diff options
Diffstat (limited to 'net')
138 files changed, 1298 insertions, 3704 deletions
diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index 0db85aeb1..99b277775 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -118,12 +118,16 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); vlan_dev_set_ingress_priority(dev, m->to, m->from); } } if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { + if (nla_type(attr) != IFLA_VLAN_QOS_MAPPING) + continue; m = nla_data(attr); err = vlan_dev_set_egress_priority(dev, m->from, m->to); if (err) diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 9e8ebac9b..f5019f698 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -4188,7 +4188,7 @@ void batadv_tt_local_resize_to_mtu(struct net_device *soft_iface) spin_lock_bh(&bat_priv->tt.commit_lock); - while (true) { + while (timeout) { table_size = batadv_tt_local_table_transmit_size(bat_priv); if (packet_size_max >= table_size) break; diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index e33fe4b1c..b9cf5bc93 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -2175,7 +2175,7 @@ int hci_get_dev_info(void __user *arg) else flags = hdev->flags; - strcpy(di.name, hdev->name); + strscpy(di.name, hdev->name, sizeof(di.name)); di.bdaddr = hdev->bdaddr; di.type = (hdev->bus & 0x0f) | ((hdev->dev_type & 0x03) << 4); di.flags = flags; @@ -2318,6 +2318,7 @@ static void hci_error_reset(struct work_struct *work) { struct hci_dev *hdev = container_of(work, struct hci_dev, error_reset); + hci_dev_hold(hdev); BT_DBG("%s", hdev->name); if (hdev->hw_error) @@ -2325,10 +2326,10 @@ static void hci_error_reset(struct work_struct *work) else bt_dev_err(hdev, "hardware error 0x%2.2x", hdev->hw_error_code); - if (hci_dev_do_close(hdev)) - return; + if (!hci_dev_do_close(hdev)) + hci_dev_do_open(hdev); - hci_dev_do_open(hdev); + hci_dev_put(hdev); } void hci_uuids_clear(struct hci_dev *hdev) diff --git a/net/bluetooth/hci_debugfs.c b/net/bluetooth/hci_debugfs.c index d4efc4aa5..131bb56bf 100644 --- a/net/bluetooth/hci_debugfs.c +++ b/net/bluetooth/hci_debugfs.c @@ -216,10 +216,12 @@ static int conn_info_min_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val > hdev->conn_info_max_age) + hci_dev_lock(hdev); + if (val == 0 || val > hdev->conn_info_max_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_min_age = val; hci_dev_unlock(hdev); @@ -244,10 +246,12 @@ static int conn_info_max_age_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val < hdev->conn_info_min_age) + hci_dev_lock(hdev); + if (val == 0 || val < hdev->conn_info_min_age) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->conn_info_max_age = val; hci_dev_unlock(hdev); @@ -526,10 +530,12 @@ static int sniff_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val > hdev->sniff_max_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val > hdev->sniff_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_min_interval = val; hci_dev_unlock(hdev); @@ -554,10 +560,12 @@ static int sniff_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val == 0 || val % 2 || val < hdev->sniff_min_interval) + hci_dev_lock(hdev); + if (val == 0 || val % 2 || val < hdev->sniff_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->sniff_max_interval = val; hci_dev_unlock(hdev); @@ -798,10 +806,12 @@ static int conn_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val > hdev->le_conn_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_min_interval = val; hci_dev_unlock(hdev); @@ -826,10 +836,12 @@ static int conn_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) + hci_dev_lock(hdev); + if (val < 0x0006 || val > 0x0c80 || val < hdev->le_conn_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_conn_max_interval = val; hci_dev_unlock(hdev); @@ -938,10 +950,12 @@ static int adv_min_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val > hdev->le_adv_max_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_min_interval = val; hci_dev_unlock(hdev); @@ -966,10 +980,12 @@ static int adv_max_interval_set(void *data, u64 val) { struct hci_dev *hdev = data; - if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) + hci_dev_lock(hdev); + if (val < 0x0020 || val > 0x4000 || val < hdev->le_adv_min_interval) { + hci_dev_unlock(hdev); return -EINVAL; + } - hci_dev_lock(hdev); hdev->le_adv_max_interval = val; hci_dev_unlock(hdev); diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 4027c7978..58c029958 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -2636,6 +2636,31 @@ static void hci_conn_complete_evt(struct hci_dev *hdev, struct sk_buff *skb) if (test_bit(HCI_ENCRYPT, &hdev->flags)) set_bit(HCI_CONN_ENCRYPT, &conn->flags); + /* "Link key request" completed ahead of "connect request" completes */ + if (ev->encr_mode == 1 && !test_bit(HCI_CONN_ENCRYPT, &conn->flags) && + ev->link_type == ACL_LINK) { + struct link_key *key; + struct hci_cp_read_enc_key_size cp; + + key = hci_find_link_key(hdev, &ev->bdaddr); + if (key) { + set_bit(HCI_CONN_ENCRYPT, &conn->flags); + + if (!(hdev->commands[20] & 0x10)) { + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } else { + cp.handle = cpu_to_le16(conn->handle); + if (hci_send_cmd(hdev, HCI_OP_READ_ENC_KEY_SIZE, + sizeof(cp), &cp)) { + bt_dev_err(hdev, "sending read key size failed"); + conn->enc_key_size = HCI_LINK_KEY_SIZE; + } + } + + hci_encrypt_cfm(conn, ev->status); + } + } + /* Get remote features */ if (conn->type == ACL_LINK) { struct hci_cp_read_remote_features cp; @@ -2979,8 +3004,6 @@ static void hci_remote_name_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s", hdev->name); - hci_conn_check_pending(hdev); - hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); @@ -4612,9 +4635,12 @@ static void hci_io_capa_request_evt(struct hci_dev *hdev, struct sk_buff *skb) hci_dev_lock(hdev); conn = hci_conn_hash_lookup_ba(hdev, ACL_LINK, &ev->bdaddr); - if (!conn || !hci_conn_ssp_enabled(conn)) + if (!conn || !hci_dev_test_flag(hdev, HCI_SSP_ENABLED)) goto unlock; + /* Assume remote supports SSP since it has triggered this event */ + set_bit(HCI_CONN_SSP_ENABLED, &conn->flags); + hci_conn_hold(conn); if (!hci_dev_test_flag(hdev, HCI_MGMT)) @@ -5922,6 +5948,10 @@ static void hci_le_remote_conn_param_req_evt(struct hci_dev *hdev, return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_UNKNOWN_CONN_ID); + if (max > hcon->le_conn_max_interval) + return send_conn_param_neg_reply(hdev, handle, + HCI_ERROR_INVALID_LL_PARAMS); + if (hci_check_conn_params(min, max, latency, timeout)) return send_conn_param_neg_reply(hdev, handle, HCI_ERROR_INVALID_LL_PARAMS); @@ -6139,10 +6169,10 @@ static void hci_store_wake_reason(struct hci_dev *hdev, u8 event, * keep track of the bdaddr of the connection event that woke us up. */ if (event == HCI_EV_CONN_REQUEST) { - bacpy(&hdev->wake_addr, &conn_complete->bdaddr); + bacpy(&hdev->wake_addr, &conn_request->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_CONN_COMPLETE) { - bacpy(&hdev->wake_addr, &conn_request->bdaddr); + bacpy(&hdev->wake_addr, &conn_complete->bdaddr); hdev->wake_addr_type = BDADDR_BREDR; } else if (event == HCI_EV_LE_META) { struct hci_ev_le_meta *le_ev = (void *)skb->data; diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index a0f980e61..7ce6db1ac 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -107,8 +107,10 @@ static void hci_req_sync_complete(struct hci_dev *hdev, u8 result, u16 opcode, if (hdev->req_status == HCI_REQ_PEND) { hdev->req_result = result; hdev->req_status = HCI_REQ_DONE; - if (skb) + if (skb) { + kfree_skb(hdev->req_skb); hdev->req_skb = skb_get(skb); + } wake_up_interruptible(&hdev->req_wait_q); } } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index cf78a4808..580b6d6b9 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -5609,7 +5609,13 @@ static inline int l2cap_conn_param_update_req(struct l2cap_conn *conn, memset(&rsp, 0, sizeof(rsp)); - err = hci_check_conn_params(min, max, latency, to_multiplier); + if (max > hcon->le_conn_max_interval) { + BT_DBG("requested connection interval exceeds current bounds."); + err = -EINVAL; + } else { + err = hci_check_conn_params(min, max, latency, to_multiplier); + } + if (err) rsp.result = cpu_to_le16(L2CAP_CONN_PARAM_REJECTED); else @@ -6522,7 +6528,8 @@ static inline void l2cap_sig_channel(struct l2cap_conn *conn, if (len > skb->len || !cmd->ident) { BT_DBG("corrupted command"); l2cap_sig_send_rej(conn, cmd->ident); - break; + skb_pull(skb, len > skb->len ? skb->len : len); + continue; } err = l2cap_bredr_sig_cmd(conn, cmd, len, skb->data); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index 756523e54..3a2be1b4a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -456,7 +456,8 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, struct l2cap_chan *chan = l2cap_pi(sk)->chan; struct l2cap_options opts; struct l2cap_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; u32 opt; BT_DBG("sk %p", sk); @@ -503,7 +504,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mode 0x%2.2x", chan->mode); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *) &opts, len)) err = -EFAULT; @@ -553,7 +554,7 @@ static int l2cap_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = chan->conn->hcon->handle; memcpy(cinfo.dev_class, chan->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *) &cinfo, len)) err = -EFAULT; diff --git a/net/bluetooth/rfcomm/core.c b/net/bluetooth/rfcomm/core.c index 8d6fce900..4f54c7df3 100644 --- a/net/bluetooth/rfcomm/core.c +++ b/net/bluetooth/rfcomm/core.c @@ -1937,7 +1937,7 @@ static struct rfcomm_session *rfcomm_process_rx(struct rfcomm_session *s) /* Get data directly from socket receive queue without copying it. */ while ((skb = skb_dequeue(&sk->sk_receive_queue))) { skb_orphan(skb); - if (!skb_linearize(skb)) { + if (!skb_linearize(skb) && sk->sk_state != BT_CLOSED) { s = rfcomm_recv_frame(s, skb); if (!s) break; diff --git a/net/bluetooth/sco.c b/net/bluetooth/sco.c index 8244d3ae1..2115ca6d7 100644 --- a/net/bluetooth/sco.c +++ b/net/bluetooth/sco.c @@ -825,7 +825,7 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, unsigned int optlen) { struct sock *sk = sock->sk; - int len, err = 0; + int err = 0; struct bt_voice voice; u32 opt; @@ -841,10 +841,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; } - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) set_bit(BT_SK_DEFER_SETUP, &bt_sk(sk)->flags); @@ -861,11 +860,10 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, voice.setting = sco_pi(sk)->setting; - len = min_t(unsigned int, sizeof(voice), optlen); - if (copy_from_sockptr(&voice, optval, len)) { - err = -EFAULT; + err = bt_copy_from_sockptr(&voice, sizeof(voice), optval, + optlen); + if (err) break; - } /* Explicitly check for these values */ if (voice.setting != BT_VOICE_TRANSPARENT && @@ -878,10 +876,9 @@ static int sco_sock_setsockopt(struct socket *sock, int level, int optname, break; case BT_PKT_STATUS: - if (copy_from_sockptr(&opt, optval, sizeof(u32))) { - err = -EFAULT; + err = bt_copy_from_sockptr(&opt, sizeof(opt), optval, optlen); + if (err) break; - } if (opt) sco_pi(sk)->cmsg_mask |= SCO_CMSG_PKT_STATUS; @@ -904,7 +901,8 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, struct sock *sk = sock->sk; struct sco_options opts; struct sco_conninfo cinfo; - int len, err = 0; + int err = 0; + size_t len; BT_DBG("sk %p", sk); @@ -926,7 +924,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, BT_DBG("mtu %d", opts.mtu); - len = min_t(unsigned int, len, sizeof(opts)); + len = min(len, sizeof(opts)); if (copy_to_user(optval, (char *)&opts, len)) err = -EFAULT; @@ -944,7 +942,7 @@ static int sco_sock_getsockopt_old(struct socket *sock, int optname, cinfo.hci_handle = sco_pi(sk)->conn->hcon->handle; memcpy(cinfo.dev_class, sco_pi(sk)->conn->hcon->dev_class, 3); - len = min_t(unsigned int, len, sizeof(cinfo)); + len = min(len, sizeof(cinfo)); if (copy_to_user(optval, (char *)&cinfo, len)) err = -EFAULT; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index bab14186f..14a06d8b1 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1070,6 +1070,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) struct ebt_table_info *newinfo; struct ebt_replace tmp; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1309,6 +1311,8 @@ static int update_counters(struct net *net, sockptr_t arg, unsigned int len) { struct ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; @@ -2238,6 +2242,8 @@ static int compat_update_counters(struct net *net, sockptr_t arg, { struct compat_ebt_replace hlp; + if (len < sizeof(hlp)) + return -EINVAL; if (copy_from_sockptr(&hlp, arg, sizeof(hlp))) return -EFAULT; diff --git a/net/can/j1939/j1939-priv.h b/net/can/j1939/j1939-priv.h index cea712fb2..9ac2a10b1 100644 --- a/net/can/j1939/j1939-priv.h +++ b/net/can/j1939/j1939-priv.h @@ -297,6 +297,7 @@ struct j1939_sock { int ifindex; struct j1939_addr addr; + spinlock_t filters_lock; struct j1939_filter *filters; int nfilters; pgn_t pgn_rx_filter; diff --git a/net/can/j1939/socket.c b/net/can/j1939/socket.c index 906a08d38..c216c60f5 100644 --- a/net/can/j1939/socket.c +++ b/net/can/j1939/socket.c @@ -262,12 +262,17 @@ static bool j1939_sk_match_dst(struct j1939_sock *jsk, static bool j1939_sk_match_filter(struct j1939_sock *jsk, const struct j1939_sk_buff_cb *skcb) { - const struct j1939_filter *f = jsk->filters; - int nfilter = jsk->nfilters; + const struct j1939_filter *f; + int nfilter; + + spin_lock_bh(&jsk->filters_lock); + + f = jsk->filters; + nfilter = jsk->nfilters; if (!nfilter) /* receive all when no filters are assigned */ - return true; + goto filter_match_found; for (; nfilter; ++f, --nfilter) { if ((skcb->addr.pgn & f->pgn_mask) != f->pgn) @@ -276,9 +281,15 @@ static bool j1939_sk_match_filter(struct j1939_sock *jsk, continue; if ((skcb->addr.src_name & f->name_mask) != f->name) continue; - return true; + goto filter_match_found; } + + spin_unlock_bh(&jsk->filters_lock); return false; + +filter_match_found: + spin_unlock_bh(&jsk->filters_lock); + return true; } static bool j1939_sk_recv_match_one(struct j1939_sock *jsk, @@ -401,6 +412,7 @@ static int j1939_sk_init(struct sock *sk) atomic_set(&jsk->skb_pending, 0); spin_lock_init(&jsk->sk_session_queue_lock); INIT_LIST_HEAD(&jsk->sk_session_queue); + spin_lock_init(&jsk->filters_lock); /* j1939_sk_sock_destruct() depends on SOCK_RCU_FREE flag */ sock_set_flag(sk, SOCK_RCU_FREE); @@ -703,9 +715,11 @@ static int j1939_sk_setsockopt(struct socket *sock, int level, int optname, } lock_sock(&jsk->sk); + spin_lock_bh(&jsk->filters_lock); ofilters = jsk->filters; jsk->filters = filters; jsk->nfilters = count; + spin_unlock_bh(&jsk->filters_lock); release_sock(&jsk->sk); kfree(ofilters); return 0; diff --git a/net/core/dev.c b/net/core/dev.c index fc881d60a..0e2c433be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2324,7 +2324,7 @@ void dev_queue_xmit_nit(struct sk_buff *skb, struct net_device *dev) rcu_read_lock(); again: list_for_each_entry_rcu(ptype, ptype_list, list) { - if (ptype->ignore_outgoing) + if (READ_ONCE(ptype->ignore_outgoing)) continue; /* Never send packets back to the socket @@ -8787,7 +8787,7 @@ EXPORT_SYMBOL(dev_set_mac_address_user); int dev_get_mac_address(struct sockaddr *sa, struct net *net, char *dev_name) { - size_t size = sizeof(sa->sa_data); + size_t size = sizeof(sa->sa_data_min); struct net_device *dev; int ret = 0; diff --git a/net/core/dev_ioctl.c b/net/core/dev_ioctl.c index 993420da2..60e815a71 100644 --- a/net/core/dev_ioctl.c +++ b/net/core/dev_ioctl.c @@ -245,7 +245,7 @@ static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd) if (ifr->ifr_hwaddr.sa_family != dev->type) return -EINVAL; memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data, - min(sizeof(ifr->ifr_hwaddr.sa_data), + min(sizeof(ifr->ifr_hwaddr.sa_data_min), (size_t)dev->addr_len)); call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return 0; diff --git a/net/core/filter.c b/net/core/filter.c index 6cfc8fb05..49e4d1535 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -9903,8 +9903,7 @@ int sk_detach_filter(struct sock *sk) } EXPORT_SYMBOL_GPL(sk_detach_filter); -int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, - unsigned int len) +int sk_get_filter(struct sock *sk, sockptr_t optval, unsigned int len) { struct sock_fprog_kern *fprog; struct sk_filter *filter; @@ -9935,7 +9934,7 @@ int sk_get_filter(struct sock *sk, struct sock_filter __user *ubuf, goto out; ret = -EFAULT; - if (copy_to_user(ubuf, fprog->filter, bpf_classic_proglen(fprog))) + if (copy_to_sockptr(optval, fprog->filter, bpf_classic_proglen(fprog))) goto out; /* Instead of bytes, the API requests to return the number diff --git a/net/core/request_sock.c b/net/core/request_sock.c index f35c2e998..63de5c635 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -33,9 +33,6 @@ void reqsk_queue_alloc(struct request_sock_queue *queue) { - spin_lock_init(&queue->rskq_lock); - - spin_lock_init(&queue->fastopenq.lock); queue->fastopenq.rskq_rst_head = NULL; queue->fastopenq.rskq_rst_tail = NULL; queue->fastopenq.qlen = 0; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 021dcfdae..8938320f7 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -4903,10 +4903,9 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct net *net = sock_net(skb->sk); struct ifinfomsg *ifm; struct net_device *dev; - struct nlattr *br_spec, *attr = NULL; + struct nlattr *br_spec, *attr, *br_flags_attr = NULL; int rem, err = -EOPNOTSUPP; u16 flags = 0; - bool have_flags = false; if (nlmsg_len(nlh) < sizeof(*ifm)) return -EINVAL; @@ -4924,11 +4923,11 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, br_spec = nlmsg_find_attr(nlh, sizeof(struct ifinfomsg), IFLA_AF_SPEC); if (br_spec) { nla_for_each_nested(attr, br_spec, rem) { - if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !have_flags) { + if (nla_type(attr) == IFLA_BRIDGE_FLAGS && !br_flags_attr) { if (nla_len(attr) < sizeof(flags)) return -EINVAL; - have_flags = true; + br_flags_attr = attr; flags = nla_get_u16(attr); } @@ -4972,8 +4971,8 @@ static int rtnl_bridge_setlink(struct sk_buff *skb, struct nlmsghdr *nlh, } } - if (have_flags) - memcpy(nla_data(attr), &flags, sizeof(flags)); + if (br_flags_attr) + memcpy(nla_data(br_flags_attr), &flags, sizeof(flags)); out: return err; } diff --git a/net/core/scm.c b/net/core/scm.c index 3c7f16072..d09849cb6 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -105,7 +105,7 @@ static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp) if (fd < 0 || !(file = fget_raw(fd))) return -EBADF; /* don't allow io_uring files */ - if (io_uring_get_socket(file)) { + if (io_is_uring_fops(file)) { fput(file); return -EINVAL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 196278a13..50261f3ae 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -3877,8 +3877,9 @@ struct sk_buff *skb_segment(struct sk_buff *head_skb, /* GSO partial only requires that we trim off any excess that * doesn't fit into an MSS sized block, so take care of that * now. + * Cap len to not accidentally hit GSO_BY_FRAGS. */ - partial_segs = len / mss; + partial_segs = min(len, GSO_BY_FRAGS - 1U) / mss; if (partial_segs > 1) mss *= partial_segs; else diff --git a/net/core/sock.c b/net/core/sock.c index 769e969cd..016c0b9e0 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -644,8 +644,8 @@ out: return ret; } -static int sock_getbindtodevice(struct sock *sk, char __user *optval, - int __user *optlen, int len) +static int sock_getbindtodevice(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES @@ -668,12 +668,12 @@ static int sock_getbindtodevice(struct sock *sk, char __user *optval, len = strlen(devname) + 1; ret = -EFAULT; - if (copy_to_user(optval, devname, len)) + if (copy_to_sockptr(optval, devname, len)) goto out; zero: ret = -EFAULT; - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) goto out; ret = 0; @@ -1281,22 +1281,25 @@ static void cred_to_ucred(struct pid *pid, const struct cred *cred, } } -static int groups_to_user(gid_t __user *dst, const struct group_info *src) +static int groups_to_user(sockptr_t dst, const struct group_info *src) { struct user_namespace *user_ns = current_user_ns(); int i; - for (i = 0; i < src->ngroups; i++) - if (put_user(from_kgid_munged(user_ns, src->gid[i]), dst + i)) + for (i = 0; i < src->ngroups; i++) { + gid_t gid = from_kgid_munged(user_ns, src->gid[i]); + + if (copy_to_sockptr_offset(dst, i * sizeof(gid), &gid, sizeof(gid))) return -EFAULT; + } return 0; } -int sock_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) +static int sk_getsockopt(struct sock *sk, int level, int optname, + sockptr_t optval, sockptr_t optlen) { - struct sock *sk = sock->sk; + struct socket *sock = sk->sk_socket; union { int val; @@ -1312,7 +1315,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, int lv = sizeof(int); int len; - if (get_user(len, optlen)) + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; @@ -1445,7 +1448,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, cred_to_ucred(sk->sk_peer_pid, sk->sk_peer_cred, &peercred); spin_unlock(&sk->sk_peer_lock); - if (copy_to_user(optval, &peercred, len)) + if (copy_to_sockptr(optval, &peercred, len)) return -EFAULT; goto lenout; } @@ -1463,11 +1466,11 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len < n * sizeof(gid_t)) { len = n * sizeof(gid_t); put_cred(cred); - return put_user(len, optlen) ? -EFAULT : -ERANGE; + return copy_to_sockptr(optlen, &len, sizeof(int)) ? -EFAULT : -ERANGE; } len = n * sizeof(gid_t); - ret = groups_to_user((gid_t __user *)optval, cred->group_info); + ret = groups_to_user(optval, cred->group_info); put_cred(cred); if (ret) return ret; @@ -1483,7 +1486,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, return -ENOTCONN; if (lv < len) return -EINVAL; - if (copy_to_user(optval, address, len)) + if (copy_to_sockptr(optval, address, len)) return -EFAULT; goto lenout; } @@ -1500,7 +1503,8 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_PEERSEC: - return security_socket_getpeersec_stream(sock, optval, optlen, len); + return security_socket_getpeersec_stream(sock, + optval, optlen, len); case SO_MARK: v.val = sk->sk_mark; @@ -1528,7 +1532,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, return sock_getbindtodevice(sk, optval, optlen, len); case SO_GET_FILTER: - len = sk_get_filter(sk, (struct sock_filter __user *)optval, len); + len = sk_get_filter(sk, optval, len); if (len < 0) return len; @@ -1575,7 +1579,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, sk_get_meminfo(sk, meminfo); len = min_t(unsigned int, len, sizeof(meminfo)); - if (copy_to_user(optval, &meminfo, len)) + if (copy_to_sockptr(optval, &meminfo, len)) return -EFAULT; goto lenout; @@ -1625,14 +1629,22 @@ int sock_getsockopt(struct socket *sock, int level, int optname, if (len > lv) len = lv; - if (copy_to_user(optval, &v, len)) + if (copy_to_sockptr(optval, &v, len)) return -EFAULT; lenout: - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; return 0; } +int sock_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + return sk_getsockopt(sock->sk, level, optname, + USER_SOCKPTR(optval), + USER_SOCKPTR(optlen)); +} + /* * Initialize an sk_lock. * diff --git a/net/core/sock_diag.c b/net/core/sock_diag.c index c9c45b935..bce65b519 100644 --- a/net/core/sock_diag.c +++ b/net/core/sock_diag.c @@ -189,7 +189,7 @@ int sock_diag_register(const struct sock_diag_handler *hndl) if (sock_diag_handlers[hndl->family]) err = -EBUSY; else - sock_diag_handlers[hndl->family] = hndl; + WRITE_ONCE(sock_diag_handlers[hndl->family], hndl); mutex_unlock(&sock_diag_table_mutex); return err; @@ -205,7 +205,7 @@ void sock_diag_unregister(const struct sock_diag_handler *hnld) mutex_lock(&sock_diag_table_mutex); BUG_ON(sock_diag_handlers[family] != hnld); - sock_diag_handlers[family] = NULL; + WRITE_ONCE(sock_diag_handlers[family], NULL); mutex_unlock(&sock_diag_table_mutex); } EXPORT_SYMBOL_GPL(sock_diag_unregister); @@ -223,7 +223,7 @@ static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; req->sdiag_family = array_index_nospec(req->sdiag_family, AF_MAX); - if (sock_diag_handlers[req->sdiag_family] == NULL) + if (READ_ONCE(sock_diag_handlers[req->sdiag_family]) == NULL) sock_load_diag_module(req->sdiag_family, 0); mutex_lock(&sock_diag_table_mutex); @@ -282,12 +282,12 @@ static int sock_diag_bind(struct net *net, int group) switch (group) { case SKNLGRP_INET_TCP_DESTROY: case SKNLGRP_INET_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET]) + if (!READ_ONCE(sock_diag_handlers[AF_INET])) sock_load_diag_module(AF_INET, 0); break; case SKNLGRP_INET6_TCP_DESTROY: case SKNLGRP_INET6_UDP_DESTROY: - if (!sock_diag_handlers[AF_INET6]) + if (!READ_ONCE(sock_diag_handlers[AF_INET6])) sock_load_diag_module(AF_INET6, 0); break; } diff --git a/net/core/sock_map.c b/net/core/sock_map.c index f375ef150..52e395a18 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -422,6 +422,9 @@ static int __sock_map_delete(struct bpf_stab *stab, struct sock *sk_test, struct sock *sk; int err = 0; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + raw_spin_lock_bh(&stab->lock); sk = *psk; if (!sk_test || sk_test == sk) @@ -955,6 +958,9 @@ static int sock_hash_delete_elem(struct bpf_map *map, void *key) struct bpf_shtab_elem *elem; int ret = -ENOENT; + if (irqs_disabled()) + return -EOPNOTSUPP; /* locks here are hardirq-unsafe */ + hash = sock_hash_bucket_hash(key, key_size); bucket = sock_hash_select_bucket(htab, hash); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index dac65180c..61cb40368 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -164,17 +164,7 @@ __be16 eth_type_trans(struct sk_buff *skb, struct net_device *dev) eth = (struct ethhdr *)skb->data; skb_pull_inline(skb, ETH_HLEN); - if (unlikely(!ether_addr_equal_64bits(eth->h_dest, - dev->dev_addr))) { - if (unlikely(is_multicast_ether_addr_64bits(eth->h_dest))) { - if (ether_addr_equal_64bits(eth->h_dest, dev->broadcast)) - skb->pkt_type = PACKET_BROADCAST; - else - skb->pkt_type = PACKET_MULTICAST; - } else { - skb->pkt_type = PACKET_OTHERHOST; - } - } + eth_skb_pkt_type(skb, dev); /* * Some variants of DSA tagging don't have an ethertype field diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 84e6ef4f3..c5a4c5fb7 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -291,7 +291,7 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "HSR: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "HSR: Could not send supervision frame\n"); return; } @@ -338,7 +338,7 @@ static void send_prp_supervision_frame(struct hsr_port *master, skb = hsr_init_skb(master); if (!skb) { - WARN_ONCE(1, "PRP: Could not send supervision frame\n"); + netdev_warn_once(master->dev, "PRP: Could not send supervision frame\n"); return; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index afc97d65c..fc9fb3e5a 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -237,6 +237,10 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct list_head *node_db, */ if (ethhdr->h_proto == htons(ETH_P_PRP) || ethhdr->h_proto == htons(ETH_P_HSR)) { + /* Check if skb contains hsr_ethhdr */ + if (skb->mac_len < sizeof(struct hsr_ethhdr)) + return NULL; + /* Use the existing sequence_nr from the tag as starting point * for filtering duplicate frames. */ @@ -327,9 +331,12 @@ void hsr_handle_sup_frame(struct hsr_frame_info *frame) node_real->addr_B_port = port_rcv->type; spin_lock_bh(&hsr->list_lock); - list_del_rcu(&node_curr->mac_list); + if (!node_curr->removed) { + list_del_rcu(&node_curr->mac_list); + node_curr->removed = true; + kfree_rcu(node_curr, rcu_head); + } spin_unlock_bh(&hsr->list_lock); - kfree_rcu(node_curr, rcu_head); done: /* PRP uses v0 header */ @@ -506,9 +513,12 @@ void hsr_prune_nodes(struct timer_list *t) if (time_is_before_jiffies(timestamp + msecs_to_jiffies(HSR_NODE_FORGET_TIME))) { hsr_nl_nodedown(hsr, node->macaddress_A); - list_del_rcu(&node->mac_list); - /* Note that we need to free this entry later: */ - kfree_rcu(node, rcu_head); + if (!node->removed) { + list_del_rcu(&node->mac_list); + node->removed = true; + /* Note that we need to free this entry later: */ + kfree_rcu(node, rcu_head); + } } } spin_unlock_bh(&hsr->list_lock); diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 5a771cb3f..48990166e 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -82,6 +82,7 @@ struct hsr_node { bool san_a; bool san_b; u16 seq_out[HSR_PT_PORTS]; + bool removed; struct rcu_head rcu_head; }; diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index 2fd1976e5..bea7f935f 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -137,14 +137,21 @@ static struct notifier_block hsr_nb = { static int __init hsr_init(void) { - int res; + int err; BUILD_BUG_ON(sizeof(struct hsr_tag) != HSR_HLEN); - register_netdevice_notifier(&hsr_nb); - res = hsr_netlink_init(); + err = register_netdevice_notifier(&hsr_nb); + if (err) + return err; + + err = hsr_netlink_init(); + if (err) { + unregister_netdevice_notifier(&hsr_nb); + return err; + } - return res; + return 0; } static void __exit hsr_exit(void) diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index acb488735..5f1b334e6 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -327,6 +327,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; @@ -1597,10 +1600,12 @@ EXPORT_SYMBOL(inet_current_timestamp); int inet_recv_error(struct sock *sk, struct msghdr *msg, int len, int *addr_len) { - if (sk->sk_family == AF_INET) + unsigned int family = READ_ONCE(sk->sk_family); + + if (family == AF_INET) return ip_recv_error(sk, msg, len, addr_len); #if IS_ENABLED(CONFIG_IPV6) - if (sk->sk_family == AF_INET6) + if (family == AF_INET6) return pingv6_ops.ipv6_recv_error(sk, msg, len, addr_len); #endif return -EINVAL; diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 83a47998c..8ae9bd6f9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -1104,7 +1104,8 @@ static int arp_req_get(struct arpreq *r, struct net_device *dev) if (neigh) { if (!(neigh->nud_state & NUD_NOARP)) { read_lock_bh(&neigh->lock); - memcpy(r->arp_ha.sa_data, neigh->ha, dev->addr_len); + memcpy(r->arp_ha.sa_data, neigh->ha, + min(dev->addr_len, (unsigned char)sizeof(r->arp_ha.sa_data_min))); r->arp_flags = arp_state_to_flags(neigh); read_unlock_bh(&neigh->lock); r->arp_ha.sa_family = dev->type; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index da1ca8081..9ac7d47d2 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1798,6 +1798,21 @@ done: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv4.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) { const struct nlmsghdr *nlh = cb->nlh; @@ -1849,8 +1864,7 @@ static int inet_dump_ifaddr(struct sk_buff *skb, struct netlink_callback *cb) idx = 0; head = &tgt_net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv4.dev_addr_genid) ^ - tgt_net->dev_base_seq; + cb->seq = inet_base_seq(tgt_net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2249,8 +2263,7 @@ static int inet_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv4.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index cb55fede0..f0a313747 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -2493,8 +2493,8 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } newpsl->sl_max = newpsl->sl_count = msf->imsf_numsrc; - memcpy(newpsl->sl_addr, msf->imsf_slist, - msf->imsf_numsrc * sizeof(msf->imsf_slist[0])); + memcpy(newpsl->sl_addr, msf->imsf_slist_flex, + flex_array_size(msf, imsf_slist_flex, msf->imsf_numsrc)); err = ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, newpsl->sl_count, newpsl->sl_addr, 0); if (err) { @@ -2526,11 +2526,10 @@ done: err = ip_mc_leave_group(sk, &imr); return err; } - int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, - struct ip_msfilter __user *optval, int __user *optlen) + sockptr_t optval, sockptr_t optlen) { - int err, len, count, copycount; + int err, len, count, copycount, msf_size; struct ip_mreqn imr; __be32 addr = msf->imsf_multiaddr; struct ip_mc_socklist *pmc; @@ -2571,14 +2570,17 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, count = psl->sl_count; } copycount = count < msf->imsf_numsrc ? count : msf->imsf_numsrc; - len = copycount * sizeof(psl->sl_addr[0]); + len = flex_array_size(psl, sl_addr, copycount); msf->imsf_numsrc = count; - if (put_user(IP_MSFILTER_SIZE(copycount), optlen) || - copy_to_user(optval, msf, IP_MSFILTER_SIZE(0))) { + msf_size = IP_MSFILTER_SIZE(copycount); + if (copy_to_sockptr(optlen, &msf_size, sizeof(int)) || + copy_to_sockptr(optval, msf, IP_MSFILTER_SIZE(0))) { return -EFAULT; } if (len && - copy_to_user(&optval->imsf_slist[0], psl->sl_addr, len)) + copy_to_sockptr_offset(optval, + offsetof(struct ip_msfilter, imsf_slist_flex), + psl->sl_addr, len)) return -EFAULT; return 0; done: @@ -2586,7 +2588,7 @@ done: } int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, - struct sockaddr_storage __user *p) + sockptr_t optval, size_t ss_offset) { int i, count, copycount; struct sockaddr_in *psin; @@ -2616,15 +2618,17 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; gsf->gf_numsrc = count; - for (i = 0; i < copycount; i++, p++) { + for (i = 0; i < copycount; i++) { struct sockaddr_storage ss; psin = (struct sockaddr_in *)&ss; memset(&ss, 0, sizeof(ss)); psin->sin_family = AF_INET; psin->sin_addr.s_addr = psl->sl_addr[i]; - if (copy_to_user(p, &ss, sizeof(ss))) + if (copy_to_sockptr_offset(optval, ss_offset, + &ss, sizeof(ss))) return -EFAULT; + ss_offset += sizeof(ss); } return 0; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 5f71a1c74..6ebe43b4d 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -536,6 +536,10 @@ out: } if (req) reqsk_put(req); + + if (newsk) + inet_init_csk_locks(newsk); + return newsk; out_err: newsk = NULL; @@ -576,6 +580,20 @@ void inet_csk_clear_xmit_timers(struct sock *sk) } EXPORT_SYMBOL(inet_csk_clear_xmit_timers); +void inet_csk_clear_xmit_timers_sync(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + + /* ongoing timer handlers need to acquire socket lock. */ + sock_not_owned_by_me(sk); + + icsk->icsk_pending = icsk->icsk_ack.pending = 0; + + sk_stop_timer_sync(sk, &icsk->icsk_retransmit_timer); + sk_stop_timer_sync(sk, &icsk->icsk_delack_timer); + sk_stop_timer_sync(sk, &sk->sk_timer); +} + void inet_csk_delete_keepalive_timer(struct sock *sk) { sk_stop_timer(sk, &sk->sk_timer); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index fa9f1de58..27a5a7d66 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -57,7 +57,7 @@ static const struct inet_diag_handler *inet_diag_lock_handler(int proto) return ERR_PTR(-ENOENT); } - if (!inet_diag_table[proto]) + if (!READ_ONCE(inet_diag_table[proto])) sock_load_diag_module(AF_INET, proto); mutex_lock(&inet_diag_table_mutex); @@ -1413,7 +1413,7 @@ int inet_diag_register(const struct inet_diag_handler *h) mutex_lock(&inet_diag_table_mutex); err = -EEXIST; if (!inet_diag_table[type]) { - inet_diag_table[type] = h; + WRITE_ONCE(inet_diag_table[type], h); err = 0; } mutex_unlock(&inet_diag_table_mutex); @@ -1430,7 +1430,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h) return; mutex_lock(&inet_diag_table_mutex); - inet_diag_table[type] = NULL; + WRITE_ONCE(inet_diag_table[type], NULL); mutex_unlock(&inet_diag_table_mutex); } EXPORT_SYMBOL_GPL(inet_diag_unregister); diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index c411c87ae..85cb44bfa 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -254,12 +254,12 @@ void __inet_twsk_schedule(struct inet_timewait_sock *tw, int timeo, bool rearm) } EXPORT_SYMBOL_GPL(__inet_twsk_schedule); +/* Remove all non full sockets (TIME_WAIT and NEW_SYN_RECV) for dead netns */ void inet_twsk_purge(struct inet_hashinfo *hashinfo, int family) { - struct inet_timewait_sock *tw; - struct sock *sk; struct hlist_nulls_node *node; unsigned int slot; + struct sock *sk; for (slot = 0; slot <= hashinfo->ehash_mask; slot++) { struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -268,25 +268,35 @@ restart_rcu: rcu_read_lock(); restart: sk_nulls_for_each_rcu(sk, node, &head->chain) { - if (sk->sk_state != TCP_TIME_WAIT) + int state = inet_sk_state_load(sk); + + if ((1 << state) & ~(TCPF_TIME_WAIT | + TCPF_NEW_SYN_RECV)) continue; - tw = inet_twsk(sk); - if ((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->count)) + + if (sk->sk_family != family || + refcount_read(&sock_net(sk)->count)) continue; - if (unlikely(!refcount_inc_not_zero(&tw->tw_refcnt))) + if (unlikely(!refcount_inc_not_zero(&sk->sk_refcnt))) continue; - if (unlikely((tw->tw_family != family) || - refcount_read(&twsk_net(tw)->count))) { - inet_twsk_put(tw); + if (unlikely(sk->sk_family != family || + refcount_read(&sock_net(sk)->count))) { + sock_gen_put(sk); goto restart; } rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule_put(tw); + if (state == TCP_TIME_WAIT) { + inet_twsk_deschedule_put(inet_twsk(sk)); + } else { + struct request_sock *req = inet_reqsk(sk); + + inet_csk_reqsk_queue_drop_and_put(req->rsk_listener, + req); + } local_bh_enable(); goto restart_rcu; } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index a6ad0fe13..0ac652fef 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -278,8 +278,13 @@ static int erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi, tpi->flags | TUNNEL_NO_KEY, iph->saddr, iph->daddr, 0); } else { + if (unlikely(!pskb_may_pull(skb, + gre_hdr_len + sizeof(*ershdr)))) + return PACKET_REJECT; + ershdr = (struct erspan_base_hdr *)(skb->data + gre_hdr_len); ver = ershdr->ver; + iph = ip_hdr(skb); tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, tpi->flags | TUNNEL_KEY, iph->saddr, iph->daddr, tpi->key); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a99c37410..12ee857d6 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1260,6 +1260,12 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, if (unlikely(!rt)) return -EFAULT; + cork->fragsize = ip_sk_use_pmtu(sk) ? + dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); + + if (!inetdev_valid_mtu(cork->fragsize)) + return -ENETUNREACH; + /* * setup for corking. */ @@ -1276,12 +1282,6 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : READ_ONCE(rt->dst.dev->mtu); - - if (!inetdev_valid_mtu(cork->fragsize)) - return -ENETUNREACH; - cork->gso_size = ipc->gso_size; cork->dst = &rt->dst; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 1b35afd32..b300d0988 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -670,12 +670,11 @@ static int set_mcast_msfilter(struct sock *sk, int ifindex, struct sockaddr_storage *group, struct sockaddr_storage *list) { - int msize = IP_MSFILTER_SIZE(numsrc); struct ip_msfilter *msf; struct sockaddr_in *psin; int err, i; - msf = kmalloc(msize, GFP_KERNEL); + msf = kmalloc(IP_MSFILTER_SIZE(numsrc), GFP_KERNEL); if (!msf) return -ENOBUFS; @@ -691,7 +690,7 @@ static int set_mcast_msfilter(struct sock *sk, int ifindex, if (psin->sin_family != AF_INET) goto Eaddrnotavail; - msf->imsf_slist[i] = psin->sin_addr.s_addr; + msf->imsf_slist_flex[i] = psin->sin_addr.s_addr; } err = ip_mc_msfilter(sk, msf, ifindex); kfree(msf); @@ -798,7 +797,8 @@ static int ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) goto out_free_gsf; err = set_mcast_msfilter(sk, gsf->gf_interface, gsf->gf_numsrc, - gsf->gf_fmode, &gsf->gf_group, gsf->gf_slist); + gsf->gf_fmode, &gsf->gf_group, + gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return err; @@ -807,7 +807,7 @@ out_free_gsf: static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; unsigned int n; void *p; @@ -821,7 +821,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, p = kmalloc(optlen + 4, GFP_KERNEL); if (!p) return -ENOMEM; - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ err = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) @@ -834,7 +834,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, goto out_free_gsf; err = -EINVAL; - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_gsf; /* numsrc >= (4G-140)/128 overflow in 32 bits */ @@ -842,7 +842,7 @@ static int compat_ip_set_mcast_msfilter(struct sock *sk, sockptr_t optval, 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); + &gf32->gf_group, gf32->gf_slist_flex); out_free_gsf: kfree(p); return err; @@ -1460,37 +1460,37 @@ static bool getsockopt_needs_rtnl(int optname) return false; } -static int ip_get_mcast_msfilter(struct sock *sk, void __user *optval, - int __user *optlen, int len) +static int ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { - const int size0 = offsetof(struct group_filter, gf_slist); - struct group_filter __user *p = optval; + const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter gsf; - int num; + int num, gsf_size; int err; if (len < size0) return -EINVAL; - if (copy_from_user(&gsf, p, size0)) + if (copy_from_sockptr(&gsf, optval, size0)) return -EFAULT; num = gsf.gf_numsrc; - err = ip_mc_gsfget(sk, &gsf, p->gf_slist); + err = ip_mc_gsfget(sk, &gsf, optval, + offsetof(struct group_filter, gf_slist_flex)); if (err) return err; if (gsf.gf_numsrc < num) num = gsf.gf_numsrc; - if (put_user(GROUP_FILTER_SIZE(num), optlen) || - copy_to_user(p, &gsf, size0)) + gsf_size = GROUP_FILTER_SIZE(num); + if (copy_to_sockptr(optlen, &gsf_size, sizeof(int)) || + copy_to_sockptr(optval, &gsf, size0)) return -EFAULT; return 0; } -static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, - int __user *optlen, int len) +static int compat_ip_get_mcast_msfilter(struct sock *sk, sockptr_t optval, + sockptr_t optlen, int len) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); - struct compat_group_filter __user *p = optval; + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter gf32; struct group_filter gf; int num; @@ -1498,7 +1498,7 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, if (len < size0) return -EINVAL; - if (copy_from_user(&gf32, p, size0)) + if (copy_from_sockptr(&gf32, optval, size0)) return -EFAULT; gf.gf_interface = gf32.gf_interface; @@ -1506,21 +1506,24 @@ static int compat_ip_get_mcast_msfilter(struct sock *sk, void __user *optval, num = gf.gf_numsrc = gf32.gf_numsrc; gf.gf_group = gf32.gf_group; - err = ip_mc_gsfget(sk, &gf, p->gf_slist); + err = ip_mc_gsfget(sk, &gf, optval, + offsetof(struct compat_group_filter, gf_slist_flex)); if (err) return err; if (gf.gf_numsrc < num) num = gf.gf_numsrc; len = GROUP_FILTER_SIZE(num) - (sizeof(gf) - sizeof(gf32)); - if (put_user(len, optlen) || - put_user(gf.gf_fmode, &p->gf_fmode) || - put_user(gf.gf_numsrc, &p->gf_numsrc)) + if (copy_to_sockptr(optlen, &len, sizeof(int)) || + copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_fmode), + &gf.gf_fmode, sizeof(gf.gf_fmode)) || + copy_to_sockptr_offset(optval, offsetof(struct compat_group_filter, gf_numsrc), + &gf.gf_numsrc, sizeof(gf.gf_numsrc))) return -EFAULT; return 0; } static int do_ip_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) + sockptr_t optval, sockptr_t optlen) { struct inet_sock *inet = inet_sk(sk); bool needs_rtnl = getsockopt_needs_rtnl(optname); @@ -1533,7 +1536,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (ip_mroute_opt(optname)) return ip_mroute_getsockopt(sk, optname, optval, optlen); - if (get_user(len, optlen)) + if (copy_from_sockptr(&len, optlen, sizeof(int))) return -EFAULT; if (len < 0) return -EINVAL; @@ -1558,15 +1561,17 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, inet_opt->opt.optlen); release_sock(sk); - if (opt->optlen == 0) - return put_user(0, optlen); + if (opt->optlen == 0) { + len = 0; + return copy_to_sockptr(optlen, &len, sizeof(int)); + } ip_options_undo(opt); len = min_t(unsigned int, len, opt->optlen); - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, opt->__data, len)) + if (copy_to_sockptr(optval, opt->__data, len)) return -EFAULT; return 0; } @@ -1657,9 +1662,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, addr.s_addr = inet->mc_addr; release_sock(sk); - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &addr, len)) + if (copy_to_sockptr(optval, &addr, len)) return -EFAULT; return 0; } @@ -1671,12 +1676,11 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, err = -EINVAL; goto out; } - if (copy_from_user(&msf, optval, IP_MSFILTER_SIZE(0))) { + if (copy_from_sockptr(&msf, optval, IP_MSFILTER_SIZE(0))) { err = -EFAULT; goto out; } - err = ip_mc_msfget(sk, &msf, - (struct ip_msfilter __user *)optval, optlen); + err = ip_mc_msfget(sk, &msf, optval, optlen); goto out; } case MCAST_MSFILTER: @@ -1698,8 +1702,13 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (sk->sk_type != SOCK_STREAM) return -ENOPROTOOPT; - msg.msg_control_is_user = true; - msg.msg_control_user = optval; + if (optval.is_kernel) { + msg.msg_control_is_user = false; + msg.msg_control = optval.kernel; + } else { + msg.msg_control_is_user = true; + msg.msg_control_user = optval.user; + } msg.msg_controllen = len; msg.msg_flags = in_compat_syscall() ? MSG_CMSG_COMPAT : 0; @@ -1720,7 +1729,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, put_cmsg(&msg, SOL_IP, IP_TOS, sizeof(tos), &tos); } len -= msg.msg_controllen; - return put_user(len, optlen); + return copy_to_sockptr(optlen, &len, sizeof(int)); } case IP_FREEBIND: val = inet->freebind; @@ -1743,15 +1752,15 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, if (len < sizeof(int) && len > 0 && val >= 0 && val <= 255) { unsigned char ucval = (unsigned char)val; len = 1; - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &ucval, 1)) + if (copy_to_sockptr(optval, &ucval, 1)) return -EFAULT; } else { len = min_t(unsigned int, sizeof(int), len); - if (put_user(len, optlen)) + if (copy_to_sockptr(optlen, &len, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &val, len)) + if (copy_to_sockptr(optval, &val, len)) return -EFAULT; } return 0; @@ -1768,7 +1777,8 @@ int ip_getsockopt(struct sock *sk, int level, { int err; - err = do_ip_getsockopt(sk, level, optname, optval, optlen); + err = do_ip_getsockopt(sk, level, optname, + USER_SOCKPTR(optval), USER_SOCKPTR(optlen)); #if IS_ENABLED(CONFIG_BPFILTER_UMH) if (optname >= BPFILTER_IPT_SO_GET_INFO && diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 99f70b990..0953d805c 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -364,7 +364,7 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, bool log_ecn_error) { const struct iphdr *iph = ip_hdr(skb); - int err; + int nh, err; #ifdef CONFIG_NET_IPGRE_BROADCAST if (ipv4_is_multicast(iph->daddr)) { @@ -390,8 +390,21 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, tunnel->i_seqno = ntohl(tpi->seq) + 1; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_set_network_header(skb, (tunnel->dev->type == ARPHRD_ETHER) ? ETH_HLEN : 0); + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + iph = (struct iphdr *)(skb->head + nh); + err = IP_ECN_decapsulate(iph, skb); if (unlikely(err)) { if (log_ecn_error) @@ -540,6 +553,20 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } +static void ip_tunnel_adj_headroom(struct net_device *dev, unsigned int headroom) +{ + /* we must cap headroom to some upperlimit, else pskb_expand_head + * will overflow header offsets in skb_headers_offset_update(). + */ + static const unsigned int max_allowed = 512; + + if (headroom > max_allowed) + headroom = max_allowed; + + if (headroom > READ_ONCE(dev->needed_headroom)) + WRITE_ONCE(dev->needed_headroom, headroom); +} + void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto, int tunnel_hlen) { @@ -613,13 +640,13 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, } headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; - if (headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, headroom); - - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, headroom)) { ip_rt_put(rt); goto tx_dropped; } + + ip_tunnel_adj_headroom(dev, headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, proto, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; @@ -797,16 +824,16 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, max_headroom = LL_RESERVED_SPACE(rt->dst.dev) + sizeof(struct iphdr) + rt->dst.header_len + ip_encap_hlen(&tunnel->encap); - if (max_headroom > READ_ONCE(dev->needed_headroom)) - WRITE_ONCE(dev->needed_headroom, max_headroom); - if (skb_cow_head(skb, READ_ONCE(dev->needed_headroom))) { + if (skb_cow_head(skb, max_headroom)) { ip_rt_put(rt); dev->stats.tx_dropped++; kfree_skb(skb); return; } + ip_tunnel_adj_headroom(dev, max_headroom); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, df, !net_eq(tunnel->net, dev_net(dev))); return; diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index da9a55c68..ba1388ba6 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -332,7 +332,7 @@ static int iptunnel_pmtud_build_icmpv6(struct