diff options
70 files changed, 2179 insertions, 888 deletions
diff --git a/drivers/net/atl1c/atl1c_main.c b/drivers/net/atl1c/atl1c_main.c index e60595f0247c..7d9d5067a65c 100644 --- a/drivers/net/atl1c/atl1c_main.c +++ b/drivers/net/atl1c/atl1c_main.c @@ -1102,10 +1102,10 @@ static void atl1c_configure_tx(struct atl1c_adapter *adapter) AT_READ_REG(hw, REG_DEVICE_CTRL, &dev_ctrl_data); max_pay_load = (dev_ctrl_data >> DEVICE_CTRL_MAX_PAYLOAD_SHIFT) & DEVICE_CTRL_MAX_PAYLOAD_MASK; - hw->dmaw_block = min(max_pay_load, hw->dmaw_block); + hw->dmaw_block = min_t(u32, max_pay_load, hw->dmaw_block); max_pay_load = (dev_ctrl_data >> DEVICE_CTRL_MAX_RREQ_SZ_SHIFT) & DEVICE_CTRL_MAX_RREQ_SZ_MASK; - hw->dmar_block = min(max_pay_load, hw->dmar_block); + hw->dmar_block = min_t(u32, max_pay_load, hw->dmar_block); txq_ctrl_data = (hw->tpd_burst & TXQ_NUM_TPD_BURST_MASK) << TXQ_NUM_TPD_BURST_SHIFT; diff --git a/drivers/net/atl1e/atl1e_main.c b/drivers/net/atl1e/atl1e_main.c index bf7500ccd73f..21f501184023 100644 --- a/drivers/net/atl1e/atl1e_main.c +++ b/drivers/net/atl1e/atl1e_main.c @@ -932,11 +932,11 @@ static inline void atl1e_configure_tx(struct atl1e_adapter *adapter) max_pay_load = ((dev_ctrl_data >> DEVICE_CTRL_MAX_PAYLOAD_SHIFT)) & DEVICE_CTRL_MAX_PAYLOAD_MASK; - hw->dmaw_block = min(max_pay_load, hw->dmaw_block); + hw->dmaw_block = min_t(u32, max_pay_load, hw->dmaw_block); max_pay_load = ((dev_ctrl_data >> DEVICE_CTRL_MAX_RREQ_SZ_SHIFT)) & DEVICE_CTRL_MAX_RREQ_SZ_MASK; - hw->dmar_block = min(max_pay_load, hw->dmar_block); + hw->dmar_block = min_t(u32, max_pay_load, hw->dmar_block); if (hw->nic_type != athr_l2e_revB) AT_WRITE_REGW(hw, REG_TXQ_CTRL + 2, diff --git a/drivers/net/igb/e1000_defines.h b/drivers/net/igb/e1000_defines.h index 6319ed902bc0..ff46c91520af 100644 --- a/drivers/net/igb/e1000_defines.h +++ b/drivers/net/igb/e1000_defines.h @@ -770,4 +770,11 @@ #define E1000_PCIEMISC_LX_DECISION 0x00000080 /* Lx power decision based on DMA coal */ +/* Tx Rate-Scheduler Config fields */ +#define E1000_RTTBCNRC_RS_ENA 0x80000000 +#define E1000_RTTBCNRC_RF_DEC_MASK 0x00003FFF +#define E1000_RTTBCNRC_RF_INT_SHIFT 14 +#define E1000_RTTBCNRC_RF_INT_MASK \ + (E1000_RTTBCNRC_RF_DEC_MASK << E1000_RTTBCNRC_RF_INT_SHIFT) + #endif diff --git a/drivers/net/igb/e1000_regs.h b/drivers/net/igb/e1000_regs.h index 8ac83c5190d5..3a6f8471aea2 100644 --- a/drivers/net/igb/e1000_regs.h +++ b/drivers/net/igb/e1000_regs.h @@ -106,6 +106,10 @@ #define E1000_RQDPC(_n) (0x0C030 + ((_n) * 0x40)) +/* TX Rate Limit Registers */ +#define E1000_RTTDQSEL 0x3604 /* Tx Desc Plane Queue Select - WO */ +#define E1000_RTTBCNRC 0x36B0 /* Tx BCN Rate-Scheduler Config - WO */ + /* Split and Replication RX Control - RW */ #define E1000_RXPBS 0x02404 /* Rx Packet Buffer Size - RW */ /* diff --git a/drivers/net/igb/igb.h b/drivers/net/igb/igb.h index 92a4ef09e55c..bbc5ebfe254a 100644 --- a/drivers/net/igb/igb.h +++ b/drivers/net/igb/igb.h @@ -77,6 +77,7 @@ struct vf_data_storage { unsigned long last_nack; u16 pf_vlan; /* When set, guest VLAN config not allowed. */ u16 pf_qos; + u16 tx_rate; }; #define IGB_VF_FLAG_CTS 0x00000001 /* VF is clear to send data */ @@ -323,6 +324,7 @@ struct igb_adapter { u16 rx_ring_count; unsigned int vfs_allocated_count; struct vf_data_storage *vf_data; + int vf_rate_link_speed; u32 rss_queues; u32 wvbr; }; diff --git a/drivers/net/igb/igb_main.c b/drivers/net/igb/igb_main.c index cb6bf7b815ae..579dbba5f9e4 100644 --- a/drivers/net/igb/igb_main.c +++ b/drivers/net/igb/igb_main.c @@ -50,12 +50,12 @@ #endif #include "igb.h" -#define DRV_VERSION "2.1.0-k2" +#define DRV_VERSION "2.4.13-k2" char igb_driver_name[] = "igb"; char igb_driver_version[] = DRV_VERSION; static const char igb_driver_string[] = "Intel(R) Gigabit Ethernet Network Driver"; -static const char igb_copyright[] = "Copyright (c) 2007-2009 Intel Corporation."; +static const char igb_copyright[] = "Copyright (c) 2007-2011 Intel Corporation."; static const struct e1000_info *igb_info_tbl[] = { [board_82575] = &e1000_82575_info, @@ -150,6 +150,7 @@ static int igb_ndo_set_vf_vlan(struct net_device *netdev, static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate); static int igb_ndo_get_vf_config(struct net_device *netdev, int vf, struct ifla_vf_info *ivi); +static void igb_check_vf_rate_limit(struct igb_adapter *); #ifdef CONFIG_PM static int igb_suspend(struct pci_dev *, pm_message_t); @@ -3511,6 +3512,7 @@ static void igb_watchdog_task(struct work_struct *work) netif_carrier_on(netdev); igb_ping_all_vfs(adapter); + igb_check_vf_rate_limit(adapter); /* link state has changed, schedule phy info update */ if (!test_bit(__IGB_DOWN, &adapter->state)) @@ -6599,9 +6601,91 @@ static int igb_ndo_set_vf_mac(struct net_device *netdev, int vf, u8 *mac) return igb_set_vf_mac(adapter, vf, mac); } +static int igb_link_mbps(int internal_link_speed) +{ + switch (internal_link_speed) { + case SPEED_100: + return 100; + case SPEED_1000: + return 1000; + default: + return 0; + } +} + +static void igb_set_vf_rate_limit(struct e1000_hw *hw, int vf, int tx_rate, + int link_speed) +{ + int rf_dec, rf_int; + u32 bcnrc_val; + + if (tx_rate != 0) { + /* Calculate the rate factor values to set */ + rf_int = link_speed / tx_rate; + rf_dec = (link_speed - (rf_int * tx_rate)); + rf_dec = (rf_dec * (1<<E1000_RTTBCNRC_RF_INT_SHIFT)) / tx_rate; + + bcnrc_val = E1000_RTTBCNRC_RS_ENA; + bcnrc_val |= ((rf_int<<E1000_RTTBCNRC_RF_INT_SHIFT) & + E1000_RTTBCNRC_RF_INT_MASK); + bcnrc_val |= (rf_dec & E1000_RTTBCNRC_RF_DEC_MASK); + } else { + bcnrc_val = 0; + } + + wr32(E1000_RTTDQSEL, vf); /* vf X uses queue X */ + wr32(E1000_RTTBCNRC, bcnrc_val); +} + +static void igb_check_vf_rate_limit(struct igb_adapter *adapter) +{ + int actual_link_speed, i; + bool reset_rate = false; + + /* VF TX rate limit was not set or not supported */ + if ((adapter->vf_rate_link_speed == 0) || + (adapter->hw.mac.type != e1000_82576)) + return; + + actual_link_speed = igb_link_mbps(adapter->link_speed); + if (actual_link_speed != adapter->vf_rate_link_speed) { + reset_rate = true; + adapter->vf_rate_link_speed = 0; + dev_info(&adapter->pdev->dev, + "Link speed has been changed. VF Transmit " + "rate is disabled\n"); + } + + for (i = 0; i < adapter->vfs_allocated_count; i++) { + if (reset_rate) + adapter->vf_data[i].tx_rate = 0; + + igb_set_vf_rate_limit(&adapter->hw, i, + adapter->vf_data[i].tx_rate, + actual_link_speed); + } +} + static int igb_ndo_set_vf_bw(struct net_device *netdev, int vf, int tx_rate) { - return -EOPNOTSUPP; + struct igb_adapter *adapter = netdev_priv(netdev); + struct e1000_hw *hw = &adapter->hw; + int actual_link_speed; + + if (hw->mac.type != e1000_82576) + return -EOPNOTSUPP; + + 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)) + 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); + + return 0; } static int igb_ndo_get_vf_config(struct net_device *netdev, @@ -6612,7 +6696,7 @@ 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 = 0; + ivi->tx_rate = adapter->vf_data[vf].tx_rate; ivi->vlan = adapter->vf_data[vf].pf_vlan; ivi->qos = adapter->vf_data[vf].pf_qos; return 0; diff --git a/drivers/net/igbvf/igbvf.h b/drivers/net/igbvf/igbvf.h index 990c329e6c3b..d5dad5d607d6 100644 --- a/drivers/net/igbvf/igbvf.h +++ b/drivers/net/igbvf/igbvf.h @@ -201,9 +201,6 @@ struct igbvf_adapter { unsigned int restart_queue; u32 txd_cmd; - bool detect_tx_hung; - u8 tx_timeout_factor; - u32 tx_int_delay; u32 tx_abs_int_delay; diff --git a/drivers/net/igbvf/netdev.c b/drivers/net/igbvf/netdev.c index 6352c8158e6d..42fdf5977be9 100644 --- a/drivers/net/igbvf/netdev.c +++ b/drivers/net/igbvf/netdev.c @@ -396,35 +396,6 @@ static void igbvf_put_txbuf(struct igbvf_adapter *adapter, buffer_info->time_stamp = 0; } -static void igbvf_print_tx_hang(struct igbvf_adapter *adapter) -{ - struct igbvf_ring *tx_ring = adapter->tx_ring; - unsigned int i = tx_ring->next_to_clean; - unsigned int eop = tx_ring->buffer_info[i].next_to_watch; - union e1000_adv_tx_desc *eop_desc = IGBVF_TX_DESC_ADV(*tx_ring, eop); - - /* detected Tx unit hang */ - dev_err(&adapter->pdev->dev, - "Detected Tx Unit Hang:\n" - " TDH <%x>\n" - " TDT <%x>\n" - " next_to_use <%x>\n" - " next_to_clean <%x>\n" - "buffer_info[next_to_clean]:\n" - " time_stamp <%lx>\n" - " next_to_watch <%x>\n" - " jiffies <%lx>\n" - " next_to_watch.status <%x>\n", - readl(adapter->hw.hw_addr + tx_ring->head), - readl(adapter->hw.hw_addr + tx_ring->tail), - tx_ring->next_to_use, - tx_ring->next_to_clean, - tx_ring->buffer_info[eop].time_stamp, - eop, - jiffies, - eop_desc->wb.status); -} - /** * igbvf_setup_tx_resources - allocate Tx resources (Descriptors) * @adapter: board private structure @@ -771,7 +742,6 @@ static void igbvf_set_itr(struct igbvf_adapter *adapter) static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring) { struct igbvf_adapter *adapter = tx_ring->adapter; - struct e1000_hw *hw = &adapter->hw; struct net_device *netdev = adapter->netdev; struct igbvf_buffer *buffer_info; struct sk_buff *skb; @@ -832,22 +802,6 @@ static bool igbvf_clean_tx_irq(struct igbvf_ring *tx_ring) } } - if (adapter->detect_tx_hung) { - /* Detect a transmit hang in hardware, this serializes the - * check with the clearing of time_stamp and movement of i */ - adapter->detect_tx_hung = false; - if (tx_ring->buffer_info[i].time_stamp && - time_after(jiffies, tx_ring->buffer_info[i].time_stamp + - (adapter->tx_timeout_factor * HZ)) && - !(er32(STATUS) & E1000_STATUS_TXOFF)) { - - tx_desc = IGBVF_TX_DESC_ADV(*tx_ring, i); - /* detected Tx unit hang */ - igbvf_print_tx_hang(adapter); - - netif_stop_queue(netdev); - } - } adapter->net_stats.tx_bytes += total_bytes; adapter->net_stats.tx_packets += total_packets; return count < tx_ring->count; @@ -1863,17 +1817,6 @@ static void igbvf_watchdog_task(struct work_struct *work) &adapter->link_duplex); igbvf_print_link_info(adapter); - /* adjust timeout factor according to speed/duplex */ - adapter->tx_timeout_factor = 1; - switch (adapter->link_speed) { - case SPEED_10: - adapter->tx_timeout_factor = 16; - break; - case SPEED_100: - /* maybe add some timeout factor ? */ - break; - } - netif_carrier_on(netdev); netif_wake_queue(netdev); } @@ -1907,9 +1850,6 @@ static void igbvf_watchdog_task(struct work_struct *work) /* Cause software interrupt to ensure Rx ring is cleaned */ ew32(EICS, adapter->rx_ring->eims_value); - /* Force detection of hung controller every watchdog period */ - adapter->detect_tx_hung = 1; - /* Reset the timer */ if (!test_bit(__IGBVF_DOWN, &adapter->state)) mod_timer(&adapter->watchdog_timer, diff --git a/drivers/net/ixgbe/ixgbe_main.c b/drivers/net/ixgbe/ixgbe_main.c index eca762d954c6..f0d0c5aad2b4 100644 --- a/drivers/net/ixgbe/ixgbe_main.c +++ b/drivers/net/ixgbe/ixgbe_main.c @@ -3077,6 +3077,14 @@ void ixgbe_configure_rx_ring(struct ixgbe_adapter *adapter, ixgbe_configure_srrctl(adapter, ring); ixgbe_configure_rscctl(adapter, ring); + /* If operating in IOV mode set RLPML for X540 */ + if ((adapter->flags & IXGBE_FLAG_SRIOV_ENABLED) && + hw->mac.type == ixgbe_mac_X540) { + rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK; + rxdctl |= ((ring->netdev->mtu + ETH_HLEN + + ETH_FCS_LEN + VLAN_HLEN) | IXGBE_RXDCTL_RLPML_EN); + } + if (hw->mac.type == ixgbe_mac_82598EB) { /* * enable cache line friendly hardware writes: @@ -5441,8 +5449,14 @@ static int ixgbe_change_mtu(struct net_device *netdev, int new_mtu) int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) - return -EINVAL; + if (adapter->flags & IXGBE_FLAG_SRIOV_ENABLED && + hw->mac.type != ixgbe_mac_X540) { + if ((new_mtu < 68) || (max_frame > MAXIMUM_ETHERNET_VLAN_SIZE)) + return -EINVAL; + } else { + if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) + return -EINVAL; + } e_info(probe, "changing MTU from %d to %d\n", netdev->mtu, new_mtu); /* must set new MTU before calling down or up */ diff --git a/drivers/net/ixgbe/ixgbe_sriov.c b/drivers/net/ixgbe/ixgbe_sriov.c index 187b3a16ec1f..fb4868d0a32d 100644 --- a/drivers/net/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ixgbe/ixgbe_sriov.c @@ -110,6 +110,33 @@ static int ixgbe_set_vf_vlan(struct ixgbe_adapter *adapter, int add, int vid, return adapter->hw.mac.ops.set_vfta(&adapter->hw, vid, vf, (bool)add); } +void ixgbe_set_vf_lpe(struct ixgbe_adapter *adapter, u32 *msgbuf) +{ + struct ixgbe_hw *hw = &adapter->hw; + int new_mtu = msgbuf[1]; + u32 max_frs; + int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; + + /* Only X540 supports jumbo frames in IOV mode */ + if (adapter->hw.mac.type != ixgbe_mac_X540) + return; + + /* MTU < 68 is an error and causes problems on some kernels */ + if ((new_mtu < 68) || (max_frame > IXGBE_MAX_JUMBO_FRAME_SIZE)) { + e_err(drv, "VF mtu %d out of range\n", new_mtu); + return; + } + + max_frs = (IXGBE_READ_REG(hw, IXGBE_MAXFRS) & + IXGBE_MHADD_MFS_MASK) >> IXGBE_MHADD_MFS_SHIFT; + if (max_frs < new_mtu) { + max_frs = new_mtu << IXGBE_MHADD_MFS_SHIFT; + IXGBE_WRITE_REG(hw, IXGBE_MAXFRS, max_frs); + } + + e_info(hw, "VF requests change max MTU to %d\n", new_mtu); +} + static void ixgbe_set_vmolr(struct ixgbe_hw *hw, u32 vf, bool aupe) { u32 vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(vf)); @@ -302,7 +329,7 @@ static int ixgbe_rcv_msg_from_vf(struct ixgbe_adapter *adapter, u32 vf) hash_list, vf); break; case IXGBE_VF_SET_LPE: - WARN_ON((msgbuf[0] & 0xFFFF) == IXGBE_VF_SET_LPE); + ixgbe_set_vf_lpe(adapter, msgbuf); break; case IXGBE_VF_SET_VLAN: add = (msgbuf[0] & IXGBE_VT_MSGINFO_MASK) diff --git a/drivers/net/ixgbe/ixgbe_type.h b/drivers/net/ixgbe/ixgbe_type.h index fd3358f54139..ab65d13969fd 100644 --- a/drivers/net/ixgbe/ixgbe_type.h +++ b/drivers/net/ixgbe/ixgbe_type.h @@ -1680,6 +1680,8 @@ #define IXGBE_RXCTRL_DMBYPS 0x00000002 /* Descriptor Monitor Bypass */ #define IXGBE_RXDCTL_ENABLE 0x02000000 /* Enable specific Rx Queue */ #define IXGBE_RXDCTL_VME 0x40000000 /* VLAN mode enable */ +#define IXGBE_RXDCTL_RLPMLMASK 0x00003FFF /* Only supported on the X540 */ +#define IXGBE_RXDCTL_RLPML_EN 0x00008000 #define IXGBE_FCTRL_SBP 0x00000002 /* Store Bad Packet */ #define IXGBE_FCTRL_MPE 0x00000100 /* Multicast Promiscuous Ena*/ diff --git a/drivers/net/ixgbevf/defines.h b/drivers/net/ixgbevf/defines.h index de643eb2ada6..78abb6f1a866 100644 --- a/drivers/net/ixgbevf/defines.h +++ b/drivers/net/ixgbevf/defines.h @@ -65,6 +65,8 @@ typedef u32 ixgbe_link_speed; #define IXGBE_RXCTRL_DMBYPS 0x00000002 /* Descriptor Monitor Bypass */ #define IXGBE_RXDCTL_ENABLE 0x02000000 /* Enable specific Rx Queue */ #define IXGBE_RXDCTL_VME 0x40000000 /* VLAN mode enable */ +#define IXGBE_RXDCTL_RLPMLMASK 0x00003FFF /* Only supported on the X540 */ +#define IXGBE_RXDCTL_RLPML_EN 0x00008000 /* DCA Control */ #define IXGBE_DCA_TXCTRL_TX_WB_RO_EN (1 << 11) /* Tx Desc writeback RO bit */ diff --git a/drivers/net/ixgbevf/ixgbevf_main.c b/drivers/net/ixgbevf/ixgbevf_main.c index 464e6c9d3fc2..43af761cdb16 100644 --- a/drivers/net/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ixgbevf/ixgbevf_main.c @@ -51,7 +51,7 @@ char ixgbevf_driver_name[] = "ixgbevf"; static const char ixgbevf_driver_string[] = "Intel(R) 82599 Virtual Function"; -#define DRV_VERSION "1.0.19-k0" +#define DRV_VERSION "1.1.0-k0" const char ixgbevf_driver_version[] = DRV_VERSION; static char ixgbevf_copyright[] = "Copyright (c) 2009 - 2010 Intel Corporation."; @@ -107,7 +107,7 @@ static inline void ixgbevf_release_rx_desc(struct ixgbe_hw *hw, } /* - * ixgbe_set_ivar - set the IVAR registers, mapping interrupt causes to vectors + * ixgbevf_set_ivar - set IVAR registers - maps interrupt causes to vectors * @adapter: pointer to adapter struct * @direction: 0 for Rx, 1 for Tx, -1 for other causes * @queue: queue to map the corresponding interrupt to @@ -1017,7 +1017,7 @@ static irqreturn_t ixgbevf_msix_clean_tx(int irq, void *data) } /** - * ixgbe_msix_clean_rx - single unshared vector rx clean (all queues) + * ixgbevf_msix_clean_rx - single unshared vector rx clean (all queues) * @irq: unused * @data: pointer to our q_vector struct for this interrupt vector **/ @@ -1665,6 +1665,11 @@ static int ixgbevf_up_complete(struct ixgbevf_adapter *adapter) j = adapter->rx_ring[i].reg_idx; rxdctl = IXGBE_READ_REG(hw, IXGBE_VFRXDCTL(j)); rxdctl |= IXGBE_RXDCTL_ENABLE; + if (hw->mac.type == ixgbe_mac_X540_vf) { + rxdctl &= ~IXGBE_RXDCTL_RLPMLMASK; + rxdctl |= ((netdev->mtu + ETH_HLEN + ETH_FCS_LEN) | + IXGBE_RXDCTL_RLPML_EN); + } IXGBE_WRITE_REG(hw, IXGBE_VFRXDCTL(j), rxdctl); ixgbevf_rx_desc_queue_enable(adapter, i); } @@ -1967,7 +1972,7 @@ static void ixgbevf_acquire_msix_vectors(struct ixgbevf_adapter *adapter, } /* - * ixgbe_set_num_queues: Allocate queues for device, feature dependant + * ixgbevf_set_num_queues: Allocate queues for device, feature dependant * @adapter: board private structure to initialize * * This is the top level queue allocation routine. The order here is very @@ -3217,10 +3222,16 @@ static int ixgbevf_set_mac(struct net_device *netdev, void *p) static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) { struct ixgbevf_adapter *adapter = netdev_priv(netdev); + struct ixgbe_hw *hw = &adapter->hw; int max_frame = new_mtu + ETH_HLEN + ETH_FCS_LEN; + int max_possible_frame = MAXIMUM_ETHERNET_VLAN_SIZE; + u32 msg[2]; + + if (adapter->hw.mac.type == ixgbe_mac_X540_vf) + max_possible_frame = IXGBE_MAX_JUMBO_FRAME_SIZE; /* MTU < 68 is an error and causes problems on some kernels */ - if ((new_mtu < 68) || (max_frame > MAXIMUM_ETHERNET_VLAN_SIZE)) + if ((new_mtu < 68) || (max_frame > max_possible_frame)) return -EINVAL; hw_dbg(&adapter->hw, "changing MTU from %d to %d\n", @@ -3228,6 +3239,10 @@ static int ixgbevf_change_mtu(struct net_device *netdev, int new_mtu) /* must set new MTU before calling down or up */ netdev->mtu = new_mtu; + msg[0] = IXGBE_VF_SET_LPE; + msg[1] = max_frame; + hw->mbx.ops.write_posted(hw, msg, 2); + if (netif_running(netdev)) ixgbevf_reinit_locked(adapter); @@ -3519,9 +3534,9 @@ static struct pci_driver ixgbevf_driver = { }; /** - * ixgbe_init_module - Driver Registration Routine + * ixgbevf_init_module - Driver Registration Routine * - * ixgbe_init_module is the first routine called when the driver is + * ixgbevf_init_module is the first routine called when the driver is * loaded. All it does is register with the PCI subsystem. **/ static int __init ixgbevf_init_module(void) @@ -3539,9 +3554,9 @@ static int __init ixgbevf_init_module(void) module_init(ixgbevf_init_module); /** - * ixgbe_exit_module - Driver Exit Cleanup Routine + * ixgbevf_exit_module - Driver Exit Cleanup Routine * - * ixgbe_exit_module is called just before the driver is removed + * ixgbevf_exit_module is called just before the driver is removed * from memory. **/ static void __exit ixgbevf_exit_module(void) @@ -3551,7 +3566,7 @@ static void __exit ixgbevf_exit_module(void) #ifdef DEBUG /** - * ixgbe_get_hw_dev_name - return device name string + * ixgbevf_get_hw_dev_name - return device name string * used by hardware layer to print debugging information **/ char *ixgbevf_get_hw_dev_name(struct ixgbe_hw *hw) diff --git a/drivers/net/qlcnic/qlcnic.h b/drivers/net/qlcnic/qlcnic.h index 44e316fd67b8..dc44564ef6f9 100644 --- a/drivers/net/qlcnic/qlcnic.h +++ b/drivers/net/qlcnic/qlcnic.h @@ -867,7 +867,6 @@ struct qlcnic_nic_intr_coalesce { #define LINKEVENT_LINKSPEED_MBPS 0 #define LINKEVENT_LINKSPEED_ENCODED 1 -#define AUTO_FW_RESET_ENABLED 0x01 /* firmware response header: * 63:58 - message type * 57:56 - owner @@ -1133,14 +1132,10 @@ struct qlcnic_eswitch { #define MAX_BW 100 /* % of link speed */ #define MAX_VLAN_ID 4095 #define MIN_VLAN_ID 2 -#define MAX_TX_QUEUES 1 -#define MAX_RX_QUEUES 4 #define DEFAULT_MAC_LEARN 1 #define IS_VALID_VLAN(vlan) (vlan >= MIN_VLAN_ID && vlan < MAX_VLAN_ID) #define IS_VALID_BW(bw) (bw <= MAX_BW) -#define IS_VALID_TX_QUEUES(que) (que > 0 && que <= MAX_TX_QUEUES) -#define IS_VALID_RX_QUEUES(que) (que > 0 && que <= MAX_RX_QUEUES) struct qlcnic_pci_func_cfg { u16 func_type; diff --git a/drivers/net/qlcnic/qlcnic_main.c b/drivers/net/qlcnic/qlcnic_main.c index 37c04b4fade3..cd88c7e1bfa9 100644 --- a/drivers/net/qlcnic/qlcnic_main.c +++ b/drivers/net/qlcnic/qlcnic_main.c @@ -42,7 +42,7 @@ static int use_msi_x = 1; module_param(use_msi_x, int, 0444); MODULE_PARM_DESC(use_msi_x, "MSI-X interrupt (0=disabled, 1=enabled"); -static int auto_fw_reset = AUTO_FW_RESET_ENABLED; +static int auto_fw_reset = 1; module_param(auto_fw_reset, int, 0644); MODULE_PARM_DESC(auto_fw_reset, "Auto firmware reset (0=disabled, 1=enabled"); @@ -2959,8 +2959,7 @@ qlcnic_check_health(struct qlcnic_adapter *adapter) if (adapter->need_fw_reset) goto detach; - if (adapter->reset_context && - auto_fw_reset == AUTO_FW_RESET_ENABLED) { + if (adapter->reset_context && auto_fw_reset) { qlcnic_reset_hw_context(adapter); adapter->netdev->trans_start = jiffies; } @@ -2973,7 +2972,7 @@ qlcnic_check_health(struct qlcnic_adapter *adapter) qlcnic_dev_request_reset(adapter); - if ((auto_fw_reset == AUTO_FW_RESET_ENABLED)) + if (auto_fw_reset) clear_bit(__QLCNIC_FW_ATTACHED, &adapter->state); dev_info(&netdev->dev, "firmware hang detected\n"); @@ -2982,7 +2981,7 @@ detach: adapter->dev_state = (state == QLCNIC_DEV_NEED_QUISCENT) ? state : QLCNIC_DEV_NEED_RESET; - if ((auto_fw_reset == AUTO_FW_RESET_ENABLED) && + if (auto_fw_reset && !test_and_set_bit(__QLCNIC_RESETTING, &adapter->state)) { qlcnic_schedule_work(adapter, qlcnic_detach_work, 0); @@ -3654,10 +3653,8 @@ validate_npar_config(struct qlcnic_adapter *adapter, if (adapter->npars[pci_func].type != QLCNIC_TYPE_NIC) return QL_STATUS_INVALID_PARAM; - if (!IS_VALID_BW(np_cfg[i].min_bw) - || !IS_VALID_BW(np_cfg[i].max_bw) - || !IS_VALID_RX_QUEUES(np_cfg[i].max_rx_queues) - || !IS_VALID_TX_QUEUES(np_cfg[i].max_tx_queues)) + if (!IS_VALID_BW(np_cfg[i].min_bw) || + !IS_VALID_BW(np_cfg[i].max_bw)) return QL_STATUS_INVALID_PARAM; } return 0; diff --git a/drivers/net/r6040.c b/drivers/net/r6040.c index 27e6f6d43cac..e3ebd90ae651 100644 --- a/drivers/net/r6040.c +++ b/drivers/net/r6040.c @@ -49,8 +49,8 @@ #include <asm/processor.h> #define DRV_NAME "r6040" -#define DRV_VERSION "0.26" -#define DRV_RELDATE "30May2010" +#define DRV_VERSION "0.27" +#define DRV_RELDATE "23Feb2011" /* PHY CHIP Address */ #define PHY1_ADDR 1 /* For MAC1 */ @@ -69,6 +69,8 @@ /* MAC registers */ #define MCR0 0x00 /* Control register 0 */ +#define MCR0_PROMISC 0x0020 /* Promiscuous mode */ +#define MCR0_HASH_EN 0x0100 /* Enable multicast hash table function */ #define MCR1 0x04 /* Control register 1 */ #define MAC_RST 0x0001 /* Reset the MAC */ #define MBCR 0x08 /* Bus control */ @@ -851,77 +853,92 @@ static void r6040_multicast_list(struct net_device *dev) { struct r6040_private *lp = netdev_priv(dev); void __iomem *ioaddr = lp->base; - u16 *adrp; - u16 reg; unsigned long flags; struct netdev_hw_addr *ha; int i; + u16 *adrp; + u16 hash_table[4] = { 0 }; + + spin_lock_irqsave(&lp->lock, flags); - /* MAC Address */ + /* Keep our MAC Address */ adrp = (u16 *)dev->dev_addr; iowrite16(adrp[0], ioaddr + MID_0L); iowrite16(adrp[1], ioaddr + MID_0M); iowrite16(adrp[2], ioaddr + MID_0H); - /* Promiscous Mode */ - spin_lock_irqsave(&lp->lock, flags); - /* Clear AMCP & PROM bits */ - reg = ioread16(ioaddr) & ~0x0120; - if (dev->flags & IFF_PROMISC) { - reg |= 0x0020; - lp->mcr0 |= 0x0020; - } - /* Too many multicast addresses - * accept all traffic */ - else if ((netdev_mc_count(dev) > MCAST_MAX) || - (dev->flags & IFF_ALLMULTI)) - reg |= 0x0020; + lp->mcr0 = ioread16(ioaddr + MCR0) & ~(MCR0_PROMISC | MCR0_HASH_EN); - iowrite16(reg, ioaddr); - spin_unlock_irqrestore(&lp->lock, flags); + /* Promiscuous mode */ + if (dev->flags & IFF_PROMISC) + lp->mcr0 |= MCR0_PROMISC; - /* Build the hash table */ - if (netdev_mc_count(dev) > MCAST_MAX) { - u16 hash_table[4]; - u32 crc; + /* Enable multicast hash table function to + * receive all multicast packets. */ + else if (dev->flags & IFF_ALLMULTI) { + lp->mcr0 |= MCR0_HASH_EN; - for (i = 0; i < 4; i++) - hash_table[i] = 0; + for (i = 0; i < MCAST_MAX ; i++) { + iowrite16(0, ioaddr + MID_1L + 8 * i); + iowrite16(0, ioaddr + MID_1M + 8 * i); + iowrite16(0, ioaddr + MID_1H + 8 * i); + } + for (i = 0; i < 4; i++) + hash_table[i] = 0xffff; + } + /* Use internal multicast address registers if the number of + * multicast addresses is not greater than MCAST_MAX. */ + else if (netdev_mc_count(dev) <= MCAST_MAX) { + i = 0; netdev_for_each_mc_addr(ha, dev) { - char *addrs = ha->addr; + u16 *adrp = (u16 *) ha->addr; + iowrite16(adrp[0], ioaddr + MID_1L + 8 * i); + iowrite16(adrp[1], ioaddr + MID_1M + 8 * i); + iowrite16(adrp[2], ioaddr + MID_1H + 8 * i); + i++; + } + while (i < MCAST_MAX) { + iowrite16(0, ioaddr + MID_1L + 8 * i); + iowrite16(0, ioaddr + MID_1M + 8 * i); + iowrite16(0, ioaddr + MID_1H + 8 * i); + i++; + } + } + /* Otherwise, Enable multicast hash table function. */ + else { + u32 crc; - if (!