diff options
36 files changed, 264 insertions, 76 deletions
diff --git a/MAINTAINERS b/MAINTAINERS index 8119141a926f..2fbe569fb76c 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -8938,7 +8938,7 @@ F: arch/mips/boot/dts/img/pistachio_marduk.dts MARVELL 88E6XXX ETHERNET SWITCH FABRIC DRIVER M: Andrew Lunn <andrew@lunn.ch> -M: Vivien Didelot <vivien.didelot@savoirfairelinux.com> +M: Vivien Didelot <vivien.didelot@gmail.com> L: netdev@vger.kernel.org S: Maintained F: drivers/net/dsa/mv88e6xxx/ @@ -10416,7 +10416,7 @@ F: drivers/net/wireless/ NETWORKING [DSA] M: Andrew Lunn <andrew@lunn.ch> -M: Vivien Didelot <vivien.didelot@savoirfairelinux.com> +M: Vivien Didelot <vivien.didelot@gmail.com> M: Florian Fainelli <f.fainelli@gmail.com> S: Maintained F: Documentation/devicetree/bindings/net/dsa/ diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index e05d4eddc935..24fb6a685039 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -1124,7 +1124,7 @@ static void mv88e6xxx_get_regs(struct dsa_switch *ds, int port, u16 *p = _p; int i; - regs->version = 0; + regs->version = chip->info->prod_num; memset(p, 0xff, 32 * sizeof(u16)); diff --git a/drivers/net/ethernet/cadence/macb_main.c b/drivers/net/ethernet/cadence/macb_main.c index 1d86b4d5645a..4c816e5a841f 100644 --- a/drivers/net/ethernet/cadence/macb_main.c +++ b/drivers/net/ethernet/cadence/macb_main.c @@ -61,7 +61,8 @@ #define MACB_TX_ERR_FLAGS (MACB_BIT(ISR_TUND) \ | MACB_BIT(ISR_RLE) \ | MACB_BIT(TXERR)) -#define MACB_TX_INT_FLAGS (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP)) +#define MACB_TX_INT_FLAGS (MACB_TX_ERR_FLAGS | MACB_BIT(TCOMP) \ + | MACB_BIT(TXUBR)) /* Max length of transmit frame must be a multiple of 8 bytes */ #define MACB_TX_LEN_ALIGN 8 @@ -680,6 +681,11 @@ static void macb_set_addr(struct macb *bp, struct macb_dma_desc *desc, dma_addr_ if (bp->hw_dma_cap & HW_DMA_CAP_64B) { desc_64 = macb_64b_desc(bp, desc); desc_64->addrh = upper_32_bits(addr); + /* The low bits of RX address contain the RX_USED bit, clearing + * of which allows packet RX. Make sure the high bits are also + * visible to HW at that point. + */ + dma_wmb(); } #endif desc->addr = lower_32_bits(addr); @@ -928,14 +934,19 @@ static void gem_rx_refill(struct macb_queue *queue) if (entry == bp->rx_ring_size - 1) paddr |= MACB_BIT(RX_WRAP); - macb_set_addr(bp, desc, paddr); desc->ctrl = 0; + /* Setting addr clears RX_USED and allows reception, + * make sure ctrl is cleared first to avoid a race. + */ + dma_wmb(); + macb_set_addr(bp, desc, paddr); /* properly align Ethernet header */ skb_reserve(skb, NET_IP_ALIGN); } else { - desc->addr &= ~MACB_BIT(RX_USED); desc->ctrl = 0; + dma_wmb(); + desc->addr &= ~MACB_BIT(RX_USED); } } @@ -989,11 +1000,15 @@ static int gem_rx(struct macb_queue *queue, int budget) rxused = (desc->addr & MACB_BIT(RX_USED)) ? true : false; addr = macb_get_addr(bp, desc); - ctrl = desc->ctrl; if (!rxused) break; + /* Ensure ctrl is at least as up-to-date as rxused */ + dma_rmb(); + + ctrl = desc->ctrl; + queue->rx_tail++; count++; @@ -1168,11 +1183,14 @@ static int macb_rx(struct macb_queue *queue, int budget) /* Make hw descriptor updates visible to CPU */ rmb(); - ctrl = desc->ctrl; - if (!(desc->addr & MACB_BIT(RX_USED))) break; + /* Ensure ctrl is at least as up-to-date as addr */ + dma_rmb(); + + ctrl = desc->ctrl; + if (ctrl & MACB_BIT(RX_SOF)) { if (first_frag != -1) discard_partial_frame(queue, first_frag, tail); @@ -1312,6 +1330,21 @@ static void macb_hresp_error_task(unsigned long data) netif_tx_start_all_queues(dev); } +static void macb_tx_restart(struct macb_queue *queue) +{ + unsigned int head = queue->tx_head; + unsigned int tail = queue->tx_tail; + struct macb *bp = queue->bp; + + if (bp->caps & MACB_CAPS_ISR_CLEAR_ON_WRITE) + queue_writel(queue, ISR, MACB_BIT(TXUBR)); + + if (head == tail) + return; + + macb_writel(bp, NCR, macb_readl(bp, NCR) | MACB_BIT(TSTART)); +} + static irqreturn_t macb_interrupt(int irq, void *dev_id) { struct macb_queue *queue = dev_id; @@ -1369,6 +1402,9 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) if (status & MACB_BIT(TCOMP)) macb_tx_interrupt(queue); + if (status & MACB_BIT(TXUBR)) + macb_tx_restart(queue); + /* Link change detection isn't possible with RMII, so we'll * add that if/when we get our hands on a full-blown MII PHY. */ diff --git a/drivers/net/ethernet/cadence/macb_ptp.c b/drivers/net/ethernet/cadence/macb_ptp.c index cd5296b84229..a6dc47edc4cf 100644 --- a/drivers/net/ethernet/cadence/macb_ptp.c +++ b/drivers/net/ethernet/cadence/macb_ptp.c @@ -319,6 +319,8 @@ int gem_ptp_txstamp(struct macb_queue *queue, struct sk_buff *skb, desc_ptp = macb_ptp_desc(queue->bp, desc); tx_timestamp = &queue->tx_timestamps[head]; tx_timestamp->skb = skb; + /* ensure ts_1/ts_2 is loaded after ctrl (TX_USED check) */ + dma_rmb(); tx_timestamp->desc_ptp.ts_1 = desc_ptp->ts_1; tx_timestamp->desc_ptp.ts_2 = desc_ptp->ts_2; /* move head */ diff --git a/drivers/net/ethernet/marvell/mvneta.c b/drivers/net/ethernet/marvell/mvneta.c index e5397c8197b9..61b23497f836 100644 --- a/drivers/net/ethernet/marvell/mvneta.c +++ b/drivers/net/ethernet/marvell/mvneta.c @@ -408,7 +408,6 @@ struct mvneta_port { struct mvneta_pcpu_stats __percpu *stats; int pkt_size; - unsigned int frag_size; void __iomem *base; struct mvneta_rx_queue *rxqs; struct mvneta_tx_queue *txqs; @@ -2905,7 +2904,9 @@ static void mvneta_rxq_hw_init(struct mvneta_port *pp, if (!pp->bm_priv) { /* Set Offset */ mvneta_rxq_offset_set(pp, rxq, 0); - mvneta_rxq_buf_size_set(pp, rxq, pp->frag_size); + mvneta_rxq_buf_size_set(pp, rxq, PAGE_SIZE < SZ_64K ? + PAGE_SIZE : + MVNETA_RX_BUF_SIZE(pp->pkt_size)); mvneta_rxq_bm_disable(pp, rxq); mvneta_rxq_fill(pp, rxq, rxq->size); } else { @@ -3760,7 +3761,6 @@ static int mvneta_open(struct net_device *dev) int ret; pp->pkt_size = MVNETA_RX_PKT_SIZE(pp->dev->mtu); - pp->frag_size = PAGE_SIZE; ret = mvneta_setup_rxqs(pp); if (ret) diff --git a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c index 125ea99418df..88aa488054a8 100644 --- a/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c +++ b/drivers/net/ethernet/marvell/mvpp2/mvpp2_main.c @@ -4405,12 +4405,14 @@ static void mvpp2_phylink_validate(struct net_device *dev, case PHY_INTERFACE_MODE_10GKR: case PHY_INTERFACE_MODE_XAUI: case PHY_INTERFACE_MODE_NA: - phylink_set(mask, 10000baseCR_Full); - phylink_set(mask, 10000baseSR_Full); - phylink_set(mask, 10000baseLR_Full); - phylink_set(mask, 10000baseLRM_Full); - phylink_set(mask, 10000baseER_Full); - phylink_set(mask, 10000baseKR_Full); + if (port->gop_id == 0) { + phylink_set(mask, 10000baseCR_Full); + phylink_set(mask, 10000baseSR_Full); + phylink_set(mask, 10000baseLR_Full); + phylink_set(mask, 10000baseLRM_Full); + phylink_set(mask, 10000baseER_Full); + phylink_set(mask, 10000baseKR_Full); + } /* Fall-through */ case PHY_INTERFACE_MODE_RGMII: case PHY_INTERFACE_MODE_RGMII_ID: diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.c b/drivers/net/ethernet/mellanox/mlxsw/core.c index 30f751e69698..f7154f358f27 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.c +++ b/drivers/net/ethernet/mellanox/mlxsw/core.c @@ -81,6 +81,7 @@ struct mlxsw_core { struct mlxsw_core_port *ports; unsigned int max_ports; bool reload_fail; + bool fw_flash_in_progress; unsigned long driver_priv[0]; /* driver_priv has to be always the last item */ }; @@ -428,12 +429,16 @@ struct mlxsw_reg_trans { struct rcu_head rcu; }; -#define MLXSW_EMAD_TIMEOUT_MS 200 +#define MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS 3000 +#define MLXSW_EMAD_TIMEOUT_MS 200 static void mlxsw_emad_trans_timeout_schedule(struct mlxsw_reg_trans *trans) { unsigned long timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_MS); + if (trans->core->fw_flash_in_progress) + timeout = msecs_to_jiffies(MLXSW_EMAD_TIMEOUT_DURING_FW_FLASH_MS); + queue_delayed_work(trans->core->emad_wq, &trans->timeout_dw, timeout); } @@ -1854,6 +1859,18 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core, } EXPORT_SYMBOL(mlxsw_core_kvd_sizes_get); +void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core) +{ + mlxsw_core->fw_flash_in_progress = true; +} +EXPORT_SYMBOL(mlxsw_core_fw_flash_start); + +void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core) +{ + mlxsw_core->fw_flash_in_progress = false; +} +EXPORT_SYMBOL(mlxsw_core_fw_flash_end); + static int __init mlxsw_core_module_init(void) { int err; diff --git a/drivers/net/ethernet/mellanox/mlxsw/core.h b/drivers/net/ethernet/mellanox/mlxsw/core.h index c35be477856f..c4e4971764e5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/core.h +++ b/drivers/net/ethernet/mellanox/mlxsw/core.h @@ -292,6 +292,9 @@ int mlxsw_core_kvd_sizes_get(struct mlxsw_core *mlxsw_core, u64 *p_single_size, u64 *p_double_size, u64 *p_linear_size); +void mlxsw_core_fw_flash_start(struct mlxsw_core *mlxsw_core); +void mlxsw_core_fw_flash_end(struct mlxsw_core *mlxsw_core); + bool mlxsw_core_res_valid(struct mlxsw_core *mlxsw_core, enum mlxsw_res_id res_id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index 9bec940330a4..f84b9c02fcc5 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -309,8 +309,13 @@ static int mlxsw_sp_firmware_flash(struct mlxsw_sp *mlxsw_sp, }, .mlxsw_sp = mlxsw_sp }; + int err; + + mlxsw_core_fw_flash_start(mlxsw_sp->core); + err = mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware); + mlxsw_core_fw_flash_end(mlxsw_sp->core); - return mlxfw_firmware_flash(&mlxsw_sp_mlxfw_dev.mlxfw_dev, firmware); + return err; } static int mlxsw_sp_fw_rev_validate(struct mlxsw_sp *mlxsw_sp) @@ -3521,6 +3526,7 @@ static const struct mlxsw_listener mlxsw_sp_listener[] = { MLXSW_SP_RXL_MR_MARK(ACL2, TRAP_TO_CPU, MULTICAST, false), /* NVE traps */ MLXSW_SP_RXL_MARK(NVE_ENCAP_ARP, TRAP_TO_CPU, ARP, false), + MLXSW_SP_RXL_NO_MARK(NVE_DECAP_ARP, TRAP_TO_CPU, ARP, false), }; static int mlxsw_sp_cpu_policers_set(struct mlxsw_core *mlxsw_core) diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c index 5c13674439f1..b5b54b41349a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_nve.c @@ -977,6 +977,6 @@ void mlxsw_sp_nve_fini(struct mlxsw_sp *mlxsw_sp) { WARN_ON(mlxsw_sp->nve->num_nve_tunnels); rhashtable_destroy(&mlxsw_sp->nve->mc_list_ht); - mlxsw_sp->nve = NULL; kfree(mlxsw_sp->nve); + mlxsw_sp->nve = NULL; } diff --git a/drivers/net/ethernet/mellanox/mlxsw/trap.h b/drivers/net/ethernet/mellanox/mlxsw/trap.h index 6f18f4d3322a..451216dd7f6b 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/trap.h +++ b/drivers/net/ethernet/mellanox/mlxsw/trap.h @@ -60,6 +60,7 @@ enum { MLXSW_TRAP_ID_IPV6_MC_LINK_LOCAL_DEST = 0x91, MLXSW_TRAP_ID_HOST_MISS_IPV6 = 0x92, MLXSW_TRAP_ID_IPIP_DECAP_ERROR = 0xB1, + MLXSW_TRAP_ID_NVE_DECAP_ARP = 0xB8, MLXSW_TRAP_ID_NVE_ENCAP_ARP = 0xBD, MLXSW_TRAP_ID_ROUTER_ALERT_IPV4 = 0xD6, MLXSW_TRAP_ID_ROUTER_ALERT_IPV6 = 0xD7, diff --git a/drivers/net/ethernet/microchip/lan743x_main.c b/drivers/net/ethernet/microchip/lan743x_main.c index e8ca98c070f6..1ba8ea07dc4f 100644 --- a/drivers/net/ethernet/microchip/lan743x_main.c +++ b/drivers/net/ethernet/microchip/lan743x_main.c @@ -2719,8 +2719,9 @@ static int lan743x_mdiobus_init(struct lan743x_adapter *adapter) snprintf(adapter->mdiobus->id, MII_BUS_ID_SIZE, "pci-%s", pci_name(adapter->pdev)); - /* set to internal PHY id */ - adapter->mdiobus->phy_mask = ~(u32)BIT(1); + if ((adapter->csr.id_rev & ID_REV_ID_MASK_) == ID_REV_ID_LAN7430_) + /* LAN7430 uses internal phy at address 1 */ + adapter->mdiobus->phy_mask = ~(u32)BIT(1); /* register mdiobus */ ret = mdiobus_register(adapter->mdiobus); diff --git a/drivers/net/ethernet/neterion/vxge/vxge-config.c b/drivers/net/ethernet/neterion/vxge/vxge-config.c index 4c1fb7e57888..7cde387e5ec6 100644 --- a/drivers/net/ethernet/neterion/vxge/vxge-config.c +++ b/drivers/net/ethernet/neterion/vxge/vxge-config.c @@ -808,7 +808,7 @@ __vxge_hw_vpath_fw_ver_get(struct __vxge_hw_virtualpath *vpath, struct vxge_hw_device_date *fw_date = &hw_info->fw_date; struct vxge_hw_device_version *flash_version = &hw_info->flash_version; struct vxge_hw_device_date *flash_date = &hw_info->flash_date; - u64 data0, data1 = 0, steer_ctrl = 0; + u64 data0 = 0, data1 = 0, steer_ctrl = 0; enum vxge_hw_status status; status = vxge_hw_vpath_fw_api(vpath, diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index aa633381aa47..c6f4bab67a5f 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -2496,6 +2496,7 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, if (unlikely(dma_mapping_error(&cdev->pdev->dev, mapping))) { DP_NOTICE(cdev, "Unable to map frag - dropping packet\n"); + rc = -ENOMEM; goto err; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index 5551fead8f66..c4a35e932f05 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -4250,6 +4250,7 @@ int stmmac_dvr_probe(struct device *device, priv->wq = create_singlethread_workqueue("stmmac_wq"); if (!priv->wq) { dev_err(priv->device, "failed to create workqueue\n"); + ret = -ENOMEM; goto error_wq; } diff --git a/drivers/net/phy/phy_device.c b/drivers/net/phy/phy_device.c index 18e92c19c5ab..26c41ede54a4 100644 --- a/drivers/net/phy/phy_device.c +++ b/drivers/net/phy/phy_device.c @@ -308,11 +308,8 @@ static int mdio_bus_phy_restore(struct device *dev) if (ret < 0) return ret; - /* The PHY needs to renegotiate. */ - phydev->link = 0; - phydev->state = PHY_UP; - - phy_start_machine(phydev); + if (phydev->attached_dev && phydev->adjust_link) + phy_start_machine(phydev); return 0; } diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index be1917be28f2..77d3c85febf1 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -2320,6 +2320,10 @@ static int lan78xx_set_mac_addr(struct net_device *netdev, void *p) ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + /* Added to support MAC address changes */ + ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); + ret = lan78xx_write_reg(dev, MAF_HI(0), addr_hi | MAF_HI_VALID_); + return 0; } diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 297cdeaef479..0565f8880199 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -568,6 +568,7 @@ static int vxlan_fdb_replace(struct vxlan_fdb *f, rd->remote_port = port; rd->remote_vni = vni; rd->remote_ifindex = ifindex; + rd->offloaded = false; return 1; } @@ -3258,6 +3259,7 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, struct vxlan_net *vn = net_generic(net, vxlan_net_id); struct vxlan_dev *vxlan = netdev_priv(dev); struct vxlan_fdb *f = NULL; + bool unregister = false; int err; err = vxlan_dev_configure(net, dev, conf, false, extack); @@ -3283,12 +3285,11 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, err = register_netdevice(dev); if (err) goto errout; + unregister = true; err = rtnl_configure_link(dev, NULL); - if (err) { - unregister_netdevice(dev); + if (err) goto errout; - } /* notify default fdb entry */ if (f) @@ -3296,9 +3297,16 @@ static int __vxlan_dev_create(struct net *net, struct net_device *dev, list_add(&vxlan->next, &vn->vxlan_list); return 0; + errout: + /* unregister_netdevice() destroys the default FDB entry with deletion + * notification. But the addition notification was not sent yet, so + * destroy the entry by hand here. + */ if (f) vxlan_fdb_destroy(vxlan, f, false); + if (unregister) + unregister_netdevice(dev); return err; } @@ -3534,7 +3542,6 