diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/dev.c | 288 | ||||
| -rw-r--r-- | net/core/dev_mcast.c | 2 | ||||
| -rw-r--r-- | net/core/drop_monitor.c | 1 | ||||
| -rw-r--r-- | net/core/ethtool.c | 386 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 2 | ||||
| -rw-r--r-- | net/core/filter.c | 8 | ||||
| -rw-r--r-- | net/core/neighbour.c | 18 | ||||
| -rw-r--r-- | net/core/net-sysfs.c | 3 | ||||
| -rw-r--r-- | net/core/netpoll.c | 169 | ||||
| -rw-r--r-- | net/core/pktgen.c | 3 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 135 | ||||
| -rw-r--r-- | net/core/scm.c | 2 | ||||
| -rw-r--r-- | net/core/sock.c | 19 |
13 files changed, 824 insertions, 212 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index be9924f60ec..bcc490cc945 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1113,19 +1113,7 @@ void dev_load(struct net *net, const char *name) } EXPORT_SYMBOL(dev_load); -/** - * dev_open - prepare an interface for use. - * @dev: device to open - * - * Takes a device from down to up state. The device's private open - * function is invoked and then the multicast lists are loaded. Finally - * the device is moved into the up state and a %NETDEV_UP message is - * sent to the netdev notifier chain. - * - * Calling this function on an active interface is a nop. On a failure - * a negative errno code is returned. - */ -int dev_open(struct net_device *dev) +static int __dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; int ret; @@ -1133,13 +1121,6 @@ int dev_open(struct net_device *dev) ASSERT_RTNL(); /* - * Is it already up? - */ - - if (dev->flags & IFF_UP) - return 0; - - /* * Is it even present? */ if (!netif_device_present(dev)) @@ -1187,36 +1168,57 @@ int dev_open(struct net_device *dev) * Wakeup transmit queue engine */ dev_activate(dev); - - /* - * ... and announce new interface. - */ - call_netdevice_notifiers(NETDEV_UP, dev); } return ret; } -EXPORT_SYMBOL(dev_open); /** - * dev_close - shutdown an interface. - * @dev: device to shutdown + * dev_open - prepare an interface for use. + * @dev: device to open * - * This function moves an active device into down state. A - * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device - * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier - * chain. + * Takes a device from down to up state. The device's private open + * function is invoked and then the multicast lists are loaded. Finally + * the device is moved into the up state and a %NETDEV_UP message is + * sent to the netdev notifier chain. + * + * Calling this function on an active interface is a nop. On a failure + * a negative errno code is returned. */ -int dev_close(struct net_device *dev) +int dev_open(struct net_device *dev) +{ + int ret; + + /* + * Is it already up? + */ + if (dev->flags & IFF_UP) + return 0; + + /* + * Open device + */ + ret = __dev_open(dev); + if (ret < 0) + return ret; + + /* + * ... and announce new interface. + */ + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_UP, dev); + + return ret; +} +EXPORT_SYMBOL(dev_open); + +static int __dev_close(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; - ASSERT_RTNL(); + ASSERT_RTNL(); might_sleep(); - if (!(dev->flags & IFF_UP)) - return 0; - /* * Tell people we are going down, so that they can * prepare to death, when device is still operating. @@ -1252,14 +1254,34 @@ int dev_close(struct net_device *dev) dev->flags &= ~IFF_UP; /* - * Tell people we are down + * Shutdown NET_DMA */ - call_netdevice_notifiers(NETDEV_DOWN, dev); + net_dmaengine_put(); + + return 0; +} + +/** + * dev_close - shutdown an interface. + * @dev: device to shutdown + * + * This function moves an active device into down state. A + * %NETDEV_GOING_DOWN is sent to the netdev notifier chain. The device + * is then deactivated and finally a %NETDEV_DOWN is sent to the notifier + * chain. + */ +int dev_close(struct net_device *dev) +{ + if (!