(*addrs & 1)) - continue; + lp->mcr0 |= MCR0_HASH_EN; + + for (i = 0; i < MCAST_MAX ; i++) { + iowrite16(0, ioaddr + MID_1L + 8 * i); + iowrite16(0, ioaddr + MID_1M + 8 * i); + iowrite16(0, ioaddr + MID_1H + 8 * i); + } - crc = ether_crc_le(6, addrs); + /* Build multicast hash table */ + netdev_for_each_mc_addr(ha, dev) { + u8 *addrs = ha->addr; + + crc = ether_crc(ETH_ALEN, addrs); crc >>= 26; - hash_table[crc >> 4] |= 1 << (15 - (crc & 0xf)); + hash_table[crc >> 4] |= 1 << (crc & 0xf); } - /* Fill the MAC hash tables with their values */ + } + + iowrite16(lp->mcr0, ioaddr + MCR0); + + /* Fill the MAC hash tables with their values */ + if (lp->mcr0 && MCR0_HASH_EN) { iowrite16(hash_table[0], ioaddr + MAR0); iowrite16(hash_table[1], ioaddr + MAR1); iowrite16(hash_table[2], ioaddr + MAR2); iowrite16(hash_table[3], ioaddr + MAR3); } - /* Multicast Address 1~4 case */ - i = 0; - netdev_for_each_mc_addr(ha, dev) { - if (i >= MCAST_MAX) - break; - adrp = (u16 *) ha->addr; - iowrite16(adrp[0], ioaddr + MID_1L + 8 * i); - iowrite16(adrp[1], ioaddr + MID_1M + 8 * i); - iowrite16(adrp[2], ioaddr + MID_1H + 8 * i); - i++; - } - while (i < MCAST_MAX) { - iowrite16(0xffff, ioaddr + MID_1L + 8 * i); - iowrite16(0xffff, ioaddr + MID_1M + 8 * i); - iowrite16(0xffff, ioaddr + MID_1H + 8 * i); - i++; - } + + spin_unlock_irqrestore(&lp->lock, flags); } static void netdev_get_drvinfo(struct net_device *dev, diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index 54d776c2c1b5..aac3e2eeb4fd 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -591,6 +591,9 @@ struct ethtool_sfeatures { * Probably there are other device-specific constraints on some features * in the set. When %ETHTOOL_F_UNSUPPORTED is set, .valid is considered * here as though ignored bits were cleared. + * %ETHTOOL_F_COMPAT - some or all changes requested were made by calling + * compatibility functions. Requested offload state cannot be properly + * managed by kernel. * * Meaning of bits in the masks are obtained by %ETHTOOL_GSSET_INFO (number of * bits in the arrays - always multiple of 32) and %ETHTOOL_GSTRINGS commands @@ -600,10 +603,12 @@ struct ethtool_sfeatures { enum ethtool_sfeatures_retval_bits { ETHTOOL_F_UNSUPPORTED__BIT, ETHTOOL_F_WISH__BIT, + ETHTOOL_F_COMPAT__BIT, }; #define ETHTOOL_F_UNSUPPORTED (1 << ETHTOOL_F_UNSUPPORTED__BIT) #define ETHTOOL_F_WISH (1 << ETHTOOL_F_WISH__BIT) +#define ETHTOOL_F_COMPAT (1 << ETHTOOL_F_COMPAT__BIT) #ifdef __KERNEL__ diff --git a/include/linux/pkt_sched.h b/include/linux/pkt_sched.h index d4bb6f58c90c..b1032a3fafdc 100644 --- a/include/linux/pkt_sched.h +++ b/include/linux/pkt_sched.h @@ -464,6 +464,7 @@ enum { TCA_NETEM_DELAY_DIST, TCA_NETEM_REORDER, TCA_NETEM_CORRUPT, + TCA_NETEM_LOSS, __TCA_NETEM_MAX, }; @@ -494,7 +495,33 @@ struct tc_netem_corrupt { __u32 correlation; }; +enum { + NETEM_LOSS_UNSPEC, + NETEM_LOSS_GI, /* General Intuitive - 4 state model */ + NETEM_LOSS_GE, /* Gilbert Elliot models */ + __NETEM_LOSS_MAX +}; +#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1) + +/* State transition probablities for 4 state model */ +struct tc_netem_gimodel { + __u32 p13; + __u32 p31; + __u32 p32; + __u32 p14; + __u32 p23; +}; + +/* Gilbert-Elliot models */ +struct tc_netem_gemodel { + __u32 p; + __u32 r; + __u32 h; + __u32 k1; +}; + #define NETEM_DIST_SCALE 8192 +#define NETEM_DIST_MAX 16384 /* DRR */ @@ -522,4 +549,43 @@ struct tc_mqprio_qopt { __u16 offset[TC_QOPT_MAX_QUEUE]; }; +/* SFB */ + +enum { + TCA_SFB_UNSPEC, + TCA_SFB_PARMS, + __TCA_SFB_MAX, +}; + +#define TCA_SFB_MAX (__TCA_SFB_MAX - 1) + +/* + * Note: increment, decrement are Q0.16 fixed-point values. + */ +struct tc_sfb_qopt { + __u32 rehash_interval; /* delay between hash move, in ms */ + __u32 warmup_time; /* double buffering warmup time in ms (warmup_time < rehash_interval) */ + __u32 max; /* max len of qlen_min */ + __u32 bin_size; /* maximum queue length per bin */ + __u32 increment; /* probability increment, (d1 in Blue) */ + __u32 decrement; /* probability decrement, (d2 in Blue) */ + __u32 limit; /* max SFB queue length */ + __u32 penalty_rate; /* inelastic flows are rate limited to 'rate' pps */ + __u32 penalty_burst; +}; + +struct tc_sfb_xstats { + __u32 earlydrop; + __u32 penaltydrop; + __u32 bucketdrop; + __u32 queuedrop; + __u32 childdrop; /* drops in child qdisc */ + __u32 marked; + __u32 maxqlen; + __u32 maxprob; + __u32 avgprob; +}; + +#define SFB_MAX_PROB 0xFFFF + #endif diff --git a/include/linux/security.h b/include/linux/security.h index b2b7f9749f5e..9b5f184a7f65 100644 --- a/include/linux/security.h +++ b/include/linux/security.h @@ -1623,7 +1623,7 @@ struct security_operations { int (*xfrm_policy_lookup) (struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); int (*xfrm_state_pol_flow_match) (struct xfrm_state *x, struct xfrm_policy *xp, - struct flowi *fl); + const struct flowi *fl); int (*xfrm_decode_session) (struct sk_buff *skb, u32 *secid, int ckall); #endif /* CONFIG_SECURITY_NETWORK_XFRM */ @@ -2761,7 +2761,8 @@ int security_xfrm_state_delete(struct xfrm_state *x); void security_xfrm_state_free(struct xfrm_state *x); int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); int security_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl); + struct xfrm_policy *xp, + const struct flowi *fl); int security_xfrm_decode_session(struct sk_buff *skb, u32 *secid); void security_skb_classify_flow(struct sk_buff *skb, struct flowi *fl); @@ -2813,7 +2814,7 @@ static inline int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_s } static inline int security_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl) + struct xfrm_policy *xp, const struct flowi *fl) { return 1; } diff --git a/include/linux/tipc.h b/include/linux/tipc.h index 1eefa3f6d1f4..a5b994a204d2 100644 --- a/include/linux/tipc.h +++ b/include/linux/tipc.h @@ -2,7 +2,7 @@ * include/linux/tipc.h: Include file for TIPC socket interface * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -130,12 +130,6 @@ static inline unsigned int tipc_node(__u32 addr) #define TIPC_SUB_PORTS 0x01 /* filter for port availability */ #define TIPC_SUB_SERVICE 0x02 /* filter for service availability */ #define TIPC_SUB_CANCEL 0x04 /* cancel a subscription */ -#if 0 -/* The following filter options are not currently implemented */ -#define TIPC_SUB_NO_BIND_EVTS 0x04 /* filter out "publish" events */ -#define TIPC_SUB_NO_UNBIND_EVTS 0x08 /* filter out "withdraw" events */ -#define TIPC_SUB_SINGLE_EVT 0x10 /* expire after first event */ -#endif #define TIPC_WAIT_FOREVER (~0) /* timeout for permanent subscription */ diff --git a/include/linux/tipc_config.h b/include/linux/tipc_config.h index 7d42460a5e3c..011556fcef04 100644 --- a/include/linux/tipc_config.h +++ b/include/linux/tipc_config.h @@ -2,7 +2,7 @@ * include/linux/tipc_config.h: Include file for TIPC configuration interface * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems + * Copyright (c) 2005-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -76,13 +76,6 @@ #define TIPC_CMD_SHOW_LINK_STATS 0x000B /* tx link_name, rx ultra_string */ #define TIPC_CMD_SHOW_STATS 0x000F /* tx unsigned, rx ultra_string */ -#if 0 -#define TIPC_CMD_SHOW_PORT_STATS 0x0008 /* tx port_ref, rx ultra_string */ -#define TIPC_CMD_RESET_PORT_STATS 0x0009 /* tx port_ref, rx none */ -#define TIPC_CMD_GET_ROUTES 0x000A /* tx ?, rx ? */ -#define TIPC_CMD_GET_LINK_PEER 0x000D /* tx link_name, rx ? */ -#endif - /* * Protected commands: * May only be issued by "network administration capable" process. @@ -109,13 +102,6 @@ #define TIPC_CMD_DUMP_LOG 0x410B /* tx none, rx ultra_string */ #define TIPC_CMD_RESET_LINK_STATS 0x410C /* tx link_name, rx none */ -#if 0 -#define TIPC_CMD_CREATE_LINK 0x4103 /* tx link_create, rx none */ -#define TIPC_CMD_REMOVE_LINK 0x4104 /* tx link_name, rx none */ -#define TIPC_CMD_BLOCK_LINK 0x4105 /* tx link_name, rx none */ -#define TIPC_CMD_UNBLOCK_LINK 0x4106 /* tx link_name, rx none */ -#endif - /* * Private commands: * May only be issued by "network administration capable" process. @@ -123,9 +109,6 @@ */ #define TIPC_CMD_SET_NODE_ADDR 0x8001 /* tx net_addr, rx none */ -#if 0 -#define TIPC_CMD_SET_ZONE_MASTER 0x8002 /* tx none, rx none */ -#endif #define TIPC_CMD_SET_REMOTE_MNG 0x8003 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PORTS 0x8004 /* tx unsigned, rx none */ #define TIPC_CMD_SET_MAX_PUBL 0x8005 /* tx unsigned, rx none */ @@ -193,6 +176,10 @@ #define TIPC_DEF_LINK_TOL 1500 #define TIPC_MAX_LINK_TOL 30000 +#if (TIPC_MIN_LINK_TOL < 16) +#error "TIPC_MIN_LINK_TOL is too small (abort limit may be NaN)" +#endif + /* * Link window limits (min, default, max), in packets */ @@ -247,15 +234,6 @@ struct tipc_name_table_query { #define TIPC_CFG_NOT_SUPPORTED "\x84" /* request is not supported by TIPC */ #define TIPC_CFG_INVALID_VALUE "\x85" /* request has invalid argument value */ -#if 0 -/* prototypes TLV structures for proposed commands */ -struct tipc_link_create { - __u32 domain; - struct tipc_media_addr peer_addr; - char bearer_name[TIPC_MAX_BEARER_NAME]; -}; -#endif - /* * A TLV consists of a descriptor, followed by the TLV value. * TLV descriptor fields are stored in network byte order; diff --git a/include/net/dst.h b/include/net/dst.h index 23b564d3e110..4fedffd7c56f 100644 --- a/include/net/dst.h +++ b/include/net/dst.h @@ -428,20 +428,22 @@ enum { struct flowi; #ifndef CONFIG_XFRM static inline int xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags) + const struct flowi *fl, struct sock *sk, + int flags) { return 0; } static inline int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags) + const struct flowi *fl, struct sock *sk, + int flags) { return 0; } #else extern int xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags); + const struct flowi *fl, struct sock *sk, int flags); extern int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, - struct flowi *fl, struct sock *sk, int flags); + const struct flowi *fl, struct sock *sk, int flags); #endif #endif diff --git a/include/net/flow.h b/include/net/flow.h index 1ae901f24436..f2080e65276d 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -102,17 +102,18 @@ struct flow_cache_ops { }; typedef struct flow_cache_object *(*flow_resolve_t)( - struct net *net, struct flowi *key, u16 family, + struct net *net, const struct flowi *key, u16 family, u8 dir, struct flow_cache_object *oldobj, void *ctx); extern struct flow_cache_object *flow_cache_lookup( - struct net *net, struct flowi *key, u16 family, + struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx); extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; -static inline int flow_cache_uli_match(struct flowi *fl1, struct flowi *fl2) +static inline int flow_cache_uli_match(const struct flowi *fl1, + const struct flowi *fl2) { return (fl1->proto == fl2->proto && !memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u))); diff --git a/include/net/route.h b/include/net/route.h index bf790c1c6ac8..b3f89ad04e0b 100644 --- a/include/net/route.h +++ b/include/net/route.h @@ -200,16 +200,19 @@ static inline int ip_route_connect(struct rtable **rp, __be32 dst, } static inline int ip_route_newports(struct rtable **rp, u8 protocol, + __be16 orig_sport, __be16 orig_dport, __be16 sport, __be16 dport, struct sock *sk) { - if (sport != (*rp)->fl.fl_ip_sport || - dport != (*rp)->fl.fl_ip_dport) { - struct flowi fl; - - memcpy(&fl, &(*rp)->fl, sizeof(fl)); - fl.fl_ip_sport = sport; - fl.fl_ip_dport = dport; - fl.proto = protocol; + if (sport != orig_sport || dport != orig_dport) { + struct flowi fl = { .oif = (*rp)->fl.oif, + .mark = (*rp)->fl.mark, + .fl4_dst = (*rp)->fl.fl4_dst, + .fl4_src = (*rp)->fl.fl4_src, + .fl4_tos = (*rp)->fl.fl4_tos, + .proto = (*rp)->fl.proto, + .fl_ip_sport = sport, + .fl_ip_dport = dport }; + if (inet_sk(sk)->transparent) fl.flags |= FLOWI_FLAG_ANYSRC; if (protocol == IPPROTO_TCP) diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 1f6e8a0eb544..44dccfcf9204 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -267,25 +267,25 @@ struct xfrm_policy_afinfo { struct dst_ops *dst_ops; void (*garbage_collect)(struct net *net); struct dst_entry *(*dst_lookup)(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr); + const xfrm_address_t *saddr, + const xfrm_address_t *daddr); int (*get_saddr)(struct net *net, xfrm_address_t *saddr, xfrm_address_t *daddr); void (*decode_session)(struct sk_buff *skb, struct flowi *fl, int reverse); - int (*get_tos)(struct flowi *fl); + int (*get_tos)(const struct flowi *fl); int (*init_path)(struct xfrm_dst *path, struct dst_entry *dst, int nfheader_len); int (*fill_dst)(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl); + const struct flowi *fl); }; extern int xfrm_policy_register_afinfo(struct xfrm_policy_afinfo *afinfo); extern int xfrm_policy_unregister_afinfo(struct xfrm_policy_afinfo *afinfo); -extern void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c); -extern void km_state_notify(struct xfrm_state *x, struct km_event *c); +extern void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c); +extern void km_state_notify(struct xfrm_state *x, const struct km_event *c); struct xfrm_tmpl; extern int km_query(struct xfrm_state *x, struct xfrm_tmpl *t, struct xfrm_policy *pol); @@ -300,9 +300,12 @@ struct xfrm_state_afinfo { const struct xfrm_type *type_map[IPPROTO_MAX]; struct xfrm_mode *mode_map[XFRM_MODE_MAX]; int (*init_flags)(struct xfrm_state *x); - void (*init_tempsel)(struct xfrm_selector *sel, struct flowi *fl); - void (*init_temprop)(struct xfrm_state *x, struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr); + void (*init_tempsel)(struct xfrm_selector *sel, + const struct flowi *fl); + void (*init_temprop)(struct xfrm_state *x, + const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr); int (*tmpl_sort)(struct xfrm_tmpl **dst, struct xfrm_tmpl **src, int n); int (*state_sort)(struct xfrm_state **dst, struct xfrm_state **src, int n); int (*output)(struct sk_buff *skb); @@ -333,7 +336,8 @@ struct xfrm_type { void (*destructor)(struct xfrm_state *); int (*input)(struct xfrm_state *, struct sk_buff *skb); int (*output)(struct xfrm_state *, struct sk_buff *pskb); - int (*reject)(struct xfrm_state *, struct sk_buff *, struct flowi *); + int (*reject)(struct xfrm_state *, struct sk_buff *, + const struct flowi *); int (*hdr_offset)(struct xfrm_state *, struct sk_buff *, u8 **); /* Estimate maximal size of result of transformation of a dgram */ u32 (*get_mtu)(struct xfrm_state *, int size); @@ -502,7 +506,7 @@ struct xfrm_policy { struct xfrm_tmpl xfrm_vec[XFRM_MAX_DEPTH]; }; -static inline struct net *xp_net(struct xfrm_policy *xp) +static inline struct net *xp_net(const struct xfrm_policy *xp) { return read_pnet(&xp->xp_net); } @@ -546,13 +550,17 @@ struct xfrm_migrate { struct xfrm_mgr { struct list_head list; char *id; - int (*notify)(struct xfrm_state *x, struct km_event *c); + int (*notify)(struct xfrm_state *x, const struct km_event *c); int (*acquire)(struct xfrm_state *x, struct xfrm_tmpl *, struct xfrm_policy *xp, int dir); struct xfrm_policy *(*compile_policy)(struct sock *sk, int opt, u8 *data, int len, int *dir); int (*new_mapping)(struct xfrm_state *x, xfrm_address_t *ipaddr, __be16 sport); - int (*notify_policy)(struct xfrm_policy *x, int dir, struct km_event *c); + int (*notify_policy)(struct xfrm_policy *x, int dir, const struct km_event *c); int (*report)(struct net *net, u8 proto, struct xfrm_selector *sel, xfrm_address_t *addr); - int (*migrate)(struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k); + int (*migrate)(const struct xfrm_selector *sel, + u8 dir, u8 type, + const struct xfrm_migrate *m, + int num_bundles, + const struct xfrm_kmaddress *k); }; extern int xfrm_register_km(struct xfrm_mgr *km); @@ -763,10 +771,11 @@ static inline void xfrm_state_hold(struct xfrm_state *x) atomic_inc(&x->refcnt); } -static __inline__ int addr_match(void *token1, void *token2, int prefixlen) +static inline bool addr_match(const void *token1, const void *token2, + int prefixlen) { - __be32 *a1 = token1; - __be32 *a2 = token2; + const __be32 *a1 = token1; + const __be32 *a2 = token2; int pdw; int pbi; @@ -775,7 +784,7 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) if (pdw) if (memcmp(a1, a2, pdw << 2)) - return 0; + return false; if (pbi) { __be32 mask; @@ -783,14 +792,14 @@ static __inline__ int addr_match(void *token1, void *token2, int prefixlen) mask = htonl((0xffffffff) << (32 - pbi)); if ((a1[pdw] ^ a2[pdw]) & mask) - return 0; + return false; } - return 1; + return true; } static __inline__ -__be16 xfrm_flowi_sport(struct flowi *fl) +__be16 xfrm_flowi_sport(const struct flowi *fl) { __be16 port; switch(fl->proto) { @@ -817,7 +826,7 @@ __be16 xfrm_flowi_sport(struct flowi *fl) } static __inline__ -__be16 xfrm_flowi_dport(struct flowi *fl) +__be16 xfrm_flowi_dport(const struct flowi *fl) { __be16 port; switch(fl->proto) { @@ -840,7 +849,8 @@ __be16 xfrm_flowi_dport(struct flowi *fl) return port; } -extern int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, +extern int xfrm_selector_match(const struct xfrm_selector *sel, + const struct flowi *fl, unsigned short family); #ifdef CONFIG_SECURITY_NETWORK_XFRM @@ -948,7 +958,7 @@ secpath_reset(struct sk_buff *skb) } static inline int -xfrm_addr_any(xfrm_address_t *addr, unsigned short family) +xfrm_addr_any(const xfrm_address_t *addr, unsigned short family) { switch (family) { case AF_INET: @@ -960,21 +970,21 @@ xfrm_addr_any(xfrm_address_t *addr, unsigned short family) } static inline int -__xfrm4_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x) +__xfrm4_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (tmpl->saddr.a4 && tmpl->saddr.a4 != x->props.saddr.a4); } static inline int -__xfrm6_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x) +__xfrm6_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x) { return (!ipv6_addr_any((struct in6_addr*)&tmpl->saddr) && ipv6_addr_cmp((struct in6_addr *)&tmpl->saddr, (struct in6_addr*)&x->props.saddr)); } static inline int -xfrm_state_addr_cmp(struct xfrm_tmpl *tmpl, struct xfrm_state *x, unsigned short family) +xfrm_state_addr_cmp(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { switch (family) { case AF_INET: @@ -1127,7 +1137,7 @@ static inline int xfrm6_policy_check_reverse(struct sock *sk, int dir, #endif static __inline__ -xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family) +xfrm_address_t *xfrm_flowi_daddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: @@ -1139,7 +1149,7 @@ xfrm_address_t *xfrm_flowi_daddr(struct flowi *fl, unsigned short family) } static __inline__ -xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family) +xfrm_address_t *xfrm_flowi_saddr(const struct flowi *fl, unsigned short family) { switch (family){ case AF_INET: @@ -1151,7 +1161,7 @@ xfrm_address_t *xfrm_flowi_saddr(struct flowi *fl, unsigned short family) } static __inline__ -void xfrm_flowi_addr_get(struct flowi *fl, +void xfrm_flowi_addr_get(const struct flowi *fl, xfrm_address_t *saddr, xfrm_address_t *daddr, unsigned short family) { @@ -1168,8 +1178,8 @@ void xfrm_flowi_addr_get(struct flowi *fl, } static __inline__ int -__xfrm4_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (daddr->a4 == x->id.daddr.a4 && (saddr->a4 == x->props.saddr.a4 || !saddr->a4 || !x->props.saddr.a4)) @@ -1178,8 +1188,8 @@ __xfrm4_state_addr_check(struct xfrm_state *x, } static __inline__ int -__xfrm6_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm6_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { if (!ipv6_addr_cmp((struct in6_addr *)daddr, (struct in6_addr *)&x->id.daddr) && (!ipv6_addr_cmp((struct in6_addr *)saddr, (struct in6_addr *)&x->props.saddr)|| @@ -1190,8 +1200,8 @@ __xfrm6_state_addr_check(struct xfrm_state *x, } static __inline__ int -xfrm_state_addr_check(struct xfrm_state *x, - xfrm_address_t *daddr, xfrm_address_t *saddr, +xfrm_state_addr_check(const struct xfrm_state *x, + const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { switch (family) { @@ -1204,23 +1214,23 @@ xfrm_state_addr_check(struct xfrm_state *x, } static __inline__ int -xfrm_state_addr_flow_check(struct xfrm_state *x, struct flowi *fl, +xfrm_state_addr_flow_check(const struct xfrm_state *x, const struct flowi *fl, unsigned short family) { switch (family) { case AF_INET: return __xfrm4_state_addr_check(x, - (xfrm_address_t *)&fl->fl4_dst, - (xfrm_address_t *)&fl->fl4_src); + (const xfrm_address_t *)&fl->fl4_dst, + (const xfrm_address_t *)&fl->fl4_src); case AF_INET6: return __xfrm6_state_addr_check(x, - (xfrm_address_t *)&fl->fl6_dst, - (xfrm_address_t *)&fl->fl6_src); + (const xfrm_address_t *)&fl->fl6_dst, + (const xfrm_address_t *)&fl->fl6_src); } return 0; } -static inline int xfrm_state_kern(struct xfrm_state *x) +static inline int xfrm_state_kern(const struct xfrm_state *x) { return atomic_read(&x->tunnel_users); } @@ -1324,8 +1334,10 @@ extern int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); extern void xfrm_state_walk_done(struct xfrm_state_walk *walk); extern struct xfrm_state *xfrm_state_alloc(struct net *net); -extern struct xfrm_state *xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, - struct flowi *fl, struct xfrm_tmpl *tmpl, +extern struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + const struct flowi *fl, + struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family); extern struct xfrm_state *xfrm_stateonly_find(struct net *net, u32 mark, @@ -1475,13 +1487,13 @@ struct xfrm_state *xfrm_find_acq(struct net *net, struct xfrm_mark *mark, extern int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol); #ifdef CONFIG_XFRM_MIGRATE -extern int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_bundles, - struct xfrm_kmaddress *k); +extern int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_bundles, + const struct xfrm_kmaddress *k); extern struct xfrm_state * xfrm_migrate_state_find(struct xfrm_migrate *m); extern struct xfrm_state * xfrm_state_migrate(struct xfrm_state *x, struct xfrm_migrate *m); -extern int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, +extern int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_bundles, struct xfrm_kmaddress *k); #endif @@ -1512,7 +1524,8 @@ struct scatterlist; typedef int (icv_update_fn_t)(struct hash_desc *, struct scatterlist *, unsigned int); -static inline int xfrm_addr_cmp(xfrm_address_t *a, xfrm_address_t *b, +static inline int xfrm_addr_cmp(const xfrm_address_t *a, + const xfrm_address_t *b, int family) { switch (family) { diff --git a/net/core/dev.c b/net/core/dev.c index 578415c1ef75..69a3c0817d6f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5476,14 +5476,14 @@ int register_netdevice(struct net_device *dev) * software offloads (GSO and GRO). */ dev->hw_features |= NETIF_F_SOFT_FEATURES; - dev->wanted_features = (dev->features & dev->hw_features) - | NETIF_F_SOFT_FEATURES; + dev->features |= NETIF_F_SOFT_FEATURES; + dev->wanted_features = dev->features & dev->hw_features; /* Avoid warning from netdev_fix_features() for GSO without SG */ - if (!(dev->wanted_features & NETIF_F_SG)) + if (!(dev->wanted_features & NETIF_F_SG)) { dev->wanted_features &= ~NETIF_F_GSO; - - netdev_update_features(dev); + dev->features &= ~NETIF_F_GSO; + } /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, * vlan_dev_init() will do the dev->features check, so these features @@ -5501,6 +5501,8 @@ int register_netdevice(struct net_device *dev) goto err_uninit; dev->reg_state = NETREG_REGISTERED; + netdev_update_features(dev); + /* * Default initial state at registry is that the * device is present. diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 66cdc76770ce..c1a71bb738da 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -168,6 +168,76 @@ EXPORT_SYMBOL(ethtool_ntuple_flush); #define ETHTOOL_DEV_FEATURE_WORDS 1 +static void ethtool_get_features_compat(struct net_device *dev, + struct ethtool_get_features_block *features) +{ + if (!dev->ethtool_ops) + return; + + /* getting RX checksum */ + if (dev->ethtool_ops->get_rx_csum) + if (dev->ethtool_ops->get_rx_csum(dev)) + features[0].active |= NETIF_F_RXCSUM; + + /* mark legacy-changeable features */ + if (dev->ethtool_ops->set_sg) + features[0].available |= NETIF_F_SG; + if (dev->ethtool_ops->set_tx_csum) + features[0].available |= NETIF_F_ALL_CSUM; + if (dev->ethtool_ops->set_tso) + features[0].available |= NETIF_F_ALL_TSO; + if (dev->ethtool_ops->set_rx_csum) + features[0].available |= NETIF_F_RXCSUM; + if (dev->ethtool_ops->set_flags) + features[0].available |= flags_dup_features; +} + +static int ethtool_set_feature_compat(struct net_device *dev, + int (*legacy_set)(struct net_device *, u32), + struct ethtool_set_features_block *features, u32 mask) +{ + u32 do_set; + + if (!legacy_set) + return 0; + + if (!(features[0].valid & mask)) + return 0; + + features[0].valid &= ~mask; + + do_set = !!