diff options
Diffstat (limited to 'net')
132 files changed, 1501 insertions, 1260 deletions
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 53b1955b027f..214532173536 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -182,10 +182,14 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, else if (dev->mtu > max_mtu) return -EINVAL; + /* Note: If this initial vlan_changelink() fails, we need + * to call vlan_dev_free_egress_priority() to free memory. + */ err = vlan_changelink(dev, tb, data, extack); - if (err) - return err; - err = register_vlan_dev(dev, extack); + + if (!err) + err = register_vlan_dev(dev, extack); + if (err) vlan_dev_free_egress_priority(dev); return err; diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index 95393bb2760b..4c7030ed8d33 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -1661,9 +1661,12 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { struct sock *sk = sock->sk; - struct sk_buff *skb; + struct sk_buff *skb, *last; + struct sk_buff_head *sk_queue; int copied; int err = 0; + int off = 0; + long timeo; lock_sock(sk); /* @@ -1675,10 +1678,29 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, goto out; } - /* Now we can treat all alike */ - skb = skb_recv_datagram(sk, flags, &err); - if (skb == NULL) - goto out; + /* We need support for non-blocking reads. */ + sk_queue = &sk->sk_receive_queue; + skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, &err, &last); + /* If no packet is available, release_sock(sk) and try again. */ + if (!skb) { + if (err != -EAGAIN) + goto out; + release_sock(sk); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + while (timeo && !__skb_wait_for_more_packets(sk, sk_queue, &err, + &timeo, last)) { + skb = __skb_try_recv_datagram(sk, sk_queue, flags, &off, + &err, &last); + if (skb) + break; + + if (err != -EAGAIN) + goto done; + } + if (!skb) + goto done; + lock_sock(sk); + } if (!sk_to_ax25(sk)->pidincl) skb_pull(skb, 1); /* Remove PID */ @@ -1725,6 +1747,7 @@ static int ax25_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, out: release_sock(sk); +done: return err; } diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index 59a5c1341c26..a0f99baafd35 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -571,6 +571,7 @@ int hci_dev_close(__u16 dev) goto done; } + cancel_work_sync(&hdev->power_on); if (hci_dev_test_and_clear_flag(hdev, HCI_AUTO_OFF)) cancel_delayed_work(&hdev->power_off); @@ -2675,6 +2676,8 @@ void hci_unregister_dev(struct hci_dev *hdev) list_del(&hdev->list); write_unlock(&hci_dev_list_lock); + cancel_work_sync(&hdev->power_on); + hci_cmd_sync_clear(hdev); if (!test_bit(HCI_QUIRK_NO_SUSPEND_NOTIFIER, &hdev->quirks)) diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 286d6767f017..c17021642234 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4088,7 +4088,6 @@ int hci_dev_close_sync(struct hci_dev *hdev) bt_dev_dbg(hdev, ""); - cancel_work_sync(&hdev->power_on); cancel_delayed_work(&hdev->power_off); cancel_delayed_work(&hdev->ncmd_timer); @@ -4974,6 +4973,9 @@ int hci_suspend_sync(struct hci_dev *hdev) return err; } + /* Update event mask so only the allowed event can wakeup the host */ + hci_set_event_mask_sync(hdev); + /* Only configure accept list if disconnect succeeded and wake * isn't being prevented. */ @@ -4985,9 +4987,6 @@ int hci_suspend_sync(struct hci_dev *hdev) /* Unpause to take care of updating scanning params */ hdev->scanning_paused = false; - /* Update event mask so only the allowed event can wakeup the host */ - hci_set_event_mask_sync(hdev); - /* Enable event filter for paired devices */ hci_update_event_filter_sync(hdev); diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index ae78490ecd3d..52668662ae8d 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -111,7 +111,8 @@ static struct l2cap_chan *__l2cap_get_chan_by_scid(struct l2cap_conn *conn, } /* Find channel with given SCID. - * Returns locked channel. */ + * Returns a reference locked channel. + */ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, u16 cid) { @@ -119,15 +120,19 @@ static struct l2cap_chan *l2cap_get_chan_by_scid(struct l2cap_conn *conn, mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_scid(conn, cid); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock); return c; } /* Find channel with given DCID. - * Returns locked channel. + * Returns a reference locked channel. */ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, u16 cid) @@ -136,8 +141,12 @@ static struct l2cap_chan *l2cap_get_chan_by_dcid(struct l2cap_conn *conn, mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_dcid(conn, cid); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock); return c; @@ -162,8 +171,12 @@ static struct l2cap_chan *l2cap_get_chan_by_ident(struct l2cap_conn *conn, mutex_lock(&conn->chan_lock); c = __l2cap_get_chan_by_ident(conn, ident); - if (c) - l2cap_chan_lock(c); + if (c) { + /* Only lock if chan reference is not 0 */ + c = l2cap_chan_hold_unless_zero(c); + if (c) + l2cap_chan_lock(c); + } mutex_unlock(&conn->chan_lock); return c; @@ -497,6 +510,16 @@ void l2cap_chan_hold(struct l2cap_chan *c) kref_get(&c->kref); } +struct l2cap_chan *l2cap_chan_hold_unless_zero(struct l2cap_chan *c) +{ + BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref)); + + if (!kref_get_unless_zero(&c->kref)) + return NULL; + + return c; +} + void l2cap_chan_put(struct l2cap_chan *c) { BT_DBG("chan %p orig refcnt %u", c, kref_read(&c->kref)); @@ -1968,7 +1991,10 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, src_match = !bacmp(&c->src, src); dst_match = !bacmp(&c->dst, dst); if (src_match && dst_match) { - l2cap_chan_hold(c); + c = l2cap_chan_hold_unless_zero(c); + if (!c) + continue; + read_unlock(&chan_list_lock); return c; } @@ -1983,7 +2009,7 @@ static struct l2cap_chan *l2cap_global_chan_by_psm(int state, __le16 psm, } if (c1) - l2cap_chan_hold(c1); + c1 = l2cap_chan_hold_unless_zero(c1); read_unlock(&chan_list_lock); @@ -4463,6 +4489,7 @@ static inline int l2cap_config_req(struct l2cap_conn *conn, unlock: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; } @@ -4577,6 +4604,7 @@ static inline int l2cap_config_rsp(struct l2cap_conn *conn, done: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return err; } @@ -5304,6 +5332,7 @@ send_move_response: l2cap_send_move_chan_rsp(chan, result); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5396,6 +5425,7 @@ static void l2cap_move_continue(struct l2cap_conn *conn, u16 icid, u16 result) } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, @@ -5425,6 +5455,7 @@ static void l2cap_move_fail(struct l2cap_conn *conn, u8 ident, u16 icid, l2cap_send_move_chan_cfm(chan, L2CAP_MC_UNCONFIRMED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static int l2cap_move_channel_rsp(struct l2cap_conn *conn, @@ -5488,6 +5519,7 @@ static int l2cap_move_channel_confirm(struct l2cap_conn *conn, l2cap_send_move_chan_cfm_rsp(conn, cmd->ident, icid); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5523,6 +5555,7 @@ static inline int l2cap_move_channel_confirm_rsp(struct l2cap_conn *conn, } l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -5895,12 +5928,11 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, if (credits > max_credits) { BT_ERR("LE credits overflow"); l2cap_send_disconn_req(chan, ECONNRESET); - l2cap_chan_unlock(chan); /* Return 0 so that we don't trigger an unnecessary * command reject packet. */ - return 0; + goto unlock; } chan->tx_credits += credits; @@ -5911,7 +5943,9 @@ static inline int l2cap_le_credits(struct l2cap_conn *conn, if (chan->tx_credits) chan->ops->resume(chan); +unlock: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); return 0; } @@ -7597,6 +7631,7 @@ drop: done: l2cap_chan_unlock(chan); + l2cap_chan_put(chan); } static void l2cap_conless_channel(struct l2cap_conn *conn, __le16 psm, @@ -8085,7 +8120,7 @@ static struct l2cap_chan *l2cap_global_fixed_chan(struct l2cap_chan *c, if (src_type != c->src_type) continue; - l2cap_chan_hold(c); + c = l2cap_chan_hold_unless_zero(c); read_unlock(&chan_list_lock); return c; } diff --git a/net/bluetooth/mgmt.c b/net/bluetooth/mgmt.c index ae758ab1b558..2f91a8c2b678 100644 --- a/net/bluetooth/mgmt.c +++ b/net/bluetooth/mgmt.c @@ -4723,7 +4723,6 @@ static int __add_adv_patterns_monitor(struct sock *sk, struct hci_dev *hdev, else status = MGMT_STATUS_FAILED; - mgmt_pending_remove(cmd); goto unlock; } diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 4fd882686b04..ff4779036649 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -1012,9 +1012,24 @@ int br_nf_hook_thresh(unsigned int hook, struct net *net, return okfn(net, sk, skb); ops = nf_hook_entries_get_hook_ops(e); - for (i = 0; i < e->num_hook_entries && - ops[i]->priority <= NF_BR_PRI_BRNF; i++) - ; + for (i = 0; i < e->num_hook_entries; i++) { + /* These hooks have already been called */ + if (ops[i]->priority < NF_BR_PRI_BRNF) + continue; + + /* These hooks have not been called yet, run them. */ + if (ops[i]->priority > NF_BR_PRI_BRNF) + break; + + /* take a closer look at NF_BR_PRI_BRNF. */ + if (ops[i]->hook == br_nf_pre_routing) { + /* This hook diverted the skb to this function, + * hooks after this have not been run yet. + */ + i++; + break; + } + } nf_hook_state_init(&state, hook, NFPROTO_BRIDGE, indev, outdev, sk, net, okfn); diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index bb01776d2d88..c96509c442a5 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -589,9 +589,13 @@ static int br_fill_ifinfo(struct sk_buff *skb, } done: + if (af) { + if (nlmsg_get_pos(skb) - (void *)af > nla_attr_size(0)) + nla_nest_end(skb, af); + else + nla_nest_cancel(skb, af); + } - if (af) - nla_nest_end(skb, af); nlmsg_end(skb, nlh); return 0; diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 251e666ba9a2..748be7253248 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -47,7 +47,7 @@ enum caif_states { struct caifsock { struct sock sk; /* must be first member */ struct cflayer layer; - u32 flow_state; + unsigned long flow_state; struct caif_connect_request conn_req; struct mutex readlock; struct dentry *debugfs_socket_dir; @@ -56,38 +56,32 @@ struct caifsock { static int rx_flow_is_on(struct caifsock *cf_sk) { - return test_bit(RX_FLOW_ON_BIT, - (void *) &cf_sk->flow_state); + return test_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state); } static int tx_flow_is_on(struct caifsock *cf_sk) { - return test_bit(TX_FLOW_ON_BIT, - (void *) &cf_sk->flow_state); + return test_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state); } static void set_rx_flow_off(struct caifsock *cf_sk) { - clear_bit(RX_FLOW_ON_BIT, - (void *) &cf_sk->flow_state); + clear_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state); } static void set_rx_flow_on(struct caifsock *cf_sk) { - set_bit(RX_FLOW_ON_BIT, - (void *) &cf_sk->flow_state); + set_bit(RX_FLOW_ON_BIT, &cf_sk->flow_state); } static void set_tx_flow_off(struct caifsock *cf_sk) { - clear_bit(TX_FLOW_ON_BIT, - (void *) &cf_sk->flow_state); + clear_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state); } static void set_tx_flow_on(struct caifsock *cf_sk) { - set_bit(TX_FLOW_ON_BIT, - (void *) &cf_sk->flow_state); + set_bit(TX_FLOW_ON_BIT, &cf_sk->flow_state); } static void caif_read_lock(struct sock *sk) diff --git a/net/can/bcm.c b/net/can/bcm.c index 65ee1b784a30..e60161bec850 100644 --- a/net/can/bcm.c +++ b/net/can/bcm.c @@ -100,6 +100,7 @@ static inline u64 get_u64(const struct canfd_frame *cp, int offset) struct bcm_op { struct list_head list; + struct rcu_head rcu; int ifindex; canid_t can_id; u32 flags; @@ -718,10 +719,9 @@ static struct bcm_op *bcm_find_op(struct list_head *ops, return NULL; } -static void bcm_remove_op(struct bcm_op *op) +static void bcm_free_op_rcu(struct rcu_head *rcu_head) { - hrtimer_cancel(&op->timer); - hrtimer_cancel(&op->thrtimer); + struct bcm_op *op = container_of(rcu_head, struct bcm_op, rcu); if ((op->frames) && (op->frames != &op->sframe)) kfree(op->frames); @@ -732,6 +732,14 @@ static void bcm_remove_op(struct bcm_op *op) kfree(op); } +static void bcm_remove_op(struct bcm_op *op) +{ + hrtimer_cancel(&op->timer); + hrtimer_cancel(&op->thrtimer); + + call_rcu(&op->rcu, bcm_free_op_rcu); +} + static void bcm_rx_unreg(struct net_device *dev, struct bcm_op *op) { if (op->rx_reg_dev == dev) { @@ -757,6 +765,9 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, if ((op->can_id == mh->can_id) && (op->ifindex == ifindex) && (op->flags & CAN_FD_FRAME) == (mh->flags & CAN_FD_FRAME)) { + /* disable automatic timer on frame reception */ + op->flags |= RX_NO_AUTOTIMER; + /* * Don't care if we're bound or not (due to netdev * problems) can_rx_unregister() is always a save @@ -785,7 +796,6 @@ static int bcm_delete_rx_op(struct list_head *ops, struct bcm_msg_head *mh, bcm_rx_handler, op); list_del(&op->list); - synchronize_rcu(); bcm_remove_op(op); return 1; /* done */ } diff --git a/net/compat.c b/net/compat.c index 210fc3b4d0d8..fe9be3c56ef7 100644 --- a/net/compat.c +++ b/net/compat.c @@ -34,20 +34,15 @@ #include <net/compat.h> int __get_compat_msghdr(struct msghdr *kmsg, - struct compat_msghdr __user *umsg, - struct sockaddr __user **save_addr, - compat_uptr_t *ptr, compat_size_t *len) + struct compat_msghdr *msg, + struct sockaddr __user **save_addr) { - struct compat_msghdr msg; ssize_t err; - if (copy_from_user(&msg, umsg, sizeof(*umsg))) - return -EFAULT; - - kmsg->msg_flags = msg.msg_flags; - kmsg->msg_namelen = msg.msg_namelen; + kmsg->msg_flags = msg->msg_flags; + kmsg->msg_namelen = msg->msg_namelen; - if (!msg.msg_name) + if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -57,15 +52,15 @@ int __get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); kmsg->msg_control_is_user = true; - kmsg->msg_control_user = compat_ptr(msg.msg_control); - kmsg->msg_controllen = msg.msg_controllen; + kmsg->msg_control_user = compat_ptr(msg->msg_control); + kmsg->msg_controllen = msg->msg_controllen; if (save_addr) - *save_addr = compat_ptr(msg.msg_name); + *save_addr = compat_ptr(msg->msg_name); - if (msg.msg_name && kmsg->msg_namelen) { + if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(compat_ptr(msg.msg_name), + err = move_addr_to_kernel(compat_ptr(msg->msg_name), kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -76,12 +71,11 @@ int __get_compat_msghdr(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (msg.msg_iovlen > UIO_MAXIOV) + if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; - *ptr = msg.msg_iov; - *len = msg.msg_iovlen; + kmsg->msg_ubuf = NULL; return 0; } @@ -90,15 +84,17 @@ int get_compat_msghdr(struct msghdr *kmsg, struct sockaddr __user **save_addr, struct iovec **iov) { - compat_uptr_t ptr; - compat_size_t len; + struct compat_msghdr msg; ssize_t err; - err = __get_compat_msghdr(kmsg, umsg, save_addr, &ptr, &len); + if (copy_from_user(&msg, umsg, sizeof(*umsg))) + return -EFAULT; + + err = __get_compat_msghdr(kmsg, &msg, save_addr); if (err) return err; - err = import_iovec(save_addr ? READ : WRITE, compat_ptr(ptr), len, + err = import_iovec(save_addr ? READ : WRITE, compat_ptr(msg.msg_iov), msg.msg_iovlen, UIO_FASTIOV, iov, &kmsg->msg_iter); return err < 0 ? err : 0; } diff --git a/net/core/datagram.c b/net/core/datagram.c index 50f4faeea76c..ecbc0f471089 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -613,10 +613,16 @@ fault: } EXPORT_SYMBOL(skb_copy_datagram_from_iter); -int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, - struct iov_iter *from, size_t length) +int __zerocopy_sg_from_iter(struct msghdr *msg, struct sock *sk, + struct sk_buff *skb, struct iov_iter *from, + size_t length) { - int frag = skb_shinfo(skb)->nr_frags; + int frag; + + if (msg && msg->msg_ubuf && msg->sg_from_iter) + return msg->sg_from_iter(sk, skb, from, length); + + frag = skb_shinfo(skb)->nr_frags; while (length && iov_iter_count(from)) { struct page *pages[MAX_SKB_FRAGS]; @@ -702,7 +708,7 @@ int zerocopy_sg_from_iter(struct sk_buff *skb, struct iov_iter *from) if (skb_copy_datagram_from_iter(skb, 0, from, copy)) return -EFAULT; - return __zerocopy_sg_from_iter(NULL, skb, from, ~0U); + return __zerocopy_sg_from_iter(NULL, NULL, skb, from, ~0U); } EXPORT_SYMBOL(zerocopy_sg_from_iter); diff --git a/net/core/dev.c b/net/core/dev.c index 08ce317fcec8..30a1603a7225 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -397,16 +397,18 @@ static void list_netdevice(struct net_device *dev) /* Device list removal * caller must respect a RCU grace period before freeing/reusing dev */ -static void unlist_netdevice(struct net_device *dev) +static void unlist_netdevice(struct net_device *dev, bool lock) { ASSERT_RTNL(); /* Unlink dev from the device chain */ - write_lock(&dev_base_lock); + if (lock) + write_lock(&dev_base_lock); list_del_rcu(&dev->dev_list); netdev_name_node_del(dev->name_node); hlist_del_rcu(&dev->index_hlist); - write_unlock(&dev_base_lock); + if (lock) + write_unlock(&dev_base_lock); dev_base_seq_inc(dev_net(dev)); } @@ -4861,7 +4863,10 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, } /* When doing generic XDP we have to bypass the qdisc layer and the - * network taps in order to match in-driver-XDP behavior. + * network taps in order to match in-driver-XDP behavior. This also means + * that XDP packets are able to starve other packets going through a qdisc, + * and DDOS attacks will be more effective. In-driver-XDP use dedicated TX + * queues, so they do not have this starvation issue. */ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) { @@ -4873,7 +4878,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) txq = netdev_core_pick_tx(dev, skb, NULL); cpu = smp_processor_id(); HARD_TX_LOCK(dev, txq, cpu); - if (!netif_xmit_stopped(txq)) { + if (!netif_xmit_frozen_or_drv_stopped(txq)) { rc = netdev_start_xmit(skb, dev, txq, 0); if (dev_xmit_complete(rc)) free_skb = false; @@ -4881,6 +4886,7 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) HARD_TX_UNLOCK(dev, txq); if (free_skb) { trace_xdp_exception(dev, xdp_prog, XDP_TX); + dev_core_stats_tx_dropped_inc(dev); kfree_skb(skb); } } @@ -10043,11 +10049,11 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) { - dev->reg_state = NETREG_UNREGISTERED; + write_lock(&dev_base_lock); + dev->reg_state = ret ? NETREG_UNREGISTERED : NETREG_REGISTERED; + write_unlock(&dev_base_lock); + if (ret) goto err_uninit; - } - dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); @@ -10329,7 +10335,9 @@ void netdev_run_todo(void) continue; } + write_lock(&dev_base_lock); dev->reg_state = NETREG_UNREGISTERED; + write_unlock(&dev_base_lock); linkwatch_forget_dev(dev); } @@ -10810,9 +10818,10 @@ void unregister_netdevice_many(struct list_head *head) list_for_each_entry(dev, head, unreg_list) { /* And unlink it from device chain. */ - unlist_netdevice(dev); - + write_lock(&dev_base_lock); + unlist_netdevice(dev, false); dev->reg_state = NETREG_UNREGISTERING; + write_unlock(&dev_base_lock); } flush_all_backlogs(); @@ -10959,7 +10968,7 @@ int __dev_change_net_namespace(struct net_device *dev, struct net *net, dev_close(dev); /* And unlink it from device chain */ - unlist_netdevice(dev); + unlist_netdevice(dev, true); synchronize_net(); diff --git a/net/core/filter.c b/net/core/filter.c index 5af58eb48587..7950f7520765 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -6158,7 +6158,6 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len if (err) return err; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); return seg6_lookup_nexthop(skb, NULL, 0); @@ -6516,10 +6515,21 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, ifindex, proto, netns_id, flags); if (sk) { - sk = sk_to_full_sk(sk); - if (!sk_fullsock(sk)) { + struct sock *sk2 = sk_to_full_sk(sk); + + /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk + * sock refcnt is decremented to prevent a request_sock leak. + */ + if (!sk_fullsock(sk2)) + sk2 = NULL; + if (sk2 != sk) { sock_gen_put(sk); - return NULL; + /* Ensure there is no need to bump sk2 refcnt */ + if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + return NULL; + } + sk = sk2; } } @@ -6553,10 +6563,21 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, flags); if (sk) { - sk = sk_to_full_sk(sk); - if (!sk_fullsock(sk)) { + struct sock *sk2 = sk_to_full_sk(sk); + + /* sk_to_full_sk() may return (sk)->rsk_listener, so make sure the original sk + * sock refcnt is decremented to prevent a request_sock leak. + */ + if (!sk_fullsock(sk2)) + sk2 = NULL; + if (sk2 != sk) { sock_gen_put(sk); - return NULL; + /* Ensure there is no need to bump sk2 refcnt */ + if (unlikely(sk2 && !sock_flag(sk2, SOCK_RCU_FREE))) { + WARN_ONCE(1, "Found non-RCU, unreferenced socket!"); + return NULL; + } + sk = sk2; } } @@ -7020,7 +7041,7 @@ BPF_CALL_5(bpf_tcp_check_syncookie, struct sock *, sk, void *, iph, u32, iph_len if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -EINVAL; if (!th->ack || th->rst || th->syn) @@ -7095,7 +7116,7 @@ BPF_CALL_5(bpf_tcp_gen_syncookie, struct sock *, sk, void *, iph, u32, iph_len, if (sk->sk_protocol != IPPROTO_TCP || sk->sk_state != TCP_LISTEN) return -EINVAL; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies)) return -ENOENT; if (!th->syn || th->ack || th->fin || th->rst) diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index e319e242dddf..a3642569fe53 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -33,6 +33,7 @@ static const char fmt_dec[] = "%d\n"; static const char fmt_ulong[] = "%lu\n"; static const char fmt_u64[] = "%llu\n"; +/* Caller holds RTNL or dev_base_lock */ static inline int dev_isalive(const struct net_device *dev) { return dev->reg_state <= NETREG_REGISTERED; diff --git a/net/core/secure_seq.c b/net/core/secure_seq.c index 5f85e01d4093..b0ff6153be62 100644 --- a/net/core/secure_seq.c +++ b/net/core/secure_seq.c @@ -64,7 +64,7 @@ u32 secure_tcpv6_ts_off(const struct net *net, .daddr = *(struct in6_addr *)daddr, }; - if (net->ipv4.sysctl_tcp_timestamps != 1) + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); @@ -120,7 +120,7 @@ EXPORT_SYMBOL(secure_ipv6_port_ephemeral); #ifdef CONFIG_INET u32 secure_tcp_ts_off(const struct net *net, __be32 saddr, __be32 daddr) { - if (net->ipv4.sysctl_tcp_timestamps != 1) + if (READ_ONCE(net->ipv4.sysctl_tcp_timestamps) != 1) return 0; ts_secret_init(); diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 5b3559cb1d82..cf4107d80bc4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -666,11 +666,18 @@ static void skb_release_data(struct sk_buff *skb) &shinfo->dataref)) goto exit; - skb_zcopy_clear(skb, true); + if (skb_zcopy(skb)) { + bool skip_unref = shinfo->flags & SKBFL_MANAGED_FRAG_REFS; + + skb_zcopy_clear(skb, true); + if (skip_unref) + goto free_head; + } for (i = 0; i < shinfo->nr_frags; i++) __skb_frag_unref(&shinfo->frags[i], skb->pp_recycle); +free_head: if (shinfo->frag_list) kfree_skb_list(shinfo->frag_list); @@ -895,7 +902,10 @@ EXPORT_SYMBOL(skb_dump); */ void skb_tx_error(struct sk_buff *skb) { - skb_zcopy_clear(skb, true); + if (skb) { + skb_zcopy_downgrade_managed(skb); + skb_zcopy_clear(skb, true); + } } EXPORT_SYMBOL(skb_tx_error); @@ -1193,7 +1203,7 @@ static struct ubuf_info *msg_zerocopy_alloc(struct sock *sk, size_t size) uarg->len = 1; uarg->bytelen = size; uarg->zerocopy = 1; - uarg->flags = SKBFL_ZEROCOPY_FRAG; + uarg->flags = SKBFL_ZEROCOPY_FRAG | SKBFL_DONT_ORPHAN; refcount_set(&uarg->refcnt, 1); sock_hold(sk); @@ -1212,6 +1222,10 @@ struct ubuf_info *msg_zerocopy_realloc(struct sock *sk, size_t size, const u32 byte_limit = 1 << 19; /* limit to a few TSO */ u32 bytelen, next; + /* there might be non MSG_ZEROCOPY users */ + if (uarg->callback != msg_zerocopy_callback) + return NULL; + /* realloc only when socket is locked (TCP, UDP cork), * so uarg->len and sk_zckey access is serialized */ @@ -1354,7 +1368,7 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, if (orig_uarg && uarg != orig_uarg) return -EEXIST; - err = __zerocopy_sg_from_iter(sk, skb, &msg->msg_iter, len); + err = __zerocopy_sg_from_iter(msg, sk, skb, &msg->msg_iter, len); if (err == -EFAULT || (err == -EMSGSIZE && skb->len == orig_len)) { struct sock *save_sk = skb->sk; @@ -1371,6 +1385,16 @@ int skb_zerocopy_iter_stream(struct sock *sk, struct sk_buff *skb, } EXPORT_SYMBOL_GPL(skb_zerocopy_iter_stream); +void __skb_zcopy_downgrade_managed(struct sk_buff *skb) +{ + int i; + + skb_shinfo(skb)->flags &= ~SKBFL_MANAGED_FRAG_REFS; + for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) + skb_frag_ref(skb, i); +} +EXPORT_SYMBOL_GPL(__skb_zcopy_downgrade_managed); + static int skb_zerocopy_clone(struct sk_buff *nskb, struct sk_buff *orig, gfp_t gfp_mask) { @@ -1688,6 +1712,8 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, BUG_ON(skb_shared(skb)); + skb_zcopy_downgrade_managed(skb); + size = SKB_DATA_ALIGN(size); if (skb_pfmemalloc(skb)) @@ -3484,6 +3510,8 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) int pos = skb_headlen(skb); const int zc_flags = SKBFL_SHARED_FRAG | SKBFL_PURE_ZEROCOPY; + skb_zcopy_downgrade_managed(skb); + skb_shinfo(skb1)->flags |= skb_shinfo(skb)->flags & zc_flags; skb_zerocopy_clone(skb1, skb, 0); if (len < pos) /* Split line is inside header. */ @@ -3837,6 +3865,7 @@ int skb_append_pagefrags(struct sk_buff *skb, struct page *page, if (skb_can_coalesce(skb, i, page, offset)) { skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], size); } else if (i < MAX_SKB_FRAGS) { + skb_zcopy_downgrade_managed(skb); get_page(page); skb_fill_page_desc(skb, i, page, offset, size); } else { diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 22b983ade0e7..b0fcd0200e84 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -699,6 +699,11 @@ struct sk_psock *sk_psock_init(struct sock *sk, int node) write_lock_bh(&sk->sk_callback_lock); + if (sk_is_inet(sk) && inet_csk_has_ulp(sk)) { + psock = ERR_PTR(-EINVAL); + goto out; + } + if (sk->sk_user_data) { psock = ERR_PTR(-EBUSY); goto out; diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 3f00a28fe762..5daa1fa54249 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -387,7 +387,7 @@ void reuseport_stop_listen_sock(struct sock *sk) prog = rcu_dereference_protected(reuse->prog, lockdep_is_held(&reuseport_lock)); - if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req || + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req) || (prog && prog->expected_attach_type == BPF_SK_REUSEPORT_SELECT_OR_MIGRATE)) { /* Migration capable, move sk from the listening section * to the closed section. @@ -545,7 +545,7 @@ struct sock *reuseport_migrate_sock(struct sock *sk, hash = migrating_sk->sk_hash; prog = rcu_dereference(reuse->prog); if (!prog || prog->expected_attach_type != BPF_SK_REUSEPORT_SELECT_OR_MIGRATE) { - if (sock_net(sk)->ipv4.sysctl_tcp_migrate_req) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_migrate_req)) goto select_by_hash; goto failure; } diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 2e78458900f2..eb8e128e43e8 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1120,12 +1120,6 @@ static int __init dccp_init(void) SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); if (!dccp_hashinfo.bind_bucket_cachep) goto out_free_hashinfo2; - dccp_hashinfo.bind2_bucket_cachep = - kmem_cache_create("dccp_bind2_bucket", - sizeof(struct inet_bind2_bucket), 0, - SLAB_HWCACHE_ALIGN | SLAB_ACCOUNT, NULL); - if (!dccp_hashinfo.bind2_bucket_cachep) - goto out_free_bind_bucket_cachep; /* * Size and allocate the main established and bind bucket @@ -1156,7 +1150,7 @@ static int __init dccp_init(void) if (!dccp_hashinfo.ehash) { DCCP_CRIT("Failed to allocate DCCP established hash table"); - goto out_free_bind2_bucket_cachep; + goto out_free_bind_bucket_cachep; } for (i = 0; i <= dccp_hashinfo.ehash_mask; i++) @@ -1182,23 +1176,14 @@ static int __init dccp_init(void) goto out_free_dccp_locks; } - dccp_hashinfo.bhash2 = (struct inet_bind2_hashbucket *) - __get_free_pages(GFP_ATOMIC | __GFP_NOWARN, bhash_order); - - if (!dccp_hashinfo.bhash2) { - DCCP_CRIT("Failed to allocate DCCP bind2 hash table"); - goto out_free_dccp_bhash; - } - for (i = 0; i < dccp_hashinfo.bhash_size; i++) { spin_lock_init(&dccp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&dccp_hashinfo.bhash[i].chain); - INIT_HLIST_HEAD(&dccp_hashinfo.bhash2[i].chain); } rc = dccp_mib_init(); if (rc) - goto out_free_dccp_bhash2; + goto out_free_dccp_bhash; rc = dccp_ackvec_init(); if (rc) @@ -1222,38 +1207,30 @@ out_ackvec_exit: dccp_ackvec_exit(); out_free_dccp_mib: dccp_mib_exit(); -out_free_dccp_bhash2: - free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); out_free_dccp_bhash: free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); out_free_dccp_locks: inet_ehash_locks_free(&dccp_hashinfo); out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); -out_free_bind2_bucket_cachep: - kmem_cache_destroy(dccp_hashinfo.bind2_bucket_cachep); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); out_free_hashinfo2: inet_hashinfo2_free_mod(&dccp_hashinfo); out_fail: dccp_hashinfo.bhash = NULL; - dccp_hashinfo.bhash2 = NULL; dccp_hashinfo.ehash = NULL; dccp_hashinfo.bind_bucket_cachep = NULL; - dccp_hashinfo.bind2_bucket_cachep = NULL; return rc; } static void __exit dccp_fini(void) { - int bhash_order = get_order(dccp_hashinfo.bhash_size * - sizeof(struct inet_bind_hashbucket)); - ccid_cleanup_builtins(); dccp_mib_exit(); - free_pages((unsigned long)dccp_hashinfo.bhash, bhash_order); - free_pages((unsigned long)dccp_hashinfo.bhash2, bhash_order); + free_pages((unsigned long)dccp_hashinfo.bhash, + get_order(dccp_hashinfo.bhash_size * + sizeof(struct inet_bind_hashbucket))); free_pages((unsigned long)dccp_hashinfo.ehash, get_order((dccp_hashinfo.ehash_mask + 1) * sizeof(struct inet_ehash_bucket))); diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index dc92a67baea3..7d542eb46172 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -480,8 +480,8 @@ static struct sock *dn_alloc_sock(struct net *net, struct socket *sock, gfp_t gf sk->sk_family = PF_DECnet; sk->sk_protocol = 0; sk->sk_allocation = gfp; - sk->sk_sndbuf = sysctl_decnet_wmem[1]; - sk->sk_rcvbuf = sysctl_decnet_rmem[1]; + sk->sk_sndbuf = READ_ONCE(sysctl_decnet_wmem[1]); + sk->sk_rcvbuf = READ_ONCE(sysctl_decnet_rmem[1]); /* Initialization of DECnet Session Control Port */ scp = DN_SK(sk); diff --git a/net/dsa/port.c b/net/dsa/port.c index 3738f2d40a0b..2dd76eb1621c 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -248,6 +248,7 @@ static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, struct netlink_ext_ack extack = {0}; bool change_vlan_filtering = false; struct dsa_switch *ds = dp->ds; + struct dsa_port *other_dp; bool vlan_filtering; int err; @@ -270,8 +271,8 @@ static void dsa_port_reset_vlan_filtering(struct dsa_port *dp, * VLAN-aware bridge. */ if (change_vlan_filtering && ds->vlan_filtering_is_global) { - dsa_switch_for_each_port(dp, ds) { - struct net_device *br = dsa_port_bridge_dev_get(dp); + dsa_switch_for_each_port(other_dp, ds) { + struct net_device *br = dsa_port_bridge_dev_get(other_dp); if (br && br_vlan_enabled(br)) { change_vlan_filtering = false; @@ -799,7 +800,7 @@ int dsa_port_vlan_filtering(struct dsa_port *dp, bool vlan_filtering, ds->vlan_filtering = vlan_filtering; dsa_switch_for_each_user_port(other_dp, ds) { - struct net_device *slave = dp->slave; + struct net_device *slave = other_dp->slave; /* We might be called in the unbind path, so not * all slave devices might still be registered. diff --git a/net/dsa/switch.c b/net/dsa/switch.c index 2b56218fc57c..4dfd68cf61c5 100644 --- a/net/dsa/switch.c +++ b/net/dsa/switch.c @@ -344,6 +344,7 @@ static int dsa_switch_do_lag_fdb_add(struct dsa_switch *ds, struct dsa_lag *lag, ether_addr_copy(a->addr, addr); a->vid = vid; + a->db = db; refcount_set(&a->refcount, 1); list_add_tail(&a->list, &lag->fdbs); diff --git a/net/ethtool/eeprom.c b/net/ethtool/eeprom.c index 7e6b37a54add..1c94bb8ea03f 100644 --- a/net/ethtool/eeprom.c +++ b/net/ethtool/eeprom.c @@ -36,7 +36,7 @@ static int fallback_set_params(struct eeprom_req_info *request, if (request->page) offset = request->page * ETH_MODULE_EEPROM_PAGE_LEN + offset; - if (modinfo->type == ETH_MODULE_SFF_8079 && + if (modinfo->type == ETH_MODULE_SFF_8472 && request->i2c_address == 0x51) offset += ETH_MODULE_EEPROM_PAGE_LEN * 2; diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 93da9f783bec..252c8bceaba4 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -217,7 +217,7 @@ int inet_listen(struct socket *sock, int backlog) * because the socket was in TCP_LISTEN state previously but * was shutdown() rather than close(). */ - tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); if ((tcp_fastopen & TFO_SERVER_WO_SOCKOPT1) && (tcp_fastopen & TFO_SERVER_ENABLE) && !inet_csk(sk)->icsk_accept_queue.fastopenq.max_qlen) { @@ -335,7 +335,7 @@ lookup_protocol: inet->hdrincl = 1; } - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; @@ -1246,7 +1246,7 @@ static int inet_sk_reselect_saddr(struct sock *sk) if (new_saddr == old_saddr) return 0; - if (sock_net(sk)->ipv4.sysctl_ip_dynaddr > 1) { + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) > 1) { pr_info("%s(): shifting inet->saddr from %pI4 to %pI4\n", __func__, &old_saddr, &new_saddr); } @@ -1301,7 +1301,7 @@ int inet_sk_rebuild_header(struct sock *sk) * Other protocols have to map its equivalent state to TCP_SYN_SENT. * DCCP maps its DCCP_REQUESTING state to TCP_SYN_SENT. -acme */ - if (!sock_net(sk)->ipv4.sysctl_ip_dynaddr || + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_ip_dynaddr) || sk->sk_state != TCP_SYN_SENT || (sk->sk_userlocks & SOCK_BINDADDR_LOCK) || (err = inet_sk_reselect_saddr(sk)) != 0) @@ -1710,24 +1710,14 @@ static const struct net_protocol igmp_protocol = { }; #endif -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol tcp_protocol = { - .early_demux = tcp_v4_early_demux, - .early_demux_handler = tcp_v4_early_demux, +static const struct net_protocol tcp_protocol = { .handler = tcp_v4_rcv, .err_handler = tcp_v4_err, .no_policy = 1, .icmp_strict_tag_validation = 1, }; -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct net_protocol udp_protocol = { - .early_demux = udp_v4_early_demux, - .early_demux_handler = udp_v4_early_demux, +static const struct net_protocol udp_protocol = { .handler = udp_rcv, .err_handler = udp_err, .no_policy = 1, diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 6eea1e9e998d..f8ad04470d3a 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -507,7 +507,7 @@ static int ah_init_state(struct xfrm_state *x) if (aalg_desc->uinfo.auth.icv_fullbits/8 != crypto_ahash_digestsize(ahash)) { - pr_info("%s: %s digestsize %u != %hu\n", + pr_info("%s: %s digestsize %u != %u\n", __func__, x->aalg->alg_name, crypto_ahash_digestsize(ahash), aalg_desc->uinfo.auth.icv_fullbits / 8); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 62d5f99760aa..6cd3b6c559f0 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -239,7 +239,7 @@ static int cipso_v4_cache_check(const unsigned char *key, struct cipso_v4_map_cache_entry *prev_entry = NULL; u32 hash; - if (!cipso_v4_cache_enabled) + if (!READ_ONCE(cipso_v4_cache_enabled)) return -ENOENT; hash = cipso_v4_map_cache_hash(key, key_len); @@ -296,13 +296,14 @@ static int cipso_v4_cache_check(const unsigned char *key, int cipso_v4_cache_add(const unsigned char *cipso_ptr, const struct netlbl_lsm_secattr *secattr) { + int bkt_size = READ_ONCE(cipso_v4_cache_bucketsize); int ret_val = -EPERM; u32 bkt; struct cipso_v4_map_cache_entry *entry = NULL; struct cipso_v4_map_cache_entry *old_entry = NULL; u32 cipso_ptr_len; - if (!cipso_v4_cache_enabled || cipso_v4_cache_bucketsize <= 0) + if (!READ_ONCE(cipso_v4_cache_enabled) || bkt_size <= 0) return 0; cipso_ptr_len = cipso_ptr[1]; @@ -322,7 +323,7 @@ int cipso_v4_cache_add(const unsigned char *cipso_ptr, bkt = entry->hash & (CIPSO_V4_CACHE_BUCKETS - 1); spin_lock_bh(&cipso_v4_cache[bkt].lock); - if (cipso_v4_cache[bkt].size < cipso_v4_cache_bucketsize) { + if (cipso_v4_cache[bkt].size < bkt_size) { list_add(&entry->list, &cipso_v4_cache[bkt].list); cipso_v4_cache[bkt].size += 1; } else { @@ -1199,7 +1200,8 @@ static int cipso_v4_gentag_rbm(const struct cipso_v4_doi *doi_def, /* This will send packets using the "optimized" format when * possible as specified in section 3.4.2.6 of the * CIPSO draft. */ - if (cipso_v4_rbm_optfmt && ret_val > 0 && ret_val <= 10) + if (READ_ONCE(cipso_v4_rbm_optfmt) && ret_val > 0 && + ret_val <= 10) tag_len = 14; else tag_len = 4 + ret_val; @@ -1603,7 +1605,7 @@ int cipso_v4_validate(const struct sk_buff *skb, unsigned char **option) * all the CIPSO validations here but it doesn't * really specify _exactly_ what we need to validate * ... so, just make it a sysctl tunable. */ - if (cipso_v4_rbm_strictvalid) { + if (READ_ONCE(cipso_v4_rbm_strictvalid)) { if (cipso_v4_map_lvl_valid(doi_def, tag[3]) < 0) { err_offset = opt_iter + 3; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index b21238df3301..b694f352ce7a 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -1108,7 +1108,7 @@ static int esp_init_authenc(struct xfrm_state *x) err = -EINVAL; if (aalg_desc->uinfo.auth.icv_fullbits / 8 != crypto_aead_authsize(aead)) { - pr_info("ESP: %s digestsize %u != %hu\n", + pr_info("ESP: %s digestsize %u != %u\n", x->aalg->alg_name, crypto_aead_authsize(aead), aalg_desc->uinfo.auth.icv_fullbits / 8); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a57ba23571c9..db7b2503f068 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1230,7 +1230,7 @@ static int fib_check_nh_nongw(struct net *net, struct fib_nh *nh, nh->fib_nh_dev = in_dev->dev; dev_hold_track(nh->fib_nh_dev, &nh->fib_nh_dev_tracker, GFP_ATOMIC); - nh->fib_nh_scope = RT_SCOPE_HOST; + nh->fib_nh_scope = RT_SCOPE_LINK; if (!netif_carrier_ok(nh->fib_nh_dev)) nh->fib_nh_flags |= RTNH_F_LINKDOWN; err = 0; @@ -1811,7 +1811,7 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; if (nexthop_is_blackhole(fi->nh)) rtm->rtm_type = RTN_BLACKHOLE; - if (!fi->fib_net->ipv4.sysctl_nexthop_compat_mode) + if (!READ_ONCE(fi->fib_net->ipv4.sysctl_nexthop_compat_mode)) goto offload; } @@ -2216,7 +2216,7 @@ void fib_select_multipath(struct fib_result *res, int hash) } change_nexthops(fi) { - if (net->ipv4.sysctl_fib_multipath_use_neigh) { + if (READ_ONCE(net->ipv4.sysctl_fib_multipath_use_neigh)) { if (!fib_good_nh(nexthop_nh)) continue; if (!first) { diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 2734c3af7e24..452ff177e4da 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -498,7 +498,7 @@ static void tnode_free(struct key_vector *tn) tn = container_of(head, struct tnode, rcu)->kv; } - if (tnode_free_size >= sysctl_fib_sync_mem) { + if (tnode_free_size >= READ_ONCE(sysctl_fib_sync_mem)) { tnode_free_size = 0; synchronize_rcu(); } @@ -1042,6 +1042,7 @@ fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) { + u8 fib_notify_on_flag_change; struct fib_alias *fa_match; struct sk_buff *skb; int err; @@ -1063,14 +1064,16 @@ void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) WRITE_ONCE(fa_match->offload, fri->offload); WRITE_ONCE(fa_match->trap, fri->trap); + fib_notify_on_flag_change = READ_ONCE(net->ipv4.sysctl_fib_notify_on_flag_change); + /* 2 means send notifications only if offload_failed was changed. */ - if (net->ipv4.sysctl_fib_notify_on_flag_change == 2 && + if (fib_notify_on_flag_change == 2 && READ_ONCE(fa_match->offload_failed) == fri->offload_failed) goto out; WRITE_ONCE(fa_match->offload_failed, fri->offload_failed); - if (!net->ipv4.sysctl_fib_notify_on_flag_change) + if (!fib_notify_on_flag_change) goto out; skb = nlmsg_new(fib_nlmsg_size(fa_match->fa_info), GFP_ATOMIC); diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index efea0e796f06..d5d745c3e345 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -253,11 +253,12 @@ bool icmp_global_allow(void) spin_lock(&icmp_global.lock); delta = min_t(u32, now - icmp_global.stamp, HZ); if (delta >= HZ / 50) { - incr = sysctl_icmp_msgs_per_sec * delta / HZ ; + incr = READ_ONCE(sysctl_icmp_msgs_per_sec) * delta / HZ; if (incr) WRITE_ONCE(icmp_global.stamp, now); } - credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); + credit = min_t(u32, icmp_global.credit + incr, + READ_ONCE(sysctl_icmp_msgs_burst)); if (credit) { /* We want to use a credit of one in average, but need to randomize * it for security reasons. @@ -281,7 +282,7 @@ static bool icmpv4_mask_allow(struct net *net, int type, int code) return true; /* Limit if icmp type is enabled in ratemask. */ - if (!((1 << type) & net->ipv4.sysctl_icmp_ratemask)) + if (!((1 << type) & READ_ONCE(net->ipv4.sysctl_icmp_ratemask))) return true; return false; @@ -319,7 +320,8 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, vif = l3mdev_master_ifindex(dst->dev); peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); - rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); + rc = inet_peer_xrlim_allow(peer, + READ_ONCE(net->ipv4.sysctl_icmp_ratelimit)); if (peer) inet_putpeer(peer); out: @@ -692,7 +694,7 @@ void __icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info, rcu_read_lock(); if (rt_is_input_route(rt) && - net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr) + READ_ONCE(net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr)) dev = dev_get_by_index_rcu(net, inet_iif(skb_in)); if (dev) @@ -879,7 +881,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) * values please see * Documentation/networking/ip-sysctl.rst */ - switch (net->ipv4.sysctl_ip_no_pmtu_disc) { + switch (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) { default: net_dbg_ratelimited("%pI4: fragmentation needed and DF set\n", &iph->daddr); @@ -932,7 +934,7 @@ static enum skb_drop_reason icmp_unreach(struct sk_buff *skb) * get the other vendor to fix their kit. */ - if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && + if (!READ_ONCE(net->ipv4.sysctl_icmp_ignore_bogus_error_responses) && inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, @@ -992,7 +994,7 @@ static enum skb_drop_reason icmp_echo(struct sk_buff *skb) net = dev_net(skb_dst(skb)->dev); /* should there be an ICMP stat for ignored echos? */ - if (net->ipv4.sysctl_icmp_echo_ignore_all) + if (READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_all)) return SKB_NOT_DROPPED_YET; icmp_param.data.icmph = *icmp_hdr(skb); @@ -1027,7 +1029,7 @@ bool icmp_build_probe(struct sk_buff *skb, struct icmphdr *icmphdr) u16 ident_len; u8 status; - if (!net->ipv4.sysctl_icmp_echo_enable_probe) + if (!READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) return false; /* We currently only support probing interfaces on the proxy node @@ -1248,7 +1250,7 @@ int icmp_rcv(struct sk_buff *skb) */ if ((icmph->type == ICMP_ECHO || icmph->type == ICMP_TIMESTAMP) && - net->ipv4.sysctl_icmp_echo_ignore_broadcasts) { + READ_ONCE(net->ipv4.sysctl_icmp_echo_ignore_broadcasts)) { reason = SKB_DROP_REASON_INVALID_PROTO; goto error; } diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index b65d074d9620..e3ab0cb61624 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -467,7 +467,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; - if (ipv4_is_local_multicast(pmc->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(pmc->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return skb; mtu = READ_ONCE(dev->mtu); @@ -593,7 +594,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(pmc->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -736,7 +737,8 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return 0; if (type == IGMP_HOST_LEAVE_MESSAGE) @@ -825,7 +827,7 @@ static void igmp_ifc_event(struct in_device *in_dev) struct net *net = dev_net(in_dev->dev); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) return; - WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv); + WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv)); igmp_ifc_start_timer(in_dev, 1); } @@ -920,7 +922,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return false; - if (ipv4_is_local_multicast(group) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(group) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return false; rcu_read_lock(); @@ -1006,7 +1009,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * received value was zero, use the default or statically * configured value. */ - in_dev->mr_qrv = ih3->qrv ?: net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qrv = ih3->qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); in_dev->mr_qi = IGMPV3_QQIC(ih3->qqic)*HZ ?: IGMP_QUERY_INTERVAL; /* RFC3376, 8.3. Query Response Interval: @@ -1045,7 +1048,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; spin_lock_bh(&im->lock); if (im->tm_running) @@ -1186,7 +1189,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, pmc->interface = im->interface; in_dev_hold(in_dev); pmc->multiaddr = im->multiaddr; - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); pmc->sfmode = im->sfmode; if (pmc->sfmode == MCAST_INCLUDE) { struct ip_sf_list *psf; @@ -1237,9 +1240,11 @@ static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im) swap(im->tomb, pmc->tomb); swap(im->sources, pmc->sources); for (psf = im->sources; psf; psf = psf->sf_next) - psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); } else { - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: + READ_ONCE(net->ipv4.sysctl_igmp_qrv); } in_dev_put(pmc->interface); kfree_pmc(pmc); @@ -1296,7 +1301,8 @@ static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; reporter = im->reporter; @@ -1338,13 +1344,14 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (ipv4_is_local_multicast(im->multiaddr) && !net->ipv4.sysctl_igmp_llm_reports) + if (ipv4_is_local_multicast(im->multiaddr) && + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) return; if (in_dev->dead) return; - im->unsolicit_count = net->ipv4.sysctl_igmp_qrv; + im->unsolicit_count = READ_ONCE(net->ipv4.sysctl_igmp_qrv); if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { spin_lock_bh(&im->lock); igmp_start_timer(im, IGMP_INITIAL_REPORT_DELAY); @@ -1358,7 +1365,7 @@ static void igmp_group_added(struct ip_mc_list *im) * IN() to IN(A). */ if (im->sfmode == MCAST_EXCLUDE) - im->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + im->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); igmp_ifc_event(in_dev); #endif @@ -1642,7 +1649,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) if (im->multiaddr == IGMP_ALL_HOSTS) continue; if (ipv4_is_local_multicast(im->multiaddr) && - !net->ipv4.sysctl_igmp_llm_reports) + !READ_ONCE(net->ipv4.sysctl_igmp_llm_reports)) continue; /* a failover is happening and switches @@ -1749,7 +1756,7 @@ static void ip_mc_reset(struct in_device *in_dev) in_dev->mr_qi = IGMP_QUERY_INTERVAL; in_dev->mr_qri = IGMP_QUERY_RESPONSE_INTERVAL; - in_dev->mr_qrv = net->ipv4.sysctl_igmp_qrv; + in_dev->mr_qrv = READ_ONCE(net->ipv4.sysctl_igmp_qrv); } #else static void ip_mc_reset(struct in_device *in_dev) @@ -1883,7 +1890,7 @@ static int ip_mc_del1_src(struct ip_mc_list *pmc, int sfmode, #ifdef CONFIG_IP_MULTICAST if (psf->sf_oldin && !IGMP_V1_SEEN(in_dev) && !IGMP_V2_SEEN(in_dev)) { - psf->sf_crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + psf->sf_crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); psf->sf_next = pmc->tomb; pmc->tomb = psf; rv = 1; @@ -1947,7 +1954,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, /* filter mode change */ pmc->sfmode = MCAST_INCLUDE; #ifdef CONFIG_IP_MULTICAST - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -2126,7 +2133,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, #ifdef CONFIG_IP_MULTICAST /* else no filters; keep old mode for reports */ - pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv; + pmc->crcount = in_dev->mr_qrv ?: READ_ONCE(net->ipv4.sysctl_igmp_qrv); WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount); for (psf = pmc->sources; psf; psf = psf->sf_next) psf->sf_crcount = 0; @@ -2192,7 +2199,7 @@ static int __ip_mc_join_group(struct sock *sk, struct ip_mreqn *imr, count++; } err = -ENOBUFS; - if (count >= net->ipv4.sysctl_igmp_max_memberships) + if (count >= READ_ONCE(net->ipv4.sysctl_igmp_max_memberships)) goto done; iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (!iml) @@ -2379,7 +2386,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } /* else, add a new source to the filter */ - if (psl && psl->sl_count >= net->ipv4.sysctl_igmp_max_msf) { + if (psl && psl->sl_count >= READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { err = -ENOBUFS; goto done; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c0b7e6c21360..eb31c7158b39 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -117,32 +117,6 @@ bool inet_rcv_saddr_any(const struct sock *sk) return !sk->sk_rcv_saddr; } -static bool use_bhash2_on_bind(const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - int addr_type; - - if (sk->sk_family == AF_INET6) { - addr_type = ipv6_addr_type(&sk->sk_v6_rcv_saddr); - return addr_type != IPV6_ADDR_ANY && - addr_type != IPV6_ADDR_MAPPED; - } -#endif - return sk->sk_rcv_saddr != htonl(INADDR_ANY); -} - -static u32 get_bhash2_nulladdr_hash(const struct sock *sk, struct net *net, - int port) -{ -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr nulladdr = {}; - - if (sk->sk_family == AF_INET6) - return ipv6_portaddr_hash(net, &nulladdr, port); -#endif - return ipv4_portaddr_hash(net, 0, port); -} - void inet_get_local_port_range(struct net *net, int *low, int *high) { unsigned int seq; @@ -156,71 +130,16 @@ void inet_get_local_port_range(struct net *net, int *low, int *high) } EXPORT_SYMBOL(inet_get_local_port_range); -static bool bind_conflict_exist(const struct sock *sk, struct sock *sk2, - kuid_t sk_uid, bool relax, - bool reuseport_cb_ok, bool reuseport_ok) -{ - int bound_dev_if2; - - if (sk == sk2) - return false; - - bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); - - if (!sk->sk_bound_dev_if || !bound_dev_if2 || - sk->sk_bound_dev_if == bound_dev_if2) { - if (sk->sk_reuse && sk2->sk_reuse && - sk2->sk_state != TCP_LISTEN) { - if (!relax || (!reuseport_ok && sk->sk_reuseport && - sk2->sk_reuseport && reuseport_cb_ok && - (sk2->sk_state == TCP_TIME_WAIT || - uid_eq(sk_uid, sock_i_uid(sk2))))) - return true; - } else if (!reuseport_ok || !sk->sk_reuseport || - !sk2->sk_reuseport || !reuseport_cb_ok || - (sk2->sk_state != TCP_TIME_WAIT && - !uid_eq(sk_uid, sock_i_uid(sk2)))) { - return true; - } - } - return false; -} - -static bool check_bhash2_conflict(const struct sock *sk, - struct inet_bind2_bucket *tb2, kuid_t sk_uid, - bool relax, bool reuseport_cb_ok, - bool reuseport_ok) -{ - struct sock *sk2; - - sk_for_each_bound_bhash2(sk2, &tb2->owners) { - if (sk->sk_family == AF_INET && ipv6_only_sock(sk2)) - continue; - - if (bind_conflict_exist(sk, sk2, sk_uid, relax, - reuseport_cb_ok, reuseport_ok)) - return true; - } - return false; -} - -/* This should be called only when the corresponding inet_bind_bucket spinlock - * is held - */ -static int inet_csk_bind_conflict(const struct sock *sk, int port, - struct inet_bind_bucket *tb, - struct inet_bind2_bucket *tb2, /* may be null */ +static int inet_csk_bind_conflict(const struct sock *sk, + const struct inet_bind_bucket *tb, bool relax, bool reuseport_ok) { - struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - kuid_t uid = sock_i_uid((struct sock *)sk); - struct sock_reuseport *reuseport_cb; - struct inet_bind2_hashbucket *head2; - bool reuseport_cb_ok; struct sock *sk2; - struct net *net; - int l3mdev; - u32 hash; + bool reuseport_cb_ok; + bool reuse = sk->sk_reuse; + bool reuseport = !!sk->sk_reuseport; + struct sock_reuseport *reuseport_cb; + kuid_t uid = sock_i_uid((struct sock *)sk); rcu_read_lock(); reuseport_cb = rcu_dereference(sk->sk_reuseport_cb); @@ -231,42 +150,40 @@ static int inet_csk_bind_conflict(const struct sock *sk, int port, /* * Unlike other sk lookup places we do not check * for sk_net here, since _all_ the socks listed - * in tb->owners and tb2->owners list belong - * to the same net + * in tb->owners list belong to the same net - the + * one this bucket belongs to. */ - if (!use_bhash2_on_bind(sk)) { - sk_for_each_bound(sk2, &tb->owners) - if (bind_conflict_exist(sk, sk2, uid, relax, - reuseport_cb_ok, reuseport_ok) && - inet_rcv_saddr_equal(sk, sk2, true)) - return true; + sk_for_each_bound(sk2, &tb->owners) { + int bound_dev_if2; - return false; + if (sk == sk2) + continue; + bound_dev_if2 = READ_ONCE(sk2->sk_bound_dev_if); + if ((!sk->sk_bound_dev_if || + !bound_dev_if2 || + sk->sk_bound_dev_if == bound_dev_if2)) { + if (reuse && sk2->sk_reuse && + sk2->sk_state != TCP_LISTEN) { + if ((!relax || + (!reuseport_ok && + reuseport && sk2->sk_reuseport && + reuseport_cb_ok && + (sk2->sk_state == TCP_TIME_WAIT || + uid_eq(uid, sock_i_uid(sk2))))) && + inet_rcv_saddr_equal(sk, sk2, true)) + break; + } else if (!reuseport_ok || + !reuseport || !sk2->sk_reuseport || + !reuseport_cb_ok || + (sk2->sk_state != TCP_TIME_WAIT && + !uid_eq(uid, sock_i_uid(sk2)))) { + if (inet_rcv_saddr_equal(sk, sk2, true)) + break; + } + } } - - if (tb2 && check_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) - return true; - - net = sock_net(sk); - - /* check there's no conflict with an existing IPV6_ADDR_ANY (if ipv6) or - * INADDR_ANY (if ipv4) socket. - */ - hash = get_bhash2_nulladdr_hash(sk, net, port); - head2 = &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; - - l3mdev = inet_sk_bound_l3mdev(sk); - inet_bind_bucket_for_each(tb2, &head2->chain) - if (check_bind2_bucket_match_nulladdr(tb2, net, port, l3mdev, sk)) - break; - - if (tb2 && check_bhash2_conflict(sk, tb2, uid, relax, reuseport_cb_ok, - reuseport_ok)) - return true; - - return false; + return sk2 != NULL; } /* @@ -274,20 +191,16 @@ static int inet_csk_bind_conflict(const struct sock *sk, int port, * inet_bind_hashbucket lock held. */ static struct inet_bind_hashbucket * -inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, - struct inet_bind2_bucket **tb2_ret, - struct inet_bind2_hashbucket **head2_ret, int *port_ret) +inet_csk_find_open_port(struct sock *sk, struct inet_bind_bucket **tb_ret, int *port_ret) { struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - struct inet_bind2_hashbucket *head2; + int port = 0; struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); + bool relax = false; int i, low, high, attempt_half; - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; u32 remaining, offset; - bool relax = false; - int port = 0; int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); @@ -326,12 +239,10 @@ other_parity_scan: head = &hinfo->bhash[inet_bhashfn(net, port, hinfo->bhash_size)]; spin_lock_bh(&head->lock); - tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, - &head2); inet_bind_bucket_for_each(tb, &head->chain) - if (check_bind_bucket_match(tb, net, port, l3mdev)) { - if (!inet_csk_bind_conflict(sk, port, tb, tb2, - relax, false)) + if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && + tb->port == port) { + if (!inet_csk_bind_conflict(sk, tb, relax, false)) goto success; goto next_port; } @@ -352,7 +263,7 @@ next_port: goto other_half_scan; } - if (net->ipv4.sysctl_ip_autobind_reuse && !relax) { + if (READ_ONCE(net->ipv4.sysctl_ip_autobind_reuse) && !relax) { /* We still have a chance to connect to different destinations */ relax = true; goto ports_exhausted; @@ -361,8 +272,6 @@ next_port: success: *port_ret = port; *tb_ret = tb; - *tb2_ret = tb2; - *head2_ret = head2; return head; } @@ -458,81 +367,54 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) { bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; struct inet_hashinfo *hinfo = sk->sk_prot->h.hashinfo; - bool bhash_created = false, bhash2_created = false; - struct inet_bind2_bucket *tb2 = NULL; - struct inet_bind2_hashbucket *head2; - struct inet_bind_bucket *tb = NULL; + int ret = 1, port = snum; struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); - int ret = 1, port = snum; - bool found_port = false; + struct inet_bind_bucket *tb = NULL; int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); if (!port) { - head = inet_csk_find_open_port(sk, &tb, &tb2, &head2, &port); + head = inet_csk_find_open_port(sk, &tb, &port); if (!head) return ret; - if (tb && tb2) - goto success; - found_port = true; - } else { - head = &hinfo->bhash[inet_bhashfn(net, port, - hinfo->bhash_size)]; - spin_lock_bh(&head->lock); - inet_bind_bucket_for_each(tb, &head->chain) - if (check_bind_bucket_match(tb, net, port, l3mdev)) - break; - - tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, - &head2); - } - - if (!tb) { - tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, net, - head, port, l3mdev); if (!tb) - goto fail_unlock; - bhash_created = true; - } - - if (!tb2) { - tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, - net, head2, port, l3mdev, sk); - if (!tb2) - goto fail_unlock; - bhash2_created = true; + goto tb_not_found; + goto success; } - - /* If we had to find an open port, we already checked for conflicts */ - if (!found_port && !hlist_empty(&tb->owners)) { + head = &hinfo->bhash[inet_bhashfn(net, port, + hinfo->bhash_size)]; + spin_lock_bh(&head->lock); + inet_bind_bucket_for_each(tb, &head->chain) + if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && + tb->port == port) + goto tb_found; +tb_not_found: + tb = inet_bind_bucket_create(hinfo->bind_bucket_cachep, + net, head, port, l3mdev); + if (!tb) + goto fail_unlock; +tb_found: + if (!hlist_empty(&tb->owners)) { if (sk->sk_reuse == SK_FORCE_REUSE) goto success; if ((tb->fastreuse > 0 && reuse) || sk_reuseport_match(tb, sk)) goto success; - if (inet_csk_bind_conflict(sk, port, tb, tb2, true, true)) + if (inet_csk_bind_conflict(sk, tb, true, true)) goto fail_unlock; } success: inet_csk_update_fastreuse(tb, sk); if (!inet_csk(sk)->icsk_bind_hash) - inet_bind_hash(sk, tb, tb2, port); + inet_bind_hash(sk, tb, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); - WARN_ON(inet_csk(sk)->icsk_bind2_hash != tb2); ret = 0; fail_unlock: - if (ret) { - if (bhash_created) - inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - if (bhash2_created) - inet_bind2_bucket_destroy(hinfo->bind2_bucket_cachep, - tb2); - } spin_unlock_bh(&head->lock); return ret; } @@ -951,7 +833,8 @@ static void reqsk_timer_handler(struct timer_list *t) icsk = inet_csk(sk_listener); net = sock_net(sk_listener); - max_syn_ack_retries = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_synack_retries; + max_syn_ack_retries = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_synack_retries); /* Normally all the openreqs are young and become mature * (i.e. converted to established socket) for first timeout. * If synack was not acknowledged for 1 second, it means @@ -1079,7 +962,6 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, inet_sk_set_state(newsk, TCP_SYN_RECV); newicsk->icsk_bind_hash = NULL; - newicsk->icsk_bind2_hash = NULL; inet_sk(newsk)->inet_dport = inet_rsk(req)->ir_rmt_port; inet_sk(newsk)->inet_num = inet_rsk(req)->ir_num; diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 545f91b6cb5e..b9d995b5ce24 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -81,41 +81,6 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, return tb; } -struct inet_bind2_bucket *inet_bind2_bucket_create(struct kmem_cache *cachep, - struct net *net, - struct inet_bind2_hashbucket *head, - const unsigned short port, - int l3mdev, - const struct sock *sk) -{ - struct inet_bind2_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); - - if (tb) { - write_pnet(&tb->ib_net, net); - tb->l3mdev = l3mdev; - tb->port = port; -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - tb->v6_rcv_saddr = sk->sk_v6_rcv_saddr; - else -#endif - tb->rcv_saddr = sk->sk_rcv_saddr; - INIT_HLIST_HEAD(&tb->owners); - hlist_add_head(&tb->node, &head->chain); - } - return tb; -} - -static bool bind2_bucket_addr_match(struct inet_bind2_bucket *tb2, struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - return ipv6_addr_equal(&tb2->v6_rcv_saddr, - &sk->sk_v6_rcv_saddr); -#endif - return tb2->rcv_saddr == sk->sk_rcv_saddr; -} - /* * Caller must hold hashbucket lock for this tb with local BH disabled */ @@ -127,25 +92,12 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket } } -/* Caller must hold the lock for the corresponding hashbucket in the bhash table - * with local BH disabled - */ -void inet_bind2_bucket_destroy(struct kmem_cache *cachep, struct inet_bind2_bucket *tb) -{ - if (hlist_empty(&tb->owners)) { - __hlist_del(&tb->node); - kmem_cache_free(cachep, tb); - } -} - void inet_bind_hash(struct sock *sk, struct inet_bind_bucket *tb, - struct inet_bind2_bucket *tb2, const unsigned short snum) + const unsigned short snum) { inet_sk(sk)->inet_num = snum; sk_add_bind_node(sk, &tb->owners); inet_csk(sk)->icsk_bind_hash = tb; - sk_add_bind2_node(sk, &tb2->owners); - inet_csk(sk)->icsk_bind2_hash = tb2; } /* @@ -157,7 +109,6 @@ static void __inet_put_port(struct sock *sk) const int bhash = inet_bhashfn(sock_net(sk), inet_sk(sk)->inet_num, hashinfo->bhash_size); struct inet_bind_hashbucket *head = &hashinfo->bhash[bhash]; - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; spin_lock(&head->lock); @@ -166,13 +117,6 @@ static void __inet_put_port(struct sock *sk) inet_csk(sk)->icsk_bind_hash = NULL; inet_sk(sk)->inet_num = 0; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - - if (inet_csk(sk)->icsk_bind2_hash) { - tb2 = inet_csk(sk)->icsk_bind2_hash; - __sk_del_bind2_node(sk); - inet_csk(sk)->icsk_bind2_hash = NULL; - inet_bind2_bucket_destroy(hashinfo->bind2_bucket_cachep, tb2); - } spin_unlock(&head->lock); } @@ -189,19 +133,14 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; unsigned short port = inet_sk(child)->inet_num; const int bhash = inet_bhashfn(sock_net(sk), port, - table->bhash_size); + table->bhash_size); struct inet_bind_hashbucket *head = &table->bhash[bhash]; - struct inet_bind2_hashbucket *head_bhash2; - bool created_inet_bind_bucket = false; - struct net *net = sock_net(sk); - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; int l3mdev; spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; - tb2 = inet_csk(sk)->icsk_bind2_hash; - if (unlikely(!tb || !tb2)) { + if (unlikely(!tb)) { spin_unlock(&head->lock); return -ENOENT; } @@ -214,45 +153,25 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) * as that of the child socket. We have to look up or * create a new bind bucket for the child here. */ inet_bind_bucket_for_each(tb, &head->chain) { - if (check_bind_bucket_match(tb, net, port, l3mdev)) + if (net_eq(ib_net(tb), sock_net(sk)) && + tb->l3mdev == l3mdev && tb->port == port) break; } if (!tb) { tb = inet_bind_bucket_create(table->bind_bucket_cachep, - net, head, port, l3mdev); + sock_net(sk), head, port, + l3mdev); if (!tb) { spin_unlock(&head->lock); return -ENOMEM; } - created_inet_bind_bucket = true; } inet_csk_update_fastreuse(tb, child); - - goto bhash2_find; - } else if (!bind2_bucket_addr_match(tb2, child)) { - l3mdev = inet_sk_bound_l3mdev(sk); - -bhash2_find: - tb2 = inet_bind2_bucket_find(table, net, port, l3mdev, child, - &head_bhash2); - if (!tb2) { - tb2 = inet_bind2_bucket_create(table->bind2_bucket_cachep, - net, head_bhash2, port, - l3mdev, child); - if (!tb2) - goto error; - } } - inet_bind_hash(child, tb, tb2, port); + inet_bind_hash(child, tb, port); spin_unlock(&head->lock); return 0; - -error: - if (created_inet_bind_bucket) - inet_bind_bucket_destroy(table->bind_bucket_cachep, tb); - spin_unlock(&head->lock); - return -ENOMEM; } EXPORT_SYMBOL_GPL(__inet_inherit_port); @@ -756,76 +675,6 @@ void inet_unhash(struct sock *sk) } EXPORT_SYMBOL_GPL(inet_unhash); -static bool check_bind2_bucket_match(struct inet_bind2_bucket *tb, - struct net *net, unsigned short port, - int l3mdev, struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &sk->sk_v6_rcv_saddr); - else -#endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == sk->sk_rcv_saddr; -} - -bool check_bind2_bucket_match_nulladdr(struct inet_bind2_bucket *tb, - struct net *net, const unsigned short port, - int l3mdev, const struct sock *sk) -{ -#if IS_ENABLED(CONFIG_IPV6) - struct in6_addr nulladdr = {}; - - if (sk->sk_family == AF_INET6) - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && - ipv6_addr_equal(&tb->v6_rcv_saddr, &nulladdr); - else -#endif - return net_eq(ib2_net(tb), net) && tb->port == port && - tb->l3mdev == l3mdev && tb->rcv_saddr == 0; -} - -static struct inet_bind2_hashbucket * -inet_bhashfn_portaddr(struct inet_hashinfo *hinfo, const struct sock *sk, - const struct net *net, unsigned short port) -{ - u32 hash; - -#if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) - hash = ipv6_portaddr_hash(net, &sk->sk_v6_rcv_saddr, port); - else -#endif - hash = ipv4_portaddr_hash(net, sk->sk_rcv_saddr, port); - return &hinfo->bhash2[hash & (hinfo->bhash_size - 1)]; -} - -/* This should only be called when the spinlock for the socket's corresponding - * bind_hashbucket is held - */ -struct inet_bind2_bucket * -inet_bind2_bucket_find(struct inet_hashinfo *hinfo, struct net *net, - const unsigned short port, int l3mdev, struct sock *sk, - struct inet_bind2_hashbucket **head) -{ - struct inet_bind2_bucket *bhash2 = NULL; - struct inet_bind2_hashbucket *h; - - h = inet_bhashfn_portaddr(hinfo, sk, net, port); - inet_bind_bucket_for_each(bhash2, &h->chain) { - if (check_bind2_bucket_match(bhash2, net, port, l3mdev, sk)) - break; - } - - if (head) - *head = h; - - return bhash2; -} - /* RFC 6056 3.3.4. Algorithm 4: Double-Hash Port Selection Algorithm * Note that we use 32bit integers (vs RFC 'short integers') * because 2^16 is not a multiple of num_ephemeral and this @@ -846,13 +695,10 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, { struct inet_hashinfo *hinfo = death_row->hashinfo; struct inet_timewait_sock *tw = NULL; - struct inet_bind2_hashbucket *head2; struct inet_bind_hashbucket *head; int port = inet_sk(sk)->inet_num; struct net *net = sock_net(sk); - struct inet_bind2_bucket *tb2; struct inet_bind_bucket *tb; - bool tb_created = false; u32 remaining, offset; int ret, i, low, high; int l3mdev; @@ -909,7 +755,8 @@ other_parity_scan: * the established check is already unique enough. */ inet_bind_bucket_for_each(tb, &head->chain) { - if (check_bind_bucket_match(tb, net, port, l3mdev)) { + if (net_eq(ib_net(tb), net) && tb->l3mdev == l3mdev && + tb->port == port) { if (tb->fastreuse >= 0 || tb->fastreuseport >= 0) goto next_port; @@ -927,7 +774,6 @@ other_parity_scan: spin_unlock_bh(&head->lock); return -ENOMEM; } - tb_created = true; tb->fastreuse = -1; tb->fastreuseport = -1; goto ok; @@ -943,17 +789,6 @@ next_port: return -EADDRNOTAVAIL; ok: - /* Find the corresponding tb2 bucket since we need to - * add the socket to the bhash2 table as well - */ - tb2 = inet_bind2_bucket_find(hinfo, net, port, l3mdev, sk, &head2); - if (!tb2) { - tb2 = inet_bind2_bucket_create(hinfo->bind2_bucket_cachep, net, - head2, port, l3mdev, sk); - if (!tb2) - goto error; - } - /* Here we want to add a little bit of randomness to the next source * port that will be chosen. We use a max() with a random here so that * on low contention the randomness is maximal and on high contention @@ -963,7 +798,7 @@ ok: WRITE_ONCE(table_perturb[index], READ_ONCE(table_perturb[index]) + i + 2); /* Head lock still held and bh's disabled */ - inet_bind_hash(sk, tb, tb2, port); + inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); inet_ehash_nolisten(sk, (struct sock *)tw, NULL); @@ -975,12 +810,6 @@ ok: inet_twsk_deschedule_put(tw); local_bh_enable(); return 0; - -error: - if (tb_created) - inet_bind_bucket_destroy(hinfo->bind_bucket_cachep, tb); - spin_unlock_bh(&head->lock); - return -ENOMEM; } /* diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 0ec501845cb3..47ccc343c9fb 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -156,7 +156,8 @@ struct inet_timewait_sock *inet_twsk_alloc(const struct sock *sk, { struct inet_timewait_sock *tw; - if (refcount_read(&dr->tw_refcount) - 1 >= dr->sysctl_max_tw_buckets) + if (refcount_read(&dr->tw_refcount) - 1 >= + READ_ONCE(dr->sysctl_max_tw_buckets)) return NULL; tw = kmem_cache_alloc(sk->sk_prot_creator->twsk_prot->twsk_slab, diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index da21dfce24d7..e9fed83e9b3c 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -141,16 +141,20 @@ static void inet_peer_gc(struct inet_peer_base *base, struct inet_peer *gc_stack[], unsigned int gc_cnt) { + int peer_threshold, peer_maxttl, peer_minttl; struct inet_peer *p; __u32 delta, ttl; int i; - if (base->total >= inet_peer_threshold) + peer_threshold = READ_ONCE(inet_peer_threshold); + peer_maxttl = READ_ONCE(inet_peer_maxttl); + peer_minttl = READ_ONCE(inet_peer_minttl); + + if (base->total >= peer_threshold) ttl = 0; /* be aggressive */ else - ttl = inet_peer_maxttl - - (inet_peer_maxttl - inet_peer_minttl) / HZ * - base->total / inet_peer_threshold * HZ; + ttl = peer_maxttl - (peer_maxttl - peer_minttl) / HZ * + base->total / peer_threshold * HZ; for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index e3aa436a1bdf..e18931a6d153 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -157,7 +157,7 @@ int ip_forward(struct sk_buff *skb) !skb_sec_path(skb)) ip_rt_send_redirect(skb); - if (net->ipv4.sysctl_ip_fwd_update_priority) + if (READ_ONCE(net->ipv4.sysctl_ip_fwd_update_priority)) skb->priority = rt_tos2priority(iph->tos); return NF_HOOK(NFPROTO_IPV4, NF_INET_FORWARD, diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 3b9cd487075a..5c58e21f724e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -524,7 +524,6 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) int tunnel_hlen; int version; int nhoff; - int thoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -558,10 +557,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; - thoff = skb_transport_header(skb) - skb_mac_header(skb); - if (skb->protocol == htons(ETH_P_IPV6) && - (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) - truncate = true; + if (skb->protocol == htons(ETH_P_IPV6)) { + int thoff; + + if (skb_transport_header_was_set(skb)) + thoff = skb_transport_header(skb) - skb_mac_header(skb); + else + thoff = nhoff + sizeof(struct ipv6hdr); + if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) + truncate = true; + } if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index b1165f717cd1..1b512390b3cf 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -312,14 +312,13 @@ static bool ip_can_use_hint(const struct sk_buff *skb, const struct iphdr *iph, ip_hdr(hint)->tos == iph->tos; } -INDIRECT_CALLABLE_DECLARE(int udp_v4_early_demux(struct sk_buff *)); -INDIRECT_CALLABLE_DECLARE(int tcp_v4_early_demux(struct sk_buff *)); +int tcp_v4_early_demux(struct sk_buff *skb); +int udp_v4_early_demux(struct sk_buff *skb); static int ip_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb, struct net_device *dev, const struct sk_buff *hint) { const struct iphdr *iph = ip_hdr(skb); - int (*edemux)(struct sk_buff *skb); int err, drop_reason; struct rtable *rt; @@ -332,21 +331,29 @@ static int ip_rcv_finish_core(struct net *net, struct sock *sk, goto drop_error; } - if (net->ipv4.sysctl_ip_early_demux && + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && !skb_dst(skb) && !skb->sk && !ip_is_fragment(iph)) { - const struct net_protocol *ipprot; - int protocol = iph->protocol; - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) { - err = INDIRECT_CALL_2(edemux, tcp_v4_early_demux, - udp_v4_early_demux, skb); - if (unlikely(err)) - goto drop_error; - /* must reload iph, skb->head might have changed */ - iph = ip_hdr(skb); + switch (iph->protocol) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) { + tcp_v4_early_demux(skb); + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) { + err = udp_v4_early_demux(skb); + if (unlikely(err)) + goto drop_error; + + /* must reload iph, skb->head might have changed */ + iph = ip_hdr(skb); + } + break; } } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 00b4bf26fd93..df7f9dfbe8be 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -969,7 +969,6 @@ static int __ip_append_data(struct sock *sk, struct inet_sock *inet = inet_sk(sk); struct ubuf_info *uarg = NULL; struct sk_buff *skb; - struct ip_options *opt = cork->opt; int hh_len; int exthdrlen; @@ -977,6 +976,7 @@ static int __ip_append_data(struct sock *sk, int copy; int err; int offset = 0; + bool zc = false; unsigned int maxfraglen, fragheaderlen, maxnonfragsize; int csummode = CHECKSUM_NONE; struct rtable *rt = (struct rtable *)cork->dst; @@ -1017,17 +1017,35 @@ static int __ip_append_data(struct sock *sk, (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; - if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); - if (!uarg) - return -ENOBUFS; - extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ - if (rt->dst.dev->features & NETIF_F_SG && - csummode == CHECKSUM_PARTIAL) { - paged = true; - } else { - uarg->zerocopy = 0; - skb_zcopy_set(skb, uarg, &extra_uref); + if ((flags & MSG_ZEROCOPY) && length) { + struct msghdr *msg = from; + + if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { + if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) + return -EINVAL; + + /* Leave uarg NULL if can't zerocopy, callers should + * be able to handle it. + */ + if ((rt->dst.dev->features & NETIF_F_SG) && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + uarg = msg->msg_ubuf; + } + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + if (!uarg) + return -ENOBUFS; + extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ + if (rt->dst.dev->features & NETIF_F_SG && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + } else { + uarg->zerocopy = 0; + skb_zcopy_set(skb, uarg, &extra_uref); + } } } @@ -1091,9 +1109,12 @@ alloc_new_skb: (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; - else { + else if (!zc) { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; + } else { + alloclen = fragheaderlen + transhdrlen; + pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; @@ -1188,13 +1209,14 @@ alloc_new_skb: err = -EFAULT; goto error; } - } else if (!uarg || !uarg->zerocopy) { + } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; + skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 445a9ecaefa1..a8a323ecbb54 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -782,7 +782,7 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; if (gsf->gf_numsrc >= 0x1ffffff || - gsf->gf_numsrc > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + gsf->gf_numsrc > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = -EINVAL; @@ -832,7 +832,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, /* numsrc >= (4G-140)/128 overflow in 32 bits */ err = -ENOBUFS; - if (n > sock_net(sk)->ipv4.sysctl_igmp_max_msf) + if (n > READ_ONCE(sock_net(sk)->ipv4.sysctl_igmp_max_msf)) goto out_free_gsf; err = set_mcast_msfilter(sk, gf32->gf_interface, n, gf32->gf_fmode, &gf32->gf_group, gf32->gf_slist_flex); @@ -1244,7 +1244,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, } /* numsrc >= (1G-4) overflow in 32 bits */ if (msf->imsf_numsrc >= 0x3ffffffcU || - msf->imsf_numsrc > net->ipv4.sysctl_igmp_max_msf) { + msf->imsf_numsrc > READ_ONCE(net->ipv4.sysctl_igmp_max_msf)) { kfree(msf); err = -ENOBUFS; break; @@ -1606,7 +1606,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, { struct net *net = sock_net(sk); val = (inet->uc_ttl == -1 ? - net->ipv4.sysctl_ip_default_ttl : + READ_ONCE(net->ipv4.sysctl_ip_default_ttl) : inet->uc_ttl); break; } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6b2dc7b2b612..cc1caab4a654 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -410,7 +410,7 @@ int skb_tunnel_check_pmtu(struct sk_buff *skb, struct dst_entry *encap_dst, u32 mtu = dst_mtu(encap_dst) - headroom; if ((skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) || - (!skb_is_gso(skb) && (skb->len - skb_mac_header_len(skb)) <= mtu)) + (!skb_is_gso(skb) && (skb->len - skb_network_offset(skb)) <= mtu)) return 0; skb_dst_update_pmtu_no_confirm(skb, mtu); diff --git a/net/ipv4/netfilter/nf_reject_ipv4.c b/net/ipv4/netfilter/nf_reject_ipv4.c index 918c61fda0f3..d640adcaf1b1 100644 --- a/net/ipv4/netfilter/nf_reject_ipv4.c +++ b/net/ipv4/netfilter/nf_reject_ipv4.c @@ -62,7 +62,7 @@ struct sk_buff *nf_reject_skb_v4_tcp_reset(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_TCP, - net->ipv4.sysctl_ip_default_ttl); + READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); nf_reject_ip_tcphdr_put(nskb, oldskb, oth); niph->tot_len = htons(nskb->len); ip_send_check(niph); @@ -117,7 +117,7 @@ struct sk_buff *nf_reject_skb_v4_unreach(struct net *net, skb_reserve(nskb, LL_MAX_HEADER); niph = nf_reject_iphdr_put(nskb, oldskb, IPPROTO_ICMP, - net->ipv4.sysctl_ip_default_ttl); + READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); skb_reset_transport_header(nskb); icmph = skb_put_zero(nskb, sizeof(struct icmphdr)); diff --git a/net/ipv4/nexthop.c b/net/ipv4/nexthop.c index e459a391e607..853a75a8fbaf 100644 --- a/net/ipv4/nexthop.c +++ b/net/ipv4/nexthop.c @@ -1858,7 +1858,7 @@ static void __remove_nexthop_fib(struct net *net, struct nexthop *nh) /* __ip6_del_rt does a release, so do a hold here */ fib6_info_hold(f6i); ipv6_stub->ip6_del_rt(net, f6i, - !net->ipv4.sysctl_nexthop_compat_mode); + !READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)); } } @@ -2361,7 +2361,8 @@ out: if (!rc) { nh_base_seq_inc(net); nexthop_notify(RTM_NEWNEXTHOP, new_nh, &cfg->nlinfo); - if (replace_notify && net->ipv4.sysctl_nexthop_compat_mode) + if (replace_notify && + READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode)) nexthop_replace_notify(net, new_nh, &cfg->nlinfo); } diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 1a43ca73f94d..3c6101def7d6 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -319,12 +319,16 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, pr_debug("ping_check_bind_addr(sk=%p,addr=%pI4,port=%d)\n", sk, &addr->sin_addr.s_addr, ntohs(addr->sin_port)); + if (addr->sin_addr.s_addr == htonl(INADDR_ANY)) + return 0; + tb_id = l3mdev_fib_table_by_index(net, sk->sk_bound_dev_if) ? : tb_id; chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); - if (!inet_addr_valid_or_nonlocal(net, inet_sk(sk), - addr->sin_addr.s_addr, - chk_addr_ret)) + if (chk_addr_ret == RTN_MULTICAST || + chk_addr_ret == RTN_BROADCAST || + (chk_addr_ret != RTN_LOCAL && + !inet_can_nonlocal_bind(net, isk))) return -EADDRNOTAVAIL; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 28836071f0a6..0088a4c64d77 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -387,7 +387,7 @@ static int snmp_seq_show_ipstats(struct seq_file *seq, void *v) seq_printf(seq, "\nIp: %d %d", IPV4_DEVCONF_ALL(net, FORWARDING) ? 1 : 2, - net->ipv4.sysctl_ip_default_ttl); + READ_ONCE(net->ipv4.sysctl_ip_default_ttl)); BUILD_BUG_ON(offsetof(struct ipstats_mib, mibs) != 0); snmp_get_cpu_field64_batch(buff64, snmp4_ipstats_list, diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 356f535f3443..4702c61207a8 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1398,7 +1398,7 @@ u32 ip_mtu_from_fib_result(struct fib_result *res, __be32 daddr) struct fib_info *fi = res->fi; u32 mtu = 0; - if (dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu || + if (READ_ONCE(dev_net(dev)->ipv4.sysctl_ip_fwd_use_pmtu) || fi->fib_metrics->metrics[RTAX_LOCK - 1] & (1 << RTAX_MTU)) mtu = fi->fib_mtu; @@ -1929,7 +1929,7 @@ static u32 fib_multipath_custom_hash_outer(const struct net *net, const struct sk_buff *skb, bool *p_has_inner) { - u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) @@ -1958,7 +1958,7 @@ static u32 fib_multipath_custom_hash_inner(const struct net *net, const struct sk_buff *skb, bool has_inner) { - u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys keys, hash_keys; /* We assume the packet carries an encapsulation, but if none was @@ -2018,7 +2018,7 @@ static u32 fib_multipath_custom_hash_skb(const struct net *net, static u32 fib_multipath_custom_hash_fl4(const struct net *net, const struct flowi4 *fl4) { - u32 hash_fields = net->ipv4.sysctl_fib_multipath_hash_fields; + u32 hash_fields = READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_fields); struct flow_keys hash_keys; if (!