(dev->flags & IFF_UP)) + return 0; + + __dev_close(dev); /* - * Shutdown NET_DMA + * Tell people we are down */ - net_dmaengine_put(); + rtmsg_ifinfo(RTM_NEWLINK, dev, IFF_UP|IFF_RUNNING); + call_netdevice_notifiers(NETDEV_DOWN, dev); return 0; } @@ -1448,13 +1470,10 @@ int dev_forward_skb(struct net_device *dev, struct sk_buff *skb) if (skb->len > (dev->mtu + dev->hard_header_len)) return NET_RX_DROP; - skb_dst_drop(skb); + skb_set_dev(skb, dev); skb->tstamp.tv64 = 0; skb->pkt_type = PACKET_HOST; skb->protocol = eth_type_trans(skb, dev); - skb->mark = 0; - secpath_reset(skb); - nf_reset(skb); return netif_rx(skb); } EXPORT_SYMBOL_GPL(dev_forward_skb); @@ -1614,6 +1633,36 @@ static bool dev_can_checksum(struct net_device *dev, struct sk_buff *skb) return false; } +/** + * skb_dev_set -- assign a new device to a buffer + * @skb: buffer for the new device + * @dev: network device + * + * If an skb is owned by a device already, we have to reset + * all data private to the namespace a device belongs to + * before assigning it a new device. + */ +#ifdef CONFIG_NET_NS +void skb_set_dev(struct sk_buff *skb, struct net_device *dev) +{ + skb_dst_drop(skb); + if (skb->dev && !net_eq(dev_net(skb->dev), dev_net(dev))) { + secpath_reset(skb); + nf_reset(skb); + skb_init_secmark(skb); + skb->mark = 0; + skb->priority = 0; + skb->nf_trace = 0; + skb->ipvs_property = 0; +#ifdef CONFIG_NET_SCHED + skb->tc_index = 0; +#endif + } + skb->dev = dev; +} +EXPORT_SYMBOL(skb_set_dev); +#endif /* CONFIG_NET_NS */ + /* * Invalidate hardware checksum when packet is to be mangled, and * complete checksum manually on outgoing path. @@ -1853,6 +1902,14 @@ gso: skb->next = nskb->next; nskb->next = NULL; + + /* + * If device doesnt need nskb->dst, release it right now while + * its hot in this cpu cache + */ + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(nskb); + rc = ops->ndo_start_xmit(nskb, dev); if (unlikely(rc != NETDEV_TX_OK)) { if (rc & ~NETDEV_TX_MASK) @@ -1974,6 +2031,21 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, 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))); +} + /** * dev_queue_xmit - transmit a buffer * @skb: buffer to transmit @@ -2010,18 +2082,8 @@ int dev_queue_xmit(struct sk_buff *skb) if (netif_needs_gso(dev, skb)) goto gso; - if (skb_has_frags(skb) && - !(dev->features & NETIF_F_FRAGLIST) && - __skb_linearize(skb)) - goto out_kfree_skb; - - /* Fragmented skb is linearized if device does not support SG, - * or if at least one of fragments is in highmem and device - * does not support DMA from it. - */ - if (skb_shinfo(skb)->nr_frags && - (!(dev->features & NETIF_F_SG) || illegal_highdma(dev, skb)) && - __skb_linearize(skb)) + /* 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 @@ -2041,7 +2103,7 @@ gso: rcu_read_lock_bh(); txq = dev_pick_tx(dev, skb); - q = rcu_dereference(txq->qdisc); + q = rcu_dereference_bh(txq->qdisc); #ifdef CONFIG_NET_CLS_ACT skb->tc_verd = SET_TC_AT(skb->tc_verd, AT_EGRESS); @@ -2422,6 +2484,7 @@ int netif_receive_skb(struct sk_buff *skb) struct packet_type *ptype, *pt_prev; struct net_device *orig_dev; struct net_device *null_or_orig; + struct net_device *null_or_bond; int ret = NET_RX_DROP; __be16 type; @@ -2487,12 +2550,24 @@ ncls: if (!skb) goto out; + /* + * Make sure frames received on VLAN interfaces stacked on + * bonding interfaces still make their way to any base bonding + * device that may have registered for a specific ptype. The + * handler may have to adjust skb->dev and orig_dev. + */ + null_or_bond = NULL; + if ((skb->dev->priv_flags & IFF_802_1Q_VLAN) && + (vlan_dev_real_dev(skb->dev)->priv_flags & IFF_BONDING)) { + null_or_bond = vlan_dev_real_dev(skb->dev); + } + type = skb->protocol; list_for_each_entry_rcu(ptype, &ptype_base[ntohs(type) & PTYPE_HASH_MASK], list) { - if (ptype->type == type && - (ptype->dev == null_or_orig || ptype->dev == skb->dev || - ptype->dev == orig_dev)) { + if (ptype->type == type && (ptype->dev == null_or_orig || + ptype->dev == skb->dev || ptype->dev == orig_dev || + ptype->dev == null_or_bond)) { if (pt_prev) ret = deliver_skb(skb, pt_prev, orig_dev); pt_prev = ptype; @@ -2561,7 +2636,7 @@ out: return netif_receive_skb(skb); } -void napi_gro_flush(struct napi_struct *napi) +static void napi_gro_flush(struct napi_struct *napi) { struct sk_buff *skb, *next; @@ -2574,7 +2649,6 @@ 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) { @@ -2761,7 +2835,7 @@ gro_result_t napi_frags_finish(struct napi_struct *napi, struct sk_buff *skb, switch (ret) { case GRO_NORMAL: case GRO_HELD: - skb->protocol = eth_type_trans(skb, napi->dev); + skb->protocol = eth_type_trans(skb, skb->dev); if (ret == GRO_HELD) skb_gro_pull(skb, -ETH_HLEN); @@ -2966,7 +3040,7 @@ static void net_rx_action(struct softirq_action *h) * entries to the tail of this list, and only ->poll() * calls can remove this head entry from the list. */ - n = list_entry(list->next, struct napi_struct, poll_list); + n = list_first_entry(list, struct napi_struct, poll_list); have = netpoll_poll_lock(n); @@ -3185,7 +3259,7 @@ static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev) { const struct net_device_stats *stats = dev_get_stats(dev); - seq_printf(seq, "%6s:%8lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " + seq_printf(seq, "%6s: %7lu %7lu %4lu %4lu %4lu %5lu %10lu %9lu " "%8lu %7lu %4lu %4lu %4lu %5lu %7lu %10lu\n", dev->name, stats->rx_bytes, stats->rx_packets, stats->rx_errors, @@ -3640,10 +3714,10 @@ void __dev_set_rx_mode(struct net_device *dev) /* Unicast addresses changes may only happen under the rtnl, * therefore calling __dev_set_promiscuity here is safe. */ - if (dev->uc.count > 0 && !dev->uc_promisc) { + if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1); dev->uc_promisc = 1; - } else if (dev->uc.count == 0 && dev->uc_promisc) { + } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1); dev->uc_promisc = 0; } @@ -4211,7 +4285,7 @@ static void dev_addr_discard(struct net_device *dev) netif_addr_lock_bh(dev); __dev_addr_discard(&dev->mc_list); - dev->mc_count = 0; + netdev_mc_count(dev) = 0; netif_addr_unlock_bh(dev); } @@ -4247,18 +4321,10 @@ unsigned dev_get_flags(const struct net_device *dev) } EXPORT_SYMBOL(dev_get_flags); -/** - * dev_change_flags - change device settings - * @dev: device - * @flags: device state flags - * - * Change settings on device based state flags. The flags are - * in the userspace exported format. - */ -int dev_change_flags(struct net_device *dev, unsigned flags) +int __dev_change_flags(struct net_device *dev, unsigned int flags) { - int ret, changes; int old_flags = dev->flags; + int ret; ASSERT_RTNL(); @@ -4289,17 +4355,12 @@ int dev_change_flags(struct net_device *dev, unsigned flags) ret = 0; if ((old_flags ^ flags) & IFF_UP) { /* Bit is different ? */ - ret = ((old_flags & IFF_UP) ? dev_close : dev_open)(dev); + ret = ((old_flags & IFF_UP) ? __dev_close : __dev_open)(dev); if (!ret) dev_set_rx_mode(dev); } - if (dev->flags & IFF_UP && - ((old_flags ^ dev->flags) & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | - IFF_VOLATILE))) - call_netdevice_notifiers(NETDEV_CHANGE, dev); - if ((flags ^ dev->gflags) & IFF_PROMISC) { int inc = (flags & IFF_PROMISC) ? 