(features[0].requested & mask); + + if (legacy_set(dev, do_set) < 0) + netdev_info(dev, + "Legacy feature change (%s) failed for 0x%08x\n", + do_set ? "set" : "clear", mask); + + return 1; +} + +static int ethtool_set_features_compat(struct net_device *dev, + struct ethtool_set_features_block *features) +{ + int compat; + + if (!dev->ethtool_ops) + return 0; + + compat = ethtool_set_feature_compat(dev, dev->ethtool_ops->set_sg, + features, NETIF_F_SG); + compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tx_csum, + features, NETIF_F_ALL_CSUM); + compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_tso, + features, NETIF_F_ALL_TSO); + compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_rx_csum, + features, NETIF_F_RXCSUM); + compat |= ethtool_set_feature_compat(dev, dev->ethtool_ops->set_flags, + features, flags_dup_features); + + return compat; +} + static int ethtool_get_features(struct net_device *dev, void __user *useraddr) { struct ethtool_gfeatures cmd = { @@ -185,6 +255,8 @@ static int ethtool_get_features(struct net_device *dev, void __user *useraddr) u32 __user *sizeaddr; u32 copy_size; + ethtool_get_features_compat(dev, features); + sizeaddr = useraddr + offsetof(struct ethtool_gfeatures, size); if (get_user(copy_size, sizeaddr)) return -EFAULT; @@ -220,6 +292,9 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) if (features[0].valid & ~NETIF_F_ETHTOOL_BITS) return -EINVAL; + if (ethtool_set_features_compat(dev, features)) + ret |= ETHTOOL_F_COMPAT; + if (features[0].valid & ~dev->hw_features) { features[0].valid &= dev->hw_features; ret |= ETHTOOL_F_UNSUPPORTED; diff --git a/net/core/flow.c b/net/core/flow.c index 127c8a7ffd61..990703b8863b 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -172,9 +172,9 @@ static void flow_new_hash_rnd(struct flow_cache *fc, static u32 flow_hash_code(struct flow_cache *fc, struct flow_cache_percpu *fcp, - struct flowi *key) + const struct flowi *key) { - u32 *k = (u32 *) key; + const u32 *k = (const u32 *) key; return jhash2(k, (sizeof(*key) / sizeof(u32)), fcp->hash_rnd) & (flow_cache_hash_size(fc) - 1); @@ -186,17 +186,17 @@ typedef unsigned long flow_compare_t; * important assumptions that we can here, such as alignment and * constant size. */ -static int flow_key_compare(struct flowi *key1, struct flowi *key2) +static int flow_key_compare(const struct flowi *key1, const struct flowi *key2) { - flow_compare_t *k1, *k1_lim, *k2; + const flow_compare_t *k1, *k1_lim, *k2; const int n_elem = sizeof(struct flowi) / sizeof(flow_compare_t); BUILD_BUG_ON(sizeof(struct flowi) % sizeof(flow_compare_t)); - k1 = (flow_compare_t *) key1; + k1 = (const flow_compare_t *) key1; k1_lim = k1 + n_elem; - k2 = (flow_compare_t *) key2; + k2 = (const flow_compare_t *) key2; do { if (*k1++ != *k2++) @@ -207,7 +207,7 @@ static int flow_key_compare(struct flowi *key1, struct flowi *key2) } struct flow_cache_object * -flow_cache_lookup(struct net *net, struct flowi *key, u16 family, u8 dir, +flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir, flow_resolve_t resolver, void *ctx) { struct flow_cache *fc = &flow_cache_global; diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index 45a434f94169..937989199c80 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -43,6 +43,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct dccp_sock *dp = dccp_sk(sk); const struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; + __be16 orig_sport, orig_dport; struct rtable *rt; __be32 daddr, nexthop; int tmp; @@ -63,10 +64,12 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = inet->opt->faddr; } + orig_sport = inet->inet_sport; + orig_dport = usin->sin_port; tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_DCCP, - inet->inet_sport, usin->sin_port, sk, 1); + orig_sport, orig_dport, sk, 1); if (tmp < 0) return tmp; @@ -99,8 +102,9 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err != 0) goto failure; - err = ip_route_newports(&rt, IPPROTO_DCCP, inet->inet_sport, - inet->inet_dport, sk); + err = ip_route_newports(&rt, IPPROTO_DCCP, + orig_sport, orig_dport, + inet->inet_sport, inet->inet_dport, sk); if (err != 0) goto failure; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index ef5a90beb9b0..27a0cc8cc888 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -149,6 +149,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) struct inet_sock *inet = inet_sk(sk); struct tcp_sock *tp = tcp_sk(sk); struct sockaddr_in *usin = (struct sockaddr_in *)uaddr; + __be16 orig_sport, orig_dport; struct rtable *rt; __be32 daddr, nexthop; int tmp; @@ -167,10 +168,12 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) nexthop = inet->opt->faddr; } + orig_sport = inet->inet_sport; + orig_dport = usin->sin_port; tmp = ip_route_connect(&rt, nexthop, inet->inet_saddr, RT_CONN_FLAGS(sk), sk->sk_bound_dev_if, IPPROTO_TCP, - inet->inet_sport, usin->sin_port, sk, 1); + orig_sport, orig_dport, sk, 1); if (tmp < 0) { if (tmp == -ENETUNREACH) IP_INC_STATS_BH(sock_net(sk), IPSTATS_MIB_OUTNOROUTES); @@ -234,6 +237,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) goto failure; err = ip_route_newports(&rt, IPPROTO_TCP, + orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); if (err) goto failure; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 19fbdec6baaa..63aa88efdcef 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -19,8 +19,8 @@ static struct xfrm_policy_afinfo xfrm4_policy_afinfo; static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr) + const xfrm_address_t *saddr, + const xfrm_address_t *daddr) { struct flowi fl = { .fl4_dst = daddr->a4, @@ -56,7 +56,7 @@ static int xfrm4_get_saddr(struct net *net, return 0; } -static int xfrm4_get_tos(struct flowi *fl) +static int xfrm4_get_tos(const struct flowi *fl) { return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */ } @@ -68,7 +68,7 @@ static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst, } static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl) + const struct flowi *fl) { struct rtable *rt = (struct rtable *)xdst->route; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 47947624eccc..983eff248988 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -21,7 +21,7 @@ static int xfrm4_init_flags(struct xfrm_state *x) } static void -__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +__xfrm4_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { sel->daddr.a4 = fl->fl4_dst; sel->saddr.a4 = fl->fl4_src; @@ -37,8 +37,8 @@ __xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) } static void -xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +xfrm4_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { x->id = tmpl->id; if (x->id.daddr.a4 == 0) diff --git a/net/ipv6/mip6.c b/net/ipv6/mip6.c index d6e9599d0705..f3e3ca938a54 100644 --- a/net/ipv6/mip6.c +++ b/net/ipv6/mip6.c @@ -203,7 +203,8 @@ static inline int mip6_report_rl_allow(struct timeval *stamp, return allow; } -static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, struct flowi *fl) +static int mip6_destopt_reject(struct xfrm_state *x, struct sk_buff *skb, + const struct flowi *fl) { struct net *net = xs_net(x); struct inet6_skb_parm *opt = (struct inet6_skb_parm *)skb->cb; diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 834dc02f1d4f..c128ca1affe3 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -27,8 +27,8 @@ static struct xfrm_policy_afinfo xfrm6_policy_afinfo; static struct dst_entry *xfrm6_dst_lookup(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr) + const xfrm_address_t *saddr, + const xfrm_address_t *daddr) { struct flowi fl = {}; struct dst_entry *dst; @@ -67,7 +67,7 @@ static int xfrm6_get_saddr(struct net *net, return 0; } -static int xfrm6_get_tos(struct flowi *fl) +static int xfrm6_get_tos(const struct flowi *fl) { return 0; } @@ -87,7 +87,7 @@ static int xfrm6_init_path(struct xfrm_dst *path, struct dst_entry *dst, } static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl) + const struct flowi *fl) { struct rt6_info *rt = (struct rt6_info*)xdst->route; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index a67575d472a3..a02598e0079a 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -20,7 +20,7 @@ #include <net/addrconf.h> static void -__xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +__xfrm6_init_tempsel(struct xfrm_selector *sel, const struct flowi *fl) { /* Initialize temporary selector matching only * to current session. */ @@ -38,8 +38,8 @@ __xfrm6_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) } static void -xfrm6_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, const xfrm_address_t *saddr) { x->id = tmpl->id; if (ipv6_addr_any((struct in6_addr*)&x->id.daddr)) diff --git a/net/key/af_key.c b/net/key/af_key.c index d87c22df6f1e..56372853142a 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -690,7 +690,7 @@ static inline int pfkey_mode_to_xfrm(int mode) } } -static unsigned int pfkey_sockaddr_fill(xfrm_address_t *xaddr, __be16 port, +static unsigned int pfkey_sockaddr_fill(const xfrm_address_t *xaddr, __be16 port, struct sockaddr *sa, unsigned short family) { @@ -1429,7 +1429,7 @@ static inline int event2keytype(int event) } /* ADD/UPD/DEL */ -static int key_notify_sa(struct xfrm_state *x, struct km_event *c) +static int key_notify_sa(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; @@ -1688,7 +1688,7 @@ static int unicast_flush_resp(struct sock *sk, struct sadb_msg *ihdr) return pfkey_broadcast(skb, GFP_ATOMIC, BROADCAST_ONE, sk, sock_net(sk)); } -static int key_notify_sa_flush(struct km_event *c) +static int key_notify_sa_flush(const struct km_event *c) { struct sk_buff *skb; struct sadb_msg *hdr; @@ -2123,7 +2123,7 @@ static int pfkey_xfrm_policy2msg(struct sk_buff *skb, struct xfrm_policy *xp, in return 0; } -static int key_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) +static int key_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; @@ -2660,7 +2660,7 @@ static int pfkey_spddump(struct sock *sk, struct sk_buff *skb, struct sadb_msg * return pfkey_do_dump(pfk); } -static int key_notify_policy_flush(struct km_event *c) +static int key_notify_policy_flush(const struct km_event *c) { struct sk_buff *skb_out; struct sadb_msg *hdr; @@ -2914,12 +2914,12 @@ static void dump_esp_combs(struct sk_buff *skb, struct xfrm_tmpl *t) } } -static int key_notify_policy_expire(struct xfrm_policy *xp, struct km_event *c) +static int key_notify_policy_expire(struct xfrm_policy *xp, const struct km_event *c) { return 0; } -static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c) +static int key_notify_sa_expire(struct xfrm_state *x, const struct km_event *c) { struct sk_buff *out_skb; struct sadb_msg *out_hdr; @@ -2949,7 +2949,7 @@ static int key_notify_sa_expire(struct xfrm_state *x, struct km_event *c) return 0; } -static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) +static int pfkey_send_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = x ? xs_net(x) : c->net; struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); @@ -2976,7 +2976,7 @@ static int pfkey_send_notify(struct xfrm_state *x, struct km_event *c) return 0; } -static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +static int pfkey_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { if (xp && xp->type != XFRM_POLICY_TYPE_MAIN) return 0; @@ -3318,7 +3318,7 @@ static int pfkey_send_new_mapping(struct xfrm_state *x, xfrm_address_t *ipaddr, #ifdef CONFIG_NET_KEY_MIGRATE static int set_sadb_address(struct sk_buff *skb, int sasize, int type, - struct xfrm_selector *sel) + const struct xfrm_selector *sel) { struct sadb_address *addr; addr = (struct sadb_address *)skb_put(skb, sizeof(struct sadb_address) + sasize); @@ -3348,7 +3348,7 @@ static int set_sadb_address(struct sk_buff *skb, int sasize, int type, } -static int set_sadb_kmaddress(struct sk_buff *skb, struct xfrm_kmaddress *k) +static int set_sadb_kmaddress(struct sk_buff *skb, const struct xfrm_kmaddress *k) { struct sadb_x_kmaddress *kma; u8 *sa; @@ -3376,7 +3376,7 @@ static int set_sadb_kmaddress(struct sk_buff *skb, struct xfrm_kmaddress *k) static int set_ipsecrequest(struct sk_buff *skb, uint8_t proto, uint8_t mode, int level, uint32_t reqid, uint8_t family, - xfrm_address_t *src, xfrm_address_t *dst) + const xfrm_address_t *src, const xfrm_address_t *dst) { struct sadb_x_ipsecrequest *rq; u8 *sa; @@ -3404,9 +3404,9 @@ static int set_ipsecrequest(struct sk_buff *skb, #endif #ifdef CONFIG_NET_KEY_MIGRATE -static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_bundles, - struct xfrm_kmaddress *k) +static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_bundles, + const struct xfrm_kmaddress *k) { int i; int sasize_sel; @@ -3415,7 +3415,7 @@ static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, struct sk_buff *skb; struct sadb_msg *hdr; struct sadb_x_policy *pol; - struct xfrm_migrate *mp; + const struct xfrm_migrate *mp; if (type != XFRM_POLICY_TYPE_MAIN) return 0; @@ -3513,9 +3513,9 @@ err: return -EINVAL; } #else -static int pfkey_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_bundles, - struct xfrm_kmaddress *k) +static int pfkey_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_bundles, + const struct xfrm_kmaddress *k) { return -ENOPROTOOPT; } @@ -3655,6 +3655,7 @@ static int pfkey_seq_show(struct seq_file *f, void *v) } static void *pfkey_seq_start(struct seq_file *f, loff_t *ppos) + __acquires(rcu) { struct net *net = seq_file_net(f); struct netns_pfkey *net_pfkey = net_generic(net, pfkey_net_id); @@ -3672,6 +3673,7 @@ static void *pfkey_seq_next(struct seq_file *f, void *v, loff_t *ppos) } static void pfkey_seq_stop(struct seq_file *f, void *v) + __releases(rcu) { rcu_read_unlock(); } diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 8c19b6e3201e..a7a5583d4f68 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -126,6 +126,17 @@ config NET_SCH_RED To compile this code as a module, choose M here: the module will be called sch_red. +config NET_SCH_SFB + tristate "Stochastic Fair Blue (SFB)" + ---help--- + Say Y here if you want to use the Stochastic Fair Blue (SFB) + packet scheduling algorithm. + + See the top of <file:net/sched/sch_sfb.c> for more details. + + To compile this code as a module, choose M here: the + module will be called sch_sfb. + config NET_SCH_SFQ tristate "Stochastic Fairness Queueing (SFQ)" ---help--- diff --git a/net/sched/Makefile b/net/sched/Makefile index 06c6cdfd1948..2e77b8dba22e 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -24,6 +24,7 @@ obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o +obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index 966920c14e7a..3b93fc0c8955 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -134,12 +134,12 @@ next_knode: for (i = n->sel.nkeys; i > 0; i--, key++) { int toff = off + key->off + (off2 & key->offmask); - __be32 *data, _data; + __be32 *data, hdata; if (skb_headroom(skb) + toff > INT_MAX) goto out; - data = skb_header_pointer(skb, toff, 4, &_data); + data = skb_header_pointer(skb, toff, 4, &hdata); if (!data) goto out; if ((*data ^ key->val) & key->mask) { @@ -187,10 +187,10 @@ check_terminal: ht = n->ht_down; sel = 0; if (ht->divisor) { - __be32 *data, _data; + __be32 *data, hdata; data = skb_header_pointer(skb, off + n->sel.hoff, 4, - &_data); + &hdata); if (!data) goto out; sel = ht->divisor & u32_hash_fold(*data, &n->sel, @@ -202,11 +202,11 @@ check_terminal: if (n->sel.flags & (TC_U32_OFFSET | TC_U32_VAROFFSET)) { off2 = n->sel.off + 3; if (n->sel.flags & TC_U32_VAROFFSET) { - __be16 *data, _data; + __be16 *data, hdata; data = skb_header_pointer(skb, off + n->sel.offoff, - 2, &_data); + 2, &hdata); if (!data) goto out; off2 += ntohs(n->sel.offmask & *data) >> diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index a889d099320f..e5e174782677 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -401,7 +401,7 @@ META_COLLECTOR(int_sk_sndbuf) META_COLLECTOR(int_sk_alloc) { SKIP_NONLOCAL(skb); - dst->value = skb->sk->sk_allocation; + dst->value = (__force int) skb->sk->sk_allocation; } META_COLLECTOR(int_sk_route_caps) diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index ee1e2090eebe..06afbaeb4c88 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -219,14 +219,25 @@ static bool choke_match_flow(struct sk_buff *skb1, return *ports1 == *ports2; } +struct choke_skb_cb { + u16 classid; +}; + +static inline struct choke_skb_cb *choke_skb_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(skb->cb) < + sizeof(struct qdisc_skb_cb) + sizeof(struct choke_skb_cb)); + return (struct choke_skb_cb *)qdisc_skb_cb(skb)->data; +} + static inline void choke_set_classid(struct sk_buff *skb, u16 classid) { - *(unsigned int *)(qdisc_skb_cb(skb)->data) = classid; + choke_skb_cb(skb)->classid = classid; } static u16 choke_get_classid(const struct sk_buff *skb) { - return *(unsigned int *)(qdisc_skb_cb(skb)->data); + return choke_skb_cb(skb)->classid; } /* diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index ace37f9f1cd0..ea17cbed29ef 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -311,7 +311,9 @@ static int mqprio_dump_class(struct Qdisc *sch, unsigned long cl, } static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, - struct gnet_dump *d) + struct gnet_dump *d) + __releases(d->lock) + __acquires(d->lock) { struct net_device *dev = qdisc_dev(sch); @@ -389,7 +391,7 @@ static const struct Qdisc_class_ops mqprio_class_ops = { .dump_stats = mqprio_dump_class_stats, }; -struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { +static struct Qdisc_ops mqprio_qdisc_ops __read_mostly = { .cl_ops = &mqprio_class_ops, .id = "mqprio", .priv_size = sizeof(struct mqprio_sched), diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index 64f0d3293b49..28b3f7e83517 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -24,7 +24,7 @@ #include <net/netlink.h> #include <net/pkt_sched.h> -#define VERSION "1.2" +#define VERSION "1.3" /* Network Emulation Queuing algorithm. ==================================== @@ -47,6 +47,20 @@ layering other disciplines. It does not need to do bandwidth control either since that can be handled by using token bucket or other rate control. + + Correlated Loss Generator models + + Added generation of correlated loss according to the + "Gilbert-Elliot" model, a 4-state markov model. + + References: + [1] NetemCLG Home http://netgroup.uniroma2.it/NetemCLG + [2] S. Salsano, F. Ludovici, A. Ordine, "Definition of a general + and intuitive loss model for packet networks and its implementation + in the Netem module in the Linux kernel", available in [1] + + Authors: Stefano Salsano <stefano.salsano at uniroma2.it + Fabio Ludovici <fabio.ludovici at yahoo.it> */ struct netem_sched_data { @@ -73,6 +87,26 @@ struct netem_sched_data { u32 size; s16 table[0]; } *delay_dist; + + enum { + CLG_RANDOM, + CLG_4_STATES, + CLG_GILB_ELL, + } loss_model; + + /* Correlated Loss Generation models */ + struct clgstate { + /* state of the Markov chain */ + u8 state; + + /* 4-states and Gilbert-Elliot models */ + u32 a1; /* p13 for 4-states or p for GE */ + u32 a2; /* p31 for 4-states or r for GE */ + u32 a3; /* p32 for 4-states or h for GE */ + u32 a4; /* p14 for 4-states or 1-k for GE */ + u32 a5; /* p23 used only in 4-states */ + } clg; + }; /* Time stamp put into socket buffer control block */ @@ -115,6 +149,122 @@ static u32 get_crandom(struct crndstate *state) return answer; } +/* loss_4state - 4-state model loss generator + * Generates losses according to the 4-state Markov chain adopted in + * the GI (General and Intuitive) loss model. + */ +static bool loss_4state(struct netem_sched_data *q) +{ + struct clgstate *clg = &q->clg; + u32 rnd = net_random(); + + /* + * Makes a comparision between rnd and the transition + * probabilities outgoing from the current state, then decides the + * next state and if the next packet has to be transmitted or lost. + * The four states correspond to: + * 1 => successfully transmitted packets within a gap period + * 4 => isolated losses within a gap period + * 3 => lost packets within a burst period + * 2 => successfully transmitted packets within a burst period + */ + switch (clg->state) { + case 1: + if (rnd < clg->a4) { + clg->state = 4; + return true; + } else if (clg->a4 < rnd && rnd < clg->a1) { + clg->state = 3; + return true; + } else if (clg->a1 < rnd) + clg->state = 1; + + break; + case 2: + if (rnd < clg->a5) { + clg->state = 3; + return true; + } else + clg->state = 2; + + break; + case 3: + if (rnd < clg->a3) + clg->state = 2; + else if (clg->a3 < rnd && rnd < clg->a2 + clg->a3) { + clg->state = 1; + return true; + } else if (clg->a2 + clg->a3 < rnd) { + clg->state = 3; + return true; + } + break; + case 4: + clg->state = 1; + break; + } + + return false; +} + +/* loss_gilb_ell - Gilbert-Elliot model loss generator + * Generates losses according to the Gilbert-Elliot loss model or + * its special cases (Gilbert or Simple Gilbert) + * + * Makes a comparision between random number and the transition + * probabilities outgoing from the current state, then decides the + * next state. A second random number is extracted and the comparision + * with the loss probability of the current state decides if the next + * packet will be transmitted or lost. + */ +static bool loss_gilb_ell(struct netem_sched_data *q) +{ + struct clgstate *clg = &q->clg; + + switch (clg->state) { + case 1: + if (net_random() < clg->a1) + clg->state = 2; + if (net_random() < clg->a4) + return true; + case 2: + if (net_random() < clg->a2) + clg->state = 1; + if (clg->a3 > net_random()) + return true; + } + + return false; +} + +static bool loss_event(struct netem_sched_data *q) +{ + switch (q->loss_model) { + case CLG_RANDOM: + /* Random packet drop 0 => none, ~0 => all */ + return q->loss && q->loss >= get_crandom(&q->loss_cor); + + case CLG_4_STATES: + /* 4state loss model algorithm (used also for GI model) + * Extracts a value from the markov 4 state loss generator, + * if it is 1 drops a packet and if needed writes the event in + * the kernel logs + */ + return loss_4state(q); + + case CLG_GILB_ELL: + /* Gilbert-Elliot loss model algorithm + * Extracts a value from the Gilbert-Elliot loss generator, + * if it is 1 drops a packet and if needed writes the event in + * the kernel logs + */ + return loss_gilb_ell(q); + } + + return false; /* not reached */ +} + + /* tabledist - return a pseudo-randomly distributed value with mean mu and * std deviation sigma. Uses table lookup to approximate the desired * distribution, and a uniformly-distributed pseudo-random source. @@ -161,14 +311,12 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) int ret; int count = 1; - pr_debug("netem_enqueue skb=%p\n", skb); - /* Random duplication */ if (q->duplicate && q->duplicate >= get_crandom(&q->dup_cor)) ++count; - /* Random packet drop 0 => none, ~0 => all */ - if (q->loss && q->loss >= get_crandom(&q->loss_cor)) + /* Drop packet? */ + if (loss_event(q)) --count; if (count == 0) { @@ -238,14 +386,15 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch) ret = NET_XMIT_SUCCESS; } - if (likely(ret == NET_XMIT_SUCCESS)) { - sch->q.qlen++; - } else if (net_xmit_drop_count(ret)) { - sch->qstats.drops++; + if (ret != NET_XMIT_SUCCESS) { + if (net_xmit_drop_count(ret)) { + sch->qstats.drops++; + return ret; + } } - pr_debug("netem: enqueue ret %d\n", ret); - return ret; + sch->q.qlen++; + return NET_XMIT_SUCCESS; } static unsigned int netem_drop(struct Qdisc *sch) @@ -287,9 +436,10 @@ static struct sk_buff *netem_dequeue(struct Qdisc *sch) if (G_TC_FROM(skb->tc_verd) & AT_INGRESS) skb->tstamp.tv64 = 0; #endif - pr_debug("netem_dequeue: return skb=%p\n", skb); - qdisc_bstats_update(sch, skb); + sch->q.qlen--; + qdisc_unthrottled(sch); + qdisc_bstats_update(sch, skb); return skb; } @@ -308,6 +458,16 @@ static void netem_reset(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); } +static void dist_free(struct disttable *d) +{ + if (d) { + if (is_vmalloc_addr(d)) + vfree(d); + else + kfree(d); + } +} + /* * Distribution data is a variable size payload containing * signed 16 bit values. @@ -315,16 +475,20 @@ static void netem_reset(struct Qdisc *sch) static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) { struct netem_sched_data *q = qdisc_priv(sch); - unsigned long n = nla_len(attr)/sizeof(__s16); + size_t n = nla_len(attr)/sizeof(__s16); const __s16 *data = nla_data(attr); spinlock_t *root_lock; struct disttable *d; int i; + size_t s; - if (n > 65536) + if (n > NETEM_DIST_MAX) return -EINVAL; - d = kmalloc(sizeof(*d) + n*sizeof(d->table[0]), GFP_KERNEL); + s = sizeof(struct disttable) + n * sizeof(s16); + d = kmalloc(s, GFP_KERNEL); + if (!d) + d = vmalloc(s); if (!d) return -ENOMEM; @@ -335,7 +499,7 @@ static int get_dist_table(struct Qdisc *sch, const struct nlattr *attr) root_lock = qdisc_root_sleeping_lock(sch); spin_lock_bh(root_lock); - kfree(q->delay_dist); + dist_free(q->delay_dist); q->delay_dist = d; spin_unlock_bh(root_lock); return 0; @@ -369,10 +533,66 @@ static void get_corrupt(struct Qdisc *sch, const struct nlattr *attr) init_crandom(&q->corrupt_cor, r->correlation); } +static int get_loss_clg(struct Qdisc *sch, const struct nlattr *attr) +{ + struct netem_sched_data *q = qdisc_priv(sch); + const struct nlattr *la; + int rem; + + nla_for_each_nested(la, attr, rem) { + u16 type = nla_type(la); + + switch(type) { + case NETEM_LOSS_GI: { + const struct tc_netem_gimodel *gi = nla_data(la); + + if (nla_len(la) != sizeof(struct