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], struct vxlan_rdst *dst = &vxlan->default_dst; struct vxlan_rdst old_dst; struct vxlan_config conf; - struct vxlan_fdb *f = NULL; int err; err = vxlan_nl2conf(tb, data, @@ -3560,19 +3567,19 @@ static int vxlan_changelink(struct net_device *dev, struct nlattr *tb[], old_dst.remote_ifindex, 0); if (!vxlan_addr_any(&dst->remote_ip)) { - err = vxlan_fdb_create(vxlan, all_zeros_mac, + err = vxlan_fdb_update(vxlan, all_zeros_mac, &dst->remote_ip, NUD_REACHABLE | NUD_PERMANENT, + NLM_F_APPEND | NLM_F_CREATE, vxlan->cfg.dst_port, dst->remote_vni, dst->remote_vni, dst->remote_ifindex, - NTF_SELF, &f); + NTF_SELF); if (err) { spin_unlock_bh(&vxlan->hash_lock); return err; } - vxlan_fdb_notify(vxlan, f, first_remote_rtnl(f), RTM_NEWNEIGH); } spin_unlock_bh(&vxlan->hash_lock); } diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index f17f602e6171..5b97cc946d70 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -905,7 +905,7 @@ static RING_IDX xennet_fill_frags(struct netfront_queue *queue, if (skb_shinfo(skb)->nr_frags == MAX_SKB_FRAGS) { unsigned int pull_to = NETFRONT_SKB_CB(skb)->pull_to; - BUG_ON(pull_to <= skb_headlen(skb)); + BUG_ON(pull_to < skb_headlen(skb)); __pskb_pull_tail(skb, pull_to - skb_headlen(skb)); } if (unlikely(skb_shinfo(skb)->nr_frags >= MAX_SKB_FRAGS)) { diff --git a/include/net/sock.h b/include/net/sock.h index f665d74ae509..0e3a09380655 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -2340,22 +2340,39 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk, void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags); /** - * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped + * _sock_tx_timestamp - checks whether the outgoing packet is to be time stamped * @sk: socket sending this packet * @tsflags: timestamping flags to use * @tx_flags: completed with instructions for time stamping + * @tskey: filled in with next sk_tskey (not for TCP, which uses seqno) * * Note: callers should take care of initial ``*tx_flags`` value (usually 0) */ -static inline void sock_tx_timestamp(const struct sock *sk, __u16 tsflags, - __u8 *tx_flags) +static inline void _sock_tx_timestamp(struct sock *sk, __u16 tsflags, + __u8 *tx_flags, __u32 *tskey) { - if (unlikely(tsflags)) + if (unlikely(tsflags)) { __sock_tx_timestamp(tsflags, tx_flags); + if (tsflags & SOF_TIMESTAMPING_OPT_ID && tskey && + tsflags & SOF_TIMESTAMPING_TX_RECORD_MASK) + *tskey = sk->sk_tskey++; + } if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS))) *tx_flags |= SKBTX_WIFI_STATUS; } +static inline void sock_tx_timestamp(struct sock *sk, __u16 tsflags, + __u8 *tx_flags) +{ + _sock_tx_timestamp(sk, tsflags, tx_flags, NULL); +} + +static inline void skb_setup_tx_timestamp(struct sk_buff *skb, __u16 tsflags) +{ + _sock_tx_timestamp(skb->sk, tsflags, &skb_shinfo(skb)->tx_flags, + &skb_shinfo(skb)->tskey); +} + /** * sk_eat_skb - Release a skb if it is no longer needed * @sk: socket to eat this skb from diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 0eb390c205af..da588def3c61 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -1552,6 +1552,7 @@ int xfrm_state_walk(struct net *net, struct xfrm_state_walk *walk, int (*func)(struct xfrm_state *, int, void*), void *); void xfrm_state_walk_done(struct xfrm_state_walk *walk, struct net *net); struct xfrm_state *xfrm_state_alloc(struct net *net); +void xfrm_state_free(struct xfrm_state *x); struct xfrm_state *xfrm_state_find(const xfrm_address_t *daddr, const xfrm_address_t *saddr, const struct flowi *fl, diff --git a/include/uapi/linux/net_tstamp.h b/include/uapi/linux/net_tstamp.h index 97ff3c17ec4d..e5b39721c6e4 100644 --- a/include/uapi/linux/net_tstamp.h +++ b/include/uapi/linux/net_tstamp.h @@ -155,8 +155,8 @@ enum txtime_flags { }; struct sock_txtime { - clockid_t clockid; /* reference