sk_buff *skb, int mtu) }; skb_reset_network_header(skb); - csum = csum_partial(icmp6h, len, 0); + csum = skb_checksum(skb, skb_transport_offset(skb), len, 0); icmp6h->icmp6_cksum = csum_ipv6_magic(&nip6h->saddr, &nip6h->daddr, len, IPPROTO_ICMPV6, csum); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index be1976536..db184cb82 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1540,7 +1540,8 @@ out: } /* Getsock opt support for the multicast routing system. */ -int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) +int ip_mroute_getsockopt(struct sock *sk, int optname, sockptr_t optval, + sockptr_t optlen) { int olr; int val; @@ -1571,14 +1572,16 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int return -ENOPROTOOPT; } - if (get_user(olr, optlen)) + if (copy_from_sockptr(&olr, optlen, sizeof(int))) return -EFAULT; - olr = min_t(unsigned int, olr, sizeof(int)); if (olr < 0) return -EINVAL; - if (put_user(olr, optlen)) + + olr = min_t(unsigned int, olr, sizeof(int)); + + if (copy_to_sockptr(optlen, &olr, sizeof(int))) return -EFAULT; - if (copy_to_user(optval, &val, olr)) + if (copy_to_sockptr(optval, &val, olr)) return -EFAULT; return 0; } diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index d6d45d820..5823e89b8 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -955,6 +955,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -963,6 +965,8 @@ static int do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1253,6 +1257,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct arpt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1261,6 +1267,8 @@ static int compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index ec981618b..22e9ff592 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1109,6 +1109,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1117,6 +1119,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1493,6 +1497,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ipt_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1501,6 +1507,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index d360c7d70..cc409cc07 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -955,13 +955,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, gw); peer->rate_last = jiffies; ++peer->n_redirects; -#ifdef CONFIG_IP_ROUTE_VERBOSE - if (log_martians && + if (IS_ENABLED(CONFIG_IP_ROUTE_VERBOSE) && log_martians && peer->n_redirects == ip_rt_redirect_number) net_warn_ratelimited("host %pI4/if%d ignores redirects for %pI4 to %pI4\n", &ip_hdr(skb)->saddr, inet_iif(skb), &ip_hdr(skb)->daddr, &gw); -#endif } out_put_peer: inet_putpeer(peer); @@ -2090,6 +2088,9 @@ int ip_route_use_hint(struct sk_buff *skb, __be32 daddr, __be32 saddr, int err = -EINVAL; u32 tag = 0; + if (!in_dev) + return -EINVAL; + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3dd9b76f4..ac6cb2dc6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -726,6 +726,7 @@ void tcp_push(struct sock *sk, int flags, int mss_now, if (!test_bit(TSQ_THROTTLED, &sk->sk_tsq_flags)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPAUTOCORKING); set_bit(TSQ_THROTTLED, &sk->sk_tsq_flags); + smp_mb__after_atomic(); } /* It is possible TX completion already happened * before we set TSQ_THROTTLED. @@ -1777,6 +1778,36 @@ static skb_frag_t *skb_advance_to_frag(struct sk_buff *skb, u32 offset_skb, return frag; } +static bool can_map_frag(const skb_frag_t *frag) +{ + struct page *page; + + if (skb_frag_size(frag) != PAGE_SIZE || skb_frag_off(frag)) + return false; + + page = skb_frag_page(frag); + + if (PageCompound(page) || page->mapping) + return false; + + return true; +} + +static int find_next_mappable_frag(const skb_frag_t *frag, + int remaining_in_skb) +{ + int offset = 0; + + if (likely(can_map_frag(frag))) + return 0; + + while (offset < remaining_in_skb && !can_map_frag(frag)) { + offset += skb_frag_size(frag); + ++frag; + } + return offset; +} + static int tcp_copy_straggler_data(struct tcp_zerocopy_receive *zc, struct sk_buff *skb, u32 copylen, u32 *offset, u32 *seq) @@ -1902,6 +1933,8 @@ static int tcp_zerocopy_receive(struct sock *sk, ret = 0; curr_addr = address; while (length + PAGE_SIZE <= zc->length) { + int mappable_offset; + if (zc->recv_skip_hint < PAGE_SIZE) { u32 offset_frag; @@ -1929,15 +1962,11 @@ static int tcp_zerocopy_receive(struct sock *sk, if (!frags || offset_frag) break; } - if (skb_frag_size(frags) != PAGE_SIZE || skb_frag_off(frags)) { - int remaining = zc->recv_skip_hint; - while (remaining && (skb_frag_size(frags) != PAGE_SIZE || - skb_frag_off(frags))) { - remaining -= skb_frag_size(frags); - frags++; - } - zc->recv_skip_hint -= remaining; + mappable_offset = find_next_mappable_frag(frags, + zc->recv_skip_hint); + if (mappable_offset) { + zc->recv_skip_hint = mappable_offset; break; } pages[pg_idx] = skb_frag_page(frags); @@ -2688,6 +2717,8 @@ void tcp_close(struct sock *sk, long timeout) lock_sock(sk); __tcp_close(sk, timeout); release_sock(sk); + if (!sk->sk_net_refcnt) + inet_csk_clear_xmit_timers_sync(sk); sock_put(sk); } EXPORT_SYMBOL(tcp_close); @@ -3713,11 +3744,11 @@ static int do_tcp_getsockopt(struct sock *sk, int level, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case TCP_MAXSEG: val = tp->mss_cache; diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 476f79f15..16ff3962b 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -602,6 +602,13 @@ static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, } DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_SYMBOL(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_SYMBOL(udpv6_encap_needed_key); +#endif + void udp_encap_enable(void) { static_branch_inc(&udp_encap_needed_key); @@ -1118,16 +1125,17 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); - if (err > 0) + if (err > 0) { err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); + connected = 0; + } if (unlikely(err < 0)) { kfree(ipc.opt); return err; } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; @@ -2748,11 +2756,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: val = READ_ONCE(up->corkflag); diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index f4b8e5606..445d8bc30 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -512,6 +512,11 @@ struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb, unsigned int off = skb_gro_offset(skb); int flush = 1; + /* We can do L4 aggregation only if the packet can't land in a tunnel + * otherwise we could corrupt the inner stream. Detecting such packets + * cannot be foolproof and the aggregation might still happen in some + * cases. Such packets should be caught in udp_unexpected_gso later. + */ NAPI_GRO_CB(skb)->is_flist = 0; if (skb->dev->features & NETIF_F_GRO_FRAGLIST) NAPI_GRO_CB(skb)->is_flist = sk ? !udp_sk(sk)->gro_enabled: 1; @@ -668,13 +673,7 @@ INDIRECT_CALLABLE_SCOPE int udp4_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 79787a1f5..8a6f4cdd5 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -698,6 +698,22 @@ errout: return err; } +/* Combine dev_addr_genid and dev_base_seq to detect changes. + */ +static u32 inet6_base_seq(const struct net *net) +{ + u32 res = atomic_read(&net->ipv6.dev_addr_genid) + + net->dev_base_seq; + + /* Must not return 0 (see nl_dump_check_consistent()). + * Chose a value far away from 0. + */ + if (!res) + res = 0x80000000; + return res; +} + + static int inet6_netconf_dump_devconf(struct sk_buff *skb, struct netlink_callback *cb) { @@ -731,8 +747,7 @@ static int inet6_netconf_dump_devconf(struct sk_buff *skb, idx = 0; head = &net->dev_index_head[h]; rcu_read_lock(); - cb->seq = atomic_read(&net->ipv6.dev_addr_genid) ^ - net->dev_base_seq; + cb->seq = inet6_base_seq(net); hlist_for_each_entry_rcu(dev, head, index_hlist) { if (idx < s_idx) goto cont; @@ -2029,9 +2044,10 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add if (ipv6_addr_equal(&ifp->addr, addr)) { if (!dev || ifp->idev->dev == dev || !(ifp->scope&(IFA_LINK|IFA_HOST) || strict)) { - result = ifp; - in6_ifa_hold(ifp); - break; + if (in6_ifa_hold_safe(ifp)) { + result = ifp; + break; + } } } } @@ -5288,7 +5304,7 @@ static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, } rcu_read_lock(); - cb->seq = atomic_read(&tgt_net->ipv6.dev_addr_genid) ^ tgt_net->dev_base_seq; + cb->seq = inet6_base_seq(tgt_net); for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &tgt_net->dev_index_head[h]; @@ -5421,9 +5437,10 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, } addr = extract_addr(tb[IFA_ADDRESS], tb[IFA_LOCAL], &peer); - if (!addr) - return -EINVAL; - + if (!addr) { + err = -EINVAL; + goto errout; + } ifm = nlmsg_data(nlh); if (ifm->ifa_index) dev = dev_get_by_index(tgt_net, ifm->ifa_index); diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index c70c192bc..5e0e2b5ba 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -213,19 +213,26 @@ const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { EXPORT_SYMBOL_GPL(ipv6_stub); /* IPv6 Wildcard Address and Loopback Address defined by RFC2553 */ -const struct in6_addr in6addr_loopback = IN6ADDR_LOOPBACK_INIT; +const struct in6_addr in6addr_loopback __aligned(BITS_PER_LONG/8) + = IN6ADDR_LOOPBACK_INIT; EXPORT_SYMBOL(in6addr_loopback); -const struct in6_addr in6addr_any = IN6ADDR_ANY_INIT; +const struct in6_addr in6addr_any __aligned(BITS_PER_LONG/8) + = IN6ADDR_ANY_INIT; EXPORT_SYMBOL(in6addr_any); -const struct in6_addr in6addr_linklocal_allnodes = IN6ADDR_LINKLOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_linklocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_linklocal_allnodes); -const struct in6_addr in6addr_linklocal_allrouters = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_linklocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_LINKLOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_linklocal_allrouters); -const struct in6_addr in6addr_interfacelocal_allnodes = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; +const struct in6_addr in6addr_interfacelocal_allnodes __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLNODES_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allnodes); -const struct in6_addr in6addr_interfacelocal_allrouters = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_interfacelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_INTERFACELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_interfacelocal_allrouters); -const struct in6_addr in6addr_sitelocal_allrouters = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; +const struct in6_addr in6addr_sitelocal_allrouters __aligned(BITS_PER_LONG/8) + = IN6ADDR_SITELOCAL_ALLROUTERS_INIT; EXPORT_SYMBOL(in6addr_sitelocal_allrouters); static void snmp6_free_dev(struct inet6_dev *idev) diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 424799707..329b3b366 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -197,6 +197,9 @@ lookup_protocol: if (INET_PROTOSW_REUSE & answer_flags) sk->sk_reuse = SK_CAN_REUSE; + if (INET_PROTOSW_ICSK & answer_flags) + inet_init_csk_locks(sk); + inet = inet_sk(sk); inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 3e4c87b29..55cd23b7a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -446,6 +446,11 @@ static size_t fib6_rule_nlmsg_payload(struct fib_rule *rule) + nla_total_size(16); /* src */ } +static void fib6_rule_flush_cache(struct fib_rules_ops *ops) +{ + rt_genid_bump_ipv6(ops->fro_net); +} + static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .family = AF_INET6, .rule_size = sizeof(struct fib6_rule), @@ -458,6 +463,7 @@ static const struct fib_rules_ops __net_initconst fib6_rules_ops_template = { .compare = fib6_rule_compare, .fill = fib6_rule_fill, .nlmsg_payload = fib6_rule_nlmsg_payload, + .flush_cache = fib6_rule_flush_cache, .nlgroup = RTNLGRP_IPV6_RULE, .policy = fib6_rule_policy, .owner = THIS_MODULE, diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 608205c63..b79e571e5 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -643,19 +643,19 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (!w) { /* New dump: * - * 1. hook callback destructor. - */ - cb->args[3] = (long)cb->done; - cb->done = fib6_dump_done; - - /* - * 2. allocate and initialize walker. + * 1. allocate and initialize walker. */ w = kzalloc(sizeof(*w), GFP_ATOMIC); if (!w) return -ENOMEM; w->func = fib6_dump_node; cb->args[2] = (long)w; + + /* 2. hook callback destructor. + */ + cb->args[3] = (long)cb->done; + cb->done = fib6_dump_done; + } arg.skb = skb; @@ -1373,7 +1373,10 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { struct fib6_table *table = rt->fib6_table; - struct fib6_node *fn, *pn = NULL; + struct fib6_node *fn; +#ifdef CONFIG_IPV6_SUBTREES + struct fib6_node *pn = NULL; +#endif int err = -ENOMEM; int allow_create = 1; int replace_required = 0; @@ -1397,9 +1400,9 @@ int fib6_add(struct fib6_node *root, struct fib6_info *rt, goto out; } +#ifdef CONFIG_IPV6_SUBTREES pn = fn; -#ifdef CONFIG_IPV6_SUBTREES if (rt->fib6_src.plen) { struct fib6_node *sn; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 2df103633..13ac0ccdc 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -533,6 +533,9 @@ static int ip6erspan_rcv(struct sk_buff *skb, struct ip6_tnl *tunnel; u8 ver; + if (unlikely(!pskb_may_pull(skb, sizeof(*ershdr)))) + return PACKET_REJECT; + ipv6h = ipv6_hdr(skb); ershdr = (struct erspan_base_hdr *)skb->data; ver = ershdr->ver; diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index edf4a8425..d1f819238 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -829,9 +829,8 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, struct sk_buff *skb), bool log_ecn_err) { - struct pcpu_sw_netstats *tstats; - const struct ipv6hdr *ipv6h = ipv6_hdr(skb); - int err; + const struct ipv6hdr *ipv6h; + int nh, err; if ((!