diff options
32 files changed, 829 insertions, 664 deletions
diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c index 81cc2d9831c..8d0479d5be8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_sriov.c @@ -2576,7 +2576,8 @@ int bnx2x_get_vf_config(struct net_device *dev, int vfidx, ivi->vf = vfidx; ivi->qos = 0; - ivi->tx_rate = 10000; /* always 10G. TBA take from link struct */ + ivi->max_tx_rate = 10000; /* always 10G. TBA take from link struct */ + ivi->min_tx_rate = 0; ivi->spoofchk = 1; /*always enabled */ if (vf->state == VF_ENABLED) { /* mac and vlan are in vlan_mac objects */ diff --git a/drivers/net/ethernet/emulex/benet/be_main.c b/drivers/net/ethernet/emulex/benet/be_main.c index dcc5e5c6974..4693d004a22 100644 --- a/drivers/net/ethernet/emulex/benet/be_main.c +++ b/drivers/net/ethernet/emulex/benet/be_main.c @@ -1302,7 +1302,8 @@ static int be_get_vf_config(struct net_device *netdev, int vf, return -EINVAL; vi->vf = vf; - vi->tx_rate = vf_cfg->tx_rate; + vi->max_tx_rate = vf_cfg->tx_rate; + vi->min_tx_rate = 0; vi->vlan = vf_cfg->vlan_tag & VLAN_VID_MASK; vi->qos = vf_cfg->vlan_tag >> VLAN_PRIO_SHIFT; memcpy(&vi->mac, vf_cfg->mac_addr, ETH_ALEN); @@ -1342,7 +1343,8 @@ static int be_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos) return status; } -static int be_set_vf_tx_rate(struct net_device *netdev, int vf, int rate) +static int be_set_vf_tx_rate(struct net_device *netdev, int vf, + int min_tx_rate, int max_tx_rate) { struct be_adapter *adapter = netdev_priv(netdev); int status = 0; @@ -1353,18 +1355,21 @@ static int be_set_vf_tx_rate(struct net_device *netdev, int vf, int rate) if (vf >= adapter->num_vfs) return -EINVAL; - if (rate < 100 || rate > 10000) { + if (min_tx_rate) + return -EINVAL; + + if (max_tx_rate < 100 || max_tx_rate > 10000) { dev_err(&adapter->pdev->dev, - "tx rate must be between 100 and 10000 Mbps\n"); + "max tx rate must be between 100 and 10000 Mbps\n"); return -EINVAL; } - status = be_cmd_config_qos(adapter, rate / 10, vf + 1); + status = be_cmd_config_qos(adapter, max_tx_rate / 10, vf + 1); if (status) dev_err(&adapter->pdev->dev, - "tx rate %d on VF %d failed\n", rate, vf); + "max tx rate %d on VF %d failed\n", max_tx_rate, vf); else - adapter->vf_cfg[vf].tx_rate = rate; + adapter->vf_cfg[vf].tx_rate = max_tx_rate; return status; } static int be_set_vf_link_state(struct net_device *netdev, int vf, @@ -4257,7 +4262,7 @@ static const struct net_device_ops be_netdev_ops = { .ndo_vlan_rx_kill_vid = be_vlan_rem_vid, .ndo_set_vf_mac = be_set_vf_mac, .ndo_set_vf_vlan = be_set_vf_vlan, - .ndo_set_vf_tx_rate = be_set_vf_tx_rate, + .ndo_set_vf_rate = be_set_vf_tx_rate, .ndo_get_vf_config = be_get_vf_config, .ndo_set_vf_link_state = be_set_vf_link_state, #ifdef CONFIG_NET_POLL_CONTROLLER diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index c2587f5a501..8e15ced897a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6724,7 +6724,7 @@ static const struct net_device_ops i40e_netdev_ops = { .ndo_set_features = i40e_set_features, .ndo_set_vf_mac = i40e_ndo_set_vf_mac, .ndo_set_vf_vlan = i40e_ndo_set_vf_port_vlan, - .ndo_set_vf_tx_rate = i40e_ndo_set_vf_bw, + .ndo_set_vf_rate = i40e_ndo_set_vf_bw, .ndo_get_vf_config = i40e_ndo_get_vf_config, .ndo_set_vf_link_state = i40e_ndo_set_vf_link_state, #ifdef CONFIG_I40E_VXLAN diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 4d219566a04..8564b0939dc 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -2205,7 +2205,8 @@ error_pvid: * * configure vf tx rate **/ -int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate) +int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate) { struct i40e_netdev_priv *np = netdev_priv(netdev); struct i40e_pf *pf = np->vsi->back; @@ -2221,6 +2222,12 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate) goto error; } + if (min_tx_rate) { + dev_err(&pf->pdev->dev, "Invalid min tx rate (%d) (greater than 0) specified for vf %d.\n", + min_tx_rate, vf_id); + return -EINVAL; + } + vf = &(pf->vf[vf_id]); vsi = pf->vsi[vf->lan_vsi_index]; if (!test_bit(I40E_VF_STAT_INIT, &vf->vf_states)) { @@ -2243,23 +2250,23 @@ int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate) break; } - if (tx_rate > speed) { - dev_err(&pf->pdev->dev, "Invalid tx rate %d specified for vf %d.", - tx_rate, vf->vf_id); + if (max_tx_rate > speed) { + dev_err(&pf->pdev->dev, "Invalid max tx rate %d specified for vf %d.", + max_tx_rate, vf->vf_id); ret = -EINVAL; goto error; } /* Tx rate credits are in values of 50Mbps, 0 is disabled*/ - ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, tx_rate / 50, 0, - NULL); + ret = i40e_aq_config_vsi_bw_limit(&pf->hw, vsi->seid, max_tx_rate / 50, + 0, NULL); if (ret) { - dev_err(&pf->pdev->dev, "Unable to set tx rate, error code %d.\n", + dev_err(&pf->pdev->dev, "Unable to set max tx rate, error code %d.\n", ret); ret = -EIO; goto error; } - vf->tx_rate = tx_rate; + vf->tx_rate = max_tx_rate; error: return ret; } @@ -2301,7 +2308,8 @@ int i40e_ndo_get_vf_config(struct net_device *netdev, memcpy(&ivi->mac, vf->default_lan_addr.addr, ETH_ALEN); - ivi->tx_rate = vf->tx_rate; + ivi->max_tx_rate = vf->tx_rate; + ivi->min_tx_rate = 0; ivi->vlan = le16_to_cpu(vsi->info.pvid) & I40E_VLAN_MASK; ivi->qos = (le16_to_cpu(vsi->info.pvid) & I40E_PRIORITY_MASK) >> I40E_VLAN_PRIORITY_SHIFT; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index ba3d1f8414b..5a559be4ba2 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -116,7 +116,8 @@ void i40e_vc_notify_vf_reset(struct i40e_vf *vf); int i40e_ndo_set_vf_mac(struct net_device *netdev, int vf_id, u8 *mac); int i40e_ndo_set_vf_port_vlan(struct net_device *netdev, int vf_id, u16 vlan_id, u8 qos); -int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int tx_rate); +int i40e_ndo_set_vf_bw(struct net_device *netdev, int vf_id, int min_tx_rate, + int max_tx_rate); int i40e_ndo_get_vf_config(struct net_device *netdev, int vf_id, struct ifla_vf_info *ivi); int i40e_ndo_set_vf_link_state(struct net_device *netdev, int vf_id, int link); diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index 0fbab80b052..ea2868b22c2 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -169,7 +169,7 @@ static void igb_restore_vf_multicasts(struct igb_adapter *adapter); static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac); static int igb_ndo_set_vf_vlan(struct net_device *netdev, int vf, u16 vlan, u8 qos); -static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); +static int igb_ndo_set_vf_bw(struct net_device *, int, int, int); static int igb_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); static int igb_ndo_get_vf_config(struct net_device *netdev, int vf, @@ -2084,7 +2084,7 @@ static const struct net_device_ops igb_netdev_ops = { .ndo_vlan_rx_kill_vid = igb_vlan_rx_kill_vid, .ndo_set_vf_mac = igb_ndo_set_vf_mac, .ndo_set_vf_vlan = igb_ndo_set_vf_vlan, - .ndo_set_vf_tx_rate = igb_ndo_set_vf_bw, + .ndo_set_vf_rate = igb_ndo_set_vf_bw, .ndo_set_vf_spoofchk = igb_ndo_set_vf_spoofchk, .ndo_get_vf_config = igb_ndo_get_vf_config, #ifdef CONFIG_NET_POLL_CONTROLLER @@ -7878,7 +7878,8 @@ static void igb_check_vf_rate_limit(struct igb_adapter *adapter) } } -static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) +static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, + int min_tx_rate, int max_tx_rate) { struct igb_adapter *adapter = netdev_priv(netdev); struct e1000_hw *hw = &adapter->hw; @@ -7887,15 +7888,19 @@ static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) if (hw->mac.type != e1000_82576) return -EOPNOTSUPP; + if (min_tx_rate) + return -EINVAL; + actual_link_speed = igb_link_mbps(adapter->link_speed); if ((vf >= adapter->vfs_allocated_count) || (!(rd32(E1000_STATUS) & E1000_STATUS_LU)) || - (tx_rate < 0) || (tx_rate > actual_link_speed)) + (max_tx_rate < 0) || + (max_tx_rate > actual_link_speed)) return -EINVAL; adapter->vf_rate_link_speed = actual_link_speed; - adapter->vf_data[vf].tx_rate = (u16)tx_rate; - igb_set_vf_rate_limit(hw, vf, tx_rate, actual_link_speed); + adapter->vf_data[vf].tx_rate = (u16)max_tx_rate; + igb_set_vf_rate_limit(hw, vf, max_tx_rate, actual_link_speed); return 0; } @@ -7935,7 +7940,8 @@ static int igb_ndo_get_vf_config(struct net_device *netdev, return -EINVAL; ivi->vf = vf; memcpy(&ivi->mac, adapter->vf_data[vf].vf_mac_addresses, ETH_ALEN); - ivi->tx_rate = adapter->vf_data[vf].tx_rate; + ivi->max_tx_rate = adapter->vf_data[vf].tx_rate; + ivi->min_tx_rate = 0; ivi->vlan = adapter->vf_data[vf].pf_vlan; ivi->qos = adapter->vf_data[vf].pf_qos; ivi->spoofchk = adapter->vf_data[vf].spoofchk_enabled; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 50f8293f5c0..3d666020ea1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -7926,7 +7926,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { .ndo_do_ioctl = ixgbe_ioctl, .ndo_set_vf_mac = ixgbe_ndo_set_vf_mac, .ndo_set_vf_vlan = ixgbe_ndo_set_vf_vlan, - .ndo_set_vf_tx_rate = ixgbe_ndo_set_vf_bw, + .ndo_set_vf_rate = ixgbe_ndo_set_vf_bw, .ndo_set_vf_spoofchk = ixgbe_ndo_set_vf_spoofchk, .ndo_get_vf_config = ixgbe_ndo_get_vf_config, .ndo_get_stats64 = ixgbe_get_stats64, diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 1460ad5a0cd..16b3a1cd9db 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1222,7 +1222,8 @@ void ixgbe_check_vf_rate_limit(struct ixgbe_adapter *adapter) } } -int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate) { struct ixgbe_adapter *adapter = netdev_priv(netdev); int link_speed; @@ -1240,13 +1241,16 @@ int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) if (link_speed != 10000) return -EINVAL; + if (min_tx_rate) + return -EINVAL; + /* rate limit cannot be less than 10Mbs or greater than link speed */ - if (tx_rate && ((tx_rate <= 10) || (tx_rate > link_speed))) + if (max_tx_rate && ((max_tx_rate <= 10) || (max_tx_rate > link_speed))) return -EINVAL; /* store values */ adapter->vf_rate_link_speed = link_speed; - adapter->vfinfo[vf].tx_rate = tx_rate; + adapter->vfinfo[vf].tx_rate = max_tx_rate; /* update hardware configuration */ ixgbe_set_vf_rate_limit(adapter, vf); @@ -1288,7 +1292,8 @@ int ixgbe_ndo_get_vf_config(struct net_device *netdev, return -EINVAL; ivi->vf = vf; memcpy(&ivi->mac, adapter->vfinfo[vf].vf_mac_addresses, ETH_ALEN); - ivi->tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->max_tx_rate = adapter->vfinfo[vf].tx_rate; + ivi->min_tx_rate = 0; ivi->vlan = adapter->vfinfo[vf].pf_vlan; ivi->qos = adapter->vfinfo[vf].pf_qos; ivi->spoofchk = adapter->vfinfo[vf].spoofchk_enabled; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index cea64014760..32c26d586c0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -44,7 +44,8 @@ void ixgbe_ping_all_vfs(struct ixgbe_adapter *adapter); int ixgbe_ndo_set_vf_mac(struct net_device *netdev, int queue, u8 *mac); int ixgbe_ndo_set_vf_vlan(struct net_device *netdev, int queue, u16 vlan, u8 qos); -int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); +int ixgbe_ndo_set_vf_bw(struct net_device *netdev, int vf, int min_tx_rate, + int max_tx_rate); int ixgbe_ndo_set_vf_spoofchk(struct net_device *netdev, int vf, bool setting); int ixgbe_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi); diff --git a/drivers/net/ethernet/marvell/mv643xx_eth.c b/drivers/net/ethernet/marvell/mv643xx_eth.c index 3b0f818a4f5..c68ff5deba8 100644 --- a/drivers/net/ethernet/marvell/mv643xx_eth.c +++ b/drivers/net/ethernet/marvell/mv643xx_eth.c @@ -1167,8 +1167,9 @@ static void txq_set_fixed_prio_mode(struct tx_queue *txq) /* mii management interface *************************************************/ -static void mv643xx_adjust_pscr(struct mv643xx_eth_private *mp) +static void mv643xx_eth_adjust_link(struct net_device *dev) { + struct mv643xx_eth_private *mp = netdev_priv(dev); u32 pscr = rdlp(mp, PORT_SERIAL_CONTROL); u32 autoneg_disable = FORCE_LINK_PASS | DISABLE_AUTO_NEG_SPEED_GMII | @@ -1544,7 +1545,7 @@ mv643xx_eth_set_settings(struct net_device *dev, struct ethtool_cmd *cmd) ret = phy_ethtool_sset(mp->phy, cmd); if (!ret) - mv643xx_adjust_pscr(mp); + mv643xx_eth_adjust_link(dev); return ret; } @@ -2473,7 +2474,7 @@ static int mv643xx_eth_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) ret = phy_mii_ioctl(mp->phy, ifr, cmd); if (!ret) - mv643xx_adjust_pscr(mp); + mv643xx_eth_adjust_link(dev); return ret; } @@ -2871,13 +2872,6 @@ static void set_params(struct mv643xx_eth_private *mp, mp->txq_count = pd->tx_queue_count ? : 1; } -static void mv643xx_eth_adjust_link(struct net_device *dev) -{ - struct mv643xx_eth_private *mp = netdev_priv(dev); - - mv643xx_adjust_pscr(mp); -} - static struct phy_device *phy_scan(struct mv643xx_eth_private *mp, int phy_addr) { diff --git a/drivers/net/ethernet/marvell/mvmdio.c b/drivers/net/ethernet/marvell/mvmdio.c index 9d5ced263a5..fc2fb25343f 100644 --- a/drivers/net/ethernet/marvell/mvmdio.c +++ b/drivers/net/ethernet/marvell/mvmdio.c @@ -195,11 +195,10 @@ static int orion_mdio_probe(struct platform_device *pdev) return -ENODEV; } - bus = mdiobus_alloc_size(sizeof(struct orion_mdio_dev)); - if (!bus) { - dev_err(&pdev->dev, "Cannot allocate MDIO bus\n"); + bus = devm_mdiobus_alloc_size(&pdev->dev, + sizeof(struct orion_mdio_dev)); + if (!bus) return -ENOMEM; - } bus->name = "orion_mdio_bus"; bus->read = orion_mdio_read; @@ -208,11 +207,10 @@ static int orion_mdio_probe(struct platform_device *pdev) dev_name(&pdev->dev)); bus->parent = &pdev->dev; - bus->irq = kmalloc(sizeof(int) * PHY_MAX_ADDR, GFP_KERNEL); - if (!bus->irq) { - mdiobus_free(bus); + bus->irq = devm_kmalloc_array(&pdev->dev, PHY_MAX_ADDR, sizeof(int), + GFP_KERNEL); + if (!bus->irq) return -ENOMEM; - } for (i = 0; i < PHY_MAX_ADDR; i++) bus->irq[i] = PHY_POLL; @@ -264,8 +262,6 @@ static int orion_mdio_probe(struct platform_device *pdev) out_mdio: if (!IS_ERR(dev->clk)) clk_disable_unprepare(dev->clk); - kfree(bus->irq); - mdiobus_free(bus); return ret; } @@ -276,8 +272,6 @@ static int orion_mdio_remove(struct platform_device *pdev) writel(0, dev->regs + MVMDIO_ERR_INT_MASK); mdiobus_unregister(bus); - kfree(bus->irq); - mdiobus_free(bus); if (!IS_ERR(dev->clk)) clk_disable_unprepare(dev->clk); diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index 18c698d9ef9..b8919fa6ed2 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -283,9 +283,6 @@ struct mvneta_port { u32 cause_rx_tx; struct napi_struct napi; - /* Napi weight */ - int weight; - /* Core clock */ struct clk *clk; u8 mcast_count[256]; @@ -451,7 +448,10 @@ struct mvneta_rx_queue { int next_desc_to_proc; }; -static int rxq_number = 8; +/* The hardware supports eight (8) rx queues, but we are only allowing + * the first one to be used. Therefore, let's just allocate one queue. + */ +static int rxq_number = 1; static int txq_number = 8; static int rxq_def; @@ -1654,9 +1654,9 @@ static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb, struct mvneta_tx_queue *txq) { struct mvneta_tx_desc *tx_desc; - int i; + int i, nr_frags = skb_shinfo(skb)->nr_frags; - for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { + for (i = 0; i < nr_frags; i++) { skb_frag_t *frag = &skb_shinfo(skb)->frags[i]; void *addr = page_address(frag->page.p) + frag->page_offset; @@ -1673,20 +1673,16 @@ static int mvneta_tx_frag_process(struct mvneta_port *pp, struct sk_buff *skb, goto error; } - if (i == (skb_shinfo(skb)->nr_frags - 1)) { + if (i == nr_frags - 1) { /* Last descriptor */ tx_desc->command = MVNETA_TXD_L_DESC | MVNETA_TXD_Z_PAD; - txq->tx_skb[txq->txq_put_index] = skb; - - mvneta_txq_inc_put(txq); } else { /* Descriptor in the middle: Not First, Not Last */ tx_desc->command = 0; - txq->tx_skb[txq->txq_put_index] = NULL; - mvneta_txq_inc_put(txq); } + mvneta_txq_inc_put(txq); } return 0; @@ -2137,7 +2133,7 @@ static void mvneta_tx_reset(struct mvneta_port *pp) { int queue; - /* free the skb's in the hal tx ring */ + /* free the skb's in the tx ring */ for (queue = 0; queue < txq_number; queue++) mvneta_txq_done_force(pp, &pp->txqs[queue]); @@ -2429,24 +2425,28 @@ static int mvneta_change_mtu(struct net_device *dev, int mtu) return 0; /* The interface is running, so we have to force a - * reallocation of the RXQs + * reallocation of the queues */ mvneta_stop_dev(pp); mvneta_cleanup_txqs(pp); mvneta_cleanup_rxqs(pp); - pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); + pp->pkt_size = MVNETA_RX_PKT_SIZE(dev->mtu); pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); ret = mvneta_setup_rxqs(pp); if (ret) { - netdev_err(pp->dev, "unable to setup rxqs after MTU change\n"); + netdev_err(dev, "unable to setup rxqs after MTU change\n"); return ret; } - mvneta_setup_txqs(pp); + ret = mvneta_setup_txqs(pp); + if (ret) { + netdev_err(dev, "unable to setup txqs after MTU change\n"); + return ret; + } mvneta_start_dev(pp); mvneta_port_up(pp); @@ -2473,22 +2473,19 @@ static void mvneta_get_mac_addr(struct mvneta_port *pp, unsigned char *addr) static int mvneta_set_mac_addr(struct net_device *dev, void *addr) { struct mvneta_port *pp = netdev_priv(dev); - u8 *mac = addr + 2; - int i; - - if (netif_running(dev)) - return -EBUSY; + struct sockaddr *sockaddr = addr; + int ret; + ret = eth_prepare_mac_addr_change(dev, addr); + if (ret < 0) + return ret; /* Remove previous address table entry */ mvneta_mac_addr_set(pp, dev->dev_addr, -1); /* Set new addr in hw */ - mvneta_mac_addr_set(pp, mac, rxq_def); - - /* Set addr in the device */ - for (i = 0; i < ETH_ALEN; i++) - dev->dev_addr[i] = mac[i]; + mvneta_mac_addr_set(pp, sockaddr->sa_data, rxq_def); + eth_commit_mac_addr_change(dev, addr); return 0; } @@ -2583,8 +2580,6 @@ static int mvneta_open(struct net_device *dev) struct mvneta_port *pp = netdev_priv(dev); int ret; - mvneta_mac_addr_set(pp, dev->dev_addr, rxq_def); - pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); pp->frag_size = SKB_DATA_ALIGN(MVNETA_RX_BUF_SIZE(pp->pkt_size)) + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); @@ -2788,7 +2783,7 @@ const struct ethtool_ops mvneta_eth_tool_ops = { }; /* Initialize hw */ -static int mvneta_init(struct mvneta_port *pp, int phy_addr) +static int mvneta_init(struct device *dev, struct mvneta_port *pp) { int queue; @@ -2798,8 +2793,8 @@ static int mvneta_init(struct mvneta_port *pp, int phy_addr) /* Set port default values */ mvneta_defaults_set(pp); - pp->txqs = kzalloc(txq_number * sizeof(struct mvneta_tx_queue), - GFP_KERNEL); + pp->txqs = devm_kcalloc(dev, txq_number, sizeof(struct mvneta_tx_queue), + GFP_KERNEL); if (!pp->txqs) return -ENOMEM; @@ -2811,12 +2806,10 @@ static int mvneta_init(struct mvneta_port *pp, int phy_addr) txq->done_pkts_coal = MVNETA_TXDONE_COAL_PKTS; } - pp->rxqs = kzalloc(rxq_number * sizeof(struct mvneta_rx_queue), - GFP_KERNEL); - if (!pp->rxqs) { - kfree(pp->txqs); + pp->rxqs = devm_kcalloc(dev, rxq_number, sizeof(struct mvneta_rx_queue), + GFP_KERNEL); + if (!pp->rxqs) return -ENOMEM; - } /* Create Rx descriptor rings */ for (queue = 0; queue < rxq_number; queue++) { @@ -2830,12 +2823,6 @@ static int mvneta_init(struct mvneta_port *pp, int phy_addr) return 0; } -static void mvneta_deinit(struct mvneta_port *pp) -{ - kfree(pp->txqs); - kfree(pp->rxqs); -} - /* platform glue : initialize decoding windows */ static void mvneta_conf_mbus_windows(struct mvneta_port *pp, const struct mbus_dram_target_info *dram) @@ -2918,7 +2905,6 @@ static int mvneta_probe(struct platform_device *pdev) struct resource *res; struct device_node *dn = pdev->dev.of_node; struct device_node *phy_node; - u32 phy_addr; struct mvneta_port *pp; struct net_device *dev; const char *dt_mac_addr; @@ -2979,8 +2965,6 @@ static int mvneta_probe(struct platform_device *pdev) dev->ethtool_ops = &mvneta_eth_tool_ops; pp = netdev_priv(dev); - - pp->weight = MVNETA_RX_POLL_WEIGHT; pp->phy_node = phy_node; pp->phy_interface = phy_mode; @@ -3027,23 +3011,21 @@ static int mvneta_probe(struct platform_device *pdev) pp->dev = dev; SET_NETDEV_DEV(dev, &pdev->dev); - err = mvneta_init(pp, phy_addr); - if (err < 0) { - dev_err(&pdev->dev, "can't init eth hal\n"); + err = mvneta_init(&pdev->dev, pp); + if (err < 0) goto err_free_stats; - } err = mvneta_port_power_up(pp, phy_mode); if (err < 0) { dev_err(&pdev->dev, "can't power up port\n"); - goto err_deinit; + goto err_free_stats; } dram_target_info = mv_mbus_dram_info(); if (dram_target_info) mvneta_conf_mbus_windows(pp, dram_target_info); - netif_napi_add(dev, &pp->napi, mvneta_poll, pp->weight); + netif_napi_add(dev, &pp->napi, mvneta_poll, MVNETA_RX_POLL_WEIGHT); dev->features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_TSO; dev->hw_features |= dev->features; @@ -3053,7 +3035,7 @@ static int mvneta_probe(struct platform_device *pdev) err = register_netdev(dev); if (err < 0) { dev_err(&pdev->dev, "failed to register\n"); - goto err_deinit; + goto err_free_stats; } netdev_info(dev, "Using %s mac address %pM\n", mac_from, @@ -3063,8 +3045,6 @@ static int mvneta_probe(struct platform_device *pdev) return 0; -err_deinit: - mvneta_deinit(pp); err_free_stats: free_percpu(pp->stats); err_clk: @@ -3083,7 +3063,6 @@ static int mvneta_remove(struct platform_device *pdev) struct mvneta_port *pp = netdev_priv(dev); unregister_netdev(dev); - mvneta_deinit(pp); clk_disable_unprepare(pp->clk); free_percpu(pp->stats); irq_dispose_mapping(dev->irq); diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c index 59c7fd40680..ca8e7cb5a8e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c @@ -2486,11 +2486,12 @@ int mlx4_get_vf_config(struct mlx4_dev *dev, int port, int vf, struct ifla_vf_in ivf->mac[4] = ((s_info->mac >> (1*8)) & 0xff); ivf->mac[5] = ((s_info->mac) & 0xff); - ivf->vlan = s_info->default_vlan; - ivf->qos = s_info->default_qos; - ivf->tx_rate = s_info->tx_rate; - ivf->spoofchk = s_info->spoofchk; - ivf->linkstate = s_info->link_state; + ivf->vlan = s_info->default_vlan; + ivf->qos = s_info->default_qos; + ivf->max_tx_rate = s_info->tx_rate; + ivf->min_tx_rate = 0; + ivf->spoofchk = s_info->spoofchk; + ivf->linkstate = s_info->link_state; return 0; } diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h index 6e7527e2b59..41abe607046 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic.h @@ -1319,6 +1319,7 @@ struct qlcnic_eswitch { #define QL_STATUS_INVALID_PARAM -1 #define MAX_BW 100 /* % of link speed */ +#define MIN_BW 1 /* % of link speed */ #define MAX_VLAN_ID 4095 #define MIN_VLAN_ID 2 #define DEFAULT_MAC_LEARN 1 diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c index f0a285359e6..f06ba90b428 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_main.c @@ -525,7 +525,7 @@ static const struct net_device_ops qlcnic_netdev_ops = { #endif #ifdef CONFIG_QLCNIC_SRIOV .ndo_set_vf_mac = qlcnic_sriov_set_vf_mac, - .ndo_set_vf_tx_rate = qlcnic_sriov_set_vf_tx_rate, + .ndo_set_vf_rate = qlcnic_sriov_set_vf_tx_rate, .ndo_get_vf_config = qlcnic_sriov_get_vf_config, .ndo_set_vf_vlan = qlcnic_sriov_set_vf_vlan, .ndo_set_vf_spoofchk = qlcnic_sriov_set_vf_spoofchk, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h index 335b50f7bd3..4677b2edccc 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov.h @@ -233,7 +233,7 @@ bool qlcnic_sriov_soft_flr_check(struct qlcnic_adapter *, void qlcnic_sriov_pf_reset(struct qlcnic_adapter *); int qlcnic_sriov_pf_reinit(struct qlcnic_adapter *); int qlcnic_sriov_set_vf_mac(struct net_device *, int, u8 *); -int qlcnic_sriov_set_vf_tx_rate(struct net_device *, int, int); +int qlcnic_sriov_set_vf_tx_rate(struct net_device *, int, int, int); int qlcnic_sriov_get_vf_config(struct net_device *, int , struct ifla_vf_info *); int qlcnic_sriov_set_vf_vlan(struct net_device *, int, u16, u8); diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c index 498fa6350c8..2bdd9deffb3 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_common.c @@ -201,6 +201,7 @@ int qlcnic_sriov_init(struct qlcnic_adapter *adapter, int num_vfs) sriov->vf_info[i].vp = vp; vp->vlan_mode = QLC_GUEST_VLAN_MODE; vp->max_tx_bw = MAX_BW; + vp->min_tx_bw = MIN_BW; vp->spoofchk = false; random_ether_addr(vp->mac); dev_info(&adapter->pdev->dev, diff --git a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c index 6d2f72f114f..a29538b86ed 100644 --- a/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c +++ b/drivers/net/ethernet/qlogic/qlcnic/qlcnic_sriov_pf.c @@ -1848,7 +1848,8 @@ int qlcnic_sriov_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) return 0; } -int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, int tx_rate) +int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, + int min_tx_rate, int max_tx_rate) { struct qlcnic_adapter *adapter = netdev_priv(netdev); struct qlcnic_sriov *sriov = adapter->ahw->sriov; @@ -1863,35 +1864,52 @@ int qlcnic_sriov_set_vf_tx_rate(struct net_device *netdev, int vf, int tx_rate) if (vf >= sriov->num_vfs) return -EINVAL; - if (tx_rate >= 10000 || tx_rate < 100) { + vf_info = &sriov->vf_info[vf]; + vp = vf_info->vp; + vpid = vp->handle; + + if (!min_tx_rate) + min_tx_rate = QLC_VF_MIN_TX_RATE; + + if (max_tx_rate && + (max_tx_rate >= 10000 || max_tx_rate < min_tx_rate)) { netdev_err(netdev, - "Invalid Tx rate, allowed range is [%d - %d]", - QLC_VF_MIN_TX_RATE, QLC_VF_MAX_TX_RATE); + "Invalid max Tx rate, allowed range is [%d - %d]", + min_tx_rate, QLC_VF_MAX_TX_RATE); return -EINVAL; } - if (tx_rate == 0) - tx_rate = 10000; + if (!max_tx_rate) + max_tx_rate = 10000; - vf_info = &sriov->vf_info[vf]; - vp = vf_info->vp; - vpid = vp->handle; + if (min_tx_rate && + (min_tx_rate > max_tx_rate || min_tx_rate < QLC_VF_MIN_TX_RATE)) { + netdev_err(netdev, + "Invalid min Tx rate, allowed range is [%d - %d]", + QLC_VF_MIN_TX_RATE, max_tx_rate); + return -EINVAL; + } if (test_bit(QLC_BC_VF_STATE, &vf_info->state)) { if (qlcnic_sriov_get_vf_vport_info(adapter, &nic_info, vpid)) return -EIO; - nic_info.max_tx_bw = tx_rate / 100; + nic_info.max_tx_bw = max_tx_rate / 100; + nic_info.min_tx_bw = min_tx_rate / 100; nic_info.bit_offsets = BIT_0; if (qlcnic_sriov_pf_set_vport_info(adapter, &nic_info, vpid)) return -EIO; } - vp->max_tx_bw = tx_rate / 100; + vp->max_tx_bw = max_tx_rate / 100; + netdev_info(netdev, + "Setting Max Tx rate %d (Mbps), %d %% of PF bandwidth, for VF %d\n", + max_tx_rate, vp->max_tx_bw, vf); + vp->min_tx_bw = min_tx_rate / 100; netdev_info(netdev, - "Setting Tx rate %d (Mbps), %d %% of PF bandwidth, for VF %d\n", - tx_rate, vp->max_tx_bw, vf); + "Setting Min Tx rate %d (Mbps), %d %% of PF bandwidth, for VF %d\n", + min_tx_rate, vp->min_tx_bw, vf); return 0; } @@ -1990,9 +2008,13 @@ int qlcnic_sriov_get_vf_config(struct net_device *netdev, ivi->qos = vp->qos; ivi->spoofchk = vp->spoofchk; if (vp->max_tx_bw == MAX_BW) - ivi->tx_rate = 0; + ivi->max_tx_rate = 0; + else + ivi->max_tx_rate = vp->max_tx_bw * 100; + if (vp->min_tx_bw == MIN_BW) + ivi->min_tx_rate = 0; else - ivi->tx_rate = vp->max_tx_bw * 100; + ivi->min_tx_rate = vp->min_tx_bw * 100; ivi->vf = vf; return 0; diff --git a/drivers/net/ethernet/sfc/siena_sriov.c b/drivers/net/ethernet/sfc/siena_sriov.c index 9a9205e7789..43d2e64546e 100644 --- a/drivers/net/ethernet/sfc/siena_sriov.c +++ b/drivers/net/ethernet/sfc/siena_sriov.c @@ -1633,7 +1633,8 @@ int efx_sriov_get_vf_config(struct net_device *net_dev, int vf_i, ivi->vf = vf_i; ether_addr_copy(ivi->mac, vf->addr.mac_addr); - ivi->tx_rate = 0; + ivi->max_tx_rate = 0; + ivi->min_tx_rate = 0; tci = ntohs(vf->addr.tci); ivi->vlan = tci & VLAN_VID_MASK; ivi->qos = (tci >> VLAN_PRIO_SHIFT) & 0x7; diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 4b7df5a5c96..6cc37c15e0b 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -791,6 +791,7 @@ enum ndis_per_pkt_info_type { IEEE_8021Q_INFO, ORIGINAL_PKTINFO, PACKET_CANCEL_ID, + NBL_HASH_VALUE = PACKET_CANCEL_ID, ORIGINAL_NET_BUFLIST, CACHED_NET_BUFLIST, SHORT_PKT_PADINFO, @@ -937,6 +938,9 @@ struct ndis_tcp_lso_info { #define NDIS_LSO_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \ sizeof(struct ndis_tcp_lso_info)) +#define NDIS_HASH_PPI_SIZE (sizeof(struct rndis_per_packet_info) + \ + sizeof(u32)) + /* Format of Information buffer passed in a SetRequest for the OID */ /* OID_GEN_RNDIS_CONFIG_PARAMETER. */ struct rndis_config_parameter_info { diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 2e967a7bdb3..4fd71b75e66 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -224,9 +224,11 @@ static u16 netvsc_select_queue(struct net_device *ndev, struct sk_buff *skb, if (nvsc_dev == NULL || ndev->real_num_tx_queues <= 1) return 0; - if (netvsc_set_hash(&hash, skb)) + if (netvsc_set_hash(&hash, skb)) { q_idx = nvsc_dev->send_table[hash % VRSS_SEND_TAB_SIZE] % ndev->real_num_tx_queues; + skb_set_hash(skb, hash, PKT_HASH_TYPE_L3); + } return q_idx; } @@ -384,6 +386,7 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) struct ndis_tcp_lso_info *lso_info; int hdr_offset; u32 net_trans_info; + u32 hash; /* We will atmost need two pages to describe the rndis @@ -402,9 +405,8 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) packet = kzalloc(sizeof(struct hv_netvsc_packet) + (num_data_pgs * sizeof(struct hv_page_buffer)) + sizeof(struct rndis_message) + - NDIS_VLAN_PPI_SIZE + - NDIS_CSUM_PPI_SIZE + - NDIS_LSO_PPI_SIZE, GFP_ATOMIC); + NDIS_VLAN_PPI_SIZE + NDIS_CSUM_PPI_SIZE + + NDIS_LSO_PPI_SIZE + NDIS_HASH_PPI_SIZE, GFP_ATOMIC); if (!packet) { /* out of memory, drop packet */ netdev_err(net, "unable to allocate hv_netvsc_packet\n"); @@ -443,6 +445,14 @@ static int netvsc_start_xmit(struct sk_buff *skb, struct net_device *net) rndis_msg_size = RNDIS_MESSAGE_SIZE(struct rndis_packet); + hash = skb_get_hash_raw(skb); + if (hash != 0 && net->real_num_tx_queues > 1) { + rndis_msg_size += NDIS_HASH_PPI_SIZE; + ppi = init_ppi_data(rndis_msg, NDIS_HASH_PPI_SIZE, + NBL_HASH_VALUE); + *(u32 *)((void *)ppi + ppi->ppi_offset) = hash; + } + if (isvlan) { struct ndis_pkt_8021q_info *vlan; diff --git a/include/linux/if_link.h b/include/linux/if_link.h index a86784dec3d..119130e9298 100644 --- a/include/linux/if_link.h +++ b/include/linux/if_link.h @@ -10,8 +10,9 @@ struct ifla_vf_info { __u8 mac[32]; __u32 vlan; __u32 qos; - __u32 tx_rate; __u32 spoofchk; __u32 linkstate; + __u32 min_tx_rate; + __u32 max_tx_rate; }; #endif /* _LINUX_IF_LINK_H */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index f4ad247fd32..9ec3a945caf 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -850,7 +850,8 @@ typedef u16 (*select_queue_fallback_t)(struct net_device *dev, * SR-IOV management functions. * int (*ndo_set_vf_mac)(struct net_device *dev, int vf, u8* mac); * int (*ndo_set_vf_vlan)(struct net_device *dev, int vf, u16 vlan, u8 qos); - * int (*ndo_set_vf_tx_rate)(struct net_device *dev, int vf, int rate); + * int (*ndo_set_vf_rate)(struct net_device *dev, int vf, int min_tx_rate, + * int max_tx_rate); * int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); * int (*ndo_get_vf_config)(struct net_device *dev, * int vf, struct ifla_vf_info *ivf); @@ -1044,8 +1045,9 @@ struct net_device_ops { int queue, u8 *mac); int (*ndo_set_vf_vlan)(struct net_device *dev, int queue, u16 vlan, u8 qos); - int (*ndo_set_vf_tx_rate)(struct net_device *dev, - int vf, int rate); + int (*ndo_set_vf_rate)(struct net_device *dev, + int vf, int min_tx_rate, + int max_tx_rate); int (*ndo_set_vf_spoofchk)(struct net_device *dev, int vf, bool setting); int (*ndo_get_vf_config)(struct net_device *dev, diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 9a7f7ace664..622e7910b8c 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -399,9 +399,10 @@ enum { IFLA_VF_UNSPEC, IFLA_VF_MAC, /* Hardware queue specific attributes */ IFLA_VF_VLAN, - IFLA_VF_TX_RATE, /* TX Bandwidth Allocation */ + IFLA_VF_TX_RATE, /* Max TX Bandwidth Allocation */ IFLA_VF_SPOOFCHK, /* Spoof Checking on/off switch */ IFLA_VF_LINK_STATE, /* link state enable/disable/auto switch */ + IFLA_VF_RATE, /* Min and Max TX Bandwidth Allocation */ __IFLA_VF_MAX, }; @@ -423,6 +424,12 @@ struct ifla_vf_tx_rate { __u32 rate; /* Max TX bandwidth in Mbps, 0 disables throttling */ }; +struct ifla_vf_rate { + __u32 vf; + __u32 min_tx_rate; /* Min Bandwidth in Mbps */ + __u32 max_tx_rate; /* Max Bandwidth in Mbps */ +}; + struct ifla_vf_spoofchk { __u32 vf; __u32 setting; diff --git a/include/uapi/linux/openvswitch.h b/include/uapi/linux/openvswitch.h index 970553cbbc8..0b979ee4bfc 100644 --- a/include/uapi/linux/openvswitch.h +++ b/include/uapi/linux/openvswitch.h @@ -395,7 +395,9 @@ struct ovs_key_nd { * @OVS_FLOW_ATTR_ACTIONS: Nested %OVS_ACTION_ATTR_* attributes specifying * the actions to take for packets that match the key. Always present in * notifications. Required for %OVS_FLOW_CMD_NEW requests, optional for - * %OVS_FLOW_CMD_SET requests. + * %OVS_FLOW_CMD_SET requests. An %OVS_FLOW_CMD_SET without + * %OVS_FLOW_ATTR_ACTIONS will not modify the actions. To clear the actions, + * an %OVS_FLOW_ATTR_ACTIONS without any nested attributes must be given. * @OVS_FLOW_ATTR_STATS: &struct ovs_flow_stats giving statistics for this * flow. Present in notifications if the stats would be nonzero. Ignored in * requests. diff --git a/lib/test_bpf.c b/lib/test_bpf.c index e160934430e..3d80adbdb55 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -54,7 +54,7 @@ struct bpf_test { union { struct sock_filter insns[MAX_INSNS]; struct sock_filter_int insns_int[MAX_INSNS]; - }; + } u; enum { NO_DATA, EXPECTED_FAIL, @@ -71,7 +71,7 @@ struct bpf_test { static struct bpf_test tests[] = { { "TAX", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 1), BPF_STMT(BPF_MISC | BPF_TAX, 0), BPF_STMT(BPF_LD | BPF_IMM, 2), @@ -90,7 +90,7 @@ static struct bpf_test tests[] = { }, { "TXA", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_MISC | BPF_TXA, 0), BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0), @@ -102,7 +102,7 @@ static struct bpf_test tests[] = { }, { "ADD_SUB_MUL_K", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 1), BPF_STMT(BPF_ALU | BPF_ADD | BPF_K, 2), BPF_STMT(BPF_LDX | BPF_IMM, 3), @@ -117,7 +117,7 @@ static struct bpf_test tests[] = { }, { "DIV_KX", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 8), BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 2), BPF_STMT(BPF_MISC | BPF_TAX, 0), @@ -135,7 +135,7 @@ static struct bpf_test tests[] = { }, { "AND_OR_LSH_K", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 0xff), BPF_STMT(BPF_ALU | BPF_AND | BPF_K, 0xf0), BPF_STMT(BPF_ALU | BPF_LSH | BPF_K, 27), @@ -151,7 +151,7 @@ static struct bpf_test tests[] = { }, { "LD_IND", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_LD | BPF_H | BPF_IND, MAX_K), BPF_STMT(BPF_RET | BPF_K, 1) @@ -162,7 +162,7 @@ static struct bpf_test tests[] = { }, { "LD_ABS", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, 1000), BPF_STMT(BPF_RET | BPF_K, 1) }, @@ -172,7 +172,7 @@ static struct bpf_test tests[] = { }, { "LD_ABS_LL", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_LL_OFF), BPF_STMT(BPF_MISC | BPF_TAX, 0), BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_LL_OFF + 1), @@ -185,7 +185,7 @@ static struct bpf_test tests[] = { }, { "LD_IND_LL", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, SKF_LL_OFF - 1), BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0), @@ -199,7 +199,7 @@ static struct bpf_test tests[] = { }, { "LD_ABS_NET", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_NET_OFF), BPF_STMT(BPF_MISC | BPF_TAX, 0), BPF_STMT(BPF_LD | BPF_B | BPF_ABS, SKF_NET_OFF + 1), @@ -212,7 +212,7 @@ static struct bpf_test tests[] = { }, { "LD_IND_NET", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, SKF_NET_OFF - 15), BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_ALU | BPF_ADD | BPF_X, 0), @@ -226,7 +226,7 @@ static struct bpf_test tests[] = { }, { "LD_PKTTYPE", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_PKTTYPE), BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, SKB_TYPE, 1, 0), @@ -247,7 +247,7 @@ static struct bpf_test