diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index dc280bc8eba2..6c884ef1b069 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -2536,7 +2536,7 @@ config S6GMAC source "drivers/net/stmmac/Kconfig" config PCH_GBE - tristate "PCH Gigabit Ethernet" + tristate "Intel EG20T PCH / OKI SEMICONDUCTOR ML7223 IOH GbE" depends on PCI select MII ---help--- @@ -2548,6 +2548,12 @@ config PCH_GBE to Gigabit Ethernet. This driver enables Gigabit Ethernet function. + This driver also can be used for OKI SEMICONDUCTOR IOH(Input/ + Output Hub), ML7223. + ML7223 IOH is for MP(Media Phone) use. + ML7223 is companion chip for Intel Atom E6xx series. + ML7223 is completely compatible for Intel EG20T PCH. + endif # NETDEV_1000 # diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index 66823eded7a3..2353eca32593 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -213,7 +213,7 @@ struct be_rx_stats { struct be_rx_compl_info { u32 rss_hash; - u16 vid; + u16 vlan_tag; u16 pkt_size; u16 rxq_idx; u16 mac_id; diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index 1e2d825bb94a..9dc9394fd4ca 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -132,7 +132,7 @@ static void be_async_grp5_pvid_state_process(struct be_adapter *adapter, struct be_async_event_grp5_pvid_state *evt) { if (evt->enabled) - adapter->pvid = evt->tag; + adapter->pvid = le16_to_cpu(evt->tag); else adapter->pvid = 0; } diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 02a0443d1821..9187fb4e08f1 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -1018,7 +1018,8 @@ static void be_rx_compl_process(struct be_adapter *adapter, kfree_skb(skb); return; } - vlan_hwaccel_receive_skb(skb, adapter->vlan_grp, rxcp->vid); + vlan_hwaccel_receive_skb(skb, adapter->vlan_grp, + rxcp->vlan_tag); } else { netif_receive_skb(skb); } @@ -1076,7 +1077,8 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter, if (likely(!rxcp->vlanf)) napi_gro_frags(&eq_obj->napi); else - vlan_gro_frags(&eq_obj->napi, adapter->vlan_grp, rxcp->vid); + vlan_gro_frags(&eq_obj->napi, adapter->vlan_grp, + rxcp->vlan_tag); } static void be_parse_rx_compl_v1(struct be_adapter *adapter, @@ -1102,7 +1104,8 @@ static void be_parse_rx_compl_v1(struct be_adapter *adapter, rxcp->pkt_type = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, cast_enc, compl); rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vtm, compl); - rxcp->vid = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag, compl); + rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v1, vlan_tag, + compl); } static void be_parse_rx_compl_v0(struct be_adapter *adapter, @@ -1128,7 +1131,8 @@ static void be_parse_rx_compl_v0(struct be_adapter *adapter, rxcp->pkt_type = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, cast_enc, compl); rxcp->vtm = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vtm, compl); - rxcp->vid = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag, compl); + rxcp->vlan_tag = AMAP_GET_BITS(struct amap_eth_rx_compl_v0, vlan_tag, + compl); } static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo) @@ -1155,9 +1159,11 @@ static struct be_rx_compl_info *be_rx_compl_get(struct be_rx_obj *rxo) rxcp->vlanf = 0; if (!lancer_chip(adapter)) - rxcp->vid = swab16(rxcp->vid); + rxcp->vlan_tag = swab16(rxcp->vlan_tag); - if ((adapter->pvid == rxcp->vid) && !adapter->vlan_tag[rxcp->vid]) + if (((adapter->pvid & VLAN_VID_MASK) == + (rxcp->vlan_tag & VLAN_VID_MASK)) && + !adapter->vlan_tag[rxcp->vlan_tag]) rxcp->vlanf = 0; /* As the compl has been parsed, reset it; we wont touch it again */ diff --git a/drivers/net/can/sja1000/sja1000.c b/drivers/net/can/sja1000/sja1000.c index a358ea9445a2..f501bba1fc6f 100644 --- a/drivers/net/can/sja1000/sja1000.c +++ b/drivers/net/can/sja1000/sja1000.c @@ -346,10 +346,10 @@ static void sja1000_rx(struct net_device *dev) | (priv->read_reg(priv, REG_ID2) >> 5); } + cf->can_dlc = get_can_dlc(fi & 0x0F); if (fi & FI_RTR) { id |= CAN_RTR_FLAG; } else { - cf->can_dlc = get_can_dlc(fi & 0x0F); for (i = 0; i < cf->can_dlc; i++) cf->data[i] = priv->read_reg(priv, dreg++); } diff --git a/drivers/net/can/slcan.c b/drivers/net/can/slcan.c index b423965a78d1..1b49df6b2470 100644 --- a/drivers/net/can/slcan.c +++ b/drivers/net/can/slcan.c @@ -583,7 +583,9 @@ static int slcan_open(struct tty_struct *tty) /* Done. We have linked the TTY line to a channel. */ rtnl_unlock(); tty->receive_room = 65536; /* We don't flow control */ - return sl->dev->base_addr; + + /* TTY layer expects 0 on success */ + return 0; err_free_chan: sl->tty = NULL; diff --git a/drivers/net/ehea/ehea_ethtool.c b/drivers/net/ehea/ehea_ethtool.c index 3e2e734fecb7..f3bbdcef338c 100644 --- a/drivers/net/ehea/ehea_ethtool.c +++ b/drivers/net/ehea/ehea_ethtool.c @@ -55,15 +55,20 @@ static int ehea_get_settings(struct net_device *dev, struct ethtool_cmd *cmd) cmd->duplex = -1; } - cmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_1000baseT_Full - | SUPPORTED_100baseT_Full | SUPPORTED_100baseT_Half - | SUPPORTED_10baseT_Full | SUPPORTED_10baseT_Half - | SUPPORTED_Autoneg | SUPPORTED_FIBRE); + if (cmd->speed == SPEED_10000) { + cmd->supported = (SUPPORTED_10000baseT_Full | SUPPORTED_FIBRE); + cmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_FIBRE); + cmd->port = PORT_FIBRE; + } else { + cmd->supported = (SUPPORTED_1000baseT_Full | SUPPORTED_100baseT_Full + | SUPPORTED_100baseT_Half | SUPPORTED_10baseT_Full + | SUPPORTED_10baseT_Half | SUPPORTED_Autoneg + | SUPPORTED_TP); + cmd->advertising = (ADVERTISED_1000baseT_Full | ADVERTISED_Autoneg + | ADVERTISED_TP); + cmd->port = PORT_TP; + } - cmd->advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Autoneg - | ADVERTISED_FIBRE); - - cmd->port = PORT_FIBRE; cmd->autoneg = port->autoneg == 1 ? AUTONEG_ENABLE : AUTONEG_DISABLE; return 0; diff --git a/drivers/net/pch_gbe/pch_gbe_main.c