(hash_fields & FIB_MULTIPATH_HASH_FIELD_OUTER_MASK)) @@ -2048,7 +2048,7 @@ int fib_multipath_hash(const struct net *net, const struct flowi4 *fl4, struct flow_keys hash_keys; u32 mhash = 0; - switch (net->ipv4.sysctl_fib_multipath_hash_policy) { + switch (READ_ONCE(net->ipv4.sysctl_fib_multipath_hash_policy)) { case 0: memset(&hash_keys, 0, sizeof(hash_keys)); hash_keys.control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index f33c31dd7366..942d2dfa1115 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -247,12 +247,12 @@ bool cookie_timestamp_decode(const struct net *net, return true; } - if (!net->ipv4.sysctl_tcp_timestamps) + if (!READ_ONCE(net->ipv4.sysctl_tcp_timestamps)) return false; tcp_opt->sack_ok = (options & TS_OPT_SACK) ? TCP_SACK_SEEN : 0; - if (tcp_opt->sack_ok && !net->ipv4.sysctl_tcp_sack) + if (tcp_opt->sack_ok && !READ_ONCE(net->ipv4.sysctl_tcp_sack)) return false; if ((options & TS_OPT_WSCALE_MASK) == TS_OPT_WSCALE_MASK) @@ -261,7 +261,7 @@ bool cookie_timestamp_decode(const struct net *net, tcp_opt->wscale_ok = 1; tcp_opt->snd_wscale = options & TS_OPT_WSCALE_MASK; - return net->ipv4.sysctl_tcp_window_scaling != 0; + return READ_ONCE(net->ipv4.sysctl_tcp_window_scaling) != 0; } EXPORT_SYMBOL(cookie_timestamp_decode); @@ -273,7 +273,7 @@ bool cookie_ecn_ok(const struct tcp_options_received *tcp_opt, if (!ecn_ok) return false; - if (net->ipv4.sysctl_tcp_ecn) + if (READ_ONCE(net->ipv4.sysctl_tcp_ecn)) return true; return dst_feature(dst, RTAX_FEATURE_ECN); @@ -340,7 +340,8 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb) struct flowi4 fl4; u32 tsoff = 0; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index cd448cdd3b38..5490c285668b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -84,7 +84,7 @@ static int ipv4_local_port_range(struct ctl_table *table, int write, * port limit. */ if ((range[1] < range[0]) || - (range[0] < net->ipv4.sysctl_ip_prot_sock)) + (range[0] < READ_ONCE(net->ipv4.sysctl_ip_prot_sock))) ret = -EINVAL; else set_local_port_range(net, range); @@ -110,7 +110,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, .extra2 = &ip_privileged_port_max, }; - pports = net->ipv4.sysctl_ip_prot_sock; + pports = READ_ONCE(net->ipv4.sysctl_ip_prot_sock); ret = proc_dointvec_minmax(&tmp, write, buffer, lenp, ppos); @@ -122,7 +122,7 @@ static int ipv4_privileged_ports(struct ctl_table *table, int write, if (range[0] < pports) ret = -EINVAL; else - net->ipv4.sysctl_ip_prot_sock = pports; + WRITE_ONCE(net->ipv4.sysctl_ip_prot_sock, pports); } return ret; @@ -350,61 +350,6 @@ bad_key: return ret; } -static void proc_configure_early_demux(int enabled, int protocol) -{ - struct net_protocol *ipprot; -#if IS_ENABLED(CONFIG_IPV6) - struct inet6_protocol *ip6prot; -#endif - - rcu_read_lock(); - - ipprot = rcu_dereference(inet_protos[protocol]); - if (ipprot) - ipprot->early_demux = enabled ? ipprot->early_demux_handler : - NULL; - -#if IS_ENABLED(CONFIG_IPV6) - ip6prot = rcu_dereference(inet6_protos[protocol]); - if (ip6prot) - ip6prot->early_demux = enabled ? ip6prot->early_demux_handler : - NULL; -#endif - rcu_read_unlock(); -} - -static int proc_tcp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_tcp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_TCP); - } - - return ret; -} - -static int proc_udp_early_demux(struct ctl_table *table, int write, - void *buffer, size_t *lenp, loff_t *ppos) -{ - int ret = 0; - - ret = proc_dou8vec_minmax(table, write, buffer, lenp, ppos); - - if (write && !ret) { - int enabled = init_net.ipv4.sysctl_udp_early_demux; - - proc_configure_early_demux(enabled, IPPROTO_UDP); - } - - return ret; -} - static int proc_tfo_blackhole_detect_timeout(struct ctl_table *table, int write, void *buffer, size_t *lenp, loff_t *ppos) @@ -599,6 +544,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_echo_enable_probe", @@ -615,6 +562,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ignore_bogus_error_responses", @@ -622,6 +571,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_errors_use_inbound_ifaddr", @@ -629,6 +580,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE }, { .procname = "icmp_ratelimit", @@ -668,6 +621,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_TWO, }, { .procname = "tcp_ecn_fallback", @@ -675,6 +630,8 @@ static struct ctl_table ipv4_net_table[] = { .maxlen = sizeof(u8), .mode = 0644, .proc_handler = proc_dou8vec_minmax, + .extra1 = SYSCTL_ZERO, + .extra2 = SYSCTL_ONE, }, { .procname = "ip_dynaddr", @@ -695,14 +652,14 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_udp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_udp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "tcp_early_demux", .data = &init_net.ipv4.sysctl_tcp_early_demux, .maxlen = sizeof(u8), .mode = 0644, - .proc_handler = proc_tcp_early_demux + .proc_handler = proc_dou8vec_minmax, }, { .procname = "nexthop_compat_mode", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 9984d23a7f3e..a628daa51113 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -441,7 +441,7 @@ void tcp_init_sock(struct sock *sk) tp->snd_cwnd_clamp = ~0; tp->mss_cache = TCP_MSS_DEFAULT; - tp->reordering = sock_net(sk)->ipv4.sysctl_tcp_reordering; + tp->reordering = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering); tcp_assign_congestion_control(sk); tp->tsoffset = 0; @@ -452,8 +452,8 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); - WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); + WRITE_ONCE(sk->sk_sndbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1])); + WRITE_ONCE(sk->sk_rcvbuf, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1])); sk_sockets_allocated_inc(sk); } @@ -686,7 +686,7 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, int size_goal) { return skb->len < size_goal && - sock_net(sk)->ipv4.sysctl_tcp_autocorking && + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_autocorking) && !tcp_rtx_queue_empty(sk) && refcount_read(&sk->sk_wmem_alloc) > skb->truesize && tcp_skb_can_collapse_to(skb); @@ -1150,7 +1150,8 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, struct sockaddr *uaddr = msg->msg_name; int err, flags; - if (!(sock_net(sk)->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) || + if (!(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) || (uaddr && msg->msg_namelen >= sizeof(uaddr->sa_family) && uaddr->sa_family == AF_UNSPEC)) return -EOPNOTSUPP; @@ -1202,17 +1203,23 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; - if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { + if ((flags & MSG_ZEROCOPY) && size) { skb = tcp_write_queue_tail(sk); - uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); - if (!uarg) { - err = -ENOBUFS; - goto out_err; - } - zc = sk->sk_route_caps & NETIF_F_SG; - if (!zc) - uarg->zerocopy = 0; + if (msg->msg_ubuf) { + uarg = msg->msg_ubuf; + net_zcopy_get(uarg); + zc = sk->sk_route_caps & NETIF_F_SG; + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, size, skb_zcopy(skb)); + if (!uarg) { + err = -ENOBUFS; + goto out_err; + } + zc = sk->sk_route_caps & NETIF_F_SG; + if (!zc) + uarg->zerocopy = 0; + } } if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && @@ -1335,8 +1342,13 @@ new_segment: copy = min_t(int, copy, pfrag->size - pfrag->offset); - if (tcp_downgrade_zcopy_pure(sk, skb) || - !sk_wmem_schedule(sk, copy)) + if (unlikely(skb_zcopy_pure(skb) || skb_zcopy_managed(skb))) { + if (tcp_downgrade_zcopy_pure(sk, skb)) + goto wait_for_space; + skb_zcopy_downgrade_managed(skb); + } + + if (!sk_wmem_schedule(sk, copy)) goto wait_for_space; err = skb_copy_to_page_nocache(sk, &msg->msg_iter, skb, @@ -1723,7 +1735,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) cap = sk->sk_rcvbuf >> 1; else - cap = sock_net(sk)->ipv4.sysctl_tcp_rmem[2] >> 1; + cap = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; val = min(val, cap); WRITE_ONCE(sk->sk_rcvlowat, val ? : 1); @@ -2715,7 +2727,8 @@ static void tcp_orphan_update(struct timer_list *unused) static bool tcp_too_many_orphans(int shift) { - return READ_ONCE(tcp_orphan_cache) << shift > sysctl_tcp_max_orphans; + return READ_ONCE(tcp_orphan_cache) << shift > + READ_ONCE(sysctl_tcp_max_orphans); } bool tcp_check_oom(struct sock *sk, int shift) @@ -3616,7 +3629,8 @@ static int do_tcp_setsockopt(struct sock *sk, int level, int optname, case TCP_FASTOPEN_CONNECT: if (val > 1 || val < 0) { err = -EINVAL; - } else if (net->ipv4.sysctl_tcp_fastopen & TFO_CLIENT_ENABLE) { + } else if (READ_ONCE(net->ipv4.sysctl_tcp_fastopen) & + TFO_CLIENT_ENABLE) { if (sk->sk_state == TCP_CLOSE) tp->fastopen_connect = val; else @@ -3966,12 +3980,13 @@ static int do_tcp_getsockopt(struct sock *sk, int level, val = keepalive_probes(tp); break; case TCP_SYNCNT: - val = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; + val = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); break; case TCP_LINGER2: val = tp->linger2; if (val >= 0) - val = (val ? : net->ipv4.sysctl_tcp_fin_timeout) / HZ; + val = (val ? : READ_ONCE(net->ipv4.sysctl_tcp_fin_timeout)) / HZ; break; case TCP_DEFER_ACCEPT: val = retrans_to_secs(icsk->icsk_accept_queue.rskq_defer_accept, @@ -4455,9 +4470,18 @@ tcp_inbound_md5_hash(const struct sock *sk, const struct sk_buff *skb, return SKB_DROP_REASON_TCP_MD5UNEXPECTED; } - /* check the signature */ - genhash = tp->af_specific->calc_md5_hash(newhash, hash_expected, - NULL, skb); + /* Check the signature. + * To support dual stack listeners, we need to handle + * IPv4-mapped case. + */ + if (family == AF_INET) + genhash = tcp_v4_md5_hash_skb(newhash, + hash_expected, + NULL, skb); + else + genhash = tp->af_specific->calc_md5_hash(newhash, + hash_expected, + NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMD5FAILURE); @@ -4604,12 +4628,6 @@ void __init tcp_init(void) SLAB_HWCACHE_ALIGN | SLAB_PANIC | SLAB_ACCOUNT, NULL); - tcp_hashinfo.bind2_bucket_cachep = - kmem_cache_create("tcp_bind2_bucket", - sizeof(struct inet_bind2_bucket), 0, - SLAB_HWCACHE_ALIGN | SLAB_PANIC | - SLAB_ACCOUNT, - NULL); /* Size and allocate the main established and bind bucket * hash tables. @@ -4632,9 +4650,8 @@ void __init tcp_init(void) if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); tcp_hashinfo.bhash = - alloc_large_system_hash("TCP bind bhash tables", - sizeof(struct inet_bind_hashbucket) + - sizeof(struct inet_bind2_hashbucket), + alloc_large_system_hash("TCP bind", + sizeof(struct inet_bind_hashbucket), tcp_hashinfo.ehash_mask + 1, 17, /* one slot per 128 KB of memory */ 0, @@ -4643,12 +4660,9 @@ void __init tcp_init(void) 0, 64 * 1024); tcp_hashinfo.bhash_size = 1U << tcp_hashinfo.bhash_size; - tcp_hashinfo.bhash2 = - (struct inet_bind2_hashbucket *)(tcp_hashinfo.bhash + tcp_hashinfo.bhash_size); for (i = 0; i < tcp_hashinfo.bhash_size; i++) { spin_lock_init(&tcp_hashinfo.bhash[i].lock); INIT_HLIST_HEAD(&tcp_hashinfo.bhash[i].chain); - INIT_HLIST_HEAD(&tcp_hashinfo.bhash2[i].chain); } diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index be3947e70fec..0d3f68bb51c0 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -611,9 +611,6 @@ int tcp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore) return 0; } - if (inet_csk_has_ulp(sk)) - return -EINVAL; - if (sk->sk_family == AF_INET6) { if (tcp_bpf_assert_proto_ops(psock->sk_proto)) return -EINVAL; diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index fdbcf2a6d08e..825b216d11f5 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -332,7 +332,7 @@ static bool tcp_fastopen_no_cookie(const struct sock *sk, const struct dst_entry *dst, int flag) { - return (sock_net(sk)->ipv4.sysctl_tcp_fastopen & flag) || + return (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen) & flag) || tcp_sk(sk)->fastopen_no_cookie || (dst && dst_metric(dst, RTAX_FASTOPEN_NO_COOKIE)); } @@ -347,7 +347,7 @@ struct sock *tcp_try_fastopen(struct sock *sk, struct sk_buff *skb, const struct dst_entry *dst) { bool syn_data = TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(skb)->seq + 1; - int tcp_fastopen = sock_net(sk)->ipv4.sysctl_tcp_fastopen; + int tcp_fastopen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen); struct tcp_fastopen_cookie valid_foc = { .len = -1 }; struct sock *child; int ret = 0; @@ -489,7 +489,7 @@ void tcp_fastopen_active_disable(struct sock *sk) { struct net *net = sock_net(sk); - if (!sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout)) return; /* Paired with READ_ONCE() in tcp_fastopen_active_should_disable() */ @@ -510,7 +510,8 @@ void tcp_fastopen_active_disable(struct sock *sk) */ bool tcp_fastopen_active_should_disable(struct sock *sk) { - unsigned int tfo_bh_timeout = sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout; + unsigned int tfo_bh_timeout = + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_fastopen_blackhole_timeout); unsigned long timeout; int tfo_da_times; int multiplier; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 2e2a9ece9af2..b1637990d570 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -426,7 +426,7 @@ static void tcp_sndbuf_expand(struct sock *sk) if (sk->sk_sndbuf < sndmem) WRITE_ONCE(sk->sk_sndbuf, - min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2])); + min(sndmem, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[2]))); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -461,7 +461,7 @@ static int __tcp_grow_window(const struct sock *sk, const struct sk_buff *skb, struct tcp_sock *tp = tcp_sk(sk); /* Optimize this! */ int truesize = tcp_win_from_space(sk, skbtruesize) >> 1; - int window = tcp_win_from_space(sk, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]) >> 1; + int window = tcp_win_from_space(sk, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])) >> 1; while (tp->rcv_ssthresh <= window) { if (truesize <= skb->len) @@ -534,7 +534,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb, */ static void tcp_init_buffer_space(struct sock *sk) { - int tcp_app_win = sock_net(sk)->ipv4.sysctl_tcp_app_win; + int tcp_app_win = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_app_win); struct tcp_sock *tp = tcp_sk(sk); int maxwin; @@ -574,16 +574,17 @@ static void tcp_clamp_window(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); + int rmem2; icsk->icsk_ack.quick = 0; + rmem2 = READ_ONCE(net->ipv4.sysctl_tcp_rmem[2]); - if (sk->sk_rcvbuf < net->ipv4.sysctl_tcp_rmem[2] && + if (sk->sk_rcvbuf < rmem2 && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { WRITE_ONCE(sk->sk_rcvbuf, - min(atomic_read(&sk->sk_rmem_alloc), - net->ipv4.sysctl_tcp_rmem[2])); + min(atomic_read(&sk->sk_rmem_alloc), rmem2)); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -724,7 +725,7 @@ void tcp_rcv_space_adjust(struct sock *sk) * <prev RTT . ><current RTT .. ><next RTT .... > */ - if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int rcvmem, rcvbuf; u64 rcvwin, grow; @@ -745,7 +746,7 @@ void tcp_rcv_space_adjust(struct sock *sk) do_div(rcvwin, tp->advmss); rcvbuf = min_t(u64, rcvwin * rcvmem, - sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); @@ -910,9 +911,9 @@ static void tcp_update_pacing_rate(struct sock *sk) * end of slow start and should slow down. */ if (tcp_snd_cwnd(tp) < tp->snd_ssthresh / 2) - rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio; + rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ss_ratio); else - rate *= sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio; + rate *= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_pacing_ca_ratio); rate *= max(tcp_snd_cwnd(tp), tp->packets_out); @@ -1051,7 +1052,7 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, tp->undo_marker ? tp->undo_retrans : 0); #endif tp->reordering = min_t(u32, (metric + mss - 1) / mss, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); } /* This exciting event is worth to be remembered. 8) */ @@ -2030,7 +2031,7 @@ static void tcp_check_reno_reordering(struct sock *sk, const int addend) return; tp->reordering = min_t(u32, tp->packets_out + addend, - sock_net(sk)->ipv4.sysctl_tcp_max_reordering); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_max_reordering)); tp->reord_seen++; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRENOREORDER); } @@ -2095,7 +2096,8 @@ static inline void tcp_init_undo(struct tcp_sock *tp) static bool tcp_is_rack(const struct sock *sk) { - return sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_LOSS_DETECTION; + return READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_LOSS_DETECTION; } /* If we detect SACK reneging, forget all SACK information @@ -2139,6 +2141,7 @@ void tcp_enter_loss(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); bool new_recovery = icsk->icsk_ca_state < TCP_CA_Recovery; + u8 reordering; tcp_timeout_mark_lost(sk); @@ -2159,10 +2162,12 @@ void tcp_enter_loss(struct sock *sk) /* Timeout in disordered state after receiving substantial DUPACKs * suggests that the degree of reordering is over-estimated. */ + reordering = READ_ONCE(net->ipv4.sysctl_tcp_reordering); if (icsk->icsk_ca_state <= TCP_CA_Disorder && - tp->sacked_out >= net->ipv4.sysctl_tcp_reordering) + tp->sacked_out >= reordering) tp->reordering = min_t(unsigned int, tp->reordering, - net->ipv4.sysctl_tcp_reordering); + reordering); + tcp_set_ca_state(sk, TCP_CA_Loss); tp->high_seq = tp->snd_nxt; tcp_ecn_queue_cwr(tp); @@ -2171,7 +2176,7 @@ void tcp_enter_loss(struct sock *sk) * loss recovery is underway except recurring timeout(s) on * the same SND.UNA (sec 3.2). Disable F-RTO on path MTU probing */ - tp->frto = net->ipv4.sysctl_tcp_frto && + tp->frto = READ_ONCE(net->ipv4.sysctl_tcp_frto) && (new_recovery || icsk->icsk_retransmits) && !inet_csk(sk)->icsk_mtup.probe_size; } @@ -3054,7 +3059,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const u32 prior_snd_una, static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us, const int flag) { - u32 wlen = sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen * HZ; + u32 wlen = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_rtt_wlen) * HZ; struct tcp_sock *tp = tcp_sk(sk); if ((flag & FLAG_ACK_MAYBE_DELAYED) && rtt_us > tcp_min_rtt(tp)) { @@ -3464,7 +3469,8 @@ static inline bool tcp_may_raise_cwnd(const struct sock *sk, const int flag) * new SACK or ECE mark may first advance cwnd here and later reduce * cwnd in tcp_fastretrans_alert() based on more states. */ - if (tcp_sk(sk)->reordering > sock_net(sk)->ipv4.sysctl_tcp_reordering) + if (tcp_sk(sk)->reordering > + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reordering)) return flag & FLAG_FORWARD_PROGRESS; return flag & FLAG_DATA_ACKED; @@ -3576,7 +3582,8 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, if (*last_oow_ack_time) { s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); - if (0 <= elapsed && elapsed < net->ipv4.sysctl_tcp_invalid_ratelimit) { + if (0 <= elapsed && + elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) { NET_INC_STATS(net, mib_idx); return true; /* rate-limited: don't send yet! */ } @@ -3624,7 +3631,7 @@ static void tcp_send_challenge_ack(struct sock *sk) /* Then check host-wide RFC 5961 rate limit. */ now = jiffies / HZ; if (now != challenge_timestamp) { - u32 ack_limit = net->ipv4.sysctl_tcp_challenge_ack_limit; + u32 ack_limit = READ_ONCE(net->ipv4.sysctl_tcp_challenge_ack_limit); u32 half = (ack_limit + 1) >> 1; challenge_timestamp = now; @@ -4056,7 +4063,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_WINDOW: if (opsize == TCPOLEN_WINDOW && th->syn && - !estab && net->ipv4.sysctl_tcp_window_scaling) { + !estab && READ_ONCE(net->ipv4.sysctl_tcp_window_scaling)) { __u8 snd_wscale = *(__u8 *)ptr; opt_rx->wscale_ok = 1; if (snd_wscale > TCP_MAX_WSCALE) { @@ -4072,7 +4079,7 @@ void tcp_parse_options(const struct net *net, case TCPOPT_TIMESTAMP: if ((opsize == TCPOLEN_TIMESTAMP) && ((estab && opt_rx->tstamp_ok) || - (!estab && net->ipv4.sysctl_tcp_timestamps))) { + (!estab && READ_ONCE(net->ipv4.sysctl_tcp_timestamps)))) { opt_rx->saw_tstamp = 1; opt_rx->rcv_tsval = get_unaligned_be32(ptr); opt_rx->rcv_tsecr = get_unaligned_be32(ptr + 4); @@ -4080,7 +4087,7 @@ void tcp_parse_options(const struct net *net, break; case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && - !estab && net->ipv4.sysctl_tcp_sack) { + !estab && READ_ONCE(net->ipv4.sysctl_tcp_sack)) { opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } @@ -4421,7 +4428,7 @@ static void tcp_dsack_set(struct sock *sk, u32 seq, u32 end_seq) { struct tcp_sock *tp = tcp_sk(sk); - if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) { int mib_idx; if (before(seq, tp->rcv_nxt)) @@ -4468,7 +4475,7 @@ static void tcp_send_dupack(struct sock *sk, const struct sk_buff *skb) NET_INC_STATS(sock_net(sk), LINUX_MIB_DELAYEDACKLOST); tcp_enter_quickack_mode(sk, TCP_MAX_QUICKACKS); - if (tcp_is_sack(tp) && sock_net(sk)->ipv4.sysctl_tcp_dsack) { + if (tcp_is_sack(tp) && READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_dsack)) { u32 end_seq = TCP_SKB_CB(skb)->end_seq; tcp_rcv_spurious_retrans(sk, skb); @@ -5514,7 +5521,7 @@ send_now: } if (!tcp_is_sack(tp) || - tp->compressed_ack >= sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr) + tp->compressed_ack >= READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_nr)) goto send_now; if (tp->compressed_ack_rcv_nxt != tp->rcv_nxt) { @@ -5535,11 +5542,12 @@ send_now: if (tp->srtt_us && tp->srtt_us < rtt) rtt = tp->srtt_us; - delay = min_t(unsigned long, sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns, + delay = min_t(unsigned long, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_delay_ns), rtt * (NSEC_PER_USEC >> 3)/20); sock_hold(sk); hrtimer_start_range_ns(&tp->compressed_ack_timer, ns_to_ktime(delay), - sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_comp_sack_slack_ns), HRTIMER_MODE_REL_PINNED_SOFT); } @@ -5567,7 +5575,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) struct tcp_sock *tp = tcp_sk(sk); u32 ptr = ntohs(th->urg_ptr); - if (ptr && !sock_net(sk)->ipv4.sysctl_tcp_stdurg) + if (ptr && !READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_stdurg)) ptr--; ptr += ntohl(th->seq); @@ -6729,7 +6737,7 @@ static void tcp_ecn_create_request(struct request_sock *req, ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield); ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); - ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; + ecn_ok = READ_ONCE(net->ipv4.sysctl_tcp_ecn) || ecn_ok_dst; if (((!ect || th->res1) && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || (ecn_ok_dst & DST_FEATURE_ECN_CA) || @@ -6797,11 +6805,14 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) { struct request_sock_queue *queue = &inet_csk(sk)->icsk_accept_queue; const char *msg = "Dropping request"; - bool want_cookie = false; struct net *net = sock_net(sk); + bool want_cookie = false; + u8 syncookies; + + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); #ifdef CONFIG_SYN_COOKIES - if (net->ipv4.sysctl_tcp_syncookies) { + if (syncookies) { msg = "Sending cookies"; want_cookie = true; __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDOCOOKIES); @@ -6809,8 +6820,7 @@ static bool tcp_syn_flood_action(const struct sock *sk, const char *proto) #endif __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPREQQFULLDROP); - if (!queue->synflood_warned && - net->ipv4.sysctl_tcp_syncookies != 2 && + if (!queue->synflood_warned && syncookies != 2 && xchg(&queue->synflood_warned, 1) == 0) net_info_ratelimited("%s: Possible SYN flooding on port %d. %s. Check SNMP counters.\n", proto, sk->sk_num, msg); @@ -6859,7 +6869,7 @@ u16 tcp_get_syncookie_mss(struct request_sock_ops *rsk_ops, struct tcp_sock *tp = tcp_sk(sk); u16 mss; - if (sock_net(sk)->ipv4.sysctl_tcp_syncookies != 2 && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) != 2 && !inet_csk_reqsk_queue_is_full(sk)) return 0; @@ -6893,13 +6903,15 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, bool want_cookie = false; struct dst_entry *dst; struct flowi fl; + u8 syncookies; + + syncookies = READ_ONCE(net->ipv4.sysctl_tcp_syncookies); /* TW buckets are converted to open requests without * limitations, they conserve resources and peer is * evidently real one. */ - if ((net->ipv4.sysctl_tcp_syncookies == 2 || - inet_csk_reqsk_queue_is_full(sk)) && !isn) { + if ((syncookies == 2 || inet_csk_reqsk_queue_is_full(sk)) && !isn) { want_cookie = tcp_syn_flood_action(sk, rsk_ops->slab_name); if (!want_cookie) goto drop; @@ -6948,10 +6960,12 @@ int tcp_conn_request(struct request_sock_ops *rsk_ops, tcp_rsk(req)->ts_off = af_ops->init_ts_off(net, skb); if (!want_cookie && !isn) { + int max_syn_backlog = READ_ONCE(net->ipv4.sysctl_max_syn_backlog); + /* Kill the following clause, if you dislike this way. */ - if (!net->ipv4.sysctl_tcp_syncookies && - (net->ipv4.sysctl_max_syn_backlog - inet_csk_reqsk_queue_len(sk) < - (net->ipv4.sysctl_max_syn_backlog >> 2)) && + if (!syncookies && + (max_syn_backlog - inet_csk_reqsk_queue_len(sk) < + (max_syn_backlog >> 2)) && !tcp_peer_is_proven(req, dst)) { /* Without syncookies last quarter of * backlog is filled with destinations, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index fe8f23b95d32..586c102ce152 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -108,10 +108,10 @@ static u32 tcp_v4_init_ts_off(const struct net *net, const struct sk_buff *skb) int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) { + int reuse = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tw_reuse); const struct inet_timewait_sock *tw = inet_twsk(sktw); const struct tcp_timewait_sock *tcptw = tcp_twsk(sktw); struct tcp_sock *tp = tcp_sk(sk); - int reuse = sock_net(sk)->ipv4.sysctl_tcp_tw_reuse; if (reuse == 2) { /* Still does not detect *everything* that goes through @@ -1006,7 +1006,7 @@ static int tcp_v4_send_synack(const struct sock *sk, struct dst_entry *dst, if (skb) { __tcp_v4_send_check(skb, ireq->ir_loc_addr, ireq->ir_rmt_addr); - tos = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tos = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (inet_sk(sk)->tos & INET_ECN_MASK) : inet_sk(sk)->tos; @@ -1526,7 +1526,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ - if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newinet->tos = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; if (!dst) { @@ -1964,7 +1964,10 @@ process: struct sock *nsk; sk = req->rsk_listener; - drop_reason = tcp_inbound_md5_hash(sk, skb, + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + drop_reason = SKB_DROP_REASON_XFRM_POLICY; + else + drop_reason = tcp_inbound_md5_hash(sk, skb, &iph->saddr, &iph->daddr, AF_INET, dif, sdif); if (unlikely(drop_reason)) { @@ -2016,6 +2019,7 @@ process: } goto discard_and_relse; } + nf_reset_ct(skb); if (nsk == sk) { reqsk_put(req); tcp_v4_restore_cb(skb); diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index 7029b0e98edb..d58e672be31c 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -329,7 +329,7 @@ void tcp_update_metrics(struct sock *sk) int m; sk_dst_confirm(sk); - if (net->ipv4.sysctl_tcp_nometrics_save || !dst) + if (READ_ONCE(net->ipv4.sysctl_tcp_nometrics_save) || !dst) return; rcu_read_lock(); @@ -385,7 +385,7 @@ void tcp_update_metrics(struct sock *sk) if (tcp_in_initial_slowstart(tp)) { /* Slow start still did not finish. */ - if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) && !