tc_netem_gimodel)) { + pr_info("netem: incorrect gi model size\n"); + return -EINVAL; + } + + q->loss_model = CLG_4_STATES; + + q->clg.state = 1; + q->clg.a1 = gi->p13; + q->clg.a2 = gi->p31; + q->clg.a3 = gi->p32; + q->clg.a4 = gi->p14; + q->clg.a5 = gi->p23; + break; + } + + case NETEM_LOSS_GE: { + const struct tc_netem_gemodel *ge = nla_data(la); + + if (nla_len(la) != sizeof(struct tc_netem_gemodel)) { + pr_info("netem: incorrect gi model size\n"); + return -EINVAL; + } + + q->loss_model = CLG_GILB_ELL; + q->clg.state = 1; + q->clg.a1 = ge->p; + q->clg.a2 = ge->r; + q->clg.a3 = ge->h; + q->clg.a4 = ge->k1; + break; + } + + default: + pr_info("netem: unknown loss type %u\n", type); + return -EINVAL; + } + } + + return 0; +} + static const struct nla_policy netem_policy[TCA_NETEM_MAX + 1] = { [TCA_NETEM_CORR] = { .len = sizeof(struct tc_netem_corr) }, [TCA_NETEM_REORDER] = { .len = sizeof(struct tc_netem_reorder) }, [TCA_NETEM_CORRUPT] = { .len = sizeof(struct tc_netem_corrupt) }, + [TCA_NETEM_LOSS] = { .type = NLA_NESTED }, }; static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, @@ -380,11 +600,15 @@ static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla, { int nested_len = nla_len(nla) - NLA_ALIGN(len); - if (nested_len < 0) + if (nested_len < 0) { + pr_info("netem: invalid attributes len %d\n", nested_len); return -EINVAL; + } + if (nested_len >= nla_attr_size(0)) return nla_parse(tb, maxtype, nla_data(nla) + NLA_ALIGN(len), nested_len, policy); + memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1)); return 0; } @@ -407,7 +631,7 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) ret = fifo_set_limit(q->qdisc, qopt->limit); if (ret) { - pr_debug("netem: can't set fifo limit\n"); + pr_info("netem: can't set fifo limit\n"); return ret; } @@ -440,7 +664,11 @@ static int netem_change(struct Qdisc *sch, struct nlattr *opt) if (tb[TCA_NETEM_CORRUPT]) get_corrupt(sch, tb[TCA_NETEM_CORRUPT]); - return 0; + q->loss_model = CLG_RANDOM; + if (tb[TCA_NETEM_LOSS]) + ret = get_loss_clg(sch, tb[TCA_NETEM_LOSS]); + + return ret; } /* @@ -535,16 +763,17 @@ static int netem_init(struct Qdisc *sch, struct nlattr *opt) qdisc_watchdog_init(&q->watchdog, sch); + q->loss_model = CLG_RANDOM; q->qdisc = qdisc_create_dflt(sch->dev_queue, &tfifo_qdisc_ops, TC_H_MAKE(sch->handle, 1)); if (!q->qdisc) { - pr_debug("netem: qdisc create failed\n"); + pr_notice("netem: qdisc create tfifo qdisc failed\n"); return -ENOMEM; } ret = netem_change(sch, opt); if (ret) { - pr_debug("netem: change failed\n"); + pr_info("netem: change failed\n"); qdisc_destroy(q->qdisc); } return ret; @@ -556,14 +785,61 @@ static void netem_destroy(struct Qdisc *sch) qdisc_watchdog_cancel(&q->watchdog); qdisc_destroy(q->qdisc); - kfree(q->delay_dist); + dist_free(q->delay_dist); +} + +static int dump_loss_model(const struct netem_sched_data *q, + struct sk_buff *skb) +{ + struct nlattr *nest; + + nest = nla_nest_start(skb, TCA_NETEM_LOSS); + if (nest == NULL) + goto nla_put_failure; + + switch (q->loss_model) { + case CLG_RANDOM: + /* legacy loss model */ + nla_nest_cancel(skb, nest); + return 0; /* no data */ + + case CLG_4_STATES: { + struct tc_netem_gimodel gi = { + .p13 = q->clg.a1, + .p31 = q->clg.a2, + .p32 = q->clg.a3, + .p14 = q->clg.a4, + .p23 = q->clg.a5, + }; + + NLA_PUT(skb, NETEM_LOSS_GI, sizeof(gi), &gi); + break; + } + case CLG_GILB_ELL: { + struct tc_netem_gemodel ge = { + .p = q->clg.a1, + .r = q->clg.a2, + .h = q->clg.a3, + .k1 = q->clg.a4, + }; + + NLA_PUT(skb, NETEM_LOSS_GE, sizeof(ge), &ge); + break; + } + } + + nla_nest_end(skb, nest); + return 0; + +nla_put_failure: + nla_nest_cancel(skb, nest); + return -1; } static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) { const struct netem_sched_data *q = qdisc_priv(sch); - unsigned char *b = skb_tail_pointer(skb); - struct nlattr *nla = (struct nlattr *) b; + struct nlattr *nla = (struct nlattr *) skb_tail_pointer(skb); struct tc_netem_qopt qopt; struct tc_netem_corr cor; struct tc_netem_reorder reorder; @@ -590,17 +866,87 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) corrupt.correlation = q->corrupt_cor.rho; NLA_PUT(skb, TCA_NETEM_CORRUPT, sizeof(corrupt), &corrupt); - nla->nla_len = skb_tail_pointer(skb) - b; + if (dump_loss_model(q, skb) != 0) + goto nla_put_failure; - return skb->len; + return nla_nest_end(skb, nla); nla_put_failure: - nlmsg_trim(skb, b); + nlmsg_trim(skb, nla); return -1; } +static int netem_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + struct netem_sched_data *q = qdisc_priv(sch); + + if (cl != 1) /* only one class */ + return -ENOENT; + + tcm->tcm_handle |= TC_H_MIN(1); + tcm->tcm_info = q->qdisc->handle; + + return 0; +} + +static int netem_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old) +{ + struct netem_sched_data *q = qdisc_priv(sch); + + if (new == NULL) + new = &noop_qdisc; + + sch_tree_lock(sch); + *old = q->qdisc; + q->qdisc = new; + qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); + qdisc_reset(*old); + sch_tree_unlock(sch); + + return 0; +} + +static struct Qdisc *netem_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct netem_sched_data *q = qdisc_priv(sch); + return q->qdisc; +} + +static unsigned long netem_get(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void netem_put(struct Qdisc *sch, unsigned long arg) +{ +} + +static void netem_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + if (walker->count >= walker->skip) + if (walker->fn(sch, 1, walker) < 0) { + walker->stop = 1; + return; + } + walker->count++; + } +} + +static const struct Qdisc_class_ops netem_class_ops = { + .graft = netem_graft, + .leaf = netem_leaf, + .get = netem_get, + .put = netem_put, + .walk = netem_walk, + .dump = netem_dump_class, +}; + static struct Qdisc_ops netem_qdisc_ops __read_mostly = { .id = "netem", + .cl_ops = &netem_class_ops, .priv_size = sizeof(struct netem_sched_data), .enqueue = netem_enqueue, .dequeue = netem_dequeue, diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c new file mode 100644 index 000000000000..0a833d0c1f61 --- /dev/null +++ b/net/sched/sch_sfb.c @@ -0,0 +1,709 @@ +/* + * net/sched/sch_sfb.c Stochastic Fair Blue + * + * Copyright (c) 2008-2011 Juliusz Chroboczek <jch@pps.jussieu.fr> + * Copyright (c) 2011 Eric Dumazet <eric.dumazet@gmail.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * version 2 as published by the Free Software Foundation. + * + * W. Feng, D. Kandlur, D. Saha, K. Shin. Blue: + * A New Class of Active Queue Management Algorithms. + * U. Michigan CSE-TR-387-99, April 1999. + * + * http://www.thefengs.com/wuchang/blue/CSE-TR-387-99.pdf + * + */ + +#include <linux/module.h> +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/skbuff.h> +#include <linux/random.h> +#include <linux/jhash.h> +#include <net/ip.h> +#include <net/pkt_sched.h> +#include <net/inet_ecn.h> + +/* + * SFB uses two B[l][n] : L x N arrays of bins (L levels, N bins per level) + * This implementation uses L = 8 and N = 16 + * This permits us to split one 32bit hash (provided per packet by rxhash or + * external classifier) into 8 subhashes of 4 bits. + */ +#define SFB_BUCKET_SHIFT 4 +#define SFB_NUMBUCKETS (1 << SFB_BUCKET_SHIFT) /* N bins per Level */ +#define SFB_BUCKET_MASK (SFB_NUMBUCKETS - 1) +#define SFB_LEVELS (32 / SFB_BUCKET_SHIFT) /* L */ + +/* SFB algo uses a virtual queue, named "bin" */ +struct sfb_bucket { + u16 qlen; /* length of virtual queue */ + u16 p_mark; /* marking probability */ +}; + +/* We use a double buffering right before hash change + * (Section 4.4 of SFB reference : moving hash functions) + */ +struct sfb_bins { + u32 perturbation; /* jhash perturbation */ + struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; +}; + +struct sfb_sched_data { + struct Qdisc *qdisc; + struct tcf_proto *filter_list; + unsigned long rehash_interval; + unsigned long warmup_time; /* double buffering warmup time in jiffies */ + u32 max; + u32 bin_size; /* maximum queue length per bin */ + u32 increment; /* d1 */ + u32 decrement; /* d2 */ + u32 limit; /* HARD maximal queue length */ + u32 penalty_rate; + u32 penalty_burst; + u32 tokens_avail; + unsigned long rehash_time; + unsigned long token_time; + + u8 slot; /* current active bins (0 or 1) */ + bool double_buffering; + struct sfb_bins bins[2]; + + struct { + u32 earlydrop; + u32 penaltydrop; + u32 bucketdrop; + u32 queuedrop; + u32 childdrop; /* drops in child qdisc */ + u32 marked; /* ECN mark */ + } stats; +}; + +/* + * Each queued skb might be hashed on one or two bins + * We store in skb_cb the two hash values. + * (A zero value means double buffering was not used) + */ +struct sfb_skb_cb { + u32 hashes[2]; +}; + +static inline struct sfb_skb_cb *sfb_skb_cb(const struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(skb->cb) < + sizeof(struct qdisc_skb_cb) + sizeof(struct sfb_skb_cb)); + return (struct sfb_skb_cb *)qdisc_skb_cb(skb)->data; +} + +/* + * If using 'internal' SFB flow classifier, hash comes from skb rxhash + * If using external classifier, hash comes from the classid. + */ +static u32 sfb_hash(const struct sk_buff *skb, u32 slot) +{ + return sfb_skb_cb(skb)->hashes[slot]; +} + +/* Probabilities are coded as Q0.16 fixed-point values, + * with 0xFFFF representing 65535/65536 (almost 1.0) + * Addition and subtraction are saturating in [0, 65535] + */ +static u32 prob_plus(u32 p1, u32 p2) +{ + u32 res = p1 + p2; + + return min_t(u32, res, SFB_MAX_PROB); +} + +static u32 prob_minus(u32 p1, u32 p2) +{ + return p1 > p2 ? p1 - p2 : 0; +} + +static void increment_one_qlen(u32 sfbhash, u32 slot, struct sfb_sched_data *q) +{ + int i; + struct sfb_bucket *b = &q->bins[slot].bins[0][0]; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b[hash].qlen < 0xFFFF) + b[hash].qlen++; + b += SFB_NUMBUCKETS; /* next level */ + } +} + +static void increment_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +{ + u32 sfbhash; + + sfbhash = sfb_hash(skb, 0); + if (sfbhash) + increment_one_qlen(sfbhash, 0, q); + + sfbhash = sfb_hash(skb, 1); + if (sfbhash) + increment_one_qlen(sfbhash, 1, q); +} + +static void decrement_one_qlen(u32 sfbhash, u32 slot, + struct sfb_sched_data *q) +{ + int i; + struct sfb_bucket *b = &q->bins[slot].bins[0][0]; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b[hash].qlen > 0) + b[hash].qlen--; + b += SFB_NUMBUCKETS; /* next level */ + } +} + +static void decrement_qlen(const struct sk_buff *skb, struct sfb_sched_data *q) +{ + u32 sfbhash; + + sfbhash = sfb_hash(skb, 0); + if (sfbhash) + decrement_one_qlen(sfbhash, 0, q); + + sfbhash = sfb_hash(skb, 1); + if (sfbhash) + decrement_one_qlen(sfbhash, 1, q); +} + +static void decrement_prob(struct sfb_bucket *b, struct sfb_sched_data *q) +{ + b->p_mark = prob_minus(b->p_mark, q->decrement); +} + +static void increment_prob(struct sfb_bucket *b, struct sfb_sched_data *q) +{ + b->p_mark = prob_plus(b->p_mark, q->increment); +} + +static void sfb_zero_all_buckets(struct sfb_sched_data *q) +{ + memset(&q->bins, 0, sizeof(q->bins)); +} + +/* + * compute max qlen, max p_mark, and avg p_mark + */ +static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_data *q) +{ + int i; + u32 qlen = 0, prob = 0, totalpm = 0; + const struct sfb_bucket *b = &q->bins[q->slot].bins[0][0]; + + for (i = 0; i < SFB_LEVELS * SFB_NUMBUCKETS; i++) { + if (qlen < b->qlen) + qlen = b->qlen; + totalpm += b->p_mark; + if (prob < b->p_mark) + prob = b->p_mark; + b++; + } + *prob_r = prob; + *avgpm_r = totalpm / (SFB_LEVELS * SFB_NUMBUCKETS); + return qlen; +} + + +static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) +{ + q->bins[slot].perturbation = net_random(); +} + +static void sfb_swap_slot(struct sfb_sched_data *q) +{ + sfb_init_perturbation(q->slot, q); + q->slot ^= 1; + q->double_buffering = false; +} + +/* Non elastic flows are allowed to use part of the bandwidth, expressed + * in "penalty_rate" packets per second, with "penalty_burst" burst + */ +static bool sfb_rate_limit(struct sk_buff *skb, struct sfb_sched_data *q) +{ + if (q->penalty_rate == 0 || q->penalty_burst == 0) + return true; + + if (q->tokens_avail < 1) { + unsigned long age = min(10UL * HZ, jiffies - q->token_time); + + q->tokens_avail = (age * q->penalty_rate) / HZ; + if (q->tokens_avail > q->penalty_burst) + q->tokens_avail = q->penalty_burst; + q->token_time = jiffies; + if (q->tokens_avail < 1) + return true; + } + + q->tokens_avail--; + return false; +} + +static bool sfb_classify(struct sk_buff *skb, struct sfb_sched_data *q, + int *qerr, u32 *salt) +{ + struct tcf_result res; + int result; + + result = tc_classify(skb, q->filter_list, &res); + if (result >= 0) { +#ifdef CONFIG_NET_CLS_ACT + switch (result) { + case TC_ACT_STOLEN: + case TC_ACT_QUEUED: + *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; + case TC_ACT_SHOT: + return false; + } +#endif + *salt = TC_H_MIN(res.classid); + return true; + } + return false; +} + +static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch) +{ + + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + int i; + u32 p_min = ~0; + u32 minqlen = ~0; + u32 r, slot, salt, sfbhash; + int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; + + if (q->rehash_interval > 0) { + unsigned long limit = q->rehash_time + q->rehash_interval; + + if (unlikely(time_after(jiffies, limit))) { + sfb_swap_slot(q); + q->rehash_time = jiffies; + } else if (unlikely(!q->double_buffering && q->warmup_time > 0 && + time_after(jiffies, limit - q->warmup_time))) { + q->double_buffering = true; + } + } + + if (q->filter_list) { + /* If using external classifiers, get result and record it. */ + if (!sfb_classify(skb, q, &ret, &salt)) + goto other_drop; + } else { + salt = skb_get_rxhash(skb); + } + + slot = q->slot; + + sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + if (!sfbhash) + sfbhash = 1; + sfb_skb_cb(skb)->hashes[slot] = sfbhash; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + struct sfb_bucket *b = &q->bins[slot].bins[i][hash]; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b->qlen == 0) + decrement_prob(b, q); + else if (b->qlen >= q->bin_size) + increment_prob(b, q); + if (minqlen > b->qlen) + minqlen = b->qlen; + if (p_min > b->p_mark) + p_min = b->p_mark; + } + + slot ^= 1; + sfb_skb_cb(skb)->hashes[slot] = 0; + + if (unlikely(minqlen >= q->max || sch->q.qlen >= q->limit)) { + sch->qstats.overlimits++; + if (minqlen >= q->max) + q->stats.bucketdrop++; + else + q->stats.queuedrop++; + goto drop; + } + + if (unlikely(p_min >= SFB_MAX_PROB)) { + /* Inelastic flow */ + if (q->double_buffering) { + sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + if (!sfbhash) + sfbhash = 1; + sfb_skb_cb(skb)->hashes[slot] = sfbhash; + + for (i = 0; i < SFB_LEVELS; i++) { + u32 hash = sfbhash & SFB_BUCKET_MASK; + struct sfb_bucket *b = &q->bins[slot].bins[i][hash]; + + sfbhash >>= SFB_BUCKET_SHIFT; + if (b->qlen == 0) + decrement_prob(b, q); + else if (b->qlen >= q->bin_size) + increment_prob(b, q); + } + } + if (sfb_rate_limit(skb, q)) { + sch->qstats.overlimits++; + q->stats.penaltydrop++; + goto drop; + } + goto enqueue; + } + + r = net_random() & SFB_MAX_PROB; + + if (unlikely(r < p_min)) { + if (unlikely(p_min > SFB_MAX_PROB / 2)) { + /* If we're marking that many packets, then either + * this flow is unresponsive, or we're badly congested. + * In either case, we want to start dropping packets. + */ + if (r < (p_min - SFB_MAX_PROB / 2) * 2) { + q->stats.earlydrop++; + goto drop; + } + } + if (INET_ECN_set_ce(skb)) { + q->stats.marked++; + } else { + q->stats.earlydrop++; + goto drop; + } + } + +enqueue: + ret = qdisc_enqueue(skb, child); + if (likely(ret == NET_XMIT_SUCCESS)) { + sch->q.qlen++; + increment_qlen(skb, q); + } else if (net_xmit_drop_count(ret)) { + q->stats.childdrop++; + sch->qstats.drops++; + } + return ret; + +drop: + qdisc_drop(skb, sch); + return NET_XMIT_CN; +other_drop: + if (ret & __NET_XMIT_BYPASS) + sch->qstats.drops++; + kfree_skb(skb); + return ret; +} + +static struct sk_buff *sfb_dequeue(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + struct sk_buff *skb; + + skb = child->dequeue(q->qdisc); + + if (skb) { + qdisc_bstats_update(sch, skb); + sch->q.qlen--; + decrement_qlen(skb, q); + } + + return skb; +} + +static struct sk_buff *sfb_peek(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child = q->qdisc; + + return child->ops->peek(child); +} + +/* No sfb_drop -- impossible since the child doesn't return the dropped skb. */ + +static void sfb_reset(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + qdisc_reset(q->qdisc); + sch->q.qlen = 0; + q->slot = 0; + q->double_buffering = false; + sfb_zero_all_buckets(q); + sfb_init_perturbation(0, q); +} + +static void sfb_destroy(struct Qdisc *sch) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + tcf_destroy_chain(&q->filter_list); + qdisc_destroy(q->qdisc); +} + +static const struct nla_policy sfb_policy[TCA_SFB_MAX + 1] = { + [TCA_SFB_PARMS] = { .len = sizeof(struct tc_sfb_qopt) }, +}; + +static const struct tc_sfb_qopt sfb_default_ops = { + .rehash_interval = 600 * MSEC_PER_SEC, + .warmup_time = 60 * MSEC_PER_SEC, + .limit = 0, + .max = 25, + .bin_size = 20, + .increment = (SFB_MAX_PROB + 500) / 1000, /* 0.1 % */ + .decrement = (SFB_MAX_PROB + 3000) / 6000, + .penalty_rate = 10, + .penalty_burst = 20, +}; + +static int sfb_change(struct Qdisc *sch, struct nlattr *opt) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct Qdisc *child; + struct nlattr *tb[TCA_SFB_MAX + 1]; + const struct tc_sfb_qopt *ctl = &sfb_default_ops; + u32 limit; + int err; + + if (opt) { + err = nla_parse_nested(tb, TCA_SFB_MAX, opt, sfb_policy); + if (err < 0) + return -EINVAL; + + if (tb[TCA_SFB_PARMS] == NULL) + return -EINVAL; + + ctl = nla_data(tb[TCA_SFB_PARMS]); + } + + limit = ctl->limit; + if (limit == 0) + limit = max_t(u32, qdisc_dev(sch)->tx_queue_len, 1); + + child = fifo_create_dflt(sch, &pfifo_qdisc_ops, limit); + if (IS_ERR(child)) + return PTR_ERR(child); + + sch_tree_lock(sch); + + qdisc_tree_decrease_qlen(q->qdisc, q->qdisc->q.qlen); + qdisc_destroy(q->qdisc); + q->qdisc = child; + + q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); + q->warmup_time = msecs_to_jiffies(ctl->warmup_time); + q->rehash_time = jiffies; + q->limit = limit; + q->increment = ctl->increment; + q->decrement = ctl->decrement; + q->max = ctl->max; + q->bin_size = ctl->bin_size; + q->penalty_rate = ctl->penalty_rate; + q->penalty_burst = ctl->penalty_burst; + q->tokens_avail = ctl->penalty_burst; + q->token_time = jiffies; + + q->slot = 0; + q->double_buffering = false; + sfb_zero_all_buckets(q); + sfb_init_perturbation(0, q); + sfb_init_perturbation(1, q); + + sch_tree_unlock(sch); + + return 0; +} + +static int sfb_init(struct Qdisc *sch, struct nlattr *opt) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + q->qdisc = &noop_qdisc; + return sfb_change(sch, opt); +} + +static int sfb_dump(struct Qdisc *sch, struct sk_buff *skb) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct nlattr *opts; + struct tc_sfb_qopt opt = { + .rehash_interval = jiffies_to_msecs(q->rehash_interval), + .warmup_time = jiffies_to_msecs(q->warmup_time), + .limit = q->limit, + .max = q->max, + .bin_size = q->bin_size, + .increment = q->increment, + .decrement = q->decrement, + .penalty_rate = q->penalty_rate, + .penalty_burst = q->penalty_burst, + }; + + sch->qstats.backlog = q->qdisc->qstats.backlog; + opts = nla_nest_start(skb, TCA_OPTIONS); + NLA_PUT(skb, TCA_SFB_PARMS, sizeof(opt), &opt); + return nla_nest_end(skb, opts); + +nla_put_failure: + nla_nest_cancel(skb, opts); + return -EMSGSIZE; +} + +static int sfb_dump_stats(struct Qdisc *sch, struct gnet_dump *d) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + struct tc_sfb_xstats st = { + .earlydrop = q->stats.earlydrop, + .penaltydrop = q->stats.penaltydrop, + .bucketdrop = q->stats.bucketdrop, + .queuedrop = q->stats.queuedrop, + .childdrop = q->stats.childdrop, + .marked = q->stats.marked, + }; + + st.maxqlen = sfb_compute_qlen(&st.maxprob, &st.avgprob, q); + + return gnet_stats_copy_app(d, &st, sizeof(st)); +} + +static int sfb_dump_class(struct Qdisc *sch, unsigned long cl, + struct sk_buff *skb, struct tcmsg *tcm) +{ + return -ENOSYS; +} + +static int sfb_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, + struct Qdisc **old) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + if (new == NULL) + new = &noop_qdisc; + + sch_tree_lock(sch); + *old = q->qdisc; + q->qdisc = new; + qdisc_tree_decrease_qlen(*old, (*old)->q.qlen); + qdisc_reset(*old); + sch_tree_unlock(sch); + return 0; +} + +static struct Qdisc *sfb_leaf(struct Qdisc *sch, unsigned long arg) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + return q->qdisc; +} + +static unsigned long sfb_get(struct Qdisc *sch, u32 classid) +{ + return 1; +} + +static void sfb_put(struct Qdisc *sch, unsigned long arg) +{ +} + +static int sfb_change_class(struct Qdisc *sch, u32 classid, u32 parentid, + struct nlattr **tca, unsigned long *arg) +{ + return -ENOSYS; +} + +static int sfb_delete(struct Qdisc *sch, unsigned long cl) +{ + return -ENOSYS; +} + +static void sfb_walk(struct Qdisc *sch, struct qdisc_walker *walker) +{ + if (!walker->stop) { + if (walker->count >= walker->skip) + if (walker->fn(sch, 1, walker) < 0) { + walker->stop = 1; + return; + } + walker->count++; + } +} + +static struct tcf_proto **sfb_find_tcf(struct Qdisc *sch, unsigned long cl) +{ + struct sfb_sched_data *q = qdisc_priv(sch); + + if (cl) + return NULL; + return &q->filter_list; +} + +static unsigned long sfb_bind(struct Qdisc *sch, unsigned long parent, + u32 classid) +{ + return 0; +} + + +static const struct Qdisc_class_ops sfb_class_ops = { + .graft = sfb_graft, + .leaf = sfb_leaf, + .get = sfb_get, + .put = sfb_put, + .change = sfb_change_class, + .delete = sfb_delete, + .walk = sfb_walk, + .tcf_chain = sfb_find_tcf, + .bind_tcf = sfb_bind, + .unbind_tcf = sfb_put, + .dump = sfb_dump_class, +}; + +static struct Qdisc_ops sfb_qdisc_ops __read_mostly = { + .id = "sfb", + .priv_size = sizeof(struct sfb_sched_data), + .cl_ops = &sfb_class_ops, + .enqueue = sfb_enqueue, + .dequeue = sfb_dequeue, + .peek = sfb_peek, + .init = sfb_init, + .reset = sfb_reset, + .destroy = sfb_destroy, + .change = sfb_change, + .dump = sfb_dump, + .dump_stats = sfb_dump_stats, + .owner = THIS_MODULE, +}; + +static int __init sfb_module_init(void) +{ + return register_qdisc(&sfb_qdisc_ops); +} + +static void __exit sfb_module_exit(void) +{ + unregister_qdisc(&sfb_qdisc_ops); +} + +module_init(sfb_module_init) +module_exit(sfb_module_exit) + +MODULE_DESCRIPTION("Stochastic Fair Blue queue discipline"); +MODULE_AUTHOR("Juliusz Chroboczek"); +MODULE_AUTHOR("Eric Dumazet"); +MODULE_LICENSE("GPL"); diff --git a/net/socket.c b/net/socket.c index 9fa1e3b4366e..937d0fcf74bc 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2648,7 +2648,8 @@ static int bond_ioctl(struct net *net, unsigned int cmd, old_fs = get_fs(); set_fs(KERNEL_DS); - err = dev_ioctl(net, cmd, &kifr); + err = dev_ioctl(net, cmd, + (struct ifreq __user __force *) &kifr); set_fs(old_fs); return err; @@ -2757,7 +2758,7 @@ static int compat_sioc_ifmap(struct net *net, unsigned int cmd, old_fs = get_fs(); set_fs(KERNEL_DS); - err = dev_ioctl(net, cmd, (void __user *)&ifr); + err = dev_ioctl(net, cmd, (void __user __force *)&ifr); set_fs(old_fs); if (cmd == SIOCGIFMAP && !err) { @@ -2862,7 +2863,8 @@ static int routing_ioctl(struct net *net, struct socket *sock, ret |= __get_user(rtdev, &(ur4->rt_dev)); if (rtdev) { ret |= copy_from_user(devname, compat_ptr(rtdev), 15); - r4.rt_dev = devname; devname[15] = 0; + r4.rt_dev = (char __user __force *)devname; + devname[15] = 0; } else r4.rt_dev = NULL; diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 70ab5ef48766..7dc1dc7151ea 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -3,7 +3,7 @@ * * Copyright (c) 2004-2006, Ericsson AB * Copyright (c) 2004, Intel Corporation. - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -61,8 +61,8 @@ */ struct bcbearer_pair { - struct bearer *primary; - struct bearer *secondary; + struct tipc_bearer *primary; + struct tipc_bearer *secondary; }; /** @@ -81,7 +81,7 @@ struct bcbearer_pair { */ struct bcbearer { - struct bearer bearer; + struct tipc_bearer bearer; struct media media; struct bcbearer_pair bpairs[MAX_BEARERS]; struct bcbearer_pair bpairs_temp[TIPC_MAX_LINK_PRI + 1]; @@ -93,6 +93,7 @@ struct bcbearer { * struct bclink - link used for broadcast messages * @link: (non-standard) broadcast link structure * @node: (non-standard) node structure representing b'cast link's peer node + * @retransmit_to: node that most recently requested a retransmit * * Handles sequence numbering, fragmentation, bundling, etc. */ @@ -100,6 +101,7 @@ struct bcbearer { struct bclink { struct link link; struct tipc_node node; + struct tipc_node *retransmit_to; }; @@ -184,6 +186,17 @@ static int bclink_ack_allowed(u32 n) /** + * tipc_bclink_retransmit_to - get most recent node to request retransmission + * + * Called with bc_lock locked + */ + +struct tipc_node *tipc_bclink_retransmit_to(void) +{ + return