diff options
Diffstat (limited to 'drivers')
45 files changed, 664 insertions, 332 deletions
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c index bda5994ceb6..8b72cf392b3 100644 --- a/drivers/infiniband/hw/mlx4/main.c +++ b/drivers/infiniband/hw/mlx4/main.c @@ -1173,18 +1173,24 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp, err = __mlx4_ib_create_flow(qp, flow_attr, domain, type[i], &mflow->reg_id[i]); if (err) - goto err_free; + goto err_create_flow; i++; } if (i < ARRAY_SIZE(type) && flow_attr->type == IB_FLOW_ATTR_NORMAL) { err = mlx4_ib_tunnel_steer_add(qp, flow_attr, &mflow->reg_id[i]); if (err) - goto err_free; + goto err_create_flow; + i++; } return &mflow->ibflow; +err_create_flow: + while (i) { + (void)__mlx4_ib_destroy_flow(to_mdev(qp->device)->dev, mflow->reg_id[i]); + i--; + } err_free: kfree(mflow); return ERR_PTR(err); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 4706386b7d3..f9009be3f30 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -135,6 +135,7 @@ config MACVLAN config MACVTAP tristate "MAC-VLAN based tap driver" depends on MACVLAN + depends on INET help This adds a specialized tap character device driver that is based on the MAC-VLAN network interface, called macvtap. A macvtap device @@ -200,6 +201,7 @@ config RIONET_RX_SIZE config TUN tristate "Universal TUN/TAP device driver support" + depends on INET select CRC32 ---help--- TUN/TAP provides packet reception and transmission for user space diff --git a/drivers/net/dsa/mv88e6171.c b/drivers/net/dsa/mv88e6171.c index 1020a7af67c..78d8e876f3a 100644 --- a/drivers/net/dsa/mv88e6171.c +++ b/drivers/net/dsa/mv88e6171.c @@ -395,7 +395,7 @@ static int mv88e6171_get_sset_count(struct dsa_switch *ds) } struct dsa_switch_driver mv88e6171_switch_driver = { - .tag_protocol = DSA_TAG_PROTO_DSA, + .tag_protocol = DSA_TAG_PROTO_EDSA, .priv_size = sizeof(struct mv88e6xxx_priv_state), .probe = mv88e6171_probe, .setup = mv88e6171_setup, diff --git a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c index 29554992215..2349ea97025 100644 --- a/drivers/net/ethernet/amd/xgbe/xgbe-drv.c +++ b/drivers/net/ethernet/amd/xgbe/xgbe-drv.c @@ -1465,7 +1465,7 @@ static int xgbe_set_features(struct net_device *netdev, { struct xgbe_prv_data *pdata = netdev_priv(netdev); struct xgbe_hw_if *hw_if = &pdata->hw_if; - unsigned int rxcsum, rxvlan, rxvlan_filter; + netdev_features_t rxcsum, rxvlan, rxvlan_filter; rxcsum = pdata->netdev_features & NETIF_F_RXCSUM; rxvlan = pdata->netdev_features & NETIF_F_HW_VLAN_CTAG_RX; @@ -1598,7 +1598,8 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget) struct skb_shared_hwtstamps *hwtstamps; unsigned int incomplete, error, context_next, context; unsigned int len, put_len, max_len; - int received = 0; + unsigned int received = 0; + int packet_count = 0; DBGPR("-->xgbe_rx_poll: budget=%d\n", budget); @@ -1608,7 +1609,7 @@ static int xgbe_rx_poll(struct xgbe_channel *channel, int budget) rdata = XGBE_GET_DESC_DATA(ring, ring->cur); packet = &ring->packet_data; - while (received < budget) { + while (packet_count < budget) { DBGPR(" cur = %d\n", ring->cur); /* First time in loop see if we need to restore state */ @@ -1662,7 +1663,7 @@ read_again: if (packet->errors) DBGPR("Error in received packet\n"); dev_kfree_skb(skb); - continue; + goto next_packet; } if (!context) { @@ -1677,7 +1678,7 @@ read_again: } dev_kfree_skb(skb); - continue; + goto next_packet; } memcpy(skb_tail_pointer(skb), rdata->skb->data, put_len); @@ -1694,7 +1695,7 @@ read_again: /* Stray Context Descriptor? */ if (!skb) - continue; + goto next_packet; /* Be sure we don't exceed the configured MTU */ max_len = netdev->mtu + ETH_HLEN; @@ -1705,7 +1706,7 @@ read_again: if (skb->len > max_len) { DBGPR("packet length exceeds configured MTU\n"); dev_kfree_skb(skb); - continue; + goto next_packet; } #ifdef XGMAC_ENABLE_RX_PKT_DUMP @@ -1739,6 +1740,9 @@ read_again: netdev->last_rx = jiffies; napi_gro_receive(&pdata->napi, skb); + +next_packet: + packet_count++; } /* Check if we need to save state before leaving */ @@ -1752,9 +1756,9 @@ read_again: rdata->state.error = error; } - DBGPR("<--xgbe_rx_poll: received = %d\n", received); + DBGPR("<--xgbe_rx_poll: packet_count = %d\n", packet_count); - return received; + return packet_count; } static int xgbe_poll(struct napi_struct *napi, int budget) diff --git a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c index e6d24c21019..c22f32622fa 100644 --- a/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c +++ b/drivers/net/ethernet/apm/xgene/xgene_enet_sgmac.c @@ -124,20 +124,18 @@ static int xgene_enet_ecc_init(struct xgene_enet_pdata *p) { struct net_device *ndev = p->ndev; u32 data; - int i; + int i = 0; xgene_enet_wr_diag_csr(p, ENET_CFG_MEM_RAM_SHUTDOWN_ADDR, 0); - for (i = 0; i < 10 && data != ~0U ; i++) { + do { usleep_range(100, 110); data = xgene_enet_rd_diag_csr(p, ENET_BLOCK_MEM_RDY_ADDR); - } + if (data == ~0U) + return 0; + } while (++i < 10); - if (data != ~0U) { - netdev_err(ndev, "Failed to release memory from shutdown\n"); - return -ENODEV; - } - - return 0; + netdev_err(ndev, "Failed to release memory from shutdown\n"); + return -ENODEV; } static void xgene_enet_config_ring_if_assoc(struct xgene_enet_pdata *p) diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index 9ae36979bde..3a6778a667f 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -1397,6 +1397,9 @@ static void bcm_sysport_netif_start(struct net_device *dev) /* Enable NAPI */ napi_enable(&priv->napi); + /* Enable RX interrupt and TX ring full interrupt */ + intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL); + phy_start(priv->phydev); /* Enable TX interrupts for the 32 TXQs */ @@ -1499,9 +1502,6 @@ static int bcm_sysport_open(struct net_device *dev) if (ret) goto out_free_rx_ring; - /* Enable RX interrupt and TX ring full interrupt */ - intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL); - /* Turn on TDMA */ ret = tdma_enable_set(priv, 1); if (ret) @@ -1858,6 +1858,8 @@ static int bcm_sysport_resume(struct device *d) if (!netif_running(dev)) return 0; + umac_reset(priv); + /* We may have been suspended and never received a WOL event that * would turn off MPD detection, take care of that now */ @@ -1885,9 +1887,6 @@ static int bcm_sysport_resume(struct device *d) netif_device_attach(dev); - /* Enable RX interrupt and TX ring full interrupt */ - intrl2_0_mask_clear(priv, INTRL2_0_RDMA_MBDONE | INTRL2_0_TX_RING_FULL); - /* RX pipe enable */ topctrl_writel(priv, 0, RX_FLUSH_CNTL); diff --git a/drivers/net/ethernet/broadcom/cnic.c b/drivers/net/ethernet/broadcom/cnic.c index 23f23c97c2a..f05fab65d78 100644 --- a/drivers/net/ethernet/broadcom/cnic.c +++ b/drivers/net/ethernet/broadcom/cnic.c @@ -382,10 +382,8 @@ static int cnic_iscsi_nl_msg_recv(struct cnic_dev *dev, u32 msg_type, if (l5_cid >= MAX_CM_SK_TBL_SZ) break; - rcu_read_lock(); if (!rcu_access_pointer(cp->ulp_ops[CNIC_ULP_L4])) { rc = -ENODEV; - rcu_read_unlock(); break; } csk = &cp->csk_tbl[l5_cid]; @@ -414,7 +412,6 @@ static int cnic_iscsi_nl_msg_recv(struct cnic_dev *dev, u32 msg_type, } } csk_put(csk); - rcu_read_unlock(); rc = 0; } } @@ -615,7 +612,7 @@ static int cnic_unregister_device(struct cnic_dev *dev, int ulp_type) cnic_send_nlmsg(cp, ISCSI_KEVENT_IF_DOWN, NULL); mutex_lock(&cnic_lock); - if (rcu_dereference(cp->ulp_ops[ulp_type])) { + if (rcu_access_pointer(cp->ulp_ops[ulp_type])) { RCU_INIT_POINTER(cp->ulp_ops[ulp_type], NULL); cnic_put(dev); } else { diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c index 8edf0f5bd67..6fe300e316c 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_dcb.c @@ -60,6 +60,42 @@ void cxgb4_dcb_version_init(struct net_device *dev) dcb->dcb_version = FW_PORT_DCB_VER_AUTO; } +static void cxgb4_dcb_cleanup_apps(struct net_device *dev) +{ + struct port_info *pi = netdev2pinfo(dev); + struct adapter *adap = pi->adapter; + struct port_dcb_info *dcb = &pi->dcb; + struct dcb_app app; + int i, err; + + /* zero priority implies remove */ + app.priority = 0; + + for (i = 0; i < CXGB4_MAX_DCBX_APP_SUPPORTED; i++) { + /* Check if app list is exhausted */ + if (!dcb->app_priority[i].protocolid) + break; + + app.protocol = dcb->app_priority[i].protocolid; + + if (dcb->dcb_version == FW_PORT_DCB_VER_IEEE) { + app.selector = dcb->app_priority[i].sel_field + 1; + err = dcb_ieee_setapp(dev, &app); + } else { + app.selector = !!