diff --git a/Makefile b/Makefile index c23d0b0c6c45..777f5685a36b 100644 --- a/Makefile +++ b/Makefile @@ -1,7 +1,7 @@ # SPDX-License-Identifier: GPL-2.0 VERSION = 4 PATCHLEVEL = 14 -SUBLEVEL = 41 +SUBLEVEL = 42 EXTRAVERSION = NAME = Petit Gorille diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index c02cc817a490..60666db31886 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -450,7 +450,7 @@ static void rlb_update_client(struct rlb_client_info *client_info) { int i; - if (!client_info->slave) + if (!client_info->slave || !is_valid_ether_addr(client_info->mac_dst)) return; for (i = 0; i < RLB_ARP_BURST_SIZE; i++) { @@ -943,6 +943,10 @@ static void alb_send_lp_vid(struct slave *slave, u8 mac_addr[], skb->priority = TC_PRIO_CONTROL; skb->dev = slave->dev; + netdev_dbg(slave->bond->dev, + "Send learning packet: dev %s mac %pM vlan %d\n", + slave->dev->name, mac_addr, vid); + if (vid) __vlan_hwaccel_put_tag(skb, vlan_proto, vid); @@ -965,14 +969,13 @@ static int alb_upper_dev_walk(struct net_device *upper, void *_data) u8 *mac_addr = data->mac_addr; struct bond_vlan_tag *tags; - if (is_vlan_dev(upper) && vlan_get_encap_level(upper) == 0) { - if (strict_match && - ether_addr_equal_64bits(mac_addr, - upper->dev_addr)) { + if (is_vlan_dev(upper) && + bond->nest_level == vlan_get_encap_level(upper) - 1) { + if (upper->addr_assign_type == NET_ADDR_STOLEN) { alb_send_lp_vid(slave, mac_addr, vlan_dev_vlan_proto(upper), vlan_dev_vlan_id(upper)); - } else if (!strict_match) { + } else { alb_send_lp_vid(slave, upper->dev_addr, vlan_dev_vlan_proto(upper), vlan_dev_vlan_id(upper)); diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index bf3be2e6d4a8..f0aa57222f17 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -1734,6 +1734,8 @@ int bond_enslave(struct net_device *bond_dev, struct net_device *slave_dev) if (bond_mode_uses_xmit_hash(bond)) bond_update_slave_arr(bond, NULL); + bond->nest_level = dev_get_nest_level(bond_dev); + netdev_info(bond_dev, "Enslaving %s as %s interface with %s link\n", slave_dev->name, bond_is_active_slave(new_slave) ? "an active" : "a backup", diff --git a/drivers/net/ethernet/broadcom/tg3.c b/drivers/net/ethernet/broadcom/tg3.c index 48738eb27806..9a8ef630466f 100644 --- a/drivers/net/ethernet/broadcom/tg3.c +++ b/drivers/net/ethernet/broadcom/tg3.c @@ -8723,14 +8723,15 @@ static void tg3_free_consistent(struct tg3 *tp) tg3_mem_rx_release(tp); tg3_mem_tx_release(tp); - /* Protect tg3_get_stats64() from reading freed tp->hw_stats. */ - tg3_full_lock(tp, 0); + /* tp->hw_stats can be referenced safely: + * 1. under rtnl_lock + * 2. or under tp->lock if TG3_FLAG_INIT_COMPLETE is set. + */ if (tp->hw_stats) { dma_free_coherent(&tp->pdev->dev, sizeof(struct tg3_hw_stats), tp->hw_stats, tp->stats_mapping); tp->hw_stats = NULL; } - tg3_full_unlock(tp); } /* @@ -14167,7 +14168,7 @@ static void tg3_get_stats64(struct net_device *dev, struct tg3 *tp = netdev_priv(dev); spin_lock_bh(&tp->lock); - if (!tp->hw_stats) { + if (!tp->hw_stats || !tg3_flag(tp, INIT_COMPLETE)) { *stats = tp->net_stats_prev; spin_unlock_bh(&tp->lock); return; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 67f74fcb265e..5fe56dc4cfae 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -1013,6 +1013,22 @@ static int mlx4_en_set_coalesce(struct net_device *dev, if (!coal->tx_max_coalesced_frames_irq) return -EINVAL; + if (coal->tx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs_low > MLX4_EN_MAX_COAL_TIME || + coal->rx_coalesce_usecs_high > MLX4_EN_MAX_COAL_TIME) { + netdev_info(dev, "%s: maximum coalesce time supported is %d usecs\n", + __func__, MLX4_EN_MAX_COAL_TIME); + return -ERANGE; + } + + if (coal->tx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS || + coal->rx_max_coalesced_frames > MLX4_EN_MAX_COAL_PKTS) { + netdev_info(dev, "%s: maximum coalesced frames supported is %d\n", + __func__, MLX4_EN_MAX_COAL_PKTS); + return -ERANGE; + } + priv->rx_frames = (coal->rx_max_coalesced_frames == MLX4_EN_AUTO_CONF) ? MLX4_EN_RX_COAL_TARGET : diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index c097eef41a9c..faa4bd21f148 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -3318,12 +3318,11 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, MAX_TX_RINGS, GFP_KERNEL); if (!priv->tx_ring[t]) { err = -ENOMEM; - goto err_free_tx; + goto out; } priv->tx_cq[t] = kzalloc(sizeof(struct mlx4_en_cq *) * MAX_TX_RINGS, GFP_KERNEL); if (!priv->tx_cq[t]) { - kfree(priv->tx_ring[t]); err = -ENOMEM; goto out; } @@ -3576,11 +3575,6 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port, return 0; -err_free_tx: - while (t--) { - kfree(priv->tx_ring[t]); - kfree(priv->tx_cq[t]); - } out: mlx4_en_destroy_netdev(dev); return err; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 2c1a5ff6acfa..09f4764a3f39 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -131,6 +131,9 @@ #define MLX4_EN_TX_COAL_PKTS 16 #define MLX4_EN_TX_COAL_TIME 0x10 +#define MLX4_EN_MAX_COAL_PKTS U16_MAX +#define MLX4_EN_MAX_COAL_TIME U16_MAX + #define MLX4_EN_RX_RATE_LOW 400000 #define MLX4_EN_RX_COAL_TIME_LOW 0 #define MLX4_EN_RX_RATE_HIGH 450000 @@ -547,8 +550,8 @@ struct mlx4_en_priv { u16 rx_usecs_low; u32 pkt_rate_high; u16 rx_usecs_high; - u16 sample_interval; - u16 adaptive_rx_coal; + u32 sample_interval; + u32 adaptive_rx_coal; u32 msg_enable; u32 loopback_ok; u32 validate_loopback; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c index 42bab73a9f40..ede66e6af786 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tc.c @@ -780,6 +780,10 @@ static int __parse_cls_flower(struct mlx5e_priv *priv, f->mask); addr_type = key->addr_type; + /* the HW doesn't support frag