diff options
Diffstat (limited to 'net/core')
| -rw-r--r-- | net/core/dev.c | 107 | ||||
| -rw-r--r-- | net/core/ethtool.c | 383 | ||||
| -rw-r--r-- | net/core/fib_rules.c | 2 | ||||
| -rw-r--r-- | net/core/neighbour.c | 18 | ||||
| -rw-r--r-- | net/core/netpoll.c | 169 | ||||
| -rw-r--r-- | net/core/rtnetlink.c | 71 | ||||
| -rw-r--r-- | net/core/sock.c | 6 |
7 files changed, 640 insertions, 116 deletions
diff --git a/net/core/dev.c b/net/core/dev.c index be9924f60ec3..d1cf53d0d597 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1448,13 +1448,10 @@ 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 +1611,36 @@ 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 +1880,14 @@ 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 +2009,21 @@ 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 +2060,8 @@ 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 @@ -2422,6 +2462,7 @@ 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 +2528,24 @@ 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 +2614,7 @@ 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 +2627,6 @@ 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) { @@ -3185,7 +3237,7 @@ 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 +3692,10 @@ 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 +4263,7 @@ 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); } @@ -5367,6 +5419,8 @@ 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 +5457,9 @@ 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/ethtool.c b/net/core/ethtool.c index 236a9988ea91..d08a0c7675bf 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 +134,42 @@ 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; + if (data & ETH_FLAG_LRO) dev->features |= NETIF_F_LRO; else dev->features &= ~NETIF_F_LRO; + if (data & ETH_FLAG_NTUPLE) { + if (!ops->set_rx_ntuple) + return -EOPNOTSUPP; + dev->features |= NETIF_F_NTUPLE; + } else { + /* safe to clear regardless */ + dev->features &= ~NETIF_F_NTUPLE; + } + 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 +197,10 @@ 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 +235,10 @@ 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 +251,10 @@ 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 +298,315 @@ 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; @@ -313,6 +654,9 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) if (copy_from_user(&reset, useraddr, sizeof(reset))) return -EFAULT; + /* Clear ethtool n-tuple list */ + ethtool_ntuple_flush(dev); + ret = dev->ethtool_ops->reset(dev, &reset.data); if (ret) return ret; @@ -324,7 +668,7 @@ 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 +800,12 @@ 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 +817,10 @@ 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 +835,7 @@ 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 +1189,7 @@ 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 +1230,10 @@ 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 +1466,12 @@ 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 02a3b2c69c1e..9a24377146bf 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -708,7 +708,7 @@ static struct notifier_block fib_rules_notifier = { .notifier_call = fib_rules_event, }; -static int fib_rules_net_init(struct net *net) +static int __net_init fib_rules_net_init(struct net *net) { INIT_LIST_HEAD(&net->rules_ops); spin_lock_init(&net->rules_mod_lock); diff --git a/net/core/neighbour.c b/net/core/neighbour.c index f35377b643e4..d102f6d9abdc 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2417,8 +2417,7 @@ EXPORT_SYMBOL(neigh_seq_stop); static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) { - struct proc_dir_entry *pde = seq->private; - struct neigh_table *tbl = pde->data; + struct neigh_table *tbl = seq->private; int cpu; if (*pos == 0) @@ -2435,8 +2434,7 @@ static void *neigh_stat_seq_start(struct seq_file *seq, loff_t *pos) static void *neigh_stat_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct proc_dir_entry *pde = seq->private; - struct neigh_table *tbl = pde->data; + struct neigh_table *tbl = seq->private; int