info.driver, dev->dev.parent->driver->name, + sizeof(info.driver)); + } else { + return -EOPNOTSUPP; + } /* * this method of obtaining string set info is deprecated; * Use ETHTOOL_GSSET_INFO instead. */ - if (ops->get_sset_count) { + if (ops && ops->get_sset_count) { int rc; rc = ops->get_sset_count(dev, ETH_SS_TEST); @@ -247,9 +237,9 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (rc >= 0) info.n_priv_flags = rc; } - if (ops->get_regs_len) + if (ops && ops->get_regs_len) info.regdump_len = ops->get_regs_len(dev); - if (ops->get_eeprom_len) + if (ops && ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); if (copy_to_user(useraddr, &info, sizeof(info))) @@ -366,7 +356,7 @@ static noinline_for_stack int ethtool_get_rxnfc(struct net_device *dev, if (info.cmd == ETHTOOL_GRXCLSRLALL) { if (info.rule_cnt > 0) { if (info.rule_cnt <= KMALLOC_MAX_SIZE / sizeof(u32)) - rule_buf = kmalloc(info.rule_cnt * sizeof(u32), + rule_buf = kzalloc(info.rule_cnt * sizeof(u32), GFP_USER); if (!rule_buf) return -ENOMEM; @@ -395,6 +385,80 @@ err_out: return ret; } +static noinline_for_stack int ethtool_get_rxfh_indir(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_rxfh_indir *indir; + u32 table_size; + size_t full_size; + int ret; + + if (!dev->ethtool_ops->get_rxfh_indir) + return -EOPNOTSUPP; + + if (copy_from_user(&table_size, + useraddr + offsetof(struct ethtool_rxfh_indir, size), + sizeof(table_size))) + return -EFAULT; + + if (table_size > + (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index)) + return -ENOMEM; + full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size; + indir = kzalloc(full_size, GFP_USER); + if (!indir) + return -ENOMEM; + + indir->cmd = ETHTOOL_GRXFHINDIR; + indir->size = table_size; + ret = dev->ethtool_ops->get_rxfh_indir(dev, indir); + if (ret) + goto out; + + if (copy_to_user(useraddr, indir, full_size)) + ret = -EFAULT; + +out: + kfree(indir); + return ret; +} + +static noinline_for_stack int ethtool_set_rxfh_indir(struct net_device *dev, + void __user *useraddr) +{ + struct ethtool_rxfh_indir *indir; + u32 table_size; + size_t full_size; + int ret; + + if (!dev->ethtool_ops->set_rxfh_indir) + return -EOPNOTSUPP; + + if (copy_from_user(&table_size, + useraddr + offsetof(struct ethtool_rxfh_indir, size), + sizeof(table_size))) + return -EFAULT; + + if (table_size > + (KMALLOC_MAX_SIZE - sizeof(*indir)) / sizeof(*indir->ring_index)) + return -ENOMEM; + full_size = sizeof(*indir) + sizeof(*indir->ring_index) * table_size; + indir = kmalloc(full_size, GFP_USER); + if (!indir) + return -ENOMEM; + + if (copy_from_user(indir, useraddr, full_size)) { + ret = -EFAULT; + goto out; + } + + ret = dev->ethtool_ops->set_rxfh_indir(dev, indir); + +out: + kfree(indir); + return ret; +} + static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, struct ethtool_rx_ntuple_flow_spec *spec, struct ethtool_rx_ntuple_flow_spec_container *fsc) @@ -423,6 +487,38 @@ static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, list->count++; } +/* + * ethtool does not (or did not) set masks for flow parameters that are + * not specified, so if both value and mask are 0 then this must be + * treated as equivalent to a mask with all bits set. Implement that + * here rather than in drivers. + */ +static void rx_ntuple_fix_masks(struct ethtool_rx_ntuple_flow_spec *fs) +{ + struct ethtool_tcpip4_spec *entry = &fs->h_u.tcp_ip4_spec; + struct ethtool_tcpip4_spec *mask = &fs->m_u.tcp_ip4_spec; + + if (fs->flow_type != TCP_V4_FLOW && + fs->flow_type != UDP_V4_FLOW && + fs->flow_type != SCTP_V4_FLOW) + return; + + if (!(entry->ip4src | mask->ip4src)) + mask->ip4src = htonl(0xffffffff); + if (!(entry->ip4dst | mask->ip4dst)) + mask->ip4dst = htonl(0xffffffff); + if (!(entry->psrc | mask->psrc)) + mask->psrc = htons(0xffff); + if (!(entry->pdst | mask->pdst)) + mask->pdst = htons(0xffff); + if (!(entry->tos | mask->tos)) + mask->tos = 0xff; + if (!(fs->vlan_tag | fs->vlan_tag_mask)) + fs->vlan_tag_mask = 0xffff; + if (!(fs->data | fs->data_mask)) + fs->data_mask = 0xffffffffffffffffULL; +} + static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr) { @@ -437,6 +533,8 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, if (copy_from_user(&cmd, useraddr, sizeof(cmd))) return -EFAULT; + rx_ntuple_fix_masks(&cmd.fs); + /* * Cache filter in dev struct for GET operation only if * the underlying driver doesn't have its own GET operation, and @@ -482,7 +580,7 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) gstrings.len = ret; - data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); if (!data) return -ENOMEM; @@ -611,19 +709,19 @@ static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) break; case IP_USER_FLOW: sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4src); + fsc->fs.h_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4src); + fsc->fs.m_u.usr_ip4_spec.ip4src); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.raw_ip4_spec.ip4dst); + fsc->fs.h_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.raw_ip4_spec.ip4dst); + fsc->fs.m_u.usr_ip4_spec.ip4dst); p += ETH_GSTRING_LEN; num_strings++; break; @@ -719,7 +817,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = kmalloc(reglen, GFP_USER); + regbuf = vmalloc(reglen); if (!regbuf) return -ENOMEM; @@ -734,7 +832,7 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) ret = 0; out: - kfree(regbuf); + vfree(regbuf); return ret; } @@ -1119,8 +1217,11 @@ static int ethtool_set_gro(struct net_device *dev, char __user *useraddr) return -EFAULT; if (edata.data) { - if (!dev->ethtool_ops->get_rx_csum || - !dev->ethtool_ops->get_rx_csum(dev)) + u32 rxcsum = dev->ethtool_ops->get_rx_csum ? + dev->ethtool_ops->get_rx_csum(dev) : + ethtool_op_get_rx_csum(dev); + + if (!rxcsum) return -EINVAL; dev->features |= NETIF_F_GRO; } else @@ -1346,14 +1447,22 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) if (!dev || !netif_device_present(dev)) return -ENODEV; - if (!dev->ethtool_ops) - return -EOPNOTSUPP; - if (copy_from_user(ðcmd, useraddr, sizeof(ethcmd))) return -EFAULT; + if (!dev->ethtool_ops) { + /* ETHTOOL_GDRVINFO does not require any driver support. + * It is also unprivileged and does not change anything, + * so we can take a shortcut to it. */ + if (ethcmd == ETHTOOL_GDRVINFO) + return ethtool_get_drvinfo(dev, useraddr); + else + return -EOPNOTSUPP; + } + /* Allow some commands to be done by anyone */ switch (ethcmd) { + case ETHTOOL_GSET: case ETHTOOL_GDRVINFO: case ETHTOOL_GMSGLVL: case ETHTOOL_GCOALESCE: @@ -1563,6 +1672,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_GSSET_INFO: rc = ethtool_get_sset_info(dev, useraddr); break; + case ETHTOOL_GRXFHINDIR: + rc = ethtool_get_rxfh_indir(dev, useraddr); + break; + case ETHTOOL_SRXFHINDIR: + rc = ethtool_set_rxfh_indir(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 42e84e08a1be..82a4369ae150 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -144,7 +144,7 @@ fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net) } EXPORT_SYMBOL_GPL(fib_rules_register); -void fib_rules_cleanup_ops(struct fib_rules_ops *ops) +static void fib_rules_cleanup_ops(struct fib_rules_ops *ops) { struct fib_rule *rule, *tmp; @@ -153,7 +153,6 @@ void fib_rules_cleanup_ops(struct fib_rules_ops *ops) fib_rule_put(rule); } } -EXPORT_SYMBOL_GPL(fib_rules_cleanup_ops); static void fib_rules_put_rcu(struct rcu_head *head) { @@ -182,7 +181,8 @@ static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops, { int ret = 0; - if (rule->iifindex && (rule->iifindex != fl->iif)) + if (rule->iifindex && (rule->iifindex != fl->iif) && + !(fl->flags & FLOWI_FLAG_MATCH_ANY_IIF)) goto out; if (rule->oifindex && (rule->oifindex != fl->oif)) @@ -225,9 +225,12 @@ jumped: err = ops->action(rule, fl, flags, arg); if (err != -EAGAIN) { - fib_rule_get(rule); - arg->rule = rule; - goto out; + if ((arg->flags & FIB_LOOKUP_NOREF) || + likely(atomic_inc_not_zero(&rule->refcnt))) { + arg->rule = rule; + goto out; + } + break; } } @@ -348,12 +351,12 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_for_each_entry(r, &ops->rules_list, list) { if (r->pref == rule->target) { - rule->ctarget = r; + RCU_INIT_POINTER(rule->ctarget, r); break; } } - if (rule->ctarget == NULL) + if (rcu_dereference_protected(rule->ctarget, 1) == NULL) unresolved = 1; } else if (rule->action == FR_ACT_GOTO) goto errout_free; @@ -370,6 +373,11 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) fib_rule_get(rule); + if (last) + list_add_rcu(&rule->list, &last->list); + else + list_add_rcu(&rule->list, &ops->rules_list); + if (ops->unresolved_rules) { /* * There are unresolved goto rules in the list, check if @@ -378,7 +386,7 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) list_for_each_entry(r, &ops->rules_list, list) { if (r->action == FR_ACT_GOTO && r->target == rule->pref) { - BUG_ON(r->ctarget != NULL); + BUG_ON(rtnl_dereference(r->ctarget) != NULL); rcu_assign_pointer(r->ctarget, rule); if (--ops->unresolved_rules == 0) break; @@ -392,11 +400,6 @@ static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) if (unresolved) ops->unresolved_rules++; - if (last) - list_add_rcu(&rule->list, &last->list); - else - list_add_rcu(&rule->list, &ops->rules_list); - notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).pid); flush_route_cache(ops); rules_ops_put(ops); @@ -484,14 +487,13 @@ static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) */ if (ops->nr_goto_rules > 0) { list_for_each_entry(tmp, &ops->rules_list, list) { - if (tmp->ctarget == rule) { + if (rtnl_dereference(tmp->ctarget) == rule) { rcu_assign_pointer(tmp->ctarget, NULL); ops->unresolved_rules++; } } } - synchronize_rcu(); notify_rule_change(RTM_DELRULE, rule, ops, nlh, NETLINK_CB(skb).pid); fib_rule_put(rule); @@ -543,7 +545,8 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh->action = rule->action; frh->flags = rule->flags; - if (rule->action == FR_ACT_GOTO && rule->ctarget == NULL) + if (rule->action == FR_ACT_GOTO && + rcu_dereference_raw(rule->ctarget) == NULL) frh->flags |= FIB_RULE_UNRESOLVED; if (rule->iifname[0]) { diff --git a/net/core/filter.c b/net/core/filter.c index da69fb728d32..7beaec36b541 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -89,8 +89,8 @@ 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, filter->len); + err = pkt_len ? pskb_trim(skb, pkt_len) : -EPERM; } rcu_read_unlock_bh(); @@ -128,87 +128,87 @@ unsigned int sk_run_filter(struct sk_buff *skb, struct sock_filter *filter, int fentry = &filter[pc]; switch (fentry->code) { - case BPF_ALU|BPF_ADD|BPF_X: + case BPF_S_ALU_ADD_X: A += X; continue; - case BPF_ALU|BPF_ADD|BPF_K: + case BPF_S_ALU_ADD_K: A += fentry->k; continue; - case BPF_ALU|BPF_SUB|BPF_X: + case BPF_S_ALU_SUB_X: A -= X; continue; - case BPF_ALU|BPF_SUB|BPF_K: + case BPF_S_ALU_SUB_K: A -= fentry->k; continue; - case BPF_ALU|BPF_MUL|BPF_X: + case BPF_S_ALU_MUL_X: A *= X; continue; - case BPF_ALU|BPF_MUL|BPF_K: + case BPF_S_ALU_MUL_K: A *= fentry->k; continue; - case BPF_ALU|BPF_DIV|BPF_X: + case BPF_S_ALU_DIV_X: if (X == 0) return 0; A /= X; continue; - case BPF_ALU|BPF_DIV|BPF_K: + case BPF_S_ALU_DIV_K: A /= fentry->k; continue; - case BPF_ALU|BPF_AND|BPF_X: + case BPF_S_ALU_AND_X: A &= X; continue; - case BPF_ALU|BPF_AND|BPF_K: + case BPF_S_ALU_AND_K: A &= fentry->k; continue; - case BPF_ALU|BPF_OR|BPF_X: + case BPF_S_ALU_OR_X: A |= X; continue; - case BPF_ALU|BPF_OR|BPF_K: + case BPF_S_ALU_OR_K: A |= fentry->k; continue; - case BPF_ALU|BPF_LSH|BPF_X: + case BPF_S_ALU_LSH_X: A <<= X; continue; - case BPF_ALU|BPF_LSH|BPF_K: + case BPF_S_ALU_LSH_K: A <<= fentry->k; continue; - case BPF_ALU|BPF_RSH|BPF_X: + case BPF_S_ALU_RSH_X: A >>= X; continue; - case BPF_ALU|BPF_RSH|BPF_K: + case BPF_S_ALU_RSH_K: A >>= fentry->k; continue; - case BPF_ALU|BPF_NEG: + case BPF_S_ALU_NEG: A = -A; continue; - case BPF_JMP|BPF_JA: + case BPF_S_JMP_JA: pc += fentry->k; continue; - case BPF_JMP|BPF_JGT|BPF_K: + case BPF_S_JMP_JGT_K: pc += (A > fentry->k) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JGE|BPF_K: + case BPF_S_JMP_JGE_K: pc += (A >= fentry->k) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JEQ|BPF_K: + case BPF_S_JMP_JEQ_K: pc += (A == fentry->k) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JSET|BPF_K: + case BPF_S_JMP_JSET_K: pc += (A & fentry->k) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JGT|BPF_X: + case BPF_S_JMP_JGT_X: pc += (A > X) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JGE|BPF_X: + case BPF_S_JMP_JGE_X: pc += (A >= X) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JEQ|BPF_X: + case BPF_S_JMP_JEQ_X: pc += (A == X) ? fentry->jt : fentry->jf; continue; - case BPF_JMP|BPF_JSET|BPF_X: + case BPF_S_JMP_JSET_X: pc += (A & X) ? fentry->jt : fentry->jf; continue; - case BPF_LD|BPF_W|BPF_ABS: + case BPF_S_LD_W_ABS: k = fentry->k; load_w: ptr = load_pointer(skb, k, 4, &tmp); @@ -217,7 +217,7 @@ load_w: continue; } break; - case BPF_LD|BPF_H|BPF_ABS: + case BPF_S_LD_H_ABS: k = fentry->k; load_h: ptr = load_pointer(skb, k, 2, &tmp); @@ -226,7 +226,7 @@ load_h: continue; } break; - case BPF_LD|BPF_B|BPF_ABS: + case BPF_S_LD_B_ABS: k = fentry->k; load_b: ptr = load_pointer(skb, k, 1, &tmp); @@ -235,54 +235,54 @@ load_b: continue; } break; - case BPF_LD|BPF_W|BPF_LEN: + case BPF_S_LD_W_LEN: A = skb->len; continue; - case BPF_LDX|BPF_W|BPF_LEN: + case BPF_S_LDX_W_LEN: X = skb->len; continue; - case BPF_LD|BPF_W|BPF_IND: + case BPF_S_LD_W_IND: k = X + fentry->k; goto load_w; - case BPF_LD|BPF_H|BPF_IND: + case BPF_S_LD_H_IND: k = X + fentry->k; goto load_h; - case BPF_LD|BPF_B|BPF_IND: + case BPF_S_LD_B_IND: k = X + fentry->k; goto load_b; - case BPF_LDX|BPF_B|BPF_MSH: + case BPF_S_LDX_B_MSH: ptr = load_pointer(skb, fentry->k, 1, &tmp); if (ptr != NULL) { X = (*(u8 *)ptr & 0xf) << 2; continue; } return 0; - case BPF_LD|BPF_IMM: + case BPF_S_LD_IMM: A = fentry->k; continue; - case BPF_LDX|BPF_IMM: + case BPF_S_LDX_IMM: X = fentry->k; continue; - case BPF_LD|BPF_MEM: + case BPF_S_LD_MEM: A = mem[fentry->k]; continue; - case BPF_LDX|BPF_MEM: + case BPF_S_LDX_MEM: X = mem[fentry->k]; continue; - case BPF_MISC|BPF_TAX: + case BPF_S_MISC_TAX: X = A; continue; - case BPF_MISC|BPF_TXA: + case BPF_S_MISC_TXA: A = X; continue; - case BPF_RET|BPF_K: + case BPF_S_RET_K: return fentry->k; - case BPF_RET|BPF_A: + case BPF_S_RET_A: return A; - case BPF_ST: + case BPF_S_ST: mem[fentry->k] = A; continue; - case BPF_STX: + case BPF_S_STX: mem[fentry->k] = X; continue; default: @@ -390,53 +390,128 @@ int sk_chk_filter(struct sock_filter *filter, int flen) /* 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; /* Some instructions need special checks */ - case BPF_ALU|BPF_DIV|BPF_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; + 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: - /* check for invalid memory addresses */ if (ftest->k >= BPF_MEMWORDS) return -EINVAL; + ftest->code = BPF_S_STX; break; case BPF_JMP|BPF_JA: @@ -447,28 +522,63 @@ 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: + 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: if (pc + ftest->jt + 1 >= flen || pc + ftest->jf + 1 >= flen) return -EINVAL; - break; + } + } + /* 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 (BPF_CLASS(filter[flen - 1].code) == BPF_RET) ? 