first/later */ + if (mask->flags & FLOW_DIS_FIRST_FRAG) + return -EOPNOTSUPP; + if (mask->flags & FLOW_DIS_IS_FRAGMENT) { MLX5_SET(fte_match_set_lyr_2_4, headers_c, frag, 1); MLX5_SET(fte_match_set_lyr_2_4, headers_v, frag, @@ -1383,7 +1387,8 @@ static bool modify_header_match_supported(struct mlx5_flow_spec *spec, } ip_proto = MLX5_GET(fte_match_set_lyr_2_4, headers_v, ip_protocol); - if (modify_ip_header && ip_proto != IPPROTO_TCP && ip_proto != IPPROTO_UDP) { + if (modify_ip_header && ip_proto != IPPROTO_TCP && + ip_proto != IPPROTO_UDP && ip_proto != IPPROTO_ICMP) { pr_info("can't offload re-write of ip proto %d\n", ip_proto); return false; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index eea7f931cad3..d560047c0bf9 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -234,7 +234,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, dma_addr = dma_map_single(sq->pdev, skb_data, headlen, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) - return -ENOMEM; + goto dma_unmap_wqe_err; dseg->addr = cpu_to_be64(dma_addr); dseg->lkey = sq->mkey_be; @@ -252,7 +252,7 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, dma_addr = skb_frag_dma_map(sq->pdev, frag, 0, fsz, DMA_TO_DEVICE); if (unlikely(dma_mapping_error(sq->pdev, dma_addr))) - return -ENOMEM; + goto dma_unmap_wqe_err; dseg->addr = cpu_to_be64(dma_addr); dseg->lkey = sq->mkey_be; @@ -264,6 +264,10 @@ mlx5e_txwqe_build_dsegs(struct mlx5e_txqsq *sq, struct sk_buff *skb, } return num_dma; + +dma_unmap_wqe_err: + mlx5e_dma_unmap_wqe_err(sq, num_dma); + return -ENOMEM; } static inline void @@ -355,17 +359,15 @@ static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, (struct mlx5_wqe_data_seg *)cseg + ds_cnt); if (unlikely(num_dma < 0)) - goto dma_unmap_wqe_err; + goto err_drop; mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma, num_bytes, num_dma, wi, cseg); return NETDEV_TX_OK; -dma_unmap_wqe_err: +err_drop: sq->stats.dropped++; - mlx5e_dma_unmap_wqe_err(sq, wi->num_dma); - dev_kfree_skb_any(skb); return NETDEV_TX_OK; @@ -594,17 +596,15 @@ netdev_tx_t mlx5i_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, num_dma = mlx5e_txwqe_build_dsegs(sq, skb, skb_data, headlen, (struct mlx5_wqe_data_seg *)cseg + ds_cnt); if (unlikely(num_dma < 0)) - goto dma_unmap_wqe_err; + goto err_drop; mlx5e_txwqe_complete(sq, skb, opcode, ds_cnt + num_dma, num_bytes, num_dma, wi, cseg); return NETDEV_TX_OK; -dma_unmap_wqe_err: +err_drop: sq->stats.dropped++; - mlx5e_dma_unmap_wqe_err(sq, wi->num_dma); - dev_kfree_skb_any(skb); return NETDEV_TX_OK; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c index c77f4c0c7769..82e37250ed01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/eswitch.c @@ -2054,26 +2054,35 @@ int mlx5_eswitch_get_vport_stats(struct mlx5_eswitch *esw, memset(vf_stats, 0, sizeof(*vf_stats)); vf_stats->rx_packets = MLX5_GET_CTR(out, received_eth_unicast.packets) + + MLX5_GET_CTR(out, received_ib_unicast.packets) + MLX5_GET_CTR(out, received_eth_multicast.packets) + + MLX5_GET_CTR(out, received_ib_multicast.packets) + MLX5_GET_CTR(out, received_eth_broadcast.packets); vf_stats->rx_bytes = MLX5_GET_CTR(out, received_eth_unicast.octets) + + MLX5_GET_CTR(out, received_ib_unicast.octets) + MLX5_GET_CTR(out, received_eth_multicast.octets) + + MLX5_GET_CTR(out, received_ib_multicast.octets) + MLX5_GET_CTR(out, received_eth_broadcast.octets); vf_stats->tx_packets = MLX5_GET_CTR(out, transmitted_eth_unicast.packets) + + MLX5_GET_CTR(out, transmitted_ib_unicast.packets) + MLX5_GET_CTR(out, transmitted_eth_multicast.packets) + + MLX5_GET_CTR(out, transmitted_ib_multicast.packets) + MLX5_GET_CTR(out, transmitted_eth_broadcast.packets); vf_stats->tx_bytes = MLX5_GET_CTR(out, transmitted_eth_unicast.octets) + + MLX5_GET_CTR(out, transmitted_ib_unicast.octets) + MLX5_GET_CTR(out, transmitted_eth_multicast.octets) + + MLX5_GET_CTR(out, transmitted_ib_multicast.octets) + MLX5_GET_CTR(out, transmitted_eth_broadcast.octets); vf_stats->multicast = - MLX5_GET_CTR(out, received_eth_multicast.packets); + MLX5_GET_CTR(out, received_eth_multicast.packets) + + MLX5_GET_CTR(out, received_ib_multicast.packets); vf_stats->broadcast = MLX5_GET_CTR(out, received_eth_broadcast.packets); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c index 5a7bea688ec8..33e5ff081e36 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fs_core.c @@ -174,6 +174,7 @@ static void del_flow_group(struct fs_node *node); static void del_fte(struct fs_node *node); static bool mlx5_flow_dests_cmp(struct mlx5_flow_destination *d1, struct mlx5_flow_destination *d2); +static void cleanup_root_ns(struct mlx5_flow_root_namespace *root_ns); static struct mlx5_flow_rule * find_flow_rule(struct fs_fte *fte, struct mlx5_flow_destination *dest); @@ -2041,23 +2042,27 @@ static int create_anchor_flow_table(struct mlx5_flow_steering *steering) static int init_root_ns(struct mlx5_flow_steering *steering) { + int err; + steering->root_ns = create_root_ns(steering, FS_FT_NIC_RX); if (!steering->root_ns) - goto cleanup; + return -ENOMEM; - if (init_root_tree(steering, &root_fs, &steering->root_ns->ns.node)) - goto cleanup; + err = init_root_tree(steering, &root_fs, &steering->root_ns->ns.node); + if (err) + goto out_err; set_prio_attrs(steering->root_ns); - - if (create_anchor_flow_table(steering)) - goto cleanup; + err = create_anchor_flow_table(steering); + if (err) + goto out_err; return 0; -cleanup: - mlx5_cleanup_fs(steering->dev); - return -ENOMEM; +out_err: + cleanup_root_ns(steering->root_ns); + steering->root_ns = NULL; + return err; } static void clean_tree(struct fs_node *node) diff --git a/drivers/net/ethernet/realtek/8139too.c