(dcb->app_priority[i].sel_field); + err = dcb_setapp(dev, &app); + } + + if (err) { + dev_err(adap->pdev_dev, + "Failed DCB Clear %s Application Priority: sel=%d, prot=%d, , err=%d\n", + dcb_ver_array[dcb->dcb_version], app.selector, + app.protocol, -err); + break; + } + } +} + /* Finite State machine for Data Center Bridging. */ void cxgb4_dcb_state_fsm(struct net_device *dev, @@ -80,7 +116,6 @@ void cxgb4_dcb_state_fsm(struct net_device *dev, /* we're going to use Host DCB */ dcb->state = CXGB4_DCB_STATE_HOST; dcb->supported = CXGB4_DCBX_HOST_SUPPORT; - dcb->enabled = 1; break; } @@ -145,6 +180,7 @@ void cxgb4_dcb_state_fsm(struct net_device *dev, * state. We need to reset back to a ground state * of incomplete. */ + cxgb4_dcb_cleanup_apps(dev); cxgb4_dcb_state_init(dev); dcb->state = CXGB4_DCB_STATE_FW_INCOMPLETE; dcb->supported = CXGB4_DCBX_FW_SUPPORT; @@ -349,6 +385,12 @@ static u8 cxgb4_setstate(struct net_device *dev, u8 enabled) { struct port_info *pi = netdev2pinfo(dev); + /* If DCBx is host-managed, dcb is enabled by outside lldp agents */ + if (pi->dcb.state == CXGB4_DCB_STATE_HOST) { + pi->dcb.enabled = enabled; + return 0; + } + /* Firmware doesn't provide any mechanism to control the DCB state. */ if (enabled != (pi->dcb.state == CXGB4_DCB_STATE_FW_ALLSYNCED)) @@ -833,11 +875,16 @@ static int cxgb4_setapp(struct net_device *dev, u8 app_idtype, u16 app_id, /* Return whether IEEE Data Center Bridging has been negotiated. */ -static inline int cxgb4_ieee_negotiation_complete(struct net_device *dev) +static inline int +cxgb4_ieee_negotiation_complete(struct net_device *dev, + enum cxgb4_dcb_fw_msgs dcb_subtype) { struct port_info *pi = netdev2pinfo(dev); struct port_dcb_info *dcb = &pi->dcb; + if (dcb_subtype && !(dcb->msgs & dcb_subtype)) + return 0; + return (dcb->state == CXGB4_DCB_STATE_FW_ALLSYNCED && (dcb->supported & DCB_CAP_DCBX_VER_IEEE)); } @@ -850,7 +897,7 @@ static int cxgb4_ieee_getapp(struct net_device *dev, struct dcb_app *app) { int prio; - if (!cxgb4_ieee_negotiation_complete(dev)) + if (!cxgb4_ieee_negotiation_complete(dev, CXGB4_DCB_FW_APP_ID)) return -EINVAL; if (!(app->selector && app->protocol)) return -EINVAL; @@ -872,7 +919,7 @@ static int cxgb4_ieee_setapp(struct net_device *dev, struct dcb_app *app) { int ret; - if (!cxgb4_ieee_negotiation_complete(dev)) + if (!cxgb4_ieee_negotiation_complete(dev, CXGB4_DCB_FW_APP_ID)) return -EINVAL; if (!(app->selector && app->protocol)) return -EINVAL; diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 3f60070f251..8520d5529df 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -694,7 +694,11 @@ int cxgb4_dcb_enabled(const struct net_device *dev) #ifdef CONFIG_CHELSIO_T4_DCB struct port_info *pi = netdev_priv(dev); - return pi->dcb.state == CXGB4_DCB_STATE_FW_ALLSYNCED; + if (!pi->dcb.enabled) + return 0; + + return ((pi->dcb.state == CXGB4_DCB_STATE_FW_ALLSYNCED) || + (pi->dcb.state == CXGB4_DCB_STATE_HOST)); #else return 0; #endif @@ -6610,6 +6614,7 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) spin_lock_init(&adapter->stats_lock); spin_lock_init(&adapter->tid_release_lock); + spin_lock_init(&adapter->win0_lock); INIT_WORK(&adapter->tid_release_task, process_tid_release_list); INIT_WORK(&adapter->db_full_task, process_db_full); diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index bfa398d9182..0b42bddaf28 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -2929,14 +2929,14 @@ static const struct pci_device_id cxgb4vf_pci_tbl[] = { CH_DEVICE(0x480d), /* T480-cr */ CH_DEVICE(0x480e), /* T440-lp-cr */ CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), - CH_DEVICE(0x4880), + CH_DEVICE(0x4881), + CH_DEVICE(0x4882), + CH_DEVICE(0x4883), + CH_DEVICE(0x4884), + CH_DEVICE(0x4885), + CH_DEVICE(0x4886), + CH_DEVICE(0x4887), + CH_DEVICE(0x4888), CH_DEVICE(0x5801), /* T520-cr */ CH_DEVICE(0x5802), /* T522-cr */ CH_DEVICE(0x5803), /* T540-cr */ diff --git a/drivers/net/ethernet/cisco/enic/enic_clsf.c b/drivers/net/ethernet/cisco/enic/enic_clsf.c index 69dfd3c9e52..0be6850be8a 100644 --- a/drivers/net/ethernet/cisco/enic/enic_clsf.c +++ b/drivers/net/ethernet/cisco/enic/enic_clsf.c @@ -86,7 +86,7 @@ void enic_rfs_flw_tbl_free(struct enic *enic) int i; enic_rfs_timer_stop(enic); - spin_lock(&enic->rfs_h.lock); + spin_lock_bh(&enic->rfs_h.lock); enic->rfs_h.free = 0; for (i = 0; i < (1 << ENIC_RFS_FLW_BITSHIFT); i++) { struct hlist_head *hhead; @@ -100,7 +100,7 @@ void enic_rfs_flw_tbl_free(struct enic *enic) kfree(n); } } - spin_unlock(&enic->rfs_h.lock); + spin_unlock_bh(&enic->rfs_h.lock); } struct enic_rfs_fltr_node *htbl_fltr_search(struct enic *enic, u16 fltr_id) @@ -128,7 +128,7 @@ void enic_flow_may_expire(unsigned long data) bool res; int j; - spin_lock(&enic->rfs_h.lock); + spin_lock_bh(&enic->rfs_h.lock); for (j = 0; j < ENIC_CLSF_EXPIRE_COUNT; j++) { struct hlist_head *hhead; struct hlist_node *tmp; @@ -148,7 +148,7 @@ void enic_flow_may_expire(unsigned long data) } } } - spin_unlock(&enic->rfs_h.lock); + spin_unlock_bh(&enic->rfs_h.lock); mod_timer(&enic->rfs_h.rfs_may_expire, jiffies + HZ/4); } @@ -183,7 +183,7 @@ int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, return -EPROTONOSUPPORT; tbl_idx = skb_get_hash_raw(skb) & ENIC_RFS_FLW_MASK; - spin_lock(&enic->rfs_h.lock); + spin_lock_bh(&enic->rfs_h.lock); n = htbl_key_search(&enic->rfs_h.ht_head[tbl_idx], &keys); if (n) { /* entry already present */ @@ -277,7 +277,7 @@ int enic_rx_flow_steer(struct net_device *dev, const struct sk_buff *skb, } ret_unlock: - spin_unlock(&enic->rfs_h.lock); + spin_unlock_bh(&enic->rfs_h.lock); return res; } diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c index 929bfe70080..180e53fa628 100644 --- a/drivers/net/ethernet/cisco/enic/enic_main.c +++ b/drivers/net/ethernet/cisco/enic/enic_main.c @@ -1674,13 +1674,13 @@ static int enic_stop(struct net_device *netdev) enic_dev_disable(enic); - local_bh_disable(); for (i = 0; i < enic->rq_count; i++) { napi_disable(&enic->napi[i]); + local_bh_disable(); while (!enic_poll_lock_napi(&enic->rq[i])) mdelay(1); + local_bh_enable(); } - local_bh_enable(); netif_carrier_off(netdev); netif_tx_disable(netdev); diff --git a/drivers/net/ethernet/freescale/fec_main.c b/drivers/net/ethernet/freescale/fec_main.c index 81b96cf8757..50a851db285 100644 --- a/drivers/net/ethernet/freescale/fec_main.c +++ b/drivers/net/ethernet/freescale/fec_main.c @@ -1581,7 +1581,8 @@ fec_enet_interrupt(int irq, void *dev_id) complete(&fep->mdio_done); } - fec_ptp_check_pps_event(fep); + if (fep->ptp_clock) + fec_ptp_check_pps_event(fep); return ret; } diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c index 3d4e08be170..b34214e2df5 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-fec.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-fec.c @@ -341,6 +341,9 @@ static void restart(struct net_device *dev) FC(fecp, x_cntrl, FEC_TCNTRL_FDEN); /* FD disable */ } + /* Restore multicast and promiscuous settings */ + set_multicast_list(dev); + /* * Enable interrupts we wish to service. */ diff --git a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c index f30411f0701..7a184e8816a 100644 --- a/drivers/net/ethernet/freescale/fs_enet/mac-scc.c +++ b/drivers/net/ethernet/freescale/fs_enet/mac-scc.c @@ -355,6 +355,9 @@ static void restart(struct net_device *dev) if (fep->phydev->duplex) S16(sccp, scc_psmr, SCC_PSMR_LPB | SCC_PSMR_FDE); + /* Restore multicast and promiscuous settings */ + set_multicast_list(dev); + S32(sccp, scc_gsmrl, SCC_GSMRL_ENR | SCC_GSMRL_ENT); } diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index 5f6aded512f..24f3986cfae 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1075,7 +1075,10 @@ static int e1000_probe(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_CSUM | NETIF_F_SG); - netdev->priv_flags |= IFF_UNICAST_FLT; + /* Do not set IFF_UNICAST_FLT for VMWare's 82545EM */ + if (hw->device_id != E1000_DEV_ID_82545EM_COPPER || + hw->subsystem_vendor_id != PCI_VENDOR_ID_VMWARE) + netdev->priv_flags |= IFF_UNICAST_FLT; adapter->en_mng_pt = e1000_enable_mng_pass_thru(hw); diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index ed5f1c15fb0..c3a7f4a4b77 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -6151,7 +6151,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) I40E_GL_MDET_TX_PF_NUM_SHIFT; u8 vf_num = (reg & I40E_GL_MDET_TX_VF_NUM_MASK) >> I40E_GL_MDET_TX_VF_NUM_SHIFT; - u8 event = (reg & I40E_GL_MDET_TX_EVENT_SHIFT) >> + u8 event = (reg & I40E_GL_MDET_TX_EVENT_MASK) >> I40E_GL_MDET_TX_EVENT_SHIFT; u8 queue = (reg & I40E_GL_MDET_TX_QUEUE_MASK) >> I40E_GL_MDET_TX_QUEUE_SHIFT; @@ -6165,7 +6165,7 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) if (reg & I40E_GL_MDET_RX_VALID_MASK) { u8 func = (reg & I40E_GL_MDET_RX_FUNCTION_MASK) >> I40E_GL_MDET_RX_FUNCTION_SHIFT; - u8 event = (reg & I40E_GL_MDET_RX_EVENT_SHIFT) >> + u8 event = (reg & I40E_GL_MDET_RX_EVENT_MASK) >> I40E_GL_MDET_RX_EVENT_SHIFT; u8 queue = (reg & I40E_GL_MDET_RX_QUEUE_MASK) >> I40E_GL_MDET_RX_QUEUE_SHIFT; diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index a21b14495eb..a2d72a87cbd 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -6537,6 +6537,9 @@ static bool igb_can_reuse_rx_page(struct