diff --git a/MAINTAINERS b/MAINTAINERS index 9800de5ec222..e7c528ff1013 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1445,6 +1445,16 @@ S: Maintained F: Documentation/video4linux/cafe_ccic F: drivers/media/video/cafe_ccic* +CAIF NETWORK LAYER +M: Sjur Braendeland +L: netdev@vger.kernel.org +S: Supported +F: Documentation/networking/caif/ +F: drivers/net/caif/ +F: include/linux/caif/ +F: include/net/caif/ +F: net/caif/ + CALGARY x86-64 IOMMU M: Muli Ben-Yehuda M: "Jon D. Mason" diff --git a/drivers/net/3c59x.c b/drivers/net/3c59x.c index a045559c81cf..85671adae455 100644 --- a/drivers/net/3c59x.c +++ b/drivers/net/3c59x.c @@ -1994,10 +1994,9 @@ vortex_error(struct net_device *dev, int status) } } - if (status & RxEarly) { /* Rx early is unused. */ - vortex_rx(dev); + if (status & RxEarly) /* Rx early is unused. */ iowrite16(AckIntr | RxEarly, ioaddr + EL3_CMD); - } + if (status & StatsFull) { /* Empty statistics. */ static int DoneDidThat; if (vortex_debug > 4) @@ -2298,7 +2297,12 @@ vortex_interrupt(int irq, void *dev_id) if (status & (HostError | RxEarly | StatsFull | TxComplete | IntReq)) { if (status == 0xffff) break; + if (status & RxEarly) + vortex_rx(dev); + spin_unlock(&vp->window_lock); vortex_error(dev, status); + spin_lock(&vp->window_lock); + window_set(vp, 7); } if (--work_done < 0) { diff --git a/drivers/net/b44.c b/drivers/net/b44.c index 37617abc1647..1e620e287ae0 100644 --- a/drivers/net/b44.c +++ b/drivers/net/b44.c @@ -848,6 +848,15 @@ static int b44_poll(struct napi_struct *napi, int budget) b44_tx(bp); /* spin_unlock(&bp->tx_lock); */ } + if (bp->istat & ISTAT_RFO) { /* fast recovery, in ~20msec */ + bp->istat &= ~ISTAT_RFO; + b44_disable_ints(bp); + ssb_device_enable(bp->sdev, 0); /* resets ISTAT_RFO */ + b44_init_rings(bp); + b44_init_hw(bp, B44_FULL_RESET_SKIP_PHY); + netif_wake_queue(bp->dev); + } + spin_unlock_irqrestore(&bp->lock, flags); work_done = 0; diff --git a/drivers/net/benet/be.h b/drivers/net/benet/be.h index 99197bd54da5..53306bf3f401 100644 --- a/drivers/net/benet/be.h +++ b/drivers/net/benet/be.h @@ -181,6 +181,7 @@ struct be_drvr_stats { u64 be_rx_bytes_prev; u64 be_rx_pkts; u32 be_rx_rate; + u32 be_rx_mcast_pkt; /* number of non ether type II frames dropped where * frame len > length field of Mac Hdr */ u32 be_802_3_dropped_frames; diff --git a/drivers/net/benet/be_cmds.c b/drivers/net/benet/be_cmds.c index 3d305494a606..34abcc9403d6 100644 --- a/drivers/net/benet/be_cmds.c +++ b/drivers/net/benet/be_cmds.c @@ -140,10 +140,8 @@ int be_process_mcc(struct be_adapter *adapter, int *status) while ((compl = be_mcc_compl_get(adapter))) { if (compl->flags & CQE_FLAGS_ASYNC_MASK) { /* Interpret flags as an async trailer */ - BUG_ON(!is_link_state_evt(compl->flags)); - - /* Interpret compl as a async link evt */ - be_async_link_state_process(adapter, + if (is_link_state_evt(compl->flags)) + be_async_link_state_process(adapter, (struct be_async_event_link_state *) compl); } else if (compl->flags & CQE_FLAGS_COMPLETED_MASK) { *status = be_mcc_compl_process(adapter, compl); @@ -207,7 +205,7 @@ static int be_mbox_db_ready_wait(struct be_adapter *adapter, void __iomem *db) if (msecs > 4000) { dev_err(&adapter->pdev->dev, "mbox poll timed out\n"); - be_dump_ue(adapter); + be_detect_dump_ue(adapter); return -1; } diff --git a/drivers/net/benet/be_cmds.h b/drivers/net/benet/be_cmds.h index bdc10a28cfda..ad1e6fac60c5 100644 --- a/drivers/net/benet/be_cmds.h +++ b/drivers/net/benet/be_cmds.h @@ -992,5 +992,5 @@ extern int be_cmd_set_loopback(struct be_adapter *adapter, u8 port_num, extern int be_cmd_get_phy_info(struct be_adapter *adapter, struct be_dma_mem *cmd); extern int be_cmd_set_qos(struct be_adapter *adapter, u32 bps, u32 domain); -extern void be_dump_ue(struct be_adapter *adapter); +extern void be_detect_dump_ue(struct be_adapter *adapter); diff --git a/drivers/net/benet/be_ethtool.c b/drivers/net/benet/be_ethtool.c index cd16243c7c36..13f0abbc5205 100644 --- a/drivers/net/benet/be_ethtool.c +++ b/drivers/net/benet/be_ethtool.c @@ -60,6 +60,7 @@ static const struct be_ethtool_stat et_stats[] = { {DRVSTAT_INFO(be_rx_events)}, {DRVSTAT_INFO(be_tx_compl)}, {DRVSTAT_INFO(be_rx_compl)}, + {DRVSTAT_INFO(be_rx_mcast_pkt)}, {DRVSTAT_INFO(be_ethrx_post_fail)}, {DRVSTAT_INFO(be_802_3_dropped_frames)}, {DRVSTAT_INFO(be_802_3_malformed_frames)}, diff --git a/drivers/net/benet/be_hw.h b/drivers/net/benet/be_hw.h index 5d38046402b2..a2ec5df0d733 100644 --- a/drivers/net/benet/be_hw.h +++ b/drivers/net/benet/be_hw.h @@ -167,8 +167,11 @@ #define FLASH_FCoE_BIOS_START_g3 (13631488) #define FLASH_REDBOOT_START_g3 (262144) - - +/************* Rx Packet Type Encoding **************/ +#define BE_UNICAST_PACKET 0 +#define BE_MULTICAST_PACKET 1 +#define BE_BROADCAST_PACKET 2 +#define BE_RSVD_PACKET 3 /* * BE descriptors: host memory data structures whose formats diff --git a/drivers/net/benet/be_main.c b/drivers/net/benet/be_main.c index 74e146f470c6..6eda7a022256 100644 --- a/drivers/net/benet/be_main.c +++ b/drivers/net/benet/be_main.c @@ -247,6 +247,7 @@ void netdev_stats_update(struct be_adapter *adapter) dev_stats->tx_packets = drvr_stats(adapter)->be_tx_pkts; dev_stats->rx_bytes = drvr_stats(adapter)->be_rx_bytes; dev_stats->tx_bytes = drvr_stats(adapter)->be_tx_bytes; + dev_stats->multicast = drvr_stats(adapter)->be_rx_mcast_pkt; /* bad pkts received */ dev_stats->rx_errors = port_stats->rx_crc_errors + @@ -294,7 +295,6 @@ void netdev_stats_update(struct be_adapter *adapter) /* no space available in linux */ dev_stats->tx_dropped = 0; - dev_stats->multicast = port_stats->rx_multicast_frames; dev_stats->collisions = 0; /* detailed tx_errors */ @@ -848,7 +848,7 @@ static void be_rx_rate_update(struct be_adapter *adapter) } static void be_rx_stats_update(struct be_adapter *adapter, - u32 pktsize, u16 numfrags) + u32 pktsize, u16 numfrags, u8 pkt_type) { struct be_drvr_stats *stats = drvr_stats(adapter); @@ -856,6 +856,9 @@ static void be_rx_stats_update(struct be_adapter *adapter, stats->be_rx_frags += numfrags; stats->be_rx_bytes += pktsize; stats->be_rx_pkts++; + + if (pkt_type == BE_MULTICAST_PACKET) + stats->be_rx_mcast_pkt++; } static inline bool do_pkt_csum(struct be_eth_rx_compl *rxcp, bool cso) @@ -925,9 +928,11 @@ static void skb_fill_rx_data(struct be_adapter *adapter, u16 rxq_idx, i, j; u32 pktsize, hdr_len, curr_frag_len, size; u8 *start; + u8 pkt_type; rxq_idx = AMAP_GET_BITS(struct amap_eth_rx_compl, fragndx, rxcp); pktsize = AMAP_GET_BITS(struct amap_eth_rx_compl, pktsize, rxcp); + pkt_type = AMAP_GET_BITS(struct amap_eth_rx_compl, cast_enc, rxcp); page_info = get_rx_page_info(adapter, rxq_idx); @@ -993,7 +998,7 @@ static void skb_fill_rx_data(struct be_adapter *adapter, BUG_ON(j > MAX_SKB_FRAGS); done: - be_rx_stats_update(adapter, pktsize, num_rcvd); + be_rx_stats_update(adapter, pktsize, num_rcvd, pkt_type); } /* Process the RX completion indicated by rxcp when GRO is disabled */ @@ -1060,6 +1065,7 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter, u32 num_rcvd, pkt_size, remaining, vlanf, curr_frag_len; u16 i, rxq_idx = 0, vid, j; u8 vtm; + u8 pkt_type; num_rcvd = AMAP_GET_BITS(struct amap_eth_rx_compl, numfrags, rxcp); /* Is it a flush compl that has no data */ @@ -1070,6 +1076,7 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter, vlanf = AMAP_GET_BITS(struct amap_eth_rx_compl, vtp, rxcp); rxq_idx = AMAP_GET_BITS(struct amap_eth_rx_compl, fragndx, rxcp); vtm = AMAP_GET_BITS(struct amap_eth_rx_compl, vtm, rxcp); + pkt_type = AMAP_GET_BITS(struct amap_eth_rx_compl, cast_enc, rxcp); /* vlanf could be wrongly set in some cards. * ignore if vtm is not set */ @@ -1125,7 +1132,7 @@ static void be_rx_compl_process_gro(struct be_adapter *adapter, vlan_gro_frags(&eq_obj->napi, adapter->vlan_grp, vid); } - be_rx_stats_update(adapter, pkt_size, num_rcvd); + be_rx_stats_update(adapter, pkt_size, num_rcvd, pkt_type); } static struct be_eth_rx_compl *be_rx_compl_get(struct be_adapter *adapter) @@ -1743,26 +1750,7 @@ static int be_poll_tx_mcc(struct napi_struct *napi, int budget) return 1; } -static inline bool be_detect_ue(struct be_adapter *adapter) -{ - u32 online0 = 0, online1 = 0; - - pci_read_config_dword(adapter->pdev, PCICFG_ONLINE0, &online0); - - pci_read_config_dword(adapter->pdev, PCICFG_ONLINE1, &online1); - - if (!online0 || !online1) { - adapter->ue_detected = true; - dev_err(&adapter->pdev->dev, - "UE Detected!! online0=%d online1=%d\n", - online0, online1); - return true; - } - - return false; -} - -void be_dump_ue(struct be_adapter *adapter) +void be_detect_dump_ue(struct be_adapter *adapter) { u32 ue_status_lo, ue_status_hi, ue_status_lo_mask, ue_status_hi_mask; u32 i; @@ -1779,6 +1767,11 @@ void be_dump_ue(struct be_adapter *adapter) ue_status_lo = (ue_status_lo & (~ue_status_lo_mask)); ue_status_hi = (ue_status_hi & (~ue_status_hi_mask)); + if (ue_status_lo || ue_status_hi) { + adapter->ue_detected = true; + dev_err(&adapter->pdev->dev, "UE Detected!!\n"); + } + if (ue_status_lo) { for (i = 0; ue_status_lo; ue_status_lo >>= 1, i++) { if (ue_status_lo & 1) @@ -1814,10 +1807,8 @@ static void be_worker(struct work_struct *work) adapter->rx_post_starved = false; be_post_rx_frags(adapter); } - if (!adapter->ue_detected) { - if (be_detect_ue(adapter)) - be_dump_ue(adapter); - } + if (!adapter->ue_detected) + be_detect_dump_ue(adapter); schedule_delayed_work(&adapter->work, msecs_to_jiffies(1000)); } diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 2cc4cfc31892..3b16f62d5606 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -2797,9 +2797,15 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * so it can wait */ bond_for_each_slave(bond, slave, i) { + unsigned long trans_start = dev_trans_start(slave->dev); + if (slave->link != BOND_LINK_UP) { - if (time_before_eq(jiffies, dev_trans_start(slave->dev) + delta_in_ticks) && - time_before_eq(jiffies, slave->dev->last_rx + delta_in_ticks)) { + if (time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + delta_in_ticks) && + time_in_range(jiffies, + slave->dev->last_rx - delta_in_ticks, + slave->dev->last_rx + delta_in_ticks)) { slave->link = BOND_LINK_UP; slave->state = BOND_STATE_ACTIVE; @@ -2827,8 +2833,12 @@ void bond_loadbalance_arp_mon(struct work_struct *work) * when the source ip is 0, so don't take the link down * if we