b/drivers/net/ethernet/realtek/8139too.c index d24b47b8e0b2..d118da5a10a2 100644 --- a/drivers/net/ethernet/realtek/8139too.c +++ b/drivers/net/ethernet/realtek/8139too.c @@ -2224,7 +2224,7 @@ static void rtl8139_poll_controller(struct net_device *dev) struct rtl8139_private *tp = netdev_priv(dev); const int irq = tp->pci_dev->irq; - disable_irq(irq); + disable_irq_nosync(irq); rtl8139_interrupt(irq, dev); enable_irq(irq); } diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index db553d4e8d22..b98fcc9e93e5 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -4886,6 +4886,9 @@ static void rtl_pll_power_down(struct rtl8169_private *tp) static void rtl_pll_power_up(struct rtl8169_private *tp) { rtl_generic_op(tp, tp->pll_power_ops.up); + + /* give MAC/PHY some time to resume */ + msleep(20); } static void rtl_init_pll_power_ops(struct rtl8169_private *tp) diff --git a/drivers/net/ethernet/sun/niu.c b/drivers/net/ethernet/sun/niu.c index 6a4e8e1bbd90..e92f41d20a2c 100644 --- a/drivers/net/ethernet/sun/niu.c +++ b/drivers/net/ethernet/sun/niu.c @@ -3442,7 +3442,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, len = (val & RCR_ENTRY_L2_LEN) >> RCR_ENTRY_L2_LEN_SHIFT; - len -= ETH_FCS_LEN; + append_size = len + ETH_HLEN + ETH_FCS_LEN; addr = (val & RCR_ENTRY_PKT_BUF_ADDR) << RCR_ENTRY_PKT_BUF_ADDR_SHIFT; @@ -3452,7 +3452,6 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, RCR_ENTRY_PKTBUFSZ_SHIFT]; off = addr & ~PAGE_MASK; - append_size = rcr_size; if (num_rcr == 1) { int ptype; @@ -3465,7 +3464,7 @@ static int niu_process_rx_pkt(struct napi_struct *napi, struct niu *np, else skb_checksum_none_assert(skb); } else if (!(val & RCR_ENTRY_MULTI)) - append_size = len - skb->len; + append_size = append_size - skb->len; niu_rx_skb_append(skb, page, off, append_size, rcr_size); if ((page->index + rp->rbr_block_size) - rcr_size == addr) { diff --git a/drivers/net/ethernet/ti/cpsw.c b/drivers/net/ethernet/ti/cpsw.c index 992c43b1868f..8cb44eabc283 100644 --- a/drivers/net/ethernet/ti/cpsw.c +++ b/drivers/net/ethernet/ti/cpsw.c @@ -1260,6 +1260,8 @@ static inline void cpsw_add_dual_emac_def_ale_entries( cpsw_ale_add_ucast(cpsw->ale, priv->mac_addr, HOST_PORT_NUM, ALE_VLAN | ALE_SECURE, slave->port_vlan); + cpsw_ale_control_set(cpsw->ale, slave_port, + ALE_PORT_DROP_UNKNOWN_VLAN, 1); } static void soft_reset_slave(struct cpsw_slave *slave) diff --git a/drivers/net/hyperv/netvsc_drv.c b/drivers/net/hyperv/netvsc_drv.c index c849de3cb046..444e560d928b 100644 --- a/drivers/net/hyperv/netvsc_drv.c +++ b/drivers/net/hyperv/netvsc_drv.c @@ -1742,7 +1742,8 @@ static int netvsc_vf_join(struct net_device *vf_netdev, goto rx_handler_failed; } - ret = netdev_upper_dev_link(vf_netdev, ndev); + ret = netdev_master_upper_dev_link(vf_netdev, ndev, + NULL, NULL); if (ret != 0) { netdev_err(vf_netdev, "can not set master device %s (err = %d)\n", diff --git a/drivers/net/usb/qmi_wwan.c b/drivers/net/usb/qmi_wwan.c index 1aad0568dcc6..2f828eb9ace6 100644 --- a/drivers/net/usb/qmi_wwan.c +++ b/drivers/net/usb/qmi_wwan.c @@ -1338,6 +1338,18 @@ static int qmi_wwan_probe(struct usb_interface *intf, id->driver_info = (unsigned long)&qmi_wwan_info; } + /* There are devices where the same interface number can be + * configured as different functions. We should only bind to + * vendor specific functions when matching on interface number + */ + if (id->match_flags & USB_DEVICE_ID_MATCH_INT_NUMBER && + desc->bInterfaceClass != USB_CLASS_VENDOR_SPEC) { + dev_dbg(&intf->dev, + "Rejecting interface number match for class %02x\n", + desc->bInterfaceClass); + return -ENODEV; + } + /* Quectel EC20 quirk where we've QMI on interface 4 instead of 0 */ if (quectel_ec20_detected(intf) && desc->bInterfaceNumber == 0) { dev_dbg(&intf->dev, "Quectel EC20 quirk, skipping interface 0\n"); diff --git a/drivers/scsi/aacraid/commsup.c b/drivers/scsi/aacraid/commsup.c index c0a4fcb7fd0a..3696f9ded252 100644 --- a/drivers/scsi/aacraid/commsup.c +++ b/drivers/scsi/aacraid/commsup.c @@ -752,6 +752,8 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, int wait; unsigned long flags = 0; unsigned long mflags = 0; + struct aac_hba_cmd_req *hbacmd = (struct aac_hba_cmd_req *) + fibptr->hw_fib_va; fibptr->flags = (FIB_CONTEXT_FLAG | FIB_CONTEXT_FLAG_NATIVE_HBA); if (callback) { @@ -762,11 +764,9 @@ int aac_hba_send(u8 command, struct fib *fibptr, fib_callback callback, wait = 1; - if (command == HBA_IU_TYPE_SCSI_CMD_REQ) { - struct aac_hba_cmd_req *hbacmd = - (struct aac_hba_cmd_req *)fibptr->hw_fib_va; + hbacmd->iu_type = command; - hbacmd->iu_type = command; + if (command == HBA_IU_TYPE_SCSI_CMD_REQ) { /* bit1 of request_id must be 0 */ hbacmd->request_id = cpu_to_le32((((u32)(fibptr - dev->fibs)) << 2) + 1); diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c index d227d8514b25..1bc62294fe6b 100644 --- a/fs/btrfs/extent-tree.c +++ b/fs/btrfs/extent-tree.c @@ -3171,7 +3171,11 @@ static noinline int check_delayed_ref(struct btrfs_root *root, struct btrfs_transaction *cur_trans; int ret = 0; + spin_lock(&root->fs_info->trans_lock); cur_trans = root->fs_info->running_transaction; + if (cur_trans) + refcount_inc(&cur_trans->use_count); + spin_unlock(&root->fs_info->trans_lock); if (!cur_trans) return 0; @@ -3180,6 +3184,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root, head = btrfs_find_delayed_ref_head(delayed_refs, bytenr); if (!head) { spin_unlock(&delayed_refs->lock); + btrfs_put_transaction(cur_trans); return 0; } @@ -3196,6 +3201,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root, mutex_lock(&head->mutex); mutex_unlock(&head->mutex); btrfs_put_delayed_ref(&head->node); + btrfs_put_transaction(cur_trans); return -EAGAIN; } spin_unlock(&delayed_refs->lock); @@ -3223,6 +3229,7 @@ static noinline int check_delayed_ref(struct btrfs_root *root, } spin_unlock(&head->lock); mutex_unlock(&head->mutex); + btrfs_put_transaction(cur_trans); return ret; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 2ff11a693360..dd9d4d3a2e39 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -263,7 +263,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, * Inherently racy -- command line shares address space * with code and data. */ - rv = access_remote_vm(mm, arg_end - 1, &c, 1, 0); + rv = access_remote_vm(mm, arg_end - 1, &c, 1, FOLL_ANON); if (rv <= 0) goto out_free_page; @@ -281,7 +281,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, int nr_read; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -327,7 +327,7 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf, bool final; _count = min3(count, len, PAGE_SIZE); - nr_read = access_remote_vm(mm, p, page, _count, 0); + nr_read = access_remote_vm(mm, p, page, _count, FOLL_ANON); if (nr_read < 0) rv = nr_read; if (nr_read <= 0) @@ -946,7 +946,7 @@ static ssize_t environ_read(struct file *file, char __user *buf, max_len = min_t(size_t, PAGE_SIZE, count); this_len = min(max_len, this_len); - retval = access_remote_vm(mm, (env_start + src), page, this_len, 0); + retval = access_remote_vm(mm, (env_start + src), page, this_len, FOLL_ANON); if (retval <= 0) { ret = retval; diff --git a/include/linux/mm.h b/include/linux/mm.h index f50deada0f5c..f23215854c80 100644 --- a/include/linux/mm.h +++ b/include/linux/mm.h @@ -2383,6 +2383,7 @@ static inline struct page *follow_page(struct vm_area_struct *vma, #define FOLL_MLOCK 0x1000 /* lock present pages */ #define FOLL_REMOTE 0x2000 /* we are working on non-current tsk/mm */ #define FOLL_COW 0x4000 /* internal GUP flag */ +#define FOLL_ANON 0x8000 /* don't do file mappings */ static inline int vm_fault_to_errno(int vm_fault, int foll_flags) { diff --git a/include/net/bonding.h b/include/net/bonding.h index b2e68657a216..73799da57400 100644 --- a/include/net/bonding.h +++ b/include/net/bonding.h @@ -198,6 +198,7 @@ struct bonding { struct slave __rcu *primary_slave; struct bond_up_slave __rcu *slave_arr; /* Array of usable slaves */ bool force_primary; + u32 nest_level; s32 slave_cnt; /* never change this value outside the attach/detach wrappers */ int (*recv_probe)(const struct sk_buff *, struct bonding *, struct slave *); diff --git a/include/net/tls.h b/include/net/tls.h index df950383b8c1..48940a883d9a 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -98,6 +98,7 @@ struct tls_context { struct scatterlist *partially_sent_record; u16 partially_sent_offset; unsigned long flags; + bool in_tcp_sendpages; u16 pending_open_record_frags; int (*push_pending_record)(struct sock *sk, int flags); diff --git a/mm/gup.c b/mm/gup.c index 8fc23a60487d..d2ba0be71441 100644 --- a/mm/gup.c +++ b/mm/gup.c @@ -544,6 +544,9 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) if (vm_flags & (VM_IO | VM_PFNMAP)) return -EFAULT; + if (gup_flags & FOLL_ANON && !vma_is_anonymous(vma)) + return -EFAULT; + if (write) { if (!(vm_flags & VM_WRITE)) { if (!(gup_flags & FOLL_FORCE)) diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index f3aef22931ab..55a73ef388bf 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -503,8 +503,8 @@ int br_add_if(struct net_bridge *br, struct net_device *dev) if (dev->netdev_ops->ndo_start_xmit == br_dev_xmit) return -ELOOP; - /* Device is already being bridged */ - if (br_port_exists(dev)) + /* Device has master upper dev */ + if (netdev_master_upper_dev_get(dev)) return -EBUSY; /* No bridging devices that dislike that (e.g. wireless) */ diff --git a/net/compat.c b/net/compat.c index 22381719718c..32ed993588d6 100644 --- a/net/compat.c +++ b/net/compat.c @@ -377,7 +377,8 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, optname == SO_ATTACH_REUSEPORT_CBPF) return do_set_attach_filter(sock, level, optname, optval, optlen); - if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + if (!COMPAT_USE_64BIT_TIME && + (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) return do_set_sock_timeout(sock, level, optname, optval, optlen); return sock_setsockopt(sock, level, optname, optval, optlen); @@ -442,7 +443,8 @@ static int do_get_sock_timeout(struct socket *sock, int level, int optname, static int compat_sock_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { - if (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO) + if (!COMPAT_USE_64BIT_TIME && + (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) return do_get_sock_timeout(sock, level, optname, optval, optlen); return sock_getsockopt(sock, level, optname, optval, optlen); } diff --git a/net/dccp/ccids/ccid2.c b/net/dccp/ccids/ccid2.c index 97791b0b1b51..3887bc115762 100644 --- a/net/dccp/ccids/ccid2.c +++ b/net/dccp/ccids/ccid2.c @@ -126,6 +126,16 @@ static void ccid2_change_l_seq_window(struct sock *sk, u64 val) DCCPF_SEQ_WMAX)); } +static void dccp_tasklet_schedule(struct sock *sk) +{ + struct tasklet_struct *t = &dccp_sk(sk)->dccps_xmitlet; + + if (!test_and_set_bit(TASKLET_STATE_SCHED, &t->state)) { + sock_hold(sk); + __tasklet_schedule(t); + } +} + static void ccid2_hc_tx_rto_expire(unsigned long data) { struct sock *sk = (struct sock *)data; @@ -166,7 +176,7 @@ static void ccid2_hc_tx_rto_expire(unsigned long data) /* if we were blocked before, we may now send cwnd=1 packet */ if (sender_was_blocked) - tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_tasklet_schedule(sk); /* restart backed-off timer */ sk_reset_timer(sk, &hc->tx_rtotimer, jiffies + hc->tx_rto); out: @@ -706,7 +716,7 @@ static void ccid2_hc_tx_packet_recv(struct sock *sk, struct sk_buff *skb) done: /* check if incoming Acks allow pending packets to be sent */ if (sender_was_blocked && !ccid2_cwnd_network_limited(hc)) - tasklet_schedule(&dccp_sk(sk)->dccps_xmitlet); + dccp_tasklet_schedule(sk); dccp_ackvec_parsed_cleanup(&hc->tx_av_chunks); } diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 3a2c34027758..2a952cbd6efa 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -230,12 +230,12 @@ static void dccp_write_xmitlet(unsigned long data) else dccp_write_xmit(sk); bh_unlock_sock(sk); + sock_put(sk); } static void dccp_write_xmit_timer(unsigned long data) { dccp_write_xmitlet(data); - sock_put((struct sock *)data); } void dccp_init_xmit_timers(struct sock *sk) diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index b8f0db54b197..16226d49263d 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -775,8 +775,10 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; } tos = get_rttos(&ipc, inet); @@ -842,6 +844,7 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5ea559f8c456..28bc3a98adc7 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -711,7 +711,7 @@ static void update_or_create_fnhe(struct fib_nh *nh, __be32 daddr, __be32 gw, fnhe->fnhe_daddr = daddr; fnhe->fnhe_gw = gw; fnhe->fnhe_pmtu = pmtu; - fnhe->fnhe_expires = expires; + fnhe->fnhe_expires = max(1UL, expires); /* Exception created; mark the cached routes for the nexthop * stale, so anyone caching it rechecks if this exception @@ -1286,6 +1286,36 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst) return mtu - lwtunnel_headroom(dst->lwtstate, mtu); } +static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) +{ + struct fnhe_hash_bucket *hash; + struct fib_nh_exception *fnhe, __rcu **fnhe_p; + u32 hval = fnhe_hashfun(daddr); + + spin_lock_bh(&fnhe_lock); + + hash = rcu_dereference_protected(nh->nh_exceptions, + lockdep_is_held(&fnhe_lock)); + hash += hval; + + fnhe_p = &hash->chain; + fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); + while (fnhe) { + if (fnhe->fnhe_daddr == daddr) { + rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( + fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); + fnhe_flush_routes(fnhe); + kfree_rcu(fnhe, rcu); + break; + } + fnhe_p = &fnhe->fnhe_next; + fnhe = rcu_dereference_protected(fnhe->fnhe_next, + lockdep_is_held(&fnhe_lock)); + } + + spin_unlock_bh(&fnhe_lock); +} + static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) { struct fnhe_hash_bucket *hash = rcu_dereference(nh->nh_exceptions); @@ -1299,8 +1329,14 @@ static struct fib_nh_exception *find_exception(struct fib_nh *nh, __be32 daddr) for (fnhe = rcu_dereference(hash[hval].chain); fnhe; fnhe = rcu_dereference(fnhe->fnhe_next)) { - if (fnhe->fnhe_daddr == daddr) + if (fnhe->fnhe_daddr == daddr) { + if (fnhe->fnhe_expires && + time_after(jiffies, fnhe->fnhe_expires)) { + ip_del_fnhe(nh, daddr); + break; + } return fnhe; + } } return NULL; } @@ -1620,36 +1656,6 @@ static void ip_handle_martian_source(struct net_device *dev, #endif } -static void ip_del_fnhe(struct fib_nh *nh, __be32 daddr) -{ - struct fnhe_hash_bucket *hash; - struct fib_nh_exception *fnhe, __rcu **fnhe_p; - u32 hval = fnhe_hashfun(daddr); - - spin_lock_bh(&fnhe_lock); - - hash = rcu_dereference_protected(nh->nh_exceptions, - lockdep_is_held(&fnhe_lock)); - hash += hval; - - fnhe_p = &hash->chain; - fnhe = rcu_dereference_protected(*fnhe_p, lockdep_is_held(&fnhe_lock)); - while (fnhe) { - if (fnhe->fnhe_daddr == daddr) { - rcu_assign_pointer(*fnhe_p, rcu_dereference_protected( - fnhe->fnhe_next, lockdep_is_held(&fnhe_lock))); - fnhe_flush_routes(fnhe); - kfree_rcu(fnhe, rcu); - break; - } - fnhe_p = &fnhe->fnhe_next; - fnhe = rcu_dereference_protected(fnhe->fnhe_next, - lockdep_is_held(&fnhe_lock)); - } - - spin_unlock_bh(&fnhe_lock); -} - static void set_lwt_redirect(struct rtable *rth) { if (lwtunnel_output_redirect(rth->dst.lwtstate)) { @@ -1716,20 +1722,10 @@ static int __mkroute_input(struct sk_buff *skb, fnhe = find_exception(&FIB_RES_NH(*res), daddr); if (do_cache) { - if (fnhe) { + if (fnhe) rth = rcu_dereference(fnhe->fnhe_rth_input); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(&FIB_RES_NH(*res), daddr); - fnhe = NULL; - } else { - goto rt_cache; - } - } - - rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); - -rt_cache: + else + rth = rcu_dereference(FIB_RES_NH(*res).nh_rth_input); if (rt_cache_valid(rth)) { skb_dst_set_noref(skb, &rth->dst); goto out; @@ -2206,39 +2202,31 @@ static struct rtable *__mkroute_output(const struct fib_result *res, * the loopback interface and the IP_PKTINFO ipi_ifindex will * be set to the loopback interface as well. */ - fi = NULL; + do_cache = false; } fnhe = NULL; do_cache &= fi != NULL; - if (do_cache) { + if (fi) { struct rtable __rcu **prth; struct fib_nh *nh = &FIB_RES_NH(*res); fnhe = find_exception(nh, fl4->daddr); + if (!do_cache) + goto add; if (fnhe) { prth = &fnhe->fnhe_rth_output; - rth = rcu_dereference(*prth); - if (rth && rth->dst.expires && - time_after(jiffies, rth->dst.expires)) { - ip_del_fnhe(nh, fl4->daddr); - fnhe = NULL; - } else { - goto rt_cache; + } else { + if (unlikely(fl4->flowi4_flags & + FLOWI_FLAG_KNOWN_NH && + !(nh->nh_gw && + nh->nh_scope == RT_SCOPE_LINK))) { + do_cache = false; + goto add; } + prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); } - - if (unlikely(fl4->flowi4_flags & - FLOWI_FLAG_KNOWN_NH && - !