clockid */ - __u32 flags; /* as defined by enum txtime_flags */ + __kernel_clockid_t clockid;/* reference clockid */ + __u32 flags; /* as defined by enum txtime_flags */ }; #endif /* _NET_TIMESTAMPING_H */ diff --git a/net/can/raw.c b/net/can/raw.c index 3aab7664933f..c70207537488 100644 --- a/net/can/raw.c +++ b/net/can/raw.c @@ -771,7 +771,7 @@ static int raw_sendmsg(struct socket *sock, struct msghdr *msg, size_t size) if (err < 0) goto free_skb; - sock_tx_timestamp(sk, sk->sk_tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sk->sk_tsflags); skb->dev = dev; skb->sk = sk; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 8ca3eb06ba04..169a652b3dd1 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -391,7 +391,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, skb->ip_summed = CHECKSUM_NONE; - sock_tx_timestamp(sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 5e0efd3954e9..fc2b5e845fdf 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -658,6 +658,8 @@ static int rawv6_send_hdrinc(struct sock *sk, struct msghdr *msg, int length, skb->ip_summed = CHECKSUM_NONE; + skb_setup_tx_timestamp(skb, sockc->tsflags); + if (flags & MSG_CONFIRM) skb_set_dst_pending_confirm(skb, 1); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index a74650e98f42..6655793765b2 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1965,7 +1965,7 @@ retry: skb->mark = sk->sk_mark; skb->tstamp = sockc.transmit_time; - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (unlikely(extra_len == 4)) skb->no_fcs = 1; @@ -2460,7 +2460,7 @@ static int tpacket_fill_skb(struct packet_sock *po, struct sk_buff *skb, skb->priority = po->sk.sk_priority; skb->mark = po->sk.sk_mark; skb->tstamp = sockc->transmit_time; - sock_tx_timestamp(&po->sk, sockc->tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc->tsflags); skb_zcopy_set_nouarg(skb, ph.raw); skb_reserve(skb, hlen); @@ -2898,7 +2898,7 @@ static int packet_snd(struct socket *sock, struct msghdr *msg, size_t len) goto out_free; } - sock_tx_timestamp(sk, sockc.tsflags, &skb_shinfo(skb)->tx_flags); + skb_setup_tx_timestamp(skb, sockc.tsflags); if (!vnet_hdr.gso_type && (len > dev->mtu + reserve + extra_len) && !packet_extra_vlan_len_allowed(dev, skb)) { diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 5fbaf1901571..82cb0e5634bc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -147,8 +147,14 @@ static int smc_release(struct socket *sock) sk->sk_shutdown |= SHUTDOWN_MASK; } if (smc->clcsock) { + if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + /* wake up clcsock accept */ + rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); + } + mutex_lock(&smc->clcsock_release_lock); sock_release(smc->clcsock); smc->clcsock = NULL; + mutex_unlock(&smc->clcsock_release_lock); } if (smc->use_fallback) { if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) @@ -205,6 +211,7 @@ static struct sock *smc_sock_alloc(struct net *net, struct socket *sock, spin_lock_init(&smc->conn.send_lock); sk->sk_prot->hash(sk); sk_refcnt_debug_inc(sk); + mutex_init(&smc->clcsock_release_lock); return sk; } @@ -821,7 +828,7 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) struct socket *new_clcsock = NULL; struct sock *lsk = &lsmc->sk; struct sock *new_sk; - int rc; + int rc = -EINVAL; release_sock(lsk); new_sk = smc_sock_alloc(sock_net(lsk), NULL, lsk->sk_protocol); @@ -834,7 +841,10 @@ static int smc_clcsock_accept(struct smc_sock *lsmc, struct smc_sock **new_smc) } *new_smc = smc_sk(new_sk); - rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_lock(&lsmc->clcsock_release_lock); + if (lsmc->clcsock) + rc = kernel_accept(lsmc->clcsock, &new_clcsock, 0); + mutex_unlock(&lsmc->clcsock_release_lock); lock_sock(lsk); if (rc < 0) lsk->sk_err = -rc; diff --git a/net/smc/smc.h b/net/smc/smc.h index 08786ace6010..5721416d0605 