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val && (tcp_snd_cwnd(tp) >> 1) > val) @@ -401,7 +401,7 @@ void tcp_update_metrics(struct sock *sk) } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ - if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) && !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) tcp_metric_set(tm, TCP_METRIC_SSTHRESH, max(tcp_snd_cwnd(tp) >> 1, tp->snd_ssthresh)); @@ -418,7 +418,7 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, (val + tp->snd_ssthresh) >> 1); } - if (!net->ipv4.sysctl_tcp_no_ssthresh_metrics_save && + if (!READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) && !tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) { val = tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val && tp->snd_ssthresh > val) @@ -428,7 +428,8 @@ void tcp_update_metrics(struct sock *sk) if (!tcp_metric_locked(tm, TCP_METRIC_REORDERING)) { val = tcp_metric_get(tm, TCP_METRIC_REORDERING); if (val < tp->reordering && - tp->reordering != net->ipv4.sysctl_tcp_reordering) + tp->reordering != + READ_ONCE(net->ipv4.sysctl_tcp_reordering)) tcp_metric_set(tm, TCP_METRIC_REORDERING, tp->reordering); } @@ -462,7 +463,7 @@ void tcp_init_metrics(struct sock *sk) if (tcp_metric_locked(tm, TCP_METRIC_CWND)) tp->snd_cwnd_clamp = tcp_metric_get(tm, TCP_METRIC_CWND); - val = net->ipv4.sysctl_tcp_no_ssthresh_metrics_save ? + val = READ_ONCE(net->ipv4.sysctl_tcp_no_ssthresh_metrics_save) ? 0 : tcp_metric_get(tm, TCP_METRIC_SSTHRESH); if (val) { tp->snd_ssthresh = val; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 6854bb1fb32b..cb95d88497ae 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -173,7 +173,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, * Oh well... nobody has a sufficient solution to this * protocol bug yet. */ - if (twsk_net(tw)->ipv4.sysctl_tcp_rfc1337 == 0) { + if (!READ_ONCE(twsk_net(tw)->ipv4.sysctl_tcp_rfc1337)) { kill: inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; @@ -781,7 +781,7 @@ listen_overflow: if (sk != req->rsk_listener) __NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPMIGRATEREQFAILURE); - if (!sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow) { + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_abort_on_overflow)) { inet_rsk(req)->acked = 1; return NULL; } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 1c054431e358..4c376b6d8764 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -167,16 +167,13 @@ static void tcp_event_data_sent(struct tcp_sock *tp, if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); - /* If this is the first data packet sent in response to the - * previous received data, - * and it is a reply for ato after last received packet, - * increase pingpong count. - */ - if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) && - (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - inet_csk_inc_pingpong_cnt(sk); - tp->lsndtime = now; + + /* If it is a reply for ato after last received + * packet, enter pingpong mode. + */ + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + inet_csk_enter_pingpong_mode(sk); } /* Account for an ACK we sent. */ @@ -230,7 +227,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, * which we interpret as a sign the remote TCP is not * misinterpreting the window field as a signed quantity. */ - if (sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) (*rcv_wnd) = min(space, MAX_TCP_WINDOW); else (*rcv_wnd) = min_t(u32, space, U16_MAX); @@ -241,7 +238,7 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, *rcv_wscale = 0; if (wscale_ok) { /* Set window scaling on max possible window */ - space = max_t(u32, space, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + space = max_t(u32, space, READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); space = max_t(u32, space, sysctl_rmem_max); space = min_t(u32, space, *window_clamp); *rcv_wscale = clamp_t(int, ilog2(space) - 15, @@ -285,7 +282,7 @@ static u16 tcp_select_window(struct sock *sk) * scaled window. */ if (!tp->rx_opt.rcv_wscale && - sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows) + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); @@ -324,7 +321,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); bool bpf_needs_ecn = tcp_bpf_ca_needs_ecn(sk); - bool use_ecn = sock_net(sk)->ipv4.sysctl_tcp_ecn == 1 || + bool use_ecn = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn) == 1 || tcp_ca_needs_ecn(sk) || bpf_needs_ecn; if (!use_ecn) { @@ -346,7 +343,7 @@ static void tcp_ecn_send_syn(struct sock *sk, struct sk_buff *skb) static void tcp_ecn_clear_syn(struct sock *sk, struct sk_buff *skb) { - if (sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_ecn_fallback)) /* tp->ecn_flags are cleared at a later point in time when * SYN ACK is ultimatively being received. */ @@ -791,18 +788,18 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, opts->mss = tcp_advertise_mss(sk); remaining -= TCPOLEN_MSS_ALIGNED; - if (likely(sock_net(sk)->ipv4.sysctl_tcp_timestamps && !*md5)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps) && !*md5)) { opts->options |= OPTION_TS; opts->tsval = tcp_skb_timestamp(skb) + tp->tsoffset; opts->tsecr = tp->rx_opt.ts_recent; remaining -= TCPOLEN_TSTAMP_ALIGNED; } - if (likely(sock_net(sk)->ipv4.sysctl_tcp_window_scaling)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling))) { opts->ws = tp->rx_opt.rcv_wscale; opts->options |= OPTION_WSCALE; remaining -= TCPOLEN_WSCALE_ALIGNED; } - if (likely(sock_net(sk)->ipv4.sysctl_tcp_sack)) { + if (likely(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_sack))) { opts->options |= OPTION_SACK_ADVERTISE; if (unlikely(!(OPTION_TS & opts->options))) remaining -= TCPOLEN_SACKPERM_ALIGNED; @@ -1719,7 +1716,8 @@ static inline int __tcp_mtu_to_mss(struct sock *sk, int pmtu) mss_now -= icsk->icsk_ext_hdr_len; /* Then reserve room for full set of TCP options and 8 bytes of data */ - mss_now = max(mss_now, sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss); + mss_now = max(mss_now, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_snd_mss)); return mss_now; } @@ -1762,10 +1760,10 @@ void tcp_mtup_init(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct net *net = sock_net(sk); - icsk->icsk_mtup.enabled = net->ipv4.sysctl_tcp_mtu_probing > 1; + icsk->icsk_mtup.enabled = READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing) > 1; icsk->icsk_mtup.search_high = tp->rx_opt.mss_clamp + sizeof(struct tcphdr) + icsk->icsk_af_ops->net_header_len; - icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, net->ipv4.sysctl_tcp_base_mss); + icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, READ_ONCE(net->ipv4.sysctl_tcp_base_mss)); icsk->icsk_mtup.probe_size = 0; if (icsk->icsk_mtup.enabled) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; @@ -1897,7 +1895,7 @@ static void tcp_cwnd_validate(struct sock *sk, bool is_cwnd_limited) if (tp->packets_out > tp->snd_cwnd_used) tp->snd_cwnd_used = tp->packets_out; - if (sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_slow_start_after_idle) && (s32)(tcp_jiffies32 - tp->snd_cwnd_stamp) >= inet_csk(sk)->icsk_rto && !ca_ops->cong_control) tcp_cwnd_application_limited(sk); @@ -1975,7 +1973,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, bytes = sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift); - r = tcp_min_rtt(tcp_sk(sk)) >> sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log; + r = tcp_min_rtt(tcp_sk(sk)) >> READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_tso_rtt_log); if (r < BITS_PER_TYPE(sk->sk_gso_max_size)) bytes += sk->sk_gso_max_size >> r; @@ -1994,7 +1992,7 @@ static u32 tcp_tso_segs(struct sock *sk, unsigned int mss_now) min_tso = ca_ops->min_tso_segs ? ca_ops->min_tso_segs(sk) : - sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs; + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_min_tso_segs); tso_segs = tcp_tso_autosize(sk, mss_now, min_tso); return min_t(u32, tso_segs, sk->sk_gso_max_segs); @@ -2282,7 +2280,7 @@ static inline void tcp_mtu_check_reprobe(struct sock *sk) u32 interval; s32 delta; - interval = net->ipv4.sysctl_tcp_probe_interval; + interval = READ_ONCE(net->ipv4.sysctl_tcp_probe_interval); delta = tcp_jiffies32 - icsk->icsk_mtup.probe_timestamp; if (unlikely(delta >= interval * HZ)) { int mss = tcp_current_mss(sk); @@ -2366,7 +2364,7 @@ static int tcp_mtu_probe(struct sock *sk) * probing process by not resetting search range to its orignal. */ if (probe_size > tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_high) || - interval < net->ipv4.sysctl_tcp_probe_threshold) { + interval < READ_ONCE(net->ipv4.sysctl_tcp_probe_threshold)) { /* Check whether enough time has elaplased for * another round of probing. */ @@ -2506,7 +2504,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, - sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes)); limit <<= factor; if (static_branch_unlikely(&tcp_tx_delay_enabled) && @@ -2740,7 +2738,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) if (rcu_access_pointer(tp->fastopen_rsk)) return false; - early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; + early_retrans = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_early_retrans); /* Schedule a loss probe in 2*RTT for SACK capable connections * not in loss recovery, that are either limited by cwnd or application. */ @@ -3104,7 +3102,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, struct sk_buff *skb = to, *tmp; bool first = true; - if (!sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retrans_collapse)) return; if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_SYN) return; @@ -3646,7 +3644,7 @@ static void tcp_connect_init(struct sock *sk) * See tcp_input.c:tcp_rcv_state_process case TCP_SYN_SENT. */ tp->tcp_header_len = sizeof(struct tcphdr); - if (sock_net(sk)->ipv4.sysctl_tcp_timestamps) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_timestamps)) tp->tcp_header_len += TCPOLEN_TSTAMP_ALIGNED; #ifdef CONFIG_TCP_MD5SIG @@ -3682,7 +3680,7 @@ static void tcp_connect_init(struct sock *sk) tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, &tp->window_clamp, - sock_net(sk)->ipv4.sysctl_tcp_window_scaling, + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_window_scaling), &rcv_wscale, rcv_wnd); @@ -4089,7 +4087,7 @@ void tcp_send_probe0(struct sock *sk) icsk->icsk_probes_out++; if (err <= 0) { - if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) + if (icsk->icsk_backoff < READ_ONCE(net->ipv4.sysctl_tcp_retries2)) icsk->icsk_backoff++; timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 48f30e7209f2..50abaa941387 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -14,7 +14,8 @@ static u32 tcp_rack_reo_wnd(const struct sock *sk) return 0; if (tp->sacked_out >= tp->reordering && - !(sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_NO_DUPTHRESH)) + !(READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_NO_DUPTHRESH)) return 0; } @@ -187,7 +188,8 @@ void tcp_rack_update_reo_wnd(struct sock *sk, struct rate_sample *rs) { struct tcp_sock *tp = tcp_sk(sk); - if (sock_net(sk)->ipv4.sysctl_tcp_recovery & TCP_RACK_STATIC_REO_WND || + if ((READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_recovery) & + TCP_RACK_STATIC_REO_WND) || !rs->prior_delivered) return; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 20cf4a98c69d..50bba370486e 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -143,7 +143,7 @@ static int tcp_out_of_resources(struct sock *sk, bool do_reset) */ static int tcp_orphan_retries(struct sock *sk, bool alive) { - int retries = sock_net(sk)->ipv4.sysctl_tcp_orphan_retries; /* May be zero. */ + int retries = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_orphan_retries); /* May be zero. */ /* We know from an ICMP that something is wrong. */ if (sk->sk_err_soft && !alive) @@ -163,7 +163,7 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) int mss; /* Black hole detection */ - if (!net->ipv4.sysctl_tcp_mtu_probing) + if (!READ_ONCE(net->ipv4.sysctl_tcp_mtu_probing)) return; if (!icsk->icsk_mtup.enabled) { @@ -171,9 +171,9 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) icsk->icsk_mtup.probe_timestamp = tcp_jiffies32; } else { mss = tcp_mtu_to_mss(sk, icsk->icsk_mtup.search_low) >> 1; - mss = min(net->ipv4.sysctl_tcp_base_mss, mss); - mss = max(mss, net->ipv4.sysctl_tcp_mtu_probe_floor); - mss = max(mss, net->ipv4.sysctl_tcp_min_snd_mss); + mss = min(READ_ONCE(net->ipv4.sysctl_tcp_base_mss), mss); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_mtu_probe_floor)); + mss = max(mss, READ_ONCE(net->ipv4.sysctl_tcp_min_snd_mss)); icsk->icsk_mtup.search_low = tcp_mss_to_mtu(sk, mss); } tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -239,17 +239,18 @@ static int tcp_write_timeout(struct sock *sk) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) __dst_negative_advice(sk); - retry_until = icsk->icsk_syn_retries ? : net->ipv4.sysctl_tcp_syn_retries; + retry_until = icsk->icsk_syn_retries ? : + READ_ONCE(net->ipv4.sysctl_tcp_syn_retries); expired = icsk->icsk_retransmits >= retry_until; } else { - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1, 0)) { + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1), 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); __dst_negative_advice(sk); } - retry_until = net->ipv4.sysctl_tcp_retries2; + retry_until = READ_ONCE(net->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = icsk->icsk_rto < TCP_RTO_MAX; @@ -380,7 +381,7 @@ static void tcp_probe_timer(struct sock *sk) msecs_to_jiffies(icsk->icsk_user_timeout)) goto abort; - max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; + max_probes = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_retries2); if (sock_flag(sk, SOCK_DEAD)) { const bool alive = inet_csk_rto_backoff(icsk, TCP_RTO_MAX) < TCP_RTO_MAX; @@ -406,12 +407,15 @@ abort: tcp_write_err(sk); static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); - int max_retries = icsk->icsk_syn_retries ? : - sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); + int max_retries; req->rsk_ops->syn_ack_timeout(req); + /* add one more retry for fastopen */ + max_retries = icsk->icsk_syn_retries ? : + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_synack_retries) + 1; + if (req->num_timeout >= max_retries) { tcp_write_err(sk); return; @@ -574,7 +578,7 @@ out_reset_timer: * linear-timeout retransmissions into a black hole */ if (sk->sk_state == TCP_ESTABLISHED && - (tp->thin_lto || net->ipv4.sysctl_tcp_thin_linear_timeouts) && + (tp->thin_lto || READ_ONCE(net->ipv4.sysctl_tcp_thin_linear_timeouts)) && tcp_stream_is_thin(tp) && icsk->icsk_retransmits <= TCP_THIN_LINEAR_RETRIES) { icsk->icsk_backoff = 0; @@ -585,7 +589,7 @@ out_reset_timer: } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, tcp_clamp_rto_to_user_timeout(sk), TCP_RTO_MAX); - if (retransmits_timed_out(sk, net->ipv4.sysctl_tcp_retries1 + 1, 0)) + if (retransmits_timed_out(sk, READ_ONCE(net->ipv4.sysctl_tcp_retries1) + 1, 0)) __sk_dst_reset(sk); out:; diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index bf2e5e5fe142..658bfed1df8b 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -7,6 +7,7 @@ menuconfig IPV6 tristate "The IPv6 protocol" default y + select CRYPTO_LIB_SHA1 help Support for IP version 6 (IPv6). diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 1b1932502e9e..49cc6587dd77 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1109,10 +1109,6 @@ ipv6_add_addr(struct inet6_dev *idev, struct ifa6_config *cfg, goto out; } - if (net->ipv6.devconf_all->disable_policy || - idev->cnf.disable_policy) - f6i->dst_nopolicy = true; - neigh_parms_data_state_setall(idev->nd_parms); ifa->addr = *cfg->pfx; @@ -5172,9 +5168,9 @@ next: fillargs->event = RTM_GETMULTICAST; /* multicast address */ - for (ifmca = rcu_dereference(idev->mc_list); + for (ifmca = rtnl_dereference(idev->mc_list); ifmca; - ifmca = rcu_dereference(ifmca->next), ip_idx++) { + ifmca = rtnl_dereference(ifmca->next), ip_idx++) { if (ip_idx < s_ip_idx) continue; err = inet6_fill_ifmcaddr(skb, ifmca, fillargs); diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 70564ddccc46..6f354f8be2c5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -226,7 +226,7 @@ lookup_protocol: RCU_INIT_POINTER(inet->mc_list, NULL); inet->rcv_tos = 0; - if (net->ipv4.sysctl_ip_no_pmtu_disc) + if (READ_ONCE(net->ipv4.sysctl_ip_no_pmtu_disc)) inet->pmtudisc = IP_PMTUDISC_DONT; else inet->pmtudisc = IP_PMTUDISC_WANT; diff --git a/net/ipv6/icmp.c b/net/ipv6/icmp.c index 61770220774e..9d92d51c4757 100644 --- a/net/ipv6/icmp.c +++ b/net/ipv6/icmp.c @@ -925,7 +925,7 @@ static int icmpv6_rcv(struct sk_buff *skb) break; case ICMPV6_EXT_ECHO_REQUEST: if (!net->ipv6.sysctl.icmpv6_echo_ignore_all && - net->ipv4.sysctl_icmp_echo_enable_probe) + READ_ONCE(net->ipv4.sysctl_icmp_echo_enable_probe)) icmpv6_echo_reply(skb); break; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 4e37f7c29900..a9051df0625d 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -939,7 +939,6 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, __be16 proto; __u32 mtu; int nhoff; - int thoff; if (!pskb_inet_may_pull(skb)) goto tx_err; @@ -960,10 +959,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) truncate = true; - thoff = skb_transport_header(skb) - skb_mac_header(skb); - if (skb->protocol == htons(ETH_P_IPV6) && - (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) - truncate = true; + if (skb->protocol == htons(ETH_P_IPV6)) { + int thoff; + + if (skb_transport_header_was_set(skb)) + thoff = skb_transport_header(skb) - skb_mac_header(skb); + else + thoff = nhoff + sizeof(struct ipv6hdr); + if (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff) + truncate = true; + } if (skb_cow_head(skb, dev->needed_headroom ?: t->hlen)) goto tx_err; diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 0322cc86b84e..e1ebf5e42ebe 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -45,20 +45,23 @@ #include <net/inet_ecn.h> #include <net/dst_metadata.h> -INDIRECT_CALLABLE_DECLARE(void tcp_v6_early_demux(struct sk_buff *)); static void ip6_rcv_finish_core(struct net *net, struct sock *sk, struct sk_buff *skb) { - void (*edemux)(struct sk_buff *skb); - - if (net->ipv4.sysctl_ip_early_demux && !skb_dst(skb) && skb->sk == NULL) { - const struct inet6_protocol *ipprot; - - ipprot = rcu_dereference(inet6_protos[ipv6_hdr(skb)->nexthdr]); - if (ipprot && (edemux = READ_ONCE(ipprot->early_demux))) - INDIRECT_CALL_2(edemux, tcp_v6_early_demux, - udp_v6_early_demux, skb); + if (READ_ONCE(net->ipv4.sysctl_ip_early_demux) && + !skb_dst(skb) && !skb->sk) { + switch (ipv6_hdr(skb)->nexthdr) { + case IPPROTO_TCP: + if (READ_ONCE(net->ipv4.sysctl_tcp_early_demux)) + tcp_v6_early_demux(skb); + break; + case IPPROTO_UDP: + if (READ_ONCE(net->ipv4.sysctl_udp_early_demux)) + udp_v6_early_demux(skb); + break; + } } + if (!skb_valid_dst(skb)) ip6_route_input(skb); } diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 77e3f5970ce4..897ca4f9b791 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1464,6 +1464,7 @@ static int __ip6_append_data(struct sock *sk, int copy; int err; int offset = 0; + bool zc = false; u32 tskey = 0; struct rt6_info *rt = (struct rt6_info *)cork->dst; struct ipv6_txoptions *opt = v6_cork->opt; @@ -1541,17 +1542,35 @@ emsgsize: rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; - if (flags & MSG_ZEROCOPY && length && sock_flag(sk, SOCK_ZEROCOPY)) { - uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); - if (!uarg) - return -ENOBUFS; - extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ - if (rt->dst.dev->features & NETIF_F_SG && - csummode == CHECKSUM_PARTIAL) { - paged = true; - } else { - uarg->zerocopy = 0; - skb_zcopy_set(skb, uarg, &extra_uref); + if ((flags & MSG_ZEROCOPY) && length) { + struct msghdr *msg = from; + + if (getfrag == ip_generic_getfrag && msg->msg_ubuf) { + if (skb_zcopy(skb) && msg->msg_ubuf != skb_zcopy(skb)) + return -EINVAL; + + /* Leave uarg NULL if can't zerocopy, callers should + * be able to handle it. + */ + if ((rt->dst.dev->features & NETIF_F_SG) && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + uarg = msg->msg_ubuf; + } + } else if (sock_flag(sk, SOCK_ZEROCOPY)) { + uarg = msg_zerocopy_realloc(sk, length, skb_zcopy(skb)); + if (!uarg) + return -ENOBUFS; + extra_uref = !skb_zcopy(skb); /* only ref on new uarg */ + if (rt->dst.dev->features & NETIF_F_SG && + csummode == CHECKSUM_PARTIAL) { + paged = true; + zc = true; + } else { + uarg->zerocopy = 0; + skb_zcopy_set(skb, uarg, &extra_uref); + } } } @@ -1630,9 +1649,12 @@ alloc_new_skb: (fraglen + alloc_extra < SKB_MAX_ALLOC || !(rt->dst.dev->features & NETIF_F_SG))) alloclen = fraglen; - else { + else if (!zc) { alloclen = min_t(int, fraglen, MAX_HEADER); pagedlen = fraglen - alloclen; + } else { + alloclen = fragheaderlen + transhdrlen; + pagedlen = datalen - transhdrlen; } alloclen += alloc_extra; @@ -1742,13 +1764,14 @@ alloc_new_skb: err = -EFAULT; goto error; } - } else if (!uarg || !uarg->zerocopy) { + } else if (!zc) { int i = skb_shinfo(skb)->nr_frags; err = -ENOMEM; if (!sk_page_frag_refill(sk, pfrag)) goto error; + skb_zcopy_downgrade_managed(skb); if (!skb_can_coalesce(skb, i, pfrag->page, pfrag->offset)) { err = -EMSGSIZE; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 7f695c39d9a8..87c699d57b36 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1522,7 +1522,6 @@ static void mld_query_work(struct work_struct *work) if (++cnt >= MLD_MAX_QUEUE) { rework = true; - schedule_delayed_work(&idev->mc_query_work, 0); break; } } @@ -1533,8 +1532,10 @@ static void mld_query_work(struct work_struct *work) __mld_query_work(skb); mutex_unlock(&idev->mc_lock); - if (!rework) - in6_dev_put(idev); + if (rework && queue_delayed_work(mld_wq, &idev->mc_query_work, 0)) + return; + + in6_dev_put(idev); } /* called with rcu_read_lock() */ @@ -1624,7 +1625,6 @@ static void mld_report_work(struct work_struct *work) if (++cnt >= MLD_MAX_QUEUE) { rework = true; - schedule_delayed_work(&idev->mc_report_work, 0); break; } } @@ -1635,8 +1635,10 @@ static void mld_report_work(struct work_struct *work) __mld_report_work(skb); mutex_unlock(&idev->mc_lock); - if (!rework) - in6_dev_put(idev); + if (rework && queue_delayed_work(mld_wq, &idev->mc_report_work, 0)) + return; + + in6_dev_put(idev); } static bool is_in(struct ifmcaddr6 *pmc, struct ip6_sf_list *psf, int type, diff --git a/net/ipv6/ping.c b/net/ipv6/ping.c index ecf3a553a0dc..8c6c2d82c1cd 100644 --- a/net/ipv6/ping.c +++ b/net/ipv6/ping.c @@ -22,6 +22,11 @@ #include <linux/proc_fs.h> #include <net/ping.h> +static void ping_v6_destroy(struct sock *sk) +{ + inet6_destroy_sock(sk); +} + /* Compatibility glue so we can support IPv6 when it's compiled as a module */ static int dummy_ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) @@ -181,6 +186,7 @@ struct proto pingv6_prot = { .owner = THIS_MODULE, .init = ping_init_sock, .close = ping_close, + .destroy = ping_v6_destroy, .connect = ip6_datagram_connect_v6_only, .disconnect = __udp_disconnect, .setsockopt = ipv6_setsockopt, diff --git a/net/ipv6/route.c b/net/ipv6/route.c index d25dc83bac62..916417944ec8 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4569,8 +4569,15 @@ struct fib6_info *addrconf_f6i_alloc(struct net *net, } f6i = ip6_route_info_create(&cfg, gfp_flags, NULL); - if (!IS_ERR(f6i)) + if (!IS_ERR(f6i)) { f6i->dst_nocount = true; + + if (!anycast && + (net->ipv6.devconf_all->disable_policy || + idev->cnf.disable_policy)) + f6i->dst_nopolicy = true; + } + return f6i; } @@ -5734,7 +5741,7 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, if (nexthop_is_blackhole(rt->nh)) rtm->rtm_type = RTN_BLACKHOLE; - if (net->ipv4.sysctl_nexthop_compat_mode && + if (READ_ONCE(net->ipv4.sysctl_nexthop_compat_mode) && rt6_fill_node_nexthop(skb, rt->nh, &nh_flags) < 0) goto nla_put_failure; diff --git a/net/ipv6/seg6_hmac.c b/net/ipv6/seg6_hmac.c index 6de01185cc68..d43c50a7310d 100644 --- a/net/ipv6/seg6_hmac.c +++ b/net/ipv6/seg6_hmac.c @@ -406,7 +406,6 @@ int __net_init seg6_hmac_net_init(struct net *net) return rhashtable_init(&sdata->hmac_infos, &rht_params); } -EXPORT_SYMBOL(seg6_hmac_net_init); void seg6_hmac_exit(void) { diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index d64855010948..e756ba705fd9 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -189,6 +189,8 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) } #endif + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, hdr, tot_len); return 0; @@ -241,6 +243,8 @@ int seg6_do_srh_inline(struct sk_buff *skb, struct ipv6_sr_hdr *osrh) } #endif + hdr->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); + skb_postpush_rcsum(skb, hdr, sizeof(struct ipv6hdr) + hdrlen); return 0; @@ -302,7 +306,6 @@ static int seg6_do_srh(struct sk_buff *skb) break; } - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); nf_reset_ct(skb); diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 98a34287439c..2cd4a8d3b30a 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -826,7 +826,6 @@ static int input_action_end_b6(struct sk_buff *skb, struct seg6_local_lwt *slwt) if (err) goto drop; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); seg6_lookup_nexthop(skb, NULL, 0); @@ -858,7 +857,6 @@ static int input_action_end_b6_encap(struct sk_buff *skb, if (err) goto drop; - ipv6_hdr(skb)->payload_len = htons(skb->len - sizeof(struct ipv6hdr)); skb_set_transport_header(skb, sizeof(struct ipv6hdr)); seg6_lookup_nexthop(skb, NULL, 0); diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index c0b138c20992..6bcd5e419a08 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -323,8 +323,6 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u kcalloc(cmax, sizeof(*kp), GFP_KERNEL_ACCOUNT | __GFP_NOWARN) : NULL; - rcu_read_lock(); - ca = min(t->prl_count, cmax); if (!kp) { @@ -341,7 +339,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u } } - c = 0; + rcu_read_lock(); for_each_prl_rcu(t->prl) { if (c >= cmax) break; @@ -353,7 +351,7 @@ static int ipip6_tunnel_get_prl(struct net_device *dev, struct ip_tunnel_prl __u if (kprl.addr != htonl(INADDR_ANY)) break; } -out: + rcu_read_unlock(); len = sizeof(*kp) * c; @@ -362,7 +360,7 @@ out: ret = -EFAULT; kfree(kp); - +out: return ret; } diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 9cc123f000fb..5014aa663452 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -141,7 +141,8 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) __u8 rcv_wscale; u32 tsoff = 0; - if (!sock_net(sk)->ipv4.sysctl_tcp_syncookies || !th->ack || th->rst) + if (!READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_syncookies) || + !th->ack || th->rst) goto out; if (tcp_synq_no_recent_overflow(sk)) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f37dd4aa91c6..be09941fe6d9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -546,7 +546,7 @@ static int tcp_v6_send_synack(const struct sock *sk, struct dst_entry *dst, if (np->repflow && ireq->pktopts) fl6->flowlabel = ip6_flowlabel(ipv6_hdr(ireq->pktopts)); - tclass = sock_net(sk)->ipv4.sysctl_tcp_reflect_tos ? + tclass = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) ? (tcp_rsk(req)->syn_tos & ~INET_ECN_MASK) | (np->tclass & INET_ECN_MASK) : np->tclass; @@ -1314,7 +1314,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Set ToS of the new socket based upon the value of incoming SYN. * ECT bits are set later in tcp_init_transfer(). */ - if (sock_net(sk)->ipv4.sysctl_tcp_reflect_tos) + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_reflect_tos)) newnp->tclass = tcp_rsk(req)->syn_tos & ~INET_ECN_MASK; /* Clone native IPv6 options from listening socket (if any) @@ -1822,7 +1822,7 @@ do_time_wait: goto discard_it; } -INDIRECT_CALLABLE_SCOPE void tcp_v6_early_demux(struct sk_buff *skb) +void tcp_v6_early_demux(struct sk_buff *skb) { const struct ipv6hdr *hdr; const struct tcphdr *th; @@ -2176,12 +2176,7 @@ struct proto tcpv6_prot = { }; EXPORT_SYMBOL_GPL(tcpv6_prot); -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol tcpv6_protocol = { - .early_demux = tcp_v6_early_demux, - .early_demux_handler = tcp_v6_early_demux, +static const struct inet6_protocol tcpv6_protocol = { .handler = tcp_v6_rcv, .err_handler = tcp_v6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 55afd7f39c04..e2f2e087a753 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -1052,7 +1052,7 @@ static struct sock *__udp6_lib_demux_lookup(struct net *net, return NULL; } -INDIRECT_CALLABLE_SCOPE void udp_v6_early_demux(struct sk_buff *skb) +void udp_v6_early_demux(struct sk_buff *skb) { struct net *net = dev_net(skb->dev); const struct udphdr *uh; @@ -1660,12 +1660,7 @@ int udpv6_getsockopt(struct sock *sk, int level, int optname, return ipv6_getsockopt(sk, level, optname, optval, optlen); } -/* thinking of making this const? Don't. - * early_demux can change based on sysctl. - */ -static struct inet6_protocol udpv6_protocol = { - .early_demux = udp_v6_early_demux, - .early_demux_handler = udp_v6_early_demux, +static const struct inet6_protocol udpv6_protocol = { .handler = udpv6_rcv, .err_handler = udpv6_err, .flags = INET6_PROTO_NOPOLICY|INET6_PROTO_FINAL, diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index f7896f257e1b..4ddf297f40f2 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -4468,14 +4468,14 @@ EXPORT_SYMBOL_GPL(ieee80211_color_change_finish); void ieeee80211_obss_color_collision_notify(struct ieee80211_vif *vif, - u64 color_bitmap) + u64 color_bitmap, gfp_t gfp) { struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif); if (sdata->vif.color_change_active || sdata->vif.csa_active) return; - cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap); + cfg80211_obss_color_collision_notify(sdata->dev, color_bitmap, gfp); } EXPORT_SYMBOL_GPL(ieeee80211_obss_color_collision_notify); diff --git a/net/mac80211/iface.c b/net/mac80211/iface.c index 41531478437c..1a9ada411879 100644 --- a/net/mac80211/iface.c +++ b/net/mac80211/iface.c @@ -378,6 +378,7 @@ static void ieee80211_do_stop(struct ieee80211_sub_if_data *sdata, bool going_do struct cfg80211_nan_func *func; clear_bit(SDATA_STATE_RUNNING, &sdata->state); + synchronize_rcu(); /* flush _ieee80211_wake_txqs() */ cancel_scan = rcu_access_pointer(local->scan_sdata) == sdata; if (cancel_scan) diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 3c08ae04ddbc..1675f8cb87f1 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -3217,7 +3217,8 @@ ieee80211_rx_check_bss_color_collision(struct ieee80211_rx_data *rx) IEEE80211_HE_OPERATION_BSS_COLOR_MASK); if (color == bss_conf->he_bss_color.color) ieeee80211_obss_color_collision_notify(&rx->sdata->vif, - BIT_ULL(color)); + BIT_ULL(color), + GFP_ATOMIC); } } diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 0e4efc08c762..c425f4fb7c2e 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2818,19 +2818,10 @@ static struct sk_buff *ieee80211_build_hdr(struct ieee80211_sub_if_data *sdata, /* * If the skb is shared we need to obtain our own copy. */ - if (skb_shared(skb)) { - struct sk_buff *tmp_skb = skb; - - /* can't happen -- skb is a clone if info_id != 0 */ - WARN_ON(info_id); - - skb = skb_clone(skb, GFP_ATOMIC); - kfree_skb(tmp_skb); - - if (!skb) { - ret = -ENOMEM; - goto free; - } + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) { + ret = -ENOMEM; + goto free; } hdr.frame_control = fc; @@ -3539,15 +3530,9 @@ static bool ieee80211_xmit_fast(struct ieee80211_sub_if_data *sdata, /* after this point (skb is modified) we cannot return false */ - if (skb_shared(skb)) { - struct sk_buff *tmp_skb = skb; - - skb = skb_clone(skb, GFP_ATOMIC); - kfree_skb(tmp_skb); - - if (!skb) - return true; - } + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return true; if ((hdr->frame_control & cpu_to_le16(IEEE80211_STYPE_QOS_DATA)) && ieee80211_amsdu_aggregate(sdata, sta, fast_tx, skb)) @@ -4437,7 +4422,7 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, struct net_device *dev, struct sta_info *sta, struct ieee80211_key *key, struct sk_buff *skb) { - struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb); + struct ieee80211_tx_info *info; struct ieee80211_local *local = sdata->local; struct tid_ampdu_tx *tid_tx; u8 tid; @@ -4452,6 +4437,11 @@ static void ieee80211_8023_xmit(struct ieee80211_sub_if_data *sdata, test_bit(SDATA_STATE_OFFCHANNEL, &sdata->state)) goto out_free; + skb = skb_share_check(skb, GFP_ATOMIC); + if (unlikely(!skb)) + return; + + info = IEEE80211_SKB_CB(skb); memset(info, 0, sizeof(*info)); ieee80211_aggr_check(sdata, sta, skb); diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 1e26b5235add..dad42d42aa84 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -301,6 +301,9 @@ static void __ieee80211_wake_txqs(struct ieee80211_sub_if_data *sdata, int ac) local_bh_disable(); spin_lock(&fq->lock); + if (!test_bit(SDATA_STATE_RUNNING, &sdata->state)) + goto out; + if (sdata->vif.type == NL80211_IFTYPE_AP) ps = &sdata->bss->ps; diff --git a/net/mac80211/wme.c b/net/mac80211/wme.c index 62c6733e0792..d50480b31750 100644 --- a/net/mac80211/wme.c +++ b/net/mac80211/wme.c @@ -147,8 +147,8 @@ u16 __ieee80211_select_queue(struct ieee80211_sub_if_data *sdata, bool qos; /* all mesh/ocb stations are required to support WME */ - if (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || - sdata->vif.type == NL80211_IFTYPE_OCB) + if (sta && (sdata->vif.type == NL80211_IFTYPE_MESH_POINT || + sdata->vif.type == NL80211_IFTYPE_OCB)) qos = true; else if (sta) qos = sta->sta.wme; diff --git a/net/mptcp/options.c b/net/mptcp/options.c index be3b918a6d15..30d289044e71 100644 --- a/net/mptcp/options.c +++ b/net/mptcp/options.c @@ -765,6 +765,7 @@ static noinline bool mptcp_established_options_rst(struct sock *sk, struct sk_bu opts->suboptions |= OPTION_MPTCP_RST; opts->reset_transient = subflow->reset_transient; opts->reset_reason = subflow->reset_reason; + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX); return true; } @@ -788,6 +789,7 @@ static bool mptcp_established_options_fastclose(struct sock *sk, opts->rcvr_key = msk->remote_key; pr_debug("FASTCLOSE key=%llu", opts->rcvr_key); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); return true; } @@ -809,6 +811,7 @@ static bool mptcp_established_options_mp_fail(struct sock *sk, opts->fail_seq = subflow->map_seq; pr_debug("MP_FAIL fail_seq=%llu", opts->fail_seq); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); return true; } @@ -833,13 +836,11 @@ bool mptcp_established_options(struct sock *sk, struct sk_buff *skb, mptcp_established_options_mp_fail(sk, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFASTCLOSETX); } /* MP_RST can be used with MP_FASTCLOSE and MP_FAIL if there is room */ if (mptcp_established_options_rst(sk, skb, &opt_size, remaining, opts)) { *size += opt_size; remaining -= opt_size; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPRSTTX); } return true; } @@ -966,7 +967,7 @@ static bool check_fully_established(struct mptcp_sock *msk, struct sock *ssk, goto reset; subflow->mp_capable = 0; pr_fallback(msk); - __mptcp_do_fallback(msk); + mptcp_do_fallback(ssk); return false; } @@ -1270,7 +1271,7 @@ raise_win: if (unlikely(th->syn)) new_win = min(new_win, 65535U) << tp->rx_opt.rcv_wscale; if (!tp->rx_opt.rcv_wscale && - sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows) + READ_ONCE(sock_net(ssk)->ipv4.sysctl_tcp_workaround_signed_windows)) new_win = min(new_win, MAX_TCP_WINDOW); else new_win = min(new_win, (65535U << tp->rx_opt.rcv_wscale)); @@ -1583,6 +1584,9 @@ mp_rst: *ptr++ = mptcp_option(MPTCPOPT_MP_PRIO, TCPOLEN_MPTCP_PRIO, opts->backup, TCPOPT_NOP); + + MPTCP_INC_STATS(sock_net((const struct sock *)tp), + MPTCP_MIB_MPPRIOTX); } mp_capable_done: diff --git a/net/mptcp/pm.c b/net/mptcp/pm.c index 59a85220edc9..45e2a48397b9 100644 --- a/net/mptcp/pm.c +++ b/net/mptcp/pm.c @@ -299,23 +299,21 @@ void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); struct mptcp_sock *msk = mptcp_sk(subflow->conn); - struct sock *s = (struct sock *)msk; pr_debug("fail_seq=%llu", fail_seq); if (!READ_ONCE(msk->allow_infinite_fallback)) return; - if (!READ_ONCE(subflow->mp_fail_response_expect)) { + if (!subflow->fail_tout) { pr_debug("send MP_FAIL response and infinite map"); subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPFAILTX); subflow->send_infinite_map = 1; - } else if (!sock_flag(sk, SOCK_DEAD)) { + tcp_send_ack(sk); + } else { pr_debug("MP_FAIL response received"); - - sk_stop_timer(s, &s->sk_timer); + WRITE_ONCE(subflow->fail_tout, 0); } } diff --git a/net/mptcp/pm_netlink.c b/net/mptcp/pm_netlink.c index e099f2a12504..7c7395b58944 100644 --- a/net/mptcp/pm_netlink.c +++ b/net/mptcp/pm_netlink.c @@ -717,9 +717,10 @@ void mptcp_pm_nl_addr_send_ack(struct mptcp_sock *msk) } } -static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, - struct mptcp_addr_info *addr, - u8 bkup) +int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + struct mptcp_addr_info *rem, + u8 bkup) { struct mptcp_subflow_context *subflow; @@ -727,24 +728,29 @@ static int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); - struct sock *sk = (struct sock *)msk; - struct mptcp_addr_info local; + struct mptcp_addr_info local, remote; + bool slow; local_address((struct sock_common *)ssk, &local); if (!mptcp_addresses_equal(&local, addr, addr->port)) continue; + if (rem && rem->family != AF_UNSPEC) { + remote_address((struct sock_common *)ssk, &remote); + if (!mptcp_addresses_equal(&remote, rem, rem->port)) + continue; + } + + slow = lock_sock_fast(ssk); if (subflow->backup != bkup) msk->last_snd = NULL; subflow->backup = bkup; subflow->send_mp_prio = 1; subflow->request_bkup = bkup; - __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPPRIOTX); - spin_unlock_bh(&msk->pm.lock); pr_debug("send ack for mp_prio"); - mptcp_subflow_send_ack(ssk); - spin_lock_bh(&msk->pm.lock); + __mptcp_subflow_send_ack(ssk); + unlock_sock_fast(ssk, slow); return 0; } @@ -801,7 +807,8 @@ static void mptcp_pm_nl_rm_addr_or_subflow(struct mptcp_sock *msk, removed = true; __MPTCP_INC_STATS(sock_net(sk), rm_type); } - __set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap); + if (rm_type == MPTCP_MIB_RMSUBFLOW) + __set_bit(rm_list->ids[i], msk->pm.id_avail_bitmap); if (!removed) continue; @@ -1816,8 +1823,10 @@ static void mptcp_pm_nl_fullmesh(struct mptcp_sock *msk, list.ids[list.nr++] = addr->id; + spin_lock_bh(&msk->pm.lock); mptcp_pm_nl_rm_subflow_received(msk, &list); mptcp_pm_create_subflow_or_signal_addr(msk); + spin_unlock_bh(&msk->pm.lock); } static int mptcp_nl_set_flags(struct net *net, @@ -1835,12 +1844,10 @@ static int mptcp_nl_set_flags(struct net *net, goto next; lock_sock(sk); - spin_lock_bh(&msk->pm.lock); if (changed & MPTCP_PM_ADDR_FLAG_BACKUP) - ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, bkup); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, addr, NULL, bkup); if (changed & MPTCP_PM_ADDR_FLAG_FULLMESH) mptcp_pm_nl_fullmesh(msk, addr); - spin_unlock_bh(&msk->pm.lock); release_sock(sk); next: @@ -1854,6 +1861,9 @@ next: static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) { struct mptcp_pm_addr_entry addr = { .addr = { .family = AF_UNSPEC }, }, *entry; + struct mptcp_pm_addr_entry remote = { .addr = { .family = AF_UNSPEC }, }; + struct nlattr *attr_rem = info->attrs[MPTCP_PM_ATTR_ADDR_REMOTE]; + struct nlattr *token = info->attrs[MPTCP_PM_ATTR_TOKEN]; struct nlattr *attr = info->attrs[MPTCP_PM_ATTR_ADDR]; struct pm_nl_pernet *pernet = genl_info_pm_nl(info); u8 changed, mask = MPTCP_PM_ADDR_FLAG_BACKUP | @@ -1866,6 +1876,12 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) if (ret < 0) return ret; + if (attr_rem) { + ret = mptcp_pm_parse_entry(attr_rem, info, false, &remote); + if (ret < 0) + return ret; + } + if (addr.flags & MPTCP_PM_ADDR_FLAG_BACKUP) bkup = 1; if (addr.addr.family == AF_UNSPEC) { @@ -1874,6 +1890,10 @@ static int mptcp_nl_cmd_set_flags(struct sk_buff *skb, struct genl_info *info) return -EOPNOTSUPP; } + if (token) + return mptcp_userspace_pm_set_flags(sock_net(skb->sk), + token, &addr, &remote, bkup); + spin_lock_bh(&pernet->lock); entry = __lookup_addr(pernet, &addr.addr, lookup_by_id); if (!entry) { diff --git a/net/mptcp/pm_userspace.c b/net/mptcp/pm_userspace.c index f56378e4f597..9e82250cbb70 100644 --- a/net/mptcp/pm_userspace.c +++ b/net/mptcp/pm_userspace.c @@ -5,6 +5,7 @@ */ #include "protocol.h" +#include "mib.h" void mptcp_free_local_addr_list(struct mptcp_sock *msk) { @@ -306,15 +307,11 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, const struct mptcp_addr_info *local, const struct mptcp_addr_info *remote) { - struct sock *sk = &msk->sk.icsk_inet.sk; struct mptcp_subflow_context *subflow; - struct sock *found = NULL; if (local->family != remote->family) return NULL; - lock_sock(sk); - mptcp_for_each_subflow(msk, subflow) { const struct inet_sock *issk; struct sock *ssk; @@ -347,16 +344,11 @@ static struct sock *mptcp_nl_find_ssk(struct mptcp_sock *msk, } if (issk->inet_sport == local->port && - issk->inet_dport == remote->port) { - found = ssk; - goto found; - } + issk->inet_dport == remote->port) + return ssk; } -found: - release_sock(sk); - - return found; + return NULL; } int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) @@ -412,18 +404,51 @@ int mptcp_nl_cmd_sf_destroy(struct sk_buff *skb, struct genl_info *info) } sk = &msk->sk.icsk_inet.sk; + lock_sock(sk); ssk = mptcp_nl_find_ssk(msk, &addr_l, &addr_r); if (ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); mptcp_subflow_shutdown(sk, ssk, RCV_SHUTDOWN | SEND_SHUTDOWN); mptcp_close_ssk(sk, ssk, subflow); + MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_RMSUBFLOW); err = 0; } else { err = -ESRCH; } + release_sock(sk); - destroy_err: +destroy_err: sock_put((struct sock *)msk); return err; } + +int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, + struct mptcp_pm_addr_entry *loc, + struct mptcp_pm_addr_entry *rem, u8 bkup) +{ + struct mptcp_sock *msk; + int ret = -EINVAL; + u32 token_val; + + token_val = nla_get_u32(token); + + msk = mptcp_token_get_sock(net, token_val); + if (!msk) + return ret; + + if (!mptcp_pm_is_userspace(msk)) + goto set_flags_err; + + if (loc->addr.family == AF_UNSPEC || + rem->addr.family == AF_UNSPEC) + goto set_flags_err; + + lock_sock((struct sock *)msk); + ret = mptcp_pm_nl_mp_prio_send_ack(msk, &loc->addr, &rem->addr, bkup); + release_sock((struct sock *)msk); + +set_flags_err: + sock_put((struct sock *)msk); + return ret; +} diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 17e13396024a..7e1518bb6115 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -500,19 +500,24 @@ static void mptcp_set_timeout(struct sock *sk) __mptcp_set_timeout(sk, tout); } -static bool tcp_can_send_ack(const struct sock *ssk) +static inline bool tcp_can_send_ack(const struct sock *ssk) { return !((1 << inet_sk_state_load(ssk)) & (TCPF_SYN_SENT | TCPF_SYN_RECV | TCPF_TIME_WAIT | TCPF_CLOSE | TCPF_LISTEN)); } +void __mptcp_subflow_send_ack(struct sock *ssk) +{ + if (tcp_can_send_ack(ssk)) + tcp_send_ack(ssk); +} + void mptcp_subflow_send_ack(struct sock *ssk) { bool slow; slow = lock_sock_fast(ssk); - if (tcp_can_send_ack(ssk)) - tcp_send_ack(ssk); + __mptcp_subflow_send_ack(ssk); unlock_sock_fast(ssk, slow); } @@ -1245,7 +1250,7 @@ static void mptcp_update_infinite_map(struct mptcp_sock *msk, MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPTX); mptcp_subflow_ctx(ssk)->send_infinite_map = 0; pr_fallback(msk); - __mptcp_do_fallback(msk); + mptcp_do_fallback(ssk); } static int mptcp_sendmsg_frag(struct sock *sk, struct sock *ssk, @@ -1903,7 +1908,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) if (msk->rcvq_space.copied <= msk->rcvq_space.space) goto new_measure; - if (sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf && + if (READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_moderate_rcvbuf) && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK)) { int rcvmem, rcvbuf; u64 rcvwin, grow; @@ -1921,7 +1926,7 @@ static void mptcp_rcv_space_adjust(struct mptcp_sock *msk, int copied) do_div(rcvwin, advmss); rcvbuf = min_t(u64, rcvwin * rcvmem, - sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[2])); if (rcvbuf > sk->sk_rcvbuf) { u32 window_clamp; @@ -2175,21 +2180,6 @@ static void mptcp_retransmit_timer(struct timer_list *t) sock_put(sk); } -static struct mptcp_subflow_context * -mp_fail_response_expect_subflow(struct mptcp_sock *msk) -{ - struct mptcp_subflow_context *subflow, *ret = NULL; - - mptcp_for_each_subflow(msk, subflow) { - if (READ_ONCE(subflow->mp_fail_response_expect)) { - ret = subflow; - break; - } - } - - return ret; -} - static void mptcp_timeout_timer(struct timer_list *t) { struct sock *sk = from_timer(sk, t, sk_timer); @@ -2346,6 +2336,11 @@ static void __mptcp_close_ssk(struct sock *sk, struct sock *ssk, kfree_rcu(subflow, rcu); } else { /* otherwise tcp will dispose of the ssk and subflow ctx */ + if (ssk->sk_state == TCP_LISTEN) { + tcp_set_state(ssk, TCP_CLOSE); + mptcp_subflow_queue_clean(ssk); + inet_csk_listen_stop(ssk); + } __tcp_close(ssk, 0); /* close acquired an extra ref */ @@ -2518,27 +2513,50 @@ reset_timer: mptcp_reset_timer(sk); } +/* schedule the timeout timer for the relevant event: either close timeout + * or mp_fail timeout. The close timeout takes precedence on the mp_fail one + */ +void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout) +{ + struct sock *sk = (struct sock *)msk; + unsigned long timeout, close_timeout; + + if (!fail_tout && !sock_flag(sk, SOCK_DEAD)) + return; + + close_timeout = inet_csk(sk)->icsk_mtup.probe_timestamp - tcp_jiffies32 + jiffies + TCP_TIMEWAIT_LEN; + + /* the close timeout takes precedence on the fail one, and here at least one of + * them is active + */ + timeout = sock_flag(sk, SOCK_DEAD) ? close_timeout : fail_tout; + + sk_reset_timer(sk, &sk->sk_timer, timeout); +} + static void mptcp_mp_fail_no_response(struct mptcp_sock *msk) { - struct mptcp_subflow_context *subflow; - struct sock *ssk; + struct sock *ssk = msk->first; bool slow; - subflow = mp_fail_response_expect_subflow(msk); - if (subflow) { - pr_debug("MP_FAIL doesn't respond, reset the subflow"); + if (!ssk) + return; - ssk = mptcp_subflow_tcp_sock(subflow); - slow = lock_sock_fast(ssk); - mptcp_subflow_reset(ssk); - unlock_sock_fast(ssk, slow); - } + pr_debug("MP_FAIL doesn't respond, reset the subflow"); + + slow = lock_sock_fast(ssk); + mptcp_subflow_reset(ssk); + WRITE_ONCE(mptcp_subflow_ctx(ssk)->fail_tout, 0); + unlock_sock_fast(ssk, slow); + + mptcp_reset_timeout(msk, 0); } static void mptcp_worker(struct work_struct *work) { struct mptcp_sock *msk = container_of(work, struct mptcp_sock, work); struct sock *sk = &msk->sk.icsk_inet.sk; + unsigned long fail_tout; int state; lock_sock(sk); @@ -2575,7 +2593,9 @@ static void mptcp_worker(struct work_struct *work) if (test_and_clear_bit(MPTCP_WORK_RTX, &msk->flags)) __mptcp_retrans(sk); - mptcp_mp_fail_no_response(msk); + fail_tout = msk->first ? READ_ONCE(mptcp_subflow_ctx(msk->first)->fail_tout) : 0; + if (fail_tout && time_after(jiffies, fail_tout)) + mptcp_mp_fail_no_response(msk); unlock: release_sock(sk); @@ -2649,8 +2669,8 @@ static int mptcp_init_sock(struct sock *sk) mptcp_ca_reset(sk); sk_sockets_allocated_inc(sk); - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; + sk->sk_rcvbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); + sk->sk_sndbuf = READ_ONCE(sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); return 0; } @@ -2822,6 +2842,7 @@ static void __mptcp_destroy_sock(struct sock *sk) static void mptcp_close(struct sock *sk, long timeout) { struct mptcp_subflow_context *subflow; + struct mptcp_sock *msk = mptcp_sk(sk); bool do_cancel_work = false; lock_sock(sk); @@ -2840,10 +2861,16 @@ static void mptcp_close(struct sock *sk, long timeout) cleanup: /* orphan all the subflows */ inet_csk(sk)->icsk_mtup.probe_timestamp = tcp_jiffies32; - mptcp_for_each_subflow(mptcp_sk(sk), subflow) { + mptcp_for_each_subflow(msk, subflow) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); bool slow = lock_sock_fast_nested(ssk); + /* since the close timeout takes precedence on the fail one, + * cancel the latter + */ + if (ssk == msk->first) + subflow->fail_tout = 0; + sock_orphan(ssk); unlock_sock_fast(ssk, slow); } @@ -2852,13 +2879,13 @@ cleanup: sock_hold(sk); pr_debug("msk=%p state=%d", sk, sk->sk_state); if (mptcp_sk(sk)->token) - mptcp_event(MPTCP_EVENT_CLOSED, mptcp_sk(sk), NULL, GFP_KERNEL); + mptcp_event(MPTCP_EVENT_CLOSED, msk, NULL, GFP_KERNEL); if (sk->sk_state == TCP_CLOSE) { __mptcp_destroy_sock(sk); do_cancel_work = true; } else { - sk_reset_timer(sk, &sk->sk_timer, jiffies + TCP_TIMEWAIT_LEN); + mptcp_reset_timeout(msk, 0); } release_sock(sk); if (do_cancel_work) @@ -2892,12 +2919,12 @@ static void mptcp_copy_inaddrs(struct sock *msk, const struct sock *ssk) static int mptcp_disconnect(struct sock *sk, int flags) { - struct mptcp_subflow_context *subflow; + struct mptcp_subflow_context *subflow, *tmp; struct mptcp_sock *msk = mptcp_sk(sk); inet_sk_state_store(sk, TCP_CLOSE); - mptcp_for_each_subflow(msk, subflow) { + list_for_each_entry_safe(subflow, tmp, &msk->conn_list, node) { struct sock *ssk = mptcp_subflow_tcp_sock(subflow); __mptcp_close_ssk(sk, ssk, subflow, MPTCP_CF_FASTCLOSE); diff --git a/net/mptcp/protocol.h b/net/mptcp/protocol.h index 200f89f6d62f..480c5320b86e 100644 --- a/net/mptcp/protocol.h +++ b/net/mptcp/protocol.h @@ -306,6 +306,7 @@ struct mptcp_sock { u32 setsockopt_seq; char ca_name[TCP_CA_NAME_MAX]; + struct mptcp_sock *dl_next; }; #define mptcp_data_lock(sk) spin_lock_bh(&(sk)->sk_lock.slock) @@ -468,7 +469,6 @@ struct mptcp_subflow_context { local_id_valid : 1, /* local_id is correctly initialized */ valid_csum_seen : 1; /* at least one csum validated */ enum mptcp_data_avail data_avail; - bool mp_fail_response_expect; u32 remote_nonce; u64 thmac; u32 local_nonce; @@ -482,6 +482,7 @@ struct mptcp_subflow_context { u8 stale_count; long delegated_status; + unsigned long fail_tout; ); @@ -606,8 +607,10 @@ void __init mptcp_subflow_init(void); void mptcp_subflow_shutdown(struct sock *sk, struct sock *ssk, int how); void mptcp_close_ssk(struct sock *sk, struct sock *ssk, struct mptcp_subflow_context *subflow); +void __mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_send_ack(struct sock *ssk); void mptcp_subflow_reset(struct sock *ssk); +void mptcp_subflow_queue_clean(struct sock *ssk); void mptcp_sock_graft(struct sock *sk, struct socket *parent); struct socket *__mptcp_nmpc_socket(const struct mptcp_sock *msk); @@ -662,6 +665,7 @@ void mptcp_get_options(const struct sk_buff *skb, void mptcp_finish_connect(struct sock *sk); void __mptcp_set_connected(struct sock *sk); +void mptcp_reset_timeout(struct mptcp_sock *msk, unsigned long fail_tout); static inline bool mptcp_is_fully_established(struct sock *sk) { return inet_sk_state_load(sk) == TCP_ESTABLISHED && @@ -768,6 +772,10 @@ void mptcp_pm_rm_addr_received(struct mptcp_sock *msk, const struct mptcp_rm_list *rm_list); void mptcp_pm_mp_prio_received(struct sock *sk, u8 bkup); void mptcp_pm_mp_fail_received(struct sock *sk, u64 fail_seq); +int mptcp_pm_nl_mp_prio_send_ack(struct mptcp_sock *msk, + struct mptcp_addr_info *addr, + struct mptcp_addr_info *rem, + u8 bkup); bool mptcp_pm_alloc_anno_list(struct mptcp_sock *msk, const struct mptcp_pm_addr_entry *entry); void mptcp_pm_free_anno_list(struct mptcp_sock *msk); @@ -784,7 +792,9 @@ int mptcp_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, int mptcp_userspace_pm_get_flags_and_ifindex_by_id(struct mptcp_sock *msk, unsigned int id, u8 *flags, int *ifindex); - +int mptcp_userspace_pm_set_flags(struct net *net, struct nlattr *token, + struct mptcp_pm_addr_entry *loc, + struct mptcp_pm_addr_entry *rem, u8 bkup); int mptcp_pm_announce_addr(struct mptcp_sock *msk, const struct mptcp_addr_info *addr, bool echo); @@ -926,12 +936,25 @@ static inline void __mptcp_do_fallback(struct mptcp_sock *msk) set_bit(MPTCP_FALLBACK_DONE, &msk->flags); } -static inline void mptcp_do_fallback(struct sock *sk) +static inline void mptcp_do_fallback(struct sock *ssk) { - struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(sk); - struct mptcp_sock *msk = mptcp_sk(subflow->conn); + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + struct sock *sk = subflow->conn; + struct mptcp_sock *msk; + msk = mptcp_sk(sk); __mptcp_do_fallback(msk); + if (READ_ONCE(msk->snd_data_fin_enable) && !