(nh->nh_gw && - nh->nh_scope == RT_SCOPE_LINK))) { - do_cache = false; - goto add; - } - prth = raw_cpu_ptr(nh->nh_pcpu_rth_output); rth = rcu_dereference(*prth); - -rt_cache: if (rt_cache_valid(rth) && dst_hold_safe(&rth->dst)) return rth; } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b694fbf44a35..e3ece12f0250 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1194,7 +1194,8 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) uarg->zerocopy = 0; } - if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect)) { + if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && + !tp->repair) { err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); if (err == -EINPROGRESS && copied_syn > 0) goto out; diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 25c5a0b60cfc..9a0b952dd09b 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -802,7 +802,9 @@ static void bbr_update_min_rtt(struct sock *sk, const struct rate_sample *rs) } } } - bbr->idle_restart = 0; + /* Restart after idle ends only once we process a new S/ACK for data */ + if (rs->delivered > 0) + bbr->idle_restart = 0; } static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index c79fa6f6b758..b0ad62bd38f7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -413,9 +413,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score += 4; } @@ -978,8 +978,10 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) sock_tx_timestamp(sk, ipc.sockc.tsflags, &ipc.tx_flags); if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } @@ -1087,6 +1089,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) diff --git a/net/ipv6/route.c b/net/ipv6/route.c index e04c534b573e..7d50d889ab6e 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1222,11 +1222,16 @@ static void ip6_multipath_l3_keys(const struct sk_buff *skb, const struct ipv6hdr *inner_iph; const struct icmp6hdr *icmph; struct ipv6hdr _inner_iph; + struct icmp6hdr _icmph; if (likely(outer_iph->nexthdr != IPPROTO_ICMPV6)) goto out; - icmph = icmp6_hdr(skb); + icmph = skb_header_pointer(skb, skb_transport_offset(skb), + sizeof(_icmph), &_icmph); + if (!icmph) + goto out; + if (icmph->icmp6_type != ICMPV6_DEST_UNREACH && icmph->icmp6_type != ICMPV6_PKT_TOOBIG && icmph->icmp6_type != ICMPV6_TIME_EXCEED && diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 40d7234c27b9..0146dcdc5c40 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -164,9 +164,9 @@ static int compute_score(struct sock *sk, struct net *net, bool dev_match = (sk->sk_bound_dev_if == dif || sk->sk_bound_dev_if == sdif); - if (exact_dif && !dev_match) + if (!dev_match) return -1; - if (sk->sk_bound_dev_if && dev_match) + if (sk->sk_bound_dev_if) score++; } diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index fca69c3771f5..c28223d8092b 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -765,8 +765,6 @@ static int l2tp_nl_session_send(struct sk_buff *skb, u32 portid, u32 seq, int fl if ((session->ifname[0] && nla_put_string(skb, L2TP_ATTR_IFNAME, session->ifname)) || - (session->offset && - nla_put_u16(skb, L2TP_ATTR_OFFSET, session->offset)) || (session->cookie_len && nla_put(skb, L2TP_ATTR_COOKIE, session->cookie_len, &session->cookie[0])) || diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index cf41d9b4a0b8..b49f5afab405 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -930,6 +930,9 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (size > llc->dev->mtu) size = llc->dev->mtu; copied = size - hdrlen; + rc = -EINVAL; + if (copied < 0) + goto release; release_sock(sk); skb = sock_alloc_send_skb(sk, size, noblock, &rc); lock_sock(sk); diff --git a/net/nsh/nsh.c b/net/nsh/nsh.c index 58fb827439a8..6df6f58a8103 100644 --- a/net/nsh/nsh.c +++ b/net/nsh/nsh.c @@ -30,6 +30,8 @@ static struct sk_buff *nsh_gso_segment(struct sk_buff *skb, if (unlikely(!pskb_may_pull(skb, NSH_BASE_HDR_LEN))) goto out; nsh_len = nsh_hdr_len(nsh_hdr(skb)); + if (nsh_len < NSH_BASE_HDR_LEN) + goto out; if (unlikely(!pskb_may_pull(skb, nsh_len))) goto out; diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 0d9f6afa266c..4c9c9458374a 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -1404,13 +1404,10 @@ static void nlattr_set(struct nlattr *attr, u8 val, /* The nlattr stream should already have been validated */ nla_for_each_nested(nla, attr, rem) { - if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) { - if (tbl[nla_type(nla)].next) - tbl = tbl[nla_type(nla)].next; - nlattr_set(nla, val, tbl); - } else { + if (tbl[nla_type(nla)].len == OVS_ATTR_NESTED) + nlattr_set(nla, val, tbl[nla_type(nla)].next ? : tbl); + else memset(nla_data(nla), val, nla_len(nla)); - } if (nla_type(nla) == OVS_KEY_ATTR_CT_STATE) *(u32 *)nla_data(nla) &= CT_SUPPORTED_MASK; diff --git a/net/rds/recv.c b/net/rds/recv.c index b25bcfe411ca..555f07ccf0dc 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -558,6 +558,7 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, struct rds_cmsg_rx_trace t; int i, j; + memset(&t, 0, sizeof(t)); inc->i_rx_lat_trace[RDS_MSG_RX_CMSG] = local_clock(); t.rx_traces = rs->rs_rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 6d10b3af479b..821823b2518a 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -131,8 +131,11 @@ static int tcf_skbmod_init(struct net *net, struct nlattr *nla, if (exists && bind) return 0; - if (!lflags) + if (!lflags) { + if (exists) + tcf_idr_release(*a, bind); return -EINVAL; + } if (!exists) { ret = tcf_idr_create(tn, parm->index, est, a, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index c2fab4bcb8be..2f4e1483aced 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -151,8 +151,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, } else { err = -ENOENT; } - goto errout; #endif + goto errout; } tp->classify = tp->ops->classify; tp->protocol = protocol; diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 