don't know our ip yet */ - if (time_after_eq(jiffies, dev_trans_start(slave->dev) + 2*delta_in_ticks) || - (time_after_eq(jiffies, slave->dev->last_rx + 2*delta_in_ticks))) { + if (!time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + 2 * delta_in_ticks) || + !time_in_range(jiffies, + slave->dev->last_rx - delta_in_ticks, + slave->dev->last_rx + 2 * delta_in_ticks)) { slave->link = BOND_LINK_DOWN; slave->state = BOND_STATE_BACKUP; @@ -2883,13 +2893,16 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) { struct slave *slave; int i, commit = 0; + unsigned long trans_start; bond_for_each_slave(bond, slave, i) { slave->new_link = BOND_LINK_NOCHANGE; if (slave->link != BOND_LINK_UP) { - if (time_before_eq(jiffies, slave_last_rx(bond, slave) + - delta_in_ticks)) { + if (time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + delta_in_ticks)) { + slave->new_link = BOND_LINK_UP; commit++; } @@ -2902,8 +2915,9 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * active. This avoids bouncing, as the last receive * times need a full ARP monitor cycle to be updated. */ - if (!time_after_eq(jiffies, slave->jiffies + - 2 * delta_in_ticks)) + if (time_in_range(jiffies, + slave->jiffies - delta_in_ticks, + slave->jiffies + 2 * delta_in_ticks)) continue; /* @@ -2921,8 +2935,10 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) */ if (slave->state == BOND_STATE_BACKUP && !bond->current_arp_slave && - time_after(jiffies, slave_last_rx(bond, slave) + - 3 * delta_in_ticks)) { + !time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + 3 * delta_in_ticks)) { + slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2933,11 +2949,15 @@ static int bond_ab_arp_inspect(struct bonding *bond, int delta_in_ticks) * - (more than 2*delta since receive AND * the bond has an IP address) */ + trans_start = dev_trans_start(slave->dev); if ((slave->state == BOND_STATE_ACTIVE) && - (time_after_eq(jiffies, dev_trans_start(slave->dev) + - 2 * delta_in_ticks) || - (time_after_eq(jiffies, slave_last_rx(bond, slave) - + 2 * delta_in_ticks)))) { + (!time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + 2 * delta_in_ticks) || + !time_in_range(jiffies, + slave_last_rx(bond, slave) - delta_in_ticks, + slave_last_rx(bond, slave) + 2 * delta_in_ticks))) { + slave->new_link = BOND_LINK_DOWN; commit++; } @@ -2956,6 +2976,7 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) { struct slave *slave; int i; + unsigned long trans_start; bond_for_each_slave(bond, slave, i) { switch (slave->new_link) { @@ -2963,10 +2984,11 @@ static void bond_ab_arp_commit(struct bonding *bond, int delta_in_ticks) continue; case BOND_LINK_UP: + trans_start = dev_trans_start(slave->dev); if ((!bond->curr_active_slave && - time_before_eq(jiffies, - dev_trans_start(slave->dev) + - delta_in_ticks)) || + time_in_range(jiffies, + trans_start - delta_in_ticks, + trans_start + delta_in_ticks)) || bond->curr_active_slave != slave) { slave->link = BOND_LINK_UP; bond->current_arp_slave = NULL; diff --git a/drivers/net/ks8851.c b/drivers/net/ks8851.c index b4fb07a6f13f..51919fcd50c2 100644 --- a/drivers/net/ks8851.c +++ b/drivers/net/ks8851.c @@ -503,30 +503,33 @@ static void ks8851_rx_pkts(struct ks8851_net *ks) ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr | RXQCR_SDA | RXQCR_ADRFE); - if (rxlen > 0) { - skb = netdev_alloc_skb(ks->netdev, rxlen + 2 + 8); - if (!skb) { - /* todo - dump frame and move on */ + if (rxlen > 4) { + unsigned int rxalign; + + rxlen -= 4; + rxalign = ALIGN(rxlen, 4); + skb = netdev_alloc_skb_ip_align(ks->netdev, rxalign); + if (skb) { + + /* 4 bytes of status header + 4 bytes of + * garbage: we put them before ethernet + * header, so that they are copied, + * but ignored. + */ + + rxpkt = skb_put(skb, rxlen) - 8; + + ks8851_rdfifo(ks, rxpkt, rxalign + 8); + + if (netif_msg_pktdata(ks)) + ks8851_dbg_dumpkkt(ks, rxpkt); + + skb->protocol = eth_type_trans(skb, ks->netdev); + netif_rx(skb); + + ks->netdev->stats.rx_packets++; + ks->netdev->stats.rx_bytes += rxlen; } - - /* two bytes to ensure ip is aligned, and four bytes - * for the status header and 4 bytes of garbage */ - skb_reserve(skb, 2 + 4 + 4); - - rxpkt = skb_put(skb, rxlen - 4) - 8; - - /* align the packet length to 4 bytes, and add 4 bytes - * as we're getting the rx status header as well */ - ks8851_rdfifo(ks, rxpkt, ALIGN(rxlen, 4) + 8); - - if (netif_msg_pktdata(ks)) - ks8851_dbg_dumpkkt(ks, rxpkt); - - skb->protocol = eth_type_trans(skb, ks->netdev); - netif_rx(skb); - - ks->netdev->stats.rx_packets++; - ks->netdev->stats.rx_bytes += rxlen - 4; } ks8851_wrreg16(ks, KS_RXQCR, ks->rc_rxqcr); diff --git a/drivers/net/niu.c b/drivers/net/niu.c index bc695d53cdcc..fe6983af6918 100644 --- a/drivers/net/niu.c +++ b/drivers/net/niu.c @@ -7269,32 +7269,28 @@ static int niu_get_ethtool_tcam_all(struct niu *np, struct niu_parent *parent = np->parent; struct niu_tcam_entry *tp; int i, idx, cnt; - u16 n_entries; unsigned long flags; - + int ret = 0; /* put the tcam size here */ nfc->data = tcam_get_size(np); niu_lock_parent(np, flags); - n_entries = nfc->rule_cnt; for (cnt = 0, i = 0; i < nfc->data; i++) { idx = tcam_get_index(np, i); tp = &parent->tcam[idx]; if (!tp->valid) continue; + if (cnt == nfc->rule_cnt) { + ret = -EMSGSIZE; + break; + } rule_locs[cnt] = i; cnt++; } niu_unlock_parent(np, flags); - if (n_entries != cnt) { - /* print warning, this should not happen */ - netdev_info(np->dev, "niu%d: In %s(): n_entries[%d] != cnt[%d]!!!