(ssk->sk_shutdown & SEND_SHUTDOWN)) { + gfp_t saved_allocation = ssk->sk_allocation; + + /* we are in a atomic (BH) scope, override ssk default for data + * fin allocation + */ + ssk->sk_allocation = GFP_ATOMIC; + ssk->sk_shutdown |= SEND_SHUTDOWN; + tcp_shutdown(ssk, SEND_SHUTDOWN); + ssk->sk_allocation = saved_allocation; + } } #define pr_fallback(a) pr_debug("%s:fallback to TCP (msk=%p)", __func__, a) diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 8841e8cd9ad8..af28f3b60389 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -843,7 +843,8 @@ enum mapping_status { MAPPING_INVALID, MAPPING_EMPTY, MAPPING_DATA_FIN, - MAPPING_DUMMY + MAPPING_DUMMY, + MAPPING_BAD_CSUM }; static void dbg_bad_map(struct mptcp_subflow_context *subflow, u32 ssn) @@ -958,11 +959,7 @@ static enum mapping_status validate_data_csum(struct sock *ssk, struct sk_buff * subflow->map_data_csum); if (unlikely(csum)) { MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_DATACSUMERR); - if (subflow->mp_join || subflow->valid_csum_seen) { - subflow->send_mp_fail = 1; - MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_MPFAILTX); - } - return subflow->mp_join ? MAPPING_INVALID : MAPPING_DUMMY; + return MAPPING_BAD_CSUM; } subflow->valid_csum_seen = 1; @@ -974,7 +971,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); bool csum_reqd = READ_ONCE(msk->csum_enabled); - struct sock *sk = (struct sock *)msk; struct mptcp_ext *mpext; struct sk_buff *skb; u16 data_len; @@ -1016,9 +1012,6 @@ static enum mapping_status get_mapping_status(struct sock *ssk, pr_debug("infinite mapping received"); MPTCP_INC_STATS(sock_net(ssk), MPTCP_MIB_INFINITEMAPRX); subflow->map_data_len = 0; - if (!sock_flag(ssk, SOCK_DEAD)) - sk_stop_timer(sk, &sk->sk_timer); - return MAPPING_INVALID; } @@ -1165,6 +1158,33 @@ static bool subflow_can_fallback(struct mptcp_subflow_context *subflow) return !subflow->fully_established; } +static void mptcp_subflow_fail(struct mptcp_sock *msk, struct sock *ssk) +{ + struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); + unsigned long fail_tout; + + /* greceful failure can happen only on the MPC subflow */ + if (WARN_ON_ONCE(ssk != READ_ONCE(msk->first))) + return; + + /* since the close timeout take precedence on the fail one, + * no need to start the latter when the first is already set + */ + if (sock_flag((struct sock *)msk, SOCK_DEAD)) + return; + + /* we don't need extreme accuracy here, use a zero fail_tout as special + * value meaning no fail timeout at all; + */ + fail_tout = jiffies + TCP_RTO_MAX; + if (!fail_tout) + fail_tout = 1; + WRITE_ONCE(subflow->fail_tout, fail_tout); + tcp_send_ack(ssk); + + mptcp_reset_timeout(msk, subflow->fail_tout); +} + static bool subflow_check_data_avail(struct sock *ssk) { struct mptcp_subflow_context *subflow = mptcp_subflow_ctx(ssk); @@ -1184,10 +1204,8 @@ static bool subflow_check_data_avail(struct sock *ssk) status = get_mapping_status(ssk, msk); trace_subflow_check_data_avail(status, skb_peek(&ssk->sk_receive_queue)); - if (unlikely(status == MAPPING_INVALID)) - goto fallback; - - if (unlikely(status == MAPPING_DUMMY)) + if (unlikely(status == MAPPING_INVALID || status == MAPPING_DUMMY || + status == MAPPING_BAD_CSUM)) goto fallback; if (status != MAPPING_OK) @@ -1229,22 +1247,17 @@ no_data: fallback: if (!__mptcp_check_fallback(msk)) { /* RFC 8684 section 3.7. */ - if (subflow->send_mp_fail) { + if (status == MAPPING_BAD_CSUM && + (subflow->mp_join || subflow->valid_csum_seen)) { + subflow->send_mp_fail = 1; + if (!READ_ONCE(msk->allow_infinite_fallback)) { - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMIDDLEBOX; - tcp_send_active_reset(ssk, GFP_ATOMIC); - while ((skb = skb_peek(&ssk->sk_receive_queue))) - sk_eat_skb(ssk, skb); - } else if (!sock_flag(ssk, SOCK_DEAD)) { - WRITE_ONCE(subflow->mp_fail_response_expect, true); - sk_reset_timer((struct sock *)msk, - &((struct sock *)msk)->sk_timer, - jiffies + TCP_RTO_MAX); + goto reset; } - WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); + mptcp_subflow_fail(msk, ssk); + WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_DATA_AVAIL); return true; } @@ -1252,16 +1265,20 @@ fallback: /* fatal protocol error, close the socket. * subflow_error_report() will introduce the appropriate barriers */ - ssk->sk_err = EBADMSG; - tcp_set_state(ssk, TCP_CLOSE); subflow->reset_transient = 0; subflow->reset_reason = MPTCP_RST_EMPTCP; + +reset: + ssk->sk_err = EBADMSG; + tcp_set_state(ssk, TCP_CLOSE); + while ((skb = skb_peek(&ssk->sk_receive_queue))) + sk_eat_skb(ssk, skb); tcp_send_active_reset(ssk, GFP_ATOMIC); WRITE_ONCE(subflow->data_avail, MPTCP_SUBFLOW_NODATA); return false; } - __mptcp_do_fallback(msk); + mptcp_do_fallback(ssk); } skb = skb_peek(&ssk->sk_receive_queue); @@ -1516,7 +1533,7 @@ int __mptcp_subflow_connect(struct sock *sk, const struct mptcp_addr_info *loc, mptcp_sock_graft(ssk, sk->sk_socket); iput(SOCK_INODE(sf)); WRITE_ONCE(msk->allow_infinite_fallback, false); - return err; + return 0; failed_unlink: list_del(&subflow->node); @@ -1706,6 +1723,58 @@ static void subflow_state_change(struct sock *sk) } } +void mptcp_subflow_queue_clean(struct sock *listener_ssk) +{ + struct request_sock_queue *queue = &inet_csk(listener_ssk)->icsk_accept_queue; + struct mptcp_sock *msk, *next, *head = NULL; + struct request_sock *req; + + /* build a list of all unaccepted mptcp sockets */ + spin_lock_bh(&queue->rskq_lock); + for (req = queue->rskq_accept_head; req; req = req->dl_next) { + struct mptcp_subflow_context *subflow; + struct sock *ssk = req->sk; + struct mptcp_sock *msk; + + if (!sk_is_mptcp(ssk)) + continue; + + subflow = mptcp_subflow_ctx(ssk); + if (!subflow || !subflow->conn) + continue; + + /* skip if already in list */ + msk = mptcp_sk(subflow->conn); + if (msk->dl_next || msk == head) + continue; + + msk->dl_next = head; + head = msk; + } + spin_unlock_bh(&queue->rskq_lock); + if (!head) + return; + + /* can't acquire the msk socket lock under the subflow one, + * or will cause ABBA deadlock + */ + release_sock(listener_ssk); + + for (msk = head; msk; msk = next) { + struct sock *sk = (struct sock *)msk; + bool slow; + + slow = lock_sock_fast_nested(sk); + next = msk->dl_next; + msk->first = NULL; + msk->dl_next = NULL; + unlock_sock_fast(sk, slow); + } + + /* we are still under the listener msk socket lock */ + lock_sock_nested(listener_ssk, SINGLE_DEPTH_NESTING); +} + static int subflow_ulp_init(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index 78814417d753..80713febfac6 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -1803,7 +1803,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, pdev = to_platform_device(dev->dev.parent); if (pdev) { np = pdev->dev.of_node; - if (np && of_get_property(np, "mlx,multi-host", NULL)) + if (np && (of_get_property(np, "mellanox,multi-host", NULL) || + of_get_property(np, "mlx,multi-host", NULL))) ndp->mlx_multi_host = true; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 082a2fd8d85b..369aeabb94fe 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -729,6 +729,9 @@ static void nf_ct_gc_expired(struct nf_conn *ct) if (!refcount_inc_not_zero(&ct->ct_general.use)) return; + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + if (nf_ct_should_gc(ct)) nf_ct_kill(ct); @@ -795,6 +798,9 @@ __nf_conntrack_find_get(struct net *net, const struct nf_conntrack_zone *zone, */ ct = nf_ct_tuplehash_to_ctrack(h); if (likely(refcount_inc_not_zero(&ct->ct_general.use))) { + /* re-check key after refcount */ + smp_acquire__after_ctrl_dep(); + if (likely(nf_ct_key_equal(h, tuple, zone, net))) goto found; @@ -1387,6 +1393,9 @@ static unsigned int early_drop_list(struct net *net, if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue; + /* load ->ct_net and ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + /* kill only if still in same netns -- might have moved due to * SLAB_TYPESAFE_BY_RCU rules. * @@ -1536,6 +1545,9 @@ static void gc_worker(struct work_struct *work) if (!refcount_inc_not_zero(&tmp->ct_general.use)) continue; + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + if (gc_worker_skip_ct(tmp)) { nf_ct_put(tmp); continue; @@ -1775,6 +1787,16 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, if (!exp) __nf_ct_try_assign_helper(ct, tmpl, GFP_ATOMIC); + /* Other CPU might have obtained a pointer to this object before it was + * released. Because refcount is 0, refcount_inc_not_zero() will fail. + * + * After refcount_set(1) it will succeed; ensure that zeroing of + * ct->status and the correct ct->net pointer are visible; else other + * core might observe CONFIRMED bit which means the entry is valid and + * in the hash table, but its not (anymore). + */ + smp_wmb(); + /* Now it is going to be associated with an sk_buff, set refcount to 1. */ refcount_set(&ct->ct_general.use, 1); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 722af5e309ba..f5905b5201a7 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -1203,6 +1203,7 @@ restart: hnnode) { ct = nf_ct_tuplehash_to_ctrack(h); if (nf_ct_is_expired(ct)) { + /* need to defer nf_ct_kill() until lock is released */ if (i < ARRAY_SIZE(nf_ct_evict) && refcount_inc_not_zero(&ct->ct_general.use)) nf_ct_evict[i++] = ct; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 6ad7bbc90d38..05895878610c 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -306,6 +306,9 @@ static int ct_seq_show(struct seq_file *s, void *v) if (unlikely(!refcount_inc_not_zero(&ct->ct_general.use))) return 0; + /* load ->status after refcount increase */ + smp_acquire__after_ctrl_dep(); + if (nf_ct_should_gc(ct)) { nf_ct_kill(ct); goto release; diff --git a/net/netfilter/nf_dup_netdev.c b/net/netfilter/nf_dup_netdev.c index 7873bd1389c3..a8e2425e43b0 100644 --- a/net/netfilter/nf_dup_netdev.c +++ b/net/netfilter/nf_dup_netdev.c @@ -13,14 +13,31 @@ #include <net/netfilter/nf_tables_offload.h> #include <net/netfilter/nf_dup_netdev.h> -static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev) +#define NF_RECURSION_LIMIT 2 + +static DEFINE_PER_CPU(u8, nf_dup_skb_recursion); + +static void nf_do_netdev_egress(struct sk_buff *skb, struct net_device *dev, + enum nf_dev_hooks hook) { - if (skb_mac_header_was_set(skb)) + if (__this_cpu_read(nf_dup_skb_recursion) > NF_RECURSION_LIMIT) + goto err; + + if (hook == NF_NETDEV_INGRESS && skb_mac_header_was_set(skb)) { + if (skb_cow_head(skb, skb->mac_len)) + goto err; + skb_push(skb, skb->mac_len); + } skb->dev = dev; skb_clear_tstamp(skb); + __this_cpu_inc(nf_dup_skb_recursion); dev_queue_xmit(skb); + __this_cpu_dec(nf_dup_skb_recursion); + return; +err: + kfree_skb(skb); } void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif) @@ -33,7 +50,7 @@ void nf_fwd_netdev_egress(const struct nft_pktinfo *pkt, int oif) return; } - nf_do_netdev_egress(pkt->skb, dev); + nf_do_netdev_egress(pkt->skb, dev, nft_hook(pkt)); } EXPORT_SYMBOL_GPL(nf_fwd_netdev_egress); @@ -48,7 +65,7 @@ void nf_dup_netdev_egress(const struct nft_pktinfo *pkt, int oif) skb = skb_clone(pkt->skb, GFP_ATOMIC); if (skb) - nf_do_netdev_egress(skb, dev); + nf_do_netdev_egress(skb, dev, nft_hook(pkt)); } EXPORT_SYMBOL_GPL(nf_dup_netdev_egress); diff --git a/net/netfilter/nf_log_syslog.c b/net/netfilter/nf_log_syslog.c index 77bcb10fc586..cb894f0d63e9 100644 --- a/net/netfilter/nf_log_syslog.c +++ b/net/netfilter/nf_log_syslog.c @@ -67,7 +67,7 @@ dump_arp_packet(struct nf_log_buf *m, unsigned int logflags; struct arphdr _arph; - ah = skb_header_pointer(skb, 0, sizeof(_arph), &_arph); + ah = skb_header_pointer(skb, nhoff, sizeof(_arph), &_arph); if (!ah) { nf_log_buf_add(m, "TRUNCATED"); return; @@ -96,7 +96,7 @@ dump_arp_packet(struct nf_log_buf *m, ah->ar_pln != sizeof(__be32)) return; - ap = skb_header_pointer(skb, sizeof(_arph), sizeof(_arpp), &_arpp); + ap = skb_header_pointer(skb, nhoff + sizeof(_arph), sizeof(_arpp), &_arpp); if (!ap) { nf_log_buf_add(m, " INCOMPLETE [%zu bytes]", skb->len - sizeof(_arph)); @@ -149,7 +149,7 @@ static void nf_log_arp_packet(struct net *net, u_int8_t pf, nf_log_dump_packet_common(m, pf, hooknum, skb, in, out, loginfo, prefix); - dump_arp_packet(m, loginfo, skb, 0); + dump_arp_packet(m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); } @@ -850,7 +850,7 @@ static void nf_log_ip_packet(struct net *net, u_int8_t pf, if (in) dump_mac_header(m, loginfo, skb); - dump_ipv4_packet(net, m, loginfo, skb, 0); + dump_ipv4_packet(net, m, loginfo, skb, skb_network_offset(skb)); nf_log_buf_close(m); } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index e479dd0561c5..16915f8eef2b 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -405,7 +405,7 @@ synproxy_build_ip(struct net *net, struct sk_buff *skb, __be32 saddr, iph->tos = 0; iph->id = 0; iph->frag_off = htons(IP_DF); - iph->ttl = net->ipv4.sysctl_ip_default_ttl; + iph->ttl = READ_ONCE(net->ipv4.sysctl_ip_default_ttl); iph->protocol = IPPROTO_TCP; iph->check = 0; iph->saddr = saddr; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 51144fc66889..9f976b11d896 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -3340,6 +3340,8 @@ int nft_chain_validate(const struct nft_ctx *ctx, const struct nft_chain *chain) if (err < 0) return err; } + + cond_resched(); } return 0; @@ -5213,13 +5215,20 @@ static int nft_setelem_parse_data(struct nft_ctx *ctx, struct nft_set *set, struct nft_data *data, struct nlattr *attr) { + u32 dtype; int err; err = nft_data_init(ctx, data, NFT_DATA_VALUE_MAXLEN, desc, attr); if (err < 0) return err; - if (desc->type != NFT_DATA_VERDICT && desc->len != set->dlen) { + if (set->dtype == NFT_DATA_VERDICT) + dtype = NFT_DATA_VERDICT; + else + dtype = NFT_DATA_VALUE; + + if (dtype != desc->type || + set->dlen != desc->len) { nft_data_release(data, desc->type); return -EINVAL; } @@ -5826,8 +5835,11 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (!nla[NFTA_SET_ELEM_KEY] && !(flags & NFT_SET_ELEM_CATCHALL)) return -EINVAL; - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (set->flags & NFT_SET_MAP) { if (nla[NFTA_SET_ELEM_DATA] == NULL && @@ -5936,7 +5948,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_set_elem_expr; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto err_parse_key; } if (nla[NFTA_SET_ELEM_KEY_END]) { @@ -5945,22 +5959,31 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) goto err_parse_key; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto err_parse_key_end; } if (timeout > 0) { - nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); - if (timeout != set->timeout) - nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_EXPIRATION); + if (err < 0) + goto err_parse_key_end; + + if (timeout != set->timeout) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_TIMEOUT); + if (err < 0) + goto err_parse_key_end; + } } if (num_exprs) { for (i = 0; i < num_exprs; i++) size += expr_array[i]->ops->size; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, - sizeof(struct nft_set_elem_expr) + - size); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_EXPRESSIONS, + sizeof(struct nft_set_elem_expr) + size); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_OBJREF] != NULL) { @@ -5975,7 +5998,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = PTR_ERR(obj); goto err_parse_key_end; } - nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_OBJREF); + if (err < 0) + goto err_parse_key_end; } if (nla[NFTA_SET_ELEM_DATA] != NULL) { @@ -6009,7 +6034,9 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, NFT_VALIDATE_NEED); } - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_DATA, desc.len); + if (err < 0) + goto err_parse_data; } /* The full maximum length of userdata can exceed the maximum @@ -6019,9 +6046,12 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, ulen = 0; if (nla[NFTA_SET_ELEM_USERDATA] != NULL) { ulen = nla_len(nla[NFTA_SET_ELEM_USERDATA]); - if (ulen > 0) - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, - ulen); + if (ulen > 0) { + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_USERDATA, + ulen); + if (err < 0) + goto err_parse_data; + } } err = -ENOMEM; @@ -6249,8 +6279,11 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, nft_set_ext_prepare(&tmpl); - if (flags != 0) - nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (flags != 0) { + err = nft_set_ext_add(&tmpl, NFT_SET_EXT_FLAGS); + if (err < 0) + return err; + } if (nla[NFTA_SET_ELEM_KEY]) { err = nft_setelem_parse_key(ctx, set, &elem.key.val, @@ -6258,16 +6291,20 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, if (err < 0) return err; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY, set->klen); + if (err < 0) + goto fail_elem; } if (nla[NFTA_SET_ELEM_KEY_END]) { err = nft_setelem_parse_key(ctx, set, &elem.key_end.val, nla[NFTA_SET_ELEM_KEY_END]); if (err < 0) - return err; + goto fail_elem; - nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + err = nft_set_ext_add_length(&tmpl, NFT_SET_EXT_KEY_END, set->klen); + if (err < 0) + goto fail_elem_key_end; } err = -ENOMEM; @@ -6275,7 +6312,7 @@ static int nft_del_setelem(struct nft_ctx *ctx, struct nft_set *set, elem.key_end.val.data, NULL, 0, 0, GFP_KERNEL_ACCOUNT); if (elem.priv == NULL) - goto fail_elem; + goto fail_elem_key_end; ext = nft_set_elem_ext(set, elem.priv); if (flags) @@ -6299,6 +6336,8 @@ fail_ops: kfree(trans); fail_trans: kfree(elem.priv); +fail_elem_key_end: + nft_data_release(&elem.key_end.val, NFT_DATA_VALUE); fail_elem: nft_data_release(&elem.key.val, NFT_DATA_VALUE); return err; @@ -9330,9 +9369,13 @@ static int nf_tables_check_loops(const struct nft_ctx *ctx, break; } } + + cond_resched(); } list_for_each_entry(set, &ctx->table->sets, list) { + cond_resched(); + if (!nft_is_active_next(ctx->net, set)) continue; if (!(set->flags & NFT_SET_MAP) || diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index 53f40e473855..3ddce24ac76d 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -25,9 +25,7 @@ static noinline void __nft_trace_packet(struct nft_traceinfo *info, const struct nft_chain *chain, enum nft_trace_types type) { - const struct nft_pktinfo *pkt = info->pkt; - - if (!info->trace || !pkt->skb->nf_trace) + if (!info->trace || !info->nf_trace) return; info->chain = chain; @@ -42,11 +40,24 @@ static inline void nft_trace_packet(struct nft_traceinfo *info, enum nft_trace_types type) { if (static_branch_unlikely(&nft_trace_enabled)) { + const struct nft_pktinfo *pkt = info->pkt; + + info->nf_trace = pkt->skb->nf_trace; info->rule = rule; __nft_trace_packet(info, chain, type); } } +static inline void nft_trace_copy_nftrace(struct nft_traceinfo *info) +{ + if (static_branch_unlikely(&nft_trace_enabled)) { + const struct nft_pktinfo *pkt = info->pkt; + + if (info->trace) + info->nf_trace = pkt->skb->nf_trace; + } +} + static void nft_bitwise_fast_eval(const struct nft_expr *expr, struct nft_regs *regs) { @@ -85,6 +96,7 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info, const struct nft_chain *chain, const struct nft_regs *regs) { + const struct nft_pktinfo *pkt = info->pkt; enum nft_trace_types type; switch (regs->verdict.code) { @@ -92,8 +104,13 @@ static noinline void __nft_trace_verdict(struct nft_traceinfo *info, case NFT_RETURN: type = NFT_TRACETYPE_RETURN; break; + case NF_STOLEN: + type = NFT_TRACETYPE_RULE; + /* can't access skb->nf_trace; use copy */ + break; default: type = NFT_TRACETYPE_RULE; + info->nf_trace = pkt->skb->nf_trace; break; } @@ -254,6 +271,7 @@ next_rule: switch (regs.verdict.code) { case NFT_BREAK: regs.verdict.code = NFT_CONTINUE; + nft_trace_copy_nftrace(&info); continue; case NFT_CONTINUE: nft_trace_packet(&info, chain, rule, diff --git a/net/netfilter/nf_tables_trace.c b/net/netfilter/nf_tables_trace.c index 5041725423c2..1163ba9c1401 100644 --- a/net/netfilter/nf_tables_trace.c +++ b/net/netfilter/nf_tables_trace.c @@ -7,7 +7,7 @@ #include <linux/module.h> #include <linux/static_key.h> #include <linux/hash.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/if_vlan.h> #include <linux/init.h> #include <linux/skbuff.h> @@ -25,22 +25,6 @@ DEFINE_STATIC_KEY_FALSE(nft_trace_enabled); EXPORT_SYMBOL_GPL(nft_trace_enabled); -static int trace_fill_id(struct sk_buff *nlskb, struct sk_buff *skb) -{ - __be32 id; - - /* using skb address as ID results in a limited number of - * values (and quick reuse). - * - * So we attempt to use as many skb members that will not - * change while skb is with netfilter. - */ - id = (__be32)jhash_2words(hash32_ptr(skb), skb_get_hash(skb), - skb->skb_iif); - - return nla_put_be32(nlskb, NFTA_TRACE_ID, id); -} - static int trace_fill_header(struct sk_buff *nlskb, u16 type, const struct sk_buff *skb, int off, unsigned int len) @@ -186,6 +170,7 @@ void nft_trace_notify(struct nft_traceinfo *info) struct nlmsghdr *nlh; struct sk_buff *skb; unsigned int size; + u32 mark = 0; u16 event; if (!nfnetlink_has_listeners(nft_net(pkt), NFNLGRP_NFTRACE)) @@ -229,7 +214,7 @@ void nft_trace_notify(struct nft_traceinfo *info) if (nla_put_be32(skb, NFTA_TRACE_TYPE, htonl(info->type))) goto nla_put_failure; - if (trace_fill_id(skb, pkt->skb)) + if (nla_put_u32(skb, NFTA_TRACE_ID, info->skbid)) goto nla_put_failure; if (nla_put_string(skb, NFTA_TRACE_CHAIN, info->chain->name)) @@ -249,16 +234,24 @@ void nft_trace_notify(struct nft_traceinfo *info) case NFT_TRACETYPE_RULE: if (nft_verdict_dump(skb, NFTA_TRACE_VERDICT, info->verdict)) goto nla_put_failure; + + /* pkt->skb undefined iff NF_STOLEN, disable dump */ + if (info->verdict->code == NF_STOLEN) + info->packet_dumped = true; + else + mark = pkt->skb->mark; + break; case NFT_TRACETYPE_POLICY: + mark = pkt->skb->mark; + if (nla_put_be32(skb, NFTA_TRACE_POLICY, htonl(info->basechain->policy))) goto nla_put_failure; break; } - if (pkt->skb->mark && - nla_put_be32(skb, NFTA_TRACE_MARK, htonl(pkt->skb->mark))) + if (mark && nla_put_be32(skb, NFTA_TRACE_MARK, htonl(mark))) goto nla_put_failure; if (!info->packet_dumped) { @@ -283,9 +276,20 @@ void nft_trace_init(struct nft_traceinfo *info, const struct nft_pktinfo *pkt, const struct nft_verdict *verdict, const struct nft_chain *chain) { + static siphash_key_t trace_key __read_mostly; + struct sk_buff *skb = pkt->skb; + info->basechain = nft_base_chain(chain); info->trace = true; + info->nf_trace = pkt->skb->nf_trace; info->packet_dumped = false; info->pkt = pkt; info->verdict = verdict; + + net_get_random_once(&trace_key, sizeof(trace_key)); + + info->skbid = (u32)siphash_3u32(hash32_ptr(skb), + skb_get_hash(skb), + skb->skb_iif, + &trace_key); } diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index af15102bc696..f466af4f8531 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -614,7 +614,7 @@ static void __net_exit cttimeout_net_exit(struct net *net) nf_ct_untimeout(net, NULL); - list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, head) { + list_for_each_entry_safe(cur, tmp, &pernet->nfct_timeout_freelist, free_head) { list_del(&cur->free_head); if (refcount_dec_and_test(&cur->refcnt)) diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index a364f8e5e698..87a9009d5234 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -843,11 +843,16 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) } static int -nfqnl_mangle(void *data, int data_len, struct nf_queue_entry *e, int diff) +nfqnl_mangle(void *data, unsigned int data_len, struct nf_queue_entry *e, int diff) { struct sk_buff *nskb; if (diff < 0) { + unsigned int min_len = skb_transport_offset(e->skb); + + if (data_len < min_len) + return -EINVAL; + if (pskb_trim(e->skb, data_len)) return -ENOMEM; } else if (diff > 0) { diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index ac4859241e17..55d2d49c3425 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -14,6 +14,7 @@ #include <linux/in.h> #include <linux/ip.h> #include <linux/ipv6.h> +#include <linux/random.h> #include <linux/smp.h> #include <linux/static_key.h> #include <net/dst.h> @@ -32,8 +33,6 @@ #define NFT_META_SECS_PER_DAY 86400 #define NFT_META_DAYS_PER_WEEK 7 -static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); - static u8 nft_meta_weekday(void) { time64_t secs = ktime_get_real_seconds(); @@ -271,13 +270,6 @@ static bool nft_meta_get_eval_ifname(enum nft_meta_keys key, u32 *dest, return true; } -static noinline u32 nft_prandom_u32(void) -{ - struct rnd_state *state = this_cpu_ptr(&nft_prandom_state); - - return prandom_u32_state(state); -} - #ifdef CONFIG_IP_ROUTE_CLASSID static noinline bool nft_meta_get_eval_rtclassid(const struct sk_buff *skb, u32 *dest) @@ -389,7 +381,7 @@ void nft_meta_get_eval(const struct nft_expr *expr, break; #endif case NFT_META_PRANDOM: - *dest = nft_prandom_u32(); + *dest = get_random_u32(); break; #ifdef CONFIG_XFRM case NFT_META_SECPATH: @@ -518,7 +510,6 @@ int nft_meta_get_init(const struct nft_ctx *ctx, len = IFNAMSIZ; break; case NFT_META_PRANDOM: - prandom_init_once(&nft_prandom_state); len = sizeof(u32); break; #ifdef CONFIG_XFRM diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 81b40c663d86..45d3dc9e96f2 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -9,12 +9,11 @@ #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <linux/random.h> #include <linux/static_key.