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -219,6 +219,10 @@ struct smc_sock { /* smc sock container */ * started, waiting for unsent * data to be sent */ + struct mutex clcsock_release_lock; + /* protects clcsock of a listen + * socket + * */ }; static inline struct smc_sock *smc_sk(const struct sock *sk) diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 656940692a44..8f34db2a9785 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -1009,7 +1009,7 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sock *sk = sock->sk; struct net *net = sock_net(sk); struct tipc_sock *tsk = tipc_sk(sk); - struct tipc_nlist *dsts = tipc_group_dests(tsk->group); + struct tipc_nlist *dsts; struct tipc_mc_method *method = &tsk->mc_method; bool ack = method->mandatory && method->rcast; int blks = tsk_blocks(MCAST_H_SIZE + dlen); @@ -1018,9 +1018,6 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, struct sk_buff_head pkts; int rc = -EHOSTUNREACH; - if (!dsts->local && !dsts->remote) - return -EHOSTUNREACH; - /* Block or return if any destination link or member is congested */ rc = tipc_wait_for_cond(sock, &timeout, !tsk->cong_link_cnt && tsk->group && @@ -1028,6 +1025,10 @@ static int tipc_send_group_bcast(struct socket *sock, struct msghdr *m, if (unlikely(rc)) return rc; + dsts = tipc_group_dests(tsk->group); + if (!dsts->local && !dsts->remote) + return -EHOSTUNREACH; + /* Complete message header */ if (dest) { msg_set_type(hdr, TIPC_GRP_MCAST_MSG); diff --git a/net/vmw_vsock/vmci_transport.c b/net/vmw_vsock/vmci_transport.c index cb332adb84cd..c361ce782412 100644 --- a/net/vmw_vsock/vmci_transport.c +++ b/net/vmw_vsock/vmci_transport.c @@ -264,6 +264,31 @@ vmci_transport_send_control_pkt_bh(struct sockaddr_vm *src, } static int +vmci_transport_alloc_send_control_pkt(struct sockaddr_vm *src, + struct sockaddr_vm *dst, + enum vmci_transport_packet_type type, + u64 size, + u64 mode, + struct vmci_transport_waiting_info *wait, + u16 proto, + struct vmci_handle handle) +{ + struct vmci_transport_packet *pkt; + int err; + + pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); + if (!pkt) + return -ENOMEM; + + err = __vmci_transport_send_control_pkt(pkt, src, dst, type, size, + mode, wait, proto, handle, + true); + kfree(pkt); + + return err; +} + +static int vmci_transport_send_control_pkt(struct sock *sk, enum vmci_transport_packet_type type, u64 size, @@ -272,9 +297,7 @@ vmci_transport_send_control_pkt(struct sock *sk, u16 proto, struct vmci_handle handle) { - struct vmci_transport_packet *pkt; struct vsock_sock *vsk; - int err; vsk = vsock_sk(sk); @@ -284,17 +307,10 @@ vmci_transport_send_control_pkt(struct sock *sk, if (!vsock_addr_bound(&vsk->remote_addr)) return -EINVAL; - pkt = kmalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) - return -ENOMEM; - - err = __vmci_transport_send_control_pkt(pkt, &vsk->local_addr, - &vsk->remote_addr, type, size, - mode, wait, proto, handle, - true); - kfree(pkt); - - return err; + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, + &vsk->remote_addr, + type, size, mode, + wait, proto, handle); } static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, @@ -312,12 +328,29 @@ static int vmci_transport_send_reset_bh(struct sockaddr_vm *dst, static int vmci_transport_send_reset(struct sock *sk, struct vmci_transport_packet *pkt) { + struct sockaddr_vm *dst_ptr; + struct sockaddr_vm dst; + struct vsock_sock *vsk; + if (pkt->type == VMCI_TRANSPORT_PACKET_TYPE_RST) return 0; - return vmci_transport_send_control_pkt(sk, - VMCI_TRANSPORT_PACKET_TYPE_RST, - 0, 0, NULL, VSOCK_PROTO_INVALID, - VMCI_INVALID_HANDLE); + + vsk = vsock_sk(sk); + + if (!vsock_addr_bound(&vsk->local_addr)) + return -EINVAL; + + if (vsock_addr_bound(&vsk->remote_addr)) { + dst_ptr = &vsk->remote_addr; + } else { + vsock_addr_init(&dst, pkt->dg.src.context, + pkt->src_port); + dst_ptr = &dst; + } + return vmci_transport_alloc_send_control_pkt(&vsk->local_addr, dst_ptr, + VMCI_TRANSPORT_PACKET_TYPE_RST, + 0, 0, NULL, VSOCK_PROTO_INVALID, + VMCI_INVALID_HANDLE); } static int vmci_transport_send_negotiate(struct sock *sk, size_t size) diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 684c0bc01e2c..d5635908587f 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -346,6 +346,12 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) skb->sp->xvec[skb->sp->len++] = x; + skb_dst_force(skb); + if (!skb_dst(skb)) { + XFRM_INC_STATS(net, LINUX_MIB_XFRMINERROR); + goto drop; + } + lock: spin_lock(&x->lock); @@ -385,7 +391,6 @@ lock: XFRM_SKB_CB(skb)->seq.input.low = seq; XFRM_SKB_CB(skb)->seq.input.hi = seq_hi; - skb_dst_force(skb); dev_hold(skb->dev); if (crypto_done) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 4ae87c5ce2e3..fef6b2da3c5d 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -102,6 +102,7 @@ static int xfrm_output_one(struct sk_buff *skb, int err) skb_dst_force(skb); if (!skb_dst(skb)) { XFRM_INC_STATS(net, LINUX_MIB_XFRMOUTERROR); + err = -EHOSTUNREACH; goto error_nolock; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index dc4a9f1fb941..23c92891758a 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -426,6 +426,12 @@ static void xfrm_put_mode(struct xfrm_mode *mode) module_put(mode->owner); } +void xfrm_state_free(struct xfrm_state *x) +{ + kmem_cache_free(xfrm_state_cache, x); +} +EXPORT_SYMBOL(xfrm_state_free); + static void xfrm_state_gc_destroy(struct xfrm_state *x) { tasklet_hrtimer_cancel(&x->mtimer); @@ -452,7 +458,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) } xfrm_dev_state_free(x); security_xfrm_state_free(x); - kmem_cache_free(xfrm_state_cache, x); + xfrm_state_free(x); } static void xfrm_state_gc_task(struct work_struct *work) @@ -788,7 +794,7 @@ void xfrm_sad_getinfo(struct net *net, struct xfrmk_sadinfo *si) { spin_lock_bh(&net->xfrm.xfrm_state_lock); si->sadcnt = net->xfrm.state_num; - si->sadhcnt = net->xfrm.state_hmask; + si->sadhcnt = net->xfrm.state_hmask + 1; si->sadhmcnt = xfrm_state_hashmax; spin_unlock_bh(&net->xfrm.xfrm_state_lock); } diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index c9a84e22f5d5..277c1c46fe94 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -2288,13 +2288,13 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, } - kfree(x); + xfrm_state_free(x); kfree(xp); return 0; free_state: - kfree(x); + xfrm_state_free(x); nomem: return err; } diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 256d82d5fa87..923570a9708a 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -7,6 +7,7 @@ CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh ip_defrag.sh TEST_PROGS += udpgso_bench.sh fib_rule_tests.sh msg_zerocopy.sh psock_snd.sh +TEST_PROGS += test_vxlan_fdb_changelink.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy diff --git a/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh new file mode 100755 index 000000000000..2d442cdab11e --- /dev/null +++ b/tools/testing/selftests/net/test_vxlan_fdb_changelink.sh @@ -0,0 +1,29 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# Check FDB default-remote handling across "ip link set". + +check_remotes() +{ + local what=$1; shift + local N=$(bridge fdb sh dev vx | grep 00:00:00:00:00:00 | wc -l) + + echo -ne "expected two remotes after $what\t" + if [[ $N != 2 ]]; then + echo "[FAIL]" + EXIT_STATUS=1 + else + echo "[ OK ]" + fi +} + +ip link add name vx up type vxlan id 2000 dstport 4789 +bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.20 self permanent +bridge fdb ap dev vx 00:00:00:00:00:00 dst 192.0.2.30 self permanent +check_remotes "fdb append" + +ip link set dev vx type vxlan remote 192.0.2.30 +check_remotes "link set" + +ip link del dev vx +exit $EXIT_STATUS |