(tpi->flags & TUNNEL_CSUM) && (tunnel->parms.i_flags & TUNNEL_CSUM)) || @@ -863,14 +862,29 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, goto drop; } - ipv6h = ipv6_hdr(skb); skb->protocol = eth_type_trans(skb, tunnel->dev); skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } else { skb->dev = tunnel->dev; } + /* Save offset of outer header relative to skb->head, + * because we are going to reset the network header to the inner header + * and might change skb->head. + */ + nh = skb_network_header(skb) - skb->head; + skb_reset_network_header(skb); + + if (!pskb_inet_may_pull(skb)) { + DEV_STATS_INC(tunnel->dev, rx_length_errors); + DEV_STATS_INC(tunnel->dev, rx_errors); + goto drop; + } + + /* Get the outer header. */ + ipv6h = (struct ipv6hdr *)(skb->head + nh); + memset(skb->cb, 0, sizeof(struct inet6_skb_parm)); __skb_tunnel_rx(skb, tunnel->dev, tunnel->net); @@ -888,11 +902,7 @@ static int __ip6_tnl_rcv(struct ip6_tnl *tunnel, struct sk_buff *skb, } } - tstats = this_cpu_ptr(tunnel->dev->tstats); - u64_stats_update_begin(&tstats->syncp); - tstats->rx_packets++; - tstats->rx_bytes += skb->len; - u64_stats_update_end(&tstats->syncp); + dev_sw_netstats_rx_add(tunnel->dev, skb->len); skb_scrub_packet(skb, !net_eq(tunnel->net, dev_net(tunnel->dev))); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 7b4b457a8..0ac527cd5 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -225,7 +225,7 @@ static int ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (GROUP_FILTER_SIZE(gsf->gf_numsrc) > optlen) goto out_free_gsf; - ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist); + ret = ip6_mc_msfilter(sk, gsf, gsf->gf_slist_flex); out_free_gsf: kfree(gsf); return ret; @@ -234,7 +234,7 @@ out_free_gsf: static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, int optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter *gf32; void *p; int ret; @@ -249,7 +249,7 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, if (!p) return -ENOMEM; - gf32 = p + 4; /* we want ->gf_group and ->gf_slist aligned */ + gf32 = p + 4; /* we want ->gf_group and ->gf_slist_flex aligned */ ret = -EFAULT; if (copy_from_sockptr(gf32, optval, optlen)) goto out_free_p; @@ -261,14 +261,14 @@ static int compat_ipv6_set_mcast_msfilter(struct sock *sk, sockptr_t optval, goto out_free_p; ret = -EINVAL; - if (offsetof(struct compat_group_filter, gf_slist[n]) > optlen) + if (offsetof(struct compat_group_filter, gf_slist_flex[n]) > optlen) goto out_free_p; ret = ip6_mc_msfilter(sk, &(struct group_filter){ .gf_interface = gf32->gf_interface, .gf_group = gf32->gf_group, .gf_fmode = gf32->gf_fmode, - .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist); + .gf_numsrc = gf32->gf_numsrc}, gf32->gf_slist_flex); out_free_p: kfree(p); @@ -1051,7 +1051,7 @@ static int ipv6_getsockopt_sticky(struct sock *sk, struct ipv6_txoptions *opt, static int ipv6_get_msfilter(struct sock *sk, void __user *optval, int __user *optlen, int len) { - const int size0 = offsetof(struct group_filter, gf_slist); + const int size0 = offsetof(struct group_filter, gf_slist_flex); struct group_filter __user *p = optval; struct group_filter gsf; int num; @@ -1065,7 +1065,7 @@ static int ipv6_get_msfilter(struct sock *sk, void __user *optval, return -EADDRNOTAVAIL; num = gsf.gf_numsrc; lock_sock(sk); - err = ip6_mc_msfget(sk, &gsf, p->gf_slist); + err = ip6_mc_msfget(sk, &gsf, p->gf_slist_flex); if (!err) { if (num > gsf.gf_numsrc) num = gsf.gf_numsrc; @@ -1080,7 +1080,7 @@ static int ipv6_get_msfilter(struct sock *sk, void __user *optval, static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, int __user *optlen) { - const int size0 = offsetof(struct compat_group_filter, gf_slist); + const int size0 = offsetof(struct compat_group_filter, gf_slist_flex); struct compat_group_filter __user *p = optval; struct compat_group_filter gf32; struct group_filter gf; @@ -1103,7 +1103,7 @@ static int compat_ipv6_get_msfilter(struct sock *sk, void __user *optval, return -EADDRNOTAVAIL; lock_sock(sk); - err = ip6_mc_msfget(sk, &gf, p->gf_slist); + err = ip6_mc_msfget(sk, &gf, p->gf_slist_flex); release_sock(sk); if (err) return err; diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 99bb11d16..df7cd3d28 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -1127,6 +1127,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1135,6 +1137,8 @@ do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; @@ -1503,6 +1507,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) void *loc_cpu_entry; struct ip6t_entry *iter; + if (len < sizeof(tmp)) + return -EINVAL; if (copy_from_sockptr(&tmp, arg, sizeof(tmp)) != 0) return -EFAULT; @@ -1511,6 +1517,8 @@ compat_do_replace(struct net *net, sockptr_t arg, unsigned int len) return -ENOMEM; if (tmp.num_counters == 0) return -EINVAL; + if ((u64)len < (u64)tmp.size + sizeof(tmp)) + return -EINVAL; tmp.name[sizeof(tmp.name)-1] = 0; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index b23e42efb..2d53c362f 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5235,19 +5235,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { err = __ip6_ins_rt(nh->fib6_info, info, extack); - fib6_info_release(nh->fib6_info); - - if (!err) { - /* save reference to last route successfully inserted */ - rt_last = nh->fib6_info; - - /* save reference to first route for notification */ - if (!rt_notif) - rt_notif = nh->fib6_info; - } - /* nh->fib6_info is used or freed at this point, reset to NULL*/ - nh->fib6_info = NULL; if (err) { if (replace && nhn) NL_SET_ERR_MSG_MOD(extack, @@ -5255,6 +5243,12 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = nh; goto add_errout; } + /* save reference to last route successfully inserted */ + rt_last = nh->fib6_info; + + /* save reference to first route for notification */ + if (!rt_notif) + rt_notif = nh->fib6_info; /* Because each route is added like a single route we remove * these flags after the first nexthop: if there is a collision, @@ -5315,8 +5309,7 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->fib6_info) - fib6_info_release(nh->fib6_info); + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } diff --git a/net/ipv6/seg6.c b/net/ipv6/seg6.c index 2278c0234..a8439fded 100644 --- a/net/ipv6/seg6.c +++ b/net/ipv6/seg6.c @@ -451,22 +451,24 @@ int __init seg6_init(void) { int err; - err = genl_register_family(&seg6_genl_family); + err = register_pernet_subsys(&ip6_segments_ops); if (err) goto out; - err = register_pernet_subsys(&ip6_segments_ops); + err = genl_register_family(&seg6_genl_family); if (err) - goto out_unregister_genl; + goto out_unregister_pernet; #ifdef CONFIG_IPV6_SEG6_LWTUNNEL err = seg6_iptunnel_init(); if (err) - goto out_unregister_pernet; + goto out_unregister_genl; err = seg6_local_init(); - if (err) - goto out_unregister_pernet; + if (err) { + seg6_iptunnel_exit(); + goto out_unregister_genl; + } #endif #ifdef CONFIG_IPV6_SEG6_HMAC @@ -487,11 +489,11 @@ out_unregister_iptun: #endif #endif #ifdef CONFIG_IPV6_SEG6_LWTUNNEL -out_unregister_pernet: - unregister_pernet_subsys(&ip6_segments_ops); -#endif out_unregister_genl: genl_unregister_family(&seg6_genl_family); +#endif +out_unregister_pernet: + unregister_pernet_subsys(&ip6_segments_ops); goto out; } diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 538503720..8c9672e7a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -474,7 +474,7 @@ csum_copy_err: goto try_again; } -DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { static_branch_inc(&udpv6_encap_needed_key); @@ -1453,9 +1453,11 @@ do_udp_sendmsg: ipc6.opt = opt; err = udp_cmsg_send(sk, msg, &ipc6.gso_size); - if (err > 0) + if (err > 0) { err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6); + connected = false; + } if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1467,7 +1469,6 @@ do_udp_sendmsg: } if (!(opt->opt_nflen|opt->opt_flen)) opt = NULL; - connected = false; } if (!opt) { opt = txopt_get(np); diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index ebee748f2..7752e1e92 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -169,13 +169,7 @@ INDIRECT_CALLABLE_SCOPE int udp6_gro_complete(struct sk_buff *skb, int nhoff) skb_shinfo(skb)->gso_type |= (SKB_GSO_FRAGLIST|SKB_GSO_UDP_L4); skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; - if (skb->ip_summed == CHECKSUM_UNNECESSARY) { - if (skb->csum_level < SKB_MAX_CSUM_LEVEL) - skb->csum_level++; - } else { - skb->ip_summed = CHECKSUM_UNNECESSARY; - skb->csum_level = 0; - } + __skb_incr_checksum_unnecessary(skb); return 0; } diff --git a/net/iucv/af_iucv.c b/net/iucv/af_iucv.c index e14368ced..7c73faa53 100644 --- a/net/iucv/af_iucv.c +++ b/net/iucv/af_iucv.c @@ -2310,7 +2310,7 @@ static int __init afiucv_init(void) { int err; - if (MACHINE_IS_VM) { + if (MACHINE_IS_VM && IS_ENABLED(CONFIG_IUCV)) { cpcmd("QUERY USERID", iucv_userid, sizeof(iucv_userid), &err); if (unlikely(err)) { WARN_ON(err); @@ -2318,11 +2318,7 @@ static int __init afiucv_init(void) goto out; } - pr_iucv = try_then_request_module(symbol_get(iucv_if), "iucv"); - if (!pr_iucv) { - printk(KERN_WARNING "iucv_if lookup failed\n"); - memset(&iucv_userid, 0, sizeof(iucv_userid)); - } + pr_iucv = &iucv_if; } else { memset(&iucv_userid, 0, sizeof(iucv_userid)); pr_iucv = NULL; @@ -2356,17 +2352,13 @@ out_sock: out_proto: proto_unregister(&iucv_proto); out: - if (pr_iucv) - symbol_put(iucv_if); return err; } static void __exit afiucv_exit(void) { - if (pr_iucv) { + if (pr_iucv) afiucv_iucv_exit(); - symbol_put(iucv_if); - } unregister_netdevice_notifier(&afiucv_netdev_notifier); dev_remove_pack(&iucv_packet_type); diff --git a/net/iucv/iucv.c b/net/iucv/iucv.c index 6f84978a7..ed0dbdbba 100644 --- a/net/iucv/iucv.c +++ b/net/iucv/iucv.c @@ -156,7 +156,7 @@ static char iucv_error_pathid[16] = "INVALID PATHID"; static LIST_HEAD(iucv_handler_list); /* - * iucv_path_table: an array of iucv_path structures. + * iucv_path_table: array of pointers to iucv_path structures. */ static struct iucv_path **iucv_path_table; static unsigned long iucv_max_pathid; @@ -542,7 +542,7 @@ static int iucv_enable(void) get_online_cpus(); rc = -ENOMEM; - alloc_size = iucv_max_pathid * sizeof(struct iucv_path); + alloc_size = iucv_max_pathid * sizeof(*iucv_path_table); iucv_path_table = kzalloc(alloc_size, GFP_KERNEL); if (!iucv_path_table) goto out; diff --git a/net/kcm/kcmsock.c b/net/kcm/kcmsock.c index 39b3c7fbf..7420b4f19 100644 --- a/net/kcm/kcmsock.c +++ b/net/kcm/kcmsock.c @@ -1275,10 +1275,11 @@ static int kcm_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case