0 : -EINVAL; } EXPORT_SYMBOL(sk_chk_filter); @@ -528,10 +638,9 @@ int sk_attach_filter(struct sock_fprog *fprog, struct sock *sk) return err; } - rcu_read_lock_bh(); - old_fp = rcu_dereference_bh(sk->sk_filter); + old_fp = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); rcu_assign_pointer(sk->sk_filter, fp); - rcu_read_unlock_bh(); if (old_fp) sk_filter_delayed_uncharge(sk, old_fp); @@ -544,14 +653,13 @@ int sk_detach_filter(struct sock *sk) int ret = -ENOENT; struct sk_filter *filter; - rcu_read_lock_bh(); - filter = rcu_dereference_bh(sk->sk_filter); + filter = rcu_dereference_protected(sk->sk_filter, + sock_owned_by_user(sk)); if (filter) { rcu_assign_pointer(sk->sk_filter, NULL); sk_filter_delayed_uncharge(sk, filter); ret = 0; } - rcu_read_unlock_bh(); return ret; } EXPORT_SYMBOL_GPL(sk_detach_filter); diff --git a/net/core/flow.c b/net/core/flow.c index 161900674009..127c8a7ffd61 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -53,8 +53,7 @@ struct flow_flush_info { struct flow_cache { u32 hash_shift; - unsigned long order; - struct flow_cache_percpu *percpu; + struct flow_cache_percpu __percpu *percpu; struct notifier_block hotcpu_notifier; int low_watermark; int high_watermark; @@ -62,8 +61,9 @@ struct flow_cache { }; atomic_t flow_cache_genid = ATOMIC_INIT(0); +EXPORT_SYMBOL(flow_cache_genid); static struct flow_cache flow_cache_global; -static struct kmem_cache *flow_cachep; +static struct kmem_cache *flow_cachep __read_mostly; static DEFINE_SPINLOCK(flow_cache_gc_lock); static LIST_HEAD(flow_cache_gc_list); @@ -176,15 +176,11 @@ static u32 flow_hash_code(struct flow_cache *fc, { u32 *k = (u32 *) key; - return (jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) - & (flow_cache_hash_size(fc) - 1)); + return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) + & (flow_cache_hash_size(fc) - 1); } -#if (BITS_PER_LONG == 64) -typedef u64 flow_compare_t; -#else -typedef u32 flow_compare_t; -#endif +typedef unsigned long flow_compare_t; /* I hear what you're saying, use memcmp. But memcmp cannot make * important assumptions that we can here, such as alignment and @@ -222,7 +218,7 @@ flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, unsigned int hash; local_bh_disable(); - fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); + fcp = this_cpu_ptr(fc->percpu); fle = NULL; flo = NULL; @@ -291,6 +287,7 @@ ret_object: local_bh_enable(); return flo; } +EXPORT_SYMBOL(flow_cache_lookup); static void flow_cache_flush_tasklet(unsigned long data) { @@ -302,7 +299,7 @@ static void flow_cache_flush_tasklet(unsigned long data) LIST_HEAD(gc_list); int i, deleted = 0; - fcp = per_cpu_ptr(fc->percpu, smp_processor_id()); + fcp = this_cpu_ptr(fc->percpu); for (i = 0; i < flow_cache_hash_size(fc); i++) { hlist_for_each_entry_safe(fle, entry, tmp, &fcp->hash_table[i], u.hlist) { @@ -355,62 +352,73 @@ void flow_cache_flush(void) put_online_cpus(); } -static void __init flow_cache_cpu_prepare(struct flow_cache *fc, - struct flow_cache_percpu *fcp) +static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { - fcp->hash_table = (struct hlist_head *) - __get_free_pages(GFP_KERNEL|__GFP_ZERO, fc->order); - if (!fcp->hash_table) - panic("NET: failed to allocate flow cache order %lu\n", fc->order); + struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); + size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); - fcp->hash_rnd_recalc = 1; - fcp->hash_count = 0; - tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0); + if (!fcp->hash_table) { + fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu)); + if (!fcp->hash_table) { + pr_err("NET: failed to allocate flow cache sz %zu\n", sz); + return -ENOMEM; + } + fcp->hash_rnd_recalc = 1; + fcp->hash_count = 0; + tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0); + } + return 0; } -static int flow_cache_cpu(struct notifier_block *nfb, +static int __cpuinit flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { struct flow_cache *fc = container_of(nfb, struct flow_cache, hotcpu_notifier); - int cpu = (unsigned long) hcpu; + int res, cpu = (unsigned long) hcpu; struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); - if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) + switch (action) { + case CPU_UP_PREPARE: + case CPU_UP_PREPARE_FROZEN: + res = flow_cache_cpu_prepare(fc, cpu); + if (res) + return notifier_from_errno(res); + break; + case CPU_DEAD: + case CPU_DEAD_FROZEN: __flow_cache_shrink(fc, fcp, 0); + break; + } return NOTIFY_OK; } -static int flow_cache_init(struct flow_cache *fc) +static int __init flow_cache_init(struct flow_cache *fc) { - unsigned long order; int i; fc->hash_shift = 10; fc->low_watermark = 2 * flow_cache_hash_size(fc); fc->high_watermark = 4 * flow_cache_hash_size(fc); - for (order = 0; - (PAGE_SIZE << order) < - (sizeof(struct hlist_head)*flow_cache_hash_size(fc)); - order++) - /* NOTHING */; - fc->order = order; fc->percpu = alloc_percpu(struct flow_cache_percpu); + if (!fc->percpu) + return -ENOMEM; - setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, - (unsigned long) fc); - fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; - add_timer(&fc->rnd_timer); - - for_each_possible_cpu(i) - flow_cache_cpu_prepare(fc, per_cpu_ptr(fc->percpu, i)); - + for_each_online_cpu(i) { + if (flow_cache_cpu_prepare(fc, i)) + return -ENOMEM; + } fc->hotcpu_notifier = (struct notifier_block){ .notifier_call = flow_cache_cpu, }; register_hotcpu_notifier(&fc->hotcpu_notifier); + setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd, + (unsigned long) fc); + fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD; + add_timer(&fc->rnd_timer); + return 0; } @@ -424,6 +432,3 @@ static int __init flow_cache_init_global(void) } module_init(flow_cache_init_global); - -EXPORT_SYMBOL(flow_cache_genid); -EXPORT_SYMBOL(flow_cache_lookup); diff --git a/net/core/gen_estimator.c b/net/core/gen_estimator.c index 785e5276a300..7c2373321b74 100644 --- a/net/core/gen_estimator.c +++ b/net/core/gen_estimator.c @@ -232,7 +232,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, est->last_packets = bstats->packets; est->avpps = rate_est->pps<<10; - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); if (!elist[idx].timer.function) { INIT_LIST_HEAD(&elist[idx].list); setup_timer(&elist[idx].timer, est_timer, idx); @@ -243,7 +243,7 @@ int gen_new_estimator(struct gnet_stats_basic_packed *bstats, list_add_rcu(&est->list, &elist[idx].list); gen_add_node(est); - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); return 0; } @@ -263,24 +263,25 @@ static void __gen_kill_estimator(struct rcu_head *head) * * Removes the rate estimator specified by &bstats and &rate_est. * + * Note : Caller should respect an RCU grace period before freeing stats_lock */ void gen_kill_estimator(struct gnet_stats_basic_packed *bstats, struct gnet_stats_rate_est *rate_est) { struct gen_estimator *e; - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); while ((e = gen_find_node(bstats, rate_est))) { rb_erase(&e->node, &est_root); - write_lock_bh(&est_lock); + write_lock(&est_lock); e->bstats = NULL; - write_unlock_bh(&est_lock); + write_unlock(&est_lock); list_del_rcu(&e->list); call_rcu(&e->e_rcu, __gen_kill_estimator); } - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); } EXPORT_SYMBOL(gen_kill_estimator); @@ -319,9 +320,9 @@ bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats, ASSERT_RTNL(); - spin_lock(&est_tree_lock); + spin_lock_bh(&est_tree_lock); res = gen_find_node(bstats, rate_est) != NULL; - spin_unlock(&est_tree_lock); + spin_unlock_bh(&est_tree_lock); return res; } diff --git a/net/core/gen_stats.c b/net/core/gen_stats.c index 393b1d8618e2..0452eb27a272 100644 --- a/net/core/gen_stats.c +++ b/net/core/gen_stats.c @@ -73,6 +73,7 @@ gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type, return 0; } +EXPORT_SYMBOL(gnet_stats_start_copy_compat); /** * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode @@ -93,6 +94,7 @@ gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock, { return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d); } +EXPORT_SYMBOL(gnet_stats_start_copy); /** * gnet_stats_copy_basic - copy basic statistics into statistic TLV @@ -123,6 +125,7 @@ gnet_stats_copy_basic(struct gnet_dump *d, struct gnet_stats_basic_packed *b) } return 0; } +EXPORT_SYMBOL(gnet_stats_copy_basic); /** * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV @@ -154,6 +157,7 @@ gnet_stats_copy_rate_est(struct gnet_dump *d, return 0; } +EXPORT_SYMBOL(gnet_stats_copy_rate_est); /** * gnet_stats_copy_queue - copy queue statistics into statistics TLV @@ -181,6 +185,7 @@ gnet_stats_copy_queue(struct gnet_dump *d, struct gnet_stats_queue *q) return 0; } +EXPORT_SYMBOL(gnet_stats_copy_queue); /** * gnet_stats_copy_app - copy application specific statistics into statistics TLV @@ -208,6 +213,7 @@ gnet_stats_copy_app(struct gnet_dump *d, void *st, int len) return 0; } +EXPORT_SYMBOL(gnet_stats_copy_app); /** * gnet_stats_finish_copy - finish dumping procedure @@ -241,12 +247,4 @@ gnet_stats_finish_copy(struct gnet_dump *d) spin_unlock_bh(d->lock); return 0; } - - -EXPORT_SYMBOL(gnet_stats_start_copy); -EXPORT_SYMBOL(gnet_stats_start_copy_compat); -EXPORT_SYMBOL(gnet_stats_copy_basic); -EXPORT_SYMBOL(gnet_stats_copy_rate_est); -EXPORT_SYMBOL(gnet_stats_copy_queue); -EXPORT_SYMBOL(gnet_stats_copy_app); EXPORT_SYMBOL(gnet_stats_finish_copy); diff --git a/net/core/iovec.c b/net/core/iovec.c index 1e7f4e91a935..c40f27e7d208 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -37,11 +37,13 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, int mode) { - int size, err, ct; + int size, ct, err; if (m->msg_namelen) { if (mode == VERIFY_READ) { - err = move_addr_to_kernel(m->msg_name, m->msg_namelen, + void __user *namep; + namep = (void __user __force *) m->msg_name; + err = move_addr_to_kernel(namep, m->msg_namelen, address); if (err < 0) return err; @@ -52,21 +54,20 @@ int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr *address, } size = m->msg_iovlen * sizeof(struct iovec); - if (copy_from_user(iov, m->msg_iov, size)) + if (copy_from_user(iov, (void __user __force *) m->msg_iov, size)) return -EFAULT; m->msg_iov = iov; err = 0; for (ct = 0; ct < m->msg_iovlen; ct++) { - err += iov[ct].iov_len; - /* - * Goal is not to verify user data, but to prevent returning - * negative value, which is interpreted as errno. - * Overflow is still possible, but it is harmless. - */ - if (err < 0) - return -EMSGSIZE; + size_t len = iov[ct].iov_len; + + if (len > INT_MAX - err) { + len = INT_MAX - err; + iov[ct].iov_len = len; + } + err += len; } return err; @@ -95,6 +96,7 @@ int memcpy_toiovec(struct iovec *iov, unsigned char *kdata, int len) return 0; } +EXPORT_SYMBOL(memcpy_toiovec); /* * Copy kernel to iovec. Returns -EFAULT on error. @@ -120,6 +122,7 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, return 0; } +EXPORT_SYMBOL(memcpy_toiovecend); /* * Copy iovec to kernel. Returns -EFAULT on error. @@ -144,6 +147,7 @@ int memcpy_fromiovec(unsigned char *kdata, struct iovec *iov, int len) return 0; } +EXPORT_SYMBOL(memcpy_fromiovec); /* * Copy iovec from kernel. Returns -EFAULT on error. @@ -172,6 +176,7 @@ int memcpy_fromiovecend(unsigned char *kdata, const struct iovec *iov, return 0; } +EXPORT_SYMBOL(memcpy_fromiovecend); /* * And now for the all-in-one: copy and checksum from a user iovec @@ -256,9 +261,4 @@ out_fault: err = -EFAULT; goto out; } - EXPORT_SYMBOL(csum_partial_copy_fromiovecend); -EXPORT_SYMBOL(memcpy_fromiovec); -EXPORT_SYMBOL(memcpy_fromiovecend); -EXPORT_SYMBOL(memcpy_toiovec); -EXPORT_SYMBOL(memcpy_toiovecend); diff --git a/net/core/link_watch.c b/net/core/link_watch.c index bdbce2f5875b..01a1101b5936 100644 --- a/net/core/link_watch.c +++ b/net/core/link_watch.c @@ -243,5 +243,4 @@ void linkwatch_fire_event(struct net_device *dev) linkwatch_schedule_work(urgent); } - EXPORT_SYMBOL(linkwatch_fire_event); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a4e0a7482c2b..8cc8f9a79db9 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -122,7 +122,7 @@ static void neigh_cleanup_and_release(struct neighbour *neigh) unsigned long neigh_rand_reach_time(unsigned long base) { - return (base ? (net_random() % base) + (base >> 1) : 0); + return base ? (net_random() % base) + (base >> 1) : 0; } EXPORT_SYMBOL(neigh_rand_reach_time); @@ -131,15 +131,20 @@ static int neigh_forced_gc(struct neigh_table *tbl) { int shrunk = 0; int i; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, forced_gc_runs); write_lock_bh(&tbl->lock); - for (i = 0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + for (i = 0; i <= nht->hash_mask; i++) { + struct neighbour *n; + struct neighbour __rcu **np; - np = &tbl->hash_buckets[i]; - while ((n = *np) != NULL) { + np = &nht->hash_buckets[i]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { /* Neighbour record may be discarded if: * - nobody refers to it. * - it is not permanent @@ -147,7 +152,9 @@ static int neigh_forced_gc(struct neigh_table *tbl) write_lock(&n->lock); if (atomic_read(&n->refcnt) == 1 && !