diff options
51 files changed, 308 insertions, 105 deletions
diff --git a/Documentation/devicetree/bindings/net/cdns-emac.txt b/Documentation/devicetree/bindings/net/cdns-emac.txt index abd67c1..4451ee97 100644 --- a/Documentation/devicetree/bindings/net/cdns-emac.txt +++ b/Documentation/devicetree/bindings/net/cdns-emac.txt @@ -3,7 +3,8 @@ Required properties: - compatible: Should be "cdns,[<chip>-]{emac}" Use "cdns,at91rm9200-emac" Atmel at91rm9200 SoC. - or the generic form: "cdns,emac". + Use "cdns,zynq-gem" Xilinx Zynq-7xxx SoC. + Or the generic form: "cdns,emac". - reg: Address and length of the register set for the device - interrupts: Should contain macb interrupt - phy-mode: see ethernet.txt file in the same directory. diff --git a/arch/arm/boot/dts/zynq-7000.dtsi b/arch/arm/boot/dts/zynq-7000.dtsi index a5cd2ed..9ea54b3 100644 --- a/arch/arm/boot/dts/zynq-7000.dtsi +++ b/arch/arm/boot/dts/zynq-7000.dtsi @@ -193,7 +193,7 @@ }; gem0: ethernet@e000b000 { - compatible = "cdns,gem"; + compatible = "cdns,zynq-gem"; reg = <0xe000b000 0x1000>; status = "disabled"; interrupts = <0 22 4>; @@ -204,7 +204,7 @@ }; gem1: ethernet@e000c000 { - compatible = "cdns,gem"; + compatible = "cdns,zynq-gem"; reg = <0xe000c000 0x1000>; status = "disabled"; interrupts = <0 45 4>; diff --git a/drivers/bluetooth/ath3k.c b/drivers/bluetooth/ath3k.c index 288547a..8c81af6 100644 --- a/drivers/bluetooth/ath3k.c +++ b/drivers/bluetooth/ath3k.c @@ -88,6 +88,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x04CA, 0x3007) }, { USB_DEVICE(0x04CA, 0x3008) }, { USB_DEVICE(0x04CA, 0x300b) }, + { USB_DEVICE(0x04CA, 0x300f) }, { USB_DEVICE(0x04CA, 0x3010) }, { USB_DEVICE(0x0930, 0x0219) }, { USB_DEVICE(0x0930, 0x0220) }, @@ -104,6 +105,7 @@ static const struct usb_device_id ath3k_table[] = { { USB_DEVICE(0x0cf3, 0xe003) }, { USB_DEVICE(0x0CF3, 0xE004) }, { USB_DEVICE(0x0CF3, 0xE005) }, + { USB_DEVICE(0x0CF3, 0xE006) }, { USB_DEVICE(0x13d3, 0x3362) }, { USB_DEVICE(0x13d3, 0x3375) }, { USB_DEVICE(0x13d3, 0x3393) }, @@ -143,6 +145,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, @@ -158,6 +161,7 @@ static const struct usb_device_id ath3k_blist_tbl[] = { { USB_DEVICE(0x0CF3, 0x817a), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0xe006), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, diff --git a/drivers/bluetooth/btusb.c b/drivers/bluetooth/btusb.c index d21f3b4..3c10d4d 100644 --- a/drivers/bluetooth/btusb.c +++ b/drivers/bluetooth/btusb.c @@ -186,6 +186,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x04ca, 0x3007), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3008), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x300b), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x04ca, 0x300f), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x04ca, 0x3010), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0219), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0930, 0x0220), .driver_info = BTUSB_ATH3012 }, @@ -202,6 +203,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0cf3, 0xe003), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe004), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x0cf3, 0xe005), .driver_info = BTUSB_ATH3012 }, + { USB_DEVICE(0x0cf3, 0xe006), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3362), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3375), .driver_info = BTUSB_ATH3012 }, { USB_DEVICE(0x13d3, 0x3393), .driver_info = BTUSB_ATH3012 }, @@ -218,6 +220,7 @@ static const struct usb_device_id blacklist_table[] = { { USB_DEVICE(0x0489, 0xe03c), .driver_info = BTUSB_ATH3012 }, /* QCA ROME chipset */ + { USB_DEVICE(0x0cf3, 0xe007), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe300), .driver_info = BTUSB_QCA_ROME }, { USB_DEVICE(0x0cf3, 0xe360), .driver_info = BTUSB_QCA_ROME }, diff --git a/drivers/net/bonding/bond_options.c b/drivers/net/bonding/bond_options.c index 4df2894..e8d3c1d 100644 --- a/drivers/net/bonding/bond_options.c +++ b/drivers/net/bonding/bond_options.c @@ -624,7 +624,7 @@ int __bond_opt_set(struct bonding *bond, out: if (ret) bond_opt_error_interpret(bond, opt, ret, val); - else + else if (bond->dev->reg_state == NETREG_REGISTERED) call_netdevice_notifiers(NETDEV_CHANGEINFODATA, bond->dev); return ret; diff --git a/drivers/net/ethernet/cadence/macb.c b/drivers/net/ethernet/cadence/macb.c index 61aa570..fc646a4 100644 --- a/drivers/net/ethernet/cadence/macb.c +++ b/drivers/net/ethernet/cadence/macb.c @@ -350,6 +350,9 @@ static int macb_mii_probe(struct net_device *dev) else phydev->supported &= PHY_BASIC_FEATURES; + if (bp->caps & MACB_CAPS_NO_GIGABIT_HALF) + phydev->supported &= ~SUPPORTED_1000baseT_Half; + phydev->advertising = phydev->supported; bp->link = 0; @@ -1037,6 +1040,12 @@ static irqreturn_t macb_interrupt(int irq, void *dev_id) * add that if/when we get our hands on a full-blown MII PHY. */ + /* There is a hardware issue under heavy load where DMA can + * stop, this causes endless "used buffer descriptor read" + * interrupts but it can be cleared by re-enabling RX. See + * the at91 manual, section 41.3.1 or the Zynq manual + * section 16.7.4 for details. + */ if (status & MACB_BIT(RXUBR)) { ctrl = macb_readl(bp, NCR); macb_writel(bp, NCR, ctrl & ~MACB_BIT(RE)); @@ -2693,6 +2702,14 @@ static const struct macb_config emac_config = { .init = at91ether_init, }; +static const struct macb_config zynq_config = { + .caps = MACB_CAPS_SG_DISABLED | MACB_CAPS_GIGABIT_MODE_AVAILABLE | + MACB_CAPS_NO_GIGABIT_HALF, + .dma_burst_length = 16, + .clk_init = macb_clk_init, + .init = macb_init, +}; + static const struct of_device_id macb_dt_ids[] = { { .compatible = "cdns,at32ap7000-macb" }, { .compatible = "cdns,at91sam9260-macb", .data = &at91sam9260_config }, @@ -2703,6 +2720,7 @@ static const struct of_device_id macb_dt_ids[] = { { .compatible = "atmel,sama5d4-gem", .data = &sama5d4_config }, { .compatible = "cdns,at91rm9200-emac", .data = &emac_config }, { .compatible = "cdns,emac", .data = &emac_config }, + { .compatible = "cdns,zynq-gem", .data = &zynq_config }, { /* sentinel */ } }; MODULE_DEVICE_TABLE(of, macb_dt_ids); diff --git a/drivers/net/ethernet/cadence/macb.h b/drivers/net/ethernet/cadence/macb.h index eb7d76f..24b1d9b 100644 --- a/drivers/net/ethernet/cadence/macb.h +++ b/drivers/net/ethernet/cadence/macb.h @@ -393,6 +393,7 @@ #define MACB_CAPS_ISR_CLEAR_ON_WRITE 0x00000001 #define MACB_CAPS_USRIO_HAS_CLKEN 0x00000002 #define MACB_CAPS_USRIO_DEFAULT_IS_MII 0x00000004 +#define MACB_CAPS_NO_GIGABIT_HALF 0x00000008 #define MACB_CAPS_FIFO_MODE 0x10000000 #define MACB_CAPS_GIGABIT_MODE_AVAILABLE 0x20000000 #define MACB_CAPS_SG_DISABLED 0x40000000 diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c index 92fce1b..bafe218 100644 --- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c +++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c @@ -3187,7 +3187,7 @@ int mlx4_SW2HW_CQ_wrapper(struct mlx4_dev *dev, int slave, int cqn = vhcr->in_modifier; struct mlx4_cq_context *cqc = inbox->buf; int mtt_base = cq_get_mtt_addr(cqc) / dev->caps.mtt_entry_sz; - struct res_cq *cq; + struct res_cq *cq = NULL; struct res_mtt *mtt; err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_HW, &cq); @@ -3223,7 +3223,7 @@ int mlx4_HW2SW_CQ_wrapper(struct mlx4_dev *dev, int slave, { int err; int cqn = vhcr->in_modifier; - struct res_cq *cq; + struct res_cq *cq = NULL; err = cq_res_start_move_to(dev, slave, cqn, RES_CQ_ALLOCATED, &cq); if (err) @@ -3362,7 +3362,7 @@ int mlx4_SW2HW_SRQ_wrapper(struct mlx4_dev *dev, int slave, int err; int srqn = vhcr->in_modifier; struct res_mtt *mtt; - struct res_srq *srq; + struct res_srq *srq = NULL; struct mlx4_srq_context *srqc = inbox->buf; int mtt_base = srq_get_mtt_addr(srqc) / dev->caps.mtt_entry_sz; @@ -3406,7 +3406,7 @@ int mlx4_HW2SW_SRQ_wrapper(struct mlx4_dev *dev, int slave, { int err; int srqn = vhcr->in_modifier; - struct res_srq *srq; + struct res_srq *srq = NULL; err = srq_res_start_move_to(dev, slave, srqn, RES_SRQ_ALLOCATED, &srq); if (err) diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index ec25153..cf98cc9 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -2921,10 +2921,11 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, struct neighbour *n = __ipv4_neigh_lookup(dev, (__force u32)ip_addr); int err = 0; - if (!n) + if (!n) { n = neigh_create(&arp_tbl, &ip_addr, dev); - if (!n) - return -ENOMEM; + if (IS_ERR(n)) + return IS_ERR(n); + } /* If the neigh is already resolved, then go ahead and * install the entry, otherwise start the ARP process to @@ -2936,6 +2937,7 @@ static int rocker_port_ipv4_resolve(struct rocker_port *rocker_port, else neigh_event_send(n, NULL); + neigh_release(n); return err; } diff --git a/drivers/net/phy/phy.c b/drivers/net/phy/phy.c index 52cd8db..47cd578 100644 --- a/drivers/net/phy/phy.c +++ b/drivers/net/phy/phy.c @@ -742,6 +742,9 @@ EXPORT_SYMBOL(phy_stop); */ void phy_start(struct phy_device *phydev) { + bool do_resume = false; + int err = 0; + mutex_lock(&phydev->lock); switch (phydev->state) { @@ -752,11 +755,22 @@ void phy_start(struct phy_device *phydev) phydev->state = PHY_UP; break; case PHY_HALTED: + /* make sure interrupts are re-enabled for the PHY */ + err = phy_enable_interrupts(phydev); + if (err < 0) + break; + phydev->state = PHY_RESUMING; + do_resume = true; + break; default: break; } mutex_unlock(&phydev->lock); + + /* if phy was suspended, bring the physical link up again */ + if (do_resume) + phy_resume(phydev); } EXPORT_SYMBOL(phy_start); @@ -769,7 +783,7 @@ void phy_state_machine(struct work_struct *work) struct delayed_work *dwork = to_delayed_work(work); struct phy_device *phydev = container_of(dwork, struct phy_device, state_queue); - bool needs_aneg = false, do_suspend = false, do_resume = false; + bool needs_aneg = false, do_suspend = false; int err = 0; mutex_lock(&phydev->lock); @@ -888,14 +902,6 @@ void phy_state_machine(struct work_struct *work) } break; case PHY_RESUMING: - err = phy_clear_interrupt(phydev); - if (err) - break; - - err = phy_config_interrupt(phydev, PHY_INTERRUPT_ENABLED); - if (err) - break; - if (AUTONEG_ENABLE == phydev->autoneg) { err = phy_aneg_done(phydev); if (err < 0) @@ -933,7 +939,6 @@ void phy_state_machine(struct work_struct *work) } phydev->adjust_link(phydev->attached_dev); } - do_resume = true; break; } @@ -943,8 +948,6 @@ void phy_state_machine(struct work_struct *work) err = phy_start_aneg(phydev); else if (do_suspend) phy_suspend(phydev); - else if (do_resume) - phy_resume(phydev); if (err < 0) phy_error(phydev); @@ -1053,13 +1056,14 @@ int phy_init_eee(struct phy_device *phydev, bool clk_stop_enable) { /* According to 802.3az,the EEE is supported only in full duplex-mode. * Also EEE feature is active when core is operating with MII, GMII - * or RGMII. Internal PHYs