b/drivers/net/pch_gbe/pch_gbe_main.c index 2ef2f9cdefa6..56d049a472da 100644 --- a/drivers/net/pch_gbe/pch_gbe_main.c +++ b/drivers/net/pch_gbe/pch_gbe_main.c @@ -34,6 +34,10 @@ const char pch_driver_version[] = DRV_VERSION; #define PCH_GBE_COPYBREAK_DEFAULT 256 #define PCH_GBE_PCI_BAR 1 +/* Macros for ML7223 */ +#define PCI_VENDOR_ID_ROHM 0x10db +#define PCI_DEVICE_ID_ROHM_ML7223_GBE 0x8013 + #define PCH_GBE_TX_WEIGHT 64 #define PCH_GBE_RX_WEIGHT 64 #define PCH_GBE_RX_BUFFER_WRITE 16 @@ -43,8 +47,7 @@ const char pch_driver_version[] = DRV_VERSION; #define PCH_GBE_MAC_RGMII_CTRL_SETTING ( \ PCH_GBE_CHIP_TYPE_INTERNAL | \ - PCH_GBE_RGMII_MODE_RGMII | \ - PCH_GBE_CRS_SEL \ + PCH_GBE_RGMII_MODE_RGMII \ ) /* Ethertype field values */ @@ -1494,12 +1497,11 @@ pch_gbe_clean_rx(struct pch_gbe_adapter *adapter, /* Write meta date of skb */ skb_put(skb, length); skb->protocol = eth_type_trans(skb, netdev); - if ((tcp_ip_status & PCH_GBE_RXD_ACC_STAT_TCPIPOK) == - PCH_GBE_RXD_ACC_STAT_TCPIPOK) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else { + if (tcp_ip_status & PCH_GBE_RXD_ACC_STAT_TCPIPOK) skb->ip_summed = CHECKSUM_NONE; - } + else + skb->ip_summed = CHECKSUM_UNNECESSARY; + napi_gro_receive(&adapter->napi, skb); (*work_done)++; pr_debug("Receive skb->ip_summed: %d length: %d\n", @@ -2420,6 +2422,13 @@ static DEFINE_PCI_DEVICE_TABLE(pch_gbe_pcidev_id) = { .class = (PCI_CLASS_NETWORK_ETHERNET << 8), .class_mask = (0xFFFF00) }, + {.vendor = PCI_VENDOR_ID_ROHM, + .device = PCI_DEVICE_ID_ROHM_ML7223_GBE, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, + .class = (PCI_CLASS_NETWORK_ETHERNET << 8), + .class_mask = (0xFFFF00) + }, /* required last entry */ {0} }; diff --git a/drivers/net/slip.c b/drivers/net/slip.c index 86cbb9ea2f26..8ec1a9a0bb9a 100644 --- a/drivers/net/slip.c +++ b/drivers/net/slip.c @@ -853,7 +853,9 @@ static int slip_open(struct tty_struct *tty) /* Done. We have linked the TTY line to a channel. */ rtnl_unlock(); tty->receive_room = 65536; /* We don't flow control */ - return sl->dev->base_addr; + + /* TTY layer expects 0 on success */ + return 0; err_free_bufs: sl_free_bufs(sl); diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index a301479ecc60..c924ea2bce07 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -567,7 +567,7 @@ static const struct usb_device_id products [] = { { USB_DEVICE_AND_INTERFACE_INFO(0x1004, 0x61aa, USB_CLASS_COMM, USB_CDC_SUBCLASS_ETHERNET, USB_CDC_PROTO_NONE), - .driver_info = 0, + .driver_info = (unsigned long)&wwan_info, }, /* diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 7d42f9a2c068..81126ff85e05 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -65,6 +65,7 @@ #define IPHETH_USBINTF_PROTO 1 #define IPHETH_BUF_SIZE 1516 +#define IPHETH_IP_ALIGN 2 /* padding at front of URB */ #define IPHETH_TX_TIMEOUT (5 * HZ) #define IPHETH_INTFNUM 2 @@ -202,18 +203,21 @@ static void ipheth_rcvbulk_callback(struct urb *urb) return; } - len = urb->actual_length; - buf = urb->transfer_buffer; + if (urb->actual_length <= IPHETH_IP_ALIGN) { + dev->net->stats.rx_length_errors++; + return; + } + len = urb->actual_length - IPHETH_IP_ALIGN; + buf = urb->transfer_buffer + IPHETH_IP_ALIGN; - skb = dev_alloc_skb(NET_IP_ALIGN + len); + skb = dev_alloc_skb(len); if (!skb) { err("%s: dev_alloc_skb: -ENOMEM", __func__); dev->net->stats.rx_dropped++; return; } - skb_reserve(skb, NET_IP_ALIGN); - memcpy(skb_put(skb, len), buf + NET_IP_ALIGN, len - NET_IP_ALIGN); + memcpy(skb_put(skb, len), buf, len); skb->dev = dev->net; skb->protocol = eth_type_trans(skb, dev->net); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 009bba3d753e..9ab439d144ed 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -645,6 +645,7 @@ int usbnet_stop (struct net_device *net) struct driver_info *info = dev->driver_info; int retval; + clear_bit(EVENT_DEV_OPEN, &dev->flags); netif_stop_queue (net); netif_info(dev, ifdown, dev->net, @@ -1524,9 +1525,12 @@ int usbnet_resume (struct usb_interface *intf) smp_mb(); clear_bit(EVENT_DEV_ASLEEP, &dev->flags); spin_unlock_irq(&dev->txq.lock); - if (!(dev->txq.qlen >= TX_QLEN(dev))) - netif_start_queue(dev->net); - tasklet_schedule (&dev->bh); + + if (test_bit(EVENT_DEV_OPEN, &dev->flags)) { + if (!(dev->txq.qlen >= TX_QLEN(dev))) + netif_start_queue(dev->net); + tasklet_schedule (&dev->bh); + } } return 0; } diff --git a/drivers/net/vmxnet3/vmxnet3_drv.c b/drivers/net/vmxnet3/vmxnet3_drv.c index 0d47c3a05307..c16ed961153a 100644 --- a/drivers/net/vmxnet3/vmxnet3_drv.c +++ b/drivers/net/vmxnet3/vmxnet3_drv.c @@ -178,6 +178,7 @@ static void vmxnet3_process_events(struct vmxnet3_adapter *adapter) { int i; + unsigned long flags; u32 events = le32_to_cpu(adapter->shared->ecr); if (!events) return; @@ -190,10 +191,10 @@ vmxnet3_process_events(struct vmxnet3_adapter *adapter) /* Check if there is an error on xmit/recv queues */ if (events & (VMXNET3_ECR_TQERR | VMXNET3_ECR_RQERR)) { - spin_lock(&adapter->cmd_lock); + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_QUEUE_STATUS); - spin_unlock(&adapter->cmd_lock); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); for (i = 0; i < adapter->num_tx_queues; i++) if (adapter->tqd_start[i].status.stopped) @@ -2733,13 +2734,14 @@ static void vmxnet3_alloc_intr_resources(struct vmxnet3_adapter *adapter) { u32 cfg; + unsigned long flags; /* intr settings */ - spin_lock(&adapter->cmd_lock); + spin_lock_irqsave(&adapter->cmd_lock, flags); VMXNET3_WRITE_BAR1_REG(adapter, VMXNET3_REG_CMD, VMXNET3_CMD_GET_CONF_INTR); cfg = VMXNET3_READ_BAR1_REG(adapter, VMXNET3_REG_CMD); - spin_unlock(&adapter->cmd_lock); + spin_unlock_irqrestore(&adapter->cmd_lock, flags); adapter->intr.type = cfg & 0x3; adapter->intr.mask_mode = (cfg >> 2) & 0x3; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index d516f00c8e0f..86aefed6140b 