(n->nud_state & NUD_PERMANENT)) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); n->dead = 1; shrunk = 1; write_unlock(&n->lock); @@ -199,16 +206,24 @@ static void pneigh_queue_purge(struct sk_buff_head *list) static void neigh_flush_dev(struct neigh_table *tbl, struct net_device *dev) { int i; + struct neigh_hash_table *nht; - for (i = 0; i <= tbl->hash_mask; i++) { - struct neighbour *n, **np = &tbl->hash_buckets[i]; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); - while ((n = *np) != NULL) { + for (i = 0; i <= nht->hash_mask; i++) { + struct neighbour *n; + struct neighbour __rcu **np = &nht->hash_buckets[i]; + + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { if (dev && n->dev != dev) { np = &n->next; continue; } - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); write_lock(&n->lock); neigh_del_timer(n); n->dead = 1; @@ -279,6 +294,7 @@ static struct neighbour *neigh_alloc(struct neigh_table *tbl) skb_queue_head_init(&n->arp_queue); rwlock_init(&n->lock); + seqlock_init(&n->ha_lock); n->updated = n->used = now; n->nud_state = NUD_NONE; n->output = neigh_blackhole; @@ -297,64 +313,86 @@ out_entries: goto out; } -static struct neighbour **neigh_hash_alloc(unsigned int entries) +static struct neigh_hash_table *neigh_hash_alloc(unsigned int entries) { - unsigned long size = entries * sizeof(struct neighbour *); - struct neighbour **ret; + size_t size = entries * sizeof(struct neighbour *); + struct neigh_hash_table *ret; + struct neighbour **buckets; - if (size <= PAGE_SIZE) { - ret = kzalloc(size, GFP_ATOMIC); - } else { - ret = (struct neighbour **) - __get_free_pages(GFP_ATOMIC|__GFP_ZERO, get_order(size)); + ret = kmalloc(sizeof(*ret), GFP_ATOMIC); + if (!ret) + return NULL; + if (size <= PAGE_SIZE) + buckets = kzalloc(size, GFP_ATOMIC); + else + buckets = (struct neighbour **) + __get_free_pages(GFP_ATOMIC | __GFP_ZERO, + get_order(size)); + if (!buckets) { + kfree(ret); + return NULL; } + rcu_assign_pointer(ret->hash_buckets, buckets); + ret->hash_mask = entries - 1; + get_random_bytes(&ret->hash_rnd, sizeof(ret->hash_rnd)); return ret; } -static void neigh_hash_free(struct neighbour **hash, unsigned int entries) +static void neigh_hash_free_rcu(struct rcu_head *head) { - unsigned long size = entries * sizeof(struct neighbour *); + struct neigh_hash_table *nht = container_of(head, + struct neigh_hash_table, + rcu); + size_t size = (nht->hash_mask + 1) * sizeof(struct neighbour *); + struct neighbour **buckets = nht->hash_buckets; if (size <= PAGE_SIZE) - kfree(hash); + kfree(buckets); else - free_pages((unsigned long)hash, get_order(size)); + free_pages((unsigned long)buckets, get_order(size)); + kfree(nht); } -static void neigh_hash_grow(struct neigh_table *tbl, unsigned long new_entries) +static struct neigh_hash_table *neigh_hash_grow(struct neigh_table *tbl, + unsigned long new_entries) { - struct neighbour **new_hash, **old_hash; - unsigned int i, new_hash_mask, old_entries; + unsigned int i, hash; + struct neigh_hash_table *new_nht, *old_nht; NEIGH_CACHE_STAT_INC(tbl, hash_grows); BUG_ON(!is_power_of_2(new_entries)); - new_hash = neigh_hash_alloc(new_entries); - if (!new_hash) - return; - - old_entries = tbl->hash_mask + 1; - new_hash_mask = new_entries - 1; - old_hash = tbl->hash_buckets; + old_nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + new_nht = neigh_hash_alloc(new_entries); + if (!new_nht) + return old_nht; - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); - for (i = 0; i < old_entries; i++) { + for (i = 0; i <= old_nht->hash_mask; i++) { struct neighbour *n, *next; - for (n = old_hash[i]; n; n = next) { - unsigned int hash_val = tbl->hash(n->primary_key, n->dev); - - hash_val &= new_hash_mask; - next = n->next; - - n->next = new_hash[hash_val]; - new_hash[hash_val] = n; + for (n = rcu_dereference_protected(old_nht->hash_buckets[i], + lockdep_is_held(&tbl->lock)); + n != NULL; + n = next) { + hash = tbl->hash(n->primary_key, n->dev, + new_nht->hash_rnd); + + hash &= new_nht->hash_mask; + next = rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock)); + + rcu_assign_pointer(n->next, + rcu_dereference_protected( + new_nht->hash_buckets[hash], + lockdep_is_held(&tbl->lock))); + rcu_assign_pointer(new_nht->hash_buckets[hash], n); } } - tbl->hash_buckets = new_hash; - tbl->hash_mask = new_hash_mask; - neigh_hash_free(old_hash, old_entries); + rcu_assign_pointer(tbl->nht, new_nht); + call_rcu(&old_nht->rcu, neigh_hash_free_rcu); + return new_nht; } struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, @@ -363,19 +401,26 @@ struct neighbour *neigh_lookup(struct neigh_table *tbl, const void *pkey, struct neighbour *n; int key_len = tbl->key_len; u32 hash_val; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); - read_lock_bh(&tbl->lock); - hash_val = tbl->hash(pkey, dev); - for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; + + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { if (dev == n->dev && !memcmp(n->primary_key, pkey, key_len)) { - neigh_hold(n); + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; } } - read_unlock_bh(&tbl->lock); + + rcu_read_unlock_bh(); return n; } EXPORT_SYMBOL(neigh_lookup); @@ -386,20 +431,27 @@ struct neighbour *neigh_lookup_nodev(struct neigh_table *tbl, struct net *net, struct neighbour *n; int key_len = tbl->key_len; u32 hash_val; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, lookups); - read_lock_bh(&tbl->lock); - hash_val = tbl->hash(pkey, NULL); - for (n = tbl->hash_buckets[hash_val & tbl->hash_mask]; n; n = n->next) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + hash_val = tbl->hash(pkey, NULL, nht->hash_rnd) & nht->hash_mask; + + for (n = rcu_dereference_bh(nht->hash_buckets[hash_val]); + n != NULL; + n = rcu_dereference_bh(n->next)) { if (!memcmp(n->primary_key, pkey, key_len) && net_eq(dev_net(n->dev), net)) { - neigh_hold(n); + if (!atomic_inc_not_zero(&n->refcnt)) + n = NULL; NEIGH_CACHE_STAT_INC(tbl, hits); break; } } - read_unlock_bh(&tbl->lock); + + rcu_read_unlock_bh(); return n; } EXPORT_SYMBOL(neigh_lookup_nodev); @@ -411,6 +463,7 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, int key_len = tbl->key_len; int error; struct neighbour *n1, *rc, *n = neigh_alloc(tbl); + struct neigh_hash_table *nht; if (!n) { rc = ERR_PTR(-ENOBUFS); @@ -437,18 +490,24 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, n->confirmed = jiffies - (n->parms->base_reachable_time << 1); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); - if (atomic_read(&tbl->entries) > (tbl->hash_mask + 1)) - neigh_hash_grow(tbl, (tbl->hash_mask + 1) << 1); + if (atomic_read(&tbl->entries) > (nht->hash_mask + 1)) + nht = neigh_hash_grow(tbl, (nht->hash_mask + 1) << 1); - hash_val = tbl->hash(pkey, dev) & tbl->hash_mask; + hash_val = tbl->hash(pkey, dev, nht->hash_rnd) & nht->hash_mask; if (n->parms->dead) { rc = ERR_PTR(-EINVAL); goto out_tbl_unlock; } - for (n1 = tbl->hash_buckets[hash_val]; n1; n1 = n1->next) { + for (n1 = rcu_dereference_protected(nht->hash_buckets[hash_val], + lockdep_is_held(&tbl->lock)); + n1 != NULL; + n1 = rcu_dereference_protected(n1->next, + lockdep_is_held(&tbl->lock))) { if (dev == n1->dev && !memcmp(n1->primary_key, pkey, key_len)) { neigh_hold(n1); rc = n1; @@ -456,10 +515,12 @@ struct neighbour *neigh_create(struct neigh_table *tbl, const void *pkey, } } - n->next = tbl->hash_buckets[hash_val]; - tbl->hash_buckets[hash_val] = n; n->dead = 0; neigh_hold(n); + rcu_assign_pointer(n->next, + rcu_dereference_protected(nht->hash_buckets[hash_val], + lockdep_is_held(&tbl->lock))); + rcu_assign_pointer(nht->hash_buckets[hash_val], n); write_unlock_bh(&tbl->lock); NEIGH_PRINTK2("neigh %p is created.\n", n); rc = n; @@ -616,6 +677,12 @@ static inline void neigh_parms_put(struct neigh_parms *parms) neigh_parms_destroy(parms); } +static void neigh_destroy_rcu(struct rcu_head *head) +{ + struct neighbour *neigh = container_of(head, struct neighbour, rcu); + + kmem_cache_free(neigh->tbl->kmem_cachep, neigh); +} /* * neighbour must already be out of the table; * @@ -643,8 +710,7 @@ void neigh_destroy(struct neighbour *neigh) write_seqlock_bh(&hh->hh_lock); hh->hh_output = neigh_blackhole; write_sequnlock_bh(&hh->hh_lock); - if (atomic_dec_and_test(&hh->hh_refcnt)) - kfree(hh); + hh_cache_put(hh); } skb_queue_purge(&neigh->arp_queue); @@ -655,7 +721,7 @@ void neigh_destroy(struct neighbour *neigh) NEIGH_PRINTK2("neigh %p is destroyed.\n", neigh); atomic_dec(&neigh->tbl->entries); - kmem_cache_free(neigh->tbl->kmem_cachep, neigh); + call_rcu(&neigh->rcu, neigh_destroy_rcu); } EXPORT_SYMBOL(neigh_destroy); @@ -696,12 +762,16 @@ static void neigh_connect(struct neighbour *neigh) static void neigh_periodic_work(struct work_struct *work) { struct neigh_table *tbl = container_of(work, struct neigh_table, gc_work.work); - struct neighbour *n, **np; + struct neighbour *n; + struct neighbour __rcu **np; unsigned int i; + struct neigh_hash_table *nht; NEIGH_CACHE_STAT_INC(tbl, periodic_gc_runs); write_lock_bh(&tbl->lock); + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); /* * periodically recompute ReachableTime from random function @@ -715,10 +785,11 @@ static void neigh_periodic_work(struct work_struct *work) neigh_rand_reach_time(p->base_reachable_time); } - for (i = 0 ; i <= tbl->hash_mask; i++) { - np = &tbl->hash_buckets[i]; + for (i = 0 ; i <= nht->hash_mask; i++) { + np = &nht->hash_buckets[i]; - while ((n = *np) != NULL) { + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { unsigned int state; write_lock(&n->lock); @@ -766,9 +837,9 @@ next_elt: static __inline__ int neigh_max_probes(struct neighbour *n) { struct neigh_parms *p = n->parms; - return (n->nud_state & NUD_PROBE ? + return (n->nud_state & NUD_PROBE) ? p->ucast_probes : - p->ucast_probes + p->app_probes + p->mcast_probes); + p->ucast_probes + p->app_probes + p->mcast_probes; } static void neigh_invalidate(struct neighbour *neigh) @@ -945,7 +1016,7 @@ out_unlock_bh: } EXPORT_SYMBOL(__neigh_event_send); -static void neigh_update_hhs(struct neighbour *neigh) +static void neigh_update_hhs(const struct neighbour *neigh) { struct hh_cache *hh; void (*update)(struct hh_cache*, const struct net_device*, const unsigned char *) @@ -1081,7 +1152,9 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, } if (lladdr != neigh->ha) { + write_seqlock(&neigh->ha_lock); memcpy(&neigh->ha, lladdr, dev->addr_len); + write_sequnlock(&neigh->ha_lock); neigh_update_hhs(neigh); if (!(new & NUD_CONNECTED)) neigh->confirmed = jiffies - @@ -1139,44 +1212,73 @@ struct neighbour *neigh_event_ns(struct neigh_table *tbl, } EXPORT_SYMBOL(neigh_event_ns); +static inline bool neigh_hh_lookup(struct neighbour *n, struct dst_entry *dst, + __be16 protocol) +{ + struct hh_cache *hh; + + smp_rmb(); /* paired with smp_wmb() in neigh_hh_init() */ + for (hh = n->hh; hh; hh = hh->hh_next) { + if (hh->hh_type == protocol) { + atomic_inc(&hh->hh_refcnt); + if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) + hh_cache_put(hh); + return true; + } + } + return false; +} + +/* called with read_lock_bh(&n->lock); */ static void neigh_hh_init(struct neighbour *n, struct dst_entry *dst, __be16 protocol) { struct hh_cache *hh; struct net_device *dev = dst->dev; - for (hh = n->hh; hh; hh = hh->hh_next) - if (hh->hh_type == protocol) - break; + if (likely(neigh_hh_lookup(n, dst, protocol))) + return; - if (!hh && (hh = kzalloc(sizeof(*hh), GFP_ATOMIC)) != NULL) { - seqlock_init(&hh->hh_lock); - hh->hh_type = protocol; - atomic_set(&hh->hh_refcnt, 0); - hh->hh_next = NULL; + /* slow path */ + hh = kzalloc(sizeof(*hh), GFP_ATOMIC); + if (!hh) + return; - if (dev->header_ops->cache(n, hh)) { - kfree(hh); - hh = NULL; - } else { - atomic_inc(&hh->hh_refcnt); - hh->hh_next = n->hh; - n->hh = hh; - if (n->nud_state & NUD_CONNECTED) - hh->hh_output = n->ops->hh_output; - else - hh->hh_output = n->ops->output; - } + seqlock_init(&hh->hh_lock); + hh->hh_type = protocol; + atomic_set(&hh->hh_refcnt, 2); + + if (dev->header_ops->cache(n, hh)) { + kfree(hh); + return; } - if (hh) { - atomic_inc(&hh->hh_refcnt); - dst->hh = hh; + + write_lock_bh(&n->lock); + + /* must check if another thread already did the insert */ + if (neigh_hh_lookup(n, dst, protocol)) { + kfree(hh); + goto end; } + + if (n->nud_state & NUD_CONNECTED) + hh->hh_output = n->ops->hh_output; + else + hh->hh_output = n->ops->output; + + hh->hh_next = n->hh; + smp_wmb(); /* paired with smp_rmb() in neigh_hh_lookup() */ + n->hh = hh; + + if (unlikely(cmpxchg(&dst->hh, NULL, hh) != NULL)) + hh_cache_put(hh); +end: + write_unlock_bh(&n->lock); } /* This function can be used in contexts, where only old dev_queue_xmit - worked, f.e. if you want to override normal output path (eql, shaper), - but resolution is not made yet. + * worked, f.e. if you want to override normal output path (eql, shaper), + * but resolution is not made yet. */ int neigh_compat_output(struct sk_buff *skb) @@ -1210,19 +1312,19 @@ int neigh_resolve_output(struct sk_buff *skb) if (!neigh_event_send(neigh, skb)) { int err; struct net_device *dev = neigh->dev; - if (dev->header_ops->cache && !dst->hh) { - write_lock_bh(&neigh->lock); - if (!dst->hh) - neigh_hh_init(neigh, dst, dst->ops->protocol); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - write_unlock_bh(&neigh->lock); - } else { - read_lock_bh(&neigh->lock); + unsigned int seq; + + if (dev->header_ops->cache && + !dst->hh && + !