cpu; for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { @@ -2455,8 +2453,7 @@ static void neigh_stat_seq_stop(struct seq_file *seq, void *v) static int neigh_stat_seq_show(struct seq_file *seq, void *v) { - struct proc_dir_entry *pde = seq->private; - struct neigh_table *tbl = pde->data; + struct neigh_table *tbl = seq->private; struct neigh_statistics *st = v; if (v == SEQ_START_TOKEN) { @@ -2501,7 +2498,7 @@ static int neigh_stat_seq_open(struct inode *inode, struct file *file) if (!ret) { struct seq_file *sf = file->private_data; - sf->private = PDE(inode); + sf->private = PDE(inode)->data; } return ret; }; @@ -2559,9 +2556,11 @@ EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL +#define NEIGH_VARS_MAX 19 + static struct neigh_sysctl_table { struct ctl_table_header *sysctl_header; - struct ctl_table neigh_vars[__NET_NEIGH_MAX]; + struct ctl_table neigh_vars[NEIGH_VARS_MAX]; char *dev_name; } neigh_sysctl_template __read_mostly = { .neigh_vars = { @@ -2678,8 +2677,7 @@ static struct neigh_sysctl_table { }; int neigh_sysctl_register(struct net_device *dev, struct neigh_parms *p, - int p_id, int pdev_id, char *p_name, - proc_handler *handler) + char *p_name, proc_handler *handler) { struct neigh_sysctl_table *t; const char *dev_name_source = NULL; diff --git a/net/core/netpoll.c b/net/core/netpoll.c index 0b4d0d35ef40..7aa697253765 100644 --- a/net/core/netpoll.c +++ b/net/core/netpoll.c @@ -407,11 +407,24 @@ static void arp_reply(struct sk_buff *skb) __be32 sip, tip; unsigned char *sha; struct sk_buff *send_skb; - struct netpoll *np = NULL; + struct netpoll *np, *tmp; + unsigned long flags; + int hits = 0; + + if (list_empty(&npinfo->rx_np)) + return; + + /* Before checking the packet, we do some early + inspection whether this is interesting at all */ + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->dev == skb->dev) + hits++; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); - if (npinfo->rx_np && npinfo->rx_np->dev == skb->dev) - np = npinfo->rx_np; - if (!np) + /* No netpoll struct is using this dev */ + if (!hits) return; /* No arp on this interface */ @@ -437,77 +450,91 @@ static void arp_reply(struct sk_buff *skb) arp_ptr += skb->dev->addr_len; memcpy(&sip, arp_ptr, 4); arp_ptr += 4; - /* if we actually cared about dst hw addr, it would get copied here */ + /* If we actually cared about dst hw addr, + it would get copied here */ arp_ptr += skb->dev->addr_len; memcpy(&tip, arp_ptr, 4); /* Should we ignore arp? */ - if (tip != np->local_ip || - ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) + if (ipv4_is_loopback(tip) || ipv4_is_multicast(tip)) return; size = arp_hdr_len(skb->dev); - send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), - LL_RESERVED_SPACE(np->dev)); - if (!send_skb) - return; - - skb_reset_network_header(send_skb); - arp = (struct arphdr *) skb_put(send_skb, size); - send_skb->dev = skb->dev; - send_skb->protocol = htons(ETH_P_ARP); + spin_lock_irqsave(&npinfo->rx_lock, flags); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (tip != np->local_ip) + continue; - /* Fill the device header for the ARP frame */ - if (dev_hard_header(send_skb, skb->dev, ptype, - sha, np->dev->dev_addr, - send_skb->len) < 0) { - kfree_skb(send_skb); - return; - } + send_skb = find_skb(np, size + LL_ALLOCATED_SPACE(np->dev), + LL_RESERVED_SPACE(np->dev)); + if (!send_skb) + continue; - /* - * Fill out the arp protocol part. - * - * we only support ethernet device type, - * which (according to RFC 1390) should always equal 1 (Ethernet). - */ + skb_reset_network_header(send_skb); + arp = (struct arphdr *) skb_put(send_skb, size); + send_skb->dev = skb->dev; + send_skb->protocol = htons(ETH_P_ARP); - arp->ar_hrd = htons(np->dev->type); - arp->ar_pro = htons(ETH_P_IP); - arp->ar_hln = np->dev->addr_len; - arp->ar_pln = 4; - arp->ar_op = htons(type); + /* Fill the device header for the ARP frame */ + if (dev_hard_header(send_skb, skb->dev, ptype, + sha, np->dev->dev_addr, + send_skb->len) < 0) { + kfree_skb(send_skb); + continue; + } - arp_ptr=(unsigned char *)(arp + 1); - memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &tip, 