\n", - np->parent->index, __func__, n_entries, cnt); - } - - return 0; + return ret; } static int niu_get_nfc(struct net_device *dev, struct ethtool_rxnfc *cmd, diff --git a/drivers/net/stmmac/stmmac_main.c b/drivers/net/stmmac/stmmac_main.c index bbb7951b9c4c..ea0461eb2dbe 100644 --- a/drivers/net/stmmac/stmmac_main.c +++ b/drivers/net/stmmac/stmmac_main.c @@ -1865,15 +1865,15 @@ static int stmmac_resume(struct platform_device *pdev) if (!netif_running(dev)) return 0; - spin_lock(&priv->lock); - if (priv->shutdown) { /* Re-open the interface and re-init the MAC/DMA - and the rings. */ + and the rings (i.e. on hibernation stage) */ stmmac_open(dev); - goto out_resume; + return 0; } + spin_lock(&priv->lock); + /* Power Down bit, into the PM register, is cleared * automatically as soon as a magic packet or a Wake-up frame * is received. Anyway, it's better to manually clear @@ -1901,7 +1901,6 @@ static int stmmac_resume(struct platform_device *pdev) netif_start_queue(dev); -out_resume: spin_unlock(&priv->lock); return 0; } diff --git a/drivers/net/usb/ipheth.c b/drivers/net/usb/ipheth.c index 8ed30fa35d0a..b2bcf99e6f08 100644 --- a/drivers/net/usb/ipheth.c +++ b/drivers/net/usb/ipheth.c @@ -429,10 +429,6 @@ static const struct net_device_ops ipheth_netdev_ops = { .ndo_get_stats = &ipheth_stats, }; -static struct device_type ipheth_type = { - .name = "wwan", -}; - static int ipheth_probe(struct usb_interface *intf, const struct usb_device_id *id) { @@ -450,7 +446,7 @@ static int ipheth_probe(struct usb_interface *intf, netdev->netdev_ops = &ipheth_netdev_ops; netdev->watchdog_timeo = IPHETH_TX_TIMEOUT; - strcpy(netdev->name, "wwan%d"); + strcpy(netdev->name, "eth%d"); dev = netdev_priv(netdev); dev->udev = udev; @@ -500,7 +496,6 @@ static int ipheth_probe(struct usb_interface *intf, SET_NETDEV_DEV(netdev, &intf->dev); SET_ETHTOOL_OPS(netdev, &ops); - SET_NETDEV_DEVTYPE(netdev, &ipheth_type); retval = register_netdev(netdev); if (retval) { diff --git a/drivers/net/via-velocity.c b/drivers/net/via-velocity.c index fd69095ef6e3..f53412368ce1 100644 --- a/drivers/net/via-velocity.c +++ b/drivers/net/via-velocity.c @@ -2824,7 +2824,7 @@ static int __devinit velocity_found1(struct pci_dev *pdev, const struct pci_devi netif_napi_add(dev, &vptr->napi, velocity_poll, VELOCITY_NAPI_WEIGHT); dev->features |= NETIF_F_HW_VLAN_TX | NETIF_F_HW_VLAN_FILTER | - NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM | NETIF_F_SG; + NETIF_F_HW_VLAN_RX | NETIF_F_IP_CSUM; ret = register_netdev(dev); if (ret < 0) diff --git a/drivers/vhost/vhost.c b/drivers/vhost/vhost.c index 4b99117f3ecd..c579dcc9200c 100644 --- a/drivers/vhost/vhost.c +++ b/drivers/vhost/vhost.c @@ -60,17 +60,8 @@ static int vhost_poll_wakeup(wait_queue_t *wait, unsigned mode, int sync, return 0; } -/* Init poll structure */ -void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, - unsigned long mask, struct vhost_dev *dev) +static void vhost_work_init(struct vhost_work *work, vhost_work_fn_t fn) { - struct vhost_work *work = &poll->work; - - init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup); - init_poll_funcptr(&poll->table, vhost_poll_func); - poll->mask = mask; - poll->dev = dev; - INIT_LIST_HEAD(&work->node); work->fn = fn; init_waitqueue_head(&work->done); @@ -78,6 +69,18 @@ void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, work->queue_seq = work->done_seq = 0; } +/* Init poll structure */ +void vhost_poll_init(struct vhost_poll *poll, vhost_work_fn_t fn, + unsigned long mask, struct vhost_dev *dev) +{ + init_waitqueue_func_entry(&poll->wait, vhost_poll_wakeup); + init_poll_funcptr(&poll->table, vhost_poll_func); + poll->mask = mask; + poll->dev = dev; + + vhost_work_init(&poll->work, fn); +} + /* Start polling a file. We add ourselves to file's wait queue. The caller must * keep a reference to a file until after vhost_poll_stop is called. */ void vhost_poll_start(struct vhost_poll *poll, struct file *file) @@ -95,35 +98,38 @@ void vhost_poll_stop(struct vhost_poll *poll) remove_wait_queue(poll->wqh, &poll->wait); } -/* Flush any work that has been scheduled. When calling this, don't hold any - * locks that are also used by the callback. */ -void vhost_poll_flush(struct vhost_poll *poll) +static void vhost_work_flush(struct vhost_dev *dev, struct vhost_work *work) { - struct vhost_work *work = &poll->work; unsigned seq; int left; int flushing; - spin_lock_irq(&poll->dev->work_lock); + spin_lock_irq(&dev->work_lock); seq = work->queue_seq; work->flushing++; - spin_unlock_irq(&poll->dev->work_lock); + spin_unlock_irq(&dev->work_lock); wait_event(work->done, ({ - spin_lock_irq(&poll->dev->work_lock); + spin_lock_irq(&dev->work_lock); left = seq - work->done_seq <= 0; - spin_unlock_irq(&poll->dev->work_lock); + spin_unlock_irq(&dev->work_lock); left; })); - spin_lock_irq(&poll->dev->work_lock); + spin_lock_irq(&dev->work_lock); flushing = --work->flushing; - spin_unlock_irq(&poll->dev->work_lock); + spin_unlock_irq(&dev->work_lock); BUG_ON(flushing < 0); } -void vhost_poll_queue(struct vhost_poll *poll) +/* Flush any work that has been scheduled. When calling this, don't hold any + * locks that are also used by the callback. */ +void vhost_poll_flush(struct vhost_poll *poll) +{ + vhost_work_flush(poll->dev, &poll->work); +} + +static inline void vhost_work_queue(struct vhost_dev *dev, + struct vhost_work *work) { - struct vhost_dev *dev = poll->dev; - struct vhost_work *work = &poll->work; unsigned long flags; spin_lock_irqsave(&dev->work_lock, flags); @@ -135,6 +141,11 @@ void vhost_poll_queue(struct vhost_poll *poll) spin_unlock_irqrestore(&dev->work_lock, flags); } +void vhost_poll_queue(struct vhost_poll *poll) +{ + vhost_work_queue(poll->dev, &poll->work); +} + static void vhost_vq_reset(struct vhost_dev *dev, struct vhost_virtqueue *vq) { @@ -236,6 +247,29 @@ long vhost_dev_check_owner(struct vhost_dev *dev) return dev->mm == current->mm ? 0 : -EPERM; } +struct vhost_attach_cgroups_struct { + struct vhost_work work; + struct task_struct *owner; + int ret; +}; + +static void vhost_attach_cgroups_work(struct vhost_work *work) +{ + struct vhost_attach_cgroups_struct *s; + s = container_of(work, struct vhost_attach_cgroups_struct, work); + s->ret = cgroup_attach_task_all(s->owner, current); +} + +static int vhost_attach_cgroups(struct vhost_dev *dev) +{ + struct vhost_attach_cgroups_struct attach; + attach.owner = current; + vhost_work_init(&attach.work, vhost_attach_cgroups_work); + vhost_work_queue(dev, &attach.work); + vhost_work_flush(dev, &attach.work); + return attach.ret; +} + /* Caller should have device mutex */ static long vhost_dev_set_owner(struct vhost_dev *dev) { @@ -255,14 +289,16 @@ static long vhost_dev_set_owner(struct vhost_dev *dev) } dev->worker = worker; - err = cgroup_attach_task_current_cg(worker); + wake_up_process(worker); /* avoid contributing to loadavg */ + + err = vhost_attach_cgroups(dev); if (err) goto err_cgroup; - wake_up_process(worker); /* avoid contributing to loadavg */ return 0; err_cgroup: kthread_stop(worker); + dev->worker = NULL; err_worker: if (dev->mm) mmput(dev->mm); diff --git a/include/net/cls_cgroup.h b/include/net/cls_cgroup.h index 726cc3536409..ef6c24a529e1 100644 --- a/include/net/cls_cgroup.h +++ b/include/net/cls_cgroup.h @@ -27,11 +27,17 @@ struct cgroup_cls_state #ifdef CONFIG_NET_CLS_CGROUP static inline u32 task_cls_classid(struct task_struct *p) { + int classid; + if (in_interrupt()) return 0; - return container_of(task_subsys_state(p, net_cls_subsys_id), - struct cgroup_cls_state, css)->classid; + rcu_read_lock(); + classid = container_of(task_subsys_state(p, net_cls_subsys_id), + struct cgroup_cls_state, css)->classid; + rcu_read_unlock(); + + return classid; } #else extern int net_cls_subsys_id; diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index a4747a0f7303..f976885f686f 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -955,6 +955,9 @@ static inline __wsum ip_vs_check_diff2(__be16 old, __be16 new, __wsum oldsum) return csum_partial(diff, sizeof(diff), oldsum); } +extern void ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, + int outin); + #endif /* __KERNEL__ */ #endif /* _NET_IP_VS_H */ diff --git a/include/net/sock.h b/include/net/sock.h index ac53bfbdfe16..adab9dc58183 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -752,6 +752,7 @@ struct proto { /* Keeping track of sk's, looking them up, and port selection methods. */ void (*hash)(struct sock *sk); void (*unhash)(struct sock *sk); + void (*rehash)(struct sock *sk); int (*get_port)(struct sock *sk, unsigned short snum); /* Keeping track of sockets in use */ diff --git a/include/net/udp.h b/include/net/udp.h index 7abdf305da50..a184d3496b13 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -151,6 +151,7 @@ static inline void udp_lib_hash(struct sock *sk) } extern void udp_lib_unhash(struct sock *sk); +extern void udp_lib_rehash(struct sock *sk, u16 new_hash); static inline void udp_lib_close(struct sock *sk, long timeout) { diff --git a/net/core/dev.c b/net/core/dev.c index 3721fbb9a83c..b9b22a3c4c8f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2058,16 +2058,16 @@ static struct netdev_queue *dev_pick_tx(struct net_device *dev, struct sk_buff *skb) { int queue_index; - struct sock *sk = skb->sk; + const struct net_device_ops *ops = dev->netdev_ops; - queue_index = sk_tx_queue_get(sk); - if (queue_index < 0) { - const struct net_device_ops *ops = dev->netdev_ops; + if (ops->ndo_select_queue) { + queue_index = ops->ndo_select_queue(dev, skb); + queue_index = dev_cap_txqueue(dev, queue_index); + } else { + struct sock *sk = skb->sk; + queue_index = sk_tx_queue_get(sk); + if (queue_index < 0) { - if (ops->ndo_select_queue) { - queue_index = ops->ndo_select_queue(dev, skb); - queue_index = dev_cap_txqueue(dev, queue_index); - } else { queue_index = 0; if (dev->real_num_tx_queues > 1) queue_index = skb_tx_hash(dev, skb); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 26396ff67cf9..c83b421341c0 