(dst->flags & DST_NOCACHE)) + neigh_hh_init(neigh, dst, dst->ops->protocol); + + do { + seq = read_seqbegin(&neigh->ha_lock); err = dev_hard_header(skb, dev, ntohs(skb->protocol), neigh->ha, NULL, skb->len); - read_unlock_bh(&neigh->lock); - } + } while (read_seqretry(&neigh->ha_lock, seq)); + if (err >= 0) rc = neigh->ops->queue_xmit(skb); else @@ -1248,13 +1350,16 @@ int neigh_connected_output(struct sk_buff *skb) struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; + unsigned int seq; __skb_pull(skb, skb_network_offset(skb)); - read_lock_bh(&neigh->lock); - err = dev_hard_header(skb, dev, ntohs(skb->protocol), - neigh->ha, NULL, skb->len); - read_unlock_bh(&neigh->lock); + do { + seq = read_seqbegin(&neigh->ha_lock); + err = dev_hard_header(skb, dev, ntohs(skb->protocol), + neigh->ha, NULL, skb->len); + } while (read_seqretry(&neigh->ha_lock, seq)); + if (err >= 0) err = neigh->ops->queue_xmit(skb); else { @@ -1436,17 +1541,14 @@ void neigh_table_init_no_netlink(struct neigh_table *tbl) panic("cannot create neighbour proc dir entry"); #endif - tbl->hash_mask = 1; - tbl->hash_buckets = neigh_hash_alloc(tbl->hash_mask + 1); + tbl->nht = neigh_hash_alloc(8); phsize = (PNEIGH_HASHMASK + 1) * sizeof(struct pneigh_entry *); tbl->phash_buckets = kzalloc(phsize, GFP_KERNEL); - if (!tbl->hash_buckets || !tbl->phash_buckets) + if (!tbl->nht || !tbl->phash_buckets) panic("cannot allocate neighbour cache hashes"); - get_random_bytes(&tbl->hash_rnd, sizeof(tbl->hash_rnd)); - rwlock_init(&tbl->lock); INIT_DELAYED_WORK_DEFERRABLE(&tbl->gc_work, neigh_periodic_work); schedule_delayed_work(&tbl->gc_work, tbl->parms.reachable_time); @@ -1486,8 +1588,7 @@ int neigh_table_clear(struct neigh_table *tbl) struct neigh_table **tp; /* It is not clean... Fix it to unload IPv6 module safely */ - cancel_delayed_work(&tbl->gc_work); - flush_scheduled_work(); + cancel_delayed_work_sync(&tbl->gc_work); del_timer_sync(&tbl->proxy_timer); pneigh_queue_purge(&tbl->proxy_queue); neigh_ifdown(tbl, NULL); @@ -1502,8 +1603,8 @@ int neigh_table_clear(struct neigh_table *tbl) } write_unlock(&neigh_tbl_lock); - neigh_hash_free(tbl->hash_buckets, tbl->hash_mask + 1); - tbl->hash_buckets = NULL; + call_rcu(&tbl->nht->rcu, neigh_hash_free_rcu); + tbl->nht = NULL; kfree(tbl->phash_buckets); tbl->phash_buckets = NULL; @@ -1529,6 +1630,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct net_device *dev = NULL; int err = -EINVAL; + ASSERT_RTNL(); if (nlmsg_len(nlh) < sizeof(*ndm)) goto out; @@ -1538,7 +1640,7 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { - dev = dev_get_by_index(net, ndm->ndm_ifindex); + dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; @@ -1554,34 +1656,31 @@ static int neigh_delete(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) read_unlock(&neigh_tbl_lock); if (nla_len(dst_attr) < tbl->key_len) - goto out_dev_put; + goto out; if (ndm->ndm_flags & NTF_PROXY) { err = pneigh_delete(tbl, net, nla_data(dst_attr), dev); - goto out_dev_put; + goto out; } if (dev == NULL) - goto out_dev_put; + goto out; neigh = neigh_lookup(tbl, nla_data(dst_attr), dev); if (neigh == NULL) { err = -ENOENT; - goto out_dev_put; + goto out; } err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN); neigh_release(neigh); - goto out_dev_put; + goto out; } read_unlock(&neigh_tbl_lock); err = -EAFNOSUPPORT; -out_dev_put: - if (dev) - dev_put(dev); out: return err; } @@ -1595,6 +1694,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) struct net_device *dev = NULL; int err; + ASSERT_RTNL(); err = nlmsg_parse(nlh, sizeof(*ndm), tb, NDA_MAX, NULL); if (err < 0) goto out; @@ -1605,14 +1705,14 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) ndm = nlmsg_data(nlh); if (ndm->ndm_ifindex) { - dev = dev_get_by_index(net, ndm->ndm_ifindex); + dev = __dev_get_by_index(net, ndm->ndm_ifindex); if (dev == NULL) { err = -ENODEV; goto out; } if (tb[NDA_LLADDR] && nla_len(tb[NDA_LLADDR]) < dev->addr_len) - goto out_dev_put; + goto out; } read_lock(&neigh_tbl_lock); @@ -1626,7 +1726,7 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) read_unlock(&neigh_tbl_lock); if (nla_len(tb[NDA_DST]) < tbl->key_len) - goto out_dev_put; + goto out; dst = nla_data(tb[NDA_DST]); lladdr = tb[NDA_LLADDR] ? nla_data(tb[NDA_LLADDR]) : NULL; @@ -1639,29 +1739,29 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) pn->flags = ndm->ndm_flags; err = 0; } - goto out_dev_put; + goto out; } if (dev == NULL) - goto out_dev_put; + goto out; neigh = neigh_lookup(tbl, dst, dev); if (neigh == NULL) { if (!(nlh->nlmsg_flags & NLM_F_CREATE)) { err = -ENOENT; - goto out_dev_put; + goto out; } neigh = __neigh_lookup_errno(tbl, dst, dev); if (IS_ERR(neigh)) { err = PTR_ERR(neigh); - goto out_dev_put; + goto out; } } else { if (nlh->nlmsg_flags & NLM_F_EXCL) { err = -EEXIST; neigh_release(neigh); - goto out_dev_put; + goto out; } if (!(nlh->nlmsg_flags & NLM_F_REPLACE)) @@ -1674,15 +1774,11 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) } else err = neigh_update(neigh, lladdr, ndm->ndm_state, flags); neigh_release(neigh); - goto out_dev_put; + goto out; } read_unlock(&neigh_tbl_lock); err = -EAFNOSUPPORT; - -out_dev_put: - if (dev) - dev_put(dev); out: return err; } @@ -1748,18 +1844,22 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, unsigned long now = jiffies; unsigned int flush_delta = now - tbl->last_flush; unsigned int rand_delta = now - tbl->last_rand; - + struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, .ndtc_entry_size = tbl->entry_size, .ndtc_entries = atomic_read(&tbl->entries), .ndtc_last_flush = jiffies_to_msecs(flush_delta), .ndtc_last_rand = jiffies_to_msecs(rand_delta), - .ndtc_hash_rnd = tbl->hash_rnd, - .ndtc_hash_mask = tbl->hash_mask, .ndtc_proxy_qlen = tbl->proxy_queue.qlen, }; + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + ndc.ndtc_hash_rnd = nht->hash_rnd; + ndc.ndtc_hash_mask = nht->hash_mask; + rcu_read_unlock_bh(); + NLA_PUT(skb, NDTA_CONFIG, sizeof(ndc), &ndc); } @@ -2056,10 +2156,14 @@ static int neigh_fill_info(struct sk_buff *skb, struct neighbour *neigh, read_lock_bh(&neigh->lock); ndm->ndm_state = neigh->nud_state; - if ((neigh->nud_state & NUD_VALID) && - nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, neigh->ha) < 0) { - read_unlock_bh(&neigh->lock); - goto nla_put_failure; + if (neigh->nud_state & NUD_VALID) { + char haddr[MAX_ADDR_LEN]; + + neigh_ha_snapshot(haddr, neigh, neigh->dev); + if (nla_put(skb, NDA_LLADDR, neigh->dev->addr_len, haddr) < 0) { + read_unlock_bh(&neigh->lock); + goto nla_put_failure; + } } ci.ndm_used = jiffies_to_clock_t(now - neigh->used); @@ -2087,18 +2191,23 @@ static void neigh_update_notify(struct neighbour *neigh) static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, struct netlink_callback *cb) { - struct net * net = sock_net(skb->sk); + struct net *net = sock_net(skb->sk); struct neighbour *n; int rc, h, s_h = cb->args[1]; int idx, s_idx = idx = cb->args[2]; + struct neigh_hash_table *nht; - read_lock_bh(&tbl->lock); - for (h = 0; h <= tbl->hash_mask; h++) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + + for (h = 0; h <= nht->hash_mask; h++) { if (h < s_h) continue; if (h > s_h) s_idx = 0; - for (n = tbl->hash_buckets[h], idx = 0; n; n = n->next) { + for (n = rcu_dereference_bh(nht->hash_buckets[h]), idx = 0; + n != NULL; + n = rcu_dereference_bh(n->next)) { if (!net_eq(dev_net(n->dev), net)) continue; if (idx < s_idx) @@ -2107,17 +2216,16 @@ static int neigh_dump_table(struct neigh_table *tbl, struct sk_buff *skb, cb->nlh->nlmsg_seq, RTM_NEWNEIGH, NLM_F_MULTI) <= 0) { - read_unlock_bh(&tbl->lock); rc = -1; goto out; } - next: +next: idx++; } } - read_unlock_bh(&tbl->lock); rc = skb->len; out: + rcu_read_unlock_bh(); cb->args[1] = h; cb->args[2] = idx; return rc; @@ -2150,15 +2258,22 @@ static int neigh_dump_info(struct sk_buff *skb, struct netlink_callback *cb) void neigh_for_each(struct neigh_table *tbl, void (*cb)(struct neighbour *, void *), void *cookie) { int chain; + struct neigh_hash_table *nht; - read_lock_bh(&tbl->lock); - for (chain = 0; chain <= tbl->hash_mask; chain++) { + rcu_read_lock_bh(); + nht = rcu_dereference_bh(tbl->nht); + + read_lock(&tbl->lock); /* avoid resizes */ + for (chain = 0; chain <= nht->hash_mask; chain++) { struct neighbour *n; - for (n = tbl->hash_buckets[chain]; n; n = n->next) + for (n = rcu_dereference_bh(nht->hash_buckets[chain]); + n != NULL; + n = rcu_dereference_bh(n->next)) cb(n, cookie); } - read_unlock_bh(&tbl->lock); + read_unlock(&tbl->lock); + rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_for_each); @@ -2167,18 +2282,25 @@ void __neigh_for_each_release(struct neigh_table *tbl, int (*cb)(struct neighbour *)) { int chain; + struct neigh_hash_table *nht; - for (chain = 0; chain <= tbl->hash_mask; chain++) { - struct neighbour *n, **np; + nht = rcu_dereference_protected(tbl->nht, + lockdep_is_held(&tbl->lock)); + for (chain = 0; chain <= nht->hash_mask; chain++) { + struct neighbour *n; + struct neighbour __rcu **np; - np = &tbl->hash_buckets[chain]; - while ((n = *np) != NULL) { + np = &nht->hash_buckets[chain]; + while ((n = rcu_dereference_protected(*np, + lockdep_is_held(&tbl->lock))) != NULL) { int release; write_lock(&n->lock); release = cb(n); if (release) { - *np = n->next; + rcu_assign_pointer(*np, + rcu_dereference_protected(n->next, + lockdep_is_held(&tbl->lock))); n->dead = 1; } else np = &n->next; @@ -2196,13 +2318,13 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); - struct neigh_table *tbl = state->tbl; + struct neigh_hash_table *nht = state->nht; struct neighbour *n = NULL; int bucket = state->bucket; state->flags &= ~NEIGH_SEQ_IS_PNEIGH; - for (bucket = 0; bucket <= tbl->hash_mask; bucket++) { - n = tbl->hash_buckets[bucket]; + for (bucket = 0; bucket <= nht->hash_mask; bucket++) { + n = rcu_dereference_bh(nht->hash_buckets[bucket]); while (n) { if (!net_eq(dev_net(n->dev), net)) @@ -2219,8 +2341,8 @@ static struct neighbour *neigh_get_first(struct seq_file *seq) break; if (n->nud_state & ~NUD_NOARP) break; - next: - n = n->next; +next: + n = rcu_dereference_bh(n->next); } if (n) @@ -2237,14 +2359,14 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, { struct neigh_seq_state *state = seq->private; struct net *net = seq_file_net(seq); - struct neigh_table *tbl = state->tbl; + struct neigh_hash_table *nht = state->nht; if (state->neigh_sub_iter) { void *v = state->neigh_sub_iter(state, n, pos); if (v) return n; } - n = n->next; + n = rcu_dereference_bh(n->next); while (1) { while (n) { @@ -2261,17 +2383,17 @@ static struct neighbour *neigh_get_next(struct seq_file *seq, if (n->nud_state & ~NUD_NOARP) break; - next: - n = n->next; +next: + n = rcu_dereference_bh(n->next); } if (n) break; - if (++state->bucket > tbl->hash_mask) + if (++state->bucket > nht->hash_mask) break; - n = tbl->hash_buckets[state->bucket]; + n = rcu_dereference_bh(nht->hash_buckets[state->bucket]); } if (n && pos) @@ -2369,7 +2491,7 @@ static void *neigh_get_idx_any(struct seq_file *seq, loff_t *pos) } void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl, unsigned int neigh_seq_flags) - __acquires(tbl->lock) + __acquires(rcu_bh) { struct neigh_seq_state *state = seq->private; @@ -2377,7 +2499,8 @@ void *neigh_seq_start(struct seq_file *seq, loff_t *pos, struct neigh_table *tbl state->bucket = 0; state->flags = (neigh_seq_flags & ~NEIGH_SEQ_IS_PNEIGH); - read_lock_bh(&tbl->lock); + rcu_read_lock_bh(); + state->nht = rcu_dereference_bh(tbl->nht); return *pos ? neigh_get_idx_any(seq, pos) : SEQ_START_TOKEN; } @@ -2411,12 +2534,9 @@ out: EXPORT_SYMBOL(neigh_seq_next); void neigh_seq_stop(struct seq_file *seq, void *v) - __releases(tbl->lock) + __releases(rcu_bh) { - struct neigh_seq_state *state = seq->private; - struct neigh_table *tbl = state->tbl; - - read_unlock_bh(&tbl->lock); + rcu_read_unlock_bh(); } EXPORT_SYMBOL(neigh_seq_stop); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 99e7052d7323..a5ff5a89f376 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -29,6 +29,7 @@ static const char fmt_hex[] = "%#x\n"; static const char fmt_long_hex[] = "%#lx\n"; static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; +static const char fmt_u64[] = "%llu\n"; static inline int dev_isalive(const struct net_device *dev) { @@ -94,6 +95,7 @@ static ssize_t netdev_store(struct device *dev, struct device_attribute *attr, } NETDEVICE_SHOW(dev_id, fmt_hex); +NETDEVICE_SHOW(addr_assign_type, fmt_dec); NETDEVICE_SHOW(addr_len, fmt_dec); NETDEVICE_SHOW(iflink, fmt_dec); NETDEVICE_SHOW(ifindex, fmt_dec); @@ -294,6 +296,7 @@ static ssize_t show_ifalias(struct device *dev, } static struct device_attribute net_class_attributes[] = { + __ATTR(addr_assign_type, S_IRUGO, show_addr_assign_type, NULL), __ATTR(addr_len, S_IRUGO, show_addr_len, NULL), __ATTR(dev_id, S_IRUGO, show_dev_id, NULL), __ATTR(ifalias, S_IRUGO | S_IWUSR, show_ifalias, store_ifalias), @@ -324,14 +327,15 @@ static ssize_t netstat_show(const struct device *d, struct net_device *dev = to_net_dev(d); ssize_t ret = -EINVAL; - WARN_ON(offset > sizeof(struct net_device_stats) || - offset % sizeof(unsigned long) != 0); + WARN_ON(offset > sizeof(struct rtnl_link_stats64) || + offset % sizeof(u64) != 0); read_lock(&dev_base_lock); if (dev_isalive(dev)) { - const struct net_device_stats *stats = dev_get_stats(dev); - ret = sprintf(buf, fmt_ulong, - *(unsigned long *)(((u8 *) stats) + offset)); + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp); + + ret = sprintf(buf, fmt_u64, *(u64 *)(((u8 *) stats) + offset)); } read_unlock(&dev_base_lock); return ret; @@ -343,7 +347,7 @@ static ssize_t show_##name(struct device *d, \ struct device_attribute *attr, char *buf) \ { \ return netstat_show(d, attr, buf, \ - offsetof(struct net_device_stats, name)); \ + offsetof(struct rtnl_link_stats64, name)); \ } \ static DEVICE_ATTR(name, S_IRUGO, show_##name, NULL) @@ -511,7 +515,7 @@ static ssize_t rx_queue_attr_store(struct kobject *kobj, struct attribute *attr, return attribute->store(queue, attribute, buf, count); } -static struct sysfs_ops rx_queue_sysfs_ops = { +static const struct sysfs_ops rx_queue_sysfs_ops = { .show = rx_queue_attr_show, .store = rx_queue_attr_store, }; @@ -594,7 +598,8 @@ static ssize_t store_rps_map(struct netdev_rx_queue *queue, } spin_lock(&rps_map_lock); - old_map = queue->rps_map; + old_map = rcu_dereference_protected(queue->rps_map, + lockdep_is_held(&rps_map_lock)); rcu_assign_pointer(queue->rps_map, map); spin_unlock(&rps_map_lock); @@ -673,7 +678,8 @@ static ssize_t store_rps_dev_flow_table_cnt(struct netdev_rx_queue *queue, table = NULL; spin_lock(&rps_dev_flow_lock); - old_table = queue->rps_flow_table; + old_table = rcu_dereference_protected(queue->rps_flow_table, + lockdep_is_held(&rps_dev_flow_lock)); rcu_assign_pointer(queue->rps_flow_table, table); spin_unlock(&rps_dev_flow_lock); @@ -701,13 +707,17 @@ 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; + - if (queue->rps_map) - call_rcu(&queue->rps_map->rcu, rps_map_release); + map = rcu_dereference_raw(queue->rps_map); + if (map) + call_rcu(&map->rcu, rps_map_release); - if (queue->rps_flow_table) - call_rcu(&queue->rps_flow_table->rcu, - rps_dev_flow_table_release); + flow_table = rcu_dereference_raw(queue->rps_flow_table); + if (flow_table) + call_rcu(&flow_table->rcu, rps_dev_flow_table_release); if (atomic_dec_and_test(&first->count)) kfree(first); @@ -722,6 +732,7 @@ 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; @@ -734,38 +745,43 @@ static int rx_queue_add_kobject(struct net_device *net, int index) } kobject_uevent(kobj, KOBJ_ADD); + atomic_inc(&first->count); return error; } -static int rx_queue_register_kobjects(struct net_device *net) +int +net_rx_queue_update_kobjects(struct net_device *net, int old_num, int new_num) { int i; int error = 0; - net->queues_kset = kset_create_and_add("queues", - NULL, &net->dev.kobj); - if (!net->queues_kset) - return -ENOMEM; - for (i = 0; i < net->num_rx_queues; i++) { + for (i = old_num; i < new_num; i++) { error = rx_queue_add_kobject(net, i); - if (error) + if (error) { + new_num = old_num; break; + } } - if (error) - while (--i >= 0) - kobject_put(&net->_rx[i].kobj); + while (--i >= new_num) + kobject_put(&net->_rx[i].kobj); return error; } -static void rx_queue_remove_kobjects(struct net_device *net) +static int rx_queue_register_kobjects(struct net_device *net) { - int i; + 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); +} - for (i = 0; i < net->num_rx_queues; i++) - kobject_put(&net->_rx[i].kobj); +static void rx_queue_remove_kobjects(struct net_device *net) +{ + net_rx_queue_update_kobjects(net, net->real_num_rx_queues, 0); kset_unregister(net->queues_kset); } #endif /* CONFIG_RPS */ @@ -785,12 +801,13 @@ static const void *net_netlink_ns(struct sock *sk) return sock_net(sk); } -static struct kobj_ns_type_operations net_ns_type_operations = { +struct kobj_ns_type_operations net_ns_type_operations = { .type = KOBJ_NS_TYPE_NET, .current_ns = net_current_ns, .netlink_ns = net_netlink_ns, .initial_ns = net_initial_ns, }; +EXPORT_SYMBOL_GPL(net_ns_type_operations); static void net_kobj_ns_exit(struct net *net) { @@ -922,13 +939,12 @@ int netdev_class_create_file(struct class_attribute *class_attr) { return class_create_file(&net_class, class_attr); } +EXPORT_SYMBOL(netdev_class_create_file); void netdev_class_remove_file(struct class_attribute *class_attr) { class_remove_file(&net_class, class_attr); } - -EXPORT_SYMBOL(netdev_class_create_file); EXPORT_SYMBOL(netdev_class_remove_file); int netdev_kobject_init(void) diff --git a/net/core/net-sysfs.h b/net/core/net-sysfs.h index 805555e8b187..778e1571548d 100644 --- a/net/core/net-sysfs.h +++ b/net/core/net-sysfs.h @@ -4,4 +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 + #endif diff --git a/net/core/net-traces.c b/net/core/net-traces.c index afa6380ed88a..7f1bb2aba03b 100644 --- a/net/core/net-traces.c +++ b/net/core/net-traces.c @@ -26,6 +26,7 @@ #define CREATE_TRACE_POINTS #include <trace/events/skb.h> +#include <trace/events/net.h> #include <trace/events/napi.h> EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index c988e685433a..3f860261c5ee 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -42,7 +42,9 @@ static int net_assign_generic(struct net *net, int id, void *data) BUG_ON(!mutex_is_locked(&net_mutex)); BUG_ON(id == 0); - ng = old_ng = net->gen; + old_ng = rcu_dereference_protected(net->gen, + lockdep_is_held(&net_mutex)); + ng = old_ng; if (old_ng->len >= id) goto assign; diff --git a/net/core/netevent.c b/net/core/netevent.c index 95f81de87502..865f0ceb81fb 100644 --- a/net/core/netevent.c +++ b/net/core/netevent.c @@ -35,6 +35,7 @@ int register_netevent_notifier(struct notifier_block *nb) err = atomic_notifier_chain_register(&netevent_notif_chain, nb); return err; } +EXPORT_SYMBOL_GPL(register_netevent_notifier); /** * netevent_unregister_notifier - unregister a netevent notifier block @@ -50,6 +51,7 @@ int unregister_netevent_notifier(struct notifier_block *nb) { return atomic_notifier_chain_unregister(&netevent_notif_chain, nb); } +EXPORT_SYMBOL_GPL(unregister_netevent_notifier); /** * call_netevent_notifiers - call all netevent notifier blocks @@ -64,7 +66,4 @@ int call_netevent_notifiers(unsigned long val, void *v) { return atomic_notifier_call_chain(&netevent_notif_chain, val, v); } - -EXPORT_SYMBOL_GPL(register_netevent_notifier); -EXPORT_SYMBOL_GPL(unregister_netevent_notifier); EXPORT_SYMBOL_GPL(call_netevent_notifiers); diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 94825b109551..4e98ffac3af0 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -199,11 +199,13 @@ void netpoll_poll_dev(struct net_device *dev) zap_completion_queue(); } +EXPORT_SYMBOL(netpoll_poll_dev); void netpoll_poll(struct netpoll *np) { netpoll_poll_dev(np->dev); } +EXPORT_SYMBOL(netpoll_poll); static void refill_skbs(void) { @@ -286,12 +288,13 @@ static int netpoll_owner_active(struct net_device *dev) return 0; } -void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) +void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb, + struct net_device *dev) { int status = NETDEV_TX_BUSY; unsigned long tries; - struct net_device *dev = np->dev; const struct net_device_ops *ops = dev->netdev_ops; + /* It is up to the caller to keep npinfo alive. */ struct netpoll_info *npinfo = np->dev->npinfo; if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) { @@ -343,6 +346,7 @@ void netpoll_send_skb(struct netpoll *np, struct sk_buff *skb) schedule_delayed_work(&npinfo->tx_work,0); } } +EXPORT_SYMBOL(netpoll_send_skb_on_dev); void netpoll_send_udp(struct netpoll *np, const char *msg, int len) { @@ -404,6 +408,7 @@ void netpoll_send_udp(struct netpoll *np, const char *msg, int len) netpoll_send_skb(np, skb); } +EXPORT_SYMBOL(netpoll_send_udp); static void arp_reply(struct sk_buff *skb) { @@ -630,6 +635,7 @@ void netpoll_print_options(struct netpoll *np) printk(KERN_INFO "%s: remote ethernet address %pM\n", np->name, np->remote_mac); } +EXPORT_SYMBOL(netpoll_print_options); int netpoll_parse_options(struct netpoll *np, char *opt) { @@ -722,30 +728,29 @@ int netpoll_parse_options(struct netpoll *np, char *opt) np->name, cur); return -1; } +EXPORT_SYMBOL(netpoll_parse_options); -int netpoll_setup(struct netpoll *np) +int __netpoll_setup(struct netpoll *np) { - struct net_device *ndev = NULL; - struct in_device *in_dev; + struct net_device *ndev = np->dev; struct netpoll_info *npinfo; - struct netpoll *npe, *tmp; + const struct net_device_ops *ops; unsigned long flags; int err; - if (np->dev_name) - ndev = dev_get_by_name(&init_net, np->dev_name); - if (!ndev) { - printk(KERN_ERR "%s: %s doesn't exist, aborting.\n", + if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || + !ndev->netdev_ops->ndo_poll_controller) { + printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n", np->name, np->dev_name); - return -ENODEV; + err = -ENOTSUPP; + goto out; } - np->dev = ndev; if (!ndev->npinfo) { npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL); if (!npinfo) { err = -ENOMEM; - goto put; + goto out; } npinfo->rx_flags = 0; @@ -757,6 +762,13 @@ int netpoll_setup(struct netpoll *np) INIT_DELAYED_WORK(&npinfo->tx_work, queue_process); atomic_set(&npinfo->refcnt, 1); + + ops = np->dev->netdev_ops; + if (ops->ndo_netpoll_setup) { + err = ops->ndo_netpoll_setup(ndev, npinfo); + if (err) + goto free_npinfo; + } } else { npinfo = ndev->npinfo; atomic_inc(&npinfo->refcnt); @@ -764,12 +776,37 @@ int netpoll_setup(struct netpoll *np) npinfo->netpoll = np; - if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) || - !ndev->netdev_ops->ndo_poll_controller) { - printk(KERN_ERR "%s: %s doesn't support polling, aborting.\n", + if (np->rx_hook) { + spin_lock_irqsave(&npinfo->rx_lock, flags); + npinfo->rx_flags |= NETPOLL_RX_ENABLED; + list_add_tail(&np->rx, &npinfo->rx_np); + spin_unlock_irqrestore(&npinfo->rx_lock, flags); + } + + /* last thing to do is link it to the net device structure */ + rcu_assign_pointer(ndev->npinfo, npinfo); + + return 0; + +free_npinfo: + kfree(npinfo); +out: + return err; +} +EXPORT_SYMBOL_GPL(__netpoll_setup); + +int netpoll_setup(struct netpoll *np) +{ + struct net_device *ndev = NULL; + struct in_device *in_dev; + int err; + + if (np->dev_name) + ndev = dev_get_by_name(&init_net, np->dev_name); + if (!ndev) { + printk(KERN_ERR "%s: %s doesn't exist, aborting.\n", np->name, np->dev_name); - err = -ENOTSUPP; - goto release; + return -ENODEV; } if (!netif_running(ndev)) { @@ -785,7 +822,7 @@ int netpoll_setup(struct netpoll *np) if (err) { printk(KERN_ERR "%s: failed to open %s\n", np->name, ndev->name); - goto release; + goto put; } atleast = jiffies + HZ/10; @@ -822,7 +859,7 @@ int netpoll_setup(struct netpoll *np) printk(KERN_ERR "%s: no IP address for %s, aborting\n", np->name, np->dev_name); err = -EDESTADDRREQ; - goto release; + goto put; } np->local_ip = in_dev->ifa_list->ifa_local; @@ -830,38 +867,25 @@ int netpoll_setup(struct netpoll *np) printk(KERN_INFO "%s: local IP %pI4\n", np->name, &np->local_ip); } - if (np->rx_hook) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_flags |= NETPOLL_RX_ENABLED; - list_add_tail(&np->rx, &npinfo->rx_np); - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } + np->dev = ndev; /* fill up the skb queue */ refill_skbs(); - /* last thing to do is link it to the net device structure */ - ndev->npinfo = npinfo; + rtnl_lock(); + err = __netpoll_setup(np); + rtnl_unlock(); - /* avoid racing with NAPI reading npinfo */ - synchronize_rcu(); + if (err) + goto put; return 0; - release: - if (!ndev->npinfo) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_for_each_entry_safe(npe, tmp, &npinfo->rx_np, rx) { - npe->dev = NULL; - } - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - - kfree(npinfo); - } put: dev_put(ndev); return err; } +EXPORT_SYMBOL(netpoll_setup); static int __init netpoll_init(void) { @@ -870,49 +894,65 @@ static int __init netpoll_init(void) } core_initcall(netpoll_init); -void netpoll_cleanup(struct netpoll *np) +void __netpoll_cleanup(struct netpoll *np) { struct netpoll_info *npinfo; unsigned long flags; - if (np->dev) { - npinfo = np->dev->npinfo; - if (npinfo) { - if (!list_empty(&npinfo->rx_np)) { - spin_lock_irqsave(&npinfo->rx_lock, flags); - list_del(&np->rx); - if (list_empty(&npinfo->rx_np)) - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; - spin_unlock_irqrestore(&npinfo->rx_lock, flags); - } + npinfo = np->dev->npinfo; + if (!npinfo) + return; - if (atomic_dec_and_test(&npinfo->refcnt)) { - const struct net_device_ops *ops; - skb_queue_purge(&npinfo->arp_tx); - skb_queue_purge(&npinfo->txq); - cancel_rearming_delayed_work(&npinfo->tx_work); - - /* clean after last, unfinished work */ - __skb_queue_purge(&npinfo->txq); - kfree(npinfo); - ops = np->dev->netdev_ops; - if (ops->ndo_netpoll_cleanup) - ops->ndo_netpoll_cleanup(np->dev); - else - np->dev->npinfo = NULL; - } - } + if (!list_empty(&npinfo->rx_np)) { + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_del(&np->rx); + if (list_empty(&npinfo->rx_np)) + npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; + spin_unlock_irqrestore(&npinfo->rx_lock, flags); + } + + if (atomic_dec_and_test(&npinfo->refcnt)) { + const struct net_device_ops *ops; + + ops = np->dev->netdev_ops; + if (ops->ndo_netpoll_cleanup) + ops->ndo_netpoll_cleanup(np->dev); + + rcu_assign_pointer(np->dev->npinfo, NULL); + + /* avoid racing with NAPI reading npinfo */ + synchronize_rcu_bh(); + + skb_queue_purge(&npinfo->arp_tx); + skb_queue_purge(&npinfo->txq); + cancel_rearming_delayed_work(&npinfo->tx_work); - dev_put(np->dev); + /* clean after last, unfinished work */ + __skb_queue_purge(&npinfo->txq); + kfree(npinfo); } +} +EXPORT_SYMBOL_GPL(__netpoll_cleanup); + +void netpoll_cleanup(struct netpoll *np) +{ + if (!np->dev) + return; + rtnl_lock(); + __netpoll_cleanup(np); + rtnl_unlock(); + + dev_put(np->dev); np->dev = NULL; } +EXPORT_SYMBOL(netpoll_cleanup); int netpoll_trap(void) { return atomic_read(&trapped); } +EXPORT_SYMBOL(netpoll_trap); void netpoll_set_trap(int trap) { @@ -921,14 +961,4 @@ void netpoll_set_trap(int trap) else atomic_dec(&trapped); } - -EXPORT_SYMBOL(netpoll_send_skb); EXPORT_SYMBOL(netpoll_set_trap); -EXPORT_SYMBOL(netpoll_trap); -EXPORT_SYMBOL(netpoll_print_options); -EXPORT_SYMBOL(netpoll_parse_options); -EXPORT_SYMBOL(netpoll_setup); -EXPORT_SYMBOL(netpoll_cleanup); -EXPORT_SYMBOL(netpoll_send_udp); -EXPORT_SYMBOL(netpoll_poll_dev); -EXPORT_SYMBOL(netpoll_poll); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 1dacd7ba8dbb..fbce4b05a53e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -115,6 +115,9 @@ * command by Adit Ranadive <adit.262@gmail.com> * */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt + #include <linux/sys.h> #include <linux/types.h> #include <linux/module.h> @@ -169,11 +172,13 @@ #include <asm/dma.h> #include <asm/div64.h> /* do_div */ -#define VERSION "2.73" +#define VERSION "2.74" #define IP_NAME_SZ 32 #define MAX_MPLS_LABELS 16 /* This is the max label stack depth */ #define MPLS_STACK_BOTTOM htonl(0x00000100) +#define func_enter() pr_debug("entering %s\n", __func__); + /* Device flag bits */ #define F_IPSRC_RND (1<<0) /* IP-Src Random */ #define F_IPDST_RND (1<<1) /* IP-Dst Random */ @@ -424,7 +429,8 @@ static inline int ktime_lt(const ktime_t cmp1, const ktime_t cmp2) } static const char version[] = - "pktgen " VERSION ": Packet Generator for packet performance testing.