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -791,6 +791,7 @@ struct ip_vs_app { /* IPVS in network namespace */ struct netns_ipvs { int gen; /* Generation */ + int enable; /* enable like nf_hooks do */ /* * Hash table: for real service lookups */ @@ -1089,6 +1090,22 @@ ip_vs_control_add(struct ip_vs_conn *cp, struct ip_vs_conn *ctl_cp) atomic_inc(&ctl_cp->n_control); } +/* + * IPVS netns init & cleanup functions + */ +extern int __ip_vs_estimator_init(struct net *net); +extern int __ip_vs_control_init(struct net *net); +extern int __ip_vs_protocol_init(struct net *net); +extern int __ip_vs_app_init(struct net *net); +extern int __ip_vs_conn_init(struct net *net); +extern int __ip_vs_sync_init(struct net *net); +extern void __ip_vs_conn_cleanup(struct net *net); +extern void __ip_vs_app_cleanup(struct net *net); +extern void __ip_vs_protocol_cleanup(struct net *net); +extern void __ip_vs_control_cleanup(struct net *net); +extern void __ip_vs_estimator_cleanup(struct net *net); +extern void __ip_vs_sync_cleanup(struct net *net); +extern void __ip_vs_service_cleanup(struct net *net); /* * IPVS application functions diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 6ae4bc5ce8a7..20afeaa39395 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -324,6 +324,7 @@ struct xfrm_state_afinfo { int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sk_buff *skb); + int (*output_finish)(struct sk_buff *skb); int (*extract_input)(struct xfrm_state *x, struct sk_buff *skb); int (*extract_output)(struct xfrm_state *x, @@ -1454,6 +1455,7 @@ static inline int xfrm4_rcv_spi(struct sk_buff *skb, int nexthdr, __be32 spi) extern int xfrm4_extract_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm4_output(struct sk_buff *skb); +extern int xfrm4_output_finish(struct sk_buff *skb); extern int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family); extern int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family); extern int xfrm6_extract_header(struct sk_buff *skb); @@ -1470,6 +1472,7 @@ extern __be32 xfrm6_tunnel_spi_lookup(struct net *net, xfrm_address_t *saddr); extern int xfrm6_extract_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb); extern int xfrm6_output(struct sk_buff *skb); +extern int xfrm6_output_finish(struct sk_buff *skb); extern int xfrm6_find_1stfragopt(struct xfrm_state *x, struct sk_buff *skb, u8 **prevhdr); diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 7850412f52b7..0eb1a886b370 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -124,6 +124,9 @@ void unregister_vlan_dev(struct net_device *dev, struct list_head *head) grp->nr_vlans--; + if (vlan->flags & VLAN_FLAG_GVRP) + vlan_gvrp_request_leave(dev); + vlan_group_set_device(grp, vlan_id, NULL); if (!grp->killall) synchronize_net(); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index e34ea9e5e28b..b2ff6c8d3603 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -487,9 +487,6 @@ static int vlan_dev_stop(struct net_device *dev) struct vlan_dev_info *vlan = vlan_dev_info(dev); struct net_device *real_dev = vlan->real_dev; - if (vlan->flags & VLAN_FLAG_GVRP) - vlan_gvrp_request_leave(dev); - dev_mc_unsync(real_dev, dev); dev_uc_unsync(real_dev, dev); if (dev->flags & IFF_ALLMULTI) diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 893669caa8de..1a92b369c820 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1766,7 +1766,7 @@ static int compat_table_info(const struct ebt_table_info *info, newinfo->entries_size = size; - xt_compat_init_offsets(AF_INET, info->nentries); + xt_compat_init_offsets(NFPROTO_BRIDGE, info->nentries); return EBT_ENTRY_ITERATE(entries, size, compat_calc_entry, info, entries, newinfo); } @@ -1882,7 +1882,7 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, struct xt_match *match; struct xt_target *wt; void *dst = NULL; - int off, pad = 0, ret = 0; + int off, pad = 0; unsigned int size_kern, entry_offset, match_size = mwt->match_size; strlcpy(name, mwt->u.name, sizeof(name)); @@ -1935,13 +1935,6 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, break; } - if (!dst) { - ret = xt_compat_add_offset(NFPROTO_BRIDGE, entry_offset, - off + ebt_compat_entry_padsize()); - if (ret < 0) - return ret; - } - state->buf_kern_offset += match_size + off; state->buf_user_offset += match_size; pad = XT_ALIGN(size_kern) - size_kern; @@ -2016,50 +2009,6 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, return growth; } -#define EBT_COMPAT_WATCHER_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct compat_ebt_entry_mwt *__watcher; \ - \ - for (__i = e->watchers_offset; \ - __i < (e)->target_offset; \ - __i += __watcher->watcher_size + \ - sizeof(struct compat_ebt_entry_mwt)) { \ - __watcher = (void *)(e) + __i; \ - __ret = fn(__watcher , ## args); \ - if (__ret != 0) \ - break; \ - } \ - if (__ret == 0) { \ - if (__i != (e)->target_offset) \ - __ret = -EINVAL; \ - } \ - __ret; \ -}) - -#define EBT_COMPAT_MATCH_ITERATE(e, fn, args...) \ -({ \ - unsigned int __i; \ - int __ret = 0; \ - struct compat_ebt_entry_mwt *__match; \ - \ - for (__i = sizeof(struct ebt_entry); \ - __i < (e)->watchers_offset; \ - __i += __match->match_size + \ - sizeof(struct compat_ebt_entry_mwt)) { \ - __match = (void *)(e) + __i; \ - __ret = fn(__match , ## args); \ - if (__ret != 0) \ - break; \ - } \ - if (__ret == 0) { \ - if (__i != (e)->watchers_offset) \ - __ret = -EINVAL; \ - } \ - __ret; \ -}) - /* called for all ebt_entry structures. */ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, unsigned int *total, @@ -2132,6 +2081,14 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, } } + if (state->buf_kern_start == NULL) { + unsigned int offset = buf_start - (char *) base; + + ret = xt_compat_add_offset(NFPROTO_BRIDGE, offset, new_offset); + if (ret < 0) + return ret; + } + startoff = state->buf_user_offset - startoff; BUG_ON(*total < startoff); @@ -2240,6 +2197,7 @@ static int compat_do_replace(struct net *net, void __user *user, xt_compat_lock(NFPROTO_BRIDGE); + xt_compat_init_offsets(NFPROTO_BRIDGE, tmp.nentries); ret = compat_copy_entries(entries_tmp, tmp.entries_size, &state); if (ret < 0) goto out_unlock; diff --git a/net/core/dev.c b/net/core/dev.c index 856b6ee9a1d5..92009440d28b 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1284,11 +1284,13 @@ static int dev_close_many(struct list_head *head) */ int dev_close(struct net_device *dev) { - LIST_HEAD(single); + if (dev->flags & IFF_UP) { + LIST_HEAD(single); - list_add(&dev->unreg_list, &single); - dev_close_many(&single); - list_del(&single); + list_add(&dev->unreg_list, &single); + dev_close_many(&single); + list_del(&single); + } return 0; } EXPORT_SYMBOL(dev_close); diff --git a/net/dccp/options.c b/net/dccp/options.c index f06ffcfc8d71..4b2ab657ac8e 100644 --- a/net/dccp/options.c +++ b/net/dccp/options.c @@ -123,6 +123,8 @@ int dccp_parse_options(struct sock *sk, struct dccp_request_sock *dreq, case DCCPO_CHANGE_L ... DCCPO_CONFIRM_R: if (pkt_type == DCCP_PKT_DATA) /* RFC 4340, 6 */ break; + if (len == 0) + goto out_invalid_option; rc = dccp_feat_parse_options(sk, dreq, mandatory, opt, *value, value + 1, len - 1); if (rc) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index a1151b8adf3c..b1d282f11be7 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -223,31 +223,30 @@ static void ip_expire(unsigned long arg) if ((qp->q.last_in & INET_FRAG_FIRST_IN) && qp->q.fragments != NULL) { struct sk_buff *head = qp->q.fragments; + const struct iphdr *iph; + int err; rcu_read_lock(); head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out_rcu_unlock; + /* skb dst is stale, drop it, and perform route lookup again */ + skb_dst_drop(head); + iph = ip_hdr(head); + err = ip_route_input_noref(head, iph->daddr, iph->saddr, + iph->tos, head->dev); + if (err) + goto out_rcu_unlock; + /* - * Only search router table for the head fragment, - * when defraging timeout at PRE_ROUTING HOOK. + * Only an end host needs to send an ICMP + * "Fragment Reassembly Timeout" message, per RFC792. */ - if (qp->user == IP_DEFRAG_CONNTRACK_IN && !skb_dst(head)) { - const struct iphdr *iph = ip_hdr(head); - int err = ip_route_input(head, iph->daddr, iph->saddr, - iph->tos, head->dev); - if (unlikely(err)) - goto out_rcu_unlock; + if (qp->user == IP_DEFRAG_CONNTRACK_IN && + skb_rtable(head)->rt_type != RTN_LOCAL) + goto out_rcu_unlock; - /* - * Only an end host needs to send an ICMP - * "Fragment Reassembly Timeout" message, per RFC792. - */ - if (skb_rtable(head)->rt_type != RTN_LOCAL) - goto out_rcu_unlock; - - } /* Send an ICMP "Fragment Reassembly Timeout" message. */ icmp_send(head, ICMP_TIME_EXCEEDED, ICMP_EXC_FRAGTIME, 0); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 34340c9c95fa..f376b05cca81 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -93,6 +93,7 @@ struct bictcp { u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ #define ACK_RATIO_SHIFT 4 +#define ACK_RATIO_LIMIT (32u << ACK_RATIO_SHIFT) u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ u8 sample_cnt; /* number of samples to decide curr_rtt */ u8 found; /* the exit point is found? */ @@ -398,8 +399,12 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) u32 delay; if (icsk->icsk_ca_state == TCP_CA_Open) { - cnt -= ca->delayed_ack >> ACK_RATIO_SHIFT; - ca->delayed_ack += cnt; + u32 ratio = ca->delayed_ack; + + ratio -= ca->delayed_ack >> ACK_RATIO_SHIFT; + ratio += cnt; + + ca->delayed_ack = min(ratio, ACK_RATIO_LIMIT); } /* Some calls are for duplicates without timetamps */ diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index 571aa96a175c..2d51840e53a1 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -69,7 +69,7 @@ int xfrm4_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm4_prepare_output); -static int xfrm4_output_finish(struct sk_buff *skb) +int xfrm4_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER if (!skb_dst(skb)->xfrm) { @@ -86,7 +86,11 @@ static int xfrm4_output_finish(struct sk_buff *skb) int xfrm4_output(struct sk_buff *skb) { + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + return NF_HOOK_COND(NFPROTO_IPV4, NF_INET_POST_ROUTING, skb, - NULL, skb_dst(skb)->dev, xfrm4_output_finish, + NULL, dst->dev, + x->outer_mode->afinfo->output_finish, !(IPCB(skb)->flags & IPSKB_REROUTED)); } diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1717c64628d1..805d63ef4340 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -78,6 +78,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .init_tempsel = __xfrm4_init_tempsel, .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, + .output_finish = xfrm4_output_finish, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, .transport_finish = xfrm4_transport_finish, diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 28e74488a329..a5a4c5dd5396 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -45,6 +45,8 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) int tcphoff, needs_ack; const struct ipv6hdr *oip6h = ipv6_hdr(oldskb); struct ipv6hdr *ip6h; +#define DEFAULT_TOS_VALUE 0x0U + const __u8 tclass = DEFAULT_TOS_VALUE; struct dst_entry *dst = NULL; u8 proto; struct flowi6 fl6; @@ -124,7 +126,7 @@ static void send_reset(struct net *net, struct sk_buff *oldskb) skb_put(nskb, sizeof(struct ipv6hdr)); skb_reset_network_header(nskb); ip6h = ipv6_hdr(nskb); - ip6h->version = 6; + *(__be32 *)ip6h = htonl(0x60000000 | (tclass << 20)); ip6h->hop_limit = ip6_dst_hoplimit(dst); ip6h->nexthdr = IPPROTO_TCP; ipv6_addr_copy(&ip6h->saddr, &oip6h->daddr); diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index 8e688b3de9ab..49a91c5f5623 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -79,7 +79,7 @@ int xfrm6_prepare_output(struct xfrm_state *x, struct sk_buff *skb) } EXPORT_SYMBOL(xfrm6_prepare_output); -static int xfrm6_output_finish(struct sk_buff *skb) +int xfrm6_output_finish(struct sk_buff *skb) { #ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; @@ -97,9 +97,9 @@ static int __xfrm6_output(struct sk_buff *skb) if ((x && x->props.mode == XFRM_MODE_TUNNEL) && ((skb->len > ip6_skb_dst_mtu(skb) && !skb_is_gso(skb)) || dst_allfrag(skb_dst(skb)))) { - return ip6_fragment(skb, xfrm6_output_finish); + return ip6_fragment(skb, x->outer_mode->afinfo->output_finish); } - return xfrm6_output_finish(skb); + return x->outer_mode->afinfo->output_finish(skb); } int xfrm6_output(struct sk_buff *skb) diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index afe941e9415c..248f0b2a7ee9 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -178,6 +178,7 @@ static struct xfrm_state_afinfo xfrm6_state_afinfo = { .tmpl_sort = __xfrm6_tmpl_sort, .state_sort = __xfrm6_state_sort, .output = xfrm6_output, + .output_finish = xfrm6_output_finish, .extract_input = xfrm6_extract_input, .extract_output = xfrm6_extract_output, .transport_finish = xfrm6_transport_finish, diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index 2dc6de13ac18..51f3af7c4743 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -576,7 +576,7 @@ static const struct file_operations ip_vs_app_fops = { }; #endif -static int __net_init __ip_vs_app_init(struct net *net) +int __net_init __ip_vs_app_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -585,26 +585,17 @@ static int __net_init __ip_vs_app_init(struct net *net) return 0; } -static void __net_exit __ip_vs_app_cleanup(struct net *net) +void __net_exit __ip_vs_app_cleanup(struct net *net) { proc_net_remove(net, "ip_vs_app"); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_app_init, - .exit = __ip_vs_app_cleanup, -}; - int __init ip_vs_app_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_app_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_conn.c b/net/netfilter/ipvs/ip_vs_conn.c index c97bd45975be..d3fd91bbba49 100644 --- a/net/netfilter/ipvs/ip_vs_conn.c +++ b/net/netfilter/ipvs/ip_vs_conn.c @@ -1258,22 +1258,17 @@ int __net_init __ip_vs_conn_init(struct net *net) return 0; } -static void __net_exit __ip_vs_conn_cleanup(struct net *net) +void __net_exit __ip_vs_conn_cleanup(struct net *net) { /* flush all the connection entries first */ ip_vs_conn_flush(net); proc_net_remove(net, "ip_vs_conn"); proc_net_remove(net, "ip_vs_conn_sync"); } -static struct pernet_operations ipvs_conn_ops = { - .init = __ip_vs_conn_init, - .exit = __ip_vs_conn_cleanup, -}; int __init ip_vs_conn_init(void) { int idx; - int retc; /* Compute size and mask */ ip_vs_conn_tab_size = 1 << ip_vs_conn_tab_bits; @@ -1309,17 +1304,14 @@ int __init ip_vs_conn_init(void) rwlock_init(&__ip_vs_conntbl_lock_array[idx].l); } - retc = register_pernet_subsys(&ipvs_conn_ops); - /* calculate the random value for connection hash */ get_random_bytes(&ip_vs_conn_rnd, sizeof(ip_vs_conn_rnd)); - return retc; + return 0; } void ip_vs_conn_cleanup(void) { - unregister_pernet_subsys(&ipvs_conn_ops); /* Release the empty cache */ kmem_cache_destroy(ip_vs_conn_cachep); vfree(ip_vs_conn_tab); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 07accf6b2401..a74dae6c5dbc 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1113,6 +1113,9 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) return NF_ACCEPT; net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); #ifdef CONFIG_IP_VS_IPV6 if (af == AF_INET6) { @@ -1343,6 +1346,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) return NF_ACCEPT; /* The packet looks wrong, ignore */ net = skb_net(skb); + pd = ip_vs_proto_data_get(net, cih->protocol); if (!pd) return NF_ACCEPT; @@ -1529,6 +1533,11 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) IP_VS_DBG_ADDR(af, &iph.daddr), hooknum); return NF_ACCEPT; } + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); /* Bad... Do not break raw sockets */ @@ -1562,7 +1571,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } - net = skb_net(skb); /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); if (unlikely(!pd)) @@ -1588,7 +1596,6 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) } IP_VS_DBG_PKT(11, af, pp, skb, 0, "Incoming packet"); - net = skb_net(skb); ipvs = net_ipvs(net); /* Check the server status */ if (cp->dest && !(cp->dest->flags & IP_VS_DEST_F_AVAILABLE)) { @@ -1743,10 +1750,16 @@ ip_vs_forward_icmp(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ip_hdr(skb)->protocol != IPPROTO_ICMP) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp(skb, &r, hooknum); } @@ -1757,10 +1770,16 @@ ip_vs_forward_icmp_v6(unsigned int hooknum, struct sk_buff *skb, int (*okfn)(struct sk_buff *)) { int r; + struct net *net; if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) return NF_ACCEPT; + /* ipvs enabled in this netns ? */ + net = skb_net(skb); + if (!net_ipvs(net)->enable) + return NF_ACCEPT; + return ip_vs_in_icmp_v6(skb, &r, hooknum); } #endif @@ -1884,19 +1903,70 @@ static int __net_init __ip_vs_init(struct net *net) pr_err("%s(): no memory.