KCM_RECV_DISABLE: val = kcm->rx_disabled; diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 9746c624a..eb3d81bcc 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -628,7 +628,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) back_from_confirm: lock_sock(sk); - ulen = len + skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0; + ulen = len + (skb_queue_empty(&sk->sk_write_queue) ? transhdrlen : 0); err = ip6_append_data(sk, ip_generic_getfrag, msg, ulen, transhdrlen, &ipc6, &fl6, (struct rt6_info *)dst, diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 5ecc0f200..b1d89c850 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1357,11 +1357,11 @@ static int pppol2tp_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + err = -ENOTCONN; if (!sk->sk_user_data) goto end; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 01e266982..dae978bad 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -227,6 +227,8 @@ static int llc_ui_release(struct socket *sock) if (llc->dev) dev_put(llc->dev); sock_put(sk); + sock_orphan(sk); + sock->sk = NULL; llc_sk_free(sk); out: return 0; @@ -927,14 +929,15 @@ copy_uaddr: */ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) { + DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); struct sock *sk = sock->sk; struct llc_sock *llc = llc_sk(sk); - DECLARE_SOCKADDR(struct sockaddr_llc *, addr, msg->msg_name); int flags = msg->msg_flags; int noblock = flags & MSG_DONTWAIT; + int rc = -EINVAL, copied = 0, hdrlen, hh_len; struct sk_buff *skb = NULL; + struct net_device *dev; size_t size = 0; - int rc = -EINVAL, copied = 0, hdrlen; dprintk("%s: sending from %02X to %02X\n", __func__, llc->laddr.lsap, llc->daddr.lsap); @@ -954,22 +957,29 @@ static int llc_ui_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) if (rc) goto out; } - hdrlen = llc->dev->hard_header_len + llc_ui_header_len(sk, addr); + dev = llc->dev; + hh_len = LL_RESERVED_SPACE(dev); + hdrlen = llc_ui_header_len(sk, addr); size = hdrlen + len; - if (size > llc->dev->mtu) - size = llc->dev->mtu; + size = min_t(size_t, size, READ_ONCE(dev->mtu)); copied = size - hdrlen; rc = -EINVAL; if (copied < 0) goto out; release_sock(sk); - skb = sock_alloc_send_skb(sk, size, noblock, &rc); + skb = sock_alloc_send_skb(sk, hh_len + size, noblock, &rc); lock_sock(sk); if (!skb) goto out; - skb->dev = llc->dev; + if (sock_flag(sk, SOCK_ZAPPED) || + llc->dev != dev || + hdrlen != llc_ui_header_len(sk, addr) || + hh_len != LL_RESERVED_SPACE(dev) || + size > READ_ONCE(dev->mtu)) + goto out; + skb->dev = dev; skb->protocol = llc_proto_type(addr->sllc_arphrd); - skb_reserve(skb, hdrlen); + skb_reserve(skb, hh_len + hdrlen); rc = memcpy_from_msg(skb_put(skb, copied), msg, copied); if (rc) goto out; diff --git a/net/llc/llc_core.c b/net/llc/llc_core.c index 64d4bef04..4900a27b5 100644 --- a/net/llc/llc_core.c +++ b/net/llc/llc_core.c @@ -135,22 +135,15 @@ static struct packet_type llc_packet_type __read_mostly = { .func = llc_rcv, }; -static struct packet_type llc_tr_packet_type __read_mostly = { - .type = cpu_to_be16(ETH_P_TR_802_2), - .func = llc_rcv, -}; - static int __init llc_init(void) { dev_add_pack(&llc_packet_type); - dev_add_pack(&llc_tr_packet_type); return 0; } static void __exit llc_exit(void) { dev_remove_pack(&llc_packet_type); - dev_remove_pack(&llc_tr_packet_type); } module_init(llc_init); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 45bb6f275..0c3da7771 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1811,15 +1811,14 @@ static int ieee80211_change_station(struct wiphy *wiphy, } if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN && - sta->sdata->u.vlan.sta) { - ieee80211_clear_fast_rx(sta); + sta->sdata->u.vlan.sta) RCU_INIT_POINTER(sta->sdata->u.vlan.sta, NULL); - } if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) ieee80211_vif_dec_num_mcast(sta->sdata); sta->sdata = vlansdata; + ieee80211_check_fast_rx(sta); ieee80211_check_fast_xmit(sta); if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 2e8436099..44bd03c6b 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -700,6 +700,8 @@ static int sta_info_insert_finish(struct sta_info *sta) __acquires(RCU) if (ieee80211_vif_is_mesh(&sdata->vif)) mesh_accept_plinks_update(sdata); + ieee80211_check_fast_xmit(sta); + return 0; out_remove: sta_info_hash_del(local, sta); diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 788b6a3c1..0d6d12fc3 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -2959,7 +2959,7 @@ void ieee80211_check_fast_xmit(struct sta_info *sta) sdata->vif.type == NL80211_IFTYPE_STATION) goto out; - if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (!test_sta_flag(sta, WLAN_STA_AUTHORIZED) || !sta->uploaded) goto out; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -3721,6 +3721,7 @@ begin: goto begin; skb = __skb_dequeue(&tx.skbs); + info = IEEE80211_SKB_CB(skb); if (!skb_queue_empty(&tx.skbs)) { spin_lock_bh(&fq->lock); @@ -3765,7 +3766,7 @@ begin: } encap_out: - IEEE80211_SKB_CB(skb)->control.vif = vif; + info->control.vif = vif; if (vif && wiphy_ext_feature_isset(local->hw.wiphy, NL80211_EXT_FEATURE_AQL)) { diff --git a/net/mac802154/llsec.c b/net/mac802154/llsec.c index 55550ead2..a4cc9d077 100644 --- a/net/mac802154/llsec.c +++ b/net/mac802154/llsec.c @@ -265,19 +265,27 @@ fail: return -ENOMEM; } +static void mac802154_llsec_key_del_rcu(struct rcu_head *rcu) +{ + struct ieee802154_llsec_key_entry *pos; + struct mac802154_llsec_key *mkey; + + pos = container_of(rcu, struct ieee802154_llsec_key_entry, rcu); + mkey = container_of(pos->key, struct mac802154_llsec_key, key); + + llsec_key_put(mkey); + kfree_sensitive(pos); +} + int mac802154_llsec_key_del(struct mac802154_llsec *sec, const struct ieee802154_llsec_key_id *key) { struct ieee802154_llsec_key_entry *pos; list_for_each_entry(pos, &sec->table.keys, list) { - struct mac802154_llsec_key *mkey; - - mkey = container_of(pos->key, struct mac802154_llsec_key, key); - if (llsec_key_id_equal(&pos->id, key)) { list_del_rcu(&pos->list); - llsec_key_put(mkey); + call_rcu(&pos->rcu, mac802154_llsec_key_del_rcu); return 0; } } diff --git a/net/mptcp/diag.c b/net/mptcp/diag.c index a53658674..d7ca71c59 100644 --- a/net/mptcp/diag.c +++ b/net/mptcp/diag.c @@ -13,17 +13,22 @@ #include <uapi/linux/mptcp.h> #include "protocol.h" -static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) +static int subflow_get_info(struct sock *sk, struct sk_buff *skb) { struct mptcp_subflow_context *sf; struct nlattr *start; u32 flags = 0; + bool slow; int err; + if (inet_sk_state_load(sk) == TCP_LISTEN) + return 0; + start = nla_nest_start_noflag(skb, INET_ULP_INFO_MPTCP); if (!start) return -EMSGSIZE; + slow = lock_sock_fast(sk); rcu_read_lock(); sf = rcu_dereference(inet_csk(sk)->icsk_ulp_data); if (!sf) { @@ -69,11 +74,13 @@ static int subflow_get_info(const struct sock *sk, struct sk_buff *skb) } rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_end(skb, start); return 0; nla_failure: rcu_read_unlock(); + unlock_sock_fast(sk, slow); nla_nest_cancel(skb, start); return err; } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index 72d944e6a..6be7e7592 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2052,8 +2052,50 @@ static struct ipv6_pinfo *mptcp_inet6_sk(const struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } + +static void mptcp_copy_ip6_options(struct sock *newsk, const struct sock *sk) +{ + const struct ipv6_pinfo *np = inet6_sk(sk); + struct ipv6_txoptions *opt; + struct ipv6_pinfo *newnp; + + newnp = inet6_sk(newsk); + + rcu_read_lock(); + opt = rcu_dereference(np->opt); + if (opt) { + opt = ipv6_dup_options(newsk, opt); + if (!opt) + net_warn_ratelimited("%s: Failed to copy ip6 options\n", __func__); + } + RCU_INIT_POINTER(newnp->opt, opt); + rcu_read_unlock(); +} #endif +static void mptcp_copy_ip_options(struct sock *newsk, const struct sock *sk) +{ + struct ip_options_rcu *inet_opt, *newopt = NULL; + const struct inet_sock *inet = inet_sk(sk); + struct inet_sock *newinet; + + newinet = inet_sk(newsk); + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + newopt = sock_kmalloc(newsk, sizeof(*inet_opt) + + inet_opt->opt.optlen, GFP_ATOMIC); + if (newopt) + memcpy(newopt, inet_opt, sizeof(*inet_opt) + + inet_opt->opt.optlen); + else + net_warn_ratelimited("%s: Failed to copy ip options\n", __func__); + } + RCU_INIT_POINTER(newinet->inet_opt, newopt); + rcu_read_unlock(); +} + struct sock *mptcp_sk_clone(const struct sock *sk, const struct mptcp_options_received *mp_opt, struct request_sock *req) @@ -2073,6 +2115,13 @@ struct sock *mptcp_sk_clone(const struct sock *sk, __mptcp_init_sock(nsk); +#if IS_ENABLED(CONFIG_MPTCP_IPV6) + if (nsk->sk_family == AF_INET6) + mptcp_copy_ip6_options(nsk, sk); + else +#endif + mptcp_copy_ip_options(nsk, sk); + msk = mptcp_sk(nsk); msk->local_key = subflow_req->local_key; msk->token = subflow_req->token; @@ -2169,9 +2218,6 @@ static struct sock *mptcp_accept(struct sock *sk, int flags, int *err, __MPTCP_INC_STATS(sock_net(sk), MPTCP_MIB_MPCAPABLEPASSIVEACK); local_bh_enable(); - } else { - MPTCP_INC_STATS(sock_net(sk), - MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); } out: diff --git a/net/mptcp/subflow.c b/net/mptcp/subflow.c index 607519246..276fe9f44 100644 --- a/net/mptcp/subflow.c +++ b/net/mptcp/subflow.c @@ -595,6 +595,9 @@ create_child: if (fallback_is_fatal) goto dispose_child; + if (fallback) + SUBFLOW_REQ_INC_STATS(req, MPTCP_MIB_MPCAPABLEPASSIVEFALLBACK); + subflow_drop_ctx(child); goto out; } diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 26ab0e961..9523104a9 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -28,6 +28,7 @@ #define mtype_del IPSET_TOKEN(MTYPE, _del) #define mtype_list IPSET_TOKEN(MTYPE, _list) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype MTYPE #define get_ext(set, map, id) ((map)->extensions + ((set)->dsize * (id))) @@ -57,9 +58,6 @@ mtype_destroy(struct ip_set *set) { struct mtype *map = set->data; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); ip_set_free(map->members); @@ -288,6 +286,15 @@ mtype_gc(struct timer_list *t) add_timer(&map->gc); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct mtype *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant mtype = { .kadt = mtype_kadt, .uadt = mtype_uadt, @@ -301,6 +308,7 @@ static const struct ip_set_type_variant mtype = { .head = mtype_head, .list = mtype_list, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, }; #endif /* __IP_SET_BITMAP_IP_GEN_H */ diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 24f81826e..cc04c4d79 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1158,6 +1158,7 @@ static int ip_set_create(struct net *net, struct sock *ctnl, return ret; cleanup: + set->variant->cancel_gc(set); set->variant->destroy(set); put_out: module_put(set->type->me); @@ -1186,6 +1187,14 @@ ip_set_destroy_set(struct ip_set *set) kfree(set); } +static void +ip_set_destroy_set_rcu(struct rcu_head *head) +{ + struct ip_set *set = container_of(head, struct ip_set, rcu); + + ip_set_destroy_set(set); +} + static int ip_set_destroy(struct net *net, struct sock *ctnl, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const attr[], @@ -1199,8 +1208,6 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, if (unlikely(protocol_min_failed(attr))) return -IPSET_ERR_PROTOCOL; - /* Must wait for flush to be really finished in list:set */ - rcu_barrier(); /* Commands are serialized and references are * protected by the ip_set_ref_lock. @@ -1212,8 +1219,10 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, * counter, so if it's already zero, we can proceed * without holding the lock. */ - read_lock_bh(&ip_set_ref_lock); if (!attr[IPSET_ATTR_SETNAME]) { + /* Must wait for flush to be really finished in list:set */ + rcu_barrier(); + read_lock_bh(&ip_set_ref_lock); for (i = 0; i < inst->ip_set_max; i++) { s = ip_set(inst, i); if (s && (s->ref || s->ref_netlink)) { @@ -1227,12 +1236,17 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, s = ip_set(inst, i); if (s) { ip_set(inst, i) = NULL; + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); ip_set_destroy_set(s); } } /* Modified