\n"; + "Packet Generator for packet performance testing. " + "Version: " VERSION "\n"; static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *i); static int pktgen_add_device(struct pktgen_thread *t, const char *ifname); @@ -495,7 +501,7 @@ static ssize_t pgctrl_write(struct file *file, const char __user *buf, pktgen_reset_all_threads(); else - printk(KERN_WARNING "pktgen: Unknown command: %s\n", data); + pr_warning("Unknown command: %s\n", data); err = count; @@ -723,16 +729,14 @@ static int hex32_arg(const char __user *user_buffer, unsigned long maxlen, *num = 0; for (; i < maxlen; i++) { + int value; char c; *num <<= 4; if (get_user(c, &user_buffer[i])) return -EFAULT; - if ((c >= '0') && (c <= '9')) - *num |= c - '0'; - else if ((c >= 'a') && (c <= 'f')) - *num |= c - 'a' + 10; - else if ((c >= 'A') && (c <= 'F')) - *num |= c - 'A' + 10; + value = hex_to_bin(c); + if (value >= 0) + *num |= value; else break; } @@ -767,10 +771,10 @@ done: static unsigned long num_arg(const char __user * user_buffer, unsigned long maxlen, unsigned long *num) { - int i = 0; + int i; *num = 0; - for (; i < maxlen; i++) { + for (i = 0; i < maxlen; i++) { char c; if (get_user(c, &user_buffer[i])) return -EFAULT; @@ -785,9 +789,9 @@ static unsigned long num_arg(const char __user * user_buffer, static int strn_len(const char __user * user_buffer, unsigned int maxlen) { - int i = 0; + int i; - for (; i < maxlen; i++) { + for (i = 0; i < maxlen; i++) { char c; if (get_user(c, &user_buffer[i])) return -EFAULT; @@ -840,9 +844,9 @@ static ssize_t pktgen_if_write(struct file *file, const char __user * user_buffer, size_t count, loff_t * offset) { - struct seq_file *seq = (struct seq_file *)file->private_data; + struct seq_file *seq = file->private_data; struct pktgen_dev *pkt_dev = seq->private; - int i = 0, max, len; + int i, max, len; char name[16], valstr[32]; unsigned long value = 0; char *pg_result = NULL; @@ -852,17 +856,17 @@ static ssize_t pktgen_if_write(struct file *file, pg_result = &(pkt_dev->result[0]); if (count < 1) { - printk(KERN_WARNING "pktgen: wrong command format\n"); + pr_warning("wrong command format\n"); return -EINVAL; } - max = count - i; - tmp = count_trail_chars(&user_buffer[i], max); + max = count; + tmp = count_trail_chars(user_buffer, max); if (tmp < 0) { - printk(KERN_WARNING "pktgen: illegal format\n"); + pr_warning("illegal format\n"); return tmp; } - i += tmp; + i = tmp; /* Read variable name */ @@ -883,10 +887,11 @@ static ssize_t pktgen_if_write(struct file *file, i += len; if (debug) { - char tb[count + 1]; - if (copy_from_user(tb, user_buffer, count)) + size_t copy = min(count, 1023); + char tb[copy + 1]; + if (copy_from_user(tb, user_buffer, copy)) return -EFAULT; - tb[count] = 0; + tb[copy] = 0; printk(KERN_DEBUG "pktgen: %s,%lu buffer -:%s:-\n", name, (unsigned long)count, tb); } @@ -980,6 +985,36 @@ static ssize_t pktgen_if_write(struct file *file, (unsigned long long) pkt_dev->delay); return count; } + if (!strcmp(name, "rate")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + if (!value) + return len; + pkt_dev->delay = pkt_dev->min_pkt_size*8*NSEC_PER_USEC/value; + if (debug) + pr_info("Delay set at: %llu ns\n", pkt_dev->delay); + + sprintf(pg_result, "OK: rate=%lu", value); + return count; + } + if (!strcmp(name, "ratep")) { + len = num_arg(&user_buffer[i], 10, &value); + if (len < 0) + return len; + + i += len; + if (!value) + return len; + pkt_dev->delay = NSEC_PER_SEC/value; + if (debug) + pr_info("Delay set at: %llu ns\n", pkt_dev->delay); + + sprintf(pg_result, "OK: rate=%lu", value); + return count; + } if (!strcmp(name, "udp_src_min")) { len = num_arg(&user_buffer[i], 10, &value); if (len < 0) @@ -1398,18 +1433,12 @@ static ssize_t pktgen_if_write(struct file *file, i += len; for (*m = 0; *v && m < pkt_dev->dst_mac + 6; v++) { - if (*v >= '0' && *v <= '9') { - *m *= 16; - *m += *v - '0'; - } - if (*v >= 'A' && *v <= 'F') { - *m *= 16; - *m += *v - 'A' + 10; - } - if (*v >= 'a' && *v <= 'f') { - *m *= 16; - *m += *v - 'a' + 10; - } + int value; + + value = hex_to_bin(*v); + if (value >= 0) + *m = *m * 16 + value; + if (*v == ':') { m++; *m = 0; @@ -1440,18 +1469,12 @@ static ssize_t pktgen_if_write(struct file *file, i += len; for (*m = 0; *v && m < pkt_dev->src_mac + 6; v++) { - if (*v >= '0' && *v <= '9') { - *m *= 16; - *m += *v - '0'; - } - if (*v >= 'A' && *v <= 'F') { - *m *= 16; - *m += *v - 'A' + 10; - } - if (*v >= 'a' && *v <= 'f') { - *m *= 16; - *m += *v - 'a' + 10; - } + int value; + + value = hex_to_bin(*v); + if (value >= 0) + *m = *m * 16 + value; + if (*v == ':') { m++; *m = 0; @@ -1740,9 +1763,9 @@ static ssize_t pktgen_thread_write(struct file *file, const char __user * user_buffer, size_t count, loff_t * offset) { - struct seq_file *seq = (struct seq_file *)file->private_data; + struct seq_file *seq = file->private_data; struct pktgen_thread *t = seq->private; - int i = 0, max, len, ret; + int i, max, len, ret; char name[40]; char *pg_result; @@ -1751,12 +1774,12 @@ static ssize_t pktgen_thread_write(struct file *file, return -EINVAL; } - max = count - i; - len = count_trail_chars(&user_buffer[i], max); + max = count; + len = count_trail_chars(user_buffer, max); if (len < 0) return len; - i += len; + i = len; /* Read variable name */ @@ -1781,7 +1804,7 @@ static ssize_t pktgen_thread_write(struct file *file, name, (unsigned long)count); if (!t) { - printk(KERN_ERR "pktgen: ERROR: No thread\n"); + pr_err("ERROR: No thread\n"); ret = -EINVAL; goto out; } @@ -1874,7 +1897,7 @@ static void pktgen_mark_device(const char *ifname) int i = 0; mutex_lock(&pktgen_thread_lock); - pr_debug("pktgen: pktgen_mark_device marking %s for removal\n", ifname); + pr_debug("%s: marking %s for removal\n", __func__, ifname); while (1) { @@ -1883,15 +1906,14 @@ static void pktgen_mark_device(const char *ifname) break; /* success */ mutex_unlock(&pktgen_thread_lock); - pr_debug("pktgen: pktgen_mark_device waiting for %s " - "to disappear....\n", ifname); + pr_debug("%s: waiting for %s to disappear....\n", + __func__, ifname); schedule_timeout_interruptible(msecs_to_jiffies(msec_per_try)); mutex_lock(&pktgen_thread_lock); if (++i >= max_tries) { - printk(KERN_ERR "pktgen_mark_device: timed out after " - "waiting %d msec for device %s to be removed\n", - msec_per_try * i, ifname); + pr_err("%s: timed out after waiting %d msec for device %s to be removed\n", + __func__, msec_per_try * i, ifname); break; } @@ -1918,8 +1940,8 @@ static void pktgen_change_name(struct net_device *dev) &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) - printk(KERN_ERR "pktgen: can't move proc " - " entry for '%s'\n", dev->name); + pr_err("can't move proc entry for '%s'\n", + dev->name); break; } } @@ -1954,7 +1976,7 @@ static struct net_device *pktgen_dev_get_by_name(struct pktgen_dev *pkt_dev, const char *ifname) { char b[IFNAMSIZ+5]; - int i = 0; + int i; for (i = 0; ifname[i] != '@'; i++) { if (i == IFNAMSIZ) @@ -1983,15 +2005,15 @@ static int pktgen_setup_dev(struct pktgen_dev *pkt_dev, const char *ifname) odev = pktgen_dev_get_by_name(pkt_dev, ifname); if (!odev) { - printk(KERN_ERR "pktgen: no such netdevice: \"%s\"\n", ifname); + pr_err("no such netdevice: \"%s\"\n", ifname); return -ENODEV; } if (odev->type != ARPHRD_ETHER) { - printk(KERN_ERR "pktgen: not an ethernet device: \"%s\"\n", ifname); + pr_err("not an ethernet device: \"%s\"\n", ifname); err = -EINVAL; } else if (!netif_running(odev)) { - printk(KERN_ERR "pktgen: device is down: \"%s\"\n", ifname); + pr_err("device is down: \"%s\"\n", ifname); err = -ENETDOWN; } else { pkt_dev->odev = odev; @@ -2010,8 +2032,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) int ntxq; if (!pkt_dev->odev) { - printk(KERN_ERR "pktgen: ERROR: pkt_dev->odev == NULL in " - "setup_inject.\n"); + pr_err("ERROR: pkt_dev->odev == NULL in setup_inject\n"); sprintf(pkt_dev->result, "ERROR: pkt_dev->odev == NULL in setup_inject.\n"); return; @@ -2021,19 +2042,15 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) ntxq = pkt_dev->odev->real_num_tx_queues; if (ntxq <= pkt_dev->queue_map_min) { - printk(KERN_WARNING "pktgen: WARNING: Requested " - "queue_map_min (zero-based) (%d) exceeds valid range " - "[0 - %d] for (%d) queues on %s, resetting\n", - pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odevname); + pr_warning("WARNING: Requested queue_map_min (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_min, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); pkt_dev->queue_map_min = ntxq - 1; } if (pkt_dev->queue_map_max >= ntxq) { - printk(KERN_WARNING "pktgen: WARNING: Requested " - "queue_map_max (zero-based) (%d) exceeds valid range " - "[0 - %d] for (%d) queues on %s, resetting\n", - pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, - pkt_dev->odevname); + pr_warning("WARNING: Requested queue_map_max (zero-based) (%d) exceeds valid range [0 - %d] for (%d) queues on %s, resetting\n", + pkt_dev->queue_map_max, (ntxq ?: 1) - 1, ntxq, + pkt_dev->odevname); pkt_dev->queue_map_max = ntxq - 1; } @@ -2093,8 +2110,7 @@ static void pktgen_setup_inject(struct pktgen_dev *pkt_dev) } rcu_read_unlock(); if (err) - printk(KERN_ERR "pktgen: ERROR: IPv6 link " - "address not availble.\n"); + pr_err("ERROR: IPv6 link address not available\n"); } #endif } else { @@ -2142,15 +2158,15 @@ static void spin(struct pktgen_dev *pkt_dev, ktime_t spin_until) hrtimer_init_on_stack(&t.timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS); hrtimer_set_expires(&t.timer, spin_until); - remaining = ktime_to_us(hrtimer_expires_remaining(&t.timer)); + remaining = ktime_to_ns(hrtimer_expires_remaining(&t.timer)); if (remaining <= 0) { pkt_dev->next_tx = ktime_add_ns(spin_until, pkt_dev->delay); return; } start_time = ktime_now(); - if (remaining < 100) - udelay(remaining); /* really small just spin */ + if (remaining < 100000) + ndelay(remaining); /* really small just spin */ else { /* see do_nanosleep */ hrtimer_init_sleeper(&t, current); @@ -2504,8 +2520,8 @@ static void free_SAs(struct pktgen_dev *pkt_dev) { if (pkt_dev->cflows) { /* let go of the SAs if we have them */ - int i = 0; - for (; i < pkt_dev->cflows; i++) { + int i; + for (i = 0; i < pkt_dev->cflows; i++) { struct xfrm_state *x = pkt_dev->flows[i].x; if (x) { xfrm_state_put(x); @@ -2528,8 +2544,8 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, if (nhead > 0) { ret = pskb_expand_head(skb, nhead, 0, GFP_ATOMIC); if (ret < 0) { - printk(KERN_ERR "Error expanding " - "ipsec packet %d\n", ret); + pr_err("Error expanding ipsec packet %d\n", + ret); goto err; } } @@ -2538,8 +2554,7 @@ static int process_ipsec(struct pktgen_dev *pkt_dev, skb_pull(skb, ETH_HLEN); ret = pktgen_output_ipsec(skb, pkt_dev); if (ret) { - printk(KERN_ERR "Error creating ipsec " - "packet %d\n", ret); + pr_err("Error creating ipsec packet %d\n", ret); goto err; } /* restore ll */ @@ -3015,8 +3030,7 @@ static struct sk_buff *fill_packet_ipv6(struct net_device *odev, if (datalen < sizeof(struct pktgen_hdr)) { datalen = sizeof(struct pktgen_hdr); if (net_ratelimit()) - printk(KERN_INFO "pktgen: increased datalen to %d\n", - datalen); + pr_info("increased datalen to %d\n", datalen); } udph->source = htons(pkt_dev->cur_udp_src); @@ -3143,7 +3157,7 @@ static void pktgen_run(struct pktgen_thread *t) struct pktgen_dev *pkt_dev; int started = 0; - pr_debug("pktgen: entering pktgen_run. %p\n", t); + func_enter(); if_lock(t); list_for_each_entry(pkt_dev, &t->if_list, list) { @@ -3176,7 +3190,7 @@ static void pktgen_stop_all_threads_ifs(void) { struct pktgen_thread *t; - pr_debug("pktgen: entering pktgen_stop_all_threads_ifs.\n"); + func_enter(); mutex_lock(&pktgen_thread_lock); @@ -3241,7 +3255,7 @@ static void pktgen_run_all_threads(void) { struct pktgen_thread *t; - pr_debug("pktgen: entering pktgen_run_all_threads.\n"); + func_enter(); mutex_lock(&pktgen_thread_lock); @@ -3260,7 +3274,7 @@ static void pktgen_reset_all_threads(void) { struct pktgen_thread *t; - pr_debug("pktgen: entering pktgen_reset_all_threads.\n"); + func_enter(); mutex_lock(&pktgen_thread_lock); @@ -3310,8 +3324,8 @@ static int pktgen_stop_device(struct pktgen_dev *pkt_dev) int nr_frags = pkt_dev->skb ? skb_shinfo(pkt_dev->skb)->nr_frags : -1; if (!pkt_dev->running) { - printk(KERN_WARNING "pktgen: interface: %s is already " - "stopped\n", pkt_dev->odevname); + pr_warning("interface: %s is already stopped\n", + pkt_dev->odevname); return -EINVAL; } @@ -3347,7 +3361,7 @@ static void pktgen_stop(struct pktgen_thread *t) { struct pktgen_dev *pkt_dev; - pr_debug("pktgen: entering pktgen_stop\n"); + func_enter(); if_lock(t); @@ -3367,7 +3381,7 @@ static void pktgen_rem_one_if(struct pktgen_thread *t) struct list_head *q, *n; struct pktgen_dev *cur; - pr_debug("pktgen: entering pktgen_rem_one_if\n"); + func_enter(); if_lock(t); @@ -3393,9 +3407,10 @@ static void pktgen_rem_all_ifs(struct pktgen_thread *t) struct list_head *q, *n; struct pktgen_dev *cur; + func_enter(); + /* Remove all devices, free mem */ - pr_debug("pktgen: entering pktgen_rem_all_ifs\n"); if_lock(t); list_for_each_safe(q, n, &t->if_list) { @@ -3477,8 +3492,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) pkt_dev->skb = fill_packet(odev, pkt_dev); if (pkt_dev->skb == NULL) { - printk(KERN_ERR "pktgen: ERROR: couldn't " - "allocate skb in fill_packet.