igb_rx_buffer *rx_buffer, if (unlikely(page_to_nid(page) != numa_node_id())) return false; + if (unlikely(page->pfmemalloc)) + return false; + #if (PAGE_SIZE < 8192) /* if we are only owner of page we can reuse it */ if (unlikely(page_count(page) != 1)) @@ -6603,7 +6606,8 @@ static bool igb_add_rx_frag(struct igb_ring *rx_ring, memcpy(__skb_put(skb, size), va, ALIGN(size, sizeof(long))); /* we can reuse buffer as-is, just make sure it is local */ - if (likely(page_to_nid(page) == numa_node_id())) + if (likely((page_to_nid(page) == numa_node_id()) && + !page->pfmemalloc)) return true; /* this page cannot be reused so discard it */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index 3ce4a258f94..0ae038b9af9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -342,12 +342,16 @@ static int ixgbe_set_settings(struct net_device *netdev, if (old == advertised) return err; /* this sets the link speed and restarts auto-neg */ + while (test_and_set_bit(__IXGBE_IN_SFP_INIT, &adapter->state)) + usleep_range(1000, 2000); + hw->mac.autotry_restart = true; err = hw->mac.ops.setup_link(hw, advertised, true); if (err) { e_info(probe, "setup link failed with code %d\n", err); hw->mac.ops.setup_link(hw, old, true); } + clear_bit(__IXGBE_IN_SFP_INIT, &adapter->state); } else { /* in this case we currently only support 10Gb/FULL */ u32 speed = ethtool_cmd_speed(ecmd); diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index fec5212d433..d2df4e3d103 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -4321,8 +4321,8 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) IXGBE_CB(skb)->page_released = false; } dev_kfree_skb(skb); + rx_buffer->skb = NULL; } - rx_buffer->skb = NULL; if (rx_buffer->dma) dma_unmap_page(dev, rx_buffer->dma, ixgbe_rx_pg_size(rx_ring), diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 34c13787854..454d9fea640 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -836,8 +836,11 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev) * whether LSO is used */ tx_desc->ctrl.srcrb_flags = priv->ctrl_flags; if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) { - tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM | - MLX4_WQE_CTRL_TCP_UDP_CSUM); + if (!skb->encapsulation) + tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM | + MLX4_WQE_CTRL_TCP_UDP_CSUM); + else + tx_desc->ctrl.srcrb_flags |= cpu_to_be32(MLX4_WQE_CTRL_IP_CSUM); ring->tx_csum++; } diff --git a/drivers/net/ethernet/mellanox/mlx4/eq.c b/drivers/net/ethernet/mellanox/mlx4/eq.c index a49c9d11d8a..49290a40590 100644 --- a/drivers/net/ethernet/mellanox/mlx4/eq.c +++ b/drivers/net/ethernet/mellanox/mlx4/eq.c @@ -1026,6 +1026,7 @@ static void mlx4_free_eq(struct mlx4_dev *dev, pr_cont("\n"); } } + synchronize_irq(eq->irq); mlx4_mtt_cleanup(dev, &eq->mtt); for (i = 0; i < npages; ++i) diff --git a/drivers/net/ethernet/mellanox/mlx4/mcg.c b/drivers/net/ethernet/mellanox/mlx4/mcg.c index ca0f98c9510..872843179f4 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mcg.c +++ b/drivers/net/ethernet/mellanox/mlx4/mcg.c @@ -955,6 +955,10 @@ static void mlx4_err_rule(struct mlx4_dev *dev, char *str, cur->ib.dst_gid_msk); break; + case MLX4_NET_TRANS_RULE_ID_VXLAN: + len += snprintf(buf + len, BUF_SIZE - len, + "VNID = %d ", be32_to_cpu(cur->vxlan.vni)); + break; case MLX4_NET_TRANS_RULE_ID_IPV6: break; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eq.c b/drivers/net/ethernet/mellanox/mlx5/core/eq.c index ed53291468f..a278238a2db 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eq.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eq.c @@ -420,6 +420,7 @@ int mlx5_destroy_unmap_eq(struct mlx5_core_dev *dev, struct mlx5_eq *eq) if (err) mlx5_core_warn(dev, "failed to destroy a previously created eq: eqn %d\n", eq->eqn); + synchronize_irq(table->msix_arr[eq->irqn].vector); mlx5_buf_free(dev, &eq->buf); return err; diff --git a/drivers/net/ethernet/sfc/tx.c b/drivers/net/ethernet/sfc/tx.c index ee84a90e371..aaf2987512b 100644 --- a/drivers/net/ethernet/sfc/tx.c +++ b/drivers/net/ethernet/sfc/tx.c @@ -343,8 +343,6 @@ netdev_tx_t efx_enqueue_skb(struct efx_tx_queue *tx_queue, struct sk_buff *skb) unsigned short dma_flags; int i = 0; - EFX_BUG_ON_PARANOID(tx_queue->write_count > tx_queue->insert_count); - if (skb_shinfo(skb)->gso_size) return efx_enqueue_skb_tso(tx_queue, skb); @@ -1258,8 +1256,6 @@ static int efx_enqueue_skb_tso(struct efx_tx_queue *tx_queue, /* Find the packet protocol and sanity-check it */ state.protocol = efx_tso_check_protocol(skb); - EFX_BUG_ON_PARANOID(tx_queue->write_count > tx_queue->insert_count); - rc = tso_start(&state, efx, skb); if (rc) goto mem_err; diff --git a/drivers/net/ethernet/smsc/smc91x.c b/drivers/net/ethernet/smsc/smc91x.c index 5e94d00b96b..2c62208077f 100644 --- a/drivers/net/ethernet/smsc/smc91x.c +++ b/drivers/net/ethernet/smsc/smc91x.c @@ -81,6 +81,7 @@ static const char version[] = #include <linux/workqueue.h> #include <linux/of.h> #include <linux/of_device.h> +#include <linux/of_gpio.h> #include <linux/netdevice.h> #include <linux/etherdevice.h> @@ -2188,6 +2189,41 @@ static const struct of_device_id smc91x_match[] = { {}, }; MODULE_DEVICE_TABLE(of, smc91x_match); + +/** + * of_try_set_control_gpio - configure a gpio if it exists + */ +static int try_toggle_control_gpio(struct device *dev, + struct gpio_desc **desc, + const char *name, int index, + int value, unsigned int nsdelay) +{ + struct gpio_desc *gpio = *desc; + int res; + + gpio = devm_gpiod_get_index(dev, name, index); + if (IS_ERR(gpio)) { + if (PTR_ERR(gpio) == -ENOENT) { + *desc = NULL; + return 0; + } + + return PTR_ERR(gpio); + } + res = gpiod_direction_output(gpio, !value); + if (res) { + dev_err(dev, "unable to toggle gpio %s: %i\n", name, res); + devm_gpiod_put(dev, gpio); + gpio = NULL; + return res; + } + if (nsdelay) + usleep_range(nsdelay, 2 * nsdelay); + gpiod_set_value_cansleep(gpio, value); + *desc = gpio; + + return 0; +} #endif /* @@ -2237,6 +2273,28 @@ static int smc_drv_probe(struct platform_device *pdev) struct device_node *np = pdev->dev.of_node; u32 val; + /* Optional pwrdwn GPIO configured? */ + ret = try_toggle_control_gpio(&pdev->dev, &lp->power_gpio, + "power", 0, 0, 100); + if (ret) + return ret; + + /* + * Optional reset GPIO configured? Minimum 100 ns reset needed + * according to LAN91C96 datasheet page 14. + */ + ret = try_toggle_control_gpio(&pdev->dev, &lp->reset_gpio, + "reset", 0, 0, 100); + if (ret) + return ret; + + /* + * Need to wait for optional EEPROM to load, max 750 us according + * to LAN91C96 datasheet page 55. + */ + if (lp->reset_gpio) + usleep_range(750, 1000); + /* Combination of IO widths supported, default to 16-bit */ if (!of_property_read_u32(np, "reg-io-width", &val)) { if (val & 1) diff --git a/drivers/net/ethernet/smsc/smc91x.h b/drivers/net/ethernet/smsc/smc91x.h index 47dce918eb0..2a38dacbbd2 100644 --- a/drivers/net/ethernet/smsc/smc91x.h +++ b/drivers/net/ethernet/smsc/smc91x.h @@ -298,6 +298,9 @@ struct smc_local { struct sk_buff *pending_tx_skb; struct tasklet_struct tx_task; + struct gpio_desc *power_gpio; + struct gpio_desc *reset_gpio; + /* version/revision of the SMC91x chip */ int version; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c index 655a23bbc45..e17a970eaf2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_pci.c @@ -33,6 +33,7 @@ static struct stmmac_dma_cfg dma_cfg; static void stmmac_default_data(void) { memset(&plat_dat, 0, sizeof(struct plat_stmmacenet_data)); + plat_dat.bus_id = 1; plat_dat.phy_addr = 0; plat_dat.interface = PHY_INTERFACE_MODE_GMII; @@ -47,6 +48,12 @@ static void stmmac_default_data(void) dma_cfg.pbl = 32; dma_cfg.burst_len = DMA_AXI_BLEN_256; plat_dat.dma_cfg = &dma_cfg; + + /* Set default value for multicast hash bins */ + plat_dat.multicast_filter_bins = HASH_TABLE_SIZE; + + /* Set default value for unicast filter entries */ + plat_dat.unicast_filter_entries = 1; } /** diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 952e1e4764b..d8794488f80 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -591,8 +591,8 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) if (enable) { unsigned long timeout = jiffies + HZ; - /* Disable Learn for all ports */ - for (i = 0; i < priv->data.slaves; i++) { + /* Disable Learn for all ports (host is port 0 and slaves are port 1 and up */ + for (i = 0; i <= priv->data.slaves; i++) { cpsw_ale_control_set(ale, i, ALE_PORT_NOLEARN, 1); cpsw_ale_control_set(ale, i, @@ -616,11 +616,11 @@ static void cpsw_set_promiscious(struct net_device *ndev, bool enable) cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1); dev_dbg(&ndev->dev, "promiscuity enabled\n"); } else { - /* Flood All Unicast Packets to Host port */ + /* Don't Flood All Unicast Packets to Host port */ cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 