diff options
30 files changed, 541 insertions, 303 deletions
diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index c99e3e845ac0..a90080f12e67 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1074,16 +1074,12 @@ static int amd8111e_calc_coalesce(struct net_device *dev) amd8111e_set_coalesce(dev,TX_INTR_COAL); coal_conf->tx_coal_type = MEDIUM_COALESCE; } - - } - else if(tx_pkt_size >= 1024){ - if (tx_pkt_size >= 1024){ - if(coal_conf->tx_coal_type != HIGH_COALESCE){ - coal_conf->tx_timeout = 4; - coal_conf->tx_event_count = 8; - amd8111e_set_coalesce(dev,TX_INTR_COAL); - coal_conf->tx_coal_type = HIGH_COALESCE; - } + } else if (tx_pkt_size >= 1024) { + if (coal_conf->tx_coal_type != HIGH_COALESCE) { + coal_conf->tx_timeout = 4; + coal_conf->tx_event_count = 8; + amd8111e_set_coalesce(dev, TX_INTR_COAL); + coal_conf->tx_coal_type = HIGH_COALESCE; } } } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index df8607097e4a..c51d61f5f715 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -445,15 +445,14 @@ static void fm10k_type_trans(struct fm10k_ring *rx_ring, l2_accel = NULL; } - skb->protocol = eth_type_trans(skb, dev); - /* Record Rx queue, or update macvlan statistics */ if (!l2_accel) skb_record_rx_queue(skb, rx_ring->queue_index); else macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true, - (skb->pkt_type == PACKET_BROADCAST) || - (skb->pkt_type == PACKET_MULTICAST)); + false); + + skb->protocol = eth_type_trans(skb, dev); } /** diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 45793491d4ba..26e749766337 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -22,6 +22,7 @@ #include "fm10k.h" #include <linux/vmalloc.h> #include <net/udp_tunnel.h> +#include <linux/if_macvlan.h> /** * fm10k_setup_tx_resources - allocate Tx resources (Descriptors) @@ -1254,7 +1255,7 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) glort = l2_accel->dglort + 1 + i; hw->mac.ops.update_xcast_mode(hw, glort, - FM10K_XCAST_MODE_MULTI); + FM10K_XCAST_MODE_NONE); fm10k_queue_mac_request(interface, glort, sdev->dev_addr, hw->mac.default_vid, true); @@ -1449,6 +1450,13 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, int size = 0, i; u16 glort; + /* The hardware supported by fm10k only filters on the destination MAC + * address. In order to avoid issues we only support offloading modes + * where the hardware can actually provide the functionality. + */ + if (!macvlan_supports_dest_filter(sdev)) + return ERR_PTR(-EMEDIUMTYPE); + /* allocate l2 accel structure if it is not available */ if (!l2_accel) { /* verify there is enough free GLORTs to support l2_accel */ @@ -1515,7 +1523,7 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, if (fm10k_host_mbx_ready(interface)) { hw->mac.ops.update_xcast_mode(hw, glort, - FM10K_XCAST_MODE_MULTI); + FM10K_XCAST_MODE_NONE); fm10k_queue_mac_request(interface, glort, sdev->dev_addr, hw->mac.default_vid, true); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 7dd5038cfcc4..8fccca57cd6a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -305,7 +305,6 @@ enum ixgbe_ring_state_t { struct ixgbe_fwd_adapter { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; struct net_device *netdev; - struct ixgbe_adapter *real_adapter; unsigned int tx_base_queue; unsigned int rx_base_queue; int pool; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index 51e7d82a5860..b6e5cea84949 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1768,15 +1768,14 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP)) ixgbe_ipsec_rx(rx_ring, rx_desc, skb); - skb->protocol = eth_type_trans(skb, dev); - /* record Rx queue, or update MACVLAN statistics */ if (netif_is_ixgbe(dev)) skb_record_rx_queue(skb, rx_ring->queue_index); else macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true, - (skb->pkt_type == PACKET_BROADCAST) || - (skb->pkt_type == PACKET_MULTICAST)); + false); + + skb->protocol = eth_type_trans(skb, dev); } static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, @@ -4219,7 +4218,8 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 reg_offset, vf_shift; + u16 pool = adapter->num_rx_pools; + u32 reg_offset, vf_shift, vmolr; u32 gcr_ext, vmdctl; int i; @@ -4233,6 +4233,13 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) vmdctl |= IXGBE_VT_CTL_REPLEN; IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); + /* accept untagged packets until a vlan tag is + * specifically set for the VMDQ queue/pool + */ + vmolr = IXGBE_VMOLR_AUPE; + while (pool--) + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(pool)), vmolr); + vf_shift = VMDQ_P(0) % 32; reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0; @@ -4900,36 +4907,6 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, return -ENOMEM; } -/** - * ixgbe_write_uc_addr_list - write unicast addresses to RAR table - * @netdev: network interface device structure - * @vfn: pool to associate with unicast addresses - * - * Writes unicast address list to the RAR table. - * Returns: -ENOMEM on failure/insufficient address space - * 0 on no addresses written - * X on writing X addresses to the RAR table - **/ -static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn) -{ - struct ixgbe_adapter *adapter = netdev_priv(netdev); - int count = 0; - - /* return ENOMEM indicating insufficient memory for addresses */ - if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter, vfn)) - return -ENOMEM; - - if (!netdev_uc_empty(netdev)) { - struct netdev_hw_addr *ha; - netdev_for_each_uc_addr(ha, netdev) { - ixgbe_del_mac_filter(adapter, ha->addr, vfn); - ixgbe_add_mac_filter(adapter, ha->addr, vfn); - count++; - } - } - return count; -} - static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -5309,29 +5286,6 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) spin_unlock(&adapter->fdir_perfect_lock); } -static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool, - struct