\n"); + pr_err("ERROR: couldn't allocate skb in fill_packet\n"); schedule(); pkt_dev->clone_count--; /* back out increment, OOM */ return; @@ -3558,8 +3572,7 @@ static int pktgen_thread_worker(void *arg) init_waitqueue_head(&t->queue); complete(&t->start_done); - pr_debug("pktgen: starting pktgen/%d: pid=%d\n", - cpu, task_pid_nr(current)); + pr_debug("starting pktgen/%d: pid=%d\n", cpu, task_pid_nr(current)); set_current_state(TASK_INTERRUPTIBLE); @@ -3612,13 +3625,13 @@ static int pktgen_thread_worker(void *arg) set_current_state(TASK_INTERRUPTIBLE); } - pr_debug("pktgen: %s stopping all device\n", t->tsk->comm); + pr_debug("%s stopping all device\n", t->tsk->comm); pktgen_stop(t); - pr_debug("pktgen: %s removing all device\n", t->tsk->comm); + pr_debug("%s removing all device\n", t->tsk->comm); pktgen_rem_all_ifs(t); - pr_debug("pktgen: %s removing thread.\n", t->tsk->comm); + pr_debug("%s removing thread\n", t->tsk->comm); pktgen_rem_thread(t); return 0; @@ -3642,7 +3655,7 @@ static struct pktgen_dev *pktgen_find_dev(struct pktgen_thread *t, } if_unlock(t); - pr_debug("pktgen: find_dev(%s) returning %p\n", ifname, pkt_dev); + pr_debug("find_dev(%s) returning %p\n", ifname, pkt_dev); return pkt_dev; } @@ -3658,8 +3671,7 @@ static int add_dev_to_thread(struct pktgen_thread *t, if_lock(t); if (pkt_dev->pg_thread) { - printk(KERN_ERR "pktgen: ERROR: already assigned " - "to a thread.\n"); + pr_err("ERROR: already assigned to a thread\n"); rv = -EBUSY; goto out; } @@ -3685,7 +3697,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev = __pktgen_NN_threads(ifname, FIND); if (pkt_dev) { - printk(KERN_ERR "pktgen: ERROR: interface already used.\n"); + pr_err("ERROR: interface already used\n"); return -EBUSY; } @@ -3730,7 +3742,7 @@ static int pktgen_add_device(struct pktgen_thread *t, const char *ifname) pkt_dev->entry = proc_create_data(ifname, 0600, pg_proc_dir, &pktgen_if_fops, pkt_dev); if (!pkt_dev->entry) { - printk(KERN_ERR "pktgen: cannot create %s/%s procfs entry.\n", + pr_err("cannot create %s/%s procfs entry\n", PG_PROC_DIR, ifname); err = -EINVAL; goto out2; @@ -3761,8 +3773,7 @@ static int __init pktgen_create_thread(int cpu) t = kzalloc_node(sizeof(struct pktgen_thread), GFP_KERNEL, cpu_to_node(cpu)); if (!t) { - printk(KERN_ERR "pktgen: ERROR: out of memory, can't " - "create new thread.\n"); + pr_err("ERROR: out of memory, can't create new thread\n"); return -ENOMEM; } @@ -3776,8 +3787,7 @@ static int __init pktgen_create_thread(int cpu) p = kthread_create(pktgen_thread_worker, t, "kpktgend_%d", cpu); if (IS_ERR(p)) { - printk(KERN_ERR "pktgen: kernel_thread() failed " - "for cpu %d\n", t->cpu); + pr_err("kernel_thread() failed for cpu %d\n", t->cpu); list_del(&t->th_list); kfree(t); return PTR_ERR(p); @@ -3788,7 +3798,7 @@ static int __init pktgen_create_thread(int cpu) pe = proc_create_data(t->tsk->comm, 0600, pg_proc_dir, &pktgen_thread_fops, t); if (!pe) { - printk(KERN_ERR "pktgen: cannot create %s/%s procfs entry.\n", + pr_err("cannot create %s/%s procfs entry\n", PG_PROC_DIR, t->tsk->comm); kthread_stop(p); list_del(&t->th_list); @@ -3822,11 +3832,10 @@ static int pktgen_remove_device(struct pktgen_thread *t, struct pktgen_dev *pkt_dev) { - pr_debug("pktgen: remove_device pkt_dev=%p\n", pkt_dev); + pr_debug("remove_device pkt_dev=%p\n", pkt_dev); if (pkt_dev->running) { - printk(KERN_WARNING "pktgen: WARNING: trying to remove a " - "running interface, stopping it now.\n"); + pr_warning("WARNING: trying to remove a running interface, stopping it now\n"); pktgen_stop_device(pkt_dev); } @@ -3857,7 +3866,7 @@ static int __init pg_init(void) int cpu; struct proc_dir_entry *pe; - printk(KERN_INFO "%s", version); + pr_info("%s", version); pg_proc_dir = proc_mkdir(PG_PROC_DIR, init_net.proc_net); if (!pg_proc_dir) @@ -3865,8 +3874,7 @@ static int __init pg_init(void) pe = proc_create(PGCTRL, 0600, pg_proc_dir, &pktgen_fops); if (pe == NULL) { - printk(KERN_ERR "pktgen: ERROR: cannot create %s " - "procfs entry.\n", PGCTRL); + pr_err("ERROR: cannot create %s procfs entry\n", PGCTRL); proc_net_remove(&init_net, PG_PROC_DIR); return -EINVAL; } @@ -3879,13 +3887,12 @@ static int __init pg_init(void) err = pktgen_create_thread(cpu); if (err) - printk(KERN_WARNING "pktgen: WARNING: Cannot create " - "thread for cpu %d (%d)\n", cpu, err); + pr_warning("WARNING: Cannot create thread for cpu %d (%d)\n", + cpu, err); } if (list_empty(&pktgen_threads)) { - printk(KERN_ERR "pktgen: ERROR: Initialization failed for " - "all threads\n"); + pr_err("ERROR: Initialization failed for all threads\n"); unregister_netdevice_notifier(&pktgen_notifier_block); remove_proc_entry(PGCTRL, pg_proc_dir); proc_net_remove(&init_net, PG_PROC_DIR); @@ -3899,8 +3906,6 @@ static void __exit pg_cleanup(void) { struct pktgen_thread *t; struct list_head *q, *n; - wait_queue_head_t queue; - init_waitqueue_head(&queue); /* Stop all interfaces & threads */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 1a2af24e9e3d..8121268ddbdd 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -299,14 +299,6 @@ static void __rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) unregister_netdevice_many(&list_kill); } -void rtnl_kill_links(struct net *net, struct rtnl_link_ops *ops) -{ - rtnl_lock(); - __rtnl_kill_links(net, ops); - rtnl_unlock(); -} -EXPORT_SYMBOL_GPL(rtnl_kill_links); - /** * __rtnl_link_unregister - Unregister rtnl_link_ops from rtnetlink. * @ops: struct rtnl_link_ops * to unregister @@ -579,7 +571,7 @@ static unsigned int rtnl_dev_combine_flags(const struct net_device *dev, } static void copy_rtnl_link_stats(struct rtnl_link_stats *a, - const struct net_device_stats *b) + const struct rtnl_link_stats64 *b) { a->rx_packets = b->rx_packets; a->tx_packets = b->tx_packets; @@ -610,38 +602,9 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->tx_compressed = b->tx_compressed; } -static void copy_rtnl_link_stats64(void *v, const struct net_device_stats *b) +static void copy_rtnl_link_stats64(void *v, const struct rtnl_link_stats64 *b) { - struct rtnl_link_stats64 a; - - a.rx_packets = b->rx_packets; - a.tx_packets = b->tx_packets; - a.rx_bytes = b->rx_bytes; - a.tx_bytes = b->tx_bytes; - a.rx_errors = b->rx_errors; - a.tx_errors = b->tx_errors; - a.rx_dropped = b->rx_dropped; - a.tx_dropped = b->tx_dropped; - - a.multicast = b->multicast; - a.collisions = b->collisions; - - a.rx_length_errors = b->rx_length_errors; - a.rx_over_errors = b->rx_over_errors; - a.rx_crc_errors = b->rx_crc_errors; - a.rx_frame_errors = b->rx_frame_errors; - a.rx_fifo_errors = b->rx_fifo_errors; - a.rx_missed_errors = b->rx_missed_errors; - - a.tx_aborted_errors = b->tx_aborted_errors; - a.tx_carrier_errors = b->tx_carrier_errors; - a.tx_fifo_errors = b->tx_fifo_errors; - a.tx_heartbeat_errors = b->tx_heartbeat_errors; - a.tx_window_errors = b->tx_window_errors; - - a.rx_compressed = b->rx_compressed; - a.tx_compressed = b->tx_compressed; - memcpy(v, &a, sizeof(a)); + memcpy(v, b, sizeof(*b)); } /* All VF info */ @@ -686,7 +649,7 @@ static size_t rtnl_port_size(const struct net_device *dev) return port_self_size; } -static inline size_t if_nlmsg_size(const struct net_device *dev) +static noinline size_t if_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) + nla_total_size(IFNAMSIZ) /* IFLA_IFNAME */ @@ -791,7 +754,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, { struct ifinfomsg *ifm; struct nlmsghdr *nlh; - const struct net_device_stats *stats; + struct rtnl_link_stats64 temp; + const struct rtnl_link_stats64 *stats; struct nlattr *attr; nlh = nlmsg_put(skb, pid, seq, type, sizeof(*ifm), flags); @@ -847,7 +811,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, if (attr == NULL) goto nla_put_failure; - stats = dev_get_stats(dev); + stats = dev_get_stats(dev, &temp); copy_rtnl_link_stats(nla_data(attr), stats); attr = nla_reserve(skb, IFLA_STATS64, diff --git a/net/core/scm.c b/net/core/scm.c index b88f6f9d0b97..413cab89017d 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -130,6 +130,7 @@ void __scm_destroy(struct scm_cookie *scm) } } } +EXPORT_SYMBOL(__scm_destroy); int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) { @@ -170,6 +171,30 @@ int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p) err = scm_check_creds(&p->creds); if (err) goto error; + + if (pid_vnr(p->pid) != p->creds.pid) { + struct pid *pid; + err = -ESRCH; + pid = find_get_pid(p->creds.pid); + if (!pid) + goto error; + put_pid(p->pid); + p->pid = pid; + } + + if ((p->cred->euid != p->creds.uid) || + (p->cred->egid != p->creds.gid)) { + struct cred *cred; + err = -ENOMEM; + cred = prepare_creds(); + if (!cred) + goto error; + + cred->uid = cred->euid = p->creds.uid; + cred->gid = cred->egid = p->creds.uid; + put_cred(p->cred); + p->cred = cred; + } break; default: goto error; @@ -187,6 +212,7 @@ error: scm_destroy(p); return err; } +EXPORT_SYMBOL(__scm_send); int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) { @@ -225,6 +251,7 @@ int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data) out: return err; } +EXPORT_SYMBOL(put_cmsg); void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { @@ -294,6 +321,7 @@ void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) */ __scm_destroy(scm); } +EXPORT_SYMBOL(scm_detach_fds); struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) { @@ -311,9 +339,4 @@ struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl) } return new_fpl; } - -EXPORT_SYMBOL(__scm_destroy); -EXPORT_SYMBOL(__scm_send); -EXPORT_SYMBOL(put_cmsg); -EXPORT_SYMBOL(scm_detach_fds); EXPORT_SYMBOL(scm_fp_dup); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index ce88293a34e2..104f8444754a 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -202,8 +202,6 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, skb->data = data; skb_reset_tail_pointer(skb); skb->end = skb->tail + size; - kmemcheck_annotate_bitfield(skb, flags1); - kmemcheck_annotate_bitfield(skb, flags2); #ifdef NET_SKBUFF_DATA_USES_OFFSET skb->mac_header = ~0U; #endif @@ -249,10 +247,9 @@ EXPORT_SYMBOL(__alloc_skb); struct sk_buff *__netdev_alloc_skb(struct net_device *dev, unsigned int length, gfp_t gfp_mask) { - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; struct sk_buff *skb; - skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, node); + skb = __alloc_skb(length + NET_SKB_PAD, gfp_mask, 0, NUMA_NO_NODE); if (likely(skb)) { skb_reserve(skb, NET_SKB_PAD); skb->dev = dev; @@ -261,16 +258,6 @@ struct sk_buff *__netdev_alloc_skb(struct net_device *dev, } EXPORT_SYMBOL(__netdev_alloc_skb); -struct page *__netdev_alloc_page(struct net_device *dev, gfp_t gfp_mask) -{ - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; - struct page *page; - - page = alloc_pages_node(node, gfp_mask, 0); - return page; -} -EXPORT_SYMBOL(__netdev_alloc_page); - void skb_add_rx_frag(struct sk_buff *skb, int i, struct page *page, int off, int size) { @@ -340,7 +327,7 @@ static void skb_release_data(struct sk_buff *skb) put_page(skb_shinfo(skb)->frags[i].page); } - if (skb_has_frags(skb)) + if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); kfree(skb->head); @@ -466,6 +453,7 @@ void consume_skb(struct sk_buff *skb) smp_rmb(); else if (likely(!atomic_dec_and_test(&skb->users))) return; + trace_consume_skb(skb); __kfree_skb(skb); } EXPORT_SYMBOL(consume_skb); @@ -685,16 +673,10 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) { - int headerlen = skb->data - skb->head; - /* - * Allocate the copy buffer - */ - struct sk_buff *n; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - n = alloc_skb(skb->end + skb->data_len, gfp_mask); -#else - n = alloc_skb(skb->end - skb->head + skb->data_len, gfp_mask); -#endif + int headerlen = skb_headroom(skb); + unsigned int size = (skb_end_pointer(skb) - skb->head) + skb->data_len; + struct sk_buff *n = alloc_skb(size, gfp_mask); + if (!n) return NULL; @@ -726,20 +708,14 @@ EXPORT_SYMBOL(skb_copy); struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) { - /* - * Allocate the copy buffer - */ - struct sk_buff *n; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - n = alloc_skb(skb->end, gfp_mask); -#else - n = alloc_skb(skb->end - skb->head, gfp_mask); -#endif + unsigned int size = skb_end_pointer(skb) - skb->head; + struct sk_buff *n = alloc_skb(size, gfp_mask); + if (!n) goto out; /* Set the data pointer */ - skb_reserve(n, skb->data - skb->head); + skb_reserve(n, skb_headroom(skb)); /* Set the tail pointer and length */ skb_put(n, skb_headlen(skb)); /* Copy the bytes */ @@ -759,7 +735,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) skb_shinfo(n)->nr_frags = i; } - if (skb_has_frags(skb)) { + if (skb_has_frag_list(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } @@ -791,12 +767,9 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, { int i; u8 *data; -#ifdef NET_SKBUFF_DATA_USES_OFFSET - int size = nhead + skb->end + ntail; -#else - int size = nhead + (skb->end - skb->head) + ntail; -#endif + int size = nhead + (skb_end_pointer(skb) - skb->head) + ntail; long off; + bool fastpath; BUG_ON(nhead < 0); @@ -810,23 +783,36 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, goto nodata; /* Copy only real data... and, alas, header. This should be - * optimized for the cases when header is void. */ -#ifdef NET_SKBUFF_DATA_USES_OFFSET - memcpy(data + nhead, skb->head, skb->tail); -#else - memcpy(data + nhead, skb->head, skb->tail - skb->head); -#endif - memcpy(data + size, skb_end_pointer(skb), - sizeof(struct skb_shared_info)); + * optimized for the cases when header is void. + */ + memcpy(data + nhead, skb->head, skb_tail_pointer(skb) - skb->head); - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) - get_page(skb_shinfo(skb)->frags[i].page); + memcpy((struct skb_shared_info *)(data + size), + skb_shinfo(skb), + offsetof(struct skb_shared_info, frags[skb_shinfo(skb)->nr_frags])); - if (skb_has_frags(skb)) - skb_clone_fraglist(skb); + /* 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; - skb_release_data(skb); + fastpath = atomic_read(&skb_shinfo(skb)->dataref) == delta; + } + + if (fastpath) { + kfree(skb->head); + } else { + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + get_page(skb_shinfo(skb)->frags[i].page); + if (skb_has_frag_list(skb)) + skb_clone_fraglist(skb); + + skb_release_data(skb); + } off = (data + nhead) - skb->head; skb->head = data; @@ -1099,7 +1085,7 @@ drop_pages: for (; i < nfrags; i++) put_page(skb_shinfo(skb)->frags[i].page); - if (skb_has_frags(skb)) + if (skb_has_frag_list(skb)) skb_drop_fraglist(skb); goto done; } @@ -1194,7 +1180,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ - if (!skb_has_frags(skb)) + if (!skb_has_frag_list(skb)) goto pull_pages; /* Estimate size of pulled pages. */ @@ -2323,7 +2309,7 @@ next_skb: st->frag_data = NULL; } - if (st->root_skb == st->cur_skb && skb_has_frags(st->root_skb)) { + if (st->root_skb == st->cur_skb && skb_has_frag_list(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; @@ -2486,7 +2472,6 @@ unsigned char *skb_pull_rcsum(struct sk_buff *skb, unsigned int len) skb_postpull_rcsum(skb, skb->data, len); return skb->data += len; } - EXPORT_SYMBOL_GPL(skb_pull_rcsum); /** @@ -2574,6 +2559,10 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) __copy_skb_header(nskb, skb); nskb->mac_len = skb->mac_len; + /* nskb and skb might have different headroom */ + if (nskb->ip_summed == CHECKSUM_PARTIAL) + nskb->csum_start += skb_headroom(nskb) - headroom; + skb_reset_mac_header(nskb); skb_set_network_header(nskb, skb->mac_len); nskb->transport_header = (nskb->network_header + @@ -2704,7 +2693,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) return -E2BIG; headroom = skb_headroom(p); - nskb = netdev_alloc_skb(p->dev, headroom + skb_gro_offset(p)); + nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; @@ -2890,7 +2879,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) return -ENOMEM; /* Easy case. Most of packets will go this way. */ - if (!skb_has_frags(skb)) { + if (!skb_has_frag_list(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more @@ -2925,7 +2914,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || - skb_has_frags(skb1) || + skb_has_frag_list(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } @@ -2934,7 +2923,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || - skb_has_frags(skb1)) { + skb_has_frag_list(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ @@ -3017,7 +3006,7 @@ void skb_tstamp_tx(struct sk_buff *orig_skb, } else { /* * no hardware time stamps available, - * so keep the skb_shared_tx and only + * so keep the shared tx_flags and only * store software time stamp */ skb->tstamp = ktime_get_real(); diff --git a/net/core/sock.c b/net/core/sock.c index 2cf7f9f7e775..3eed5424e659 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -110,6 +110,7 @@ #include <linux/tcp.h> #include <linux/init.h> #include <linux/highmem.h> +#include <linux/user_namespace.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -156,7 +157,7 @@ static const char *const af_family_key_strings[AF_MAX+1] = { "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , - "sk_lock-AF_IEEE802154", + "sk_lock-AF_IEEE802154", "sk_lock-AF_CAIF" , "sk_lock-AF_MAX" }; static const char *const af_family_slock_key_strings[AF_MAX+1] = { @@ -172,7 +173,7 @@ static const char *const af_family_slock_key_strings[AF_MAX+1] = { "slock-27" , "slock-28" , "slock-AF_CAN" , "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , - "slock-AF_IEEE802154", + "slock-AF_IEEE802154", "slock-AF_CAIF" , "slock-AF_MAX" }; static const char *const af_family_clock_key_strings[AF_MAX+1] = { @@ -188,7 +189,7 @@ static const char *const af_family_clock_key_strings[AF_MAX+1] = { "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , - "clock-AF_IEEE802154", + "clock-AF_IEEE802154", "clock-AF_CAIF" , "clock-AF_MAX" }; @@ -749,6 +750,20 @@ set_rcvbuf: EXPORT_SYMBOL(sock_setsockopt); +void cred_to_ucred(struct pid *pid, const struct cred *cred, + struct ucred *ucred) +{ + ucred->pid = pid_vnr(pid); + ucred->uid = ucred->gid = -1; + if (cred) { + struct user_namespace *current_ns = current_user_ns(); + + ucred->uid = user_ns_map_uid(current_ns, cred, cred->euid); + ucred->gid = user_ns_map_gid(current_ns, cred, cred->egid); + } +} +EXPORT_SYMBOL_GPL(cred_to_ucred); + int sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { @@ -901,11 +916,15 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PEERCRED: - if (len > sizeof(sk->sk_peercred)) - len = sizeof(sk->sk_peercred); - if (copy_to_user(optval, &sk->sk_peercred, len)) + { + struct ucred peercred; + if (len > sizeof(peercred)) + len = sizeof(peercred); + cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); + if (copy_to_user(optval, &peercred, len)) return -EFAULT; goto lenout; + } case SO_PEERNAME: { @@ -1059,8 +1078,11 @@ static void sk_prot_free(struct proto *prot, struct sock *sk) #ifdef CONFIG_CGROUPS void sock_update_classid(struct sock *sk) { - u32 classid = task_cls_classid(current); + u32 classid; + rcu_read_lock(); /* doing current task, which cannot vanish. */ + classid = task_cls_classid(current); + rcu_read_unlock(); if (classid && classid != sk->sk_classid) sk->sk_classid = classid; } @@ -1119,6 +1141,9 @@ static void __sk_free(struct sock *sk) printk(KERN_DEBUG "%s: optmem leakage (%d bytes) detected.\n", __func__, atomic_read(&sk->sk_omem_alloc)); + if (sk->sk_peer_cred) + put_cred(sk->sk_peer_cred); + put_pid(sk->sk_peer_pid); put_net(sock_net(sk)); sk_prot_free(sk->sk_prot_creator, sk); } @@ -1200,7 +1225,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) sock_reset_flag(newsk, SOCK_DONE); skb_queue_head_init(&newsk->sk_error_queue); - filter = newsk->sk_filter; + filter = rcu_dereference_protected(newsk->sk_filter, 1); if (filter != NULL) sk_filter_charge(newsk, filter); @@ -1317,9 +1342,10 @@ EXPORT_SYMBOL(sock_wfree); void sock_rfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + unsigned int len = skb->truesize; - atomic_sub(skb->truesize, &sk->sk_rmem_alloc); - sk_mem_uncharge(skb->sk, skb->truesize); + atomic_sub(len, &sk->sk_rmem_alloc); + sk_mem_uncharge(sk, len); } EXPORT_SYMBOL(sock_rfree); @@ -1328,9 +1354,9 @@ int sock_i_uid(struct sock *sk) { int uid; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); uid = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_uid : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return uid; } EXPORT_SYMBOL(sock_i_uid); @@ -1339,9 +1365,9 @@ unsigned long sock_i_ino(struct sock *sk) { unsigned long ino; - read_lock(&sk->sk_callback_lock); + read_lock_bh(&sk->sk_callback_lock); ino = sk->sk_socket ? SOCK_INODE(sk->sk_socket)->i_ino : 0; - read_unlock(&sk->sk_callback_lock); + read_unlock_bh(&sk->sk_callback_lock); return ino; } EXPORT_SYMBOL(sock_i_ino); @@ -1534,6 +1560,8 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, EXPORT_SYMBOL(sock_alloc_send_skb); static void __lock_sock(struct sock *sk) + __releases(&sk->sk_lock.slock) + __acquires(&sk->sk_lock.slock) { DEFINE_WAIT(wait); @@ -1550,6 +1578,8 @@ static void __lock_sock(struct sock *sk) } static void __release_sock(struct sock *sk) + __releases(&sk->sk_lock.slock) + __acquires(&sk->sk_lock.slock) { struct sk_buff *skb = sk->sk_backlog.head; @@ -1954,9 +1984,8 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - sk->sk_peercred.pid = 0; - sk->sk_peercred.uid = -1; - sk->sk_peercred.gid = -1; + sk->sk_peer_pid = NULL; + sk->sk_peer_cred = NULL; sk->sk_write_pending = 0; sk->sk_rcvlowat = 1; sk->sk_rcvtimeo = MAX_SCHEDULE_TIMEOUT; @@ -2210,8 +2239,7 @@ static DECLARE_BITMAP(proto_inuse_idx, PROTO_INUSE_NR); #ifdef CONFIG_NET_NS void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { - int cpu = smp_processor_id(); - per_cpu_ptr(net->core.inuse, cpu)->val[prot->inuse_idx] += val; + __this_cpu_add(net->core.inuse->val[prot->inuse_idx], val); } EXPORT_SYMBOL_GPL(sock_prot_inuse_add); @@ -2257,7 +2285,7 @@ static DEFINE_PER_CPU(struct prot_inuse, prot_inuse); void sock_prot_inuse_add(struct net *net, struct proto *prot, int val) { - __get_cpu_var(prot_inuse).val[prot->inuse_idx] += val; + __this_cpu_add(prot_inuse.val[prot->inuse_idx], val); } EXPORT_SYMBOL_GPL(sock_prot_inuse_add); diff --git a/net/core/stream.c b/net/core/stream.c index cc196f42b8d8..f5df85dcd20b 100644 --- a/net/core/stream.c +++ b/net/core/stream.c @@ -43,7 +43,6 @@ void sk_stream_write_space(struct sock *sk) rcu_read_unlock(); } } - EXPORT_SYMBOL(sk_stream_write_space); /** @@ -81,7 +80,6 @@ int sk_stream_wait_connect(struct sock *sk, long *timeo_p) } while (!done); return 0; } - EXPORT_SYMBOL(sk_stream_wait_connect); /** @@ -109,7 +107,6 @@ void sk_stream_wait_close(struct sock *sk, long timeout) finish_wait(sk_sleep(sk), &wait); } } - EXPORT_SYMBOL(sk_stream_wait_close); /** @@ -144,10 +141,10 @@ int sk_stream_wait_memory(struct sock *sk, long *timeo_p) set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); sk->sk_write_pending++; - sk_wait_event(sk, ¤t_timeo, !sk->sk_err && - !(sk->sk_shutdown & SEND_SHUTDOWN) && - sk_stream_memory_free(sk) && - vm_wait); + sk_wait_event(sk, ¤t_timeo, sk->sk_err || + (sk->sk_shutdown & SEND_SHUTDOWN) || + (sk_stream_memory_free(sk) && + !vm_wait)); sk->sk_write_pending--; if (vm_wait) { @@ -174,7 +171,6 @@ do_interrupted: err = sock_intr_errno(*timeo_p); goto out; } - EXPORT_SYMBOL(sk_stream_wait_memory); int sk_stream_error(struct sock *sk, int flags, int err) @@ -185,7 +181,6 @@ int sk_stream_error(struct sock *sk, int flags, int err) send_sig(SIGPIPE, current, 0); return err; } - EXPORT_SYMBOL(sk_stream_error); void sk_stream_kill_queues(struct sock *sk) @@ -210,5 +205,4 @@ void sk_stream_kill_queues(struct sock *sk) * have gone away, only the net layer knows can touch it. */ } - EXPORT_SYMBOL(sk_stream_kill_queues); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 01eee5d984be..385b6095fdc4 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -34,7 +34,8 @@ static int rps_sock_flow_sysctl(ctl_table *table, int write, mutex_lock(&sock_flow_mutex); - orig_sock_table = rps_sock_flow_table; + orig_sock_table = rcu_dereference_protected(rps_sock_flow_table, + lockdep_is_held(&sock_flow_mutex)); size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0; ret = proc_dointvec(&tmp, write, buffer, lenp, ppos); diff --git a/net/core/timestamping.c b/net/core/timestamping.c new file mode 100644 index 000000000000..0ae6c22da85b --- /dev/null +++ b/net/core/timestamping.c @@ -0,0 +1,126 @@ +/* + * PTP 1588 clock support - support for timestamping in PHY devices + * + * Copyright (C) 2010 OMICRON electronics GmbH + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation; either version 2 of the License, or + * (at your option) any later version. + * + * This program is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the + * GNU General Public License for more details. + * + * You should have received a copy of the GNU General Public License + * along with this program; if not, write to the Free Software + * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA. + */ +#include <linux/errqueue.h> +#include <linux/phy.h> +#include <linux/ptp_classify.h> +#include <linux/skbuff.h> + +static struct sock_filter ptp_filter[] = { + PTP_FILTER +}; + +static unsigned int classify(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)); + else + return PTP_CLASS_NONE; +} + +void skb_clone_tx_timestamp(struct sk_buff *skb) +{ + struct phy_device *phydev; + struct sk_buff *clone; + struct sock *sk = skb->sk; + unsigned int type; + + if (!sk) + return; + + type = classify(skb); + + switch (type) { + case PTP_CLASS_V1_IPV4: + case PTP_CLASS_V1_IPV6: + case PTP_CLASS_V2_IPV4: + case PTP_CLASS_V2_IPV6: + case PTP_CLASS_V2_L2: + case PTP_CLASS_V2_VLAN: + phydev = skb->dev->phydev; + if (likely(phydev->drv->txtstamp)) { + clone = skb_clone(skb, GFP_ATOMIC); + if (!clone) + return; + clone->sk = sk; + phydev->drv->txtstamp(phydev, clone, type); + } + break; + default: + break; + } +} + +void skb_complete_tx_timestamp(struct sk_buff *skb, + struct skb_shared_hwtstamps *hwtstamps) +{ + struct sock *sk = skb->sk; + struct sock_exterr_skb *serr; + int err; + + if (!hwtstamps) + return; + + *skb_hwtstamps(skb) = *hwtstamps; + serr = SKB_EXT_ERR(skb); + memset(serr, 0, sizeof(*serr)); + serr->ee.ee_errno = ENOMSG; + serr->ee.ee_origin = SO_EE_ORIGIN_TIMESTAMPING; + skb->sk = NULL; + err = sock_queue_err_skb(sk, skb); + if (err) + kfree_skb(skb); +} +EXPORT_SYMBOL_GPL(skb_complete_tx_timestamp); + +bool skb_defer_rx_timestamp(struct sk_buff *skb) +{ + struct phy_device *phydev; + unsigned int type; + + skb_push(skb, ETH_HLEN); + + type = classify(skb); + + skb_pull(skb, ETH_HLEN); + + switch (type) { + case PTP_CLASS_V1_IPV4: + case PTP_CLASS_V1_IPV6: + case PTP_CLASS_V2_IPV4: + case PTP_CLASS_V2_IPV6: + case PTP_CLASS_V2_L2: + case PTP_CLASS_V2_VLAN: + phydev = skb->dev->phydev; + if (likely(phydev->drv->rxtstamp)) + return phydev->drv->rxtstamp(phydev, skb, type); + break; + default: + break; + } + + return false; +} + +void __init skb_timestamping_init(void) +{ + BUG_ON(sk_chk_filter(ptp_filter, ARRAY_SIZE(ptp_filter))); +} diff --git a/net/core/utils.c b/net/core/utils.c index 838250241d26..5fea0ab21902 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -75,9 +75,8 @@ __be32 in_aton(const char *str) str++; } } - return(htonl(l)); + return htonl(l); } - EXPORT_SYMBOL(in_aton); #define IN6PTON_XDIGIT 0x00010000 @@ -93,18 +92,19 @@ EXPORT_SYMBOL(in_aton); static inline int xdigit2bin(char c, int delim) { + int val; + if (c == delim || c == '\0') return IN6PTON_DELIM; if (c == ':') return IN6PTON_COLON_MASK; if (c == '.') return IN6PTON_DOT; - if (c >= '0' && c <= '9') - return (IN6PTON_XDIGIT | IN6PTON_DIGIT| (c - '0')); - if (c >= 'a' && c <= 'f') - return (IN6PTON_XDIGIT | (c - 'a' + 10)); - if (c >= 'A' && c <= 'F') - return (IN6PTON_XDIGIT | (c - 'A' + 10)); + + val = hex_to_bin(c); + if (val >= 0) + return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0); + if (delim == -1) return IN6PTON_DELIM; return IN6PTON_UNKNOWN; @@ -162,7 +162,6 @@ out: *end = s; return ret; } - EXPORT_SYMBOL(in4_pton); int in6_pton(const char *src, int srclen, @@ -280,7 +279,6 @@ out: *end = s; return ret; } - EXPORT_SYMBOL(in6_pton); void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, |