\n", __func__); return -ENOMEM; } + /* Hold the beast until a service is registerd */ + ipvs->enable = 0; ipvs->net = net; /* Counters used for creating unique names */ ipvs->gen = atomic_read(&ipvs_netns_cnt); atomic_inc(&ipvs_netns_cnt); net->ipvs = ipvs; + + if (__ip_vs_estimator_init(net) < 0) + goto estimator_fail; + + if (__ip_vs_control_init(net) < 0) + goto control_fail; + + if (__ip_vs_protocol_init(net) < 0) + goto protocol_fail; + + if (__ip_vs_app_init(net) < 0) + goto app_fail; + + if (__ip_vs_conn_init(net) < 0) + goto conn_fail; + + if (__ip_vs_sync_init(net) < 0) + goto sync_fail; + printk(KERN_INFO "IPVS: Creating netns size=%zu id=%d\n", sizeof(struct netns_ipvs), ipvs->gen); return 0; +/* + * Error handling + */ + +sync_fail: + __ip_vs_conn_cleanup(net); +conn_fail: + __ip_vs_app_cleanup(net); +app_fail: + __ip_vs_protocol_cleanup(net); +protocol_fail: + __ip_vs_control_cleanup(net); +control_fail: + __ip_vs_estimator_cleanup(net); +estimator_fail: + return -ENOMEM; } static void __net_exit __ip_vs_cleanup(struct net *net) { - IP_VS_DBG(10, "ipvs netns %d released\n", net_ipvs(net)->gen); + __ip_vs_service_cleanup(net); /* ip_vs_flush() with locks */ + __ip_vs_conn_cleanup(net); + __ip_vs_app_cleanup(net); + __ip_vs_protocol_cleanup(net); + __ip_vs_control_cleanup(net); + __ip_vs_estimator_cleanup(net); + IP_VS_DBG(2, "ipvs netns %d released\n", net_ipvs(net)->gen); +} + +static void __net_exit __ip_vs_dev_cleanup(struct net *net) +{ + EnterFunction(2); + net_ipvs(net)->enable = 0; /* Disable packet reception */ + __ip_vs_sync_cleanup(net); + LeaveFunction(2); } static struct pernet_operations ipvs_core_ops = { @@ -1906,6 +1976,10 @@ static struct pernet_operations ipvs_core_ops = { .size = sizeof(struct netns_ipvs), }; +static struct pernet_operations ipvs_core_dev_ops = { + .exit = __ip_vs_dev_cleanup, +}; + /* * Initialize IP Virtual Server */ @@ -1913,10 +1987,6 @@ static int __init ip_vs_init(void) { int ret; - ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ - if (ret < 0) - return ret; - ip_vs_estimator_init(); ret = ip_vs_control_init(); if (ret < 0) { @@ -1944,15 +2014,28 @@ static int __init ip_vs_init(void) goto cleanup_conn; } + ret = register_pernet_subsys(&ipvs_core_ops); /* Alloc ip_vs struct */ + if (ret < 0) + goto cleanup_sync; + + ret = register_pernet_device(&ipvs_core_dev_ops); + if (ret < 0) + goto cleanup_sub; + ret = nf_register_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); if (ret < 0) { pr_err("can't register hooks.\n"); - goto cleanup_sync; + goto cleanup_dev; } pr_info("ipvs loaded.\n"); + return ret; +cleanup_dev: + unregister_pernet_device(&ipvs_core_dev_ops); +cleanup_sub: + unregister_pernet_subsys(&ipvs_core_ops); cleanup_sync: ip_vs_sync_cleanup(); cleanup_conn: @@ -1964,20 +2047,20 @@ cleanup_sync: ip_vs_control_cleanup(); cleanup_estimator: ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ return ret; } static void __exit ip_vs_cleanup(void) { nf_unregister_hooks(ip_vs_ops, ARRAY_SIZE(ip_vs_ops)); + unregister_pernet_device(&ipvs_core_dev_ops); + unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ ip_vs_sync_cleanup(); ip_vs_conn_cleanup(); ip_vs_app_cleanup(); ip_vs_protocol_cleanup(); ip_vs_control_cleanup(); ip_vs_estimator_cleanup(); - unregister_pernet_subsys(&ipvs_core_ops); /* free ip_vs struct */ pr_info("ipvs unloaded.\n"); } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index ae47090bf45f..ea722810faf3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -69,6 +69,11 @@ int ip_vs_get_debug_level(void) } #endif + +/* Protos */ +static void __ip_vs_del_service(struct ip_vs_service *svc); + + #ifdef CONFIG_IP_VS_IPV6 /* Taken from rt6_fill_node() in net/ipv6/route.c, is there a better way? */ static int __ip_vs_addr_is_local_v6(struct net *net, @@ -1214,6 +1219,8 @@ ip_vs_add_service(struct net *net, struct ip_vs_service_user_kern *u, write_unlock_bh(&__ip_vs_svc_lock); *svc_p = svc; + /* Now there is a service - full throttle */ + ipvs->enable = 1; return 0; @@ -1472,6 +1479,84 @@ static int ip_vs_flush(struct net *net) return 0; } +/* + * Delete service by {netns} in the service table. + * Called by __ip_vs_cleanup() + */ +void __ip_vs_service_cleanup(struct net *net) +{ + EnterFunction(2); + /* Check for "full" addressed entries */ + mutex_lock(&__ip_vs_mutex); + ip_vs_flush(net); + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); +} +/* + * Release dst hold by dst_cache + */ +static inline void +__ip_vs_dev_reset(struct ip_vs_dest *dest, struct net_device *dev) +{ + spin_lock_bh(&dest->dst_lock); + if (dest->dst_cache && dest->dst_cache->dev == dev) { + IP_VS_DBG_BUF(3, "Reset dev:%s dest %s:%u ,dest->refcnt=%d\n", + dev->name, + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), + atomic_read(&dest->refcnt)); + ip_vs_dst_reset(dest); + } + spin_unlock_bh(&dest->dst_lock); + +} +/* + * Netdev event receiver + * Currently only NETDEV_UNREGISTER is handled, i.e. if we hold a reference to + * a device that is "unregister" it must be released. + */ +static int ip_vs_dst_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = ptr; + struct net *net = dev_net(dev); + struct ip_vs_service *svc; + struct ip_vs_dest *dest; + unsigned int idx; + + if (event != NETDEV_UNREGISTER) + return NOTIFY_DONE; + IP_VS_DBG(3, "%s() dev=%s\n", __func__, dev->name); + EnterFunction(2); + mutex_lock(&__ip_vs_mutex); + for (idx = 0; idx < IP_VS_SVC_TAB_SIZE; idx++) { + list_for_each_entry(svc, &ip_vs_svc_table[idx], s_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + } + + list_for_each_entry(svc, &ip_vs_svc_fwm_table[idx], f_list) { + if (net_eq(svc->net, net)) { + list_for_each_entry(dest, &svc->destinations, + n_list) { + __ip_vs_dev_reset(dest, dev); + } + } + + } + } + + list_for_each_entry(dest, &net_ipvs(net)->dest_trash, n_list) { + __ip_vs_dev_reset(dest, dev); + } + mutex_unlock(&__ip_vs_mutex); + LeaveFunction(2); + return NOTIFY_DONE; +} /* * Zero counters in a service or all services @@ -3588,6 +3673,10 @@ void __net_init __ip_vs_control_cleanup_sysctl(struct net *net) { } #endif +static struct notifier_block ip_vs_dst_notifier = { + .notifier_call = ip_vs_dst_event, +}; + int __net_init __ip_vs_control_init(struct net *net) { int idx; @@ -3626,7 +3715,7 @@ err: return -ENOMEM; } -static void __net_exit __ip_vs_control_cleanup(struct net *net) +void __net_exit __ip_vs_control_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -3639,11 +3728,6 @@ static void __net_exit __ip_vs_control_cleanup(struct net *net) free_percpu(ipvs->tot_stats.cpustats); } -static struct pernet_operations ipvs_control_ops = { - .init = __ip_vs_control_init, - .exit = __ip_vs_control_cleanup, -}; - int __init ip_vs_control_init(void) { int idx; @@ -3657,33 +3741,32 @@ int __init ip_vs_control_init(void) INIT_LIST_HEAD(&ip_vs_svc_fwm_table[idx]); } - ret = register_pernet_subsys(&ipvs_control_ops); - if (ret) { - pr_err("cannot register namespace.