are also allowed to proceed and should - * return an error if they do not support EEE. + * or RGMII (all kinds). Internal PHYs are also allowed to proceed and + * should return an error if they do not support EEE. */ if ((phydev->duplex == DUPLEX_FULL) && ((phydev->interface == PHY_INTERFACE_MODE_MII) || (phydev->interface == PHY_INTERFACE_MODE_GMII) || - (phydev->interface == PHY_INTERFACE_MODE_RGMII) || + (phydev->interface >= PHY_INTERFACE_MODE_RGMII && + phydev->interface <= PHY_INTERFACE_MODE_RGMII_TXID) || phy_is_internal(phydev))) { int eee_lp, eee_cap, eee_adv; u32 lp, cap, adv; diff --git a/drivers/net/usb/cdc_ncm.c b/drivers/net/usb/cdc_ncm.c index c3e4da9..8067b8f 100644 --- a/drivers/net/usb/cdc_ncm.c +++ b/drivers/net/usb/cdc_ncm.c @@ -1182,7 +1182,7 @@ cdc_ncm_fill_tx_frame(struct usbnet *dev, struct sk_buff *skb, __le32 sign) * payload data instead. */ usbnet_set_skb_tx_stats(skb_out, n, - ctx->tx_curr_frame_payload - skb_out->len); + (long)ctx->tx_curr_frame_payload - skb_out->len); return skb_out; diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index 27a5f95..21a0fbf 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2961,7 +2961,7 @@ static void __net_exit vxlan_exit_net(struct net *net) * to the list by the previous loop. */ if (!net_eq(dev_net(vxlan->dev), net)) - unregister_netdevice_queue(dev, &list); + unregister_netdevice_queue(vxlan->dev, &list); } unregister_netdevice_many(&list); diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index dbcbcc5..843ceca 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -17,6 +17,7 @@ #ifndef _LINUX_RHASHTABLE_H #define _LINUX_RHASHTABLE_H +#include <linux/atomic.h> #include <linux/compiler.h> #include <linux/errno.h> #include <linux/jhash.h> @@ -100,6 +101,7 @@ struct rhashtable; * @key_len: Length of key * @key_offset: Offset of key in struct to be hashed * @head_offset: Offset of rhash_head in struct to be hashed + * @insecure_max_entries: Maximum number of entries (may be exceeded) * @max_size: Maximum size while expanding * @min_size: Minimum size while shrinking * @nulls_base: Base value to generate nulls marker @@ -115,6 +117,7 @@ struct rhashtable_params { size_t key_len; size_t key_offset; size_t head_offset; + unsigned int insecure_max_entries; unsigned int max_size; unsigned int min_size; u32 nulls_base; @@ -286,6 +289,18 @@ static inline bool rht_grow_above_100(const struct rhashtable *ht, (!ht->p.max_size || tbl->size < ht->p.max_size); } +/** + * rht_grow_above_max - returns true if table is above maximum + * @ht: hash table + * @tbl: current table + */ +static inline bool rht_grow_above_max(const struct rhashtable *ht, + const struct bucket_table *tbl) +{ + return ht->p.insecure_max_entries && + atomic_read(&ht->nelems) >= ht->p.insecure_max_entries; +} + /* The bucket lock is selected based on the hash and protects mutations * on a group of hash buckets. * @@ -589,6 +604,10 @@ restart: goto out; } + err = -E2BIG; + if (unlikely(rht_grow_above_max(ht, tbl))) + goto out; + if (unlikely(rht_grow_above_100(ht, tbl))) { slow_path: spin_unlock_bh(lock); diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 66e374d..f15154a 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -176,6 +176,7 @@ struct nf_bridge_info { struct net_device *physindev; struct net_device *physoutdev; char neigh_header[8]; + __be32 ipv4_daddr; }; #endif diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 3b29115..e8bbf40 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -158,6 +158,8 @@ struct tcp_sock { * sum(delta(snd_una)), or how many bytes * were acked. */ + struct u64_stats_sync syncp; /* protects 64bit vars (cf tcp_get_info()) */ + u32 snd_una; /* First byte we want an ack for */ u32 snd_sml; /* Last byte of the most recently transmitted small packet */ u32 rcv_tstamp; /* timestamp of last received ACK (for keepalives) */ diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index 48a81582..497bc14 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -129,9 +129,10 @@ struct inet_connection_sock { u32 probe_timestamp; } icsk_mtup; - u32 icsk_ca_priv[16]; u32 icsk_user_timeout; -#define ICSK_CA_PRIV_SIZE (16 * sizeof(u32)) + + u64 icsk_ca_priv[64 / sizeof(u64)]; +#define ICSK_CA_PRIV_SIZE (8 * sizeof(u64)) }; #define ICSK_TIME_RETRANS 1 /* Retransmit timer */ diff --git a/include/uapi/linux/netfilter/nf_conntrack_tcp.h b/include/uapi/linux/netfilter/nf_conntrack_tcp.h index 9993a42..ef9f80f 100644 --- a/include/uapi/linux/netfilter/nf_conntrack_tcp.h +++ b/include/uapi/linux/netfilter/nf_conntrack_tcp.h @@ -42,6 +42,9 @@ enum tcp_conntrack { /* The field td_maxack has been set */ #define IP_CT_TCP_FLAG_MAXACK_SET 0x20 +/* Marks possibility for expected RFC5961 challenge ACK */ +#define IP_CT_EXP_CHALLENGE_ACK 0x40 + struct nf_ct_tcp_flags { __u8 flags; __u8 mask; diff --git a/include/uapi/linux/rtnetlink.h b/include/uapi/linux/rtnetlink.h index 974db03..17fb02f 100644 --- a/include/uapi/linux/rtnetlink.h +++ b/include/uapi/linux/rtnetlink.h @@ -337,7 +337,7 @@ struct rtnexthop { #define RTNH_F_DEAD 1 /* Nexthop is dead (used by multipath) */ #define RTNH_F_PERVASIVE 2 /* Do recursive gateway lookup */ #define RTNH_F_ONLINK 4 /* Gateway is forced on link */ -#define RTNH_F_EXTERNAL 8 /* Route installed externally */ +#define RTNH_F_OFFLOAD 8 /* offloaded route */ /* Macros to handle hexthops */ diff --git a/lib/rhashtable.c