tests[] = { }, { "LD_MARK", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_MARK), BPF_STMT(BPF_RET | BPF_A, 0) @@ -258,7 +258,7 @@ static struct bpf_test tests[] = { }, { "LD_RXHASH", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_RXHASH), BPF_STMT(BPF_RET | BPF_A, 0) @@ -269,7 +269,7 @@ static struct bpf_test tests[] = { }, { "LD_QUEUE", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_QUEUE), BPF_STMT(BPF_RET | BPF_A, 0) @@ -280,7 +280,7 @@ static struct bpf_test tests[] = { }, { "LD_PROTOCOL", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 1), BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_K, 20, 1, 0), BPF_STMT(BPF_RET | BPF_K, 0), @@ -299,7 +299,7 @@ static struct bpf_test tests[] = { }, { "LD_VLAN_TAG", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_VLAN_TAG), BPF_STMT(BPF_RET | BPF_A, 0) @@ -313,7 +313,7 @@ static struct bpf_test tests[] = { }, { "LD_VLAN_TAG_PRESENT", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_VLAN_TAG_PRESENT), BPF_STMT(BPF_RET | BPF_A, 0) @@ -327,7 +327,7 @@ static struct bpf_test tests[] = { }, { "LD_IFINDEX", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_IFINDEX), BPF_STMT(BPF_RET | BPF_A, 0) @@ -338,7 +338,7 @@ static struct bpf_test tests[] = { }, { "LD_HATYPE", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_HATYPE), BPF_STMT(BPF_RET | BPF_A, 0) @@ -349,7 +349,7 @@ static struct bpf_test tests[] = { }, { "LD_CPU", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_CPU), BPF_STMT(BPF_MISC | BPF_TAX, 0), @@ -364,7 +364,7 @@ static struct bpf_test tests[] = { }, { "LD_NLATTR", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_IMM, 1), BPF_STMT(BPF_MISC | BPF_TXA, 0), BPF_STMT(BPF_LDX | BPF_IMM, 3), @@ -378,7 +378,7 @@ static struct bpf_test tests[] = { }, { "LD_NLATTR_NEST", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 1), BPF_STMT(BPF_LDX | BPF_IMM, 3), BPF_STMT(BPF_LD | BPF_W | BPF_ABS, @@ -412,7 +412,7 @@ static struct bpf_test tests[] = { }, { "LD_PAYLOAD_OFF", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_W | BPF_ABS, SKF_AD_OFF + SKF_AD_PAY_OFFSET), BPF_STMT(BPF_LD | BPF_W | BPF_ABS, @@ -439,7 +439,7 @@ static struct bpf_test tests[] = { }, { "LD_ANC_XOR", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 10), BPF_STMT(BPF_LDX | BPF_IMM, 300), BPF_STMT(BPF_LD | BPF_W | BPF_ABS, @@ -452,7 +452,7 @@ static struct bpf_test tests[] = { }, { "SPILL_FILL", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_LD | BPF_IMM, 2), BPF_STMT(BPF_ALU | BPF_RSH, 1), @@ -474,7 +474,7 @@ static struct bpf_test tests[] = { }, { "JEQ", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2), BPF_JUMP(BPF_JMP | BPF_JEQ | BPF_X, 0, 0, 1), @@ -487,7 +487,7 @@ static struct bpf_test tests[] = { }, { "JGT", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_LD | BPF_B | BPF_ABS, 2), BPF_JUMP(BPF_JMP | BPF_JGT | BPF_X, 0, 0, 1), @@ -500,7 +500,7 @@ static struct bpf_test tests[] = { }, { "JGE", - .insns = { + .u.insns = { BPF_STMT(BPF_LDX | BPF_LEN, 0), BPF_STMT(BPF_LD | BPF_B | BPF_IND, MAX_K), BPF_JUMP(BPF_JMP | BPF_JGE | BPF_K, 1, 1, 0), @@ -519,7 +519,7 @@ static struct bpf_test tests[] = { }, { "JSET", - .insns = { + .u.insns = { BPF_JUMP(BPF_JMP | BPF_JA, 0, 0, 0), BPF_JUMP(BPF_JMP | BPF_JA, 1, 1, 1), BPF_JUMP(BPF_JMP | BPF_JA, 0, 0, 0), @@ -551,7 +551,7 @@ static struct bpf_test tests[] = { }, { "tcpdump port 22", - .insns = { + .u.insns = { { 0x28, 0, 0, 0x0000000c }, { 0x15, 0, 8, 0x000086dd }, { 0x30, 0, 0, 0x00000014 }, @@ -596,7 +596,7 @@ static struct bpf_test tests[] = { }, { "tcpdump complex", - .insns = { + .u.insns = { /* tcpdump -nei eth0 'tcp port 22 and (((ip[2:2] - * ((ip[0]&0xf)<<2)) - ((tcp[12]&0xf0)>>2)) != 0) and * (len > 115 or len < 30000000000)' -d @@ -649,7 +649,7 @@ static struct bpf_test tests[] = { }, { "RET_A", - .insns = { + .u.insns = { /* check that unitialized X and A contain zeros */ BPF_STMT(BPF_MISC | BPF_TXA, 0), BPF_STMT(BPF_RET | BPF_A, 0) @@ -660,7 +660,7 @@ static struct bpf_test tests[] = { }, { "INT: ADD trivial", - .insns_int = { + .u.insns_int = { BPF_ALU64_IMM(BPF_MOV, R1, 1), BPF_ALU64_IMM(BPF_ADD, R1, 2), BPF_ALU64_IMM(BPF_MOV, R2, 3), @@ -676,7 +676,7 @@ static struct bpf_test tests[] = { }, { "INT: MUL_X", - .insns_int = { + .u.insns_int = { BPF_ALU64_IMM(BPF_MOV, R0, -1), BPF_ALU64_IMM(BPF_MOV, R1, -1), BPF_ALU64_IMM(BPF_MOV, R2, 3), @@ -692,7 +692,7 @@ static struct bpf_test tests[] = { }, { "INT: MUL_X2", - .insns_int = { + .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, -1), BPF_ALU32_IMM(BPF_MOV, R1, -1), BPF_ALU32_IMM(BPF_MOV, R2, 3), @@ -709,7 +709,7 @@ static struct bpf_test tests[] = { }, { "INT: MUL32_X", - .insns_int = { + .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, -1), BPF_ALU64_IMM(BPF_MOV, R1, -1), BPF_ALU32_IMM(BPF_MOV, R2, 3), @@ -730,7 +730,7 @@ static struct bpf_test tests[] = { * different asm code. */ "INT: ADD 64-bit", - .insns_int = { + .u.insns_int = { BPF_ALU64_IMM(BPF_MOV, R0, 0), BPF_ALU64_IMM(BPF_MOV, R1, 1), BPF_ALU64_IMM(BPF_MOV, R2, 2), @@ -888,7 +888,7 @@ static struct bpf_test tests[] = { }, { "INT: ADD 32-bit", - .insns_int = { + .u.insns_int = { BPF_ALU32_IMM(BPF_MOV, R0, 20), BPF_ALU32_IMM(BPF_MOV, R1, 1), BPF_ALU32_IMM(BPF_MOV, R2, 2), @@ -1034,7 +1034,7 @@ static struct bpf_test tests[] = { }, { /* Mainly checking JIT here. */ "INT: SUB", - .insns_int = { + .u.insns_int = { BPF_ALU64_IMM(BPF_MOV, R0, 0), BPF_ALU64_IMM(BPF_MOV, R1, 1), BPF_ALU64_IMM(BPF_MOV, R2, 2), @@ -1167,7 +1167,7 @@ static struct bpf_test tests[] = { }, { /* Mainly checking JIT here. */ "INT: XOR", - .insns_int = { + .u.insns_int = { BPF_ALU64_REG(BPF_SUB, R0, R0), BPF_ALU64_REG(BPF_XOR, R1, R1), BPF_JMP_REG(BPF_JEQ, R0, R1, 1), @@ -1233,7 +1233,7 @@ static struct bpf_test tests[] = { }, { /* Mainly checking JIT here. */ "INT: MUL", - .insns_int = { + .u.insns_int = { BPF_ALU64_IMM(BPF_MOV, R0, 11), BPF_ALU64_IMM(BPF_MOV, R1, 1), BPF_ALU64_IMM(BPF_MOV, R2, 2), @@ -1295,7 +1295,7 @@ static struct bpf_test tests[] = { }, { "INT: ALU MIX", - .insns_int = { + .u.insns_int = { BPF_ALU64_IMM(BPF_MOV, R0, 11), BPF_ALU64_IMM(BPF_ADD, R0, -1), BPF_ALU64_IMM(BPF_MOV, R2, 2), @@ -1315,7 +1315,7 @@ static struct bpf_test tests[] = { }, { "INT: DIV + ABS", - .insns_int = { + .u.insns_int = { BPF_ALU64_REG(BPF_MOV, R6, R1), BPF_LD_ABS(BPF_B, 3), BPF_ALU64_IMM(BPF_MOV, R2, 2), @@ -1332,7 +1332,7 @@ static struct bpf_test tests[] = { }, { "INT: DIV by zero", - .insns_int = { + .u.insns_int = { BPF_ALU64_REG(BPF_MOV, R6, R1), BPF_ALU64_IMM(BPF_MOV, R7, 0), BPF_LD_ABS(BPF_B, 3), @@ -1345,7 +1345,7 @@ static struct bpf_test tests[] = { }, { "check: missing ret", - .insns = { + .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 1), }, EXPECTED_FAIL, @@ -1354,7 +1354,7 @@ static struct bpf_test tests[] = { }, { "check: div_k_0", - .insns = { + .u.insns = { BPF_STMT(BPF_ALU | BPF_DIV | BPF_K, 0), BPF_STMT(BPF_RET | BPF_K, 0) }, @@ -1364,7 +1364,7 @@ static struct bpf_test tests[] = { }, { "check: unknown insn", - .insns = { + .u.insns = { /* seccomp insn, rejected in socket filter */ BPF_STMT(BPF_LDX | BPF_W | BPF_ABS, 0), BPF_STMT(BPF_RET | BPF_K, 0) @@ -1375,7 +1375,7 @@ static struct bpf_test tests[] = { }, { "check: out of range spill/fill", - .insns = { + .u.insns = { BPF_STMT(BPF_STX, 16), BPF_STMT(BPF_RET | BPF_K, 0) }, @@ -1478,7 +1478,7 @@ static __init int test_bpf(void) for (i = 0; i < ARRAY_SIZE(tests); i++) { pr_info("#%d %s ", i, tests[i].descr); - fprog.filter = tests[i].insns; + fprog.filter = tests[i].u.insns; fprog.len = get_length(fprog.filter); if (tests[i].data_type == SKB_INT) { @@ -1486,7 +1486,7 @@ static __init int test_bpf(void) if (!fp_ext) return -ENOMEM; fp = fp_ext; - memcpy(fp_ext->insns, tests[i].insns_int, + memcpy(fp_ext->insns, tests[i].u.insns_int, fprog.len * 8); fp->len = fprog.len; sk_filter_select_runtime(fp); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 9837bebf93c..d6417464dc6 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -767,8 +767,8 @@ static inline int rtnl_vfinfo_size(const struct net_device *dev, size += num_vfs * (nla_total_size(sizeof(struct ifla_vf_mac)) + nla_total_size(sizeof(struct ifla_vf_vlan)) + - nla_total_size(sizeof(struct ifla_vf_tx_rate)) + - nla_total_size(sizeof(struct ifla_vf_spoofchk))); + nla_total_size(sizeof(struct ifla_vf_spoofchk)) + + nla_total_size(sizeof(struct ifla_vf_rate))); return size; } else return 0; @@ -1034,6 +1034,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, struct ifla_vf_info ivi; struct ifla_vf_mac vf_mac; struct ifla_vf_vlan vf_vlan; + struct ifla_vf_rate vf_rate; struct ifla_vf_tx_rate vf_tx_rate; struct ifla_vf_spoofchk vf_spoofchk; struct ifla_vf_link_state vf_linkstate; @@ -1054,6 +1055,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, break; vf_mac.vf = vf_vlan.vf = + vf_rate.vf = vf_tx_rate.vf = vf_spoofchk.vf = vf_linkstate.vf = ivi.vf; @@ -1061,7 +1063,9 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, memcpy(vf_mac.mac, ivi.mac, sizeof(ivi.mac)); vf_vlan.vlan = ivi.vlan; vf_vlan.qos = ivi.qos; - vf_tx_rate.rate = ivi.tx_rate; + vf_tx_rate.rate = ivi.max_tx_rate; + vf_rate.min_tx_rate = ivi.min_tx_rate; + vf_rate.max_tx_rate = ivi.max_tx_rate; vf_spoofchk.setting = ivi.spoofchk; vf_linkstate.link_state = ivi.linkstate; vf = nla_nest_start(skb, IFLA_VF_INFO); @@ -1071,6 +1075,8 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, struct net_device *dev, } if (nla_put(skb, IFLA_VF_MAC, sizeof(vf_mac), &vf_mac) || nla_put(skb, IFLA_VF_VLAN, sizeof(vf_vlan), &vf_vlan) || + nla_put(skb, IFLA_VF_RATE, sizeof(vf_rate), + &vf_rate) || nla_put(skb, IFLA_VF_TX_RATE, sizeof(vf_tx_rate), &vf_tx_rate) || nla_put(skb, IFLA_VF_SPOOFCHK, sizeof(vf_spoofchk), @@ -1177,6 +1183,8 @@ static const struct nla_policy ifla_vf_policy[IFLA_VF_MAX+1] = { .len = sizeof(struct ifla_vf_tx_rate) }, [IFLA_VF_SPOOFCHK] = { .type = NLA_BINARY, .len = sizeof(struct ifla_vf_spoofchk) }, + [IFLA_VF_RATE] = { .type = NLA_BINARY, + .len = sizeof(struct ifla_vf_rate) }, }; static const struct nla_policy ifla_port_policy[IFLA_PORT_MAX+1] = { @@ -1336,11 +1344,29 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr *attr) } case IFLA_VF_TX_RATE: { struct ifla_vf_tx_rate *ivt; + struct ifla_vf_info ivf; ivt = nla_data(vf); err = -EOPNOTSUPP; - if (ops->ndo_set_vf_tx_rate) - err = ops->ndo_set_vf_tx_rate(dev, ivt->vf, - ivt->rate); + if (ops->ndo_get_vf_config) + err = ops->ndo_get_vf_config(dev, ivt->vf, + &ivf); + if (err) + break; + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivf.min_tx_rate, + ivt->rate); + break; + } + case IFLA_VF_RATE: { + struct ifla_vf_rate *ivt; + ivt = nla_data(vf); + err = -EOPNOTSUPP; + if (ops->ndo_set_vf_rate) + err = ops->ndo_set_vf_rate(dev, ivt->vf, + ivt->min_tx_rate, + ivt->max_tx_rate); break; } case IFLA_VF_SPOOFCHK: { diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index 8867d7e2d65..0d407bca81e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -44,11 +44,11 @@ #include <linux/netfilter_ipv4.h> #include <linux/inetdevice.h> #include <linux/list.h> -#include <linux/lockdep.h> #include <linux/openvswitch.h> #include <linux/rculist.h> #include <linux/dmi.h> -#include <linux/workqueue.h> +#include <linux/genetlink.h> +#include <net/genetlink.h> #include <net/genetlink.h> #include <net/net_namespace.h> #include <net/netns/generic.h> @@ -62,6 +62,31 @@ int ovs_net_id __read_mostly; +static struct genl_family dp_packet_genl_family; +static struct genl_family dp_flow_genl_family; +static struct genl_family dp_datapath_genl_family; + +static struct genl_multicast_group ovs_dp_flow_multicast_group = { + .name = OVS_FLOW_MCGROUP +}; + +static struct genl_multicast_group ovs_dp_datapath_multicast_group = { + .name = OVS_DATAPATH_MCGROUP +}; + +struct genl_multicast_group ovs_dp_vport_multicast_group = { + .name = OVS_VPORT_MCGROUP +}; + +/* Check if need to build a reply message. + * OVS userspace sets the NLM_F_ECHO flag if