1 : -1; @@ -4318,11 +4379,47 @@ int dev_change_flags(struct net_device *dev, unsigned flags) dev_set_allmulti(dev, inc); } - /* Exclude state transition flags, already notified */ - changes = (old_flags ^ dev->flags) & ~(IFF_UP | IFF_RUNNING); + return ret; +} + +void __dev_notify_flags(struct net_device *dev, unsigned int old_flags) +{ + unsigned int changes = dev->flags ^ old_flags; + + if (changes & IFF_UP) { + if (dev->flags & IFF_UP) + call_netdevice_notifiers(NETDEV_UP, dev); + else + call_netdevice_notifiers(NETDEV_DOWN, dev); + } + + if (dev->flags & IFF_UP && + (changes & ~(IFF_UP | IFF_PROMISC | IFF_ALLMULTI | IFF_VOLATILE))) + call_netdevice_notifiers(NETDEV_CHANGE, dev); +} + +/** + * dev_change_flags - change device settings + * @dev: device + * @flags: device state flags + * + * Change settings on device based state flags. The flags are + * in the userspace exported format. + */ +int dev_change_flags(struct net_device *dev, unsigned flags) +{ + int ret, changes; + int old_flags = dev->flags; + + ret = __dev_change_flags(dev, flags); + if (ret < 0) + return ret; + + changes = old_flags ^ dev->flags; if (changes) rtmsg_ifinfo(RTM_NEWLINK, dev, changes); + __dev_notify_flags(dev, old_flags); return ret; } EXPORT_SYMBOL(dev_change_flags); @@ -4813,6 +4910,10 @@ static void rollback_registered_many(struct list_head *head) */ call_netdevice_notifiers(NETDEV_UNREGISTER, dev); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_DELLINK, dev, ~0U); + /* * Flush the unicast and multicast chains */ @@ -4830,7 +4931,7 @@ static void rollback_registered_many(struct list_head *head) } /* Process any work delayed until the end of the batch */ - dev = list_entry(head->next, struct net_device, unreg_list); + dev = list_first_entry(head, struct net_device, unreg_list); call_netdevice_notifiers(NETDEV_UNREGISTER_BATCH, dev); synchronize_net(); @@ -5039,7 +5140,9 @@ int register_netdevice(struct net_device *dev) * Prevent userspace races by waiting until the network * device is fully setup before sending notifications. */ - rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); + if (!dev->rtnl_link_ops || + dev->rtnl_link_state == RTNL_LINK_INITIALIZED) + rtmsg_ifinfo(RTM_NEWLINK, dev, ~0U); out: return ret; @@ -5216,7 +5319,7 @@ void netdev_run_todo(void) while (!list_empty(&list)) { struct net_device *dev - = list_entry(list.next, struct net_device, todo_list); + = list_first_entry(&list, struct net_device, todo_list); list_del(&dev->todo_list); if (unlikely(dev->reg_state != NETREG_UNREGISTERING)) { @@ -5367,6 +5470,8 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, netdev_init_queues(dev); + INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); + dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); @@ -5403,6 +5508,9 @@ void free_netdev(struct net_device *dev) /* Flush device addresses */ dev_addr_flush(dev); + /* Clear ethtool n-tuple list */ + ethtool_ntuple_flush(dev); + list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); diff --git a/net/core/dev_mcast.c b/net/core/dev_mcast.c index 9e2fa39f22a..fd91569e239 100644 --- a/net/core/dev_mcast.c +++ b/net/core/dev_mcast.c @@ -96,6 +96,8 @@ int dev_mc_add(struct net_device *dev, void *addr, int alen, int glbl) int err; netif_addr_lock_bh(dev); + if (alen != dev->addr_len) + return -EINVAL; err = __dev_addr_add(&dev->mc_list, &dev->mc_count, addr, alen, glbl); if (!err) __dev_set_rx_mode(dev); diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index b8e9d3a8688..f8c87497535 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -296,7 +296,6 @@ static int dropmon_net_event(struct notifier_block *ev_block, new_stat->dev = dev; new_stat->last_rx = jiffies; - INIT_RCU_HEAD(&new_stat->rcu); spin_lock(&trace_state_lock); list_add_rcu(&new_stat->list, &hw_stats_list); spin_unlock(&trace_state_lock); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 236a9988ea9..0f2f82185ec 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -120,7 +120,7 @@ int ethtool_op_set_ufo(struct