0); - /* Enable Learn for all ports */ - for (i = 0; i < priv->data.slaves; i++) { + /* Enable Learn for all ports (host is port 0 and slaves are port 1 and up */ + for (i = 0; i <= priv->data.slaves; i++) { cpsw_ale_control_set(ale, i, ALE_PORT_NOLEARN, 0); cpsw_ale_control_set(ale, i, @@ -638,12 +638,16 @@ static void cpsw_ndo_set_rx_mode(struct net_device *ndev) if (ndev->flags & IFF_PROMISC) { /* Enable promiscuous mode */ cpsw_set_promiscious(ndev, true); + cpsw_ale_set_allmulti(priv->ale, IFF_ALLMULTI); return; } else { /* Disable promiscuous mode */ cpsw_set_promiscious(ndev, false); } + /* Restore allmulti on vlans if necessary */ + cpsw_ale_set_allmulti(priv->ale, priv->ndev->flags & IFF_ALLMULTI); + /* Clear all mcast from ALE */ cpsw_ale_flush_multicast(priv->ale, ALE_ALL_PORTS << priv->host_port); @@ -1149,6 +1153,7 @@ static inline void cpsw_add_default_vlan(struct cpsw_priv *priv) const int port = priv->host_port; u32 reg; int i; + int unreg_mcast_mask; reg = (priv->version == CPSW_VERSION_1) ? CPSW1_PORT_VLAN : CPSW2_PORT_VLAN; @@ -1158,9 +1163,14 @@ static inline void cpsw_add_default_vlan(struct cpsw_priv *priv) for (i = 0; i < priv->data.slaves; i++) slave_write(priv->slaves + i, vlan, reg); + if (priv->ndev->flags & IFF_ALLMULTI) + unreg_mcast_mask = ALE_ALL_PORTS; + else + unreg_mcast_mask = ALE_PORT_1 | ALE_PORT_2; + cpsw_ale_add_vlan(priv->ale, vlan, ALE_ALL_PORTS << port, ALE_ALL_PORTS << port, ALE_ALL_PORTS << port, - (ALE_PORT_1 | ALE_PORT_2) << port); + unreg_mcast_mask << port); } static void cpsw_init_host_port(struct cpsw_priv *priv) @@ -1620,11 +1630,17 @@ static inline int cpsw_add_vlan_ale_entry(struct cpsw_priv *priv, unsigned short vid) { int ret; + int unreg_mcast_mask; + + if (priv->ndev->flags & IFF_ALLMULTI) + unreg_mcast_mask = ALE_ALL_PORTS; + else + unreg_mcast_mask = ALE_PORT_1 | ALE_PORT_2; ret = cpsw_ale_add_vlan(priv->ale, vid, ALE_ALL_PORTS << priv->host_port, 0, ALE_ALL_PORTS << priv->host_port, - (ALE_PORT_1 | ALE_PORT_2) << priv->host_port); + unreg_mcast_mask << priv->host_port); if (ret != 0) return ret; @@ -2006,7 +2022,7 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, parp = of_get_property(slave_node, "phy_id", &lenp); if ((parp == NULL) || (lenp != (sizeof(void *) * 2))) { dev_err(&pdev->dev, "Missing slave[%d] phy_id property\n", i); - return -EINVAL; + goto no_phy_slave; } mdio_node = of_find_node_by_phandle(be32_to_cpup(parp)); phyid = be32_to_cpup(parp+1); @@ -2019,6 +2035,14 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, snprintf(slave_data->phy_id, sizeof(slave_data->phy_id), PHY_ID_FMT, mdio->name, phyid); + slave_data->phy_if = of_get_phy_mode(slave_node); + if (slave_data->phy_if < 0) { + dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", + i); + return slave_data->phy_if; + } + +no_phy_slave: mac_addr = of_get_mac_address(slave_node); if (mac_addr) { memcpy(slave_data->mac_addr, mac_addr, ETH_ALEN); @@ -2030,14 +2054,6 @@ static int cpsw_probe_dt(struct cpsw_platform_data *data, return ret; } } - - slave_data->phy_if = of_get_phy_mode(slave_node); - if (slave_data->phy_if < 0) { - dev_err(&pdev->dev, "Missing or malformed slave[%d] phy-mode property\n", - i); - return slave_data->phy_if; - } - if (data->dual_emac) { if (of_property_read_u32(slave_node, "dual_emac_res_vlan", &prop)) { diff --git a/drivers/net/ethernet/ti/cpsw_ale.c b/drivers/net/ethernet/ti/cpsw_ale.c index 0579b2243bb..3ae83879a75 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.c +++ b/drivers/net/ethernet/ti/cpsw_ale.c @@ -443,6 +443,35 @@ int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port_mask) return 0; } +void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti) +{ + u32 ale_entry[ALE_ENTRY_WORDS]; + int type, idx; + int unreg_mcast = 0; + + /* Only bother doing the work if the setting is actually changing */ + if (ale->allmulti == allmulti) + return; + + /* Remember the new setting to check against next time */ + ale->allmulti = allmulti; + + for (idx = 0; idx < ale->params.ale_entries; idx++) { + cpsw_ale_read(ale, idx, ale_entry); + type = cpsw_ale_get_entry_type(ale_entry); + if (type != ALE_TYPE_VLAN) + continue; + + unreg_mcast = cpsw_ale_get_vlan_unreg_mcast(ale_entry); + if (allmulti) + unreg_mcast |= 1; + else + unreg_mcast &= ~1; + cpsw_ale_set_vlan_unreg_mcast(ale_entry, unreg_mcast); + cpsw_ale_write(ale, idx, ale_entry); + } +} + struct ale_control_info { const char *name; int offset, port_offset; diff --git a/drivers/net/ethernet/ti/cpsw_ale.h b/drivers/net/ethernet/ti/cpsw_ale.h index 31cf43cab42..c0d4127aa54 100644 --- a/drivers/net/ethernet/ti/cpsw_ale.h +++ b/drivers/net/ethernet/ti/cpsw_ale.h @@ -27,6 +27,7 @@ struct cpsw_ale { struct cpsw_ale_params params; struct timer_list timer; unsigned long ageout; + int allmulti; }; enum cpsw_ale_control { @@ -103,6 +104,7 @@ int cpsw_ale_del_mcast(struct cpsw_ale *ale, u8 *addr, int port_mask, int cpsw_ale_add_vlan(struct cpsw_ale *ale, u16 vid, int port, int untag, int reg_mcast, int unreg_mcast); int cpsw_ale_del_vlan(struct cpsw_ale *ale, u16 vid, int port); +void cpsw_ale_set_allmulti(struct cpsw_ale *ale, int allmulti); int cpsw_ale_control_get(struct cpsw_ale *ale, int port, int control); int cpsw_ale_control_set(struct cpsw_ale *ale, int port, diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index 9e17d1a91e7..78ec33f5100 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -550,6 +550,7 @@ do_lso: do_send: /* Start filling in the page buffers with the rndis hdr */ rndis_msg->msg_len += rndis_msg_size; + packet->total_data_buflen = rndis_msg->msg_len; packet->page_buf_cnt = init_page_array(rndis_msg, rndis_msg_size, skb, &packet->page_buf[0]); diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 29b3bb41078..bfb0b6ec8c5 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -272,7 +272,7 @@ static void macvlan_process_broadcast(struct work_struct *w) struct sk_buff *skb; struct sk_buff_head list; - skb_queue_head_init(&list); + __skb_queue_head_init(&list); spin_lock_bh(&port->bc_queue.lock); skb_queue_splice_tail_init(&port->bc_queue, &list); @@ -1082,9 +1082,15 @@ static void macvlan_port_destroy(struct net_device *dev) { struct macvlan_port *port = macvlan_port_get_rtnl(dev); - cancel_work_sync(&port->bc_work); dev->priv_flags &= ~IFF_MACVLAN_PORT; netdev_rx_handler_unregister(dev); + + /* After this point, no packet can schedule bc_work anymore, + * but we need to cancel it and purge left skbs if any. + */ + cancel_work_sync(&port->bc_work); + __skb_queue_purge(&port->bc_queue); + kfree_rcu(port, rcu); } diff --git a/drivers/net/macvtap.c b/drivers/net/macvtap.c index 65e2892342b..6f226de655a 100644 --- a/drivers/net/macvtap.c +++ b/drivers/net/macvtap.c @@ -16,6 +16,7 @@ #include <linux/idr.h> #include <linux/fs.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/rtnetlink.h> #include <net/sock.h> @@ -65,7 +66,7 @@ static struct cdev macvtap_cdev; static const struct proto_ops macvtap_socket_ops; #define TUN_OFFLOADS (NETIF_F_HW_CSUM | NETIF_F_TSO_ECN | NETIF_F_TSO | \ - NETIF_F_TSO6 | NETIF_F_UFO) + NETIF_F_TSO6) #define RX_OFFLOADS (NETIF_F_GRO | NETIF_F_LRO) #define TAP_FEATURES (NETIF_F_GSO | NETIF_F_SG) @@ -569,7 +570,11 @@ static int macvtap_skb_from_vnet_hdr(struct sk_buff *skb, gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: + pr_warn_once("macvtap: %s: using disabled UFO feature; please fix this program\n", + current->comm); gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; default: return -EINVAL; @@ -614,8 +619,6 @@ static void macvtap_skb_to_vnet_hdr(const struct sk_buff *skb, vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - vnet_hdr->gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (sinfo->gso_type & SKB_GSO_TCP_ECN) @@ -950,9 +953,6 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) if (arg & TUN_F_TSO6) feature_mask |= NETIF_F_TSO6; } - - if (arg & TUN_F_UFO) - feature_mask |= NETIF_F_UFO; } /* tun/tap driver inverts the usage for TSO offloads, where @@ -963,7 +963,7 @@ static int set_offload(struct macvtap_queue *q, unsigned long arg) * When user space turns off TSO, we turn off GSO/LRO so that * user-space will not receive TSO frames. */ - if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_UFO)) + if (feature_mask & (NETIF_F_TSO | NETIF_F_TSO6)) features |= RX_OFFLOADS; else features &= ~RX_OFFLOADS; @@ -1064,7 +1064,7 @@ static long macvtap_ioctl(struct file *file, unsigned int cmd, case TUNSETOFFLOAD: /* let the user check for future flags */ if (arg & ~(TUN_F_CSUM | TUN_F_TSO4 | TUN_F_TSO6 | - TUN_F_TSO_ECN | TUN_F_UFO)) + TUN_F_TSO_ECN)) return -EINVAL; rtnl_lock(); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index bd37e45c89c..225c033b08f 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -50,10 +50,15 @@ #define MII_M1011_PHY_SCR 0x10 #define MII_M1011_PHY_SCR_AUTO_CROSS 0x0060 +#define MII_M1145_PHY_EXT_SR 0x1b #define MII_M1145_PHY_EXT_CR 0x14 #define MII_M1145_RGMII_RX_DELAY 0x0080 #define MII_M1145_RGMII_TX_DELAY 0x0002 +#define MII_M1145_HWCFG_MODE_SGMII_NO_CLK 0x4 +#define MII_M1145_HWCFG_MODE_MASK 0xf +#define MII_M1145_HWCFG_FIBER_COPPER_AUTO 0x8000 + #define MII_M1111_PHY_LED_CONTROL 0x18 #define MII_M1111_PHY_LED_DIRECT 0x4100 #define MII_M1111_PHY_LED_COMBINE 0x411c @@ -676,6 +681,20 @@ static int m88e1145_config_init(struct phy_device *phydev) } } + if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + int temp = phy_read(phydev, MII_M1145_PHY_EXT_SR); + if (temp < 0) + return temp; + + temp &= ~MII_M1145_HWCFG_MODE_MASK; + temp |= MII_M1145_HWCFG_MODE_SGMII_NO_CLK; + temp |= MII_M1145_HWCFG_FIBER_COPPER_AUTO; + + err = phy_write(phydev, MII_M1145_PHY_EXT_SR, temp); + if (err < 0) + return err; + } + err = marvell_of_reg_init(phydev); if (err < 0) return err; diff --git a/drivers/net/tun.c b/drivers/net/tun.c index 186ce541c65..7302398f0b1 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -65,6 +65,7 @@ #include <linux/nsproxy.h> #include <linux/virtio_net.h> #include <linux/rcupdate.h> +#include <net/ipv6.