b/lib/rhashtable.c index b28df40..4396434 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -14,6 +14,7 @@ * published by the Free Software Foundation. */ +#include <linux/atomic.h> #include <linux/kernel.h> #include <linux/init.h> #include <linux/log2.h> @@ -446,6 +447,10 @@ int rhashtable_insert_slow(struct rhashtable *ht, const void *key, if (key && rhashtable_lookup_fast(ht, key, ht->p)) goto exit; + err = -E2BIG; + if (unlikely(rht_grow_above_max(ht, tbl))) + goto exit; + err = -EAGAIN; if (rhashtable_check_elasticity(ht, tbl, hash) || rht_grow_above_100(ht, tbl)) @@ -738,6 +743,12 @@ int rhashtable_init(struct rhashtable *ht, if (params->max_size) ht->p.max_size = rounddown_pow_of_two(params->max_size); + if (params->insecure_max_entries) + ht->p.insecure_max_entries = + rounddown_pow_of_two(params->insecure_max_entries); + else + ht->p.insecure_max_entries = ht->p.max_size * 2; + ht->p.min_size = max(ht->p.min_size, HASH_MIN_SIZE); /* The maximum (not average) chain length grows with the diff --git a/net/8021q/vlan.c b/net/8021q/vlan.c index 98a30a5..59555f0 100644 --- a/net/8021q/vlan.c +++ b/net/8021q/vlan.c @@ -443,7 +443,7 @@ static int vlan_device_event(struct notifier_block *unused, unsigned long event, case NETDEV_UP: /* Put all VLANs for this dev in the up state too. */ vlan_group_for_each_dev(grp, i, vlandev) { - flgs = vlandev->flags; + flgs = dev_get_flags(vlandev); if (flgs & IFF_UP) continue; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 4663c3d..c4802f3 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2854,9 +2854,11 @@ static void le_scan_disable_work_complete(struct hci_dev *hdev, u8 status, * state. If we were running both LE and BR/EDR inquiry * simultaneously, and BR/EDR inquiry is already * finished, stop discovery, otherwise BR/EDR inquiry - * will stop discovery when finished. + * will stop discovery when finished. If we will resolve + * remote device name, do not change discovery state. */ - if (!test_bit(HCI_INQUIRY, &hdev->flags)) + if (!test_bit(HCI_INQUIRY, &hdev->flags) && + hdev->discovery.state != DISCOVERY_RESOLVING) hci_discovery_set_state(hdev, DISCOVERY_STOPPED); } else { diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 4b6722f..a3abe6e 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -1072,7 +1072,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, err = br_ip6_multicast_add_group(br, port, &grec->grec_mca, vid); - if (!err) + if (err) break; } diff --git a/net/bridge/br_netfilter.c b/net/bridge/br_netfilter.c index ab55e24..60ddfbe 100644 --- a/net/bridge/br_netfilter.c +++ b/net/bridge/br_netfilter.c @@ -37,10 +37,6 @@ #include <net/route.h> #include <net/netfilter/br_netfilter.h> -#if IS_ENABLED(CONFIG_NF_CONNTRACK) -#include <net/netfilter/nf_conntrack.h> -#endif - #include <asm/uaccess.h> #include "br_private.h" #ifdef CONFIG_SYSCTL @@ -350,24 +346,15 @@ free_skb: return 0; } -static bool dnat_took_place(const struct sk_buff *skb) +static bool daddr_was_changed(const struct sk_buff *skb, + const struct nf_bridge_info *nf_bridge) { -#if IS_ENABLED(CONFIG_NF_CONNTRACK) - enum ip_conntrack_info ctinfo; - struct nf_conn *ct; - - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_untracked(ct)) - return false; - - return test_bit(IPS_DST_NAT_BIT, &ct->status); -#else - return false; -#endif + return ip_hdr(skb)->daddr != nf_bridge->ipv4_daddr; } /* This requires some explaining. If DNAT has taken place, * we will need to fix up the destination Ethernet address. + * This is also true when SNAT takes place (for the reply direction). * * There are two cases to consider: * 1. The packet was DNAT'ed to a device in the same bridge @@ -421,7 +408,7 @@ static int br_nf_pre_routing_finish(struct sock *sk, struct sk_buff *skb) nf_bridge->pkt_otherhost = false; } nf_bridge->mask ^= BRNF_NF_BRIDGE_PREROUTING; - if (dnat_took_place(skb)) { + if (daddr_was_changed(skb, nf_bridge)) { if ((err = ip_route_input(skb, iph->daddr, iph->saddr, iph->tos, dev))) { struct in_device *in_dev = __in_dev_get_rcu(dev); @@ -632,6 +619,7 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, struct sk_buff *skb, const struct nf_hook_state *state) { + struct nf_bridge_info *nf_bridge; struct net_bridge_port *p; struct net_bridge *br; __u32 len = nf_bridge_encap_header_len(skb); @@ -669,6 +657,9 @@ static unsigned int br_nf_pre_routing(const struct nf_hook_ops *ops, if (!setup_pre_routing(skb)) return NF_DROP; + nf_bridge = nf_bridge_info_get(skb); + nf_bridge->ipv4_daddr = ip_hdr(skb)->daddr; + skb->protocol = htons(ETH_P_IP); NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, state->sk, skb, diff --git a/net/bridge/br_stp_timer.c b/net/bridge/br_stp_timer.c index 4fcaa67..7caf7fa 100644 --- a/net/bridge/br_stp_timer.c +++ b/net/bridge/br_stp_timer.c @@ -97,7 +97,9 @@ static void br_forward_delay_timer_expired(unsigned long arg) netif_carrier_on(br->dev); } br_log_state(p); + rcu_read_lock(); br_ifinfo_notify(RTM_NEWLINK, p); + rcu_read_unlock(); spin_unlock(&br->lock); } diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 91180a7..24c7c96 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1117,6 +1117,8 @@ static int do_replace(struct net *net, const void __user *user, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; tmp.name[sizeof(tmp.name) - 1] = 0; @@ -2159,6 +2161,8 @@ static int compat_copy_ebt_replace_from_user(struct ebt_replace *repl, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct ebt_counter)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; memcpy(repl, &tmp, offsetof(struct ebt_replace, hook_entry)); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 1d00b89..1347e11 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -359,7 +359,15 @@ static int ethtool_get_settings(struct net_device *dev, void __user *useraddr) int err; struct ethtool_cmd cmd; - err = __ethtool_get_settings(dev, &cmd); + if (!dev->ethtool_ops->get_settings) + return -EOPNOTSUPP; + + if (copy_from_user(&cmd, useraddr, sizeof(cmd))) + return -EFAULT; + + cmd.cmd = ETHTOOL_GSET; + + err = dev->ethtool_ops->get_settings(dev, &cmd); if (err < 0) return err; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 666e092..8de3682 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2416,6 +2416,9 @@ void rtmsg_ifinfo(int type, struct net_device *dev, unsigned int change, { struct sk_buff *skb; + if (dev->reg_state != NETREG_REGISTERED) + return; + skb = rtmsg_ifinfo_build_skb(type, dev, change, flags); if (skb) rtmsg_ifinfo_send(skb, dev, flags); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index e13fcc6..09b62e1 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1164,6 +1164,7 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) state = fa->fa_state; new_fa->fa_state = state & ~FA_S_ACCESSED; new_fa->fa_slen = fa->fa_slen; + new_fa->tb_id = tb->tb_id; err = netdev_switch_fib_ipv4_add(key, plen, fi, new_fa->fa_tos, @@ -1764,7 +1765,7 @@ void fib_table_flush_external(struct fib_table *tb) /* record local slen */ slen = fa->fa_slen; - if (!fi || !(fi->fib_flags & RTNH_F_EXTERNAL)) + if (!fi || !(fi->fib_flags & RTNH_F_OFFLOAD)) continue; netdev_switch_fib_ipv4_del(n->key, diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 13bfe84..a612007 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -1075,6 +1075,9 @@ static int do_replace(struct net *net, const void __user *user, /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1499,6 +1502,9 @@ static int compat_do_replace(struct net *net, void __user *user, return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index c69db7f..2d0e265 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1262,6 +1262,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1809,6 +1812,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index bff62fc..f45f2a1 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -902,6 +902,10 @@ static int ip_error(struct sk_buff *skb) bool send; int code; + /* IP on this device is disabled. */ + if (!in_dev) + goto out; + net = dev_net(rt->dst.dev); if (!IN_DEV_FORWARD(in_dev)) { switch (rt->dst.error) { diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 46efa03..f1377f2 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -402,6 +402,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; + u64_stats_init(&tp->syncp); tp->reordering = sysctl_tcp_reordering; tcp_enable_early_retrans(tp); @@ -2598,6 +2599,7 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) const struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 now = tcp_time_stamp; + unsigned int start; u32 rate; memset(info, 0, sizeof(*info)); @@ -2665,10 +2667,11 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) rate = READ_ONCE(sk->sk_max_pacing_rate); info->tcpi_max_pacing_rate = rate != ~0U ? rate : ~0ULL; - spin_lock_bh(&sk->sk_lock.slock); - info->tcpi_bytes_acked = tp->bytes_acked; - info->tcpi_bytes_received = tp->bytes_received; - spin_unlock_bh(&sk->sk_lock.slock); + do { + start = u64_stats_fetch_begin_irq(&tp->syncp); + info->tcpi_bytes_acked = tp->bytes_acked; + info->tcpi_bytes_received = tp->bytes_received; + } while (u64_stats_fetch_retry_irq(&tp->syncp, start)); } EXPORT_SYMBOL_GPL(tcp_get_info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index 3c673d5..46b087a 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -206,6 +206,10 @@ static bool tcp_fastopen_create_child(struct sock *sk, skb_set_owner_r(skb2, child); __skb_queue_tail(&child->sk_receive_queue, skb2); tp->syn_data_acked = 1; + + /* u64_stats_update_begin(&tp->syncp) not needed here, + * as we certainly are not changing upper 32bit value (0) + */ tp->bytes_received = end_seq - TCP_SKB_CB(skb)->seq - 1; } else { end_seq = TCP_SKB_CB(skb)->seq + 1; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index bc790ea..c9ab964 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -2698,16 +2698,21 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); + if ((flag & FLAG_SND_UNA_ADVANCED) && + tcp_try_undo_loss(sk, false)) + return; + if (tp->frto) { /* F-RTO RFC5682 sec 3.1 (sack enhanced version). */ /* Step 3.b. A timeout is spurious if not all data are * lost, i.e., never-retransmitted data are (s)acked. */ - if (tcp_try_undo_loss(sk, flag & FLAG_ORIG_SACK_ACKED)) + if ((flag & FLAG_ORIG_SACK_ACKED) && + tcp_try_undo_loss(sk, true)) return; - if (after(tp->snd_nxt, tp->high_seq) && - (flag & FLAG_DATA_SACKED || is_dupack)) { - tp->frto = 0; /* Loss was real: 2nd part of step 3.a */ + if (after(tp->snd_nxt, tp->high_seq)) { + if (flag & FLAG_DATA_SACKED || is_dupack) + tp->frto = 0; /* Step 3.a. loss was real */ } else if (flag & FLAG_SND_UNA_ADVANCED && !recovered) { tp->high_seq = tp->snd_nxt; __tcp_push_pending_frames(sk, tcp_current_mss(sk), @@ -2732,8 +2737,6 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) else if (flag & FLAG_SND_UNA_ADVANCED) tcp_reset_reno_sack(tp); } - if (tcp_try_undo_loss(sk, false)) - return; tcp_xmit_retransmit_queue(sk); } @@ -3283,7 +3286,9 @@ static void tcp_snd_una_update(struct tcp_sock *tp, u32 ack) { u32 delta = ack - tp->snd_una; + u64_stats_update_begin(&tp->syncp); tp->bytes_acked += delta; + u64_stats_update_end(&tp->syncp); tp->snd_una = ack; } @@ -3292,7 +3297,9 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) { u32 delta = seq - tp->rcv_nxt; + u64_stats_update_begin(&tp->syncp); tp->bytes_received += delta; + u64_stats_update_end(&tp->syncp); tp->rcv_nxt = seq; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index e5d7649..b5732a5 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -300,7 +300,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tw->tw_v6_daddr = sk->sk_v6_daddr; tw->tw_v6_rcv_saddr = sk->sk_v6_rcv_saddr; tw->tw_tclass = np->tclass; - tw->tw_flowlabel = np->flow_label >> 12; + tw->tw_flowlabel = be32_to_cpu(np->flow_label & IPV6_FLOWLABEL_MASK); tw->tw_ipv6only = sk->sk_ipv6only; } #endif diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 96dbfff..bde57b1 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -693,6 +693,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, { struct rt6_info *iter = NULL; struct rt6_info **ins; + struct rt6_info **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -716,8 +717,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, (info->nlh->nlmsg_flags & NLM_F_EXCL)) return -EEXIST; if (replace) { - found++; - break; + if (rt_can_ecmp == rt6_qualify_for_ecmp(iter)) { + found++; + break; + } + if (rt_can_ecmp) + fallback_ins = fallback_ins ?: ins; + goto next_iter; } if (iter->dst.dev == rt->dst.dev && @@ -753,9 +759,17 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, if (iter->rt6i_metric > rt->rt6i_metric) break; +next_iter: ins = &iter->dst.rt6_next; } + if (fallback_ins && !found) { + /* No ECMP-able route found, replace first non-ECMP one */ + ins = fallback_ins; + iter = *ins; + found++; + } + /* Reset round-robin state, if necessary */ if (ins == &fn->leaf) fn->rr_ptr = NULL; @@ -815,6 +829,8 @@ add: } } else { + int nsiblings; + if (!found) { if (add) goto add; @@ -835,8 +851,27 @@ add: info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } + nsiblings = iter->rt6i_nsiblings; fib6_purge_rt(iter, fn, info->nl_net); rt6_release(iter); + + if (nsiblings) { + /* Replacing an ECMP route, remove all siblings */ + ins = &rt->dst.rt6_next; + iter = *ins; + while (iter) { + if (rt6_qualify_for_ecmp(iter)) { + *ins = iter->dst.rt6_next; + fib6_purge_rt(iter, fn, info->nl_net); + rt6_release(iter); + nsiblings--; + } else { + ins = &iter->dst.rt6_next; + } + iter = *ins; + } + WARN_ON(nsiblings != 0); + } } return 0; diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index c217775..bc09cb9 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1300,8 +1300,10 @@ emsgsize: /* If this is the first and only packet and device * supports checksum offloading, let's use it. + * Use transhdrlen, same as IPv4, because partial + * sums only work when transhdrlen is set. */ - if (!skb && sk->sk_protocol == IPPROTO_UDP && + if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && length + fragheaderlen < mtu && rt->dst.dev->features & NETIF_F_V6_CSUM && !exthdrlen) diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 1a732a1..62f5b0d 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1275,6 +1275,9 @@ do_replace(struct net *net, const void __user *user, unsigned int len) /* overflow check */ if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); @@ -1822,6 +1825,9 @@ compat_do_replace(struct net *net, void __user *user, unsigned int len) return -ENOMEM; if (tmp.num_counters >= INT_MAX / sizeof(struct xt_counters)) return -ENOMEM; + if (tmp.num_counters == 0) + return -EINVAL; + tmp.name[sizeof(tmp.name)-1] = 0; newinfo = xt_alloc_table_info(tmp.size); diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d358888..c73ae50 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -2504,9 +2504,9 @@ static int ip6_route_multipath(struct fib6_config *cfg, int add) int attrlen; int err = 0, last_err = 0; + remaining = cfg->fc_mp_len; beginning: rtnh = (struct rtnexthop *)cfg->fc_mp; - remaining = cfg->fc_mp_len; /* Parse a Multipath Entry */ while (rtnh_ok(rtnh, remaining)) { @@ -2536,15 +2536,19 @@ beginning: * next hops that have been already added. */ add = 0; + remaining = cfg->fc_mp_len - remaining; goto beginning; } } /* Because each route is added like a single route we remove - * this flag after the first nexthop (if there is a collision, - * we have already fail to add the first nexthop: - * fib6_add_rt2node() has reject it). + * these flags after the first nexthop: if there is a collision, + * we have already failed to add the first nexthop: + * fib6_add_rt2node() has rejected it; when replacing, old + * nexthops have been replaced by first new, the rest should + * be added to it. */ - cfg->fc_nlinfo.nlh->nlmsg_flags &= ~NLM_F_EXCL; + cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | + NLM_F_REPLACE); rtnh = rtnh_next(rtnh, &remaining); } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b6575d6..3adffb3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -914,7 +914,7 @@ static void tcp_v6_timewait_ack(struct sock *sk, struct sk_buff *skb) tcptw->tw_rcv_wnd >> tw->tw_rcv_wscale, tcp_time_stamp + tcptw->tw_ts_offset, tcptw->tw_ts_recent, tw->tw_bound_dev_if, tcp_twsk_md5_key(tcptw), - tw->tw_tclass, (tw->tw_flowlabel << 12)); + tw->tw_tclass, cpu_to_be32(tw->tw_flowlabel)); inet_twsk_put(tw); } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 3477c91..c2ec416 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -731,7 +731,9 @@ static bool __udp_v6_is_mcast_sock(struct net *net, struct sock *sk, (inet->inet_dport && inet->inet_dport != rmt_port) || (!ipv6_addr_any(&sk->sk_v6_daddr) && !ipv6_addr_equal(&sk->sk_v6_daddr, rmt_addr)) || - (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif) || + (!ipv6_addr_any(&sk->sk_v6_rcv_saddr) && + !ipv6_addr_equal(&sk->sk_v6_rcv_saddr, loc_addr))) return false; if (!inet6_mc_check(sk, loc_addr, rmt_addr)) return false; diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index a4220e9..efa3f48 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -98,8 +98,7 @@ static u8 *ieee80211_wep_add_iv(struct ieee80211_local *local, hdr->frame_control |= cpu_to_le16(IEEE80211_FCTL_PROTECTED); - if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN || - skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) + if (WARN_ON(skb_headroom(skb) < IEEE80211_WEP_IV_LEN)) return NULL; hdrlen = ieee80211_hdrlen(hdr->frame_control); @@ -167,6 +166,9 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, size_t len; u8 rc4key[3 + WLAN_KEY_LEN_WEP104]; + if (WARN_ON(skb_tailroom(skb) < IEEE80211_WEP_ICV_LEN)) + return -1; + iv = ieee80211_wep_add_iv(local, skb, keylen, keyidx); if (!iv) return -1; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index f70e34a..a0f3e6a3 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -863,6 +863,7 @@ config NETFILTER_XT_TARGET_TPROXY depends on NETFILTER_XTABLES depends on NETFILTER_ADVANCED depends on (IPV6 || IPV6=n) + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) depends on IP_NF_MANGLE select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES @@ -1356,6 +1357,7 @@ config NETFILTER_XT_MATCH_SOCKET depends on NETFILTER_ADVANCED depends on !NF_CONNTRACK || NF_CONNTRACK depends on (IPV6 || IPV6=n) + depends on (IP6_NF_IPTABLES || IP6_NF_IPTABLES=n) select NF_DEFRAG_IPV4 select NF_DEFRAG_IPV6 if IP6_NF_IPTABLES help diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 4953267..285eae3 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -3823,6 +3823,9 @@ static void __net_exit ip_vs_control_net_cleanup_sysctl(struct net *net) cancel_work_sync(&ipvs->defense_work.work); unregister_net_sysctl_table(ipvs->sysctl_hdr); ip_vs_stop_estimator(net, &ipvs->tot_stats); + + if (!net_eq(net, &init_net)) + kfree(ipvs->sysctl_tbl); } #else diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 5caa0c4..70383de 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -202,7 +202,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW - * sLA -> sTW Last ACK detected. + * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. Remain in the same state. * sCL -> sCL */ @@ -261,7 +261,7 @@ static const u8 tcp_conntracks[2][6][TCP_CONNTRACK_MAX] = { * sES -> sES :-) * sFW -> sCW Normal close request answered by ACK. * sCW -> sCW - * sLA -> sTW Last ACK detected. + * sLA -> sTW Last ACK detected (RFC5961 challenged) * sTW -> sTW Retransmitted last ACK. * sCL -> sCL */ @@ -906,6 +906,7 @@ static int tcp_packet(struct nf_conn *ct, 1 : ct->proto.tcp.last_win; ct->proto.tcp.seen[ct->proto.tcp.last_dir].td_scale = ct->proto.tcp.last_wscale; + ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; ct->proto.tcp.seen[ct->proto.tcp.last_dir].flags = ct->proto.tcp.last_flags; memset(&ct->proto.tcp.seen[dir], 0, @@ -923,7 +924,9 @@ static int tcp_packet(struct nf_conn *ct, * may be in sync but we are not. In that case, we annotate * the TCP options and let the packet go through. If it is a * valid SYN packet, the server will reply with a SYN/ACK, and - * then we'll get in sync. Otherwise, the server ignores it. */ + * then we'll get in sync. Otherwise, the server potentially + * responds with a challenge ACK if implementing RFC5961. + */ if (index == TCP_SYN_SET && dir == IP_CT_DIR_ORIGINAL) { struct ip_ct_tcp_state seen = {}; @@ -939,6 +942,13 @@ static int tcp_packet(struct nf_conn *ct, ct->proto.tcp.last_flags |= IP_CT_TCP_FLAG_SACK_PERM; } + /* Mark the potential for RFC5961 challenge ACK, + * this pose a special problem for LAST_ACK state + * as ACK is intrepretated as ACKing last FIN. + */ + if (old_state == TCP_CONNTRACK_LAST_ACK) + ct->proto.tcp.last_flags |= + IP_CT_EXP_CHALLENGE_ACK; } spin_unlock_bh(&ct->lock); if (LOG_INVALID(net, IPPROTO_TCP)) @@ -970,6 +980,25 @@ static int tcp_packet(struct nf_conn *ct, nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, "nf_ct_tcp: invalid state "); return -NF_ACCEPT; + case TCP_CONNTRACK_TIME_WAIT: + /* RFC5961 compliance cause stack to send "challenge-ACK" + * e.g. in response to spurious SYNs. Conntrack MUST + * not believe this ACK is acking last FIN. + */ + if (old_state == TCP_CONNTRACK_LAST_ACK && + index == TCP_ACK_SET && + ct->proto.tcp.last_dir != dir && + ct->proto.tcp.last_index == TCP_SYN_SET && + (ct->proto.tcp.last_flags & IP_CT_EXP_CHALLENGE_ACK)) { + /* Detected RFC5961 challenge ACK */ + ct->proto.tcp.last_flags &= ~IP_CT_EXP_CHALLENGE_ACK; + spin_unlock_bh(&ct->lock); + if (LOG_INVALID(net, IPPROTO_TCP)) + nf_log_packet(net, pf, 0, skb, NULL, NULL, NULL, + "nf_ct_tcp: challenge-ACK ignored "); + return NF_ACCEPT; /* Don't change state */ + } + break; case TCP_CONNTRACK_CLOSE: if (index == TCP_RST_SET && (ct->proto.tcp.seen[!dir].flags & IP_CT_TCP_FLAG_MAXACK_SET) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index ad9d11f..34ded09 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -4472,9 +4472,9 @@ EXPORT_SYMBOL_GPL(nft_data_init); */ void nft_data_uninit(const struct nft_data *data, enum nft_data_types type) { - switch (type) { - case NFT_DATA_VALUE: + if (type < NFT_DATA_VERDICT) return; + switch (type) { case NFT_DATA_VERDICT: return nft_verdict_uninit(data); default: diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 3ad9126..4ef1fae 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -1073,7 +1073,13 @@ static struct pernet_operations nfnl_log_net_ops = { static int __init nfnetlink_log_init(void) { - int status = -ENOMEM; + int status; + + status = register_pernet_subsys(&nfnl_log_net_ops); + if (status < 0) { + pr_err("failed to register pernet ops\n"); + goto out; + } netlink_register_notifier(&nfulnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfulnl_subsys); @@ -1088,28 +1094,23 @@ static int __init nfnetlink_log_init(void) goto cleanup_subsys; } - status = register_pernet_subsys(&nfnl_log_net_ops); - if (status < 0) { - pr_err("failed to register pernet ops\n"); - goto cleanup_logger; - } return status; -cleanup_logger: - nf_log_unregister(&nfulnl_logger); cleanup_subsys: nfnetlink_subsys_unregister(&nfulnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfulnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_log_net_ops); +out: return status; } static void __exit nfnetlink_log_fini(void) { - unregister_pernet_subsys(&nfnl_log_net_ops); nf_log_unregister(&nfulnl_logger); nfnetlink_subsys_unregister(&nfulnl_subsys); netlink_unregister_notifier(&nfulnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_log_net_ops); } MODULE_DESCRIPTION("netfilter userspace logging"); diff --git a/net/netfilter/nfnetlink_queue_core.c b/net/netfilter/nfnetlink_queue_core.c index 0b98c74..11c7682 100644 --- a/net/netfilter/nfnetlink_queue_core.c +++ b/net/netfilter/nfnetlink_queue_core.c @@ -1317,7 +1317,13 @@ static struct pernet_operations nfnl_queue_net_ops = { static int __init nfnetlink_queue_init(void) { - int status = -ENOMEM; + int status; + + status = register_pernet_subsys(&nfnl_queue_net_ops); + if (status < 0) { + pr_err("nf_queue: failed to register pernet ops\n"); + goto out; + } netlink_register_notifier(&nfqnl_rtnl_notifier); status = nfnetlink_subsys_register(&nfqnl_subsys); @@ -1326,19 +1332,13 @@ static int __init nfnetlink_queue_init(void) goto cleanup_netlink_notifier; } - status = register_pernet_subsys(&nfnl_queue_net_ops); - if (status < 0) { - pr_err("nf_queue: failed to register pernet ops\n"); - goto cleanup_subsys; - } register_netdevice_notifier(&nfqnl_dev_notifier); nf_register_queue_handler(&nfqh); return status; -cleanup_subsys: - nfnetlink_subsys_unregister(&nfqnl_subsys); cleanup_netlink_notifier: netlink_unregister_notifier(&nfqnl_rtnl_notifier); +out: return status; } @@ -1346,9 +1346,9 @@ static void __exit nfnetlink_queue_fini(void) { nf_unregister_queue_handler(); unregister_netdevice_notifier(&nfqnl_dev_notifier); - unregister_pernet_subsys(&nfnl_queue_net_ops); nfnetlink_subsys_unregister(&nfqnl_subsys); netlink_unregister_notifier(&nfqnl_rtnl_notifier); + unregister_pernet_subsys(&nfnl_queue_net_ops); rcu_barrier(); /* Wait for completion of call_rcu()'s */ } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index daa0b81..bf6e766 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -89,7 +89,7 @@ static inline int netlink_is_kernel(struct sock *sk) return nlk_sk(sk)->flags & NETLINK_KERNEL_SOCKET; } -struct netlink_table *nl_table; +struct netlink_table *nl_table __read_mostly; EXPORT_SYMBOL_GPL(nl_table); static DECLARE_WAIT_QUEUE_HEAD(nl_table_wait); @@ -1081,6 +1081,7 @@ static int netlink_insert(struct sock *sk, u32 portid) if (err) { if (err == -EEXIST) err = -EADDRINUSE; + nlk_sk(sk)->portid = 0; sock_put(sk); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index b6ef9a0..a75864d 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -81,6 +81,11 @@ int unregister_tcf_proto_ops(struct tcf_proto_ops *ops) struct tcf_proto_ops *t; int rc = -ENOENT; + /* Wait for outstanding call_rcu()s, if any, from a + * tcf_proto_ops's destroy() handler. + */ + rcu_barrier(); + write_lock(&cls_mod_lock); list_for_each_entry(t, &tcf_proto_base, head) { if (t == ops) { diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 46568b8..055453d48 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -338,7 +338,7 @@ int netdev_switch_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, fi, tos, type, nlflags, tb_id); if (!err) - fi->fib_flags |= RTNH_F_EXTERNAL; + fi->fib_flags |= RTNH_F_OFFLOAD; } return err; @@ -364,7 +364,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, const struct swdev_ops *ops; int err = 0; - if (!(fi->fib_flags & RTNH_F_EXTERNAL)) + if (!(fi->fib_flags & RTNH_F_OFFLOAD)) return 0; dev = netdev_switch_get_dev_by_nhs(fi); @@ -376,7 +376,7 @@ int netdev_switch_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, err = ops->swdev_fib_ipv4_del(dev, htonl(dst), dst_len, fi, tos, type, tb_id); if (!err) - fi->fib_flags &= ~RTNH_F_EXTERNAL; + fi->fib_flags &= ~RTNH_F_OFFLOAD; } return err; |