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2706,7 +2706,7 @@ int skb_gro_receive(struct sk_buff **head, struct sk_buff *skb) } else if (skb_gro_len(p) != pinfo->gso_size) return -E2BIG; - headroom = NET_SKB_PAD + NET_IP_ALIGN; + headroom = skb_headroom(p); nskb = alloc_skb(headroom + skb_gro_offset(p), GFP_ATOMIC); if (unlikely(!nskb)) return -ENOMEM; diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f0550941df7b..721a8a37b45c 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -62,8 +62,11 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet->inet_saddr) inet->inet_saddr = rt->rt_src; /* Update source address */ - if (!inet->inet_rcv_saddr) + if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = rt->rt_src; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } inet->inet_daddr = rt->rt_dst; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a43968918350..7d02a9f999fa 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -246,6 +246,7 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct fib_result res; int no_addr, rpf, accept_local; + bool dev_match; int ret; struct net *net; @@ -273,12 +274,22 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); + dev_match = false; + #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1) + for (ret = 0; ret < res.fi->fib_nhs; ret++) { + struct fib_nh *nh = &res.fi->fib_nh[ret]; + + if (nh->nh_dev == dev) { + dev_match = true; + break; + } + } #else if (FIB_RES_DEV(res) == dev) + dev_match = true; #endif - { + if (dev_match) { ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; fib_res_put(&res); return ret; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 79d057a939ba..4a8e370862bc 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -186,7 +186,9 @@ static inline struct tnode *node_parent_rcu(struct node *node) { struct tnode *ret = node_parent(node); - return rcu_dereference(ret); + return rcu_dereference_check(ret, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); } /* Same as rcu_assign_pointer @@ -1753,7 +1755,9 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) static struct leaf *trie_firstleaf(struct trie *t) { - struct tnode *n = (struct tnode *) rcu_dereference(t->trie); + struct tnode *n = (struct tnode *) rcu_dereference_check(t->trie, + rcu_read_lock_held() || + lockdep_rtnl_is_held()); if (!n) return NULL; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3f56b6e6c6aa..6298f75d5e93 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -2738,6 +2738,11 @@ slow_output: } EXPORT_SYMBOL_GPL(__ip_route_output_key); +static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2746,7 +2751,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, - .check = ipv4_dst_check, + .check = ipv4_blackhole_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32e0bef60d0a..fb23c2e63b52 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk) } EXPORT_SYMBOL(udp_lib_unhash); +/* + * inet_rcv_saddr was changed, we must rehash secondary hash + */ +void udp_lib_rehash(struct sock *sk, u16 newhash) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2, *nhslot2; + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + nhslot2 = udp_hashslot2(udptable, newhash); + udp_sk(sk)->udp_portaddr_hash = newhash; + if (hslot2 != nhslot2) { + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + /* we must lock primary chain too */ + spin_lock_bh(&hslot->lock); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + + spin_unlock_bh(&hslot->lock); + } + } +} +EXPORT_SYMBOL(udp_lib_rehash); + +static void udp_v4_rehash(struct sock *sk) +{ + u16 new_hash = udp4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + udp_lib_rehash(sk, new_hash); +} + static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1843,6 +1886,7 @@ struct proto udp_prot = { .backlog_rcv = __udp_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 7d929a22cbc2..ef371aa01ac5 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -105,9 +105,12 @@ ipv4_connected: if (ipv6_addr_any(&np->saddr)) ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); - if (ipv6_addr_any(&np->rcv_saddr)) + if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, &np->rcv_saddr); + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } goto out; } @@ -181,6 +184,8 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); inet->inet_rcv_saddr = LOOPBACK4_IPV6; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); } ip6_dst_store(sk, dst, diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 13ef5bc05cf5..578f3c1a16db 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -113,14 +113,6 @@ static void nf_skb_free(struct sk_buff *skb) kfree_skb(NFCT_FRAG6_CB(skb)->orig); } -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf_init_frags.mem); - nf_skb_free(skb); - kfree_skb(skb); -} - /* Destruction primitives. */ static __inline__ void fq_put(struct nf_ct_frag6_queue *fq) @@ -282,66 +274,22 @@ static int nf_ct_frag6_queue(struct nf_ct_frag6_queue *fq, struct sk_buff *skb, } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. */ - if (prev) { - int i = (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset; - if (i > 0) { - offset += i; - if (end <= offset) { - pr_debug("overlap\n"); - goto