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> @@ -174,7 +175,7 @@ struct tun_struct { struct net_device *dev; netdev_features_t set_features; #define TUN_USER_FEATURES (NETIF_F_HW_CSUM|NETIF_F_TSO_ECN|NETIF_F_TSO| \ - NETIF_F_TSO6|NETIF_F_UFO) + NETIF_F_TSO6) int vnet_hdr_sz; int sndbuf; @@ -1139,6 +1140,8 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, break; } + skb_reset_network_header(skb); + if (gso.gso_type != VIRTIO_NET_HDR_GSO_NONE) { pr_debug("GSO!\n"); switch (gso.gso_type & ~VIRTIO_NET_HDR_GSO_ECN) { @@ -1149,8 +1152,20 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; case VIRTIO_NET_HDR_GSO_UDP: + { + static bool warned; + + if (!warned) { + warned = true; + netdev_warn(tun->dev, + "%s: using disabled UFO feature; please fix this program\n", + current->comm); + } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; + if (skb->protocol == htons(ETH_P_IPV6)) + ipv6_proxy_select_ident(skb); break; + } default: tun->dev->stats.rx_frame_errors++; kfree_skb(skb); @@ -1179,7 +1194,6 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, skb_shinfo(skb)->tx_flags |= SKBTX_SHARED_FRAG; } - skb_reset_network_header(skb); skb_probe_transport_header(skb, 0); rxhash = skb_get_hash(skb); @@ -1251,8 +1265,6 @@ static ssize_t tun_put_user(struct tun_struct *tun, gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (sinfo->gso_type & SKB_GSO_TCPV6) gso.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (sinfo->gso_type & SKB_GSO_UDP) - gso.gso_type = VIRTIO_NET_HDR_GSO_UDP; else { pr_err("unexpected GSO type: " "0x%x, gso_size %d, hdr_len %d\n", @@ -1762,11 +1774,6 @@ static int set_offload(struct tun_struct *tun, unsigned long arg) features |= NETIF_F_TSO6; arg &= ~(TUN_F_TSO4|TUN_F_TSO6); } - - if (arg & TUN_F_UFO) { - features |= NETIF_F_UFO; - arg &= ~TUN_F_UFO; - } } /* This gives the user a way to test for new features in future by diff --git a/drivers/net/usb/ax88179_178a.c b/drivers/net/usb/ax88179_178a.c index be427572103..e6338c16081 100644 --- a/drivers/net/usb/ax88179_178a.c +++ b/drivers/net/usb/ax88179_178a.c @@ -937,6 +937,7 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) { struct usbnet *dev = netdev_priv(net); struct sockaddr *addr = p; + int ret; if (netif_running(net)) return -EBUSY; @@ -946,8 +947,12 @@ static int ax88179_set_mac_addr(struct net_device *net, void *p) memcpy(net->dev_addr, addr->sa_data, ETH_ALEN); /* Set the MAC address */ - return ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, + ret = ax88179_write_cmd(dev, AX_ACCESS_MAC, AX_NODE_ID, ETH_ALEN, ETH_ALEN, net->dev_addr); + if (ret < 0) + return ret; + + return 0; } static const struct net_device_ops ax88179_netdev_ops = { diff --git a/drivers/net/usb/cdc_ether.c b/drivers/net/usb/cdc_ether.c index 2a32d9167d3..d3920b54a92 100644 --- a/drivers/net/usb/cdc_ether.c +++ b/drivers/net/usb/cdc_ether.c @@ -67,6 +67,35 @@ static const u8 mbm_guid[16] = { 0xa6, 0x07, 0xc0, 0xff, 0xcb, 0x7e, 0x39, 0x2a, }; +static void usbnet_cdc_update_filter(struct usbnet *dev) +{ + struct cdc_state *info = (void *) &dev->data; + struct usb_interface *intf = info->control; + + u16 cdc_filter = + USB_CDC_PACKET_TYPE_ALL_MULTICAST | USB_CDC_PACKET_TYPE_DIRECTED | + USB_CDC_PACKET_TYPE_BROADCAST; + + if (dev->net->flags & IFF_PROMISC) + cdc_filter |= USB_CDC_PACKET_TYPE_PROMISCUOUS; + + /* FIXME cdc-ether has some multicast code too, though it complains + * in routine cases. info->ether describes the multicast support. + * Implement that here, manipulating the cdc filter as needed. + */ + + usb_control_msg(dev->udev, + usb_sndctrlpipe(dev->udev, 0), + USB_CDC_SET_ETHERNET_PACKET_FILTER, + USB_TYPE_CLASS | USB_RECIP_INTERFACE, + cdc_filter, + intf->cur_altsetting->desc.bInterfaceNumber, + NULL, + 0, + USB_CTRL_SET_TIMEOUT + ); +} + /* probes control interface, claims data interface, collects the bulk * endpoints, activates data interface (if needed), maybe sets MTU. * all pure cdc, except for certain firmware workarounds, and knowing @@ -347,16 +376,8 @@ next_desc: * don't do reset all the way. So the packet filter should * be set to a sane initial value. */ - usb_control_msg(dev->udev, - usb_sndctrlpipe(dev->udev, 0), - USB_CDC_SET_ETHERNET_PACKET_FILTER, - USB_TYPE_CLASS | USB_RECIP_INTERFACE, - USB_CDC_PACKET_TYPE_ALL_MULTICAST | USB_CDC_PACKET_TYPE_DIRECTED | USB_CDC_PACKET_TYPE_BROADCAST, - intf->cur_altsetting->desc.bInterfaceNumber, - NULL, - 0, - USB_CTRL_SET_TIMEOUT - ); + usbnet_cdc_update_filter(dev); + return 0; bad_desc: @@ -468,10 +489,6 @@ int usbnet_cdc_bind(struct usbnet *dev, struct usb_interface *intf) return status; } - /* FIXME cdc-ether has some multicast code too, though it complains - * in routine cases. info->ether describes the multicast support. - * Implement that here, manipulating the cdc filter as needed. - */ return 0; } EXPORT_SYMBOL_GPL(usbnet_cdc_bind); @@ -482,6 +499,7 @@ static const struct driver_info cdc_info = { .bind = usbnet_cdc_bind, .unbind = usbnet_cdc_unbind, .status = usbnet_cdc_status, + .set_rx_mode = usbnet_cdc_update_filter, .manage_power = usbnet_manage_power, }; @@ -491,6 +509,7 @@ static const struct driver_info wwan_info = { .bind = usbnet_cdc_bind, .unbind = usbnet_cdc_unbind, .status = usbnet_cdc_status, + .set_rx_mode = usbnet_cdc_update_filter, .manage_power = usbnet_manage_power, }; diff --git a/drivers/net/usb/r8152.c b/drivers/net/usb/r8152.c index e3d84c322e4..c6554c7a814 100644 --- a/drivers/net/usb/r8152.c +++ b/drivers/net/usb/r8152.c @@ -1162,6 +1162,9 @@ static void intr_callback(struct urb *urb) case -ESHUTDOWN: netif_device_detach(tp->netdev); case -ENOENT: + case -EPROTO: + netif_info(tp, intr, tp->netdev, + "Stop submitting intr, status %d\n", status); return; case -EOVERFLOW: netif_info(tp, intr, tp->netdev, "intr status -EOVERFLOW\n"); @@ -2891,6 +2894,9 @@ static int rtl8152_open(struct net_device *netdev) if (res) goto out; + /* set speed to 0 to avoid autoresume try to submit rx */ + tp->speed = 0; + res = usb_autopm_get_interface(tp->intf); if (res < 0) { free_all_mem(tp); @@ -2904,6 +2910,8 @@ static int rtl8152_open(struct net_device *netdev) clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); cancel_delayed_work_sync(&tp->schedule); + + /* disable the tx/rx, if the workqueue has enabled them. */ if (tp->speed & LINK_STATUS) tp->rtl_ops.disable(tp); } @@ -2955,10 +2963,7 @@ static int rtl8152_close(struct net_device *netdev) * be disable when autoresume occurs, because the * netif_running() would be false. */ - if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { - rtl_runtime_suspend_enable(tp, false); - clear_bit(SELECTIVE_SUSPEND, &tp->flags); - } + rtl_runtime_suspend_enable(tp, false); tasklet_disable(&tp->tl); tp->rtl_ops.down(tp); @@ -3205,7 +3210,7 @@ static int rtl8152_suspend(struct usb_interface *intf, pm_message_t message) netif_device_detach(netdev); } - if (netif_running(netdev)) { + if (netif_running(netdev) && test_bit(WORK_ENABLE, &tp->flags)) { clear_bit(WORK_ENABLE, &tp->flags); usb_kill_urb(tp->intr_urb); tasklet_disable(&tp->tl); @@ -3253,6 +3258,8 @@ static int rtl8152_resume(struct usb_interface *intf) set_bit(WORK_ENABLE, &tp->flags); } usb_submit_urb(tp->intr_urb, GFP_KERNEL); + } else if (test_bit(SELECTIVE_SUSPEND, &tp->flags)) { + clear_bit(SELECTIVE_SUSPEND, &tp->flags); } mutex_unlock(&tp->control); diff --git a/drivers/net/usb/usbnet.c b/drivers/net/usb/usbnet.c index 20615bbd693..3a6770a65d7 100644 --- a/drivers/net/usb/usbnet.c +++ b/drivers/net/usb/usbnet.c @@ -1052,6 +1052,21 @@ static void __handle_link_change(struct usbnet *dev) clear_bit(EVENT_LINK_CHANGE, &dev->flags); } +static void usbnet_set_rx_mode(struct net_device *net) +{ + struct usbnet *dev = netdev_priv(net); + + usbnet_defer_kevent(dev, EVENT_SET_RX_MODE); +} + +static void __handle_set_rx_mode(struct usbnet *dev) +{ + if (dev->driver_info->set_rx_mode) + (dev->driver_info->set_rx_mode)(dev); + + clear_bit(EVENT_SET_RX_MODE, &dev->flags); +} + /* work that cannot be done in interrupt context uses keventd. * * NOTE: with 2.5 we could do more of this using completion callbacks, @@ -1157,6 +1172,10 @@ skip_reset: if (test_bit (EVENT_LINK_CHANGE, &dev->flags)) __handle_link_change(dev); + if (test_bit (EVENT_SET_RX_MODE, &dev->flags)) + __handle_set_rx_mode(dev); + + if (dev->flags) netdev_dbg(dev->net, "kevent done, flags = 0x%lx\n", dev->flags); } @@ -1525,6 +1544,7 @@ static const struct net_device_ops usbnet_netdev_ops = { .ndo_stop = usbnet_stop, .ndo_start_xmit = usbnet_start_xmit, .ndo_tx_timeout = usbnet_tx_timeout, + .ndo_set_rx_mode = usbnet_set_rx_mode, .ndo_change_mtu = usbnet_change_mtu, .