net_device *dev, u32 data) * NETIF_F_xxx values in include/linux/netdevice.h */ static const u32 flags_dup_features = - ETH_FLAG_LRO; + (ETH_FLAG_LRO | ETH_FLAG_NTUPLE); u32 ethtool_op_get_flags(struct net_device *dev) { @@ -134,19 +134,44 @@ u32 ethtool_op_get_flags(struct net_device *dev) int ethtool_op_set_flags(struct net_device *dev, u32 data) { + const struct ethtool_ops *ops = dev->ethtool_ops; + unsigned long features = dev->features; + if (data & ETH_FLAG_LRO) - dev->features |= NETIF_F_LRO; + features |= NETIF_F_LRO; else - dev->features &= ~NETIF_F_LRO; + 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; + } + dev->features = features; return 0; } +void ethtool_ntuple_flush(struct net_device *dev) +{ + struct ethtool_rx_ntuple_flow_spec_container *fsc, *f; + + list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) { + list_del(&fsc->list); + kfree(fsc); + } + dev->ethtool_ntuple_list.count = 0; +} +EXPORT_SYMBOL(ethtool_ntuple_flush); + /* Handlers for each ethtool command */ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) { - struct ethtool_cmd cmd = { ETHTOOL_GSET }; + struct ethtool_cmd cmd = { .cmd = ETHTOOL_GSET }; int err; if (!dev->ethtool_ops->get_settings) @@ -174,7 +199,10 @@ static int ethtool_set_settings(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_settings(dev, &cmd); } -static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) { struct ethtool_drvinfo info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -209,7 +237,10 @@ static int ethtool_get_drvinfo(struct net_device *dev, void __user *useraddr) return 0; } -static int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr) +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr) { struct ethtool_rxnfc cmd; @@ -222,7 +253,10 @@ static int ethtool_set_rxnfc(struct net_device *dev, void __user *useraddr) return dev->ethtool_ops->set_rxnfc(dev, &cmd); } -static int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr) +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_get_rxnfc(struct net_device *dev, void __user *useraddr) { struct ethtool_rxnfc info; const struct ethtool_ops *ops = dev->ethtool_ops; @@ -266,6 +300,315 @@ err_out: 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) +{ + + /* don't add filters forever */ + if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) { + /* free the container */ + kfree(fsc); + return; + } + + /* Copy the whole filter over */ + fsc->fs.flow_type = spec->flow_type; + memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u)); + memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u)); + + fsc->fs.vlan_tag = spec->vlan_tag; + fsc->fs.vlan_tag_mask = spec->vlan_tag_mask; + fsc->fs.data = spec->data; + fsc->fs.data_mask = spec->data_mask; + fsc->fs.action = spec->action; + + /* add to the list */ + list_add_tail_rcu(&fsc->list, &list->list); + list->count++; +} + +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_set_rx_ntuple(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_rx_ntuple cmd; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL; + int ret; + + if (!(dev->features & NETIF_F_NTUPLE)) + return -EINVAL; + + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + + /* + * Cache filter in dev struct for GET operation only if + * the underlying driver doesn't have its own GET operation, and + * only if the filter was added successfully. First make sure we + * can allocate the filter, then continue if successful. + */ + if (!ops->get_rx_ntuple) { + fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC); + if (!fsc) + return -ENOMEM; + } + + ret = ops->set_rx_ntuple(dev, &cmd); + if (ret) { + kfree(fsc); + return ret; + } + + if (!ops->get_rx_ntuple) + __rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs, fsc); + + return