bclink->retransmit_to; +} + +/** * bclink_retransmit_pkt - retransmit broadcast packets * @after: sequence number of last packet to *not* retransmit * @to: sequence number of last packet to retransmit @@ -285,6 +298,7 @@ static void bclink_send_nack(struct tipc_node *n_ptr) msg = buf_msg(buf); tipc_msg_init(msg, BCAST_PROTOCOL, STATE_MSG, INT_H_SIZE, n_ptr->addr); + msg_set_non_seq(msg, 1); msg_set_mc_netid(msg, tipc_net_id); msg_set_bcast_ack(msg, mod(n_ptr->bclink.last_in)); msg_set_bcgap_after(msg, n_ptr->bclink.gap_after); @@ -405,8 +419,6 @@ int tipc_bclink_send_msg(struct sk_buff *buf) else bclink_set_last_sent(); - if (bcl->out_queue_size > bcl->stats.max_queue_sz) - bcl->stats.max_queue_sz = bcl->out_queue_size; bcl->stats.queue_sz_counts++; bcl->stats.accu_queue_sz += bcl->out_queue_size; @@ -444,10 +456,9 @@ void tipc_bclink_recv_pkt(struct sk_buff *buf) tipc_node_unlock(node); spin_lock_bh(&bc_lock); bcl->stats.recv_nacks++; - bcl->owner->next = node; /* remember requestor */ + bclink->retransmit_to = node; bclink_retransmit_pkt(msg_bcgap_after(msg), msg_bcgap_to(msg)); - bcl->owner->next = NULL; spin_unlock_bh(&bc_lock); } else { tipc_bclink_peek_nack(msg_destnode(msg), @@ -574,8 +585,8 @@ static int tipc_bcbearer_send(struct sk_buff *buf, bcbearer->remains = tipc_bcast_nmap; for (bp_index = 0; bp_index < MAX_BEARERS; bp_index++) { - struct bearer *p = bcbearer->bpairs[bp_index].primary; - struct bearer *s = bcbearer->bpairs[bp_index].secondary; + struct tipc_bearer *p = bcbearer->bpairs[bp_index].primary; + struct tipc_bearer *s = bcbearer->bpairs[bp_index].secondary; if (!p) break; /* no more bearers to try */ @@ -584,11 +595,11 @@ static int tipc_bcbearer_send(struct sk_buff *buf, if (bcbearer->remains_new.count == bcbearer->remains.count) continue; /* bearer pair doesn't add anything */ - if (p->publ.blocked || - p->media->send_msg(buf, &p->publ, &p->media->bcast_addr)) { + if (p->blocked || + p->media->send_msg(buf, p, &p->media->bcast_addr)) { /* unable to send on primary bearer */ - if (!s || s->publ.blocked || - s->media->send_msg(buf, &s->publ, + if (!s || s->blocked || + s->media->send_msg(buf, s, &s->media->bcast_addr)) { /* unable to send on either bearer */ continue; @@ -633,7 +644,7 @@ void tipc_bcbearer_sort(void) memset(bp_temp, 0, sizeof(bcbearer->bpairs_temp)); for (b_index = 0; b_index < MAX_BEARERS; b_index++) { - struct bearer *b = &tipc_bearers[b_index]; + struct tipc_bearer *b = &tipc_bearers[b_index]; if (!b->active || !b->nodes.count) continue; @@ -682,12 +693,12 @@ void tipc_bcbearer_sort(void) void tipc_bcbearer_push(void) { - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; spin_lock_bh(&bc_lock); b_ptr = &bcbearer->bearer; - if (b_ptr->publ.blocked) { - b_ptr->publ.blocked = 0; + if (b_ptr->blocked) { + b_ptr->blocked = 0; tipc_bearer_lock_push(b_ptr); } spin_unlock_bh(&bc_lock); diff --git a/net/tipc/bcast.h b/net/tipc/bcast.h index 51f8c5326ce6..500c97f1c859 100644 --- a/net/tipc/bcast.h +++ b/net/tipc/bcast.h @@ -2,7 +2,7 @@ * net/tipc/bcast.h: Include file for TIPC broadcast code * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -90,6 +90,7 @@ void tipc_port_list_free(struct port_list *pl_ptr); int tipc_bclink_init(void); void tipc_bclink_stop(void); +struct tipc_node *tipc_bclink_retransmit_to(void); void tipc_bclink_acknowledge(struct tipc_node *n_ptr, u32 acked); int tipc_bclink_send_msg(struct sk_buff *buf); void tipc_bclink_recv_pkt(struct sk_buff *buf); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 837b7a467885..f2839b0f6b65 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -2,7 +2,7 @@ * net/tipc/bearer.c: TIPC bearer code * * Copyright (c) 1996-2006, Ericsson AB - * Copyright (c) 2004-2006, Wind River Systems + * Copyright (c) 2004-2006, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -44,7 +44,7 @@ static struct media media_list[MAX_MEDIA]; static u32 media_count; -struct bearer tipc_bearers[MAX_BEARERS]; +struct tipc_bearer tipc_bearers[MAX_BEARERS]; /** * media_name_valid - validate media name @@ -278,13 +278,13 @@ static int bearer_name_validate(const char *name, * bearer_find - locates bearer object with matching bearer name */ -static struct bearer *bearer_find(const char *name) +static struct tipc_bearer *bearer_find(const char *name) { - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; u32 i; for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) { - if (b_ptr->active && (!strcmp(b_ptr->publ.name, name))) + if (b_ptr->active && (!strcmp(b_ptr->name, name))) return b_ptr; } return NULL; @@ -294,16 +294,16 @@ static struct bearer *bearer_find(const char *name) * tipc_bearer_find_interface - locates bearer object with matching interface name */ -struct bearer *tipc_bearer_find_interface(const char *if_name) +struct tipc_bearer *tipc_bearer_find_interface(const char *if_name) { - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; char *b_if_name; u32 i; for (i = 0, b_ptr = tipc_bearers; i < MAX_BEARERS; i++, b_ptr++) { if (!b_ptr->active) continue; - b_if_name = strchr(b_ptr->publ.name, ':') + 1; + b_if_name = strchr(b_ptr->name, ':') + 1; if (!strcmp(b_if_name, if_name)) return b_ptr; } @@ -318,7 +318,7 @@ struct sk_buff *tipc_bearer_get_names(void) { struct sk_buff *buf; struct media *m_ptr; - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; int i, j; buf = tipc_cfg_reply_alloc(MAX_BEARERS * TLV_SPACE(TIPC_MAX_BEARER_NAME)); @@ -331,8 +331,8 @@ struct sk_buff *tipc_bearer_get_names(void) b_ptr = &tipc_bearers[j]; if (b_ptr->active && (b_ptr->media == m_ptr)) { tipc_cfg_append_tlv(buf, TIPC_TLV_BEARER_NAME, - b_ptr->publ.name, - strlen(b_ptr->publ.name) + 1); + b_ptr->name, + strlen(b_ptr->name) + 1); } } } @@ -340,14 +340,14 @@ struct sk_buff *tipc_bearer_get_names(void) return buf; } -void tipc_bearer_add_dest(struct bearer *b_ptr, u32 dest) +void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest) { tipc_nmap_add(&b_ptr->nodes, dest); tipc_disc_update_link_req(b_ptr->link_req); tipc_bcbearer_sort(); } -void tipc_bearer_remove_dest(struct bearer *b_ptr, u32 dest) +void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest) { tipc_nmap_remove(&b_ptr->nodes, dest); tipc_disc_update_link_req(b_ptr->link_req); @@ -362,12 +362,12 @@ void tipc_bearer_remove_dest(struct bearer *b_ptr, u32 dest) * bearer.lock must be taken before calling * Returns binary true(1) ore false(0) */ -static int bearer_push(struct bearer *b_ptr) +static int bearer_push(struct tipc_bearer *b_ptr) { u32 res = 0; struct link *ln, *tln; - if (b_ptr->publ.blocked) + if (b_ptr->blocked) return 0; while (!list_empty(&b_ptr->cong_links) && (res != PUSH_FAILED)) { @@ -382,13 +382,13 @@ static int bearer_push(struct bearer *b_ptr) return list_empty(&b_ptr->cong_links); } -void tipc_bearer_lock_push(struct bearer *b_ptr) +void tipc_bearer_lock_push(struct tipc_bearer *b_ptr) { int res; - spin_lock_bh(&b_ptr->publ.lock); + spin_lock_bh(&b_ptr->lock); res = bearer_push(b_ptr); - spin_unlock_bh(&b_ptr->publ.lock); + spin_unlock_bh(&b_ptr->lock); if (res) tipc_bcbearer_push(); } @@ -398,16 +398,14 @@ void tipc_bearer_lock_push(struct bearer *b_ptr) * Interrupt enabling new requests after bearer congestion or blocking: * See bearer_send(). */ -void tipc_continue(struct tipc_bearer *tb_ptr) +void tipc_continue(struct tipc_bearer *b_ptr) { - struct bearer *b_ptr = (struct bearer *)tb_ptr; - - spin_lock_bh(&b_ptr->publ.lock); + spin_lock_bh(&b_ptr->lock); b_ptr->continue_count++; if (!list_empty(&b_ptr->cong_links)) tipc_k_signal((Handler)tipc_bearer_lock_push, (unsigned long)b_ptr); - b_ptr->publ.blocked = 0; - spin_unlock_bh(&b_ptr->publ.lock); + b_ptr->blocked = 0; + spin_unlock_bh(&b_ptr->lock); } /* @@ -418,7 +416,7 @@ void tipc_continue(struct tipc_bearer *tb_ptr) * bearer.lock is busy */ -static void tipc_bearer_schedule_unlocked(struct bearer *b_ptr, struct link *l_ptr) +static void tipc_bearer_schedule_unlocked(struct tipc_bearer *b_ptr, struct link *l_ptr) { list_move_tail(&l_ptr->link_list, &b_ptr->cong_links); } @@ -431,11 +429,11 @@ static void tipc_bearer_schedule_unlocked(struct bearer *b_ptr, struct link *l_p * bearer.lock is free */ -void tipc_bearer_schedule(struct bearer *b_ptr, struct link *l_ptr) +void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct link *l_ptr) { - spin_lock_bh(&b_ptr->publ.lock); + spin_lock_bh(&b_ptr->lock); tipc_bearer_schedule_unlocked(b_ptr, l_ptr); - spin_unlock_bh(&b_ptr->publ.lock); + spin_unlock_bh(&b_ptr->lock); } @@ -444,18 +442,18 @@ void tipc_bearer_schedule(struct bearer *b_ptr, struct link *l_ptr) * and if there is, try to resolve it before returning. * 'tipc_net_lock' is read_locked when this function is called */ -int tipc_bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr) +int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, struct link *l_ptr) { int res = 1; if (list_empty(&b_ptr->cong_links)) return 1; - spin_lock_bh(&b_ptr->publ.lock); + spin_lock_bh(&b_ptr->lock); if (!bearer_push(b_ptr)) { tipc_bearer_schedule_unlocked(b_ptr, l_ptr); res = 0; } - spin_unlock_bh(&b_ptr->publ.lock); + spin_unlock_bh(&b_ptr->lock); return res; } @@ -463,9 +461,9 @@ int tipc_bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr) * tipc_bearer_congested - determines if bearer is currently congested */ -int tipc_bearer_congested(struct bearer *b_ptr, struct link *l_ptr) +int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct link *l_ptr) { - if (unlikely(b_ptr->publ.blocked)) + if (unlikely(b_ptr->blocked)) return 1; if (likely(list_empty(&b_ptr->cong_links))) return 0; @@ -478,7 +476,7 @@ int tipc_bearer_congested(struct bearer *b_ptr, struct link *l_ptr) int tipc_enable_bearer(const char *name, u32 bcast_scope, u32 priority) { - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; struct media *m_ptr; struct bearer_name b_name; char addr_string[16]; @@ -528,7 +526,7 @@ restart: bearer_id = i; continue; } - if (!strcmp(name, tipc_bearers[i].publ.name)) { + if (!strcmp(name, tipc_bearers[i].name)) { warn("Bearer <%s> rejected, already enabled\n", name); goto failed; } @@ -551,8 +549,8 @@ restart: } b_ptr = &tipc_bearers[bearer_id]; - strcpy(b_ptr->publ.name, name); - res = m_ptr->enable_bearer(&b_ptr->publ); + strcpy(b_ptr->name, name); + res = m_ptr->enable_bearer(b_ptr); if (res) { warn("Bearer <%s> rejected, enable failure (%d)\n", name, -res); goto failed; @@ -568,9 +566,9 @@ restart: INIT_LIST_HEAD(&b_ptr->links); if (m_ptr->bcast) { b_ptr->link_req = tipc_disc_init_link_req(b_ptr, &m_ptr->bcast_addr, - bcast_scope, 2); + bcast_scope); } - spin_lock_init(&b_ptr->publ.lock); + spin_lock_init(&b_ptr->lock); write_unlock_bh(&tipc_net_lock); info("Enabled bearer <%s>, discovery domain %s, priority %u\n", name, tipc_addr_string_fill(addr_string, bcast_scope), priority); @@ -587,7 +585,7 @@ failed: int tipc_block_bearer(const char *name) { - struct bearer *b_ptr = NULL; + struct tipc_bearer *b_ptr = NULL; struct link *l_ptr; struct link *temp_l_ptr; @@ -600,8 +598,8 @@ int tipc_block_bearer(const char *name) } info("Blocking bearer <%s>\n", name); - spin_lock_bh(&b_ptr->publ.lock); - b_ptr->publ.blocked = 1; + spin_lock_bh(&b_ptr->lock); + b_ptr->blocked = 1; list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { struct tipc_node *n_ptr = l_ptr->owner; @@ -609,7 +607,7 @@ int tipc_block_bearer(const char *name) tipc_link_reset(l_ptr); spin_unlock_bh(&n_ptr->lock); } - spin_unlock_bh(&b_ptr->publ.lock); + spin_unlock_bh(&b_ptr->lock); read_unlock_bh(&tipc_net_lock); return 0; } @@ -620,27 +618,27 @@ int tipc_block_bearer(const char *name) * Note: This routine assumes caller holds tipc_net_lock. */ -static void bearer_disable(struct bearer *b_ptr) +static void bearer_disable(struct tipc_bearer *b_ptr) { struct link *l_ptr; struct link *temp_l_ptr; - info("Disabling bearer <%s>\n", b_ptr->publ.name); + info("Disabling bearer <%s>\n", b_ptr->name); tipc_disc_stop_link_req(b_ptr->link_req); - spin_lock_bh(&b_ptr->publ.lock); + spin_lock_bh(&b_ptr->lock); b_ptr->link_req = NULL; - b_ptr->publ.blocked = 1; - b_ptr->media->disable_bearer(&b_ptr->publ); + b_ptr->blocked = 1; + b_ptr->media->disable_bearer(b_ptr); list_for_each_entry_safe(l_ptr, temp_l_ptr, &b_ptr->links, link_list) { tipc_link_delete(l_ptr); } - spin_unlock_bh(&b_ptr->publ.lock); - memset(b_ptr, 0, sizeof(struct bearer)); + spin_unlock_bh(&b_ptr->lock); + memset(b_ptr, 0, sizeof(struct tipc_bearer)); } int tipc_disable_bearer(const char *name) { - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; int res; write_lock_bh(&tipc_net_lock); diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 85f451d5aacf..255dea64f7bd 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -2,7 +2,7 @@ * net/tipc/bearer.h: Include file for TIPC bearer code * * Copyright (c) 1996-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -61,26 +61,7 @@ struct tipc_media_addr { } dev_addr; }; -/** - * struct tipc_bearer - TIPC bearer info available to media code - * @usr_handle: pointer to additional media-specific information about bearer - * @mtu: max packet size bearer can support - * @blocked: non-zero if bearer is blocked - * @lock: spinlock for controlling access to bearer - * @addr: media-specific address associated with bearer - * @name: bearer name (format = media:interface) - * - * Note: TIPC initializes "name" and "lock" fields; media code is responsible - * for initialization all other fields when a bearer is enabled. - */ -struct tipc_bearer { - void *usr_handle; - u32 mtu; - int blocked; - spinlock_t lock; - struct tipc_media_addr addr; - char name[TIPC_MAX_BEARER_NAME]; -}; +struct tipc_bearer; /** * struct media - TIPC media information available to internal users @@ -115,8 +96,13 @@ struct media { }; /** - * struct bearer - TIPC bearer information available to internal users - * @publ: bearer information available to privileged users + * struct tipc_bearer - TIPC bearer structure + * @usr_handle: pointer to additional media-specific information about bearer + * @mtu: max packet size bearer can support + * @blocked: non-zero if bearer is blocked + * @lock: spinlock for controlling access to bearer + * @addr: media-specific address associated with bearer + * @name: bearer name (format = media:interface) * @media: ptr to media structure associated with bearer * @priority: default link priority for bearer * @detect_scope: network address mask used during automatic link creation @@ -128,10 +114,18 @@ struct media { * @active: non-zero if bearer structure is represents a bearer * @net_plane: network plane ('A' through 'H') currently associated with bearer * @nodes: indicates which nodes in cluster can be reached through bearer + * + * Note: media-specific code is responsible for initialization of the fields + * indicated below when a bearer is enabled; TIPC's generic bearer code takes + * care of initializing all other fields. */ - -struct bearer { - struct tipc_bearer publ; +struct tipc_bearer { + void *usr_handle; /* initalized by media */ + u32 mtu; /* initalized by media */ + int blocked; /* initalized by media */ + struct tipc_media_addr addr; /* initalized by media */ + char name[TIPC_MAX_BEARER_NAME]; + spinlock_t lock; struct media *media; u32 priority; u32 detect_scope; @@ -152,7 +146,7 @@ struct bearer_name { struct link; -extern struct bearer tipc_bearers[]; +extern struct tipc_bearer tipc_bearers[]; /* * TIPC routines available to supported media types @@ -186,14 +180,14 @@ void tipc_media_addr_printf(struct print_buf *pb, struct tipc_media_addr *a); struct sk_buff *tipc_media_get_names(void); struct sk_buff *tipc_bearer_get_names(void); -void tipc_bearer_add_dest(struct bearer *b_ptr, u32 dest); -void tipc_bearer_remove_dest(struct bearer *b_ptr, u32 dest); -void tipc_bearer_schedule(struct bearer *b_ptr, struct link *l_ptr); -struct bearer *tipc_bearer_find_interface(const char *if_name); -int tipc_bearer_resolve_congestion(struct bearer *b_ptr, struct link *l_ptr); -int tipc_bearer_congested(struct bearer *b_ptr, struct link *l_ptr); +void tipc_bearer_add_dest(struct tipc_bearer *b_ptr, u32 dest); +void tipc_bearer_remove_dest(struct tipc_bearer *b_ptr, u32 dest); +void tipc_bearer_schedule(struct tipc_bearer *b_ptr, struct link *l_ptr); +struct tipc_bearer *tipc_bearer_find_interface(const char *if_name); +int tipc_bearer_resolve_congestion(struct tipc_bearer *b_ptr, struct link *l_ptr); +int tipc_bearer_congested(struct tipc_bearer *b_ptr, struct link *l_ptr); void tipc_bearer_stop(void); -void tipc_bearer_lock_push(struct bearer *b_ptr); +void tipc_bearer_lock_push(struct tipc_bearer *b_ptr); /** @@ -214,10 +208,11 @@ void tipc_bearer_lock_push(struct bearer *b_ptr); * and let TIPC's link code deal with the undelivered message. */ -static inline int tipc_bearer_send(struct bearer *b_ptr, struct sk_buff *buf, +static inline int tipc_bearer_send(struct tipc_bearer *b_ptr, + struct sk_buff *buf, struct tipc_media_addr *dest) { - return !b_ptr->media->send_msg(buf, &b_ptr->publ, dest); + return !b_ptr->media->send_msg(buf, b_ptr, dest); } #endif /* _TIPC_BEARER_H */ diff --git a/net/tipc/core.c b/net/tipc/core.c index e071579e0850..2da1fc75ad65 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -2,7 +2,7 @@ * net/tipc/core.c: TIPC module code * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005-2006, Wind River Systems + * Copyright (c) 2005-2006, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -57,7 +57,6 @@ int tipc_mode = TIPC_NOT_RUNNING; int tipc_random; -atomic_t tipc_user_count = ATOMIC_INIT(0); const char tipc_alphabet[] = "ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789_."; diff --git a/net/tipc/core.h b/net/tipc/core.h index 997158546e25..37544d9f73e1 100644 --- a/net/tipc/core.h +++ b/net/tipc/core.h @@ -2,7 +2,7 @@ * net/tipc/core.h: Include file for TIPC global declarations * * Copyright (c) 2005-2006, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems + * Copyright (c) 2005-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -161,7 +161,6 @@ extern int tipc_remote_management; extern int tipc_mode; extern int tipc_random; extern const char tipc_alphabet[]; -extern atomic_t tipc_user_count; /* diff --git a/net/tipc/discover.c b/net/tipc/discover.c index fa026bd91a68..09ce2318b89e 100644 --- a/net/tipc/discover.c +++ b/net/tipc/discover.c @@ -2,7 +2,7 @@ * net/tipc/discover.c * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005-2006, Wind River Systems + * Copyright (c) 2005-2006, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -57,7 +57,7 @@ * @timer_intv: current interval between requests (in ms) */ struct link_req { - struct bearer *bearer; + struct tipc_bearer *bearer; struct tipc_media_addr dest; struct sk_buff *buf; struct timer_list timer; @@ -67,15 +67,13 @@ struct link_req { /** * tipc_disc_init_msg - initialize a link setup message * @type: message type (request or response) - * @req_links: number of links associated with message * @dest_domain: network domain of node(s) which should respond to message * @b_ptr: ptr to bearer issuing message */ static struct sk_buff *tipc_disc_init_msg(u32 type, - u32 req_links, u32 dest_domain, - struct bearer *b_ptr) + struct tipc_bearer *b_ptr) { struct sk_buff *buf = tipc_buf_acquire(DSC_H_SIZE); struct tipc_msg *msg; @@ -84,10 +82,9 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, msg = buf_msg(buf); tipc_msg_init(msg, LINK_CONFIG, type, DSC_H_SIZE, dest_domain); msg_set_non_seq(msg, 1); - msg_set_req_links(msg, req_links); msg_set_dest_domain(msg, dest_domain); msg_set_bc_netid(msg, tipc_net_id); - msg_set_media_addr(msg, &b_ptr->publ.addr); + msg_set_media_addr(msg, &b_ptr->addr); } return buf; } @@ -99,7 +96,7 @@ static struct sk_buff *tipc_disc_init_msg(u32 type, * @media_addr: media address advertised by duplicated node */ -static void disc_dupl_alert(struct bearer *b_ptr, u32 node_addr, +static void disc_dupl_alert(struct tipc_bearer *b_ptr, u32 node_addr, struct tipc_media_addr *media_addr) { char node_addr_str[16]; @@ -111,7 +108,7 @@ static void disc_dupl_alert(struct bearer *b_ptr, u32 node_addr, tipc_media_addr_printf(&pb, media_addr); tipc_printbuf_validate(&pb); warn("Duplicate %s using %s seen on <%s>\n", - node_addr_str, media_addr_str, b_ptr->publ.name); + node_addr_str, media_addr_str, b_ptr->name); } /** @@ -120,7 +117,7 @@ static void disc_dupl_alert(struct bearer *b_ptr, u32 node_addr, * @b_ptr: bearer that message arrived on */ -void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) +void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr) { struct link *link; struct tipc_media_addr media_addr; @@ -140,7 +137,7 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) if (!tipc_addr_node_valid(orig)) return; if (orig == tipc_own_addr) { - if (memcmp(&media_addr, &b_ptr->publ.addr, sizeof(media_addr))) + if (memcmp(&media_addr, &b_ptr->addr, sizeof(media_addr))) disc_dupl_alert(b_ptr, tipc_own_addr, &media_addr); return; } @@ -191,9 +188,9 @@ void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr) spin_unlock_bh(&n_ptr->lock); if ((type == DSC_RESP_MSG) || link_fully_up) return; - rbuf = tipc_disc_init_msg(DSC_RESP_MSG, 1, orig, b_ptr); + rbuf = tipc_disc_init_msg(DSC_RESP_MSG, orig, b_ptr); if (rbuf != NULL) { - b_ptr->media->send_msg(rbuf, &b_ptr->publ, &media_addr); + b_ptr->media->send_msg(rbuf, b_ptr, &media_addr); buf_discard(rbuf); } } @@ -249,9 +246,9 @@ void tipc_disc_update_link_req(struct link_req *req) static void disc_timeout(struct link_req *req) { - spin_lock_bh(&req->bearer->publ.lock); + spin_lock_bh(&req->bearer->lock); - req->bearer->media->send_msg(req->buf, &req->bearer->publ, &req->dest); + req->bearer->media->send_msg(req->buf, req->bearer, &req->dest); if ((req->timer_intv == TIPC_LINK_REQ_SLOW) || (req->timer_intv == TIPC_LINK_REQ_FAST)) { @@ -266,7 +263,7 @@ static void disc_timeout(struct link_req *req) } k_start_timer(&req->timer, req->timer_intv); - spin_unlock_bh(&req->bearer->publ.lock); + spin_unlock_bh(&req->bearer->lock); } /** @@ -274,15 +271,13 @@ static void disc_timeout(struct link_req *req) * @b_ptr: ptr to bearer issuing requests * @dest: destination address for request messages * @dest_domain: network domain of node(s) which should respond to message - * @req_links: max number of desired links * * Returns pointer to link request structure, or NULL if unable to create. */ -struct link_req *tipc_disc_init_link_req(struct bearer *b_ptr, +struct link_req *tipc_disc_init_link_req(struct tipc_bearer *b_ptr, const struct tipc_media_addr *dest, - u32 dest_domain, - u32 req_links) + u32 dest_domain) { struct link_req *req; @@ -290,7 +285,7 @@ struct link_req *tipc_disc_init_link_req(struct bearer *b_ptr, if (!req) return NULL; - req->buf = tipc_disc_init_msg(DSC_REQ_MSG, req_links, dest_domain, b_ptr); + req->buf = tipc_disc_init_msg(DSC_REQ_MSG, dest_domain, b_ptr); if (!req->buf) { kfree(req); return NULL; diff --git a/net/tipc/discover.h b/net/tipc/discover.h index d2c3cffb79fc..e48a167e47b2 100644 --- a/net/tipc/discover.h +++ b/net/tipc/discover.h @@ -2,7 +2,7 @@ * net/tipc/discover.h * * Copyright (c) 2003-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -39,13 +39,12 @@ struct link_req; -struct link_req *tipc_disc_init_link_req(struct bearer *b_ptr, +struct link_req *tipc_disc_init_link_req(struct tipc_bearer *b_ptr, const struct tipc_media_addr *dest, - u32 dest_domain, - u32 req_links); + u32 dest_domain); void tipc_disc_update_link_req(struct link_req *req); void tipc_disc_stop_link_req(struct link_req *req); -void tipc_disc_recv_msg(struct sk_buff *buf, struct bearer *b_ptr); +void tipc_disc_recv_msg(struct sk_buff *buf, struct tipc_bearer *b_ptr); #endif diff --git a/net/tipc/link.c b/net/tipc/link.c index 18702f58d111..89fbb6d6e956 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -2,7 +2,7 @@ * net/tipc/link.c: TIPC link code * * Copyright (c) 1996-2007, Ericsson AB - * Copyright (c) 2004-2007, Wind River Systems + * Copyright (c) 2004-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -90,7 +90,7 @@ static void link_handle_out_of_seq_msg(struct link *l_ptr, static void link_recv_proto_msg(struct link *l_ptr, struct sk_buff *buf); static int link_recv_changeover_msg(struct link **l_ptr, struct sk_buff **buf); static void link_set_supervision_props(struct link *l_ptr, u32 tolerance); -static int link_send_sections_long(struct port *sender, +static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, u32 num_sect, u32 destnode); static void link_check_defragm_bufs(struct link *l_ptr); @@ -113,7 +113,7 @@ static void link_init_max_pkt(struct link *l_ptr) { u32 max_pkt; - max_pkt = (l_ptr->b_ptr->publ.mtu & ~3); + max_pkt = (l_ptr->b_ptr->mtu & ~3); if (max_pkt > MAX_MSG_SIZE) max_pkt = MAX_MSG_SIZE; @@ -246,9 +246,6 @@ static void link_timeout(struct link *l_ptr) l_ptr->stats.accu_queue_sz += l_ptr->out_queue_size; l_ptr->stats.queue_sz_counts++; - if (l_ptr->out_queue_size > l_ptr->stats.max_queue_sz) - l_ptr->stats.max_queue_sz = l_ptr->out_queue_size; - if (l_ptr->first_out) { struct tipc_msg *msg = buf_msg(l_ptr->first_out); u32 length = msg_size(msg); @@ -303,7 +300,7 @@ static void link_set_timer(struct link *l_ptr, u32 time) * Returns pointer to link. */ -struct link *tipc_link_create(struct bearer *b_ptr, const u32 peer, +struct link *tipc_link_create(struct tipc_bearer *b_ptr, const u32 peer, const struct tipc_media_addr *media_addr) { struct link *l_ptr; @@ -317,7 +314,7 @@ struct link *tipc_link_create(struct bearer *b_ptr, const u32 peer, } l_ptr->addr = peer; - if_name = strchr(b_ptr->publ.name, ':') + 1; + if_name = strchr(b_ptr->name, ':') + 1; sprintf(l_ptr->name, "%u.