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index d75256bd1a6..ec2a8b41ed4 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -491,8 +491,17 @@ static void receive_buf(struct receive_queue *rq, void *buf, unsigned int len) skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; break; case VIRTIO_NET_HDR_GSO_UDP: + { + static bool warned; + + if (!warned) { + warned = true; + netdev_warn(dev, + "host using disabled UFO feature; please fix it\n"); + } skb_shinfo(skb)->gso_type = SKB_GSO_UDP; break; + } case VIRTIO_NET_HDR_GSO_TCPV6: skb_shinfo(skb)->gso_type = SKB_GSO_TCPV6; break; @@ -881,8 +890,6 @@ static int xmit_skb(struct send_queue *sq, struct sk_buff *skb) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV4; else if (skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6) hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_TCPV6; - else if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP) - hdr->hdr.gso_type = VIRTIO_NET_HDR_GSO_UDP; else BUG(); if (skb_shinfo(skb)->gso_type & SKB_GSO_TCP_ECN) @@ -1705,7 +1712,7 @@ static int virtnet_probe(struct virtio_device *vdev) dev->features |= NETIF_F_HW_CSUM|NETIF_F_SG|NETIF_F_FRAGLIST; if (virtio_has_feature(vdev, VIRTIO_NET_F_GSO)) { - dev->hw_features |= NETIF_F_TSO | NETIF_F_UFO + dev->hw_features |= NETIF_F_TSO | NETIF_F_TSO_ECN | NETIF_F_TSO6; } /* Individual feature bits: what can host handle? */ @@ -1715,11 +1722,9 @@ static int virtnet_probe(struct virtio_device *vdev) dev->hw_features |= NETIF_F_TSO6; if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_ECN)) dev->hw_features |= NETIF_F_TSO_ECN; - if (virtio_has_feature(vdev, VIRTIO_NET_F_HOST_UFO)) - dev->hw_features |= NETIF_F_UFO; if (gso) - dev->features |= dev->hw_features & (NETIF_F_ALL_TSO|NETIF_F_UFO); + dev->features |= dev->hw_features & NETIF_F_ALL_TSO; /* (!csum && gso) case will be fixed by register_netdev() */ } if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_CSUM)) @@ -1757,8 +1762,7 @@ static int virtnet_probe(struct virtio_device *vdev) /* If we can receive ANY GSO packets, we must allocate large ones. */ if (virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO4) || virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_TSO6) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN) || - virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_UFO)) + virtio_has_feature(vdev, VIRTIO_NET_F_GUEST_ECN)) vi->big_packets = true; if (virtio_has_feature(vdev, VIRTIO_NET_F_MRG_RXBUF)) @@ -1952,9 +1956,9 @@ static struct virtio_device_id id_table[] = { static unsigned int features[] = { VIRTIO_NET_F_CSUM, VIRTIO_NET_F_GUEST_CSUM, VIRTIO_NET_F_GSO, VIRTIO_NET_F_MAC, - VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_UFO, VIRTIO_NET_F_HOST_TSO6, + VIRTIO_NET_F_HOST_TSO4, VIRTIO_NET_F_HOST_TSO6, VIRTIO_NET_F_HOST_ECN, VIRTIO_NET_F_GUEST_TSO4, VIRTIO_NET_F_GUEST_TSO6, - VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_GUEST_UFO, + VIRTIO_NET_F_GUEST_ECN, VIRTIO_NET_F_MRG_RXBUF, VIRTIO_NET_F_STATUS, VIRTIO_NET_F_CTRL_VQ, VIRTIO_NET_F_CTRL_RX, VIRTIO_NET_F_CTRL_VLAN, VIRTIO_NET_F_GUEST_ANNOUNCE, VIRTIO_NET_F_MQ, diff --git a/drivers/net/xen-netback/common.h b/drivers/net/xen-netback/common.h index d4eb8d2e9cb..083ecc93fe5 100644 --- a/drivers/net/xen-netback/common.h +++ b/drivers/net/xen-netback/common.h @@ -176,10 +176,11 @@ struct xenvif_queue { /* Per-queue data for xenvif */ char rx_irq_name[IRQ_NAME_SIZE]; /* DEVNAME-qN-rx */ struct xen_netif_rx_back_ring rx; struct sk_buff_head rx_queue; - RING_IDX rx_last_skb_slots; - unsigned long status; - struct timer_list rx_stalled; + unsigned int rx_queue_max; + unsigned int rx_queue_len; + unsigned long last_rx_time; + bool stalled; struct gnttab_copy grant_copy_op[MAX_GRANT_COPY_OPS]; @@ -199,18 +200,14 @@ struct xenvif_queue { /* Per-queue data for xenvif */ struct xenvif_stats stats; }; +/* Maximum number of Rx slots a to-guest packet may use, including the + * slot needed for GSO meta-data. + */ +#define XEN_NETBK_RX_SLOTS_MAX (MAX_SKB_FRAGS + 1) + enum state_bit_shift { /* This bit marks that the vif is connected */ VIF_STATUS_CONNECTED, - /* This bit signals the RX thread that queuing was stopped (in - * start_xmit), and either the timer fired or an RX interrupt came - */ - QUEUE_STATUS_RX_PURGE_EVENT, - /* This bit tells the interrupt handler that this queue was the reason - * for the carrier off, so it should kick the thread. Only queues which - * brought it down can turn on the carrier. - */ - QUEUE_STATUS_RX_STALLED }; struct xenvif { @@ -228,9 +225,6 @@ struct xenvif { u8 ip_csum:1; u8 ipv6_csum:1; - /* Internal feature information. */ - u8 can_queue:1; /* can queue packets for receiver? */ - /* Is this interface disabled? True when backend discovers * frontend is rogue. */ @@ -240,6 +234,9 @@ struct xenvif { /* Queues */ struct xenvif_queue *queues; unsigned int num_queues; /* active queues, resource allocated */ + unsigned int stalled_queues; + + spinlock_t lock; #ifdef CONFIG_DEBUG_FS struct dentry *xenvif_dbg_root; @@ -249,6 +246,14 @@ struct xenvif { struct net_device *dev; }; +struct xenvif_rx_cb { + unsigned long expires; + int meta_slots_used; + bool full_coalesce; +}; + +#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) + static inline struct xenbus_device *xenvif_to_xenbus_device(struct xenvif *vif) { return to_xenbus_device(vif->dev->dev.parent); @@ -272,8 +277,6 @@ void xenvif_xenbus_fini(void); int xenvif_schedulable(struct xenvif *vif); -int xenvif_must_stop_queue(struct xenvif_queue *queue); - int xenvif_queue_stopped(struct xenvif_queue *queue); void xenvif_wake_queue(struct xenvif_queue *queue); @@ -296,6 +299,8 @@ void xenvif_kick_thread(struct xenvif_queue *queue); int xenvif_dealloc_kthread(void *data); +void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb); + /* Determine whether the needed number of slots (req) are available, * and set req_event if not. */ diff --git a/drivers/net/xen-netback/interface.c b/drivers/net/xen-netback/interface.c index f379689dde3..895fe84011e 100644 --- a/drivers/net/xen-netback/interface.c +++ b/drivers/net/xen-netback/interface.c @@ -43,6 +43,9 @@ #define XENVIF_QUEUE_LENGTH 32 #define XENVIF_NAPI_WEIGHT 64 +/* Number of bytes allowed on the internal guest Rx queue. */ +#define XENVIF_RX_QUEUE_BYTES (XEN_NETIF_RX_RING_SIZE/2 * PAGE_SIZE) + /* This function is used to set SKBTX_DEV_ZEROCOPY as well as * increasing the inflight counter. We need to increase the inflight * counter because core driver calls into xenvif_zerocopy_callback @@ -60,20 +63,11 @@ void xenvif_skb_zerocopy_complete(struct xenvif_queue *queue) atomic_dec(&queue->inflight_packets); } -static inline void xenvif_stop_queue(struct xenvif_queue *queue) -{ - struct net_device *dev = queue->vif->dev; - - if (!queue->vif->can_queue) - return; - - netif_tx_stop_queue(netdev_get_tx_queue(dev, queue->id)); -} - int xenvif_schedulable(struct xenvif *vif) { return netif_running(vif->dev) && - test_bit(VIF_STATUS_CONNECTED, &vif->status); + test_bit(VIF_STATUS_CONNECTED, &vif->status) && + !vif->disabled; } static irqreturn_t xenvif_tx_interrupt(int irq, void *dev_id) @@ -114,16 +108,7 @@ int xenvif_poll(struct napi_struct *napi, int budget) static irqreturn_t xenvif_rx_interrupt(int irq, void *dev_id) { struct xenvif_queue *queue = dev_id; - struct netdev_queue *net_queue = - netdev_get_tx_queue(queue->vif->dev, queue->id); - /* QUEUE_STATUS_RX_PURGE_EVENT is only set if either QDisc was off OR - * the carrier went down and this queue was previously blocked - */ - if (unlikely(netif_tx_queue_stopped(net_queue) || - (!netif_carrier_ok(queue->vif->dev) && - test_bit(QUEUE_STATUS_RX_STALLED, &queue->status)))) - set_bit(QUEUE_STATUS_RX_PURGE_EVENT, &queue->status); xenvif_kick_thread(queue); return