err; - } - if (!pskb_pull(skb, i)) { - pr_debug("Can't pull\n"); - goto err; - } - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } + /* Check for overlap with preceding fragment. */ + if (prev && + (NFCT_FRAG6_CB(prev)->offset + prev->len) - offset > 0) + goto discard_fq; - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. - */ - while (next && NFCT_FRAG6_CB(next)->offset < end) { - /* overlap is 'i' bytes */ - int i = end - NFCT_FRAG6_CB(next)->offset; - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - pr_debug("Eat head of the overlapped parts.: %d", i); - if (!pskb_pull(next, i)) - goto err; - - /* next fragment */ - NFCT_FRAG6_CB(next)->offset += i; - fq->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragmnet is completely overridden with - * new one drop it. - */ - next = next->next; - - if (prev) - prev->next = next; - else - fq->q.fragments = next; - - fq->q.meat -= free_it->len; - frag_kfree_skb(free_it); - } - } + /* Look for overlap with succeeding segment. */ + if (next && NFCT_FRAG6_CB(next)->offset < end) + goto discard_fq; NFCT_FRAG6_CB(skb)->offset = offset; @@ -371,6 +319,8 @@ found: write_unlock(&nf_frags.lock); return 0; +discard_fq: + fq_kill(fq); err: return -1; } diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 545c4141b755..64cfef1b0a4c 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -149,13 +149,6 @@ int ip6_frag_match(struct inet_frag_queue *q, void *a) } EXPORT_SYMBOL(ip6_frag_match); -/* Memory Tracking Functions. */ -static void frag_kfree_skb(struct netns_frags *nf, struct sk_buff *skb) -{ - atomic_sub(skb->truesize, &nf->mem); - kfree_skb(skb); -} - void ip6_frag_init(struct inet_frag_queue *q, void *a) { struct frag_queue *fq = container_of(q, struct frag_queue, q); @@ -346,58 +339,22 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, } found: - /* We found where to put this one. Check for overlap with - * preceding fragment, and, if needed, align things so that - * any overlaps are eliminated. + /* RFC5722, Section 4: + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments, including those not yet received) MUST be silently + * discarded. */ - if (prev) { - int i = (FRAG6_CB(prev)->offset + prev->len) - offset; - if (i > 0) { - offset += i; - if (end <= offset) - goto err; - if (!pskb_pull(skb, i)) - goto err; - if (skb->ip_summed != CHECKSUM_UNNECESSARY) - skb->ip_summed = CHECKSUM_NONE; - } - } + /* Check for overlap with preceding fragment. */ + if (prev && + (FRAG6_CB(prev)->offset + prev->len) - offset > 0) + goto discard_fq; - /* Look for overlap with succeeding segments. - * If we can merge fragments, do it. - */ - while (next && FRAG6_CB(next)->offset < end) { - int i = end - FRAG6_CB(next)->offset; /* overlap is 'i' bytes */ - - if (i < next->len) { - /* Eat head of the next overlapped fragment - * and leave the loop. The next ones cannot overlap. - */ - if (!pskb_pull(next, i)) - goto err; - FRAG6_CB(next)->offset += i; /* next fragment */ - fq->q.meat -= i; - if (next->ip_summed != CHECKSUM_UNNECESSARY) - next->ip_summed = CHECKSUM_NONE; - break; - } else { - struct sk_buff *free_it = next; - - /* Old fragment is completely overridden with - * new one drop it. - */ - next = next->next; - - if (prev) - prev->next = next; - else - fq->q.fragments = next; - - fq->q.meat -= free_it->len; - frag_kfree_skb(fq->q.net, free_it); - } - } + /* Look for overlap with succeeding segment. */ + if (next && FRAG6_CB(next)->offset < end) + goto discard_fq; FRAG6_CB(skb)->offset = offset; @@ -436,6 +393,8 @@ found: write_unlock(&ip6_frags.lock); return -1; +discard_fq: + fq_kill(fq); err: IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 1dd1affdead2..5acb3560ff15 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -111,6 +111,15 @@ int udp_v6_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } +static void udp_v6_rehash(struct sock *sk) +{ + u16 new_hash = udp6_portaddr_hash(sock_net(sk), + &inet6_sk(sk)->rcv_saddr, + inet_sk(sk)->inet_num); + + udp_lib_rehash(sk, new_hash); +} + static inline int compute_score(struct sock *sk, struct net *net, unsigned short hnum, struct in6_addr *saddr, __be16 sport, @@ -1447,6 +1456,7 @@ struct proto udpv6_prot = { .backlog_rcv = udpv6_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v6_rehash, .get_port = udp_v6_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/irda/irlan/irlan_common.c b/net/irda/irlan/irlan_common.c index a788f9e9427d..6130f9d9dbe1 100644 --- a/net/irda/irlan/irlan_common.c +++ b/net/irda/irlan/irlan_common.c @@ -1102,7 +1102,7 @@ int irlan_extract_param(__u8 *buf, char *name, char *value, __u16 *len) memcpy(&val_len, buf+n, 2); /* To avoid alignment problems */ le16_to_cpus(&val_len); n+=2; - if (val_len > 1016) { + if (val_len >= 1016) { IRDA_DEBUG(2, "%s(), parameter length to long\n", __func__ ); return -RSP_INVALID_COMMAND_FORMAT; } diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 4f8ddba48011..4c2f89df5cce 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -924,6 +924,7 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_protocol *pp, ip_vs_out_stats(cp, skb); ip_vs_set_state(cp, IP_VS_DIR_OUTPUT, skb, pp); + ip_vs_update_conntrack(skb, cp, 