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> -static DEFINE_PER_CPU(struct rnd_state, nft_numgen_prandom_state); - struct nft_ng_inc { u8 dreg; u32 modulus; @@ -135,12 +134,9 @@ struct nft_ng_random { u32 offset; }; -static u32 nft_ng_random_gen(struct nft_ng_random *priv) +static u32 nft_ng_random_gen(const struct nft_ng_random *priv) { - struct rnd_state *state = this_cpu_ptr(&nft_numgen_prandom_state); - - return reciprocal_scale(prandom_u32_state(state), priv->modulus) + - priv->offset; + return reciprocal_scale(get_random_u32(), priv->modulus) + priv->offset; } static void nft_ng_random_eval(const struct nft_expr *expr, @@ -168,8 +164,6 @@ static int nft_ng_random_init(const struct nft_ctx *ctx, if (priv->offset + priv->modulus - 1 < priv->offset) return -EOVERFLOW; - prandom_init_once(&nft_numgen_prandom_state); - return nft_parse_register_store(ctx, tb[NFTA_NG_DREG], &priv->dreg, NULL, NFT_DATA_VALUE, sizeof(u32)); } diff --git a/net/netfilter/nft_queue.c b/net/netfilter/nft_queue.c index 15e4b7640dc0..da29e92c03e2 100644 --- a/net/netfilter/nft_queue.c +++ b/net/netfilter/nft_queue.c @@ -68,6 +68,31 @@ static void nft_queue_sreg_eval(const struct nft_expr *expr, regs->verdict.code = ret; } +static int nft_queue_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + static const unsigned int supported_hooks = ((1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + + switch (ctx->family) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + case NFPROTO_INET: + case NFPROTO_BRIDGE: + break; + case NFPROTO_NETDEV: /* lacks okfn */ + fallthrough; + default: + return -EOPNOTSUPP; + } + + return nft_chain_validate_hooks(ctx->chain, supported_hooks); +} + static const struct nla_policy nft_queue_policy[NFTA_QUEUE_MAX + 1] = { [NFTA_QUEUE_NUM] = { .type = NLA_U16 }, [NFTA_QUEUE_TOTAL] = { .type = NLA_U16 }, @@ -164,6 +189,7 @@ static const struct nft_expr_ops nft_queue_ops = { .eval = nft_queue_eval, .init = nft_queue_init, .dump = nft_queue_dump, + .validate = nft_queue_validate, .reduce = NFT_REDUCE_READONLY, }; @@ -173,6 +199,7 @@ static const struct nft_expr_ops nft_queue_sreg_ops = { .eval = nft_queue_sreg_eval, .init = nft_queue_sreg_init, .dump = nft_queue_sreg_dump, + .validate = nft_queue_validate, .reduce = NFT_REDUCE_READONLY, }; diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index df40314de21f..76de6c8d9865 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -143,6 +143,7 @@ static bool nft_rhash_update(struct nft_set *set, const u32 *key, /* Another cpu may race to insert the element with the same key */ if (prev) { nft_set_elem_destroy(set, he, true); + atomic_dec(&set->nelems); he = prev; } @@ -152,6 +153,7 @@ out: err2: nft_set_elem_destroy(set, he, true); + atomic_dec(&set->nelems); err1: return false; } diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index 2c8051d8cca6..4f9299b9dcdd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -2125,6 +2125,32 @@ out_scratch: } /** + * nft_set_pipapo_match_destroy() - Destroy elements from key mapping array + * @set: nftables API set representation + * @m: matching data pointing to key mapping array + */ +static void nft_set_pipapo_match_destroy(const struct nft_set *set, + struct nft_pipapo_match *m) +{ + struct nft_pipapo_field *f; + int i, r; + + for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) + ; + + for (r = 0; r < f->rules; r++) { + struct nft_pipapo_elem *e; + + if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) + continue; + + e = f->mt[r].e; + + nft_set_elem_destroy(set, e, true); + } +} + +/** * nft_pipapo_destroy() - Free private data for set and all committed elements * @set: nftables API set representation */ @@ -2132,26 +2158,13 @@ static void nft_pipapo_destroy(const struct nft_set *set) { struct nft_pipapo *priv = nft_set_priv(set); struct nft_pipapo_match *m; - struct nft_pipapo_field *f; - int i, r, cpu; + int cpu; m = rcu_dereference_protected(priv->match, true); if (m) { rcu_barrier(); - for (i = 0, f = m->f; i < m->field_count - 1; i++, f++) - ; - - for (r = 0; r < f->rules; r++) { - struct nft_pipapo_elem *e; - - if (r < f->rules - 1 && f->mt[r + 1].e == f->mt[r].e) - continue; - - e = f->mt[r].e; - - nft_set_elem_destroy(set, e, true); - } + nft_set_pipapo_match_destroy(set, m); #ifdef NFT_PIPAPO_ALIGN free_percpu(m->scratch_aligned); @@ -2165,6 +2178,11 @@ static void nft_pipapo_destroy(const struct nft_set *set) } if (priv->clone) { + m = priv->clone; + + if (priv->dirty) + nft_set_pipapo_match_destroy(set, m); + #ifdef NFT_PIPAPO_ALIGN free_percpu(priv->clone->scratch_aligned); #endif diff --git a/net/openvswitch/flow.c b/net/openvswitch/flow.c index 372bf54a0ca9..e20d1a973417 100644 --- a/net/openvswitch/flow.c +++ b/net/openvswitch/flow.c @@ -407,7 +407,7 @@ static int parse_ipv6hdr(struct sk_buff *skb, struct sw_flow_key *key) if (flags & IP6_FH_F_FRAG) { if (frag_off) { key->ip.frag = OVS_FRAG_TYPE_LATER; - key->ip.proto = nexthdr; + key->ip.proto = NEXTHDR_FRAGMENT; return 0; } key->ip.frag = OVS_FRAG_TYPE_FIRST; diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index fee6409c2bb3..eb0b8197ac82 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -227,8 +227,8 @@ static void rose_remove_neigh(struct rose_neigh *rose_neigh) { struct rose_neigh *s; - rose_stop_ftimer(rose_neigh); - rose_stop_t0timer(rose_neigh); + del_timer_sync(&rose_neigh->ftimer); + del_timer_sync(&rose_neigh->t0timer); skb_queue_purge(&rose_neigh->queue); diff --git a/net/rose/rose_timer.c b/net/rose/rose_timer.c index b3138fc2e552..f06ddbed3fed 100644 --- a/net/rose/rose_timer.c +++ b/net/rose/rose_timer.c @@ -31,89 +31,89 @@ static void rose_idletimer_expiry(struct timer_list *); void rose_start_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); sk->sk_timer.function = rose_heartbeat_expiry; sk->sk_timer.expires = jiffies + 5 * HZ; - add_timer(&sk->sk_timer); + sk_reset_timer(sk, &sk->sk_timer, sk->sk_timer.expires); } void rose_start_t1timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t1; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_t2timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t2; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_t3timer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->t3; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_hbtimer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->timer); + sk_stop_timer(sk, &rose->timer); rose->timer.function = rose_timer_expiry; rose->timer.expires = jiffies + rose->hb; - add_timer(&rose->timer); + sk_reset_timer(sk, &rose->timer, rose->timer.expires); } void rose_start_idletimer(struct sock *sk) { struct rose_sock *rose = rose_sk(sk); - del_timer(&rose->idletimer); + sk_stop_timer(sk, &rose->idletimer); if (rose->idle > 0) { rose->idletimer.function = rose_idletimer_expiry; rose->idletimer.expires = jiffies + rose->idle; - add_timer(&rose->idletimer); + sk_reset_timer(sk, &rose->idletimer, rose->idletimer.expires); } } void rose_stop_heartbeat(struct sock *sk) { - del_timer(&sk->sk_timer); + sk_stop_timer(sk, &sk->sk_timer); } void rose_stop_timer(struct sock *sk) { - del_timer(&rose_sk(sk)->timer); + sk_stop_timer(sk, &rose_sk(sk)->timer); } void rose_stop_idletimer(struct sock *sk) { - del_timer(&rose_sk(sk)->idletimer); + sk_stop_timer(sk, &rose_sk(sk)->idletimer); } static void rose_heartbeat_expiry(struct timer_list *t) @@ -130,6 +130,7 @@ static void rose_heartbeat_expiry(struct timer_list *t) (sk->sk_state == TCP_LISTEN && sock_flag(sk, SOCK_DEAD))) { bh_unlock_sock(sk); rose_destroy_socket(sk); + sock_put(sk); return; } break; @@ -152,6 +153,7 @@ static void rose_heartbeat_expiry(struct timer_list *t) rose_start_heartbeat(sk); bh_unlock_sock(sk); + sock_put(sk); } static void rose_timer_expiry(struct timer_list *t) @@ -181,6 +183,7 @@ static void rose_timer_expiry(struct timer_list *t) break; } bh_unlock_sock(sk); + sock_put(sk); } static void rose_idletimer_expiry(struct timer_list *t) @@ -205,4 +208,5 @@ static void rose_idletimer_expiry(struct timer_list *t) sock_set_flag(sk, SOCK_DEAD); } bh_unlock_sock(sk); + sock_put(sk); } diff --git a/net/sched/act_api.c b/net/sched/act_api.c index da9733da9868..817065aa2833 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -588,7 +588,8 @@ static int tcf_idr_release_unsafe(struct tc_action *p) } static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, - const struct tc_action_ops *ops) + const struct tc_action_ops *ops, + struct netlink_ext_ack *extack) { struct nlattr *nest; int n_i = 0; @@ -604,20 +605,25 @@ static int tcf_del_walker(struct tcf_idrinfo *idrinfo, struct sk_buff *skb, if (nla_put_string(skb, TCA_KIND, ops->kind)) goto nla_put_failure; + ret = 0; mutex_lock(&idrinfo->lock); idr_for_each_entry_ul(idr, p, tmp, id) { if (IS_ERR(p)) continue; ret = tcf_idr_release_unsafe(p); - if (ret == ACT_P_DELETED) { + if (ret == ACT_P_DELETED) module_put(ops->owner); - n_i++; - } else if (ret < 0) { - mutex_unlock(&idrinfo->lock); - goto nla_put_failure; - } + else if (ret < 0) + break; + n_i++; } mutex_unlock(&idrinfo->lock); + if (ret < 0) { + if (n_i) + NL_SET_ERR_MSG(extack, "Unable to flush all TC actions"); + else + goto nla_put_failure; + } ret = nla_put_u32(skb, TCA_FCNT, n_i); if (ret) @@ -638,7 +644,7 @@ int tcf_generic_walker(struct tc_action_net *tn, struct sk_buff *skb, struct tcf_idrinfo *idrinfo = tn->idrinfo; if (type == RTM_DELACTION) { - return tcf_del_walker(idrinfo, skb, ops); + return tcf_del_walker(idrinfo, skb, ops, extack); } else if (type == RTM_GETACTION) { return tcf_dump_walker(idrinfo, skb, cb); } else { diff --git a/net/sched/act_police.c b/net/sched/act_police.c index 79c8901f66ab..b759628a47c2 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -442,7 +442,7 @@ static int tcf_police_act_to_flow_act(int tc_act, u32 *extval, act_id = FLOW_ACTION_JUMP; *extval = tc_act & TC_ACT_EXT_VAL_MASK; } else if (tc_act == TC_ACT_UNSPEC) { - NL_SET_ERR_MSG_MOD(extack, "Offload not supported when conform/exceed action is \"continue\""); + act_id = FLOW_ACTION_CONTINUE; } else { NL_SET_ERR_MSG_MOD(extack, "Unsupported conform/exceed action offload"); } diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index 9bb4d3dcc994..ac366c99086f 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -3533,7 +3533,7 @@ int tc_setup_action(struct flow_action *flow_action, struct tc_action *actions[], struct netlink_ext_ack *extack) { - int i, j, index, err = 0; + int i, j, k, index, err = 0; struct tc_action *act; BUILD_BUG_ON(TCA_ACT_HW_STATS_ANY != FLOW_ACTION_HW_STATS_ANY); @@ -3553,14 +3553,18 @@ int tc_setup_action(struct flow_action *flow_action, if (err) goto err_out_locked; - entry->hw_stats = tc_act_hw_stats(act->hw_stats); - entry->hw_index = act->tcfa_index; index = 0; err = tc_setup_offload_act(act, entry, &index, extack); - if (!err) - j += index; - else + if (err) goto err_out_locked; + + for (k = 0; k < index ; k++) { + entry[k].hw_stats = tc_act_hw_stats(act->hw_stats); + entry[k].hw_index = act->tcfa_index; + } + + j += index; + spin_unlock_bh(&act->tcfa_lock); } diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index ed4ccef5d6a8..5449ed114e40 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -1146,9 +1146,9 @@ static int netem_dump(struct Qdisc *sch, struct sk_buff *skb) struct tc_netem_rate rate; struct tc_netem_slot slot; - qopt.latency = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->latency), + qopt.latency = min_t(psched_time_t, PSCHED_NS2TICKS(q->latency), UINT_MAX); - qopt.jitter = min_t(psched_tdiff_t, PSCHED_NS2TICKS(q->jitter), + qopt.jitter = min_t(psched_time_t, PSCHED_NS2TICKS(q->jitter), UINT_MAX); qopt.limit = q->limit; qopt.loss = q->loss; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index be29da09cc7a..3460abceba44 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -229,9 +229,8 @@ static struct sctp_association *sctp_association_init( if (!sctp_ulpq_init(&asoc->ulpq, asoc)) goto fail_init; - if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, - 0, gfp)) - goto fail_init; + if (sctp_stream_init(&asoc->stream, asoc->c.sinit_num_ostreams, 0, gfp)) + goto stream_free; /* Initialize default path MTU. */ asoc->pathmtu = sp->pathmtu; diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index 35928fefae33..1a094b087d88 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -358,7 +358,7 @@ static int sctp_v4_available(union sctp_addr *addr, struct sctp_sock *sp) if (addr->v4.sin_addr.s_addr != htonl(INADDR_ANY) && ret != RTN_LOCAL && !sp->inet.freebind && - !net->ipv4.sysctl_ip_nonlocal_bind) + !READ_ONCE(net->ipv4.sysctl_ip_nonlocal_bind)) return 0; if (ipv6_only_sock(sctp_opt2sk(sp))) diff --git a/net/sctp/stream.c b/net/sctp/stream.c index 6dc95dcc0ff4..ef9fceadef8d 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -137,7 +137,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, ret = sctp_stream_alloc_out(stream, outcnt, gfp); if (ret) - goto out_err; + return ret; for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; @@ -145,22 +145,9 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, handle_in: sctp_stream_interleave_init(stream); if (!incnt) - goto out; - - ret = sctp_stream_alloc_in(stream, incnt, gfp); - if (ret) - goto in_err; - - goto out; + return 0; -in_err: - sched->free(stream); - genradix_free(&stream->in); -out_err: - genradix_free(&stream->out); - stream->outcnt = 0; -out: - return ret; + return sctp_stream_alloc_in(stream, incnt, gfp); } int sctp_stream_init_ext(struct sctp_stream *stream, __u16 sid) diff --git a/net/sctp/stream_sched.c b/net/sctp/stream_sched.c index 518b1b9bf89d..1ad565ed5627 100644 --- a/net/sctp/stream_sched.c +++ b/net/sctp/stream_sched.c @@ -160,7 +160,7 @@ int sctp_sched_set_sched(struct sctp_association *asoc, if (!SCTP_SO(&asoc->stream, i)->ext) continue; - ret = n->init_sid(&asoc->stream, i, GFP_KERNEL); + ret = n->init_sid(&asoc->stream, i, GFP_ATOMIC); if (ret) goto err; } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index c4d057b2941d..0bde36b56472 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -2122,7 +2122,7 @@ void smc_llc_lgr_init(struct smc_link_group *lgr, struct smc_sock *smc) init_waitqueue_head(&lgr->llc_flow_waiter); init_waitqueue_head(&lgr->llc_msg_waiter); mutex_init(&lgr->llc_conf_mutex); - lgr->llc_testlink_time = net->ipv4.sysctl_tcp_keepalive_time; + lgr->llc_testlink_time = READ_ONCE(net->ipv4.sysctl_tcp_keepalive_time); } /* called after lgr was removed from lgr_list */ diff --git a/net/socket.c b/net/socket.c index 2bc8773d9dc5..ec9ef13a702e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -2106,6 +2106,7 @@ int __sys_sendto(int fd, void __user *buff, size_t len, unsigned int flags, msg.msg_control = NULL; msg.msg_controllen = 0; msg.msg_namelen = 0; + msg.msg_ubuf = NULL; if (addr) { err = move_addr_to_kernel(addr, addr_len, &address); if (err < 0) @@ -2149,10 +2150,13 @@ SYSCALL_DEFINE4(send, int, fd, void __user *, buff, size_t, len, int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, struct sockaddr __user *addr, int __user *addr_len) { + struct sockaddr_storage address; + struct msghdr msg = { + /* Save some cycles and don't copy the address if not needed */ + .msg_name = addr ? (struct sockaddr *)&address : NULL, + }; struct socket *sock; struct iovec iov; - struct msghdr msg; - struct sockaddr_storage address; int err, err2; int fput_needed; @@ -2163,14 +2167,6 @@ int __sys_recvfrom(int fd, void __user *ubuf, size_t size, unsigned int flags, if (!sock) goto out; - msg.msg_control = NULL; - msg.msg_controllen = 0; - /* Save some cycles and don't copy the address if not needed */ - msg.msg_name = addr ? (struct sockaddr *)&address : NULL; - /* We assume all kernel code knows the size of sockaddr_storage */ - msg.msg_namelen = 0; - msg.msg_iocb = NULL; - msg.msg_flags = 0; if (sock->file->f_flags & O_NONBLOCK) flags |= MSG_DONTWAIT; err = sock_recvmsg(sock, &msg, flags); @@ -2363,24 +2359,20 @@ struct used_address { unsigned int name_len; }; -int __copy_msghdr_from_user(struct msghdr *kmsg, - struct user_msghdr __user *umsg, - struct sockaddr __user **save_addr, - struct iovec __user **uiov, size_t *nsegs) +int __copy_msghdr(struct msghdr *kmsg, + struct user_msghdr *msg, + struct sockaddr __user **save_addr) { - struct user_msghdr msg; ssize_t err; - if (copy_from_user(&msg, umsg, sizeof(*umsg))) - return -EFAULT; - kmsg->msg_control_is_user = true; - kmsg->msg_control_user = msg.msg_control; - kmsg->msg_controllen = msg.msg_controllen; - kmsg->msg_flags = msg.msg_flags; + kmsg->msg_get_inq = 0; + kmsg->msg_control_user = msg->msg_control; + kmsg->msg_controllen = msg->msg_controllen; + kmsg->msg_flags = msg->msg_flags; - kmsg->msg_namelen = msg.msg_namelen; - if (!msg.msg_name) + kmsg->msg_namelen = msg->msg_namelen; + if (!msg->msg_name) kmsg->msg_namelen = 0; if (kmsg->msg_namelen < 0) @@ -2390,11 +2382,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = sizeof(struct sockaddr_storage); if (save_addr) - *save_addr = msg.msg_name; + *save_addr = msg->msg_name; - if (msg.msg_name && kmsg->msg_namelen) { + if (msg->msg_name && kmsg->msg_namelen) { if (!save_addr) { - err = move_addr_to_kernel(msg.msg_name, + err = move_addr_to_kernel(msg->msg_name, kmsg->msg_namelen, kmsg->msg_name); if (err < 0) @@ -2405,12 +2397,11 @@ int __copy_msghdr_from_user(struct msghdr *kmsg, kmsg->msg_namelen = 0; } - if (msg.msg_iovlen > UIO_MAXIOV) + if (msg->msg_iovlen > UIO_MAXIOV) return -EMSGSIZE; kmsg->msg_iocb = NULL; - *uiov = msg.msg_iov; - *nsegs = msg.msg_iovlen; + kmsg->msg_ubuf = NULL; return 0; } @@ -2422,8 +2413,10 @@ static int copy_msghdr_from_user(struct msghdr *kmsg, struct user_msghdr msg; ssize_t err; - err = __copy_msghdr_from_user(kmsg, umsg, save_addr, &msg.msg_iov, - &msg.msg_iovlen); + if (copy_from_user(&msg, umsg, sizeof(*umsg))) + return -EFAULT; + + err = __copy_msghdr(kmsg, &msg, save_addr); if (err) return err; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index e2c6eca0271b..b6781ada3aa8 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -651,6 +651,7 @@ static struct rpc_clnt *__rpc_clone_client(struct rpc_create_args *args, new->cl_discrtry = clnt->cl_discrtry; new->cl_chatty = clnt->cl_chatty; new->cl_principal = clnt->cl_principal; + new->cl_max_connect = clnt->cl_max_connect; return new; out_err: diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index f87a2d8f23a7..5d2b3e6979fb 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -984,7 +984,7 @@ static noinline __be32 *xdr_get_next_encode_buffer(struct xdr_stream *xdr, p = page_address(*xdr->page_ptr); xdr->p = p + frag2bytes; space_left = xdr->buf->buflen - xdr->buf->len; - if (space_left - nbytes >= PAGE_SIZE) + if (space_left - frag1bytes >= PAGE_SIZE) xdr->end = p + PAGE_SIZE; else xdr->end = p + space_left - frag1bytes; diff --git a/net/tipc/core.c b/net/tipc/core.c index 3f4542e0f065..434e70eabe08 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -109,10 +109,9 @@ static void __net_exit tipc_exit_net(struct net *net) struct tipc_net *tn = tipc_net(net); tipc_detach_loopback(net); + tipc_net_stop(net); /* Make sure the tipc_net_finalize_work() finished */ cancel_work_sync(&tn->work); - tipc_net_stop(net); - tipc_bcast_stop(net); tipc_nametbl_stop(net); tipc_sk_rht_destroy(net); diff --git a/net/tipc/node.c b/net/tipc/node.c index 6ef95ce565bd..b48d97cbbe29 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -472,8 +472,8 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id, bool preliminary) { struct tipc_net *tn = net_generic(net, tipc_net_id); + struct tipc_link *l, *snd_l = tipc_bc_sndlink(net); struct tipc_node *n, *temp_node; - struct tipc_link *l; unsigned long intv; int bearer_id; int i; @@ -488,6 +488,16 @@ struct tipc_node *tipc_node_create(struct net *net, u32 addr, u8 *peer_id, goto exit; /* A preliminary node becomes "real" now, refresh its data */ tipc_node_write_lock(n); + if (!tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX, + tipc_link_min_win(snd_l), tipc_link_max_win(snd_l), + n->capabilities, &n->bc_entry.inputq1, + &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) { + pr_warn("Broadcast rcv link refresh failed, no memory\n"); + tipc_node_write_unlock_fast(n); + tipc_node_put(n); + n = NULL; + goto exit; + } n->preliminary = false; n->addr = addr; hlist_del_rcu(&n->hash); @@ -567,7 +577,16 @@ update: n->signature = INVALID_NODE_SIG; n->active_links[0] = INVALID_BEARER_ID; n->active_links[1] = INVALID_BEARER_ID; - n->bc_entry.link = NULL; + if (!preliminary && + !tipc_link_bc_create(net, tipc_own_addr(net), addr, peer_id, U16_MAX, + tipc_link_min_win(snd_l), tipc_link_max_win(snd_l), + n->capabilities, &n->bc_entry.inputq1, + &n->bc_entry.namedq, snd_l, &n->bc_entry.link)) { + pr_warn("Broadcast rcv link creation failed, no memory\n"); + kfree(n); + n = NULL; + goto exit; + } tipc_node_get(n); timer_setup(&n->timer, tipc_node_timeout, 0); /* Start a slow timer anyway, crypto needs it */ @@ -1155,7 +1174,7 @@ void tipc_node_check_dest(struct net *net, u32 addr, bool *respond, bool *dupl_addr) { struct tipc_node *n; - struct tipc_link *l, *snd_l; + struct tipc_link *l; struct tipc_link_entry *le; bool addr_match = false; bool sign_match = false; @@ -1175,22 +1194,6 @@ void tipc_node_check_dest(struct net *net, u32 addr, return; tipc_node_write_lock(n); - if (unlikely(!n->bc_entry.link)) { - snd_l = tipc_bc_sndlink(net); - if (!tipc_link_bc_create(net, tipc_own_addr(net), - addr, peer_id, U16_MAX, - tipc_link_min_win(snd_l), - tipc_link_max_win(snd_l), - n->capabilities, - &n->bc_entry.inputq1, - &n->bc_entry.namedq, snd_l, - &n->bc_entry.link)) { - pr_warn("Broadcast rcv link creation failed, no mem\n"); - tipc_node_write_unlock_fast(n); - tipc_node_put(n); - return; - } - } le = &n->links[b->identity]; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 17f8c523e33b..f1c3b8eb4b3d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -502,6 +502,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, sock_init_data(sock, sk); tipc_set_sk_state(sk, TIPC_OPEN); if (tipc_sk_insert(tsk)) { + sk_free(sk); pr_warn("Socket create failed; port number exhausted\n"); return -EINVAL; } @@ -516,7 +517,7 @@ static int tipc_sk_create(struct net *net, struct socket *sock, timer_setup(&sk->sk_timer, tipc_sk_timeout, 0); sk->sk_shutdown = 0; sk->sk_backlog_rcv = tipc_sk_backlog_rcv; - sk->sk_rcvbuf = sysctl_tipc_rmem[1]; + sk->sk_rcvbuf = READ_ONCE(sysctl_tipc_rmem[1]); sk->sk_data_ready = tipc_data_ready; sk->sk_write_space = tipc_write_space; sk->sk_destruct = tipc_sock_destruct; diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index ec6f4b699a2b..9975df34d9c2 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -97,13 +97,16 @@ static void tls_device_queue_ctx_destruction(struct tls_context *ctx) unsigned long flags; spin_lock_irqsave(&tls_device_lock, flags); + if (unlikely(!refcount_dec_and_test(&ctx->refcount))) + goto unlock; + list_move_tail(&ctx->list, &tls_device_gc_list); /* schedule_work inside the spinlock * to make sure tls_device_down waits for that work. */ schedule_work(&tls_device_gc_work); - +unlock: spin_unlock_irqrestore(&tls_device_lock, flags); } @@ -194,8 +197,7 @@ void tls_device_sk_destruct(struct sock *sk) clean_acked_data_disable(inet_csk(sk)); } - if (refcount_dec_and_test(&tls_ctx->refcount)) - tls_device_queue_ctx_destruction(tls_ctx); + tls_device_queue_ctx_destruction(tls_ctx); } EXPORT_SYMBOL_GPL(tls_device_sk_destruct); @@ -1374,8 +1376,13 @@ static int tls_device_down(struct net_device *netdev) * by tls_device_free_ctx. rx_conf and tx_conf stay in TLS_HW. * Now release the ref taken above. */ - if (refcount_dec_and_test(&ctx->refcount)) + if (refcount_dec_and_test(&ctx->refcount)) { + /* sk_destruct ran after tls_device_down took a ref, and + * it returned early. Complete the destruction here. + */ + list_del(&ctx->list); tls_device_free_ctx(ctx); + } } up_write(&device_offload_lock); @@ -1419,9 +1426,9 @@ static struct notifier_block tls_dev_notifier = { .notifier_call = tls_dev_event, }; -void __init tls_device_init(void) +int __init tls_device_init(void) { - register_netdevice_notifier(&tls_dev_notifier); + return register_netdevice_notifier(&tls_dev_notifier); } void __exit tls_device_cleanup(void) diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index da176411c1b5..d80ab3d1764e 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -921,6 +921,8 @@ static void tls_update(struct sock *sk, struct proto *p, { struct tls_context *ctx; + WARN_ON_ONCE(sk->sk_prot == p); + ctx = tls_get_ctx(sk); if (likely(ctx)) { ctx->sk_write_space = write_space; @@ -1046,7 +1048,12 @@ static int __init tls_register(void) if (err) return err; - tls_device_init(); + err = tls_device_init(); + if (err) { + unregister_pernet_subsys(&tls_proc_ops); + return err; + } + tcp_register_ulp(&tcp_tls_ulp_ops); return 0; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 0513f82b8537..e30649f6dde5 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -267,9 +267,6 @@ static int tls_do_decryption(struct sock *sk, } darg->async = false; - if (ret == -EBADMSG) - TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR); - return ret; } @@ -1579,8 +1576,11 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, } err = decrypt_internal(sk, skb, dest, NULL, darg); - if (err < 0) + if (err < 0) { + if (err == -EBADMSG) + TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR); return err; + } if (darg->async) goto decrypt_next; diff --git a/net/wireless/sme.c b/net/wireless/sme.c index ff4d48fcbfb2..607a68911047 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1031,7 +1031,8 @@ void __cfg80211_port_authorized(struct wireless_dev *wdev, const u8 *bssid) { ASSERT_WDEV_LOCK(wdev); - if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION)) + if (WARN_ON(wdev->iftype != NL80211_IFTYPE_STATION && + wdev->iftype != NL80211_IFTYPE_P2P_CLIENT)) return; if (WARN_ON(!wdev->current_bss) || diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 19ac872a6624..09002387987e 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -538,12 +538,6 @@ static int xsk_generic_xmit(struct sock *sk) goto out; } - skb = xsk_build_skb(xs, &desc); - if (IS_ERR(skb)) { - err = PTR_ERR(skb); - goto out; - } - /* This is the backpressure mechanism for the Tx path. * Reserve space in the completion queue and only proceed * if there is space in it. This avoids having to implement @@ -552,11 +546,19 @@ static int xsk_generic_xmit(struct sock *sk) spin_lock_irqsave(&xs->pool->cq_lock, flags); if (xskq_prod_reserve(xs->pool->cq)) { spin_unlock_irqrestore(&xs->pool->cq_lock, flags); - kfree_skb(skb); goto out; } spin_unlock_irqrestore(&xs->pool->cq_lock, flags); + skb = xsk_build_skb(xs, &desc); + if (IS_ERR(skb)) { + err = PTR_ERR(skb); + spin_lock_irqsave(&xs->pool->cq_lock, flags); + xskq_prod_cancel(xs->pool->cq); + spin_unlock_irqrestore(&xs->pool->cq_lock, flags); + goto out; + } + err = __dev_direct_xmit(skb, xs->queue_id); if (err == NETDEV_TX_BUSY) { /* Tell user-space to retry the send */ diff --git a/net/xdp/xsk_buff_pool.c b/net/xdp/xsk_buff_pool.c index 87bdd71c7bb6..f70112176b7c 100644 --- a/net/xdp/xsk_buff_pool.c +++ b/net/xdp/xsk_buff_pool.c @@ -332,6 +332,7 @@ static void __xp_dma_unmap(struct xsk_dma_map *dma_map, unsigned long attrs) for (i = 0; i < dma_map->dma_pages_cnt; i++) { dma = &dma_map->dma_pages[i]; if (*dma) { + *dma &= ~XSK_NEXT_PG_CONTIG_MASK; dma_unmap_page_attrs(dma_map->dev, *dma, PAGE_SIZE, DMA_BIDIRECTIONAL, attrs); *dma = 0; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f1876ea61fdc..f1a0bab920a5 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -2678,8 +2678,10 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, *num_xfrms = 0; return 0; } - if (IS_ERR(pols[0])) + if (IS_ERR(pols[0])) { + *num_pols = 0; return PTR_ERR(pols[0]); + } *num_xfrms = pols[0]->xfrm_nr; @@ -2694,6 +2696,7 @@ static int xfrm_expand_policies(const struct flowi *fl, u16 family, if (pols[1]) { if (IS_ERR(pols[1])) { xfrm_pols_put(pols, *num_pols); + *num_pols = 0; return PTR_ERR(pols[1]); } (*num_pols)++; diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 08564e0eef20..ccfb172eb5b8 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -2620,7 +2620,7 @@ int __xfrm_init_state(struct xfrm_state *x, bool init_replay, bool offload) int err; if (family == AF_INET && - xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc) + READ_ONCE(xs_net(x)->ipv4.sysctl_ip_no_pmtu_disc)) x->props.flags |= XFRM_STATE_NOPMTUDISC; err = -EPROTONOSUPPORT; |