%u.%u:%s-%u.%u.%u:", tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), tipc_node(tipc_own_addr), @@ -391,7 +388,9 @@ void tipc_link_delete(struct link *l_ptr) static void link_start(struct link *l_ptr) { + tipc_node_lock(l_ptr->owner); link_state_event(l_ptr, STARTING_EVT); + tipc_node_unlock(l_ptr->owner); } /** @@ -406,7 +405,7 @@ static void link_start(struct link *l_ptr) static int link_schedule_port(struct link *l_ptr, u32 origport, u32 sz) { - struct port *p_ptr; + struct tipc_port *p_ptr; spin_lock_bh(&tipc_port_list_lock); p_ptr = tipc_port_lock(origport); @@ -415,7 +414,7 @@ static int link_schedule_port(struct link *l_ptr, u32 origport, u32 sz) goto exit; if (!list_empty(&p_ptr->wait_list)) goto exit; - p_ptr->publ.congested = 1; + p_ptr->congested = 1; p_ptr->waiting_pkts = 1 + ((sz - 1) / l_ptr->max_pkt); list_add_tail(&p_ptr->wait_list, &l_ptr->waiting_ports); l_ptr->stats.link_congs++; @@ -428,8 +427,8 @@ exit: void tipc_link_wakeup_ports(struct link *l_ptr, int all) { - struct port *p_ptr; - struct port *temp_p_ptr; + struct tipc_port *p_ptr; + struct tipc_port *temp_p_ptr; int win = l_ptr->queue_limit[0] - l_ptr->out_queue_size; if (all) @@ -445,11 +444,11 @@ void tipc_link_wakeup_ports(struct link *l_ptr, int all) if (win <= 0) break; list_del_init(&p_ptr->wait_list); - spin_lock_bh(p_ptr->publ.lock); - p_ptr->publ.congested = 0; - p_ptr->wakeup(&p_ptr->publ); + spin_lock_bh(p_ptr->lock); + p_ptr->congested = 0; + p_ptr->wakeup(p_ptr); win -= p_ptr->waiting_pkts; - spin_unlock_bh(p_ptr->publ.lock); + spin_unlock_bh(p_ptr->lock); } exit: @@ -824,7 +823,10 @@ static void link_add_to_outqueue(struct link *l_ptr, l_ptr->last_out = buf; } else l_ptr->first_out = l_ptr->last_out = buf; + l_ptr->out_queue_size++; + if (l_ptr->out_queue_size > l_ptr->stats.max_queue_sz) + l_ptr->stats.max_queue_sz = l_ptr->out_queue_size; } /* @@ -867,9 +869,6 @@ int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf) /* Packet can be queued or sent: */ - if (queue_size > l_ptr->stats.max_queue_sz) - l_ptr->stats.max_queue_sz = queue_size; - if (likely(!tipc_bearer_congested(l_ptr->b_ptr, l_ptr) && !link_congested(l_ptr))) { link_add_to_outqueue(l_ptr, buf, msg); @@ -1027,12 +1026,12 @@ int tipc_send_buf_fast(struct sk_buff *buf, u32 destnode) * except for total message length. * Returns user data length or errno. */ -int tipc_link_send_sections_fast(struct port *sender, +int tipc_link_send_sections_fast(struct tipc_port *sender, struct iovec const *msg_sect, const u32 num_sect, u32 destaddr) { - struct tipc_msg *hdr = &sender->publ.phdr; + struct tipc_msg *hdr = &sender->phdr; struct link *l_ptr; struct sk_buff *buf; struct tipc_node *node; @@ -1045,7 +1044,7 @@ again: * (Must not hold any locks while building message.) */ - res = tipc_msg_build(hdr, msg_sect, num_sect, sender->publ.max_pkt, + res = tipc_msg_build(hdr, msg_sect, num_sect, sender->max_pkt, !sender->user_port, &buf); read_lock_bh(&tipc_net_lock); @@ -1056,7 +1055,7 @@ again: if (likely(l_ptr)) { if (likely(buf)) { res = link_send_buf_fast(l_ptr, buf, - &sender->publ.max_pkt); + &sender->max_pkt); if (unlikely(res < 0)) buf_discard(buf); exit: @@ -1075,7 +1074,7 @@ exit: if (link_congested(l_ptr) || !list_empty(&l_ptr->b_ptr->cong_links)) { res = link_schedule_port(l_ptr, - sender->publ.ref, res); + sender->ref, res); goto exit; } @@ -1084,12 +1083,12 @@ exit: * then re-try fast path or fragment the message */ - sender->publ.max_pkt = l_ptr->max_pkt; + sender->max_pkt = l_ptr->max_pkt; tipc_node_unlock(node); read_unlock_bh(&tipc_net_lock); - if ((msg_hdr_sz(hdr) + res) <= sender->publ.max_pkt) + if ((msg_hdr_sz(hdr) + res) <= sender->max_pkt) goto again; return link_send_sections_long(sender, msg_sect, @@ -1123,14 +1122,14 @@ exit: * * Returns user data length or errno. */ -static int link_send_sections_long(struct port *sender, +static int link_send_sections_long(struct tipc_port *sender, struct iovec const *msg_sect, u32 num_sect, u32 destaddr) { struct link *l_ptr; struct tipc_node *node; - struct tipc_msg *hdr = &sender->publ.phdr; + struct tipc_msg *hdr = &sender->phdr; u32 dsz = msg_data_sz(hdr); u32 max_pkt, fragm_sz, rest; struct tipc_msg fragm_hdr; @@ -1142,7 +1141,7 @@ static int link_send_sections_long(struct port *sender, again: fragm_no = 1; - max_pkt = sender->publ.max_pkt - INT_H_SIZE; + max_pkt = sender->max_pkt - INT_H_SIZE; /* leave room for tunnel header in case of link changeover */ fragm_sz = max_pkt - INT_H_SIZE; /* leave room for fragmentation header in each fragment */ @@ -1157,7 +1156,7 @@ again: tipc_msg_init(&fragm_hdr, MSG_FRAGMENTER, FIRST_FRAGMENT, INT_H_SIZE, msg_destnode(hdr)); - msg_set_link_selector(&fragm_hdr, sender->publ.ref); + msg_set_link_selector(&fragm_hdr, sender->ref); msg_set_size(&fragm_hdr, max_pkt); msg_set_fragm_no(&fragm_hdr, 1); @@ -1238,13 +1237,13 @@ error: node = tipc_node_find(destaddr); if (likely(node)) { tipc_node_lock(node); - l_ptr = node->active_links[sender->publ.ref & 1]; + l_ptr = node->active_links[sender->ref & 1]; if (!l_ptr) { tipc_node_unlock(node); goto reject; } if (l_ptr->max_pkt < max_pkt) { - sender->publ.max_pkt = l_ptr->max_pkt; + sender->max_pkt = l_ptr->max_pkt; tipc_node_unlock(node); for (; buf_chain; buf_chain = buf) { buf = buf_chain->next; @@ -1441,7 +1440,7 @@ static void link_retransmit_failure(struct link *l_ptr, struct sk_buff *buf) info("Outstanding acks: %lu\n", (unsigned long) TIPC_SKB_CB(buf)->handle); - n_ptr = l_ptr->owner->next; + n_ptr = tipc_bclink_retransmit_to(); tipc_node_lock(n_ptr); tipc_addr_string_fill(addr_string, n_ptr->addr); @@ -1595,11 +1594,10 @@ static int link_recv_buf_validate(struct sk_buff *buf) * structure (i.e. cannot be NULL), but bearer can be inactive. */ -void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *tb_ptr) +void tipc_recv_msg(struct sk_buff *head, struct tipc_bearer *b_ptr) { read_lock_bh(&tipc_net_lock); while (head) { - struct bearer *b_ptr = (struct bearer *)tb_ptr; struct tipc_node *n_ptr; struct link *l_ptr; struct sk_buff *crs; @@ -1950,6 +1948,7 @@ void tipc_link_send_proto_msg(struct link *l_ptr, u32 msg_typ, int probe_msg, msg_set_ack(msg, mod(l_ptr->reset_checkpoint - 1)); msg_set_seq_gap(msg, 0); msg_set_next_sent(msg, 1); + msg_set_probe(msg, 0); msg_set_link_tolerance(msg, l_ptr->tolerance); msg_set_linkprio(msg, l_ptr->priority); msg_set_max_pkt(msg, l_ptr->max_pkt_target); @@ -2618,6 +2617,9 @@ static void link_check_defragm_bufs(struct link *l_ptr) static void link_set_supervision_props(struct link *l_ptr, u32 tolerance) { + if ((tolerance < TIPC_MIN_LINK_TOL) || (tolerance > TIPC_MAX_LINK_TOL)) + return; + l_ptr->tolerance = tolerance; l_ptr->continuity_interval = ((tolerance / 4) > 500) ? 500 : tolerance / 4; @@ -2658,7 +2660,7 @@ void tipc_link_set_queue_limits(struct link *l_ptr, u32 window) static struct link *link_find_link(const char *name, struct tipc_node **node) { struct link_name link_name_parts; - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; struct link *l_ptr; if (!link_name_validate(name, &link_name_parts)) @@ -2961,7 +2963,7 @@ static void link_print(struct link *l_ptr, const char *str) tipc_printf(buf, str); tipc_printf(buf, "Link %x<%s>:", - l_ptr->addr, l_ptr->b_ptr->publ.name); + l_ptr->addr, l_ptr->b_ptr->name); #ifdef CONFIG_TIPC_DEBUG if (link_reset_reset(l_ptr) || link_reset_unknown(l_ptr)) @@ -2981,9 +2983,9 @@ static void link_print(struct link *l_ptr, const char *str) != (l_ptr->out_queue_size - 1)) || (l_ptr->last_out->next != NULL)) { tipc_printf(buf, "\nSend queue inconsistency\n"); - tipc_printf(buf, "first_out= %x ", l_ptr->first_out); - tipc_printf(buf, "next_out= %x ", l_ptr->next_out); - tipc_printf(buf, "last_out= %x ", l_ptr->last_out); + tipc_printf(buf, "first_out= %p ", l_ptr->first_out); + tipc_printf(buf, "next_out= %p ", l_ptr->next_out); + tipc_printf(buf, "last_out= %p ", l_ptr->last_out); } } else tipc_printf(buf, "[]"); diff --git a/net/tipc/link.h b/net/tipc/link.h index 70967e637027..a7794e7ede29 100644 --- a/net/tipc/link.h +++ b/net/tipc/link.h @@ -2,7 +2,7 @@ * net/tipc/link.h: Include file for TIPC link code * * Copyright (c) 1995-2006, Ericsson AB - * Copyright (c) 2004-2005, Wind River Systems + * Copyright (c) 2004-2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -122,7 +122,7 @@ struct link { u32 checkpoint; u32 peer_session; u32 peer_bearer_id; - struct bearer *b_ptr; + struct tipc_bearer *b_ptr; u32 tolerance; u32 continuity_interval; u32 abort_limit; @@ -196,24 +196,18 @@ struct link { u32 bearer_congs; u32 deferred_recv; u32 duplicates; - - /* for statistical profiling of send queue size */ - - u32 max_queue_sz; - u32 accu_queue_sz; - u32 queue_sz_counts; - - /* for statistical profiling of message lengths */ - - u32 msg_length_counts; - u32 msg_lengths_total; - u32 msg_length_profile[7]; + u32 max_queue_sz; /* send queue size high water mark */ + u32 accu_queue_sz; /* used for send queue size profiling */ + u32 queue_sz_counts; /* used for send queue size profiling */ + u32 msg_length_counts; /* used for message length profiling */ + u32 msg_lengths_total; /* used for message length profiling */ + u32 msg_length_profile[7]; /* used for msg. length profiling */ } stats; }; -struct port; +struct tipc_port; -struct link *tipc_link_create(struct bearer *b_ptr, const u32 peer, +struct link *tipc_link_create(struct tipc_bearer *b_ptr, const u32 peer, const struct tipc_media_addr *media_addr); void tipc_link_delete(struct link *l_ptr); void tipc_link_changeover(struct link *l_ptr); @@ -230,7 +224,7 @@ void tipc_link_reset(struct link *l_ptr); int tipc_link_send(struct sk_buff *buf, u32 dest, u32 selector); int tipc_link_send_buf(struct link *l_ptr, struct sk_buff *buf); u32 tipc_link_get_max_pkt(u32 dest, u32 selector); -int tipc_link_send_sections_fast(struct port *sender, +int tipc_link_send_sections_fast(struct tipc_port *sender, struct iovec const *msg_sect, const u32 num_sect, u32 destnode); diff --git a/net/tipc/msg.c b/net/tipc/msg.c index bb6180c4fcbb..0787e12423b8 100644 --- a/net/tipc/msg.c +++ b/net/tipc/msg.c @@ -2,7 +2,7 @@ * net/tipc/msg.c: TIPC message header routines * * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005, Wind River Systems + * Copyright (c) 2005, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -381,20 +381,15 @@ void tipc_msg_dbg(struct print_buf *buf, struct tipc_msg *msg, const char *str) tipc_printf(buf, ":OPRT(%u):", msg_origport(msg)); tipc_printf(buf, ":DPRT(%u):", msg_destport(msg)); } - if (msg_routed(msg) && !msg_non_seq(msg)) - tipc_printf(buf, ":TSEQN(%u)", msg_transp_seqno(msg)); } if (msg_user(msg) == NAME_DISTRIBUTOR) { tipc_printf(buf, ":ONOD(%x):", msg_orignode(msg)); tipc_printf(buf, ":DNOD(%x):", msg_destnode(msg)); - if (msg_routed(msg)) - tipc_printf(buf, ":CSEQN(%u)", msg_transp_seqno(msg)); } if (msg_user(msg) == LINK_CONFIG) { u32 *raw = (u32 *)msg; struct tipc_media_addr *orig = (struct tipc_media_addr *)&raw[5]; - tipc_printf(buf, ":REQL(%u):", msg_req_links(msg)); tipc_printf(buf, ":DDOM(%x):", msg_dest_domain(msg)); tipc_printf(buf, ":NETID(%u):", msg_bc_netid(msg)); tipc_media_addr_printf(buf, orig); diff --git a/net/tipc/msg.h b/net/tipc/msg.h index 92c4c4fd7b3f..9d643a1b7d22 100644 --- a/net/tipc/msg.h +++ b/net/tipc/msg.h @@ -2,7 +2,7 @@ * net/tipc/msg.h: Include file for TIPC message header routines * * Copyright (c) 2000-2007, Ericsson AB - * Copyright (c) 2005-2008, Wind River Systems + * Copyright (c) 2005-2008, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -438,11 +438,6 @@ static inline void msg_set_nametype(struct tipc_msg *m, u32 n) msg_set_word(m, 8, n); } -static inline u32 msg_transp_seqno(struct tipc_msg *m) -{ - return msg_word(m, 8); -} - static inline void msg_set_timestamp(struct tipc_msg *m, u32 n) { msg_set_word(m, 8, n); @@ -453,11 +448,6 @@ static inline u32 msg_timestamp(struct tipc_msg *m) return msg_word(m, 8); } -static inline void msg_set_transp_seqno(struct tipc_msg *m, u32 n) -{ - msg_set_word(m, 8, n); -} - static inline u32 msg_nameinst(struct tipc_msg *m) { return msg_word(m, 9); @@ -577,16 +567,6 @@ static inline void msg_set_seq_gap(struct tipc_msg *m, u32 n) msg_set_bits(m, 1, 16, 0x1fff, n); } -static inline u32 msg_req_links(struct tipc_msg *m) -{ - return msg_bits(m, 1, 16, 0xfff); -} - -static inline void msg_set_req_links(struct tipc_msg *m, u32 n) -{ - msg_set_bits(m, 1, 16, 0xfff, n); -} - /* * Word 2 diff --git a/net/tipc/node.c b/net/tipc/node.c index 3af53e327f49..e4dba1dfb6ea 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -2,7 +2,7 @@ * net/tipc/node.c: TIPC node management routines * * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005-2006, Wind River Systems + * Copyright (c) 2005-2006, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -238,7 +238,7 @@ struct tipc_node *tipc_node_attach_link(struct link *l_ptr) return n_ptr; } err("Attempt to establish second link on <%s> to %s\n", - l_ptr->b_ptr->publ.name, + l_ptr->b_ptr->name, tipc_addr_string_fill(addr_string, l_ptr->addr)); } return NULL; diff --git a/net/tipc/port.c b/net/tipc/port.c index 067bab2a0b98..6ff78f9c7d65 100644 --- a/net/tipc/port.c +++ b/net/tipc/port.c @@ -2,7 +2,7 @@ * net/tipc/port.c: TIPC port code * * Copyright (c) 1992-2007, Ericsson AB - * Copyright (c) 2004-2008, Wind River Systems + * Copyright (c) 2004-2008, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -54,33 +54,19 @@ static DEFINE_SPINLOCK(queue_lock); static LIST_HEAD(ports); static void port_handle_node_down(unsigned long ref); -static struct sk_buff *port_build_self_abort_msg(struct port *, u32 err); -static struct sk_buff *port_build_peer_abort_msg(struct port *, u32 err); +static struct sk_buff *port_build_self_abort_msg(struct tipc_port *, u32 err); +static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *, u32 err); static void port_timeout(unsigned long ref); -static u32 port_peernode(struct port *p_ptr) +static u32 port_peernode(struct tipc_port *p_ptr) { - return msg_destnode(&p_ptr->publ.phdr); + return msg_destnode(&p_ptr->phdr); } -static u32 port_peerport(struct port *p_ptr) +static u32 port_peerport(struct tipc_port *p_ptr) { - return msg_destport(&p_ptr->publ.phdr); -} - -static u32 port_out_seqno(struct port *p_ptr) -{ - return msg_transp_seqno(&p_ptr->publ.phdr); -} - -static void port_incr_out_seqno(struct port *p_ptr) -{ - struct tipc_msg *m = &p_ptr->publ.phdr; - - if (likely(!msg_routed(m))) - return; - msg_set_transp_seqno(m, (msg_transp_seqno(m) + 1)); + return msg_destport(&p_ptr->phdr); } /** @@ -94,7 +80,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, struct sk_buff *buf; struct sk_buff *ibuf = NULL; struct port_list dports = {0, NULL, }; - struct port *oport = tipc_port_deref(ref); + struct tipc_port *oport = tipc_port_deref(ref); int ext_targets; int res; @@ -103,7 +89,7 @@ int tipc_multicast(u32 ref, struct tipc_name_seq const *seq, /* Create multicast message */ - hdr = &oport->publ.phdr; + hdr = &oport->phdr; msg_set_type(hdr, TIPC_MCAST_MSG); msg_set_nametype(hdr, seq->type); msg_set_namelower(hdr, seq->lower); @@ -211,7 +197,7 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, void (*wakeup)(struct tipc_port *), const u32 importance) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg; u32 ref; @@ -220,21 +206,19 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, warn("Port creation failed, no memory\n"); return NULL; } - ref = tipc_ref_acquire(p_ptr, &p_ptr->publ.lock); + ref = tipc_ref_acquire(p_ptr, &p_ptr->lock); if (!ref) { warn("Port creation failed, reference table exhausted\n"); kfree(p_ptr); return NULL; } - p_ptr->publ.usr_handle = usr_handle; - p_ptr->publ.max_pkt = MAX_PKT_DEFAULT; - p_ptr->publ.ref = ref; - msg = &p_ptr->publ.phdr; + p_ptr->usr_handle = usr_handle; + p_ptr->max_pkt = MAX_PKT_DEFAULT; + p_ptr->ref = ref; + msg = &p_ptr->phdr; tipc_msg_init(msg, importance, TIPC_NAMED_MSG, LONG_H_SIZE, 0); msg_set_origport(msg, ref); - p_ptr->last_in_seqno = 41; - p_ptr->sent = 1; INIT_LIST_HEAD(&p_ptr->wait_list); INIT_LIST_HEAD(&p_ptr->subscription.nodesub_list); p_ptr->dispatcher = dispatcher; @@ -246,12 +230,12 @@ struct tipc_port *tipc_createport_raw(void *usr_handle, INIT_LIST_HEAD(&p_ptr->port_list); list_add_tail(&p_ptr->port_list, &ports); spin_unlock_bh(&tipc_port_list_lock); - return &(p_ptr->publ); + return p_ptr; } int tipc_deleteport(u32 ref) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct sk_buff *buf = NULL; tipc_withdraw(ref, 0, NULL); @@ -263,7 +247,7 @@ int tipc_deleteport(u32 ref) tipc_port_unlock(p_ptr); k_cancel_timer(&p_ptr->timer); - if (p_ptr->publ.connected) { + if (p_ptr->connected) { buf = port_build_peer_abort_msg(p_ptr, TIPC_ERR_NO_PORT); tipc_nodesub_unsubscribe(&p_ptr->subscription); } @@ -279,14 +263,14 @@ int tipc_deleteport(u32 ref) return 0; } -static int port_unreliable(struct port *p_ptr) +static int port_unreliable(struct tipc_port *p_ptr) { - return msg_src_droppable(&p_ptr->publ.phdr); + return msg_src_droppable(&p_ptr->phdr); } int tipc_portunreliable(u32 ref, unsigned int *isunreliable) { - struct port *p_ptr; + struct tipc_port *p_ptr; p_ptr = tipc_port_lock(ref); if (!p_ptr) @@ -298,24 +282,24 @@ int tipc_portunreliable(u32 ref, unsigned int *isunreliable) int tipc_set_portunreliable(u32 ref, unsigned int isunreliable) { - struct port *p_ptr; + struct tipc_port *p_ptr; p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - msg_set_src_droppable(&p_ptr->publ.phdr, (isunreliable != 0)); + msg_set_src_droppable(&p_ptr->phdr, (isunreliable != 0)); tipc_port_unlock(p_ptr); return 0; } -static int port_unreturnable(struct port *p_ptr) +static int port_unreturnable(struct tipc_port *p_ptr) { - return msg_dest_droppable(&p_ptr->publ.phdr); + return msg_dest_droppable(&p_ptr->phdr); } int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable) { - struct port *p_ptr; + struct tipc_port *p_ptr; p_ptr = tipc_port_lock(ref); if (!p_ptr) @@ -327,12 +311,12 @@ int tipc_portunreturnable(u32 ref, unsigned int *isunrejectable) int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) { - struct port *p_ptr; + struct tipc_port *p_ptr; p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - msg_set_dest_droppable(&p_ptr->publ.phdr, (isunrejectable != 0)); + msg_set_dest_droppable(&p_ptr->phdr, (isunrejectable != 0)); tipc_port_unlock(p_ptr); return 0; } @@ -345,7 +329,7 @@ int tipc_set_portunreturnable(u32 ref, unsigned int isunrejectable) static struct sk_buff *port_build_proto_msg(u32 destport, u32 destnode, u32 origport, u32 orignode, u32 usr, u32 type, u32 err, - u32 seqno, u32 ack) + u32 ack) { struct sk_buff *buf; struct tipc_msg *msg; @@ -358,7 +342,6 @@ static struct sk_buff *port_build_proto_msg(u32 destport, u32 destnode, msg_set_destport(msg, destport); msg_set_origport(msg, origport); msg_set_orignode(msg, orignode); - msg_set_transp_seqno(msg, seqno); msg_set_msgcnt(msg, ack); } return buf; @@ -413,10 +396,10 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) /* send self-abort message when rejecting on a connected port */ if (msg_connected(msg)) { struct sk_buff *abuf = NULL; - struct port *p_ptr = tipc_port_lock(msg_destport(msg)); + struct tipc_port *p_ptr = tipc_port_lock(msg_destport(msg)); if (p_ptr) { - if (p_ptr->publ.connected) + if (p_ptr->connected) abuf = port_build_self_abort_msg(p_ptr, err); tipc_port_unlock(p_ptr); } @@ -429,7 +412,7 @@ int tipc_reject_msg(struct sk_buff *buf, u32 err) return data_sz; } -int tipc_port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, +int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, int err) { @@ -446,13 +429,13 @@ int tipc_port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, static void port_timeout(unsigned long ref) { - struct port *p_ptr = tipc_port_lock(ref); + struct tipc_port *p_ptr = tipc_port_lock(ref); struct sk_buff *buf = NULL; if (!p_ptr) return; - if (!p_ptr->publ.connected) { + if (!p_ptr->connected) { tipc_port_unlock(p_ptr); return; } @@ -463,14 +446,12 @@ static void port_timeout(unsigned long ref) } else { buf = port_build_proto_msg(port_peerport(p_ptr), port_peernode(p_ptr), - p_ptr->publ.ref, + p_ptr->ref, tipc_own_addr, CONN_MANAGER, CONN_PROBE, TIPC_OK, - port_out_seqno(p_ptr), 0); - port_incr_out_seqno(p_ptr); p_ptr->probing_state = PROBING; k_start_timer(&p_ptr->timer, p_ptr->probing_interval); } @@ -481,7 +462,7 @@ static void port_timeout(unsigned long ref) static void port_handle_node_down(unsigned long ref) { - struct port *p_ptr = tipc_port_lock(ref); + struct tipc_port *p_ptr = tipc_port_lock(ref); struct sk_buff *buf = NULL; if (!p_ptr) @@ -492,73 +473,71 @@ static void port_handle_node_down(unsigned long ref) } -static struct sk_buff *port_build_self_abort_msg(struct port *p_ptr, u32 err) +static struct sk_buff *port_build_self_abort_msg(struct tipc_port *p_ptr, u32 err) { - u32 imp = msg_importance(&p_ptr->publ.phdr); + u32 imp = msg_importance(&p_ptr->phdr); - if (!p_ptr->publ.connected) + if (!p_ptr->connected) return NULL; if (imp < TIPC_CRITICAL_IMPORTANCE) imp++; - return port_build_proto_msg(p_ptr->publ.ref, + return port_build_proto_msg(p_ptr->ref, tipc_own_addr, port_peerport(p_ptr), port_peernode(p_ptr), imp, TIPC_CONN_MSG, err, - p_ptr->last_in_seqno + 1, 0); } -static struct sk_buff *port_build_peer_abort_msg(struct port *p_ptr, u32 err) +static struct sk_buff *port_build_peer_abort_msg(struct tipc_port *p_ptr, u32 err) { - u32 imp = msg_importance(&p_ptr->publ.phdr); + u32 imp = msg_importance(&p_ptr->phdr); - if (!p_ptr->publ.connected) + if (!p_ptr->connected) return NULL; if (imp < TIPC_CRITICAL_IMPORTANCE) imp++; return port_build_proto_msg(port_peerport(p_ptr), port_peernode(p_ptr), - p_ptr->publ.ref, + p_ptr->ref, tipc_own_addr, imp, TIPC_CONN_MSG, err, - port_out_seqno(p_ptr), 0); } void tipc_port_recv_proto_msg(struct sk_buff *buf) { struct tipc_msg *msg = buf_msg(buf); - struct port *p_ptr = tipc_port_lock(msg_destport(msg)); + struct tipc_port *p_ptr = tipc_port_lock(msg_destport(msg)); u32 err = TIPC_OK; struct sk_buff *r_buf = NULL; struct sk_buff *abort_buf = NULL; if (!p_ptr) { err = TIPC_ERR_NO_PORT; - } else if (p_ptr->publ.connected) { + } else if (p_ptr->connected) { if ((port_peernode(p_ptr) != msg_orignode(msg)) || (port_peerport(p_ptr) != msg_origport(msg))) { err = TIPC_ERR_NO_PORT; } else if (msg_type(msg) == CONN_ACK) { int wakeup = tipc_port_congested(p_ptr) && - p_ptr->publ.congested && + p_ptr->congested && p_ptr->wakeup; p_ptr->acked += msg_msgcnt(msg); if (tipc_port_congested(p_ptr)) goto exit; - p_ptr->publ.congested = 0; + p_ptr->congested = 0; if (!wakeup) goto exit; - p_ptr->wakeup(&p_ptr->publ); + p_ptr->wakeup(p_ptr); goto exit; } - } else if (p_ptr->publ.published) { + } else if (p_ptr->published) { err = TIPC_ERR_NO_PORT; } if (err) { @@ -569,7 +548,6 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) TIPC_HIGH_IMPORTANCE, TIPC_CONN_MSG, err, - 0, 0); goto exit; } @@ -583,11 +561,9 @@ void tipc_port_recv_proto_msg(struct sk_buff *buf) CONN_MANAGER, CONN_PROBE_REPLY, TIPC_OK, - port_out_seqno(p_ptr), 0); } p_ptr->probing_state = CONFIRMED; - port_incr_out_seqno(p_ptr); exit: if (p_ptr) tipc_port_unlock(p_ptr); @@ -596,29 +572,29 @@ exit: buf_discard(buf); } -static void port_print(struct port *p_ptr, struct print_buf *buf, int full_id) +static void port_print(struct tipc_port *p_ptr, struct print_buf *buf, int full_id) { struct publication *publ; if (full_id) tipc_printf(buf, "<%u.%u.%u:%u>:", tipc_zone(tipc_own_addr), tipc_cluster(tipc_own_addr), - tipc_node(tipc_own_addr), p_ptr->publ.ref); + tipc_node(tipc_own_addr), p_ptr->ref); else - tipc_printf(buf, "%-10u:", p_ptr->publ.ref); + tipc_printf(buf, "%-10u:", p_ptr->ref); - if (p_ptr->publ.connected) { + if (p_ptr->connected) { u32 dport = port_peerport(p_ptr); u32 destnode = port_peernode(p_ptr); tipc_printf(buf, " connected to <%u.%u.