4); - arp_ptr += 4; - memcpy(arp_ptr, sha, np->dev->addr_len); - arp_ptr += np->dev->addr_len; - memcpy(arp_ptr, &sip, 4); + /* + * Fill out the arp protocol part. + * + * we only support ethernet device type, + * which (according to RFC 1390) should + * always equal 1 (Ethernet). + */ - netpoll_send_skb(np, send_skb); + arp->ar_hrd = htons(np->dev->type); + arp->ar_pro = htons(ETH_P_IP); + arp->ar_hln = np->dev->addr_len; + arp->ar_pln = 4; + arp->ar_op = htons(type); + + arp_ptr = (unsigned char *)(arp + 1); + memcpy(arp_ptr, np->dev->dev_addr, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &tip, 4); + arp_ptr += 4; + memcpy(arp_ptr, sha, np->dev->addr_len); + arp_ptr += np->dev->addr_len; + memcpy(arp_ptr, &sip, 4); + + netpoll_send_skb(np, send_skb); + + /* If there are several rx_hooks for the same address, + we're fine by sending a single reply */ + break; + } + spin_unlock_irqrestore(&npinfo->rx_lock, flags); } int __netpoll_rx(struct sk_buff *skb) { int proto, len, ulen; + int hits = 0; struct iphdr *iph; struct udphdr *uh; - struct netpoll_info *npi = skb->dev->npinfo; - struct netpoll *np = npi->rx_np; + struct netpoll_info *npinfo = skb->dev->npinfo; + struct netpoll *np, *tmp; - if (!np) + if (list_empty(&npinfo->rx_np)) goto out; + if (skb->dev->type != ARPHRD_ETHER) goto out; /* check if netpoll clients need ARP */ if (skb->protocol == htons(ETH_P_ARP) && atomic_read(&trapped)) { - skb_queue_tail(&npi->arp_tx, skb); + skb_queue_tail(&npinfo->arp_tx, skb); return 1; } @@ -551,16 +578,23 @@ int __netpoll_rx(struct sk_buff *skb) goto out; if (checksum_udp(skb, uh, ulen, iph->saddr, iph->daddr)) goto out; - if (np->local_ip && np->local_ip != iph->daddr) - goto out; - if (np->remote_ip && np->remote_ip != iph->saddr) - goto out; - if (np->local_port && np->local_port != ntohs(uh->dest)) - goto out; - np->rx_hook(np, ntohs(uh->source), - (char *)(uh+1), - ulen - sizeof(struct udphdr)); + list_for_each_entry_safe(np, tmp, &npinfo->rx_np, rx) { + if (np->local_ip && np->local_ip != iph->daddr) + continue; + if (np->remote_ip && np->remote_ip != iph->saddr) + continue; + if (np->local_port && np->local_port != ntohs(uh->dest)) + continue; + + np->rx_hook(np, ntohs(uh->source), + (char *)(uh+1), + ulen - sizeof(struct udphdr)); + hits++; + } + + if (!hits) + goto out; kfree_skb(skb); return 1; @@ -684,6 +718,7 @@ int netpoll_setup(struct netpoll *np) struct net_device *ndev = NULL; struct in_device *in_dev; struct netpoll_info *npinfo; + struct netpoll *npe, *tmp; unsigned long flags; int err; @@ -704,7 +739,7 @@ int netpoll_setup(struct netpoll *np) } npinfo->rx_flags = 0; - npinfo->rx_np = NULL; + INIT_LIST_HEAD(&npinfo->rx_np); spin_lock_init(&npinfo->rx_lock); skb_queue_head_init(&npinfo->arp_tx); @@ -785,7 +820,7 @@ int netpoll_setup(struct netpoll *np) if (np->rx_hook) { spin_lock_irqsave(&npinfo->rx_lock, flags); npinfo->rx_flags |= NETPOLL_RX_ENABLED; - npinfo->rx_np = np; + list_add_tail(&np->rx, &npinfo->rx_np); spin_unlock_irqrestore(&npinfo->rx_lock, flags); } @@ -801,9 +836,16 @@ int netpoll_setup(struct netpoll *np) return 0; release: - if (!ndev->npinfo) + 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); - np->dev = NULL; + } + dev_put(ndev); return err; } @@ -823,10 +865,11 @@ void netpoll_cleanup(struct netpoll *np) if (np->dev) { npinfo = np->dev->npinfo; if (npinfo) { - if (npinfo->rx_np == np) { + if (!list_empty(&npinfo->rx_np)) { spin_lock_irqsave(&npinfo->rx_lock, flags); - npinfo->rx_np = NULL; - npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; + list_del(&np->rx); + if (list_empty(&npinfo->rx_np)) + npinfo->rx_flags &= ~NETPOLL_RX_ENABLED; spin_unlock_irqrestore(&npinfo->rx_lock, flags); } diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 794bcb897ff0..42da96a4eeee 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -35,6 +35,7 @@ #include <linux/security.h> #include <linux/mutex.h> #include <linux/if_addr.h> +#include <linux/pci.h> #include <asm/uaccess.h> #include <asm/system.h> @@ -580,6 +581,15 @@ static void copy_rtnl_link_stats(struct rtnl_link_stats *a, a->tx_compressed = b->tx_compressed; }; +static inline int rtnl_vfinfo_size(const struct net_device *dev) +{ + if (dev->dev.parent && dev_is_pci(dev->dev.parent)) + return dev_num_vf(dev->dev.parent) * + sizeof(struct ifla_vf_info); + else + return 0; +} + static inline size_t if_nlmsg_size(const struct net_device *dev) { return NLMSG_ALIGN(sizeof(struct ifinfomsg)) @@ -597,6 +607,8 @@ static inline size_t if_nlmsg_size(const struct net_device *dev) + nla_total_size(4) /* IFLA_MASTER */ + nla_total_size(1) /* IFLA_OPERSTATE */ + nla_total_size(1) /* IFLA_LINKMODE */ + + nla_total_size(4) /* IFLA_NUM_VF */ + + nla_total_size(rtnl_vfinfo_size(dev)) /* IFLA_VFINFO */ + rtnl_link_get_size(dev); /* IFLA_LINKINFO */ } @@ -665,6 +677,17 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, stats = dev_get_stats(dev); copy_rtnl_link_stats(nla_data(attr), stats); + if (dev->netdev_ops->ndo_get_vf_config && dev->dev.parent) { + int i; + struct ifla_vf_info ivi; + + NLA_PUT_U32(skb, IFLA_NUM_VF, dev_num_vf(dev->dev.parent)); + for (i = 0; i < dev_num_vf(dev->dev.parent); i++) { + if (dev->netdev_ops->ndo_get_vf_config(dev, i, &ivi)) + break; + NLA_PUT(skb, IFLA_VFINFO, sizeof(ivi), &ivi); + } + } if (dev->rtnl_link_ops) { if (rtnl_link_fill(skb, dev) < 0) goto nla_put_failure; @@ -725,6 +748,12 @@ const struct nla_policy ifla_policy[IFLA_MAX+1] = { [IFLA_LINKINFO] = { .type = NLA_NESTED }, [IFLA_NET_NS_PID] = { .type = NLA_U32 }, [IFLA_IFALIAS] = { .type = NLA_STRING, .len = IFALIASZ-1 }, + [IFLA_VF_MAC] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_mac) }, + [IFLA_VF_VLAN] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_vlan) }, + [IFLA_VF_TX_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_tx_rate) }, }; EXPORT_SYMBOL(ifla_policy); @@ -898,6 +927,44 @@ static int do_setlink(struct net_device *dev, struct ifinfomsg *ifm, write_unlock_bh(&dev_base_lock); } + if (tb[IFLA_VF_MAC]) { + struct ifla_vf_mac *ivm; + ivm = nla_data(tb[IFLA_VF_MAC]); + write_lock_bh(&dev_base_lock); + if (ops->ndo_set_vf_mac) + err = ops->ndo_set_vf_mac(dev, ivm->vf, ivm->mac); + write_unlock_bh(&dev_base_lock); + if (err < 0) + goto errout; + modified = 1; + } + + if (tb[IFLA_VF_VLAN]) { + struct ifla_vf_vlan *ivv; + ivv = nla_data(tb[IFLA_VF_VLAN]); + write_lock_bh(&dev_base_lock); + if (ops->ndo_set_vf_vlan) + err = ops->ndo_set_vf_vlan(dev, ivv->vf, + (u16)ivv->vlan, + (u8)ivv->qos); + write_unlock_bh(&dev_base_lock); + if (err < 0) + goto errout; + modified = 1; + } + err = 0; + + if (tb[IFLA_VF_TX_RATE]) { + struct ifla_vf_tx_rate *ivt; + ivt = nla_data(tb[IFLA_VF_TX_RATE]); + write_lock_bh(&dev_base_lock); + if (ops->ndo_set_vf_tx_rate) + err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, ivt->rate); + write_unlock_bh(&dev_base_lock); + if (err < 0) + goto errout; + modified = 1; + } err = 0; errout: @@ -1386,7 +1453,7 @@ static struct notifier_block rtnetlink_dev_notifier = { }; -static int rtnetlink_net_init(struct net *net) +static int __net_init rtnetlink_net_init(struct net *net) { struct sock *sk; sk = netlink_kernel_create(net, NETLINK_ROUTE, RTNLGRP_MAX, @@ -1397,7 +1464,7 @@ static int rtnetlink_net_init(struct net *net) return 0; } -static void rtnetlink_net_exit(struct net *net) +static void __net_exit rtnetlink_net_exit(struct net *net) { netlink_kernel_release(net->rtnl); net->rtnl = NULL; diff --git a/net/core/sock.c b/net/core/sock.c index e1f6f225f012..ceef50bd131b 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -741,7 +741,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, struct timeval tm; } v; - unsigned int lv = sizeof(int); + int lv = sizeof(int); int len; if (get_user(len, optlen)) @@ -2140,13 +2140,13 @@ int sock_prot_inuse_get(struct net *net, struct proto *prot) } EXPORT_SYMBOL_GPL(sock_prot_inuse_get); -static int sock_inuse_init_net(struct net *net) +static int __net_init sock_inuse_init_net(struct net *net) { net->core.inuse = alloc_percpu(struct prot_inuse); return net->core.inuse ? 0 : -ENOMEM; } -static void sock_inuse_exit_net(struct net *net) +static void __net_exit sock_inuse_exit_net(struct net *net) { free_percpu(net->core.inuse); } |