ixgbe_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - u32 vmolr; - - /* No unicast promiscuous support for VMDQ devices. */ - vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool)); - vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE); - - /* clear the affected bit */ - vmolr &= ~IXGBE_VMOLR_MPE; - - if (dev->flags & IFF_ALLMULTI) { - vmolr |= IXGBE_VMOLR_MPE; - } else { - vmolr |= IXGBE_VMOLR_ROMPE; - hw->mac.ops.update_mc_addr_list(hw, dev); - } - ixgbe_write_uc_addr_list(adapter->netdev, pool); - IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr); -} - /** * ixgbe_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from @@ -5384,21 +5338,17 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) rx_ring->next_to_use = 0; } -static int ixgbe_fwd_ring_up(struct net_device *vdev, +static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter, struct ixgbe_fwd_adapter *accel) { - struct ixgbe_adapter *adapter = accel->real_adapter; + struct net_device *vdev = accel->netdev; int i, baseq, err; - if (!test_bit(accel->pool, adapter->fwd_bitmask)) - return 0; - baseq = accel->pool * adapter->num_rx_queues_per_pool; netdev_dbg(vdev, "pool %i:%i queues %i:%i\n", accel->pool, adapter->num_rx_pools, baseq, baseq + adapter->num_rx_queues_per_pool); - accel->netdev = vdev; accel->rx_base_queue = baseq; accel->tx_base_queue = baseq; @@ -5415,26 +5365,36 @@ static int ixgbe_fwd_ring_up(struct net_device *vdev, */ err = ixgbe_add_mac_filter(adapter, vdev->dev_addr, VMDQ_P(accel->pool)); - if (err >= 0) { - ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter); + if (err >= 0) return 0; - } + + /* if we cannot add the MAC rule then disable the offload */ + macvlan_release_l2fw_offload(vdev); for (i = 0; i < adapter->num_rx_queues_per_pool; i++) adapter->rx_ring[baseq + i]->netdev = NULL; + netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n"); + + clear_bit(accel->pool, adapter->fwd_bitmask); + kfree(accel); + return err; } -static int ixgbe_upper_dev_walk(struct net_device *upper, void *data) +static int ixgbe_macvlan_up(struct net_device *vdev, void *data) { - if (netif_is_macvlan(upper)) { - struct macvlan_dev *dfwd = netdev_priv(upper); - struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + struct ixgbe_adapter *adapter = data; + struct ixgbe_fwd_adapter *accel; - if (dfwd->fwd_priv) - ixgbe_fwd_ring_up(upper, vadapter); - } + if (!netif_is_macvlan(vdev)) + return 0; + + accel = macvlan_accel_priv(vdev); + if (!accel) + return 0; + + ixgbe_fwd_ring_up(adapter, accel); return 0; } @@ -5442,7 +5402,7 @@ static int ixgbe_upper_dev_walk(struct net_device *upper, void *data) static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) { netdev_walk_all_upper_dev_rcu(adapter->netdev, - ixgbe_upper_dev_walk, NULL); + ixgbe_macvlan_up, adapter); } static void ixgbe_configure(struct ixgbe_adapter *adapter) @@ -8843,6 +8803,49 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) } #endif /* CONFIG_IXGBE_DCB */ +static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) +{ + struct ixgbe_adapter *adapter = data; + struct ixgbe_fwd_adapter *accel; + int pool; + + /* we only care about macvlans... */ + if (!netif_is_macvlan(vdev)) + return 0; + + /* that have hardware offload enabled... */ + accel = macvlan_accel_priv(vdev); + if (!accel) + return 0; + + /* If we can relocate to a different bit do so */ + pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); + if (pool < adapter->num_rx_pools) { + set_bit(pool, adapter->fwd_bitmask); + accel->pool = pool; + return 0; + } + + /* if we cannot find a free pool then disable the offload */ + netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n"); + macvlan_release_l2fw_offload(vdev); + kfree(accel); + + return 0; +} + +static void ixgbe_defrag_macvlan_pools(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + /* flush any stale bits out of the fwd bitmask */ + bitmap_clear(adapter->fwd_bitmask, 1, 63); + + /* walk through upper devices reassigning pools */ + netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool, + adapter); +} + /** * ixgbe_setup_tc - configure net_device for multiple traffic classes * @@ -8910,6 +8913,8 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) #endif /* CONFIG_IXGBE_DCB */ ixgbe_init_interrupt_scheme(adapter); + ixgbe_defrag_macvlan_pools(dev); + if (netif_running(dev)) return ixgbe_open(dev); @@ -9014,13 +9019,12 @@ struct upper_walk_data { static int get_macvlan_queue(struct net_device *upper, void *_data) { if (netif_is_macvlan(upper)) { - struct macvlan_dev *dfwd = netdev_priv(upper); - struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper); struct upper_walk_data *data = _data; struct ixgbe_adapter *adapter = data->adapter; int ifindex = data->ifindex; - if (vadapter && vadapter->netdev->ifindex == ifindex) { + if (vadapter && upper->ifindex == ifindex) { data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; data->action = data->queue; return 1; @@ -9460,6 +9464,22 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev, return features; } +static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter) +{ + int rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + + /* go back to full RSS if we're not running SR-IOV */ + if (!adapter->ring_feature[RING_F_VMDQ].offset) + adapter->flags &= ~(IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED); + + adapter->ring_feature[RING_F_RSS].limit = rss; + adapter->ring_feature[RING_F_VMDQ].limit = 1; + + ixgbe_setup_tc(adapter->netdev, adapter->hw_tcs); +} + static int ixgbe_set_features(struct net_device *netdev, netdev_features_t features) { @@ -9540,7 +9560,9 @@ static int ixgbe_set_features(struct net_device *netdev, } } - if (need_reset) + if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1) + ixgbe_reset_l2fw_offload(adapter); + else if (need_reset) ixgbe_do_reset(netdev); else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER)) @@ -9803,71 +9825,98 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) { - struct ixgbe_fwd_adapter *fwd_adapter = NULL; struct ixgbe_adapter *adapter = netdev_priv(pdev); - int used_pools = adapter->num_vfs + adapter->num_rx_pools; + struct ixgbe_fwd_adapter *accel; int tcs = adapter->hw_tcs ? : 1; - unsigned int limit; int pool, err; - /* Hardware has a limited number of available pools. Each VF, and the - * PF require a pool. Check to ensure we don't attempt to use more - * then the available number of pools. + /* The hardware supported by ixgbe only filters on the destination MAC + * address. In order to avoid issues we only support offloading modes + * where the hardware can actually provide the functionality. */ - if (used_pools >= IXGBE_MAX_VF_FUNCTIONS) - return ERR_PTR(-EINVAL); + if (!macvlan_supports_dest_filter(vdev)) + return ERR_PTR(-EMEDIUMTYPE); - if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && - adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) || - (adapter->num_rx_pools > IXGBE_MAX_MACVLANS)) - return ERR_PTR(-EBUSY); + pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); + if (pool == adapter->num_rx_pools) { + u16 used_pools = adapter->num_vfs + adapter->num_rx_pools; + u16 reserved_pools; + + if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && + adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) || + adapter->num_rx_pools > IXGBE_MAX_MACVLANS) + return ERR_PTR(-EBUSY); + + /* Hardware has a limited number of available pools. Each VF, + * and the PF require a pool. Check to ensure we don't + * attempt to use more then the available number of pools. + */ + if (used_pools >= IXGBE_MAX_VF_FUNCTIONS) + return ERR_PTR(-EBUSY); - fwd_adapter = kzalloc(sizeof(*fwd_adapter), GFP_KERNEL); - if (!fwd_adapter) - return ERR_PTR(-ENOMEM); + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED; - pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); - set_bit(pool, adapter->fwd_bitmask); - limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools + 1); + /* Try to reserve as many queues per pool as possible, + * we start with the configurations that support 4 queues + * per pools, followed by 2, and then by just 1 per pool. + */ + if (used_pools < 32 && adapter->num_rx_pools < 16) + reserved_pools = min_t(u16, + 32 - used_pools, + 16 - adapter->num_rx_pools); + else if (adapter->num_rx_pools < 32) + reserved_pools = min_t(u16, + 64 - used_pools, + 32 - adapter->num_rx_pools); + else + reserved_pools = 64 - used_pools; - /* Enable VMDq flag so device will be set in VM mode */ - adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED; - adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; - fwd_adapter->pool = pool; - fwd_adapter->real_adapter = adapter; + if (!reserved_pools) + return ERR_PTR(-EBUSY); - /* Force reinit of ring allocation with VMDQ enabled */ - err = ixgbe_setup_tc(pdev, adapter->hw_tcs); + adapter->ring_feature[RING_F_VMDQ].limit += reserved_pools; - if (!err && netif_running(pdev)) - err = ixgbe_fwd_ring_up(vdev, fwd_adapter); + /* Force reinit of ring allocation with VMDQ enabled */ + err = ixgbe_setup_tc(pdev, adapter->hw_tcs); + if (err) + return ERR_PTR(err); - if (!err) - return fwd_adapter; + if (pool >= adapter->num_rx_pools) + return ERR_PTR(-ENOMEM); + } + + accel = kzalloc(sizeof(*accel), GFP_KERNEL); + if (!accel) + return ERR_PTR(-ENOMEM); - /* unwind counter and free adapter struct */ - netdev_info(pdev, - "%s: dfwd hardware acceleration failed\n", vdev->name); - clear_bit(pool, adapter->fwd_bitmask); - kfree(fwd_adapter); - return ERR_PTR(err); + set_bit(pool, adapter->fwd_bitmask); + accel->pool = pool; + accel->netdev = vdev; + + if (!netif_running(pdev)) + return accel; + + err = ixgbe_fwd_ring_up(adapter, accel); + if (err) + return ERR_PTR(err); + + return accel; } static void ixgbe_fwd_del(struct net_device *pdev, void *priv) { struct ixgbe_fwd_adapter *accel = priv; - struct ixgbe_adapter *adapter = accel->real_adapter; + struct ixgbe_adapter *adapter = netdev_priv(pdev); unsigned int rxbase = accel->rx_base_queue; - unsigned int limit, i; + unsigned int i; /* delete unicast filter associated with offloaded interface */ ixgbe_del_mac_filter(adapter, accel->netdev->dev_addr, VMDQ_P(accel->pool)); - /* disable ability to receive packets for this pool */ - IXGBE_WRITE_REG(&adapter->hw, IXGBE_VMOLR(accel->pool), 0); - /* Allow remaining Rx packets to get flushed out of the * Rx FIFO before we drop the netdev for the ring. */ @@ -9886,25 +9935,6 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv) } clear_bit(accel->pool, adapter->fwd_bitmask); - limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools); - adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; - - /* go back to full RSS if we're done with our VMQs */ - if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { - int rss = min_t(int, ixgbe_max_rss_indices(adapter), - num_online_cpus()); - - adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; - adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; - adapter->ring_feature[RING_F_RSS].limit = rss; - } - - ixgbe_setup_tc(pdev, adapter->hw_tcs); - netdev_dbg(pdev, "pool %i:%i queues %i:%i\n", - accel->pool, adapter->num_rx_pools, - accel->rx_base_queue, - accel->rx_base_queue + - adapter->num_rx_queues_per_pool); kfree(accel); } diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 008aa073a679..bfc4171cd3f9 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -266,7 +266,7 @@ int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) #endif /* Disable VMDq flag so device will be set in VM mode */ - if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { + if (bitmap_weight(adapter->fwd_bitmask, adapter->num_rx_pools) == 1) { adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; rss = min_t(int, ixgbe_max_rss_indices(adapter), @@ -312,7 +312,8 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) * other values out of range. */ num_tc = adapter->hw_tcs; - num_rx_pools = adapter->num_rx_pools; + num_rx_pools = bitmap_weight(adapter->fwd_bitmask, + adapter->num_rx_pools); limit = (num_tc > 4) ? IXGBE_MAX_VFS_8TC : (num_tc > 1) ? IXGBE_MAX_VFS_4TC : IXGBE_MAX_VFS_1TC; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index c67e1b54c614..733ff53cc601 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -47,6 +47,7 @@ struct net_device; struct nfp_app; +#define NFP_FL_STATS_CTX_DONT_CARE cpu_to_be32(0xffffffff) #define NFP_FL_STATS_ENTRY_RS BIT(20) #define NFP_FL_STATS_ELEM_RS 4 #define NFP_FL_REPEATED_HASH_MAX BIT(17) @@ -189,9 +190,11 @@ struct nfp_fl_payload { spinlock_t lock; /* lock stats */ struct nfp_fl_stats stats; __be32 nfp_tun_ipv4_addr; + struct net_device *ingress_dev; char *unmasked_data; char *mask_data; char *action_data; + bool ingress_offload; }; struct nfp_fl_stats_frame { @@ -216,12 +219,14 @@ int nfp_flower_compile_action(struct tc_cls_flower_offload *flow, struct nfp_fl_payload *nfp_flow); int nfp_compile_flow_metadata(struct nfp_app *app, struct tc_cls_flower_offload *flow, - struct nfp_fl_payload *nfp_flow); + struct nfp_fl_payload *nfp_flow, + struct net_device *netdev); int nfp_modify_flow_metadata(struct nfp_app *app, struct nfp_fl_payload *nfp_flow); struct nfp_fl_payload * -nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie); +nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie, + struct net_device *netdev, __be32 host_ctx); struct nfp_fl_payload * nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie); diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index db977cf8e933..21668aa435e8 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -99,14 +99,18 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id) /* Must be called with either RTNL or rcu_read_lock */ struct nfp_fl_payload * -nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie) +nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie, + struct net_device *netdev, __be32 host_ctx) { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *flower_entry; hash_for_each_possible_rcu(priv->flow_table, flower_entry, link, tc_flower_cookie) - if (flower_entry->tc_flower_cookie == tc_flower_cookie) + if (flower_entry->tc_flower_cookie == tc_flower_cookie && + (!netdev || flower_entry->ingress_dev == netdev) && + (host_ctx == NFP_FL_STATS_CTX_DONT_CARE || + flower_entry->meta.host_ctx_id == host_ctx)) return flower_entry; return NULL; @@ -121,13 +125,11 @@ nfp_flower_update_stats(struct nfp_app *app, struct nfp_fl_stats_frame *stats) flower_cookie = be64_to_cpu(stats->stats_cookie); rcu_read_lock(); - nfp_flow = nfp_flower_search_fl_table(app, flower_cookie); + nfp_flow = nfp_flower_search_fl_table(app, flower_cookie, NULL, + stats->stats_con_id); if (!nfp_flow) goto exit_rcu_unlock; - if (nfp_flow->meta.host_ctx_id != stats->stats_con_id) - goto exit_rcu_unlock; - spin_lock(&nfp_flow->lock); nfp_flow->stats.pkts += be32_to_cpu(stats->pkt_count); nfp_flow->stats.bytes += be64_to_cpu(stats->byte_count); @@ -317,7 +319,8 @@ nfp_check_mask_remove(struct nfp_app *app, char *mask_data, u32 mask_len, int nfp_compile_flow_metadata(struct nfp_app *app, struct tc_cls_flower_offload *flow, - struct nfp_fl_payload *nfp_flow) + struct nfp_fl_payload *nfp_flow, + struct net_device *netdev) { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *check_entry; @@ -348,7 +351,8 @@ int nfp_compile_flow_metadata(struct nfp_app *app, nfp_flow->stats.bytes = 0; nfp_flow->stats.used = jiffies; - check_entry = nfp_flower_search_fl_table(app, flow->cookie); + check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev, + NFP_FL_STATS_CTX_DONT_CARE); if (check_entry) { if (nfp_release_stats_entry(app, stats_cxt)) return -EINVAL; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 114d2ab02a38..70ec9d821b91 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -345,7 +345,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } static struct nfp_fl_payload * -nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) +nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress) { struct nfp_fl_payload *flow_pay; @@ -371,6 +371,8 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) flow_pay->meta.flags = 0; spin_lock_init(&flow_pay->lock); + flow_pay->ingress_offload = !egress; + return flow_pay; err_free_mask: @@ -402,8 +404,20 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *flow_pay; struct nfp_fl_key_ls *key_layer; + struct net_device *ingr_dev; int err; + ingr_dev = egress ? NULL : netdev; + flow_pay = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev, + NFP_FL_STATS_CTX_DONT_CARE); + if (flow_pay) { + /* Ignore as duplicate if it has been added by different cb. */ + if (flow_pay->ingress_offload && egress) + return 0; + else + return -EOPNOTSUPP; + } + key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL); if (!key_layer) return -ENOMEM; @@ -413,12 +427,14 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_free_key_ls; - flow_pay = nfp_flower_allocate_new(key_layer); + flow_pay = nfp_flower_allocate_new(key_layer, egress); if (!flow_pay) { err = -ENOMEM; goto err_free_key_ls; } + flow_pay->ingress_dev = egress ? NULL : netdev; + err = nfp_flower_compile_flow_match(flow, key_layer, netdev, flow_pay, tun_type); if (err) @@ -428,7 +444,8 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_destroy_flow; - err = nfp_compile_flow_metadata(app, flow, flow_pay); + err = nfp_compile_flow_metadata(app, flow, flow_pay, + flow_pay->ingress_dev); if (err) goto err_destroy_flow; @@ -462,6 +479,7 @@ err_free_key_ls: * @app: Pointer to the APP handle * @netdev: netdev structure. * @flow: TC flower classifier offload structure + * @egress: Netdev is the egress dev. * * Removes a flow from the repeated hash structure and clears the * action payload. @@ -470,15 +488,18 @@ err_free_key_ls: */ static int nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, - struct tc_cls_flower_offload *flow) + struct tc_cls_flower_offload *flow, bool egress) { struct nfp_port *port = nfp_port_from_netdev(netdev); struct nfp_fl_payload *nfp_flow; + struct net_device *ingr_dev; int err; - nfp_flow = nfp_flower_search_fl_table(app, flow->cookie); + ingr_dev = egress ? NULL : netdev; + nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev, + NFP_FL_STATS_CTX_DONT_CARE); if (!nfp_flow) - return -ENOENT; + return egress ? 