IRQ_HANDLED; @@ -151,24 +136,13 @@ void xenvif_wake_queue(struct xenvif_queue *queue) netif_tx_wake_queue(netdev_get_tx_queue(dev, id)); } -/* Callback to wake the queue's thread and turn the carrier off on timeout */ -static void xenvif_rx_stalled(unsigned long data) -{ - struct xenvif_queue *queue = (struct xenvif_queue *)data; - - if (xenvif_queue_stopped(queue)) { - set_bit(QUEUE_STATUS_RX_PURGE_EVENT, &queue->status); - xenvif_kick_thread(queue); - } -} - static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) { struct xenvif *vif = netdev_priv(dev); struct xenvif_queue *queue = NULL; unsigned int num_queues = vif->num_queues; u16 index; - int min_slots_needed; + struct xenvif_rx_cb *cb; BUG_ON(skb->dev != dev); @@ -191,30 +165,10 @@ static int xenvif_start_xmit(struct sk_buff *skb, struct net_device *dev) !xenvif_schedulable(vif)) goto drop; - /* At best we'll need one slot for the header and one for each - * frag. - */ - min_slots_needed = 1 + skb_shinfo(skb)->nr_frags; - - /* If the skb is GSO then we'll also need an extra slot for the - * metadata. - */ - if (skb_is_gso(skb)) - min_slots_needed++; + cb = XENVIF_RX_CB(skb); + cb->expires = jiffies + rx_drain_timeout_jiffies; - /* If the skb can't possibly fit in the remaining slots - * then turn off the queue to give the ring a chance to - * drain. - */ - if (!xenvif_rx_ring_slots_available(queue, min_slots_needed)) { - queue->rx_stalled.function = xenvif_rx_stalled; - queue->rx_stalled.data = (unsigned long)queue; - xenvif_stop_queue(queue); - mod_timer(&queue->rx_stalled, - jiffies + rx_drain_timeout_jiffies); - } - - skb_queue_tail(&queue->rx_queue, skb); + xenvif_rx_queue_tail(queue, skb); xenvif_kick_thread(queue); return NETDEV_TX_OK; @@ -465,6 +419,8 @@ struct xenvif *xenvif_alloc(struct device *parent, domid_t domid, vif->queues = NULL; vif->num_queues = 0; + spin_lock_init(&vif->lock); + dev->netdev_ops = &xenvif_netdev_ops; dev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -508,6 +464,8 @@ int xenvif_init_queue(struct xenvif_queue *queue) init_timer(&queue->credit_timeout); queue->credit_window_start = get_jiffies_64(); + queue->rx_queue_max = XENVIF_RX_QUEUE_BYTES; + skb_queue_head_init(&queue->rx_queue); skb_queue_head_init(&queue->tx_queue); @@ -539,8 +497,6 @@ int xenvif_init_queue(struct xenvif_queue *queue) queue->grant_tx_handle[i] = NETBACK_INVALID_HANDLE; } - init_timer(&queue->rx_stalled); - return 0; } @@ -551,7 +507,6 @@ void xenvif_carrier_on(struct xenvif *vif) dev_set_mtu(vif->dev, ETH_DATA_LEN); netdev_update_features(vif->dev); set_bit(VIF_STATUS_CONNECTED, &vif->status); - netif_carrier_on(vif->dev); if (netif_running(vif->dev)) xenvif_up(vif); rtnl_unlock(); @@ -611,6 +566,8 @@ int xenvif_connect(struct xenvif_queue *queue, unsigned long tx_ring_ref, disable_irq(queue->rx_irq); } + queue->stalled = true; + task = kthread_create(xenvif_kthread_guest_rx, (void *)queue, "%s-guest-rx", queue->name); if (IS_ERR(task)) { @@ -674,7 +631,6 @@ void xenvif_disconnect(struct xenvif *vif) netif_napi_del(&queue->napi); if (queue->task) { - del_timer_sync(&queue->rx_stalled); kthread_stop(queue->task); queue->task = NULL; } diff --git a/drivers/net/xen-netback/netback.c b/drivers/net/xen-netback/netback.c index 08f65996534..6563f0713fc 100644 --- a/drivers/net/xen-netback/netback.c +++ b/drivers/net/xen-netback/netback.c @@ -55,13 +55,20 @@ bool separate_tx_rx_irq = 1; module_param(separate_tx_rx_irq, bool, 0644); -/* When guest ring is filled up, qdisc queues the packets for us, but we have - * to timeout them, otherwise other guests' packets can get stuck there +/* The time that packets can stay on the guest Rx internal queue + * before they are dropped. */ unsigned int rx_drain_timeout_msecs = 10000; module_param(rx_drain_timeout_msecs, uint, 0444); unsigned int rx_drain_timeout_jiffies; +/* The length of time before the frontend is considered unresponsive + * because it isn't providing Rx slots. + */ +static unsigned int rx_stall_timeout_msecs = 60000; +module_param(rx_stall_timeout_msecs, uint, 0444); +static unsigned int rx_stall_timeout_jiffies; + unsigned int xenvif_max_queues; module_param_named(max_queues, xenvif_max_queues, uint, 0644); MODULE_PARM_DESC(max_queues, @@ -83,7 +90,6 @@ static void make_tx_response(struct xenvif_queue *queue, s8 st); static inline int tx_work_todo(struct xenvif_queue *queue); -static inline int rx_work_todo(struct xenvif_queue *queue); static struct xen_netif_rx_response *make_rx_response(struct xenvif_queue *queue, u16 id, @@ -163,6 +169,69 @@ bool xenvif_rx_ring_slots_available(struct xenvif_queue *queue, int needed) return false; } +void xenvif_rx_queue_tail(struct xenvif_queue *queue, struct sk_buff *skb) +{ + unsigned long flags; + + spin_lock_irqsave(&queue->rx_queue.lock, flags); + + __skb_queue_tail(&queue->rx_queue, skb); + + queue->rx_queue_len += skb->len; + if (queue->rx_queue_len > queue->rx_queue_max) + netif_tx_stop_queue(netdev_get_tx_queue(queue->vif->dev, queue->id)); + + spin_unlock_irqrestore(&queue->rx_queue.lock, flags); +} + +static struct sk_buff *xenvif_rx_dequeue(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + spin_lock_irq(&queue->rx_queue.lock); + + skb = __skb_dequeue(&queue->rx_queue); + if (skb) + queue->rx_queue_len -= skb->len; + + spin_unlock_irq(&queue->rx_queue.lock); + + return skb; +} + +static void xenvif_rx_queue_maybe_wake(struct xenvif_queue *queue) +{ + spin_lock_irq(&queue->rx_queue.lock); + + if (queue->rx_queue_len < queue->rx_queue_max) + netif_tx_wake_queue(netdev_get_tx_queue(queue->vif->dev, queue->id)); + + spin_unlock_irq(&queue->rx_queue.lock); +} + + +static void xenvif_rx_queue_purge(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + while ((skb = xenvif_rx_dequeue(queue)) != NULL) + kfree_skb(skb); +} + +static void xenvif_rx_queue_drop_expired(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + + for(;;) { + skb = skb_peek(&queue->rx_queue); + if (!skb) + break; + if (time_before(jiffies, XENVIF_RX_CB(skb)->expires)) + break; + xenvif_rx_dequeue(queue); + kfree_skb(skb); + } +} + /* * Returns true if we should start a new receive buffer instead of * adding 'size' bytes to a buffer which currently contains 'offset' @@ -237,13 +306,6 @@ static struct xenvif_rx_meta *get_next_rx_buffer(struct xenvif_queue *queue, return meta; } -struct xenvif_rx_cb { - int meta_slots_used; - bool full_coalesce; -}; - -#define XENVIF_RX_CB(skb) ((struct xenvif_rx_cb *)(skb)->cb) - /* * Set up the grant operations for this fragment. If it's a flipping * interface, we also set up the unmap request from here. @@ -587,12 +649,15 @@ static void xenvif_rx_action(struct xenvif_queue *queue) skb_queue_head_init(&rxq); - while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) { + while (xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX) + && (skb = xenvif_rx_dequeue(queue)) != NULL) { RING_IDX max_slots_needed; RING_IDX old_req_cons; RING_IDX ring_slots_used; int i; + queue->last_rx_time = jiffies; + /* We need a cheap worse case estimate for the number of * slots we'll use. */ @@ -634,15 +699,6 @@ static void xenvif_rx_action(struct xenvif_queue *queue) skb_shinfo(skb)->gso_type & SKB_GSO_TCPV6)) max_slots_needed++; - /* If the skb may not fit then bail out now */ - if (!xenvif_rx_ring_slots_available(queue, max_slots_needed)) { - skb_queue_head(&queue->rx_queue, skb); - need_to_notify = true; - queue->rx_last_skb_slots = max_slots_needed; - break; - } else - queue->rx_last_skb_slots = 0; - old_req_cons = queue->rx.req_cons; XENVIF_RX_CB(skb)->meta_slots_used = xenvif_gop_skb(skb, &npo, queue); ring_slots_used = queue->rx.req_cons - old_req_cons; @@ -1869,12 +1925,6 @@ void xenvif_idx_unmap(struct xenvif_queue *queue, u16 pending_idx) } } -static inline int rx_work_todo(struct xenvif_queue *queue) -{ - return (!skb_queue_empty(&queue->rx_queue) && - xenvif_rx_ring_slots_available(queue, queue->rx_last_skb_slots)); -} - static inline int tx_work_todo(struct xenvif_queue *queue) { if (likely(RING_HAS_UNCONSUMED_REQUESTS(&queue->tx))) @@ -1931,92 +1981,121 @@ err: return err; } -static void xenvif_start_queue(struct xenvif_queue *queue) +static void xenvif_queue_carrier_off(struct xenvif_queue *queue) { - if (xenvif_schedulable(queue->vif)) - xenvif_wake_queue(queue); + struct xenvif *vif = queue->vif; + + queue->stalled = true; + + /* At least one queue has stalled? Disable the carrier. */ + spin_lock(&vif->lock); + if (vif->stalled_queues++ == 0) { + netdev_info(vif->dev, "Guest Rx stalled"); + netif_carrier_off(vif->dev); + } + spin_unlock(&vif->lock); } -/* Only called from the queue's thread, it handles the situation when the guest - * doesn't post enough requests on the receiving