0); ip_vs_conn_put(cp); skb->ipvs_property = 1; diff --git a/net/netfilter/ipvs/ip_vs_ftp.c b/net/netfilter/ipvs/ip_vs_ftp.c index 33b329bfc2d2..7e9af5b76d9e 100644 --- a/net/netfilter/ipvs/ip_vs_ftp.c +++ b/net/netfilter/ipvs/ip_vs_ftp.c @@ -410,7 +410,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, union nf_inet_addr to; __be16 port; struct ip_vs_conn *n_cp; - struct nf_conn *ct; #ifdef CONFIG_IP_VS_IPV6 /* This application helper doesn't work with IPv6 yet, @@ -497,11 +496,6 @@ static int ip_vs_ftp_in(struct ip_vs_app *app, struct ip_vs_conn *cp, ip_vs_control_add(n_cp, cp); } - ct = (struct nf_conn *)skb->nfct; - if (ct && ct != &nf_conntrack_untracked) - ip_vs_expect_related(skb, ct, n_cp, - IPPROTO_TCP, &n_cp->dport, 1); - /* * Move tunnel to listen state */ diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 21e1a5e9b9d3..49df6bea6a2d 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -349,8 +349,8 @@ ip_vs_bypass_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, } #endif -static void -ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) +void +ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp, int outin) { struct nf_conn *ct = (struct nf_conn *)skb->nfct; struct nf_conntrack_tuple new_tuple; @@ -365,11 +365,17 @@ ip_vs_update_conntrack(struct sk_buff *skb, struct ip_vs_conn *cp) * real-server we will see RIP->DIP. */ new_tuple = ct->tuplehash[IP_CT_DIR_REPLY].tuple; - new_tuple.src.u3 = cp->daddr; + if (outin) + new_tuple.src.u3 = cp->daddr; + else + new_tuple.dst.u3 = cp->vaddr; /* * This will also take care of UDP and other protocols. */ - new_tuple.src.u.tcp.port = cp->dport; + if (outin) + new_tuple.src.u.tcp.port = cp->dport; + else + new_tuple.dst.u.tcp.port = cp->vport; nf_conntrack_alter_reply(ct, &new_tuple); } @@ -428,7 +434,7 @@ ip_vs_nat_xmit(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp); + ip_vs_update_conntrack(skb, cp, 1); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still @@ -506,7 +512,7 @@ ip_vs_nat_xmit_v6(struct sk_buff *skb, struct ip_vs_conn *cp, IP_VS_DBG_PKT(10, pp, skb, 0, "After DNAT"); - ip_vs_update_conntrack(skb, cp); + ip_vs_update_conntrack(skb, cp, 1); /* FIXME: when application helper enlarges the packet and the length is larger than the MTU of outgoing device, there will be still diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 24b2cd555637..d344dc481ccc 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -1232,6 +1232,18 @@ out: return 0; } +static bool list_has_sctp_addr(const struct list_head *list, + union sctp_addr *ipaddr) +{ + struct sctp_transport *addr; + + list_for_each_entry(addr, list, transports) { + if (sctp_cmp_addr_exact(ipaddr, &addr->ipaddr)) + return true; + } + + return false; +} /* A restart is occurring, check to make sure no new addresses * are being added as we may be under a takeover attack. */ @@ -1240,10 +1252,10 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, struct sctp_chunk *init, sctp_cmd_seq_t *commands) { - struct sctp_transport *new_addr, *addr; - int found; + struct sctp_transport *new_addr; + int ret = 1; - /* Implementor's Guide - Sectin 5.2.2 + /* Implementor's Guide - Section 5.2.2 * ... * Before responding the endpoint MUST check to see if the * unexpected INIT adds new addresses to the association. If new @@ -1254,31 +1266,19 @@ static int sctp_sf_check_restart_addrs(const struct sctp_association *new_asoc, /* Search through all current addresses and make sure * we aren't adding any new ones. */ - new_addr = NULL; - found = 0; - list_for_each_entry(new_addr, &new_asoc->peer.transport_addr_list, - transports) { - found = 0; - list_for_each_entry(addr, &asoc->peer.transport_addr_list, - transports) { - if (sctp_cmp_addr_exact(&new_addr->ipaddr, - &addr->ipaddr)) { - found = 1; - break; - } - } - if (!found) + transports) { + if (!list_has_sctp_addr(&asoc->peer.transport_addr_list, + &new_addr->ipaddr)) { + sctp_sf_send_restart_abort(&new_addr->ipaddr, init, + commands); + ret = 0; break; - } - - /* If a new address was added, ABORT the sender. */ - if (!found && new_addr) { - sctp_sf_send_restart_abort(&new_addr->ipaddr, init, commands); + } } /* Return success if all addresses were found. */ - return found; + return ret; } /* Populate the verification/tie tags based on overlapping INIT diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 4414a18c63b4..0b39b2451ea5 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -692,6 +692,7 @@ static int unix_autobind(struct socket *sock) static u32 ordernum = 1; struct unix_address *addr; int err; + unsigned int retries = 0; mutex_lock(&u->readlock); @@ -717,9 +718,17 @@ retry: if (__unix_find_socket_byname(net, addr->name, addr->len, sock->type, addr->hash)) { spin_unlock(&unix_table_lock); - /* Sanity yield. It is unusual case, but yet... */ - if (!(ordernum&0xFF)) - yield(); + /* + * __unix_find_socket_byname() may take long time if many names + * are already in use. + */ + cond_resched(); + /* Give up if all names seems to be in use. */ + if (retries++ == 0xFFFFF) { + err = -ENOSPC; + kfree(addr); + goto out; + } goto retry; } addr->hash ^= sk->sk_type;