ret; +} + +static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) +{ + struct ethtool_gstrings gstrings; + const struct ethtool_ops *ops = dev->ethtool_ops; + struct ethtool_rx_ntuple_flow_spec_container *fsc; + u8 *data; + char *p; + int ret, i, num_strings = 0; + + if (!ops->get_sset_count) + return -EOPNOTSUPP; + + if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) + return -EFAULT; + + ret = ops->get_sset_count(dev, gstrings.string_set); + if (ret < 0) + return ret; + + gstrings.len = ret; + + data = kmalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); + if (!data) + return -ENOMEM; + + if (ops->get_rx_ntuple) { + /* driver-specific filter grab */ + ret = ops->get_rx_ntuple(dev, gstrings.string_set, data); + goto copy; + } + + /* default ethtool filter grab */ + i = 0; + p = (char *)data; + list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) { + sprintf(p, "Filter %d:\n", i); + p += ETH_GSTRING_LEN; + num_strings++; + + switch (fsc->fs.flow_type) { + case TCP_V4_FLOW: + sprintf(p, "\tFlow Type: TCP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case UDP_V4_FLOW: + sprintf(p, "\tFlow Type: UDP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case SCTP_V4_FLOW: + sprintf(p, "\tFlow Type: SCTP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case AH_ESP_V4_FLOW: + sprintf(p, "\tFlow Type: AH ESP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case ESP_V4_FLOW: + sprintf(p, "\tFlow Type: ESP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IP_USER_FLOW: + sprintf(p, "\tFlow Type: Raw IP\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IPV4_FLOW: + sprintf(p, "\tFlow Type: IPv4\n"); + p += ETH_GSTRING_LEN; + num_strings++; + break; + default: + sprintf(p, "\tFlow Type: Unknown\n"); + p += ETH_GSTRING_LEN; + num_strings++; + goto unknown_filter; + }; + + /* now the rest of the filters */ + switch (fsc->fs.flow_type) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: + case SCTP_V4_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc IP mask: 0x%x\n", + fsc->fs.m_u.tcp_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP mask: 0x%x\n", + fsc->fs.m_u.tcp_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.psrc, + fsc->fs.m_u.tcp_ip4_spec.psrc); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest Port: %d, mask: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.pdst, + fsc->fs.m_u.tcp_ip4_spec.pdst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tTOS: %d, mask: 0x%x\n", + fsc->fs.h_u.tcp_ip4_spec.tos, + fsc->fs.m_u.tcp_ip4_spec.tos); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case AH_ESP_V4_FLOW: + case ESP_V4_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSrc IP mask: 0x%x\n", + fsc->fs.m_u.ah_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP mask: 0x%x\n", + fsc->fs.m_u.ah_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tSPI: %d, mask: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.spi, + fsc->fs.m_u.ah_ip4_spec.spi); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tTOS: %d, mask: 0x%x\n", + fsc->fs.h_u.ah_ip4_spec.tos, + fsc->fs.m_u.ah_ip4_spec.tos); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IP_USER_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + fsc->fs.h_u.raw_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); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + fsc->fs.h_u.raw_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); + p += ETH_GSTRING_LEN; + num_strings++; + break; + case IPV4_FLOW: + sprintf(p, "\tSrc IP addr: 0x%x\n", + 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.usr_ip4_spec.ip4src); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tDest IP addr: 0x%x\n", + 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.usr_ip4_spec.ip4dst); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, + fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tTOS: %d, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.tos, + fsc->fs.m_u.usr_ip4_spec.tos); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tIP Version: %d, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.ip_ver, + fsc->fs.m_u.usr_ip4_spec.ip_ver); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tProtocol: %d, mask: 0x%x\n", + fsc->fs.h_u.usr_ip4_spec.proto, + fsc->fs.m_u.usr_ip4_spec.proto); + p += ETH_GSTRING_LEN; + num_strings++; + break; + }; + sprintf(p, "\tVLAN: %d, mask: 0x%x\n", + fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); + p += ETH_GSTRING_LEN; + num_strings++; + sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask); + p += ETH_GSTRING_LEN; + num_strings++; + if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) + sprintf(p, "\tAction: Drop\n"); + else + sprintf(p, "\tAction: Direct to queue %d\n", + fsc->fs.action); + p += ETH_GSTRING_LEN; + num_strings++; +unknown_filter: + i++; + } +copy: + /* indicate to userspace how many strings we actually have */ + gstrings.len = num_strings; + ret = -EFAULT; + if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) + goto out; + useraddr += sizeof(gstrings); + if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) + goto out; + ret = 0; + +out: + kfree(data); + return ret; +} + static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) { struct ethtool_regs regs; @@ -324,7 +667,7 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { - struct ethtool_wolinfo wol = { ETHTOOL_GWOL }; + struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; @@ -456,9 +799,12 @@ static int ethtool_set_eeprom(struct net_device *dev, void __user *useraddr) return ret; } -static int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) { - struct ethtool_coalesce coalesce = { ETHTOOL_GCOALESCE }; + struct ethtool_coalesce coalesce = { .cmd = ETHTOOL_GCOALESCE }; if (!dev->ethtool_ops->get_coalesce) return -EOPNOTSUPP; @@ -470,7 +816,10 @@ static int ethtool_get_coalesce(struct net_device *dev, void __user *useraddr) return 0; } -static int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) { struct ethtool_coalesce coalesce; @@ -485,7 +834,7 @@ static int ethtool_set_coalesce(struct net_device *dev, void __user *useraddr) static int ethtool_get_ringparam(struct net_device *dev, void __user *useraddr) { - struct ethtool_ringparam ringparam = { ETHTOOL_GRINGPARAM }; + struct ethtool_ringparam ringparam = { .cmd = ETHTOOL_GRINGPARAM }; if (!dev->ethtool_ops->get_ringparam) return -EOPNOTSUPP; @@ -839,7 +1188,7 @@ static int ethtool_get_perm_addr(struct net_device *dev, void __user *useraddr) static int ethtool_get_value(struct net_device *dev, char __user *useraddr, u32 cmd, u32 (*actor)(struct net_device *)) { - struct ethtool_value edata = { cmd }; + struct ethtool_value edata = { .cmd = cmd }; if (!actor) return -EOPNOTSUPP; @@ -880,7 +1229,10 @@ static int ethtool_set_value(struct net_device *dev, char __user *useraddr, return actor(dev, edata.data); } -static int ethtool_flash_device(struct net_device *dev, char __user *useraddr) +/* + * noinline attribute so that gcc doesnt use too much stack in dev_ethtool() + */ +static noinline int ethtool_flash_device(struct net_device *dev, char __user *useraddr) { struct ethtool_flash efl; @@ -1113,6 +1465,12 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_RESET: rc = ethtool_reset(dev, useraddr); break; + case ETHTOOL_SRXNTUPLE: + rc = ethtool_set_rx_ntuple(dev, useraddr); + break; + case ETHTOOL_GRXNTUPLE: + rc = ethtool_get_rx_ntuple(dev, useraddr); + break; default: rc = -EOPNOTSUPP; } diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 02a3b2c69c1..9a24377146b 100644 --- a/net/core/fib_rules.c +++ b/ |