\n"); - goto err; - } - smp_wmb(); /* Do we really need it now ? */ ret = nf_register_sockopt(&ip_vs_sockopts); if (ret) { pr_err("cannot register sockopt.\n"); - goto err_net; + goto err_sock; } ret = ip_vs_genl_register(); if (ret) { pr_err("cannot register Generic Netlink interface.\n"); - nf_unregister_sockopt(&ip_vs_sockopts); - goto err_net; + goto err_genl; } + ret = register_netdevice_notifier(&ip_vs_dst_notifier); + if (ret < 0) + goto err_notf; + LeaveFunction(2); return 0; -err_net: - unregister_pernet_subsys(&ipvs_control_ops); -err: +err_notf: + ip_vs_genl_unregister(); +err_genl: + nf_unregister_sockopt(&ip_vs_sockopts); +err_sock: return ret; } @@ -3691,7 +3774,6 @@ err: void ip_vs_control_cleanup(void) { EnterFunction(2); - unregister_pernet_subsys(&ipvs_control_ops); ip_vs_genl_unregister(); nf_unregister_sockopt(&ip_vs_sockopts); LeaveFunction(2); diff --git a/net/netfilter/ipvs/ip_vs_est.c b/net/netfilter/ipvs/ip_vs_est.c index 8c8766ca56ad..508cce98777c 100644 --- a/net/netfilter/ipvs/ip_vs_est.c +++ b/net/netfilter/ipvs/ip_vs_est.c @@ -192,7 +192,7 @@ void ip_vs_read_estimator(struct ip_vs_stats_user *dst, dst->outbps = (e->outbps + 0xF) >> 5; } -static int __net_init __ip_vs_estimator_init(struct net *net) +int __net_init __ip_vs_estimator_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -203,24 +203,16 @@ static int __net_init __ip_vs_estimator_init(struct net *net) return 0; } -static void __net_exit __ip_vs_estimator_exit(struct net *net) +void __net_exit __ip_vs_estimator_cleanup(struct net *net) { del_timer_sync(&net_ipvs(net)->est_timer); } -static struct pernet_operations ip_vs_app_ops = { - .init = __ip_vs_estimator_init, - .exit = __ip_vs_estimator_exit, -}; int __init ip_vs_estimator_init(void) { - int rv; - - rv = register_pernet_subsys(&ip_vs_app_ops); - return rv; + return 0; } void ip_vs_estimator_cleanup(void) { - unregister_pernet_subsys(&ip_vs_app_ops); } diff --git a/net/netfilter/ipvs/ip_vs_proto.c b/net/netfilter/ipvs/ip_vs_proto.c index 17484a4416ef..eb86028536fc 100644 --- a/net/netfilter/ipvs/ip_vs_proto.c +++ b/net/netfilter/ipvs/ip_vs_proto.c @@ -316,7 +316,7 @@ ip_vs_tcpudp_debug_packet(int af, struct ip_vs_protocol *pp, /* * per network name-space init */ -static int __net_init __ip_vs_protocol_init(struct net *net) +int __net_init __ip_vs_protocol_init(struct net *net) { #ifdef CONFIG_IP_VS_PROTO_TCP register_ip_vs_proto_netns(net, &ip_vs_protocol_tcp); @@ -336,7 +336,7 @@ static int __net_init __ip_vs_protocol_init(struct net *net) return 0; } -static void __net_exit __ip_vs_protocol_cleanup(struct net *net) +void __net_exit __ip_vs_protocol_cleanup(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); struct ip_vs_proto_data *pd; @@ -349,11 +349,6 @@ static void __net_exit __ip_vs_protocol_cleanup(struct net *net) } } -static struct pernet_operations ipvs_proto_ops = { - .init = __ip_vs_protocol_init, - .exit = __ip_vs_protocol_cleanup, -}; - int __init ip_vs_protocol_init(void) { char protocols[64]; @@ -382,7 +377,6 @@ int __init ip_vs_protocol_init(void) REGISTER_PROTOCOL(&ip_vs_protocol_esp); #endif pr_info("Registered protocols (%s)\n", &protocols[2]); - return register_pernet_subsys(&ipvs_proto_ops); return 0; } @@ -393,7 +387,6 @@ void ip_vs_protocol_cleanup(void) struct ip_vs_protocol *pp; int i; - unregister_pernet_subsys(&ipvs_proto_ops); /* unregister all the ipvs protocols */ for (i = 0; i < IP_VS_PROTO_TAB_SIZE; i++) { while ((pp = ip_vs_proto_table[i]) != NULL) diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index 3e7961e85e9c..e292e5bddc70 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1303,13 +1303,18 @@ static struct socket *make_send_sock(struct net *net) struct socket *sock; int result; - /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + /* First create a socket move it to right name space later */ + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); result = set_mcast_if(sock->sk, ipvs->master_mcast_ifn); if (result < 0) { pr_err("Error setting outbound mcast interface\n"); @@ -1334,8 +1339,8 @@ static struct socket *make_send_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1350,12 +1355,17 @@ static struct socket *make_receive_sock(struct net *net) int result; /* First create a socket */ - result = __sock_create(net, PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock, 1); + result = sock_create_kern(PF_INET, SOCK_DGRAM, IPPROTO_UDP, &sock); if (result < 0) { pr_err("Error during creation of socket; terminating\n"); return ERR_PTR(result); } - + /* + * Kernel sockets that are a part of a namespace, should not + * hold a reference to a namespace in order to allow to stop it. + * After sk_change_net should be released using sk_release_kernel. + */ + sk_change_net(sock->sk, net); /* it is equivalent to the REUSEADDR option in user-space */ sock->sk->sk_reuse = 1; @@ -1377,8 +1387,8 @@ static struct socket *make_receive_sock(struct net *net) return sock; - error: - sock_release(sock); +error: + sk_release_kernel(sock->sk); return ERR_PTR(result); } @@ -1473,7 +1483,7 @@ static int sync_thread_master(void *data) ip_vs_sync_buff_release(sb); /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo); return 0; @@ -1513,7 +1523,7 @@ static int sync_thread_backup(void *data) } /* release the sending multicast socket */ - sock_release(tinfo->sock); + sk_release_kernel(tinfo->sock->sk); kfree(tinfo->buf); kfree(tinfo); @@ -1601,7 +1611,7 @@ outtinfo: outbuf: kfree(buf); outsocket: - sock_release(sock); + sk_release_kernel(sock->sk); out: return result; } @@ -1610,6 +1620,7 @@ out: int stop_sync_thread(struct net *net, int state) { struct netns_ipvs *ipvs = net_ipvs(net); + int retc = -EINVAL; IP_VS_DBG(7, "%s(): pid %d\n", __func__, task_pid_nr(current)); @@ -1629,7 +1640,7 @@ int stop_sync_thread(struct net *net, int state) spin_lock_bh(&ipvs->sync_lock); ipvs->sync_state &= ~IP_VS_STATE_MASTER; spin_unlock_bh(&ipvs->sync_lock); - kthread_stop(ipvs->master_thread); + retc = kthread_stop(ipvs->master_thread); ipvs->master_thread = NULL; } else if (state == IP_VS_STATE_BACKUP) { if (!ipvs->backup_thread) @@ -1639,22 +1650,20 @@ int stop_sync_thread(struct net *net, int state) task_pid_nr(ipvs->backup_thread)); ipvs->sync_state &= ~IP_VS_STATE_BACKUP; - kthread_stop(ipvs->backup_thread); + retc = kthread_stop(ipvs->backup_thread); ipvs->backup_thread = NULL; - } else { - return -EINVAL; } /* decrease the module use count */ ip_vs_use_count_dec(); - return 0; + return retc; } /* * Initialize data struct for each netns */ -static int __net_init __ip_vs_sync_init(struct net *net) +int __net_init __ip_vs_sync_init(struct net *net) { struct netns_ipvs *ipvs = net_ipvs(net); @@ -1668,24 +1677,24 @@ static int __net_init __ip_vs_sync_init(struct net *net) return 0; } -static void __ip_vs_sync_cleanup(struct net *net) +void __ip_vs_sync_cleanup(struct net *net) { - stop_sync_thread(net, IP_VS_STATE_MASTER); - stop_sync_thread(net, IP_VS_STATE_BACKUP); + int retc; + + retc = stop_sync_thread(net, IP_VS_STATE_MASTER); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Master Daemon\n"); + + retc = stop_sync_thread(net, IP_VS_STATE_BACKUP); + if (retc && retc != -ESRCH) + pr_err("Failed to stop Backup Daemon\n"); } -static struct pernet_operations ipvs_sync_ops = { - .init = __ip_vs_sync_init, - .exit = __ip_vs_sync_cleanup, -}; - - int __init ip_vs_sync_init(void) { - return register_pernet_subsys(&ipvs_sync_ops); + return 0; } void ip_vs_sync_cleanup(void) { - unregister_pernet_subsys(&ipvs_sync_ops); } diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 30bf8a167fc8..482e90c61850 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1334,6 +1334,7 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, struct nf_conn *ct; int err = -EINVAL; struct nf_conntrack_helper *helper; + struct nf_conn_tstamp *tstamp; ct = nf_conntrack_alloc(net, zone, otuple, rtuple, GFP_ATOMIC); if (IS_ERR(ct)) @@ -1451,6 +1452,9 @@ ctnetlink_create_conntrack(struct net *net, u16 zone, __set_bit(IPS_EXPECTED_BIT, &ct->status); ct->master = master_ct; } + tstamp = nf_conn_tstamp_find(ct); + if (tstamp) + tstamp->start = ktime_to_ns(ktime_get_real()); add_timer(&ct->timeout); nf_conntrack_hash_insert(ct); diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index a9adf4c6b299..8a025a585d2f 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -455,6 +455,7 @@ void xt_compat_flush_offsets(u_int8_t af) vfree(xt[af].compat_tab); xt[af].compat_tab = NULL; xt[af].number = 0; + xt[af].cur = 0; } } EXPORT_SYMBOL_GPL(xt_compat_flush_offsets); @@ -473,8 +474,7 @@ int xt_compat_calc_jump(u_int8_t af, unsigned int offset) else return mid ? tmp[mid - 1].delta : 0; } - WARN_ON_ONCE(1); - return 0; + return left ? tmp[left - 1].delta : 0; } EXPORT_SYMBOL_GPL(xt_compat_calc_jump); diff --git a/net/netfilter/xt_DSCP.c b/net/netfilter/xt_DSCP.c index 0a229191e55b..ae8271652efa 100644 --- a/net/netfilter/xt_DSCP.c +++ b/net/netfilter/xt_DSCP.c @@ -99,7 +99,7 @@ tos_tg6(struct sk_buff *skb, const struct xt_action_param *par) u_int8_t orig, nv; orig = ipv6_get_dsfield(iph); - nv = (orig & info->tos_mask) ^ info->tos_value; + nv = (orig & ~info->tos_mask) ^ info->tos_value; if (orig != nv) { if (!skb_make_writable(skb, sizeof(struct iphdr))) diff --git a/net/netfilter/xt_conntrack.c b/net/netfilter/xt_conntrack.c index 481a86fdc409..61805d7b38aa 100644 --- a/net/netfilter/xt_conntrack.c +++ b/net/netfilter/xt_conntrack.c @@ -272,11 +272,6 @@ static int conntrack_mt_check(const struct xt_mtchk_param *par) { int ret; - if (strcmp(par->table, "raw") == 0) { - pr_info("state is undetermined at the time of raw table\n"); - return -EINVAL; - } - ret = nf_ct_l3proto_try_module_get(par->family); if (ret < 0) pr_info("cannot load conntrack support for proto=%u\n", diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 15792d8b6272..b4d745ea8ee1 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -1406,6 +1406,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct net *net = xp_net(policy); unsigned long now = jiffies; struct net_device *dev; + struct xfrm_mode *inner_mode; struct dst_entry *dst_prev = NULL; struct dst_entry *dst0 = NULL; int i = 0; @@ -1436,6 +1437,17 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, goto put_states; } + if (xfrm[i]->sel.family == AF_UNSPEC) { + inner_mode = xfrm_ip2inner_mode(xfrm[i], + xfrm_af2proto(family)); + if (!inner_mode) { + err = -EAFNOSUPPORT; + dst_release(dst); + goto put_states; + } + } else + inner_mode = xfrm[i]->inner_mode; + if (!dst_prev) dst0 = dst1; else { @@ -1464,7 +1476,7 @@ static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, dst1->lastuse = now; dst1->input = dst_discard; - dst1->output = xfrm[i]->outer_mode->afinfo->output; + dst1->output = inner_mode->afinfo->output; dst1->next = dst_prev; dst_prev = dst1; diff --git a/net/xfrm/xfrm_replay.c b/net/xfrm/xfrm_replay.c index e8a781422feb..47f1b8638df9 100644 --- a/net/xfrm/xfrm_replay.c +++ b/net/xfrm/xfrm_replay.c @@ -535,6 +535,9 @@ int xfrm_init_replay(struct xfrm_state *x) replay_esn->bmp_len * sizeof(__u32) * 8) return -EINVAL; + if ((x->props.flags & XFRM_STATE_ESN) && replay_esn->replay_window == 0) + return -EINVAL; + if ((x->props.flags & XFRM_STATE_ESN) && x->replay_esn) x->repl = &xfrm_replay_esn; else