0 : -ENOENT; err = nfp_modify_flow_metadata(app, nfp_flow); if (err) @@ -505,7 +526,9 @@ err_free_flow: /** * nfp_flower_get_stats() - Populates flow stats obtained from hardware. * @app: Pointer to the APP handle + * @netdev: Netdev structure. * @flow: TC flower classifier offload structure + * @egress: Netdev is the egress dev. * * Populates a flow statistics structure which which corresponds to a * specific flow. @@ -513,14 +536,21 @@ err_free_flow: * Return: negative value on error, 0 if stats populated successfully. */ static int -nfp_flower_get_stats(struct nfp_app *app, struct tc_cls_flower_offload *flow) +nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev, + struct tc_cls_flower_offload *flow, bool egress) { struct nfp_fl_payload *nfp_flow; + struct net_device *ingr_dev; - nfp_flow = nfp_flower_search_fl_table(app, flow->cookie); + ingr_dev = egress ? NULL : netdev; + nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev, + NFP_FL_STATS_CTX_DONT_CARE); if (!nfp_flow) return -EINVAL; + if (nfp_flow->ingress_offload && egress) + return 0; + spin_lock_bh(&nfp_flow->lock); tcf_exts_stats_update(flow->exts, nfp_flow->stats.bytes, nfp_flow->stats.pkts, nfp_flow->stats.used); @@ -543,9 +573,9 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev, case TC_CLSFLOWER_REPLACE: return nfp_flower_add_offload(app, netdev, flower, egress); case TC_CLSFLOWER_DESTROY: - return nfp_flower_del_offload(app, netdev, flower); + return nfp_flower_del_offload(app, netdev, flower, egress); case TC_CLSFLOWER_STATS: - return nfp_flower_get_stats(app, flower); + return nfp_flower_get_stats(app, netdev, flower, egress); } return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index c4b1f344b4da..0ade122805ad 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -486,6 +486,10 @@ static int nfp_pci_probe(struct pci_dev *pdev, goto err_disable_msix; } + err = nfp_resource_table_init(pf->cpp); + if (err) + goto err_cpp_free; + pf->hwinfo = nfp_hwinfo_read(pf->cpp); dev_info(&pdev->dev, "Assembly: %s%s%s-%s CPLD: %s\n", @@ -548,6 +552,7 @@ err_fw_unload: vfree(pf->dumpspec); err_hwinfo_free: kfree(pf->hwinfo); +err_cpp_free: nfp_cpp_free(pf->cpp); err_disable_msix: destroy_workqueue(pf->wq); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h index ced62d112aa2..f44d0a857314 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h @@ -94,6 +94,8 @@ int nfp_nsp_read_sensors(struct nfp_nsp *state, unsigned int sensor_mask, /* MAC Statistics Accumulator */ #define NFP_RESOURCE_MAC_STATISTICS "mac.stat" +int nfp_resource_table_init(struct nfp_cpp *cpp); + struct nfp_resource * nfp_resource_acquire(struct nfp_cpp *cpp, const char *name); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index cd678323bacb..a0e336bd1d85 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -1330,6 +1330,7 @@ struct nfp_cpp *nfp_cpp_from_nfp6000_pcie(struct pci_dev *pdev) /* Finished with card initialization. */ dev_info(&pdev->dev, "Netronome Flow Processor NFP4000/NFP6000 PCIe Card Probe\n"); + pcie_print_link_status(pdev); nfp = kzalloc(sizeof(*nfp), GFP_KERNEL); if (!nfp) { diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h index c8f2c064cce3..4e19add1c539 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h @@ -295,6 +295,8 @@ void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex); int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex); int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex); int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex); +int nfp_cpp_mutex_reclaim(struct nfp_cpp *cpp, int target, + unsigned long long address); /** * nfp_cppcore_pcie_unit() - Get PCI Unit of a CPP handle diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c index cb28ac03e4ca..c88bf673cb76 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c @@ -59,6 +59,11 @@ static u32 nfp_mutex_unlocked(u16 interface) return (u32)interface << 16 | 0x0000; } +static u32 nfp_mutex_owner(u32 val) +{ + return val >> 16; +} + static bool nfp_mutex_is_locked(u32 val) { return (val & 0xffff) == 0x000f; @@ -351,3 +356,43 @@ int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex) return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL; } + +/** + * nfp_cpp_mutex_reclaim() - Unlock mutex if held by local endpoint + * @cpp: NFP CPP handle + * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU) + * @address: Offset into the address space of the NFP CPP target ID + * + * Release lock if held by local system. Extreme care is advised, call only + * when no local lock users can exist. + * + * Return: 0 if the lock was OK, 1 if locked by us, -errno on invalid mutex + */ +int nfp_cpp_mutex_reclaim(struct nfp_cpp *cpp, int target, + unsigned long long address) +{ + const u32 mur = NFP_CPP_ID(target, 3, 0); /* atomic_read */ + const u32 muw = NFP_CPP_ID(target, 4, 0); /* atomic_write */ + u16 interface = nfp_cpp_interface(cpp); + int err; + u32 tmp; + + err = nfp_cpp_mutex_validate(interface, &target, address); + if (err) + return err; + + /* Check lock */ + err = nfp_cpp_readl(cpp, mur, address, &tmp); + if (err < 0) + return err; + + if (nfp_mutex_is_unlocked(tmp) || nfp_mutex_owner(tmp) != interface) + return 0; + + /* Bust the lock */ + err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_unlocked(interface)); + if (err < 0) + return err; + + return 1; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c index 7e14725055c7..2dd89dba9311 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c @@ -338,3 +338,62 @@ u64 nfp_resource_size(struct nfp_resource *res) { return res->size; } + +/** + * nfp_resource_table_init() - Run initial checks on the resource table + * @cpp: NFP CPP handle + * + * Start-of-day init procedure for resource table. Must be called before + * any local resource table users may exist. + * + * Return: 0 on success, -errno on failure + */ +int nfp_resource_table_init(struct nfp_cpp *cpp) +{ + struct nfp_cpp_mutex *dev_mutex; + int i, err; + + err = nfp_cpp_mutex_reclaim(cpp, NFP_RESOURCE_TBL_TARGET, + NFP_RESOURCE_TBL_BASE); + if (err < 0) { + nfp_err(cpp, "Error: failed to reclaim resource table mutex\n"); + return err; + } + if (err) + nfp_warn(cpp, "Warning: busted main resource table mutex\n"); + + dev_mutex = nfp_cpp_mutex_alloc(cpp, NFP_RESOURCE_TBL_TARGET, + NFP_RESOURCE_TBL_BASE, + NFP_RESOURCE_TBL_KEY); + if (!dev_mutex) + return -ENOMEM; + + if (nfp_cpp_mutex_lock(dev_mutex)) { + nfp_err(cpp, "Error: failed to claim resource table mutex\n"); + nfp_cpp_mutex_free(dev_mutex); + return -EINVAL; + } + + /* Resource 0 is the dev_mutex, start from 1 */ + for (i = 1; i < NFP_RESOURCE_TBL_ENTRIES; i++) { + u64 addr = NFP_RESOURCE_TBL_BASE + + sizeof(struct nfp_resource_entry) * i; + + err = nfp_cpp_mutex_reclaim(cpp, NFP_RESOURCE_TBL_TARGET, addr); + if (err < 0) { + nfp_err(cpp, + "Error: failed to reclaim resource %d mutex\n", + i); + goto err_unlock; + } + if (err) + nfp_warn(cpp, "Warning: busted resource %d mutex\n", i); + } + + err = 0; +err_unlock: + nfp_cpp_mutex_unlock(dev_mutex); + nfp_cpp_mutex_free(dev_mutex); + + return err; +} diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index c180b480f8ef..13e4c1eff353 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -217,7 +217,7 @@ static int kiss_esc_crc(unsigned char *s, unsigned char *d, unsigned short crc, c = *s++; else if (len > 1) c = crc >> 8; - else if (len > 0) + else c = crc & 0xff; len--; diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 725f4b4afc6d..adde8fc45588 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -514,6 +514,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; + void *accel_priv = NULL; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = (void *)skb->data; @@ -533,9 +534,14 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) } } + /* For packets that are non-multicast and not bridged we will pass + * the necessary information so that the lowerdev can distinguish + * the source of the packets via the accel_priv value. + */ + accel_priv = vlan->accel_priv; xmit_world: skb->dev = vlan->lowerdev; - return dev_queue_xmit(skb); + return dev_queue_xmit_accel(skb, accel_priv); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) @@ -552,19 +558,14 @@ static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, str static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { + struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; - struct macvlan_dev *vlan = netdev_priv(dev); if (unlikely(netpoll_tx_running(dev))) return macvlan_netpoll_send_skb(vlan, skb); - if (vlan->fwd_priv) { - skb->dev = vlan->lowerdev; - ret = dev_queue_xmit_accel(skb, vlan->fwd_priv); - } else { - ret = macvlan_queue_xmit(skb, dev); - } + ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *pcpu_stats; @@ -613,26 +614,27 @@ static int macvlan_open(struct net_device *dev) goto hash_add; } - if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) { - vlan->fwd_priv = - lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); - - /* If we get a NULL pointer back, or if we get an error - * then we should just fall through to the non accelerated path - */ - if (IS_ERR_OR_NULL(vlan->fwd_priv)) { - vlan->fwd_priv = NULL; - } else - return 0; - } - err = -EBUSY; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; - err = dev_uc_add(lowerdev, dev->dev_addr); - if (err < 0) - goto out; + /* Attempt to populate accel_priv which is used to offload the L2 + * forwarding requests for unicast packets. + */ + if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) + vlan->accel_priv = + lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); + + /* If earlier attempt to offload failed, or accel_priv is not + * populated we must add the unicast address to the lower device. + */ + if (IS_ERR_OR_NULL(vlan->accel_priv)) { + vlan->accel_priv = NULL; + err = dev_uc_add(lowerdev, dev->dev_addr); + if (err < 0) + goto out; + } + if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(lowerdev, 1); if (err < 0) @@ -653,13 +655,14 @@ clear_multi: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); del_unicast: - dev_uc_del(lowerdev, dev->dev_addr); -out: - if (vlan->fwd_priv) { + if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, - vlan->fwd_priv); - vlan->fwd_priv = NULL; + vlan->accel_priv); + vlan->accel_priv = NULL; + } else { + dev_uc_del(lowerdev, dev->dev_addr); } +out: return err; } @@ -668,11 +671,10 @@ static int macvlan_stop(struct net_device *dev) struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - if (vlan->fwd_priv) { + if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, - vlan->fwd_priv); - vlan->fwd_priv = NULL; - return 0; + vlan->accel_priv); + vlan->accel_priv = NULL; } dev_uc_unsync(lowerdev, dev); diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 4cb7aeeafce0..2e55e4cdbd8a 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -21,7 +21,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - void *fwd_priv; + void *accel_priv; struct vlan_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); @@ -61,10 +61,6 @@ extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); -extern void macvlan_count_rx(const struct macvlan_dev *vlan, - unsigned int len, bool success, - bool multicast); - extern void macvlan_dellink(struct net_device *dev, struct list_head *head); extern int macvlan_link_register(struct rtnl_link_ops *ops); @@ -86,4 +82,27 @@ macvlan_dev_real_dev(const struct net_device *dev) } #endif +static inline void *macvlan_accel_priv(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->accel_priv; +} + +static inline bool macvlan_supports_dest_filter(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->mode == MACVLAN_MODE_PRIVATE || + macvlan->mode == MACVLAN_MODE_VEPA || + macvlan->mode == MACVLAN_MODE_BRIDGE; +} + +static inline int macvlan_release_l2fw_offload(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + macvlan->accel_priv = NULL; + return dev_uc_add(macvlan->lowerdev, dev->dev_addr); +} #endif /* _LINUX_IF_MACVLAN_H */ diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e421f86af043..6c1eecd56a4d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -246,6 +246,7 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_OVERRIDE 0x00000001 #define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 #define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 +#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 @@ -526,5 +527,21 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, } while (read_seqretry(&n->ha_lock, seq)); } - +static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags, + int *notify) +{ + u8 ndm_flags = 0; + + if (!(flags & NEIGH_UPDATE_F_ADMIN)) + return; + + ndm_flags |= (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + if (ndm_flags & NTF_EXT_LEARNED) + neigh->flags |= NTF_EXT_LEARNED; + else + neigh->flags &= ~NTF_EXT_LEARNED; + *notify = 1; + } +} #endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index 97b3a54579c8..c978a31b0f84 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -43,6 +43,7 @@ struct netns_sysctl_ipv6 { int max_hbh_opts_cnt; int max_dst_opts_len; int max_hbh_opts_len; + int seg6_flowlabel; }; struct netns_ipv6 { diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2d0e782c9055..f4b657478a30 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -207,7 +207,7 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, int len, __u8 flags, gfp_t gfp); struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn); -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc); +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc); struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a0ec462bc1a9..05594b248e52 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -2091,10 +2091,6 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, enum sctp_transport_cmd command, sctp_sn_error_t error); struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32); -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *, - struct net *, - const union sctp_addr *, - const union sctp_addr *); void sctp_assoc_migrate(struct sctp_association *, struct sock *); int sctp_assoc_update(struct sctp_association *old, struct sctp_association *new); diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 2271c80fd967..126ffc5bc630 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -454,6 +454,27 @@ static struct fib_rule *rule_find(struct fib_rules_ops *ops, return NULL; } +#ifdef CONFIG_NET_L3_MASTER_DEV +static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, + struct netlink_ext_ack *extack) +{ + nlrule->l3mdev = nla_get_u8(nla); + if (nlrule->l3mdev != 1) { + NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); + return -1; + } + + return 0; +} +#else +static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); + return -1; +} +#endif + static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack, struct fib_rules_ops *ops, @@ -536,16 +557,9 @@ static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); err = -EINVAL; - if (tb[FRA_L3MDEV]) { -#ifdef CONFIG_NET_L3_MASTER_DEV - nlrule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]); - if (nlrule->l3mdev != 1) -#endif - { - NL_SET_ERR_MSG(extack, "Invalid l3mdev"); - goto errout_free; - } - } + if (tb[FRA_L3MDEV] && + fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) + goto errout_free; nlrule->action = frh->action; nlrule->flags = frh->flags; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ce519861be59..5afae29367c1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -820,7 +820,8 @@ static void neigh_periodic_work(struct work_struct *work) write_lock(&n->lock); state = n->nud_state; - if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { + if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || + (n->flags & NTF_EXT_LEARNED)) { write_unlock(&n->lock); goto next_elt; } @@ -1136,6 +1137,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (neigh->dead) goto out; + neigh_update_ext_learned(neigh, flags, ¬ify); + if (!(new & NUD_VALID)) { neigh_del_timer(neigh); if (old & NUD_CONNECTED) @@ -1781,6 +1784,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, flags &= ~NEIGH_UPDATE_F_OVERRIDE; } + if (ndm->ndm_flags & NTF_EXT_LEARNED) + flags |= NEIGH_UPDATE_F_EXT_LEARNED; + if (ndm->ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 7b4d7bbf2c17..fbfd71a2d9c8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -3622,8 +3622,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - int _keep_addr; - bool keep_addr; + bool keep_addr = false; int state, i; ASSERT_RTNL(); @@ -3649,15 +3648,18 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* aggregate the system setting and interface setting */ - _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; - if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; - /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); + if (!how && !idev->cnf.disable_ipv6) { + /* aggregate the system setting and interface setting */ + int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + keep_addr = (_keep_addr > 