it needs the reply. */ +static bool ovs_must_notify(struct genl_info *info, + const struct genl_multicast_group *grp) +{ + return info->nlhdr->nlmsg_flags & NLM_F_ECHO || + netlink_has_listeners(genl_info_net(info)->genl_sock, 0); +} + static void ovs_notify(struct genl_family *family, struct sk_buff *skb, struct genl_info *info) { @@ -173,6 +198,7 @@ static struct hlist_head *vport_hash_bucket(const struct datapath *dp, return &dp->ports[port_no & (DP_VPORT_HASH_BUCKETS - 1)]; } +/* Called with ovs_mutex or RCU read lock. */ struct vport *ovs_lookup_vport(const struct datapath *dp, u16 port_no) { struct vport *vport; @@ -262,16 +288,6 @@ out: u64_stats_update_end(&stats->syncp); } -static struct genl_family dp_packet_genl_family = { - .id = GENL_ID_GENERATE, - .hdrsize = sizeof(struct ovs_header), - .name = OVS_PACKET_FAMILY, - .version = OVS_PACKET_VERSION, - .maxattr = OVS_PACKET_ATTR_MAX, - .netnsok = true, - .parallel_ops = true, -}; - int ovs_dp_upcall(struct datapath *dp, struct sk_buff *skb, const struct dp_upcall_info *upcall_info) { @@ -590,6 +606,18 @@ static const struct genl_ops dp_packet_genl_ops[] = { } }; +static struct genl_family dp_packet_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = sizeof(struct ovs_header), + .name = OVS_PACKET_FAMILY, + .version = OVS_PACKET_VERSION, + .maxattr = OVS_PACKET_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = dp_packet_genl_ops, + .n_ops = ARRAY_SIZE(dp_packet_genl_ops), +}; + static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, struct ovs_dp_megaflow_stats *mega_stats) { @@ -621,26 +649,6 @@ static void get_dp_stats(struct datapath *dp, struct ovs_dp_stats *stats, } } -static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { - [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED }, - [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED }, - [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, -}; - -static struct genl_family dp_flow_genl_family = { - .id = GENL_ID_GENERATE, - .hdrsize = sizeof(struct ovs_header), - .name = OVS_FLOW_FAMILY, - .version = OVS_FLOW_VERSION, - .maxattr = OVS_FLOW_ATTR_MAX, - .netnsok = true, - .parallel_ops = true, -}; - -static struct genl_multicast_group ovs_dp_flow_multicast_group = { - .name = OVS_FLOW_MCGROUP -}; - static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) { return NLMSG_ALIGN(sizeof(struct ovs_header)) @@ -652,8 +660,8 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts) + nla_total_size(acts->actions_len); /* OVS_FLOW_ATTR_ACTIONS */ } -/* Called with ovs_mutex. */ -static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, +/* Called with ovs_mutex or RCU read lock. */ +static int ovs_flow_cmd_fill_info(const struct sw_flow *flow, int dp_ifindex, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@ -670,7 +678,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, if (!ovs_header) return -EMSGSIZE; - ovs_header->dp_ifindex = get_dpifindex(dp); + ovs_header->dp_ifindex = dp_ifindex; /* Fill flow key. */ nla = nla_nest_start(skb, OVS_FLOW_ATTR_KEY); @@ -693,6 +701,7 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, nla_nest_end(skb, nla); ovs_flow_stats_get(flow, &stats, &used, &tcp_flags); + if (used && nla_put_u64(skb, OVS_FLOW_ATTR_USED, ovs_flow_used_time(used))) goto nla_put_failure; @@ -720,9 +729,9 @@ static int ovs_flow_cmd_fill_info(struct sw_flow *flow, struct datapath *dp, const struct sw_flow_actions *sf_acts; sf_acts = rcu_dereference_ovsl(flow->sf_acts); - err = ovs_nla_put_actions(sf_acts->actions, sf_acts->actions_len, skb); + if (!err) nla_nest_end(skb, start); else { @@ -743,112 +752,128 @@ error: return err; } -static struct sk_buff *ovs_flow_cmd_alloc_info(struct sw_flow *flow, - struct genl_info *info) +/* May not be called with RCU read lock. */ +static struct sk_buff *ovs_flow_cmd_alloc_info(const struct sw_flow_actions *acts, + struct genl_info *info, + bool always) { - size_t len; + struct sk_buff *skb; - len = ovs_flow_cmd_msg_size(ovsl_dereference(flow->sf_acts)); + if (!always && !ovs_must_notify(info, &ovs_dp_flow_multicast_group)) + return NULL; - return genlmsg_new_unicast(len, info, GFP_KERNEL); + skb = genlmsg_new_unicast(ovs_flow_cmd_msg_size(acts), info, GFP_KERNEL); + if (!skb) + return ERR_PTR(-ENOMEM); + + return skb; } -static struct sk_buff *ovs_flow_cmd_build_info(struct sw_flow *flow, - struct datapath *dp, - struct genl_info *info, - u8 cmd) +/* Called with ovs_mutex. */ +static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, + int dp_ifindex, + struct genl_info *info, u8 cmd, + bool always) { struct sk_buff *skb; int retval; - skb = ovs_flow_cmd_alloc_info(flow, info); - if (!skb) - return ERR_PTR(-ENOMEM); + skb = ovs_flow_cmd_alloc_info(ovsl_dereference(flow->sf_acts), info, + always); + if (!skb || IS_ERR(skb)) + return skb; - retval = ovs_flow_cmd_fill_info(flow, dp, skb, info->snd_portid, - info->snd_seq, 0, cmd); + retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, + info->snd_portid, info->snd_seq, 0, + cmd); BUG_ON(retval < 0); return skb; } -static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) +static int ovs_flow_cmd_new(struct sk_buff *skb, struct genl_info *info) { struct nlattr **a = info->attrs; struct ovs_header *ovs_header = info->userhdr; - struct sw_flow_key key, masked_key; - struct sw_flow *flow = NULL; + struct sw_flow *flow, *new_flow; struct sw_flow_mask mask; struct sk_buff *reply; struct datapath *dp; - struct sw_flow_actions *acts = NULL; + struct sw_flow_actions *acts; struct sw_flow_match match; int error; - /* Extract key. */ + /* Must have key and actions. */ error = -EINVAL; if (!a[OVS_FLOW_ATTR_KEY]) goto error; + if (!a[OVS_FLOW_ATTR_ACTIONS]) + goto error; - ovs_match_init(&match, &key, &mask); + /* Most of the time we need to allocate a new flow, do it before + * locking. + */ + new_flow = ovs_flow_alloc(); + if (IS_ERR(new_flow)) { + error = PTR_ERR(new_flow); + goto error; + } + + /* Extract key. */ + ovs_match_init(&match, &new_flow->unmasked_key, &mask); error = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]); if (error) - goto error; + goto err_kfree_flow; + + ovs_flow_mask_key(&new_flow->key, &new_flow->unmasked_key, &mask); /* Validate actions. */ - if (a[OVS_FLOW_ATTR_ACTIONS]) { - acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); - error = PTR_ERR(acts); - if (IS_ERR(acts)) - goto error; + acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); + error = PTR_ERR(acts); + if (IS_ERR(acts)) + goto err_kfree_flow; - ovs_flow_mask_key(&masked_key, &key, &mask); - error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], - &masked_key, 0, &acts); - if (error) { - OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); - goto err_kfree; - } - } else if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW) { - error = -EINVAL; - goto error; + error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], &new_flow->key, + 0, &acts); + if (error) { + OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); + goto err_kfree_acts; + } + + reply = ovs_flow_cmd_alloc_info(acts, info, false); + if (IS_ERR(reply)) { + error = PTR_ERR(reply); + goto err_kfree_acts; } ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - error = -ENODEV; - if (!dp) + if (unlikely(!dp)) { + error = -ENODEV; goto err_unlock_ovs; - + } /* Check if this is a duplicate flow */ - flow = ovs_flow_tbl_lookup(&dp->table, &key); - if (!flow) { - /* Bail out if we're not allowed to create a new flow. */ - error = -ENOENT; - if (info->genlhdr->cmd == OVS_FLOW_CMD_SET) - goto err_unlock_ovs; - - /* Allocate flow. */ - flow = ovs_flow_alloc(); - if (IS_ERR(flow)) { - error = PTR_ERR(flow); - goto err_unlock_ovs; - } - - flow->key = masked_key; - flow->unmasked_key = key; - rcu_assign_pointer(flow->sf_acts, acts); + flow = ovs_flow_tbl_lookup(&dp->table, &new_flow->unmasked_key); + if (likely(!flow)) { + rcu_assign_pointer(new_flow->sf_acts, acts); /* Put flow in bucket. */ - error = ovs_flow_tbl_insert(&dp->table, flow, &mask); - if (error) { + error = ovs_flow_tbl_insert(&dp->table, new_flow, &mask); + if (unlikely(error)) { acts = NULL; - goto err_flow_free; + goto err_unlock_ovs; } - reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); + if (unlikely(reply)) { + error = ovs_flow_cmd_fill_info(new_flow, + ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_NEW); + BUG_ON(error < 0); + } + ovs_unlock(); } else { - /* We found a matching flow. */ struct sw_flow_actions *old_acts; /* Bail out if we're not allowed to modify an existing flow. @@ -857,40 +882,154 @@ static int ovs_flow_cmd_new_or_set(struct sk_buff *skb, struct genl_info *info) * request. We also accept NLM_F_EXCL in case that bug ever * gets fixed. */ - error = -EEXIST; - if (info->genlhdr->cmd == OVS_FLOW_CMD_NEW && - info->nlhdr->nlmsg_flags & (NLM_F_CREATE | NLM_F_EXCL)) + if (unlikely(info->nlhdr->nlmsg_flags & (NLM_F_CREATE + | NLM_F_EXCL))) { + error = -EEXIST; goto err_unlock_ovs; - + } /* The unmasked key has to be the same for flow updates. */ - if (!ovs_flow_cmp_unmasked_key(flow, &match)) + if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) { + error = -EEXIST; goto err_unlock_ovs; - + } /* Update actions. */ old_acts = ovsl_dereference(flow->sf_acts); rcu_assign_pointer(flow->sf_acts, acts); + + if (unlikely(reply)) { + error = ovs_flow_cmd_fill_info(flow, + ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_NEW); + BUG_ON(error < 0); + } + ovs_unlock(); + ovs_nla_free_flow_actions(old_acts); + ovs_flow_free(new_flow, false); + } + + if (reply) + ovs_notify(&dp_flow_genl_family, reply, info); + return 0; + +err_unlock_ovs: + ovs_unlock(); + kfree_skb(reply); +err_kfree_acts: + kfree(acts); +err_kfree_flow: + ovs_flow_free(new_flow, false); +error: + return error; +} + +static int ovs_flow_cmd_set(struct sk_buff *skb, struct genl_info *info) +{ + struct nlattr **a = info->attrs; + struct ovs_header *ovs_header = info->userhdr; + struct sw_flow_key key, masked_key; + struct sw_flow *flow; + struct sw_flow_mask mask; + struct sk_buff *reply = NULL; + struct datapath *dp; + struct sw_flow_actions *old_acts = NULL, *acts = NULL; + struct sw_flow_match match; + int error; + + /* Extract key. */ + error = -EINVAL; + if (!a[OVS_FLOW_ATTR_KEY]) + goto error; + + ovs_match_init(&match, &key, &mask); + error = ovs_nla_get_match(&match, + a[OVS_FLOW_ATTR_KEY], a[OVS_FLOW_ATTR_MASK]); + if (error) + goto error; + + /* Validate actions. */ + if (a[OVS_FLOW_ATTR_ACTIONS]) { + acts = ovs_nla_alloc_flow_actions(nla_len(a[OVS_FLOW_ATTR_ACTIONS])); + error = PTR_ERR(acts); + if (IS_ERR(acts)) + goto error; + + ovs_flow_mask_key(&masked_key, &key, &mask); + error = ovs_nla_copy_actions(a[OVS_FLOW_ATTR_ACTIONS], + &masked_key, 0, &acts); + if (error) { + OVS_NLERR("Flow actions may not be safe on all matching packets.