%u:%u>", tipc_zone(destnode), tipc_cluster(destnode), tipc_node(destnode), dport); - if (p_ptr->publ.conn_type != 0) + if (p_ptr->conn_type != 0) tipc_printf(buf, " via {%u,%u}", - p_ptr->publ.conn_type, - p_ptr->publ.conn_instance); - } else if (p_ptr->publ.published) { + p_ptr->conn_type, + p_ptr->conn_instance); + } else if (p_ptr->published) { tipc_printf(buf, " bound to"); list_for_each_entry(publ, &p_ptr->publications, pport_list) { if (publ->lower == publ->upper) @@ -639,7 +615,7 @@ struct sk_buff *tipc_port_get_ports(void) struct sk_buff *buf; struct tlv_desc *rep_tlv; struct print_buf pb; - struct port *p_ptr; + struct tipc_port *p_ptr; int str_len; buf = tipc_cfg_reply_alloc(TLV_SPACE(MAX_PORT_QUERY)); @@ -650,9 +626,9 @@ struct sk_buff *tipc_port_get_ports(void) tipc_printbuf_init(&pb, TLV_DATA(rep_tlv), MAX_PORT_QUERY); spin_lock_bh(&tipc_port_list_lock); list_for_each_entry(p_ptr, &ports, port_list) { - spin_lock_bh(p_ptr->publ.lock); + spin_lock_bh(p_ptr->lock); port_print(p_ptr, &pb, 0); - spin_unlock_bh(p_ptr->publ.lock); + spin_unlock_bh(p_ptr->lock); } spin_unlock_bh(&tipc_port_list_lock); str_len = tipc_printbuf_validate(&pb); @@ -665,12 +641,12 @@ struct sk_buff *tipc_port_get_ports(void) void tipc_port_reinit(void) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg; spin_lock_bh(&tipc_port_list_lock); list_for_each_entry(p_ptr, &ports, port_list) { - msg = &p_ptr->publ.phdr; + msg = &p_ptr->phdr; if (msg_orignode(msg) == tipc_own_addr) break; msg_set_prevnode(msg, tipc_own_addr); @@ -695,7 +671,7 @@ static void port_dispatcher_sigh(void *dummy) spin_unlock_bh(&queue_lock); while (buf) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct user_port *up_ptr; struct tipc_portid orig; struct tipc_name_seq dseq; @@ -720,8 +696,8 @@ static void port_dispatcher_sigh(void *dummy) orig.node = msg_orignode(msg); up_ptr = p_ptr->user_port; usr_handle = up_ptr->usr_handle; - connected = p_ptr->publ.connected; - published = p_ptr->publ.published; + connected = p_ptr->connected; + published = p_ptr->published; if (unlikely(msg_errcode(msg))) goto err; @@ -732,6 +708,7 @@ static void port_dispatcher_sigh(void *dummy) tipc_conn_msg_event cb = up_ptr->conn_msg_cb; u32 peer_port = port_peerport(p_ptr); u32 peer_node = port_peernode(p_ptr); + u32 dsz; tipc_port_unlock(p_ptr); if (unlikely(!cb)) @@ -742,13 +719,14 @@ static void port_dispatcher_sigh(void *dummy) } else if ((msg_origport(msg) != peer_port) || (msg_orignode(msg) != peer_node)) goto reject; - if (unlikely(++p_ptr->publ.conn_unacked >= - TIPC_FLOW_CONTROL_WIN)) + dsz = msg_data_sz(msg); + if (unlikely(dsz && + (++p_ptr->conn_unacked >= + TIPC_FLOW_CONTROL_WIN))) tipc_acknowledge(dref, - p_ptr->publ.conn_unacked); + p_ptr->conn_unacked); skb_pull(buf, msg_hdr_sz(msg)); - cb(usr_handle, dref, &buf, msg_data(msg), - msg_data_sz(msg)); + cb(usr_handle, dref, &buf, msg_data(msg), dsz); break; } case TIPC_DIRECT_MSG:{ @@ -872,7 +850,7 @@ static u32 port_dispatcher(struct tipc_port *dummy, struct sk_buff *buf) static void port_wakeup_sh(unsigned long ref) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct user_port *up_ptr; tipc_continue_event cb = NULL; void *uh = NULL; @@ -898,14 +876,14 @@ static void port_wakeup(struct tipc_port *p_ptr) void tipc_acknowledge(u32 ref, u32 ack) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct sk_buff *buf = NULL; p_ptr = tipc_port_lock(ref); if (!p_ptr) return; - if (p_ptr->publ.connected) { - p_ptr->publ.conn_unacked -= ack; + if (p_ptr->connected) { + p_ptr->conn_unacked -= ack; buf = port_build_proto_msg(port_peerport(p_ptr), port_peernode(p_ptr), ref, @@ -913,7 +891,6 @@ void tipc_acknowledge(u32 ref, u32 ack) CONN_MANAGER, CONN_ACK, TIPC_OK, - port_out_seqno(p_ptr), ack); } tipc_port_unlock(p_ptr); @@ -936,14 +913,14 @@ int tipc_createport(void *usr_handle, u32 *portref) { struct user_port *up_ptr; - struct port *p_ptr; + struct tipc_port *p_ptr; up_ptr = kmalloc(sizeof(*up_ptr), GFP_ATOMIC); if (!up_ptr) { warn("Port creation failed, no memory\n"); return -ENOMEM; } - p_ptr = (struct port *)tipc_createport_raw(NULL, port_dispatcher, + p_ptr = (struct tipc_port *)tipc_createport_raw(NULL, port_dispatcher, port_wakeup, importance); if (!p_ptr) { kfree(up_ptr); @@ -952,7 +929,7 @@ int tipc_createport(void *usr_handle, p_ptr->user_port = up_ptr; up_ptr->usr_handle = usr_handle; - up_ptr->ref = p_ptr->publ.ref; + up_ptr->ref = p_ptr->ref; up_ptr->err_cb = error_cb; up_ptr->named_err_cb = named_error_cb; up_ptr->conn_err_cb = conn_error_cb; @@ -960,26 +937,26 @@ int tipc_createport(void *usr_handle, up_ptr->named_msg_cb = named_msg_cb; up_ptr->conn_msg_cb = conn_msg_cb; up_ptr->continue_event_cb = continue_event_cb; - *portref = p_ptr->publ.ref; + *portref = p_ptr->ref; tipc_port_unlock(p_ptr); return 0; } int tipc_portimportance(u32 ref, unsigned int *importance) { - struct port *p_ptr; + struct tipc_port *p_ptr; p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - *importance = (unsigned int)msg_importance(&p_ptr->publ.phdr); + *importance = (unsigned int)msg_importance(&p_ptr->phdr); tipc_port_unlock(p_ptr); return 0; } int tipc_set_portimportance(u32 ref, unsigned int imp) { - struct port *p_ptr; + struct tipc_port *p_ptr; if (imp > TIPC_CRITICAL_IMPORTANCE) return -EINVAL; @@ -987,7 +964,7 @@ int tipc_set_portimportance(u32 ref, unsigned int imp) p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - msg_set_importance(&p_ptr->publ.phdr, (u32)imp); + msg_set_importance(&p_ptr->phdr, (u32)imp); tipc_port_unlock(p_ptr); return 0; } @@ -995,7 +972,7 @@ int tipc_set_portimportance(u32 ref, unsigned int imp) int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct publication *publ; u32 key; int res = -EINVAL; @@ -1004,7 +981,7 @@ int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) if (!p_ptr) return -EINVAL; - if (p_ptr->publ.connected) + if (p_ptr->connected) goto exit; if (seq->lower > seq->upper) goto exit; @@ -1016,11 +993,11 @@ int tipc_publish(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) goto exit; } publ = tipc_nametbl_publish(seq->type, seq->lower, seq->upper, - scope, p_ptr->publ.ref, key); + scope, p_ptr->ref, key); if (publ) { list_add(&publ->pport_list, &p_ptr->publications); p_ptr->pub_count++; - p_ptr->publ.published = 1; + p_ptr->published = 1; res = 0; } exit: @@ -1030,7 +1007,7 @@ exit: int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct publication *publ; struct publication *tpubl; int res = -EINVAL; @@ -1063,37 +1040,36 @@ int tipc_withdraw(u32 ref, unsigned int scope, struct tipc_name_seq const *seq) } } if (list_empty(&p_ptr->publications)) - p_ptr->publ.published = 0; + p_ptr->published = 0; tipc_port_unlock(p_ptr); return res; } int tipc_connect2port(u32 ref, struct tipc_portid const *peer) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg; int res = -EINVAL; p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - if (p_ptr->publ.published || p_ptr->publ.connected) + if (p_ptr->published || p_ptr->connected) goto exit; if (!peer->ref) goto exit; - msg = &p_ptr->publ.phdr; + msg = &p_ptr->phdr; msg_set_destnode(msg, peer->node); msg_set_destport(msg, peer->ref); msg_set_orignode(msg, tipc_own_addr); - msg_set_origport(msg, p_ptr->publ.ref); - msg_set_transp_seqno(msg, 42); + msg_set_origport(msg, p_ptr->ref); msg_set_type(msg, TIPC_CONN_MSG); msg_set_hdr_sz(msg, SHORT_H_SIZE); p_ptr->probing_interval = PROBING_INTERVAL; p_ptr->probing_state = CONFIRMED; - p_ptr->publ.connected = 1; + p_ptr->connected = 1; k_start_timer(&p_ptr->timer, p_ptr->probing_interval); tipc_nodesub_subscribe(&p_ptr->subscription, peer->node, @@ -1102,7 +1078,7 @@ int tipc_connect2port(u32 ref, struct tipc_portid const *peer) res = 0; exit: tipc_port_unlock(p_ptr); - p_ptr->publ.max_pkt = tipc_link_get_max_pkt(peer->node, ref); + p_ptr->max_pkt = tipc_link_get_max_pkt(peer->node, ref); return res; } @@ -1120,7 +1096,7 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr) tp_ptr->connected = 0; /* let timer expire on it's own to avoid deadlock! */ tipc_nodesub_unsubscribe( - &((struct port *)tp_ptr)->subscription); + &((struct tipc_port *)tp_ptr)->subscription); res = 0; } else { res = -ENOTCONN; @@ -1135,7 +1111,7 @@ int tipc_disconnect_port(struct tipc_port *tp_ptr) int tipc_disconnect(u32 ref) { - struct port *p_ptr; + struct tipc_port *p_ptr; int res; p_ptr = tipc_port_lock(ref); @@ -1151,15 +1127,15 @@ int tipc_disconnect(u32 ref) */ int tipc_shutdown(u32 ref) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct sk_buff *buf = NULL; p_ptr = tipc_port_lock(ref); if (!p_ptr) return -EINVAL; - if (p_ptr->publ.connected) { - u32 imp = msg_importance(&p_ptr->publ.phdr); + if (p_ptr->connected) { + u32 imp = msg_importance(&p_ptr->phdr); if (imp < TIPC_CRITICAL_IMPORTANCE) imp++; buf = port_build_proto_msg(port_peerport(p_ptr), @@ -1169,7 +1145,6 @@ int tipc_shutdown(u32 ref) imp, TIPC_CONN_MSG, TIPC_CONN_SHUTDOWN, - port_out_seqno(p_ptr), 0); } tipc_port_unlock(p_ptr); @@ -1182,13 +1157,13 @@ int tipc_shutdown(u32 ref) * message for this node. */ -static int tipc_port_recv_sections(struct port *sender, unsigned int num_sect, +static int tipc_port_recv_sections(struct tipc_port *sender, unsigned int num_sect, struct iovec const *msg_sect) { struct sk_buff *buf; int res; - res = tipc_msg_build(&sender->publ.phdr, msg_sect, num_sect, + res = tipc_msg_build(&sender->phdr, msg_sect, num_sect, MAX_MSG_SIZE, !sender->user_port, &buf); if (likely(buf)) tipc_port_recv_msg(buf); @@ -1201,15 +1176,15 @@ static int tipc_port_recv_sections(struct port *sender, unsigned int num_sect, int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) { - struct port *p_ptr; + struct tipc_port *p_ptr; u32 destnode; int res; p_ptr = tipc_port_deref(ref); - if (!p_ptr || !p_ptr->publ.connected) + if (!p_ptr || !p_ptr->connected) return -EINVAL; - p_ptr->publ.congested = 1; + p_ptr->congested = 1; if (!tipc_port_congested(p_ptr)) { destnode = port_peernode(p_ptr); if (likely(destnode != tipc_own_addr)) @@ -1219,14 +1194,14 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect); if (likely(res != -ELINKCONG)) { - port_incr_out_seqno(p_ptr); - p_ptr->publ.congested = 0; - p_ptr->sent++; + p_ptr->congested = 0; + if (res > 0) + p_ptr->sent++; return res; } } if (port_unreliable(p_ptr)) { - p_ptr->publ.congested = 0; + p_ptr->congested = 0; /* Just calculate msg length and return */ return tipc_msg_calc_data_size(msg_sect, num_sect); } @@ -1240,17 +1215,17 @@ int tipc_send(u32 ref, unsigned int num_sect, struct iovec const *msg_sect) int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, unsigned int num_sect, struct iovec const *msg_sect) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg; u32 destnode = domain; u32 destport; int res; p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->publ.connected) + if (!p_ptr || p_ptr->connected) return -EINVAL; - msg = &p_ptr->publ.phdr; + msg = &p_ptr->phdr; msg_set_type(msg, TIPC_NAMED_MSG); msg_set_orignode(msg, tipc_own_addr); msg_set_origport(msg, ref); @@ -1263,13 +1238,17 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, msg_set_destport(msg, destport); if (likely(destport)) { - p_ptr->sent++; if (likely(destnode == tipc_own_addr)) - return tipc_port_recv_sections(p_ptr, num_sect, msg_sect); - res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, - destnode); - if (likely(res != -ELINKCONG)) + res = tipc_port_recv_sections(p_ptr, num_sect, + msg_sect); + else + res = tipc_link_send_sections_fast(p_ptr, msg_sect, + num_sect, destnode); + if (likely(res != -ELINKCONG)) { + if (res > 0) + p_ptr->sent++; return res; + } if (port_unreliable(p_ptr)) { /* Just calculate msg length and return */ return tipc_msg_calc_data_size(msg_sect, num_sect); @@ -1287,27 +1266,32 @@ int tipc_send2name(u32 ref, struct tipc_name const *name, unsigned int domain, int tipc_send2port(u32 ref, struct tipc_portid const *dest, unsigned int num_sect, struct iovec const *msg_sect) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg; int res; p_ptr = tipc_port_deref(ref); - if (!p_ptr || p_ptr->publ.connected) + if (!p_ptr || p_ptr->connected) return -EINVAL; - msg = &p_ptr->publ.phdr; + msg = &p_ptr->phdr; msg_set_type(msg, TIPC_DIRECT_MSG); msg_set_orignode(msg, tipc_own_addr); msg_set_origport(msg, ref); msg_set_destnode(msg, dest->node); msg_set_destport(msg, dest->ref); msg_set_hdr_sz(msg, DIR_MSG_H_SIZE); - p_ptr->sent++; + if (dest->node == tipc_own_addr) - return tipc_port_recv_sections(p_ptr, num_sect, msg_sect); - res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, dest->node); - if (likely(res != -ELINKCONG)) + res = tipc_port_recv_sections(p_ptr, num_sect, msg_sect); + else + res = tipc_link_send_sections_fast(p_ptr, msg_sect, num_sect, + dest->node); + if (likely(res != -ELINKCONG)) { + if (res > 0) + p_ptr->sent++; return res; + } if (port_unreliable(p_ptr)) { /* Just calculate msg length and return */ return tipc_msg_calc_data_size(msg_sect, num_sect); @@ -1322,15 +1306,15 @@ int tipc_send2port(u32 ref, struct tipc_portid const *dest, int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, struct sk_buff *buf, unsigned int dsz) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg; int res; - p_ptr = (struct port *)tipc_ref_deref(ref); - if (!p_ptr || p_ptr->publ.connected) + p_ptr = (struct tipc_port *)tipc_ref_deref(ref); + if (!p_ptr || p_ptr->connected) return -EINVAL; - msg = &p_ptr->publ.phdr; + msg = &p_ptr->phdr; msg_set_type(msg, TIPC_DIRECT_MSG); msg_set_orignode(msg, tipc_own_addr); msg_set_origport(msg, ref); @@ -1343,12 +1327,16 @@ int tipc_send_buf2port(u32 ref, struct tipc_portid const *dest, skb_push(buf, DIR_MSG_H_SIZE); skb_copy_to_linear_data(buf, msg, DIR_MSG_H_SIZE); - p_ptr->sent++; + if (dest->node == tipc_own_addr) - return tipc_port_recv_msg(buf); - res = tipc_send_buf_fast(buf, dest->node); - if (likely(res != -ELINKCONG)) + res = tipc_port_recv_msg(buf); + else + res = tipc_send_buf_fast(buf, dest->node); + if (likely(res != -ELINKCONG)) { + if (res > 0) + p_ptr->sent++; return res; + } if (port_unreliable(p_ptr)) return dsz; return -ELINKCONG; diff --git a/net/tipc/port.h b/net/tipc/port.h index 8e84b989949c..87b9424ae0ec 100644 --- a/net/tipc/port.h +++ b/net/tipc/port.h @@ -2,7 +2,7 @@ * net/tipc/port.h: Include file for TIPC port code * * Copyright (c) 1994-2007, Ericsson AB - * Copyright (c) 2004-2007, Wind River Systems + * Copyright (c) 2004-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -95,7 +95,7 @@ struct user_port { }; /** - * struct tipc_port - TIPC port info available to socket API + * struct tipc_port - TIPC port structure * @usr_handle: pointer to additional user-defined information about port * @lock: pointer to spinlock for controlling access to port * @connected: non-zero if port is currently connected to a peer port @@ -107,43 +107,33 @@ struct user_port { * @max_pkt: maximum packet size "hint" used when building messages sent by port * @ref: unique reference to port in TIPC object registry * @phdr: preformatted message header used when sending messages - */ -struct tipc_port { - void *usr_handle; - spinlock_t *lock; - int connected; - u32 conn_type; - u32 conn_instance; - u32 conn_unacked; - int published; - u32 congested; - u32 max_pkt; - u32 ref; - struct tipc_msg phdr; -}; - -/** - * struct port - TIPC port structure - * @publ: TIPC port info available to privileged users * @port_list: adjacent ports in TIPC's global list of ports * @dispatcher: ptr to routine which handles received messages * @wakeup: ptr to routine to call when port is no longer congested * @user_port: ptr to user port associated with port (if any) * @wait_list: adjacent ports in list of ports waiting on link congestion * @waiting_pkts: - * @sent: - * @acked: + * @sent: # of non-empty messages sent by port + * @acked: # of non-empty message acknowledgements from connected port's peer * @publications: list of publications for port * @pub_count: total # of publications port has made during its lifetime * @probing_state: * @probing_interval: - * @last_in_seqno: * @timer_ref: * @subscription: "node down" subscription used to terminate failed connections */ - -struct port { - struct tipc_port publ; +struct tipc_port { + void *usr_handle; + spinlock_t *lock; + int connected; + u32 conn_type; + u32 conn_instance; + u32 conn_unacked; + int published; + u32 congested; + u32 max_pkt; + u32 ref; + struct tipc_msg phdr; struct list_head port_list; u32 (*dispatcher)(struct tipc_port *, struct sk_buff *); void (*wakeup)(struct tipc_port *); @@ -156,7 +146,6 @@ struct port { u32 pub_count; u32 probing_state; u32 probing_interval; - u32 last_in_seqno; struct timer_list timer; struct tipc_node_subscr subscription; }; @@ -230,7 +219,7 @@ int tipc_send_buf2port(u32 portref, struct tipc_portid const *dest, int tipc_multicast(u32 portref, struct tipc_name_seq const *seq, unsigned int section_count, struct iovec const *msg); -int tipc_port_reject_sections(struct port *p_ptr, struct tipc_msg *hdr, +int tipc_port_reject_sections(struct tipc_port *p_ptr, struct tipc_msg *hdr, struct iovec const *msg_sect, u32 num_sect, int err); struct sk_buff *tipc_port_get_ports(void); @@ -242,9 +231,9 @@ void tipc_port_reinit(void); * tipc_port_lock - lock port instance referred to and return its pointer */ -static inline struct port *tipc_port_lock(u32 ref) +static inline struct tipc_port *tipc_port_lock(u32 ref) { - return (struct port *)tipc_ref_lock(ref); + return (struct tipc_port *)tipc_ref_lock(ref); } /** @@ -253,27 +242,27 @@ static inline struct port *tipc_port_lock(u32 ref) * Can use pointer instead of tipc_ref_unlock() since port is already locked. */ -static inline void tipc_port_unlock(struct port *p_ptr) +static inline void tipc_port_unlock(struct tipc_port *p_ptr) { - spin_unlock_bh(p_ptr->publ.lock); + spin_unlock_bh(p_ptr->lock); } -static inline struct port *tipc_port_deref(u32 ref) +static inline struct tipc_port *tipc_port_deref(u32 ref) { - return (struct port *)tipc_ref_deref(ref); + return (struct tipc_port *)tipc_ref_deref(ref); } -static inline u32 tipc_peer_port(struct port *p_ptr) +static inline u32 tipc_peer_port(struct tipc_port *p_ptr) { - return msg_destport(&p_ptr->publ.phdr); + return msg_destport(&p_ptr->phdr); } -static inline u32 tipc_peer_node(struct port *p_ptr) +static inline u32 tipc_peer_node(struct tipc_port *p_ptr) { - return msg_destnode(&p_ptr->publ.phdr); + return msg_destnode(&p_ptr->phdr); } -static inline int tipc_port_congested(struct port *p_ptr) +static inline int tipc_port_congested(struct tipc_port *p_ptr) { return (p_ptr->sent - p_ptr->acked) >= (TIPC_FLOW_CONTROL_WIN * 2); } @@ -284,7 +273,7 @@ static inline int tipc_port_congested(struct port *p_ptr) static inline int tipc_port_recv_msg(struct sk_buff *buf) { - struct port *p_ptr; + struct tipc_port *p_ptr; struct tipc_msg *msg = buf_msg(buf); u32 destport = msg_destport(msg); u32 dsz = msg_data_sz(msg); @@ -299,7 +288,7 @@ static inline int tipc_port_recv_msg(struct sk_buff *buf) /* validate destination & pass to port, otherwise reject message */ p_ptr = tipc_port_lock(destport); if (likely(p_ptr)) { - if (likely(p_ptr->publ.connected)) { + if (likely(p_ptr->connected)) { if ((unlikely(msg_origport(msg) != tipc_peer_port(p_ptr))) || (unlikely(msg_orignode(msg) != tipc_peer_node(p_ptr))) || (unlikely(!msg_connected(msg)))) { @@ -308,7 +297,7 @@ static inline int tipc_port_recv_msg(struct sk_buff *buf) goto reject; } } - err = p_ptr->dispatcher(&p_ptr->publ, buf); + err = p_ptr->dispatcher(p_ptr, buf); tipc_port_unlock(p_ptr); if (likely(!err)) return dsz; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 2b02a3a80313..125dcb0737b2 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2,7 +2,7 @@ * net/tipc/socket.c: TIPC socket API * * Copyright (c) 2001-2007, Ericsson AB - * Copyright (c) 2004-2008, Wind River Systems + * Copyright (c) 2004-2008, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -241,7 +241,6 @@ static int tipc_create(struct net *net, struct socket *sock, int protocol, tipc_set_portunreliable(tp_ptr->ref, 1); } - atomic_inc(&tipc_user_count); return 0; } @@ -321,7 +320,6 @@ static int release(struct socket *sock) sock_put(sk); sock->sk = NULL; - atomic_dec(&tipc_user_count); return res; } @@ -495,6 +493,8 @@ static int dest_name_check(struct sockaddr_tipc *dest, struct msghdr *m) if (likely(dest->addr.name.name.type != TIPC_CFG_SRV)) return -EACCES; + if (!m->msg_iovlen || (m->msg_iov[0].iov_len < sizeof(hdr))) + return -EMSGSIZE; if (copy_from_user(&hdr, m->msg_iov[0].iov_base, sizeof(hdr))) return -EFAULT; if ((ntohs(hdr.tcm_type) & 0xC000) && (!capable(CAP_NET_ADMIN))) diff --git a/net/tipc/subscr.c b/net/tipc/subscr.c index ca04479c3d42..aae9eae13404 100644 --- a/net/tipc/subscr.c +++ b/net/tipc/subscr.c @@ -2,7 +2,7 @@ * net/tipc/subscr.c: TIPC network topology service * * Copyright (c) 2000-2006, Ericsson AB - * Copyright (c) 2005-2007, Wind River Systems + * Copyright (c) 2005-2007, 2010-2011, Wind River Systems * All rights reserved. * * Redistribution and use in source and binary forms, with or without @@ -160,7 +160,7 @@ void tipc_subscr_report_overlap(struct subscription *sub, static void subscr_timeout(struct subscription *sub) { - struct port *server_port; + struct tipc_port *server_port; /* Validate server port reference (in case subscriber is terminating) */ @@ -472,8 +472,6 @@ static void subscr_named_msg_event(void *usr_handle, struct tipc_portid const *orig, struct tipc_name_seq const *dest) { - static struct iovec msg_sect = {NULL, 0}; - struct subscriber *subscriber; u32 server_port_ref; @@ -508,7 +506,7 @@ static void subscr_named_msg_event(void *usr_handle, /* Lock server port (& save lock address for future use) */ - subscriber->lock = tipc_port_lock(subscriber->port_ref)->publ.lock; + subscriber->lock = tipc_port_lock(subscriber->port_ref)->lock; /* Add subscriber to topology server's subscriber list */ @@ -523,7 +521,7 @@ static void subscr_named_msg_event(void *usr_handle, /* Send an ACK- to complete connection handshaking */ - tipc_send(server_port_ref, 1, &msg_sect); + tipc_send(server_port_ref, 0, NULL); /* Handle optional subscription request */ @@ -542,7 +540,6 @@ int tipc_subscr_start(void) spin_lock_init(&topsrv.lock); INIT_LIST_HEAD(&topsrv.subscriber_list); - spin_lock_bh(&topsrv.lock); res = tipc_createport(NULL, TIPC_CRITICAL_IMPORTANCE, NULL, @@ -563,12 +560,10 @@ int tipc_subscr_start(void) goto failed; } - spin_unlock_bh(&topsrv.lock); return 0; failed: err("Failed to create subscription service\n"); - spin_unlock_bh(&topsrv.lock); return res; } diff --git a/net/xfrm/xfrm_hash.h b/net/xfrm/xfrm_hash.h index 8e69533d2313..7199d78b2aa1 100644 --- a/net/xfrm/xfrm_hash.h +++ b/net/xfrm/xfrm_hash.h @@ -4,29 +4,32 @@ #include <linux/xfrm.h> #include <linux/socket.h> -static inline unsigned int __xfrm4_addr_hash(xfrm_address_t *addr) +static inline unsigned int __xfrm4_addr_hash(const xfrm_address_t *addr) { return ntohl(addr->a4); } -static inline unsigned int __xfrm6_addr_hash(xfrm_address_t *addr) +static inline unsigned int __xfrm6_addr_hash(const xfrm_address_t *addr) { return ntohl(addr->a6[2] ^ addr->a6[3]); } -static inline unsigned int __xfrm4_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) +static inline unsigned int __xfrm4_daddr_saddr_hash(const xfrm_address_t *daddr, + const xfrm_address_t *saddr) { u32 sum = (__force u32)daddr->a4 + (__force u32)saddr->a4; return ntohl((__force __be32)sum); } -static inline unsigned int __xfrm6_daddr_saddr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr) +static inline unsigned int __xfrm6_daddr_saddr_hash(const xfrm_address_t *daddr, + const xfrm_address_t *saddr) { return ntohl(daddr->a6[2] ^ daddr->a6[3] ^ saddr->a6[2] ^ saddr->a6[3]); } -static inline unsigned int __xfrm_dst_hash(xfrm_address_t *daddr, xfrm_address_t *saddr, +static inline unsigned int __xfrm_dst_hash(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, u32 reqid, unsigned short family, unsigned int hmask) { @@ -42,8 +45,8 @@ static inline unsigned int __xfrm_dst_hash(xfrm_address_t *daddr, xfrm_address_t return (h ^ (h >> 16)) & hmask; } -static inline unsigned __xfrm_src_hash(xfrm_address_t *daddr, - xfrm_address_t *saddr, +static inline unsigned __xfrm_src_hash(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, unsigned short family, unsigned int hmask) { @@ -60,8 +63,8 @@ static inline unsigned __xfrm_src_hash(xfrm_address_t *daddr, } static inline unsigned int -__xfrm_spi_hash(xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family, - unsigned int hmask) +__xfrm_spi_hash(const xfrm_address_t *daddr, __be32 spi, u8 proto, + unsigned short family, unsigned int hmask) { unsigned int h = (__force u32)spi ^ proto; switch (family) { @@ -80,10 +83,11 @@ static inline unsigned int __idx_hash(u32 index, unsigned int hmask) return (index ^ (index >> 8)) & hmask; } -static inline unsigned int __sel_hash(struct xfrm_selector *sel, unsigned short family, unsigned int hmask) +static inline unsigned int __sel_hash(const struct xfrm_selector *sel, + unsigned short family, unsigned int hmask) { - xfrm_address_t *daddr = &sel->daddr; - xfrm_address_t *saddr = &sel->saddr; + const xfrm_address_t *daddr = &sel->daddr; + const xfrm_address_t *saddr = &sel->saddr; unsigned int h = 0; switch (family) { @@ -107,7 +111,9 @@ static inline unsigned int __sel_hash(struct xfrm_selector *sel, unsigned short return h & hmask; } -static inline unsigned int __addr_hash(xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, unsigned int hmask) +static inline unsigned int __addr_hash(const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + unsigned short family, unsigned int hmask) { unsigned int h = 0; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7a8e2c77d08f..41a91d27d3ea 