0); + } /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3707,11 +3709,6 @@ restart: write_lock_bh(&idev->lock); } - /* re-combine the user config with event to determine if permanent - * addresses are to be removed from the interface list - */ - keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { struct fib6_info *rt = NULL; bool keep; diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 5fe139484919..9898926ce30d 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -91,6 +91,24 @@ static void set_tun_src(struct net *net, struct net_device *dev, rcu_read_unlock(); } +/* Compute flowlabel for outer IPv6 header */ +static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, + struct ipv6hdr *inner_hdr) +{ + int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel; + __be32 flowlabel = 0; + u32 hash; + + if (do_flowlabel > 0) { + hash = skb_get_hash(skb); + rol32(hash, 16); + flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; + } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { + flowlabel = ip6_flowlabel(inner_hdr); + } + return flowlabel; +} + /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { @@ -99,6 +117,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; + __be32 flowlabel; hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); @@ -119,12 +138,13 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) * decapsulation will overwrite inner hlim with outer hlim */ + flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), - ip6_flowlabel(inner_hdr)); + flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 6fbdef630152..e15cd37024fd 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -152,6 +152,13 @@ static struct ctl_table ipv6_table_template[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "seg6_flowlabel", + .data = &init_net.ipv6.sysctl.seg6_flowlabel, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -217,6 +224,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, + ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 837806dd5799..a8f3b088fcb2 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -988,31 +988,6 @@ out: return match; } -/* Is this the association we are looking for? */ -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc, - struct net *net, - const union sctp_addr *laddr, - const union sctp_addr *paddr) -{ - struct sctp_transport *transport; - - if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) && - (htons(asoc->peer.port) == paddr->v4.sin_port) && - net_eq(sock_net(asoc->base.sk), net)) { - transport = sctp_assoc_lookup_paddr(asoc, paddr); - if (!transport) - goto out; - - if (sctp_bind_addr_match(&asoc->base.bind_addr, laddr, - sctp_sk(asoc->base.sk))) - goto out; - } - transport = NULL; - -out: - return transport; -} - /* Do delayed input processing. This is scheduled by sctp_rcv(). */ static void sctp_assoc_bh_rcv(struct work_struct *work) { diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f211b3db6a35..dee7cbd54831 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1457,7 +1457,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ - if (transport) { + if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. @@ -1469,14 +1469,34 @@ static void sctp_check_transmitted(struct sctp_outq *q, * first instance of the packet or a later * instance). */ - if (!tchunk->tsn_gap_acked && - !sctp_chunk_retransmitted(tchunk) && + if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } + + if (TSN_lte(tsn, sack_ctsn)) { + /* + * SFR-CACC algorithm: + * 2) If the SACK contains gap acks + * and the flag CHANGEOVER_ACTIVE is + * set the receiver of the SACK MUST + * take the following action: + * + * B) For each TSN t being acked that + * has not been acked in any SACK so + * far, set cacc_saw_newack to 1 for + * the destination that the TSN was + * sent to. + */ + if (sack->num_gap_ack_blocks && + q->asoc->peer.primary_path->cacc. + changeover_active) + transport->cacc.cacc_saw_newack + = 1; + } } /* If the chunk hasn't been marked as ACKED, @@ -1508,28 +1528,6 @@ static void sctp_check_transmitted(struct sctp_outq *q, restart_timer = 1; forward_progress = true; - if (!tchunk->tsn_gap_acked) { - /* - * SFR-CACC algorithm: - * 2) If the SACK contains gap acks - * and the flag CHANGEOVER_ACTIVE is - * set the receiver of the SACK MUST - * take the following action: - * - * B) For each TSN t being acked that - * has not been acked in any SACK so - * far, set cacc_saw_newack to 1 for - * the destination that the TSN was - * sent to. - */ - if (transport && - sack->num_gap_ack_blocks && - q->asoc->peer.primary_path->cacc. - changeover_active) - transport->cacc.cacc_saw_newack - = 1; - } - list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 5a4fb1dc8400..db93eabd6ef5 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -779,10 +779,9 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, * association. This reports on which TSN's we've seen to date, * including duplicates and gaps. */ -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc) { struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; - struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; __u16 num_gabs, num_dup_tsns; struct sctp_transport *trans; @@ -857,7 +856,7 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) /* Add the duplicate TSN information. */ if (num_dup_tsns) { - aptr->stats.idupchunks += num_dup_tsns; + asoc->stats.idupchunks += num_dup_tsns; sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); } @@ -869,11 +868,11 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) * association so no transport will match after a wrap event like this, * Until the next sack */ - if (++aptr->peer.sack_generation == 0) { + if (++asoc->peer.sack_generation == 0) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) trans->sack_generation = 0; - aptr->peer.sack_generation = 1; + asoc->peer.sack_generation = 1; } nodata: return retval; |