\n"); + goto err_kfree_acts; + } + } + + /* Can allocate before locking if have acts. */ + if (acts) { + reply = ovs_flow_cmd_alloc_info(acts, info, false); + if (IS_ERR(reply)) { + error = PTR_ERR(reply); + goto err_kfree_acts; + } + } - reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); + ovs_lock(); + dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); + if (unlikely(!dp)) { + error = -ENODEV; + goto err_unlock_ovs; + } + /* Check that the flow exists. */ + flow = ovs_flow_tbl_lookup(&dp->table, &key); + if (unlikely(!flow)) { + error = -ENOENT; + goto err_unlock_ovs; + } + /* The unmasked key has to be the same for flow updates. */ + if (unlikely(!ovs_flow_cmp_unmasked_key(flow, &match))) { + error = -EEXIST; + goto err_unlock_ovs; + } + /* Update actions, if present. */ + if (likely(acts)) { + old_acts = ovsl_dereference(flow->sf_acts); + rcu_assign_pointer(flow->sf_acts, acts); - /* Clear stats. */ - if (a[OVS_FLOW_ATTR_CLEAR]) - ovs_flow_stats_clear(flow); + if (unlikely(reply)) { + error = ovs_flow_cmd_fill_info(flow, + ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_NEW); + BUG_ON(error < 0); + } + } else { + /* Could not alloc without acts before locking. */ + reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, + info, OVS_FLOW_CMD_NEW, false); + if (unlikely(IS_ERR(reply))) { + error = PTR_ERR(reply); + goto err_unlock_ovs; + } } + + /* Clear stats. */ + if (a[OVS_FLOW_ATTR_CLEAR]) + ovs_flow_stats_clear(flow); ovs_unlock(); - if (!IS_ERR(reply)) + if (reply) ovs_notify(&dp_flow_genl_family, reply, info); - else - genl_set_err(&dp_flow_genl_family, sock_net(skb->sk), 0, - 0, PTR_ERR(reply)); + if (old_acts) + ovs_nla_free_flow_actions(old_acts); + return 0; -err_flow_free: - ovs_flow_free(flow, false); err_unlock_ovs: ovs_unlock(); -err_kfree: + kfree_skb(reply); +err_kfree_acts: kfree(acts); error: return error; @@ -930,7 +1069,8 @@ static int ovs_flow_cmd_get(struct sk_buff *skb, struct genl_info *info) goto unlock; } - reply = ovs_flow_cmd_build_info(flow, dp, info, OVS_FLOW_CMD_NEW); + reply = ovs_flow_cmd_build_info(flow, ovs_header->dp_ifindex, info, + OVS_FLOW_CMD_NEW, true); if (IS_ERR(reply)) { err = PTR_ERR(reply); goto unlock; @@ -954,45 +1094,53 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) struct sw_flow_match match; int err; + if (likely(a[OVS_FLOW_ATTR_KEY])) { + ovs_match_init(&match, &key, NULL); + err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL); + if (unlikely(err)) + return err; + } + ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); - if (!dp) { + if (unlikely(!dp)) { err = -ENODEV; goto unlock; } - if (!a[OVS_FLOW_ATTR_KEY]) { + if (unlikely(!a[OVS_FLOW_ATTR_KEY])) { err = ovs_flow_tbl_flush(&dp->table); goto unlock; } - ovs_match_init(&match, &key, NULL); - err = ovs_nla_get_match(&match, a[OVS_FLOW_ATTR_KEY], NULL); - if (err) - goto unlock; - flow = ovs_flow_tbl_lookup(&dp->table, &key); - if (!flow || !ovs_flow_cmp_unmasked_key(flow, &match)) { + if (unlikely(!flow || !ovs_flow_cmp_unmasked_key(flow, &match))) { err = -ENOENT; goto unlock; } - reply = ovs_flow_cmd_alloc_info(flow, info); - if (!reply) { - err = -ENOMEM; - goto unlock; - } - ovs_flow_tbl_remove(&dp->table, flow); + ovs_unlock(); - err = ovs_flow_cmd_fill_info(flow, dp, reply, info->snd_portid, - info->snd_seq, 0, OVS_FLOW_CMD_DEL); - BUG_ON(err < 0); + reply = ovs_flow_cmd_alloc_info((const struct sw_flow_actions __force *) flow->sf_acts, + info, false); + if (likely(reply)) { + if (likely(!IS_ERR(reply))) { + rcu_read_lock(); /*To keep RCU checker happy. */ + err = ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, + reply, info->snd_portid, + info->snd_seq, 0, + OVS_FLOW_CMD_DEL); + rcu_read_unlock(); + BUG_ON(err < 0); + + ovs_notify(&dp_flow_genl_family, reply, info); + } else { + netlink_set_err(sock_net(skb->sk)->genl_sock, 0, 0, PTR_ERR(reply)); + } + } ovs_flow_free(flow, true); - ovs_unlock(); - - ovs_notify(&dp_flow_genl_family, reply, info); return 0; unlock: ovs_unlock(); @@ -1023,7 +1171,7 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!flow) break; - if (ovs_flow_cmd_fill_info(flow, dp, skb, + if (ovs_flow_cmd_fill_info(flow, ovs_header->dp_ifindex, skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, OVS_FLOW_CMD_NEW) < 0) @@ -1036,11 +1184,17 @@ static int ovs_flow_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static const struct genl_ops dp_flow_genl_ops[] = { +static const struct nla_policy flow_policy[OVS_FLOW_ATTR_MAX + 1] = { + [OVS_FLOW_ATTR_KEY] = { .type = NLA_NESTED }, + [OVS_FLOW_ATTR_ACTIONS] = { .type = NLA_NESTED }, + [OVS_FLOW_ATTR_CLEAR] = { .type = NLA_FLAG }, +}; + +static struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, - .doit = ovs_flow_cmd_new_or_set + .doit = ovs_flow_cmd_new }, { .cmd = OVS_FLOW_CMD_DEL, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ @@ -1056,28 +1210,22 @@ static const struct genl_ops dp_flow_genl_ops[] = { { .cmd = OVS_FLOW_CMD_SET, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = flow_policy, - .doit = ovs_flow_cmd_new_or_set, + .doit = ovs_flow_cmd_set, }, }; -static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { - [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, - [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, - [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, -}; - -static struct genl_family dp_datapath_genl_family = { +static struct genl_family dp_flow_genl_family = { .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), - .name = OVS_DATAPATH_FAMILY, - .version = OVS_DATAPATH_VERSION, - .maxattr = OVS_DP_ATTR_MAX, + .name = OVS_FLOW_FAMILY, + .version = OVS_FLOW_VERSION, + .maxattr = OVS_FLOW_ATTR_MAX, .netnsok = true, .parallel_ops = true, -}; - -static struct genl_multicast_group ovs_dp_datapath_multicast_group = { - .name = OVS_DATAPATH_MCGROUP + .ops = dp_flow_genl_ops, + .n_ops = ARRAY_SIZE(dp_flow_genl_ops), + .mcgrps = &ovs_dp_flow_multicast_group, + .n_mcgrps = 1, }; static size_t ovs_dp_cmd_msg_size(void) @@ -1092,6 +1240,7 @@ static size_t ovs_dp_cmd_msg_size(void) return msgsize; } +/* Called with ovs_mutex or RCU read lock. */ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, u32 portid, u32 seq, u32 flags, u8 cmd) { @@ -1107,9 +1256,7 @@ static int ovs_dp_cmd_fill_info(struct datapath *dp, struct sk_buff *skb, ovs_header->dp_ifindex = get_dpifindex(dp); - rcu_read_lock(); err = nla_put_string(skb, OVS_DP_ATTR_NAME, ovs_dp_name(dp)); - rcu_read_unlock(); if (err) goto nla_put_failure; @@ -1134,25 +1281,12 @@ error: return -EMSGSIZE; } -static struct sk_buff *ovs_dp_cmd_build_info(struct datapath *dp, - struct genl_info *info, u8 cmd) +static struct sk_buff *ovs_dp_cmd_alloc_info(struct genl_info *info) { - struct sk_buff *skb; - int retval; - - skb = genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL); - if (!skb) - return ERR_PTR(-ENOMEM); - - retval = ovs_dp_cmd_fill_info(dp, skb, info->snd_portid, info->snd_seq, 0, cmd); - if (retval < 0) { - kfree_skb(skb); - return ERR_PTR(retval); - } - return skb; + return genlmsg_new_unicast(ovs_dp_cmd_msg_size(), info, GFP_KERNEL); } -/* Called with ovs_mutex. */ +/* Called with rcu_read_lock or ovs_mutex. */ static struct datapath *lookup_datapath(struct net *net, struct ovs_header *ovs_header, struct nlattr *a[OVS_DP_ATTR_MAX + 1]) @@ -1164,10 +1298,8 @@ static struct datapath *lookup_datapath(struct net *net, else { struct vport *vport; - rcu_read_lock(); vport = ovs_vport_locate(net, nla_data(a[OVS_DP_ATTR_NAME])); dp = vport && vport->port_no == OVSP_LOCAL ? vport->dp : NULL; - rcu_read_unlock(); } return dp ? dp : ERR_PTR(-ENODEV); } @@ -1204,12 +1336,14 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) if (!a[OVS_DP_ATTR_NAME] || !a[OVS_DP_ATTR_UPCALL_PID]) goto err; - ovs_lock(); + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; err = -ENOMEM; dp = kzalloc(sizeof(*dp), GFP_KERNEL); if (dp == NULL) - goto err_unlock_ovs; + goto err_free_reply; ovs_dp_set_net(dp, hold_net(sock_net(skb->sk))); @@ -1244,6 +1378,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_dp_change(dp, a); + /* So far only local changes have been made, now need the lock. */ + ovs_lock(); + vport = new_vport(&parms); if (IS_ERR(vport)) { err = PTR_ERR(vport); @@ -1262,10 +1399,9 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) goto err_destroy_ports_array; } - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto err_destroy_local_port; + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_NEW); + BUG_ON(err < 0); ovs_net = net_generic(ovs_dp_get_net(dp), ovs_net_id); list_add_tail_rcu(&dp->list_node, &ovs_net->dps); @@ -1275,9 +1411,8 @@ static int ovs_dp_cmd_new(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -err_destroy_local_port: - ovs_dp_detach_port(ovs_vport_ovsl(dp, OVSP_LOCAL)); err_destroy_ports_array: + ovs_unlock(); kfree(dp->ports); err_destroy_percpu: free_percpu(dp->stats_percpu); @@ -1286,8 +1421,8 @@ err_destroy_table: err_free_dp: release_net(ovs_dp_get_net(dp)); kfree(dp); -err_unlock_ovs: - ovs_unlock(); +err_free_reply: + kfree_skb(reply); err: return err; } @@ -1325,16 +1460,19 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; + ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) - goto unlock; + goto err_unlock_free; - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_DEL); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto unlock; + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_DEL); + BUG_ON(err < 0); __dp_destroy(dp); ovs_unlock(); @@ -1342,8 +1480,10 @@ static int ovs_dp_cmd_del(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -unlock: + +err_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1353,29 +1493,30 @@ static int ovs_dp_cmd_set(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; + ovs_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); err = PTR_ERR(dp); if (IS_ERR(dp)) - goto unlock; + goto err_unlock_free; ovs_dp_change(dp, info->attrs); - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); - if (IS_ERR(reply)) { - err = PTR_ERR(reply); - genl_set_err(&dp_datapath_genl_family, sock_net(skb->sk), 0, - 0, err); - err = 0; - goto unlock; - } + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_NEW); + BUG_ON(err < 0); ovs_unlock(); ovs_notify(&dp_datapath_genl_family, reply, info); return 0; -unlock: + +err_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1385,24 +1526,26 @@ static int ovs_dp_cmd_get(struct sk_buff *skb, struct genl_info *info) struct datapath *dp; int err; - ovs_lock(); + reply = ovs_dp_cmd_alloc_info(info); + if (!reply) + return -ENOMEM; + + rcu_read_lock(); dp = lookup_datapath(sock_net(skb->sk), info->userhdr, info->attrs); if (IS_ERR(dp)) { err = PTR_ERR(dp); - goto unlock; - } - - reply = ovs_dp_cmd_build_info(dp, info, OVS_DP_CMD_NEW); - if (IS_ERR(reply)) { - err = PTR_ERR(reply); - goto unlock; + goto err_unlock_free; } + err = ovs_dp_cmd_fill_info(dp, reply, info->snd_portid, + info->snd_seq, 0, OVS_DP_CMD_NEW); + BUG_ON(err < 0); + rcu_read_unlock(); - ovs_unlock(); return genlmsg_reply(reply, info); -unlock: - ovs_unlock(); +err_unlock_free: + rcu_read_unlock(); + kfree_skb(reply); return err; } @@ -1429,7 +1572,13 @@ static int ovs_dp_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; } -static const struct genl_ops dp_datapath_genl_ops[] = { +static const struct nla_policy datapath_policy[OVS_DP_ATTR_MAX + 1] = { + [OVS_DP_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, + [OVS_DP_ATTR_UPCALL_PID] = { .type = NLA_U32 }, + [OVS_DP_ATTR_USER_FEATURES] = { .type = NLA_U32 }, +}; + +static struct genl_ops dp_datapath_genl_ops[] = { { .cmd = OVS_DP_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = datapath_policy, @@ -1453,27 +1602,18 @@ static const struct genl_ops dp_datapath_genl_ops[] = { }, }; -static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { - [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, - [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, - [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, - [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, -}; - -struct genl_family dp_vport_genl_family = { +static struct genl_family dp_datapath_genl_family = { .id = GENL_ID_GENERATE, .hdrsize = sizeof(struct ovs_header), - .name = OVS_VPORT_FAMILY, - .version = OVS_VPORT_VERSION, - .maxattr = OVS_VPORT_ATTR_MAX, + .name = OVS_DATAPATH_FAMILY, + .version = OVS_DATAPATH_VERSION, + .maxattr = OVS_DP_ATTR_MAX, .netnsok = true, .parallel_ops = true, -}; - -static struct genl_multicast_group ovs_dp_vport_multicast_group = { - .name = OVS_VPORT_MCGROUP + .ops = dp_datapath_genl_ops, + .n_ops = ARRAY_SIZE(dp_datapath_genl_ops), + .mcgrps = &ovs_dp_datapath_multicast_group, + .n_mcgrps = 1, }; /* Called with ovs_mutex or RCU read lock. */ @@ -1515,7 +1655,12 @@ error: return err; } -/* Called with ovs_mutex or RCU read lock. */ +static struct sk_buff *ovs_vport_cmd_alloc_info(void) +{ + return nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); +} + +/* Called with ovs_mutex, only via