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -51,14 +51,14 @@ static void xfrm_policy_put_afinfo(struct xfrm_policy_afinfo *afinfo); static void xfrm_init_pmtu(struct dst_entry *dst); static int stale_bundle(struct dst_entry *dst); static int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *xdst, - struct flowi *fl, int family, int strict); + const struct flowi *fl, int family); static struct xfrm_policy *__xfrm_policy_unlink(struct xfrm_policy *pol, int dir); static inline int -__xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl) +__xfrm4_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { return addr_match(&fl->fl4_dst, &sel->daddr, sel->prefixlen_d) && addr_match(&fl->fl4_src, &sel->saddr, sel->prefixlen_s) && @@ -69,7 +69,7 @@ __xfrm4_selector_match(struct xfrm_selector *sel, struct flowi *fl) } static inline int -__xfrm6_selector_match(struct xfrm_selector *sel, struct flowi *fl) +__xfrm6_selector_match(const struct xfrm_selector *sel, const struct flowi *fl) { return addr_match(&fl->fl6_dst, &sel->daddr, sel->prefixlen_d) && addr_match(&fl->fl6_src, &sel->saddr, sel->prefixlen_s) && @@ -79,8 +79,8 @@ __xfrm6_selector_match(struct xfrm_selector *sel, struct flowi *fl) (fl->oif == sel->ifindex || !sel->ifindex); } -int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, - unsigned short family) +int xfrm_selector_match(const struct xfrm_selector *sel, const struct flowi *fl, + unsigned short family) { switch (family) { case AF_INET: @@ -92,8 +92,8 @@ int xfrm_selector_match(struct xfrm_selector *sel, struct flowi *fl, } static inline struct dst_entry *__xfrm_dst_lookup(struct net *net, int tos, - xfrm_address_t *saddr, - xfrm_address_t *daddr, + const xfrm_address_t *saddr, + const xfrm_address_t *daddr, int family) { struct xfrm_policy_afinfo *afinfo; @@ -311,7 +311,9 @@ static inline unsigned int idx_hash(struct net *net, u32 index) return __idx_hash(index, net->xfrm.policy_idx_hmask); } -static struct hlist_head *policy_hash_bysel(struct net *net, struct xfrm_selector *sel, unsigned short family, int dir) +static struct hlist_head *policy_hash_bysel(struct net *net, + const struct xfrm_selector *sel, + unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash = __sel_hash(sel, family, hmask); @@ -321,7 +323,10 @@ static struct hlist_head *policy_hash_bysel(struct net *net, struct xfrm_selecto net->xfrm.policy_bydst[dir].table + hash); } -static struct hlist_head *policy_hash_direct(struct net *net, xfrm_address_t *daddr, xfrm_address_t *saddr, unsigned short family, int dir) +static struct hlist_head *policy_hash_direct(struct net *net, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + unsigned short family, int dir) { unsigned int hmask = net->xfrm.policy_bydst[dir].hmask; unsigned int hash = __addr_hash(daddr, saddr, family, hmask); @@ -864,10 +869,11 @@ EXPORT_SYMBOL(xfrm_policy_walk_done); * * Returns 0 if policy found, else an -errno. */ -static int xfrm_policy_match(struct xfrm_policy *pol, struct flowi *fl, +static int xfrm_policy_match(const struct xfrm_policy *pol, + const struct flowi *fl, u8 type, u16 family, int dir) { - struct xfrm_selector *sel = &pol->selector; + const struct xfrm_selector *sel = &pol->selector; int match, ret = -ESRCH; if (pol->family != family || @@ -884,12 +890,12 @@ static int xfrm_policy_match(struct xfrm_policy *pol, struct flowi *fl, } static struct xfrm_policy *xfrm_policy_lookup_bytype(struct net *net, u8 type, - struct flowi *fl, + const struct flowi *fl, u16 family, u8 dir) { int err; struct xfrm_policy *pol, *ret; - xfrm_address_t *daddr, *saddr; + const xfrm_address_t *daddr, *saddr; struct hlist_node *entry; struct hlist_head *chain; u32 priority = ~0U; @@ -941,7 +947,7 @@ fail: } static struct xfrm_policy * -__xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir) +__xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_policy *pol; @@ -954,7 +960,7 @@ __xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir) } static struct flow_cache_object * -xfrm_policy_lookup(struct net *net, struct flowi *fl, u16 family, +xfrm_policy_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *old_obj, void *ctx) { struct xfrm_policy *pol; @@ -990,7 +996,8 @@ static inline int policy_to_flow_dir(int dir) } } -static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, struct flowi *fl) +static struct xfrm_policy *xfrm_sk_policy_lookup(struct sock *sk, int dir, + const struct flowi *fl) { struct xfrm_policy *pol; @@ -1098,7 +1105,7 @@ int xfrm_sk_policy_insert(struct sock *sk, int dir, struct xfrm_policy *pol) return 0; } -static struct xfrm_policy *clone_policy(struct xfrm_policy *old, int dir) +static struct xfrm_policy *clone_policy(const struct xfrm_policy *old, int dir) { struct xfrm_policy *newp = xfrm_policy_alloc(xp_net(old), GFP_ATOMIC); @@ -1157,9 +1164,8 @@ xfrm_get_saddr(struct net *net, xfrm_address_t *local, xfrm_address_t *remote, /* Resolve list of templates for the flow, given policy. */ static int -xfrm_tmpl_resolve_one(struct xfrm_policy *policy, struct flowi *fl, - struct xfrm_state **xfrm, - unsigned short family) +xfrm_tmpl_resolve_one(struct xfrm_policy *policy, const struct flowi *fl, + struct xfrm_state **xfrm, unsigned short family) { struct net *net = xp_net(policy); int nx; @@ -1214,9 +1220,8 @@ fail: } static int -xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, - struct xfrm_state **xfrm, - unsigned short family) +xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, const struct flowi *fl, + struct xfrm_state **xfrm, unsigned short family) { struct xfrm_state *tp[XFRM_MAX_DEPTH]; struct xfrm_state **tpp = (npols > 1) ? tp : xfrm; @@ -1256,7 +1261,7 @@ xfrm_tmpl_resolve(struct xfrm_policy **pols, int npols, struct flowi *fl, * still valid. */ -static inline int xfrm_get_tos(struct flowi *fl, int family) +static inline int xfrm_get_tos(const struct flowi *fl, int family) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(family); int tos; @@ -1369,7 +1374,7 @@ static inline int xfrm_init_path(struct xfrm_dst *path, struct dst_entry *dst, } static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, - struct flowi *fl) + const struct flowi *fl) { struct xfrm_policy_afinfo *afinfo = xfrm_policy_get_afinfo(xdst->u.dst.ops->family); @@ -1392,7 +1397,7 @@ static inline int xfrm_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, static struct dst_entry *xfrm_bundle_create(struct xfrm_policy *policy, struct xfrm_state **xfrm, int nx, - struct flowi *fl, + const struct flowi *fl, struct dst_entry *dst) { struct net *net = xp_net(policy); @@ -1508,7 +1513,7 @@ free_dst: } static int inline -xfrm_dst_alloc_copy(void **target, void *src, int size) +xfrm_dst_alloc_copy(void **target, const void *src, int size) { if (!*target) { *target = kmalloc(size, GFP_ATOMIC); @@ -1520,7 +1525,7 @@ xfrm_dst_alloc_copy(void **target, void *src, int size) } static int inline -xfrm_dst_update_parent(struct dst_entry *dst, struct xfrm_selector *sel) +xfrm_dst_update_parent(struct dst_entry *dst, const struct xfrm_selector *sel) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -1532,7 +1537,7 @@ xfrm_dst_update_parent(struct dst_entry *dst, struct xfrm_selector *sel) } static int inline -xfrm_dst_update_origin(struct dst_entry *dst, struct flowi *fl) +xfrm_dst_update_origin(struct dst_entry *dst, const struct flowi *fl) { #ifdef CONFIG_XFRM_SUB_POLICY struct xfrm_dst *xdst = (struct xfrm_dst *)dst; @@ -1542,7 +1547,7 @@ xfrm_dst_update_origin(struct dst_entry *dst, struct flowi *fl) #endif } -static int xfrm_expand_policies(struct flowi *fl, u16 family, +static int xfrm_expand_policies(const struct flowi *fl, u16 family, struct xfrm_policy **pols, int *num_pols, int *num_xfrms) { @@ -1588,7 +1593,7 @@ static int xfrm_expand_policies(struct flowi *fl, u16 family, static struct xfrm_dst * xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, - struct flowi *fl, u16 family, + const struct flowi *fl, u16 family, struct dst_entry *dst_orig) { struct net *net = xp_net(pols[0]); @@ -1631,7 +1636,7 @@ xfrm_resolve_and_create_bundle(struct xfrm_policy **pols, int num_pols, } static struct flow_cache_object * -xfrm_bundle_lookup(struct net *net, struct flowi *fl, u16 family, u8 dir, +xfrm_bundle_lookup(struct net *net, const struct flowi *fl, u16 family, u8 dir, struct flow_cache_object *oldflo, void *ctx) { struct dst_entry *dst_orig = (struct dst_entry *)ctx; @@ -1735,7 +1740,8 @@ error: * At the moment we eat a raw IP route. Mostly to speed up lookups * on interfaces with disabled IPsec. */ -int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl, +int __xfrm_lookup(struct net *net, struct dst_entry **dst_p, + const struct flowi *fl, struct sock *sk, int flags) { struct xfrm_policy *pols[XFRM_POLICY_TYPE_MAX]; @@ -1891,7 +1897,8 @@ dropdst: } EXPORT_SYMBOL(__xfrm_lookup); -int xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl, +int xfrm_lookup(struct net *net, struct dst_entry **dst_p, + const struct flowi *fl, struct sock *sk, int flags) { int err = __xfrm_lookup(net, dst_p, fl, sk, flags); @@ -1907,7 +1914,7 @@ int xfrm_lookup(struct net *net, struct dst_entry **dst_p, struct flowi *fl, EXPORT_SYMBOL(xfrm_lookup); static inline int -xfrm_secpath_reject(int idx, struct sk_buff *skb, struct flowi *fl) +xfrm_secpath_reject(int idx, struct sk_buff *skb, const struct flowi *fl) { struct xfrm_state *x; @@ -1926,7 +1933,7 @@ xfrm_secpath_reject(int idx, struct sk_buff *skb, struct flowi *fl) */ static inline int -xfrm_state_ok(struct xfrm_tmpl *tmpl, struct xfrm_state *x, +xfrm_state_ok(const struct xfrm_tmpl *tmpl, const struct xfrm_state *x, unsigned short family) { if (xfrm_state_kern(x)) @@ -1949,7 +1956,7 @@ xfrm_state_ok(struct xfrm_tmpl *tmpl, struct xfrm_state *x, * Otherwise "-2 - errored_index" is returned. */ static inline int -xfrm_policy_ok(struct xfrm_tmpl *tmpl, struct sec_path *sp, int start, +xfrm_policy_ok(const struct xfrm_tmpl *tmpl, const struct sec_path *sp, int start, unsigned short family) { int idx = start; @@ -1987,7 +1994,7 @@ int __xfrm_decode_session(struct sk_buff *skb, struct flowi *fl, } EXPORT_SYMBOL(__xfrm_decode_session); -static inline int secpath_has_nontransport(struct sec_path *sp, int k, int *idxp) +static inline int secpath_has_nontransport(const struct sec_path *sp, int k, int *idxp) { for (; k < sp->len; k++) { if (sp->xvec[k]->props.mode != XFRM_MODE_TRANSPORT) { @@ -2210,7 +2217,7 @@ static struct dst_entry *xfrm_dst_check(struct dst_entry *dst, u32 cookie) static int stale_bundle(struct dst_entry *dst) { - return !xfrm_bundle_ok(NULL, (struct xfrm_dst *)dst, NULL, AF_UNSPEC, 0); + return !xfrm_bundle_ok(NULL, (struct xfrm_dst *)dst, NULL, AF_UNSPEC); } void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev) @@ -2283,7 +2290,7 @@ static void xfrm_init_pmtu(struct dst_entry *dst) */ static int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, - struct flowi *fl, int family, int strict) + const struct flowi *fl, int family) { struct dst_entry *dst = &first->u.dst; struct xfrm_dst *last; @@ -2320,11 +2327,6 @@ static int xfrm_bundle_ok(struct xfrm_policy *pol, struct xfrm_dst *first, xdst->policy_genid != atomic_read(&xdst->pols[0]->genid)) return 0; - if (strict && fl && - !(dst->xfrm->outer_mode->flags & XFRM_MODE_FLAG_TUNNEL) && - !xfrm_state_addr_flow_check(dst->xfrm, fl, family)) - return 0; - mtu = dst_mtu(dst->child); if (xdst->child_mtu_cached != mtu) { last = xdst; @@ -2735,8 +2737,8 @@ EXPORT_SYMBOL_GPL(xfrm_audit_policy_delete); #endif #ifdef CONFIG_XFRM_MIGRATE -static int xfrm_migrate_selector_match(struct xfrm_selector *sel_cmp, - struct xfrm_selector *sel_tgt) +static int xfrm_migrate_selector_match(const struct xfrm_selector *sel_cmp, + const struct xfrm_selector *sel_tgt) { if (sel_cmp->proto == IPSEC_ULPROTO_ANY) { if (sel_tgt->family == sel_cmp->family && @@ -2756,7 +2758,7 @@ static int xfrm_migrate_selector_match(struct xfrm_selector *sel_cmp, return 0; } -static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, +static struct xfrm_policy * xfrm_migrate_policy_find(const struct xfrm_selector *sel, u8 dir, u8 type) { struct xfrm_policy *pol, *ret = NULL; @@ -2792,7 +2794,7 @@ static struct xfrm_policy * xfrm_migrate_policy_find(struct xfrm_selector *sel, return ret; } -static int migrate_tmpl_match(struct xfrm_migrate *m, struct xfrm_tmpl *t) +static int migrate_tmpl_match(const struct xfrm_migrate *m, const struct xfrm_tmpl *t) { int match = 0; @@ -2862,7 +2864,7 @@ static int xfrm_policy_migrate(struct xfrm_policy *pol, return 0; } -static int xfrm_migrate_check(struct xfrm_migrate *m, int num_migrate) +static int xfrm_migrate_check(const struct xfrm_migrate *m, int num_migrate) { int i, j; @@ -2896,7 +2898,7 @@ static int xfrm_migrate_check(struct xfrm_migrate *m, int num_migrate) return 0; } -int xfrm_migrate(struct xfrm_selector *sel, u8 dir, u8 type, +int xfrm_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, struct xfrm_migrate *m, int num_migrate, struct xfrm_kmaddress *k) { diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 220ebc05c7af..8496b3d3e85b 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -50,8 +50,8 @@ static void xfrm_audit_state_replay(struct xfrm_state *x, #endif /* CONFIG_AUDITSYSCALL */ static inline unsigned int xfrm_dst_hash(struct net *net, - xfrm_address_t *daddr, - xfrm_address_t *saddr, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, u32 reqid, unsigned short family) { @@ -59,15 +59,16 @@ static inline unsigned int xfrm_dst_hash(struct net *net, } static inline unsigned int xfrm_src_hash(struct net *net, - xfrm_address_t *daddr, - xfrm_address_t *saddr, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, unsigned short family) { return __xfrm_src_hash(daddr, saddr, family, net->xfrm.state_hmask); } static inline unsigned int -xfrm_spi_hash(struct net *net, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) +xfrm_spi_hash(struct net *net, const xfrm_address_t *daddr, + __be32 spi, u8 proto, unsigned short family) { return __xfrm_spi_hash(daddr, spi, proto, family, net->xfrm.state_hmask); } @@ -656,9 +657,9 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) EXPORT_SYMBOL(xfrm_sad_getinfo); static int -xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr, +xfrm_init_tempstate(struct xfrm_state *x, const struct flowi *fl, + const struct xfrm_tmpl *tmpl, + const xfrm_address_t *daddr, const xfrm_address_t *saddr, unsigned short family) { struct xfrm_state_afinfo *afinfo = xfrm_state_get_afinfo(family); @@ -677,7 +678,10 @@ xfrm_init_tempstate(struct xfrm_state *x, struct flowi *fl, return 0; } -static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, xfrm_address_t *daddr, __be32 spi, u8 proto, unsigned short family) +static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, + const xfrm_address_t *daddr, + __be32 spi, u8 proto, + unsigned short family) { unsigned int h = xfrm_spi_hash(net, daddr, spi, proto, family); struct xfrm_state *x; @@ -699,7 +703,10 @@ static struct xfrm_state *__xfrm_state_lookup(struct net *net, u32 mark, xfrm_ad return NULL; } -static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, xfrm_address_t *daddr, xfrm_address_t *saddr, u8 proto, unsigned short family) +static struct xfrm_state *__xfrm_state_lookup_byaddr(struct net *net, u32 mark, + const xfrm_address_t *daddr, + const xfrm_address_t *saddr, + u8 proto, unsigned short family) { unsigned int h = xfrm_src_hash(net, daddr, saddr, family); struct xfrm_state *x; @@ -746,8 +753,7 @@ static void xfrm_hash_grow_check(struct net *net, int have_hash_collision) } static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, - struct flowi *fl, unsigned short family, - xfrm_address_t *daddr, xfrm_address_t *saddr, + const struct flowi *fl, unsigned short family, struct xfrm_state **best, int *acq_in_progress, int *error) { @@ -784,8 +790,8 @@ static void xfrm_state_look_at(struct xfrm_policy *pol, struct xfrm_state *x, } struct xfrm_state * -xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, - struct flowi *fl, struct xfrm_tmpl *tmpl, +xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, + const struct flowi *fl, struct xfrm_tmpl *tmpl, struct xfrm_policy *pol, int *err, unsigned short family) { @@ -813,7 +819,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, &best, &acquire_in_progress, &error); } if (best) @@ -829,7 +835,7 @@ xfrm_state_find(xfrm_address_t *daddr, xfrm_address_t *saddr, tmpl->mode == x->props.mode && tmpl->id.proto == x->id.proto && (tmpl->id.spi == x->id.spi || !tmpl->id.spi)) - xfrm_state_look_at(pol, x, fl, encap_family, daddr, saddr, + xfrm_state_look_at(pol, x, fl, encap_family, &best, &acquire_in_progress, &error); } @@ -1727,7 +1733,7 @@ void xfrm_replay_advance(struct xfrm_state *x, __be32 net_seq) static LIST_HEAD(xfrm_km_list); static DEFINE_RWLOCK(xfrm_km_lock); -void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +void km_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct xfrm_mgr *km; @@ -1738,7 +1744,7 @@ void km_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) read_unlock(&xfrm_km_lock); } -void km_state_notify(struct xfrm_state *x, struct km_event *c) +void km_state_notify(struct xfrm_state *x, const struct km_event *c) { struct xfrm_mgr *km; read_lock(&xfrm_km_lock); @@ -1819,9 +1825,9 @@ void km_policy_expired(struct xfrm_policy *pol, int dir, int hard, u32 pid) EXPORT_SYMBOL(km_policy_expired); #ifdef CONFIG_XFRM_MIGRATE -int km_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k) +int km_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_migrate, + const struct xfrm_kmaddress *k) { int err = -EINVAL; int ret; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 61291965c5f6..b43c1b1240d4 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1582,7 +1582,7 @@ static inline size_t xfrm_aevent_msgsize(void) + nla_total_size(4); /* XFRM_AE_ETHR */ } -static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c) +static int build_aevent(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) { struct xfrm_aevent_id *id; struct nlmsghdr *nlh; @@ -1986,7 +1986,7 @@ static int xfrm_do_migrate(struct sk_buff *skb, struct nlmsghdr *nlh, #endif #ifdef CONFIG_XFRM_MIGRATE -static int copy_to_user_migrate(struct xfrm_migrate *m, struct sk_buff *skb) +static int copy_to_user_migrate(const struct xfrm_migrate *m, struct sk_buff *skb) { struct xfrm_user_migrate um; @@ -2004,7 +2004,7 @@ static int copy_to_user_migrate(struct xfrm_migrate *m, struct sk_buff *skb) return nla_put(skb, XFRMA_MIGRATE, sizeof(um), &um); } -static int copy_to_user_kmaddress(struct xfrm_kmaddress *k, struct sk_buff *skb) +static int copy_to_user_kmaddress(const struct xfrm_kmaddress *k, struct sk_buff *skb) { struct xfrm_user_kmaddress uk; @@ -2025,11 +2025,11 @@ static inline size_t xfrm_migrate_msgsize(int num_migrate, int with_kma) + userpolicy_type_attrsize(); } -static int build_migrate(struct sk_buff *skb, struct xfrm_migrate *m, - int num_migrate, struct xfrm_kmaddress *k, - struct xfrm_selector *sel, u8 dir, u8 type) +static int build_migrate(struct sk_buff *skb, const struct xfrm_migrate *m, + int num_migrate, const struct xfrm_kmaddress *k, + const struct xfrm_selector *sel, u8 dir, u8 type) { - struct xfrm_migrate *mp; + const struct xfrm_migrate *mp; struct xfrm_userpolicy_id *pol_id; struct nlmsghdr *nlh; int i; @@ -2061,9 +2061,9 @@ nlmsg_failure: return -EMSGSIZE; } -static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k) +static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_migrate, + const struct xfrm_kmaddress *k) { struct net *net = &init_net; struct sk_buff *skb; @@ -2079,9 +2079,9 @@ static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_MIGRATE, GFP_ATOMIC); } #else -static int xfrm_send_migrate(struct xfrm_selector *sel, u8 dir, u8 type, - struct xfrm_migrate *m, int num_migrate, - struct xfrm_kmaddress *k) +static int xfrm_send_migrate(const struct xfrm_selector *sel, u8 dir, u8 type, + const struct xfrm_migrate *m, int num_migrate, + const struct xfrm_kmaddress *k) { return -ENOPROTOOPT; } @@ -2220,7 +2220,7 @@ static inline size_t xfrm_expire_msgsize(void) + nla_total_size(sizeof(struct xfrm_mark)); } -static int build_expire(struct sk_buff *skb, struct xfrm_state *x, struct km_event *c) +static int build_expire(struct sk_buff *skb, struct xfrm_state *x, const struct km_event *c) { struct xfrm_user_expire *ue; struct nlmsghdr *nlh; @@ -2242,7 +2242,7 @@ nla_put_failure: return -EMSGSIZE; } -static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) +static int xfrm_exp_state_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = xs_net(x); struct sk_buff *skb; @@ -2259,7 +2259,7 @@ static int xfrm_exp_state_notify(struct xfrm_state *x, struct km_event *c) return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); } -static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c) +static int xfrm_aevent_state_notify(struct xfrm_state *x, const struct km_event *c) { struct net *net = xs_net(x); struct sk_buff *skb; @@ -2274,7 +2274,7 @@ static int xfrm_aevent_state_notify(struct xfrm_state *x, struct km_event *c) return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_AEVENTS, GFP_ATOMIC); } -static int xfrm_notify_sa_flush(struct km_event *c) +static int xfrm_notify_sa_flush(const struct km_event *c) { struct net *net = c->net; struct xfrm_usersa_flush *p; @@ -2330,7 +2330,7 @@ static inline size_t xfrm_sa_len(struct xfrm_state *x) return l; } -static int xfrm_notify_sa(struct xfrm_state *x, struct km_event *c) +static int xfrm_notify_sa(struct xfrm_state *x, const struct km_event *c) { struct net *net = xs_net(x); struct xfrm_usersa_info *p; @@ -2387,7 +2387,7 @@ nla_put_failure: return -1; } -static int xfrm_send_state_notify(struct xfrm_state *x, struct km_event *c) +static int xfrm_send_state_notify(struct xfrm_state *x, const struct km_event *c) { switch (c->event) { @@ -2546,7 +2546,7 @@ static inline size_t xfrm_polexpire_msgsize(struct xfrm_policy *xp) } static int build_polexpire(struct sk_buff *skb, struct xfrm_policy *xp, - int dir, struct km_event *c) + int dir, const struct km_event *c) { struct xfrm_user_polexpire *upe; struct nlmsghdr *nlh; @@ -2576,7 +2576,7 @@ nlmsg_failure: return -EMSGSIZE; } -static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct net *net = xp_net(xp); struct sk_buff *skb; @@ -2591,7 +2591,7 @@ static int xfrm_exp_policy_notify(struct xfrm_policy *xp, int dir, struct km_eve return nlmsg_multicast(net->xfrm.nlsk, skb, 0, XFRMNLGRP_EXPIRE, GFP_ATOMIC); } -static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, struct km_event *c) +static int xfrm_notify_policy(struct xfrm_policy *xp, int dir, const struct km_event *c) { struct net *net = xp_net(xp); struct xfrm_userpolicy_info *p; @@ -2656,7 +2656,7 @@ nlmsg_failure: return -1; } -static int xfrm_notify_policy_flush(struct km_event *c) +static int xfrm_notify_policy_flush(const struct km_event *c) { struct net *net = c->net; struct nlmsghdr *nlh; @@ -2681,7 +2681,7 @@ nlmsg_failure: return -1; } -static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, struct km_event *c) +static int xfrm_send_policy_notify(struct xfrm_policy *xp, int dir, const struct km_event *c) { switch (c->event) { diff --git a/security/capability.c b/security/capability.c index 2a5df2b7da83..b8eeaee5c99e 100644 --- a/security/capability.c +++ b/security/capability.c @@ -760,7 +760,7 @@ static int cap_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 sk_sid, u8 dir) static int cap_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, - struct flowi *fl) + const struct flowi *fl) { return 1; } diff --git a/security/security.c b/security/security.c index 7b7308ace8c5..8ef1f7dff277 100644 --- a/security/security.c +++ b/security/security.c @@ -1233,7 +1233,8 @@ int security_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) } int security_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl) + struct xfrm_policy *xp, + const struct flowi *fl) { return security_ops->xfrm_state_pol_flow_match(x, xp, fl); } diff --git a/security/selinux/include/xfrm.h b/security/selinux/include/xfrm.h index 13128f9a3e5a..b43813c9e049 100644 --- a/security/selinux/include/xfrm.h +++ b/security/selinux/include/xfrm.h @@ -19,7 +19,7 @@ void selinux_xfrm_state_free(struct xfrm_state *x); int selinux_xfrm_state_delete(struct xfrm_state *x); int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir); int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, - struct xfrm_policy *xp, struct flowi *fl); + struct xfrm_policy *xp, const struct flowi *fl); /* * Extract the security blob from the sock (it's actually on the socket) diff --git a/security/selinux/xfrm.c b/security/selinux/xfrm.c index fff78d3b51a2..c43ab542246c 100644 --- a/security/selinux/xfrm.c +++ b/security/selinux/xfrm.c @@ -112,7 +112,7 @@ int selinux_xfrm_policy_lookup(struct xfrm_sec_ctx *ctx, u32 fl_secid, u8 dir) */ int selinux_xfrm_state_pol_flow_match(struct xfrm_state *x, struct xfrm_policy *xp, - struct flowi *fl) + const struct flowi *fl) { u32 state_sid; int rc; |