263d16e3219e..f50eb87cfe79 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -128,6 +128,28 @@ static bool fq_flow_is_detached(const struct fq_flow *f) return f->next == &detached; } +static bool fq_flow_is_throttled(const struct fq_flow *f) +{ + return f->next == &throttled; +} + +static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) +{ + if (head->first) + head->last->next = flow; + else + head->first = flow; + head->last = flow; + flow->next = NULL; +} + +static void fq_flow_unset_throttled(struct fq_sched_data *q, struct fq_flow *f) +{ + rb_erase(&f->rate_node, &q->delayed); + q->throttled_flows--; + fq_flow_add_tail(&q->old_flows, f); +} + static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) { struct rb_node **p = &q->delayed.rb_node, *parent = NULL; @@ -155,15 +177,6 @@ static void fq_flow_set_throttled(struct fq_sched_data *q, struct fq_flow *f) static struct kmem_cache *fq_flow_cachep __read_mostly; -static void fq_flow_add_tail(struct fq_flow_head *head, struct fq_flow *flow) -{ - if (head->first) - head->last->next = flow; - else - head->first = flow; - head->last = flow; - flow->next = NULL; -} /* limit number of collected flows per round */ #define FQ_GC_MAX 8 @@ -267,6 +280,8 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (fq_flow_is_throttled(f)) + fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; } return f; @@ -438,9 +453,7 @@ static void fq_check_throttled(struct fq_sched_data *q, u64 now) q->time_next_delayed_flow = f->time_next_packet; break; } - rb_erase(p, &q->delayed); - q->throttled_flows--; - fq_flow_add_tail(&q->old_flows, f); + fq_flow_unset_throttled(q, f); } } diff --git a/net/sctp/associola.c b/net/sctp/associola.c index dfb9651e818b..58f7d8cfd748 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -1025,8 +1025,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) struct sctp_endpoint *ep; struct sctp_chunk *chunk; struct sctp_inq *inqueue; - int state; + int first_time = 1; /* is this the first time through the loop */ int error = 0; + int state; /* The association should be held so we should be safe. */ ep = asoc->ep; @@ -1037,6 +1038,30 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) state = asoc->state; subtype = SCTP_ST_CHUNK(chunk->chunk_hdr->type); + /* If the first chunk in the packet is AUTH, do special + * processing specified in Section 6.3 of SCTP-AUTH spec + */ + if (first_time && subtype.chunk == SCTP_CID_AUTH) { + struct sctp_chunkhdr *next_hdr; + + next_hdr = sctp_inq_peek(inqueue); + if (!next_hdr) + goto normal; + + /* If the next chunk is COOKIE-ECHO, skip the AUTH + * chunk while saving a pointer to it so we can do + * Authentication later (during cookie-echo + * processing). + */ + if (next_hdr->type == SCTP_CID_COOKIE_ECHO) { + chunk->auth_chunk = skb_clone(chunk->skb, + GFP_ATOMIC); + chunk->auth = 1; + continue; + } + } + +normal: /* SCTP-AUTH, Section 6.3: * The receiver has a list of chunk types which it expects * to be received only after an AUTH-chunk. This list has @@ -1075,6 +1100,9 @@ static void sctp_assoc_bh_rcv(struct work_struct *work) /* If there is an error on chunk, discard this packet. */ if (error && chunk) chunk->pdiscard = 1; + + if (first_time) + first_time = 0; } sctp_association_put(asoc); } diff --git a/net/sctp/inqueue.c b/net/sctp/inqueue.c index 48392552ee7c..1aa89d4682f4 100644 --- a/net/sctp/inqueue.c +++ b/net/sctp/inqueue.c @@ -217,7 +217,7 @@ struct sctp_chunk *sctp_inq_pop(struct sctp_inq *queue) skb_pull(chunk->skb, sizeof(*ch)); chunk->subh.v = NULL; /* Subheader is no longer valid. */ - if (chunk->chunk_end + sizeof(*ch) < skb_tail_pointer(chunk->skb)) { + if (chunk->chunk_end + sizeof(*ch) <= skb_tail_pointer(chunk->skb)) { /* This is not a singleton */ chunk->singleton = 0; } else if (chunk->chunk_end > skb_tail_pointer(chunk->skb)) { diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 7219a1c041f7..853fecdf6374 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -865,6 +865,9 @@ static int sctp_inet6_cmp_addr(const union sctp_addr *addr1, if (sctp_is_any(sk, addr1) || sctp_is_any(sk, addr2)) return 1; + if (addr1->sa.sa_family == AF_INET && addr2->sa.sa_family == AF_INET) + return addr1->v4.sin_addr.s_addr == addr2->v4.sin_addr.s_addr; + return __sctp_v6_cmp_addr(addr1, addr2); } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 8f8ccded13e4..01b078172306 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -150,10 +150,7 @@ static enum sctp_disposition sctp_sf_violation_chunk( struct sctp_cmd_seq *commands); static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk); static enum sctp_disposition __sctp_sf_do_9_1_abort( @@ -618,6 +615,38 @@ enum sctp_disposition sctp_sf_do_5_1C_ack(struct net *net, return SCTP_DISPOSITION_CONSUME; } +static bool sctp_auth_chunk_verify(struct net *net, struct sctp_chunk *chunk, + const struct sctp_association *asoc) +{ + struct sctp_chunk auth; + + if (!chunk->auth_chunk) + return true; + + /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo + * is supposed to be authenticated and we have to do delayed + * authentication. We've just recreated the association using + * the information in the cookie and now it's much easier to + * do the authentication. + */ + + /* Make sure that we and the peer are AUTH capable */ + if (!net->sctp.auth_enable || !asoc->peer.auth_capable) + return false; + + /* set-up our fake chunk so that we can process it */ + auth.skb = chunk->auth_chunk; + auth.asoc = chunk->asoc; + auth.sctp_hdr = chunk->sctp_hdr; + auth.chunk_hdr = (struct sctp_chunkhdr *) + skb_push(chunk->auth_chunk, + sizeof(struct sctp_chunkhdr)); + skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); + auth.transport = chunk->transport; + + return sctp_sf_authenticate(asoc, &auth) == SCTP_IERROR_NO_ERROR; +} + /* * Respond to a normal COOKIE ECHO chunk. * We are the side that is being asked for an association. @@ -755,37 +784,9 @@ enum sctp_disposition sctp_sf_do_5_1D_ce(struct net *net, if (error) goto nomem_init; - /* SCTP-AUTH: auth_chunk pointer is only set when the cookie-echo - * is supposed to be authenticated and we have to do delayed - * authentication. We've just recreated the association using - * the information in the cookie and now it's much easier to - * do the authentication. - */ - if (chunk->auth_chunk) { - struct sctp_chunk auth; - enum sctp_ierror ret; - - /* Make sure that we and the peer are AUTH capable */ - if (!net->sctp.auth_enable || !new_asoc->peer.auth_capable) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } - - /* set-up our fake chunk so that we can process it */ - auth.skb = chunk->auth_chunk; - auth.asoc = chunk->asoc; - auth.sctp_hdr = chunk->sctp_hdr; - auth.chunk_hdr = (struct sctp_chunkhdr *) - skb_push(chunk->auth_chunk, - sizeof(struct sctp_chunkhdr)); - skb_pull(chunk->auth_chunk, sizeof(struct sctp_chunkhdr)); - auth.transport = chunk->transport; - - ret = sctp_sf_authenticate(net, ep, new_asoc, type, &auth); - if (ret != SCTP_IERROR_NO_ERROR) { - sctp_association_free(new_asoc); - return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); - } + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) { + sctp_association_free(new_asoc); + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); } repl = sctp_make_cookie_ack(new_asoc, chunk); @@ -1755,13 +1756,15 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( GFP_ATOMIC)) goto nomem; + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Make sure no new addresses are being added during the * restart. Though this is a pretty complicated attack * since you'd have to get inside the cookie. */ - if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) { + if (!sctp_sf_check_restart_addrs(new_asoc, asoc, chunk, commands)) return SCTP_DISPOSITION_CONSUME; - } /* If the endpoint is in the SHUTDOWN-ACK-SENT state and recognizes * the peer has restarted (Action A), it MUST NOT setup a new @@ -1867,6 +1870,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_b( GFP_ATOMIC)) goto nomem; + if (!sctp_auth_chunk_verify(net, chunk, new_asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -1961,6 +1967,9 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( * a COOKIE ACK. */ + if (!sctp_auth_chunk_verify(net, chunk, asoc)) + return SCTP_DISPOSITION_DISCARD; + /* Don't accidentally move back into established state. */ if (asoc->state < SCTP_STATE_ESTABLISHED) { sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, @@ -2000,7 +2009,7 @@ static enum sctp_disposition sctp_sf_do_dupcook_d( } } - repl = sctp_make_cookie_ack(new_asoc, chunk); + repl = sctp_make_cookie_ack(asoc, chunk); if (!repl) goto nomem; @@ -4111,10 +4120,7 @@ enum sctp_disposition sctp_sf_eat_fwd_tsn_fast( * The return value is the disposition of the chunk. */ static enum sctp_ierror sctp_sf_authenticate( - struct net *net, - const struct sctp_endpoint *ep, const struct sctp_association *asoc, - const union sctp_subtype type, struct sctp_chunk *chunk) { struct sctp_authhdr *auth_hdr; @@ -4212,7 +4218,7 @@ enum sctp_disposition sctp_sf_eat_auth(struct net *net, commands); auth_hdr = (struct sctp_authhdr *)chunk->skb->data; - error = sctp_sf_authenticate(net, ep, asoc, type, chunk); + error = sctp_sf_authenticate(asoc, chunk); switch (error) { case SCTP_IERROR_AUTH_BAD_HMAC: /* Generate the ERROR chunk and discard the rest diff --git a/net/sctp/ulpevent.c b/net/sctp/ulpevent.c index 5447228bf1a0..8538c96c96c1 100644 --- a/net/sctp/ulpevent.c +++ b/net/sctp/ulpevent.c @@ -717,7 +717,6 @@ struct sctp_ulpevent *sctp_ulpevent_make_rcvmsg(struct sctp_association *asoc, return event; fail_mark: - sctp_chunk_put(chunk); kfree_skb(skb); fail: return NULL; diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 282361ac0263..dfef930d1e50 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -87,6 +87,7 @@ int tls_push_sg(struct sock *sk, size = sg->length - offset; offset += sg->offset; + ctx->in_tcp_sendpages = true; while (1) { if (sg_is_last(sg)) sendpage_flags = flags; @@ -107,6 +108,7 @@ int tls_push_sg(struct sock *sk, offset -= sg->offset; ctx->partially_sent_offset = offset; ctx->partially_sent_record = (void *)sg; + ctx->in_tcp_sendpages = false; return ret; } @@ -121,6 +123,8 @@ int tls_push_sg(struct sock *sk, } clear_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + ctx->in_tcp_sendpages = false; + ctx->sk_write_space(sk); return 0; } @@ -190,6 +194,10 @@ static void tls_write_space(struct sock *sk) { struct tls_context *ctx = tls_get_ctx(sk); + /* We are already sending pages, ignore notification */ + if (ctx->in_tcp_sendpages) + return; + if (!sk->sk_write_pending && tls_is_pending_closed_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; int rc; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 3f6f6f8c9fa5..5b2409746ae0 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -518,7 +518,7 @@ int xfrm_trans_queue(struct sk_buff *skb, return -ENOBUFS; XFRM_TRANS_SKB_CB(skb)->finish = finish; - skb_queue_tail(&trans->queue, skb); + __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 8f13fb57eab5..6c4ec69e11a0 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -1345,6 +1345,7 @@ static struct xfrm_state *xfrm_state_clone(struct xfrm_state *orig, if (orig->aead) { x->aead = xfrm_algo_aead_clone(orig->aead); + x->geniv = orig->geniv; if (!x->aead) goto error; }