ovs_dp_notify_wq(). */ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, u32 portid, u32 seq, u8 cmd) { @@ -1577,33 +1722,35 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) u32 port_no; int err; - err = -EINVAL; if (!a[OVS_VPORT_ATTR_NAME] || !a[OVS_VPORT_ATTR_TYPE] || !a[OVS_VPORT_ATTR_UPCALL_PID]) - goto exit; + return -EINVAL; + + port_no = a[OVS_VPORT_ATTR_PORT_NO] + ? nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]) : 0; + if (port_no >= DP_MAX_PORTS) + return -EFBIG; + + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; ovs_lock(); dp = get_dp(sock_net(skb->sk), ovs_header->dp_ifindex); err = -ENODEV; if (!dp) - goto exit_unlock; - - if (a[OVS_VPORT_ATTR_PORT_NO]) { - port_no = nla_get_u32(a[OVS_VPORT_ATTR_PORT_NO]); - - err = -EFBIG; - if (port_no >= DP_MAX_PORTS) - goto exit_unlock; + goto exit_unlock_free; + if (port_no) { vport = ovs_vport_ovsl(dp, port_no); err = -EBUSY; if (vport) - goto exit_unlock; + goto exit_unlock_free; } else { for (port_no = 1; ; port_no++) { if (port_no >= DP_MAX_PORTS) { err = -EFBIG; - goto exit_unlock; + goto exit_unlock_free; } vport = ovs_vport_ovsl(dp, port_no); if (!vport) @@ -1621,22 +1768,19 @@ static int ovs_vport_cmd_new(struct sk_buff *skb, struct genl_info *info) vport = new_vport(&parms); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; + goto exit_unlock_free; - err = 0; - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, info->snd_seq, - OVS_VPORT_CMD_NEW); - if (IS_ERR(reply)) { - err = PTR_ERR(reply); - ovs_dp_detach_port(vport); - goto exit_unlock; - } + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0); + ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); + return 0; -exit_unlock: +exit_unlock_free: ovs_unlock(); -exit: + kfree_skb(reply); return err; } @@ -1647,28 +1791,26 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) struct vport *vport; int err; + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; + ovs_lock(); vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; + goto exit_unlock_free; if (a[OVS_VPORT_ATTR_TYPE] && nla_get_u32(a[OVS_VPORT_ATTR_TYPE]) != vport->ops->type) { err = -EINVAL; - goto exit_unlock; - } - - reply = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!reply) { - err = -ENOMEM; - goto exit_unlock; + goto exit_unlock_free; } if (a[OVS_VPORT_ATTR_OPTIONS]) { err = ovs_vport_set_options(vport, a[OVS_VPORT_ATTR_OPTIONS]); if (err) - goto exit_free; + goto exit_unlock_free; } if (a[OVS_VPORT_ATTR_UPCALL_PID]) @@ -1682,10 +1824,9 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) ovs_notify(&dp_vport_genl_family, reply, info); return 0; -exit_free: - kfree_skb(reply); -exit_unlock: +exit_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1696,30 +1837,33 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) struct vport *vport; int err; + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; + ovs_lock(); vport = lookup_vport(sock_net(skb->sk), info->userhdr, a); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; + goto exit_unlock_free; if (vport->port_no == OVSP_LOCAL) { err = -EINVAL; - goto exit_unlock; + goto exit_unlock_free; } - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, - info->snd_seq, OVS_VPORT_CMD_DEL); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto exit_unlock; - - err = 0; + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_DEL); + BUG_ON(err < 0); ovs_dp_detach_port(vport); + ovs_unlock(); ovs_notify(&dp_vport_genl_family, reply, info); + return 0; -exit_unlock: +exit_unlock_free: ovs_unlock(); + kfree_skb(reply); return err; } @@ -1731,24 +1875,25 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) struct vport *vport; int err; + reply = ovs_vport_cmd_alloc_info(); + if (!reply) + return -ENOMEM; + rcu_read_lock(); vport = lookup_vport(sock_net(skb->sk), ovs_header, a); err = PTR_ERR(vport); if (IS_ERR(vport)) - goto exit_unlock; - - reply = ovs_vport_cmd_build_info(vport, info->snd_portid, - info->snd_seq, OVS_VPORT_CMD_NEW); - err = PTR_ERR(reply); - if (IS_ERR(reply)) - goto exit_unlock; - + goto exit_unlock_free; + err = ovs_vport_cmd_fill_info(vport, reply, info->snd_portid, + info->snd_seq, 0, OVS_VPORT_CMD_NEW); + BUG_ON(err < 0); rcu_read_unlock(); return genlmsg_reply(reply, info); -exit_unlock: +exit_unlock_free: rcu_read_unlock(); + kfree_skb(reply); return err; } @@ -1791,7 +1936,16 @@ out: return skb->len; } -static const struct genl_ops dp_vport_genl_ops[] = { +static const struct nla_policy vport_policy[OVS_VPORT_ATTR_MAX + 1] = { + [OVS_VPORT_ATTR_NAME] = { .type = NLA_NUL_STRING, .len = IFNAMSIZ - 1 }, + [OVS_VPORT_ATTR_STATS] = { .len = sizeof(struct ovs_vport_stats) }, + [OVS_VPORT_ATTR_PORT_NO] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_TYPE] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_UPCALL_PID] = { .type = NLA_U32 }, + [OVS_VPORT_ATTR_OPTIONS] = { .type = NLA_NESTED }, +}; + +static struct genl_ops dp_vport_genl_ops[] = { { .cmd = OVS_VPORT_CMD_NEW, .flags = GENL_ADMIN_PERM, /* Requires CAP_NET_ADMIN privilege. */ .policy = vport_policy, @@ -1815,26 +1969,25 @@ static const struct genl_ops dp_vport_genl_ops[] = { }, }; -struct genl_family_and_ops { - struct genl_family *family; - const struct genl_ops *ops; - int n_ops; - const struct genl_multicast_group *group; +struct genl_family dp_vport_genl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = sizeof(struct ovs_header), + .name = OVS_VPORT_FAMILY, + .version = OVS_VPORT_VERSION, + .maxattr = OVS_VPORT_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, + .ops = dp_vport_genl_ops, + .n_ops = ARRAY_SIZE(dp_vport_genl_ops), + .mcgrps = &ovs_dp_vport_multicast_group, + .n_mcgrps = 1, }; -static const struct genl_family_and_ops dp_genl_families[] = { - { &dp_datapath_genl_family, - dp_datapath_genl_ops, ARRAY_SIZE(dp_datapath_genl_ops), - &ovs_dp_datapath_multicast_group }, - { &dp_vport_genl_family, - dp_vport_genl_ops, ARRAY_SIZE(dp_vport_genl_ops), - &ovs_dp_vport_multicast_group }, - { &dp_flow_genl_family, - dp_flow_genl_ops, ARRAY_SIZE(dp_flow_genl_ops), - &ovs_dp_flow_multicast_group }, - { &dp_packet_genl_family, - dp_packet_genl_ops, ARRAY_SIZE(dp_packet_genl_ops), - NULL }, +static struct genl_family * const dp_genl_families[] = { + &dp_datapath_genl_family, + &dp_vport_genl_family, + &dp_flow_genl_family, + &dp_packet_genl_family, }; static void dp_unregister_genl(int n_families) @@ -1842,33 +1995,25 @@ static void dp_unregister_genl(int n_families) int i; for (i = 0; i < n_families; i++) - genl_unregister_family(dp_genl_families[i].family); + genl_unregister_family(dp_genl_families[i]); } static int dp_register_genl(void) { - int n_registered; int err; int i; - n_registered = 0; for (i = 0; i < ARRAY_SIZE(dp_genl_families); i++) { - const struct genl_family_and_ops *f = &dp_genl_families[i]; - f->family->ops = f->ops; - f->family->n_ops = f->n_ops; - f->family->mcgrps = f->group; - f->family->n_mcgrps = f->group ? 1 : 0; - err = genl_register_family(f->family); + err = genl_register_family(dp_genl_families[i]); if (err) goto error; - n_registered++; } return 0; error: - dp_unregister_genl(n_registered); + dp_unregister_genl(i); return err; } diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index e0fc12bbeeb..334751cb152 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -64,17 +64,11 @@ u64 ovs_flow_used_time(unsigned long flow_jiffies) void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb) { struct flow_stats *stats; - __be16 tcp_flags = 0; + __be16 tcp_flags = flow->key.tp.flags; int node = numa_node_id(); stats = rcu_dereference(flow->stats[node]); - if (likely(flow->key.ip.proto == IPPROTO_TCP)) { - if (likely(flow->key.eth.type == htons(ETH_P_IP))) - tcp_flags = flow->key.ipv4.tp.flags; - else if (likely(flow->key.eth.type == htons(ETH_P_IPV6))) - tcp_flags = flow->key.ipv6.tp.flags; - } /* Check if already have node-specific stats. */ if (likely(stats)) { spin_lock(&stats->lock); @@ -128,7 +122,9 @@ unlock: spin_unlock(&stats->lock); } -void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, +/* Must be called with rcu_read_lock or ovs_mutex. */ +void ovs_flow_stats_get(const struct sw_flow *flow, + struct ovs_flow_stats *ovs_stats, unsigned long *used, __be16 *tcp_flags) { int node; @@ -138,7 +134,7 @@ void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, memset(ovs_stats, 0, sizeof(*ovs_stats)); for_each_node(node) { - struct flow_stats *stats = rcu_dereference(flow->stats[node]); + struct flow_stats *stats = rcu_dereference_ovsl(flow->stats[node]); if (stats) { /* Local CPU may write on non-local stats, so we must @@ -155,12 +151,13 @@ void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *ovs_stats, } } +/* Called with ovs_mutex. */ void ovs_flow_stats_clear(struct sw_flow *flow) { int node; for_each_node(node) { - struct flow_stats *stats = rcu_dereference(flow->stats[node]); + struct flow_stats *stats = ovsl_dereference(flow->stats[node]); if (stats) { spin_lock_bh(&stats->lock); @@ -357,8 +354,8 @@ static int parse_icmpv6(struct sk_buff *skb, struct sw_flow_key *key, /* The ICMPv6 type and code fields use the 16-bit transport port * fields, so we need to store them in 16-bit network byte order. */ - key->ipv6.tp.src = htons(icmp->icmp6_type); - key->ipv6.tp.dst = htons(icmp->icmp6_code); + key->tp.src = htons(icmp->icmp6_type); + key->tp.dst = htons(icmp->icmp6_code); if (icmp->icmp6_code == 0 && (icmp->icmp6_type == NDISC_NEIGHBOUR_SOLICITATION || @@ -520,21 +517,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) if (key->ip.proto == IPPROTO_TCP) { if (tcphdr_ok(skb)) { struct tcphdr *tcp = tcp_hdr(skb); - key->ipv4.tp.src = tcp->source; - key->ipv4.tp.dst = tcp->dest; - key->ipv4.tp.flags = TCP_FLAGS_BE16(tcp); + key->tp.src = tcp->source; + key->tp.dst = tcp->dest; + key->tp.flags = TCP_FLAGS_BE16(tcp); } } else if (key->ip.proto == IPPROTO_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); - key->ipv4.tp.src = udp->source; - key->ipv4.tp.dst = udp->dest; + key->tp.src = udp->source; + key->tp.dst = udp->dest; } } else if (key->ip.proto == IPPROTO_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); - key->ipv4.tp.src = sctp->source; - key->ipv4.tp.dst = sctp->dest; + key->tp.src = sctp->source; + key->tp.dst = sctp->dest; } } else if (key->ip.proto == IPPROTO_ICMP) { if (icmphdr_ok(skb)) { @@ -542,8 +539,8 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) /* The ICMP type and code fields use the 16-bit * transport port fields, so we need to store * them in 16-bit network byte order. */ - key->ipv4.tp.src = htons(icmp->type); - key->ipv4.tp.dst = htons(icmp->code); + key->tp.src = htons(icmp->type); + key->tp.dst = htons(icmp->code); } } @@ -589,21 +586,21 @@ int ovs_flow_extract(struct sk_buff *skb, u16 in_port, struct sw_flow_key *key) if (key->ip.proto == NEXTHDR_TCP) { if (tcphdr_ok(skb)) { struct tcphdr *tcp = tcp_hdr(skb); - key->ipv6.tp.src = tcp->source; - key->ipv6.tp.dst = tcp->dest; - key->ipv6.tp.flags = TCP_FLAGS_BE16(tcp); + key->tp.src = tcp->source; + key->tp.dst = tcp->dest; + key->tp.flags = TCP_FLAGS_BE16(tcp); } } else if (key->ip.proto == NEXTHDR_UDP) { if (udphdr_ok(skb)) { struct udphdr *udp = udp_hdr(skb); - key->ipv6.tp.src = udp->source; - key->ipv6.tp.dst = udp->dest; + key->tp.src = udp->source; + key->tp.dst = udp->dest; } } else if (key->ip.proto == NEXTHDR_SCTP) { if (sctphdr_ok(skb)) { struct sctphdr *sctp = sctp_hdr(skb); - key->ipv6.tp.src = sctp->source; - key->ipv6.tp.dst = sctp->dest; + key->tp.src = sctp->source; + key->tp.dst = sctp->dest; } } else if (key->ip.proto == NEXTHDR_ICMP) { if (icmp6hdr_ok(skb)) { diff --git a/net/openvswitch/flow.h b/net/openvswitch/flow.h index ddcebc53224..ac395d2cd82 100644 --- a/net/openvswitch/flow.h +++ b/net/openvswitch/flow.h @@ -47,7 +47,7 @@ struct ovs_key_ipv4_tunnel { __be16 tun_flags; u8 ipv4_tos; u8 ipv4_ttl; -}; +} __packed __aligned(4); /* Minimize padding. */ static inline void ovs_flow_tun_key_init(struct