ring. - * First xenvif_start_xmit disables QDisc and start a timer, and then either the - * timer fires, or the guest send an interrupt after posting new request. If it - * is the timer, the carrier is turned off here. - * */ -static void xenvif_rx_purge_event(struct xenvif_queue *queue) +static void xenvif_queue_carrier_on(struct xenvif_queue *queue) { - /* Either the last unsuccesful skb or at least 1 slot should fit */ - int needed = queue->rx_last_skb_slots ? - queue->rx_last_skb_slots : 1; + struct xenvif *vif = queue->vif; - /* It is assumed that if the guest post new slots after this, the RX - * interrupt will set the QUEUE_STATUS_RX_PURGE_EVENT bit and wake up - * the thread again - */ - set_bit(QUEUE_STATUS_RX_STALLED, &queue->status); - if (!xenvif_rx_ring_slots_available(queue, needed)) { - rtnl_lock(); - if (netif_carrier_ok(queue->vif->dev)) { - /* Timer fired and there are still no slots. Turn off - * everything except the interrupts - */ - netif_carrier_off(queue->vif->dev); - skb_queue_purge(&queue->rx_queue); - queue->rx_last_skb_slots = 0; - if (net_ratelimit()) - netdev_err(queue->vif->dev, "Carrier off due to lack of guest response on queue %d\n", queue->id); - } else { - /* Probably an another queue already turned the carrier - * off, make sure nothing is stucked in the internal - * queue of this queue - */ - skb_queue_purge(&queue->rx_queue); - queue->rx_last_skb_slots = 0; - } - rtnl_unlock(); - } else if (!netif_carrier_ok(queue->vif->dev)) { - unsigned int num_queues = queue->vif->num_queues; - unsigned int i; - /* The carrier was down, but an interrupt kicked - * the thread again after new requests were - * posted - */ - clear_bit(QUEUE_STATUS_RX_STALLED, - &queue->status); - rtnl_lock(); - netif_carrier_on(queue->vif->dev); - netif_tx_wake_all_queues(queue->vif->dev); - rtnl_unlock(); + queue->last_rx_time = jiffies; /* Reset Rx stall detection. */ + queue->stalled = false; - for (i = 0; i < num_queues; i++) { - struct xenvif_queue *temp = &queue->vif->queues[i]; + /* All queues are ready? Enable the carrier. */ + spin_lock(&vif->lock); + if (--vif->stalled_queues == 0) { + netdev_info(vif->dev, "Guest Rx ready"); + netif_carrier_on(vif->dev); + } + spin_unlock(&vif->lock); +} - xenvif_napi_schedule_or_enable_events(temp); - } - if (net_ratelimit()) - netdev_err(queue->vif->dev, "Carrier on again\n"); - } else { - /* Queuing were stopped, but the guest posted - * new requests and sent an interrupt - */ - clear_bit(QUEUE_STATUS_RX_STALLED, - &queue->status); - del_timer_sync(&queue->rx_stalled); - xenvif_start_queue(queue); +static bool xenvif_rx_queue_stalled(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + return !queue->stalled + && prod - cons < XEN_NETBK_RX_SLOTS_MAX + && time_after(jiffies, + queue->last_rx_time + rx_stall_timeout_jiffies); +} + +static bool xenvif_rx_queue_ready(struct xenvif_queue *queue) +{ + RING_IDX prod, cons; + + prod = queue->rx.sring->req_prod; + cons = queue->rx.req_cons; + + return queue->stalled + && prod - cons >= XEN_NETBK_RX_SLOTS_MAX; +} + +static bool xenvif_have_rx_work(struct xenvif_queue *queue) +{ + return (!skb_queue_empty(&queue->rx_queue) + && xenvif_rx_ring_slots_available(queue, XEN_NETBK_RX_SLOTS_MAX)) + || xenvif_rx_queue_stalled(queue) + || xenvif_rx_queue_ready(queue) + || kthread_should_stop() + || queue->vif->disabled; +} + +static long xenvif_rx_queue_timeout(struct xenvif_queue *queue) +{ + struct sk_buff *skb; + long timeout; + + skb = skb_peek(&queue->rx_queue); + if (!skb) + return MAX_SCHEDULE_TIMEOUT; + + timeout = XENVIF_RX_CB(skb)->expires - jiffies; + return timeout < 0 ? 0 : timeout; +} + +/* Wait until the guest Rx thread has work. + * + * The timeout needs to be adjusted based on the current head of the + * queue (and not just the head at the beginning). In particular, if + * the queue is initially empty an infinite timeout is used and this + * needs to be reduced when a skb is queued. + * + * This cannot be done with wait_event_timeout() because it only + * calculates the timeout once. + */ +static void xenvif_wait_for_rx_work(struct xenvif_queue *queue) +{ + DEFINE_WAIT(wait); + + if (xenvif_have_rx_work(queue)) + return; + + for (;;) { + long ret; + + prepare_to_wait(&queue->wq, &wait, TASK_INTERRUPTIBLE); + if (xenvif_have_rx_work(queue)) + break; + ret = schedule_timeout(xenvif_rx_queue_timeout(queue)); + if (!ret) + break; } + finish_wait(&queue->wq, &wait); } int xenvif_kthread_guest_rx(void *data) { struct xenvif_queue *queue = data; - struct sk_buff *skb; + struct xenvif *vif = queue->vif; - while (!kthread_should_stop()) { - wait_event_interruptible(queue->wq, - rx_work_todo(queue) || - queue->vif->disabled || - test_bit(QUEUE_STATUS_RX_PURGE_EVENT, &queue->status) || - kthread_should_stop()); + for (;;) { + xenvif_wait_for_rx_work(queue); if (kthread_should_stop()) break; @@ -2028,35 +2107,38 @@ int xenvif_kthread_guest_rx(void *data) * context so we defer it here, if this thread is * associated with queue 0. */ - if (unlikely(queue->vif->disabled && queue->id == 0)) { - xenvif_carrier_off(queue->vif); - } else if (unlikely(queue->vif->disabled)) { - /* kthread_stop() would be called upon this thread soon, - * be a bit proactive - */ - skb_queue_purge(&queue->rx_queue); - queue->rx_last_skb_slots = 0; - } else if (unlikely(test_and_clear_bit(QUEUE_STATUS_RX_PURGE_EVENT, - &queue->status))) { - xenvif_rx_purge_event(queue); - } else if (!netif_carrier_ok(queue->vif->dev)) { - /* Another queue stalled and turned the carrier off, so - * purge the internal queue of queues which were not - * blocked - */ - skb_queue_purge(&queue->rx_queue); - queue->rx_last_skb_slots = 0; + if (unlikely(vif->disabled && queue->id == 0)) { + xenvif_carrier_off(vif); + xenvif_rx_queue_purge(queue); + continue; } if (!skb_queue_empty(&queue->rx_queue)) xenvif_rx_action(queue); + /* If the guest hasn't provided any Rx slots for a + * while it's probably not responsive, drop the + * carrier so packets are dropped earlier. + */ + if (xenvif_rx_queue_stalled(queue)) + xenvif_queue_carrier_off(queue); + else if (xenvif_rx_queue_ready(queue)) + xenvif_queue_carrier_on(queue); + + /* Queued packets may have foreign pages from other + * domains. These cannot be queued indefinitely as + * this would starve guests of grant refs and transmit + * slots. + */ + xenvif_rx_queue_drop_expired(queue); + + xenvif_rx_queue_maybe_wake(queue); + cond_resched(); } /* Bin any remaining skbs */ - while ((skb = skb_dequeue(&queue->rx_queue)) != NULL) - dev_kfree_skb(skb); + xenvif_rx_queue_purge(queue); return 0; } @@ -2113,6 +2195,7 @@ static int __init netback_init(void) goto failed_init; rx_drain_timeout_jiffies = msecs_to_jiffies(rx_drain_timeout_msecs); + rx_stall_timeout_jiffies = msecs_to_jiffies(rx_stall_timeout_msecs); #ifdef CONFIG_DEBUG_FS xen_netback_dbg_root = debugfs_create_dir("xen-netback", NULL); diff --git a/drivers/net/xen-netback/xenbus.c b/drivers/net/xen-netback/xenbus.c index 8079c31ac5e..4e56a27f968 100644 --- a/drivers/net/xen-netback/xenbus.c +++ b/drivers/net/xen-netback/xenbus.c @@ -52,6 +52,7 @@ static int xenvif_read_io_ring(struct seq_file *m, void *v) struct xenvif_queue *queue = m->private; struct xen_netif_tx_back_ring *tx_ring = &queue->tx; struct xen_netif_rx_back_ring *rx_ring = &queue->rx; + struct netdev_queue *dev_queue; if (tx_ring->sring) { struct xen_netif_tx_sring *sring = tx_ring->sring; @@ -112,6 +113,13 @@ static int xenvif_read_io_ring(struct seq_file *m, void *v) queue->credit_timeout.expires, jiffies); + dev_queue = netdev_get_tx_queue(queue->vif->dev, queue->id); + + seq_printf(m, "\nRx internal queue: len %u max %u pkts %u %s\n", + queue->rx_queue_len, queue->rx_queue_max, + skb_queue_len(&queue->rx_queue), + netif_tx_queue_stopped(dev_queue) ? "stopped" : "running"); + return 0; } @@ -703,6 +711,7 @@ static void connect(struct backend_info *be) be->vif->queues = vzalloc(requested_num_queues * sizeof(struct xenvif_queue)); be->vif->num_queues = requested_num_queues; + be->vif->stalled_queues = requested_num_queues; for (queue_index = 0; queue_index < requested_num_queues; ++queue_index) { queue = &be->vif->queues[queue_index]; @@ -873,15 +882,10 @@ static int read_xenbus_vif_flags(struct backend_info *be) if (!rx_copy) return -EOPNOTSUPP; - if (vif->dev->tx_queue_len != 0) { - if (xenbus_scanf(XBT_NIL, dev->otherend, - "feature-rx-notify", "%d", &val) < 0) - val = 0; - if (val) - vif->can_queue = 1; - else - /* Must be non-zero for pfifo_fast to work. */ - vif->dev->tx_queue_len = 1; + if (xenbus_scanf(XBT_NIL, dev->otherend, + "feature-rx-notify", "%d", &val) < 0 || val == 0) { + xenbus_dev_fatal(dev, -EINVAL, "feature-rx-notify is mandatory"); + return -EINVAL; } if (xenbus_scanf(XBT_NIL, dev->otherend, "feature-sg", |