ovs_key_ipv4_tunnel *tun_key, const struct iphdr *iph, __be64 tun_id, @@ -71,7 +71,7 @@ struct sw_flow_key { u32 priority; /* Packet QoS priority. */ u32 skb_mark; /* SKB mark. */ u16 in_port; /* Input switch port (or DP_MAX_PORTS). */ - } phy; + } __packed phy; /* Safe when right after 'tun_key'. */ struct { u8 src[ETH_ALEN]; /* Ethernet source address. */ u8 dst[ETH_ALEN]; /* Ethernet destination address. */ @@ -84,23 +84,21 @@ struct sw_flow_key { u8 ttl; /* IP TTL/hop limit. */ u8 frag; /* One of OVS_FRAG_TYPE_*. */ } ip; + struct { + __be16 src; /* TCP/UDP/SCTP source port. */ + __be16 dst; /* TCP/UDP/SCTP destination port. */ + __be16 flags; /* TCP flags. */ + } tp; union { struct { struct { __be32 src; /* IP source address. */ __be32 dst; /* IP destination address. */ } addr; - union { - struct { - __be16 src; /* TCP/UDP/SCTP source port. */ - __be16 dst; /* TCP/UDP/SCTP destination port. */ - __be16 flags; /* TCP flags. */ - } tp; - struct { - u8 sha[ETH_ALEN]; /* ARP source hardware address. */ - u8 tha[ETH_ALEN]; /* ARP target hardware address. */ - } arp; - }; + struct { + u8 sha[ETH_ALEN]; /* ARP source hardware address. */ + u8 tha[ETH_ALEN]; /* ARP target hardware address. */ + } arp; } ipv4; struct { struct { @@ -109,11 +107,6 @@ struct sw_flow_key { } addr; __be32 label; /* IPv6 flow label. */ struct { - __be16 src; /* TCP/UDP/SCTP source port. */ - __be16 dst; /* TCP/UDP/SCTP destination port. */ - __be16 flags; /* TCP flags. */ - } tp; - struct { struct in6_addr target; /* ND target address. */ u8 sll[ETH_ALEN]; /* ND source link layer address. */ u8 tll[ETH_ALEN]; /* ND target link layer address. */ @@ -187,10 +180,10 @@ struct arp_eth_header { unsigned char ar_tip[4]; /* target IP address */ } __packed; -void ovs_flow_stats_update(struct sw_flow *flow, struct sk_buff *skb); -void ovs_flow_stats_get(struct sw_flow *flow, struct ovs_flow_stats *stats, +void ovs_flow_stats_update(struct sw_flow *, struct sk_buff *); +void ovs_flow_stats_get(const struct sw_flow *, struct ovs_flow_stats *, unsigned long *used, __be16 *tcp_flags); -void ovs_flow_stats_clear(struct sw_flow *flow); +void ovs_flow_stats_clear(struct sw_flow *); u64 ovs_flow_used_time(unsigned long flow_jiffies); int ovs_flow_extract(struct sk_buff *, u16 in_port, struct sw_flow_key *); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 32a725cfeb0..d757848da89 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -204,11 +204,11 @@ static bool match_validate(const struct sw_flow_match *match, if (match->mask && (match->mask->key.ip.proto == 0xff)) mask_allowed |= 1 << OVS_KEY_ATTR_ICMPV6; - if (match->key->ipv6.tp.src == + if (match->key->tp.src == htons(NDISC_NEIGHBOUR_SOLICITATION) || - match->key->ipv6.tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { + match->key->tp.src == htons(NDISC_NEIGHBOUR_ADVERTISEMENT)) { key_expected |= 1 << OVS_KEY_ATTR_ND; - if (match->mask && (match->mask->key.ipv6.tp.src == htons(0xffff))) + if (match->mask && (match->mask->key.tp.src == htons(0xffff))) mask_allowed |= 1 << OVS_KEY_ATTR_ND; } } @@ -630,27 +630,18 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, const struct ovs_key_tcp *tcp_key; tcp_key = nla_data(a[OVS_KEY_ATTR_TCP]); - if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.src, - tcp_key->tcp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, - tcp_key->tcp_dst, is_mask); - } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.src, - tcp_key->tcp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, - tcp_key->tcp_dst, is_mask); - } + SW_FLOW_KEY_PUT(match, tp.src, tcp_key->tcp_src, is_mask); + SW_FLOW_KEY_PUT(match, tp.dst, tcp_key->tcp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_TCP); } if (attrs & (1 << OVS_KEY_ATTR_TCP_FLAGS)) { if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.flags, + SW_FLOW_KEY_PUT(match, tp.flags, nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]), is_mask); } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.flags, + SW_FLOW_KEY_PUT(match, tp.flags, nla_get_be16(a[OVS_KEY_ATTR_TCP_FLAGS]), is_mask); } @@ -661,17 +652,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, const struct ovs_key_udp *udp_key; udp_key = nla_data(a[OVS_KEY_ATTR_UDP]); - if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.src, - udp_key->udp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, - udp_key->udp_dst, is_mask); - } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.src, - udp_key->udp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, - udp_key->udp_dst, is_mask); - } + SW_FLOW_KEY_PUT(match, tp.src, udp_key->udp_src, is_mask); + SW_FLOW_KEY_PUT(match, tp.dst, udp_key->udp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_UDP); } @@ -679,17 +661,8 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, const struct ovs_key_sctp *sctp_key; sctp_key = nla_data(a[OVS_KEY_ATTR_SCTP]); - if (orig_attrs & (1 << OVS_KEY_ATTR_IPV4)) { - SW_FLOW_KEY_PUT(match, ipv4.tp.src, - sctp_key->sctp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, - sctp_key->sctp_dst, is_mask); - } else { - SW_FLOW_KEY_PUT(match, ipv6.tp.src, - sctp_key->sctp_src, is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, - sctp_key->sctp_dst, is_mask); - } + SW_FLOW_KEY_PUT(match, tp.src, sctp_key->sctp_src, is_mask); + SW_FLOW_KEY_PUT(match, tp.dst, sctp_key->sctp_dst, is_mask); attrs &= ~(1 << OVS_KEY_ATTR_SCTP); } @@ -697,9 +670,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, const struct ovs_key_icmp *icmp_key; icmp_key = nla_data(a[OVS_KEY_ATTR_ICMP]); - SW_FLOW_KEY_PUT(match, ipv4.tp.src, + SW_FLOW_KEY_PUT(match, tp.src, htons(icmp_key->icmp_type), is_mask); - SW_FLOW_KEY_PUT(match, ipv4.tp.dst, + SW_FLOW_KEY_PUT(match, tp.dst, htons(icmp_key->icmp_code), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ICMP); } @@ -708,9 +681,9 @@ static int ovs_key_from_nlattrs(struct sw_flow_match *match, u64 attrs, const struct ovs_key_icmpv6 *icmpv6_key; icmpv6_key = nla_data(a[OVS_KEY_ATTR_ICMPV6]); - SW_FLOW_KEY_PUT(match, ipv6.tp.src, + SW_FLOW_KEY_PUT(match, tp.src, htons(icmpv6_key->icmpv6_type), is_mask); - SW_FLOW_KEY_PUT(match, ipv6.tp.dst, + SW_FLOW_KEY_PUT(match, tp.dst, htons(icmpv6_key->icmpv6_code), is_mask); attrs &= ~(1 << OVS_KEY_ATTR_ICMPV6); } @@ -1024,19 +997,11 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; tcp_key = nla_data(nla); - if (swkey->eth.type == htons(ETH_P_IP)) { - tcp_key->tcp_src = output->ipv4.tp.src; - tcp_key->tcp_dst = output->ipv4.tp.dst; - if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, - output->ipv4.tp.flags)) - goto nla_put_failure; - } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - tcp_key->tcp_src = output->ipv6.tp.src; - tcp_key->tcp_dst = output->ipv6.tp.dst; - if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, - output->ipv6.tp.flags)) - goto nla_put_failure; - } + tcp_key->tcp_src = output->tp.src; + tcp_key->tcp_dst = output->tp.dst; + if (nla_put_be16(skb, OVS_KEY_ATTR_TCP_FLAGS, + output->tp.flags)) + goto nla_put_failure; } else if (swkey->ip.proto == IPPROTO_UDP) { struct ovs_key_udp *udp_key; @@ -1044,13 +1009,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; udp_key = nla_data(nla); - if (swkey->eth.type == htons(ETH_P_IP)) { - udp_key->udp_src = output->ipv4.tp.src; - udp_key->udp_dst = output->ipv4.tp.dst; - } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - udp_key->udp_src = output->ipv6.tp.src; - udp_key->udp_dst = output->ipv6.tp.dst; - } + udp_key->udp_src = output->tp.src; + udp_key->udp_dst = output->tp.dst; } else if (swkey->ip.proto == IPPROTO_SCTP) { struct ovs_key_sctp *sctp_key; @@ -1058,13 +1018,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; sctp_key = nla_data(nla); - if (swkey->eth.type == htons(ETH_P_IP)) { - sctp_key->sctp_src = output->ipv4.tp.src; - sctp_key->sctp_dst = output->ipv4.tp.dst; - } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - sctp_key->sctp_src = output->ipv6.tp.src; - sctp_key->sctp_dst = output->ipv6.tp.dst; - } + sctp_key->sctp_src = output->tp.src; + sctp_key->sctp_dst = output->tp.dst; } else if (swkey->eth.type == htons(ETH_P_IP) && swkey->ip.proto == IPPROTO_ICMP) { struct ovs_key_icmp *icmp_key; @@ -1073,8 +1028,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; icmp_key = nla_data(nla); - icmp_key->icmp_type = ntohs(output->ipv4.tp.src); - icmp_key->icmp_code = ntohs(output->ipv4.tp.dst); + icmp_key->icmp_type = ntohs(output->tp.src); + icmp_key->icmp_code = ntohs(output->tp.dst); } else if (swkey->eth.type == htons(ETH_P_IPV6) && swkey->ip.proto == IPPROTO_ICMPV6) { struct ovs_key_icmpv6 *icmpv6_key; @@ -1084,8 +1039,8 @@ int ovs_nla_put_flow(const struct sw_flow_key *swkey, if (!nla) goto nla_put_failure; icmpv6_key = nla_data(nla); - icmpv6_key->icmpv6_type = ntohs(output->ipv6.tp.src); - icmpv6_key->icmpv6_code = ntohs(output->ipv6.tp.dst); + icmpv6_key->icmpv6_type = ntohs(output->tp.src); + icmpv6_key->icmpv6_code = ntohs(output->tp.dst); if (icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_SOLICITATION || icmpv6_key->icmpv6_type == NDISC_NEIGHBOUR_ADVERTISEMENT) { @@ -1263,13 +1218,10 @@ static int validate_and_copy_sample(const struct nlattr *attr, static int validate_tp_port(const struct sw_flow_key *flow_key) { - if (flow_key->eth.type == htons(ETH_P_IP)) { - if (flow_key->ipv4.tp.src || flow_key->ipv4.tp.dst) - return 0; - } else if (flow_key->eth.type == htons(ETH_P_IPV6)) { - if (flow_key->ipv6.tp.src || flow_key->ipv6.tp.dst) - return 0; - } + if ((flow_key->eth.type == htons(ETH_P_IP) || + flow_key->eth.type == htons(ETH_P_IPV6)) && + (flow_key->tp.src || flow_key->tp.dst)) + return 0; return -EINVAL; } diff --git a/net/openvswitch/flow_table.c b/net/openvswitch/flow_table.c index d8ef37b937b..574c3abc9b3 100644 --- a/net/openvswitch/flow_table.c +++ b/net/openvswitch/flow_table.c @@ -139,7 +139,7 @@ static void flow_free(struct sw_flow *flow) { int node; - kfree((struct sf_flow_acts __force *)flow->sf_acts); + kfree((struct sw_flow_actions __force *)flow->sf_acts); for_each_node(node) if (flow->stats[node]) kmem_cache_free(flow_stats_cache, @@ -159,25 +159,6 @@ void ovs_flow_free(struct sw_flow *flow, bool deferred) if (!flow) return; - if (flow->mask) { - struct sw_flow_mask *mask = flow->mask; - - /* ovs-lock is required to protect mask-refcount and - * mask list. - */ - ASSERT_OVSL(); - BUG_ON(!mask->ref_count); - mask->ref_count--; - - if (!mask->ref_count) { - list_del_rcu(&mask->list); - if (deferred) - kfree_rcu(mask, rcu); - else - kfree(mask); - } - } - if (deferred) call_rcu(&flow->rcu, rcu_free_flow_callback); else @@ -491,6 +472,25 @@ static struct table_instance *table_instance_expand(struct table_instance *ti) return table_instance_rehash(ti, ti->n_buckets * 2); } +/* Remove 'mask' from the mask list, if it is not needed any more. */ +static void flow_mask_remove(struct flow_table *tbl, struct sw_flow_mask *mask) +{ + if (mask) { + /* ovs-lock is required to protect mask-refcount and + * mask list. + */ + ASSERT_OVSL(); + BUG_ON(!mask->ref_count); + mask->ref_count--; + + if (!mask->ref_count) { + list_del_rcu(&mask->list); + kfree_rcu(mask, rcu); + } + } +} + +/* Must be called with OVS mutex held. */ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) { struct table_instance *ti = ovsl_dereference(table->ti); @@ -498,6 +498,11 @@ void ovs_flow_tbl_remove(struct flow_table *table, struct sw_flow *flow) BUG_ON(table->count == 0); hlist_del_rcu(&flow->hash_node[ti->node_ver]); table->count--; + + /* RCU delete the mask. 'flow->mask' is not NULLed, as it should be + * accessible as long as the RCU read lock is held. + */ + flow_mask_remove(table, flow->mask); } static struct sw_flow_mask *mask_alloc(void) @@ -560,6 +565,7 @@ static int flow_mask_insert(struct flow_table *tbl, struct sw_flow *flow, return 0; } +/* Must be called with OVS mutex held. */ int ovs_flow_tbl_insert(struct flow_table *table, struct sw_flow *flow, struct sw_flow_mask *mask) { |