by ip_set_destroy() only, which is serialized */ inst->is_destroyed = false; } else { + u16 features = 0; + + read_lock_bh(&ip_set_ref_lock); s = find_set_and_id(inst, nla_data(attr[IPSET_ATTR_SETNAME]), &i); if (!s) { @@ -1242,10 +1256,16 @@ static int ip_set_destroy(struct net *net, struct sock *ctnl, ret = -IPSET_ERR_BUSY; goto out; } + features = s->type->features; ip_set(inst, i) = NULL; read_unlock_bh(&ip_set_ref_lock); - - ip_set_destroy_set(s); + if (features & IPSET_TYPE_NAME) { + /* Must wait for flush to be really finished */ + rcu_barrier(); + } + /* Must cancel garbage collectors */ + s->variant->cancel_gc(s); + call_rcu(&s->rcu, ip_set_destroy_set_rcu); } return 0; out: @@ -1404,9 +1424,6 @@ static int ip_set_swap(struct net *net, struct sock *ctnl, struct sk_buff *skb, ip_set(inst, to_id) = from; write_unlock_bh(&ip_set_ref_lock); - /* Make sure all readers of the old set pointers are completed. */ - synchronize_rcu(); - return 0; } @@ -2397,6 +2414,7 @@ ip_set_net_exit(struct net *net) set = ip_set(inst, i); if (set) { ip_set(inst, i) = NULL; + set->variant->cancel_gc(set); ip_set_destroy_set(set); } } @@ -2444,8 +2462,11 @@ ip_set_fini(void) { nf_unregister_sockopt(&so_set); nfnetlink_subsys_unregister(&ip_set_netlink_subsys); - unregister_pernet_subsys(&ip_set_net_ops); + + /* Wait for call_rcu() in destroy */ + rcu_barrier(); + pr_debug("these are the famous last words\n"); } diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index b0670388d..093ec5214 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -235,6 +235,7 @@ htable_size(u8 hbits) #undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init +#undef mtype_cancel_gc #undef mtype_variant #undef mtype_data_match @@ -279,6 +280,7 @@ htable_size(u8 hbits) #define mtype_gc_do IPSET_TOKEN(MTYPE, _gc_do) #define mtype_gc IPSET_TOKEN(MTYPE, _gc) #define mtype_gc_init IPSET_TOKEN(MTYPE, _gc_init) +#define mtype_cancel_gc IPSET_TOKEN(MTYPE, _cancel_gc) #define mtype_variant IPSET_TOKEN(MTYPE, _variant) #define mtype_data_match IPSET_TOKEN(MTYPE, _data_match) @@ -444,7 +446,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) u32 i; for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference(hbucket(t, i)); + n = (__force struct hbucket *)hbucket(t, i); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -464,10 +466,7 @@ mtype_destroy(struct ip_set *set) struct htype *h = set->data; struct list_head *l, *lt; - if (SET_WITH_TIMEOUT(set)) - cancel_delayed_work_sync(&h->gc.dwork); - - mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + mtype_ahash_destroy(set, (__force struct htable *)h->table, true); list_for_each_safe(l, lt, &h->ad) { list_del(l); kfree(l); @@ -613,6 +612,15 @@ mtype_gc_init(struct htable_gc *gc) queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static void +mtype_cancel_gc(struct ip_set *set) +{ + struct htype *h = set->data; + + if (SET_WITH_TIMEOUT(set)) + cancel_delayed_work_sync(&h->gc.dwork); +} + static int mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, struct ip_set_ext *mext, u32 flags); @@ -1433,6 +1441,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .cancel_gc = mtype_cancel_gc, .region_lock = true, }; diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 5a67f7966..6bc701998 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -426,9 +426,6 @@ list_set_destroy(struct ip_set *set) struct list_set *map = set->data; struct set_elem *e, *n; - if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&map->gc); - list_for_each_entry_safe(e, n, &map->members, list) { list_del(&e->list); ip_set_put_byindex(map->net, e->id); @@ -545,6 +542,15 @@ list_set_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } +static void +list_set_cancel_gc(struct ip_set *set) +{ + struct list_set *map = set->data; + + if (SET_WITH_TIMEOUT(set)) + del_timer_sync(&map->gc); +} + static const struct ip_set_type_variant set_variant = { .kadt = list_set_kadt, .uadt = list_set_uadt, @@ -558,6 +564,7 @@ static const struct ip_set_type_variant set_variant = { .head = list_set_head, .list = list_set_list, .same_set = list_set_same_set, + .cancel_gc = list_set_cancel_gc, }; static void diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index a0921adc3..1e689c714 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -126,7 +126,8 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, if (sctph->source != cp->vport || payload_csum || skb->ip_summed == CHECKSUM_PARTIAL) { sctph->source = cp->vport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else { skb->ip_summed = CHECKSUM_UNNECESSARY; } @@ -174,7 +175,8 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, (skb->ip_summed == CHECKSUM_PARTIAL && !(skb_dst(skb)->dev->features & NETIF_F_SCTP_CRC))) { sctph->dest = cp->dport; - sctp_nat_csum(skb, sctph, sctphoff); + if (!skb_is_gso(skb) || !skb_is_gso_sctp(skb)) + sctp_nat_csum(skb, sctph, sctphoff); } else if (skb->ip_summed != CHECKSUM_PARTIAL) { skb->ip_summed = CHECKSUM_UNNECESSARY; } diff --git a/net/netfilter/nf_conntrack_h323_asn1.c b/net/netfilter/nf_conntrack_h323_asn1.c index e697a824b..540d97715 100644 --- a/net/netfilter/nf_conntrack_h323_asn1.c +++ b/net/netfilter/nf_conntrack_h323_asn1.c @@ -533,6 +533,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, /* Get fields bitmap */ if (nf_h323_error_boundary(bs, 0, f->sz)) return H323_ERROR_BOUND; + if (f->sz > 32) + return H323_ERROR_RANGE; bmp = get_bitmap(bs, f->sz); if (base) *(unsigned int *)base = bmp; @@ -589,6 +591,8 @@ static int decode_seq(struct bitstr *bs, const struct field_t *f, bmp2_len = get_bits(bs, 7) + 1; if (nf_h323_error_boundary(bs, 0, bmp2_len)) return H323_ERROR_BOUND; + if (bmp2_len > 32) + return H323_ERROR_RANGE; bmp2 = get_bitmap(bs, bmp2_len); bmp |= bmp2 >> f->sz; if (base) diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index e7545bcca..6b2a215b2 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -299,7 +299,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, pr_debug("Setting vtag %x for secondary conntrack\n", sh->vtag); ct->proto.sctp.vtag[IP_CT_DIR_ORIGINAL] = sh->vtag; - } else { + } else if (sch->type == SCTP_CID_SHUTDOWN_ACK) { /* If it is a shutdown ack OOTB packet, we expect a return shutdown complete, otherwise an ABORT Sec 8.4 (5) and (8) */ pr_debug("Setting vtag %x for new conn OOTB\n", diff --git a/net/netfilter/nf_log.c b/net/netfilter/nf_log.c index 6cb9f9474..28c6cb5cf 100644 --- a/net/netfilter/nf_log.c +++ b/net/netfilter/nf_log.c @@ -203,11 +203,12 @@ void nf_logger_put(int pf, enum nf_log_type type) return; } - BUG_ON(loggers[pf][type] == NULL); - rcu_read_lock(); logger = rcu_dereference(loggers[pf][type]); - module_put(logger->me); + if (!logger) + WARN_ON_ONCE(1); + else + module_put(logger->me); rcu_read_unlock(); } EXPORT_SYMBOL_GPL(nf_logger_put); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index fca8f9a36..858d09b54 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -25,6 +25,7 @@ #include <net/sock.h> #define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) +#define NFT_SET_MAX_ANONLEN 16 unsigned int nf_tables_net_id __read_mostly; @@ -1083,6 +1084,24 @@ static void nf_tables_table_disable(struct net *net, struct nft_table *table) #define __NFT_TABLE_F_UPDATE (__NFT_TABLE_F_WAS_DORMANT | \ __NFT_TABLE_F_WAS_AWAKEN) +static bool nft_table_pending_update(const struct nft_ctx *ctx) +{ + struct nftables_pernet *nft_net = net_generic(ctx->net, nf_tables_net_id); + struct nft_trans *trans; + + if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + return true; + + list_for_each_entry(trans, &nft_net->commit_list, list) { + if (trans->ctx.table == ctx->table && + trans->msg_type == NFT_MSG_DELCHAIN && + nft_is_base_chain(trans->ctx.chain)) + return true; + } + + return false; +} + static int nf_tables_updtable(struct nft_ctx *ctx) { struct nft_trans *trans; @@ -1096,11 +1115,11 @@ static int nf_tables_updtable(struct nft_ctx *ctx) if (flags & ~NFT_TABLE_F_DORMANT) return -EINVAL; - if (flags == ctx->table->flags) + if (flags == (ctx->table->flags & NFT_TABLE_F_MASK)) return 0; /* No dormant off/on/off/on games in single transaction */ - if (ctx->table->flags & __NFT_TABLE_F_UPDATE) + if (nft_table_pending_update(ctx)) return -EINVAL; trans = nft_trans_alloc(ctx, NFT_MSG_NEWTABLE, @@ -1131,6 +1150,7 @@ static int nf_tables_updtable(struct nft_ctx *ctx) return 0; err_register_hooks: + ctx->table->flags |= NFT_TABLE_F_DORMANT; nft_trans_destroy(trans); return ret; } @@ -2223,6 +2243,9 @@ static int nf_tables_addchain(struct nft_ctx *ctx, u8 family, u8 genmask, struct nft_stats __percpu *stats = NULL; struct nft_chain_hook hook; + if (table->flags & __NFT_TABLE_F_UPDATE) + return -EINVAL; + if (flags & NFT_CHAIN_BINDING) return -EOPNOTSUPP; @@ -2716,7 +2739,7 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, { const struct nft_expr_type *type, *candidate = NULL; - list_for_each_entry(type, &nf_tables_expressions, list) { + list_for_each_entry_rcu(type, &nf_tables_expressions, list) { if (!nla_strcmp(nla, type->name)) { if (!type->family && !candidate) candidate = type; @@ -2748,9 +2771,13 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, if (nla == NULL) return ERR_PTR(-EINVAL); + rcu_read_lock(); type = __nft_expr_type_get(family, nla); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -3930,6 +3957,9 @@ static int nf_tables_set_alloc_name(struct nft_ctx *ctx, struct nft_set *set, if (p[1] != 'd' || strchr(p + 2, '%')) return -EINVAL; + if (strnlen(name, NFT_SET_MAX_ANONLEN) >= NFT_SET_MAX_ANONLEN) + return -EINVAL; + inuse = (unsigned long *)get_zeroed_page(GFP_KERNEL); if (inuse == NULL) return -ENOMEM; @@ -4405,6 +4435,12 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if ((flags & (NFT_SET_EVAL | NFT_SET_OBJECT)) == (NFT_SET_EVAL | NFT_SET_OBJECT)) return -EOPNOTSUPP; + if ((flags & (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT | NFT_SET_EVAL)) == + (NFT_SET_ANONYMOUS | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; + if ((flags & (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) == + (NFT_SET_CONSTANT | NFT_SET_TIMEOUT)) + return -EOPNOTSUPP; } dtype = 0; @@ -4446,6 +4482,9 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout); if (err) return err; @@ -4454,6 +4493,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_GC_INTERVAL] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; + + if (flags & NFT_SET_ANONYMOUS) + return -EOPNOTSUPP; + gc_int = ntohl(nla_get_be32(nla[NFTA_SET_GC_INTERVAL])); } @@ -4749,6 +4792,7 @@ static void nf_tables_unbind_set(const struct nft_ctx *ctx, struct nft_set *set, if (list_empty(&set->bindings) && nft_set_is_anonymous(set)) { list_del_rcu(&set->list); + set->dead = 1; if (event) nf_tables_set_notify(ctx, set, NFT_MSG_DELSET, GFP_KERNEL); @@ -6857,11 +6901,12 @@ static int nft_flowtable_parse_hook(const struct nft_ctx *ctx, return err; } +/* call under rcu_read_lock */ static const struct nf_flowtable_type *__nft_flowtable_type_get(u8 family) { const struct nf_flowtable_type *type; - list_for_each_entry(type, &nf_tables_flowtables, list) { + list_for_each_entry_rcu(type, &nf_tables_flowtables, list) { if (family == type->family) return type; } @@ -6873,9 +6918,13 @@ nft_flowtable_type_get(struct net *net, u8 family) { const struct nf_flowtable_type *type; + rcu_read_lock(); type = __nft_flowtable_type_get(family); - if (type != NULL && try_module_get(type->owner)) + if (type != NULL && try_module_get(type->owner)) { + rcu_read_unlock(); return type; + } + rcu_read_unlock(); lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES @@ -8773,10 +8822,11 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) struct nft_trans *trans, *next; LIST_HEAD(set_update_list); struct nft_trans_elem *te; + int err = 0; if (action == NFNL_ABORT_VALIDATE && nf_tables_validate(net) < 0) - return -EAGAIN; + err = -EAGAIN; list_for_each_entry_safe_reverse(trans, next, &nft_net->commit_list, list) { @@ -8936,12 +8986,7 @@ static int __nf_tables_abort(struct net *net, enum nfnl_abort_action action) nf_tables_abort_release(trans); } - if (action == NFNL_ABORT_AUTOLOAD) - nf_tables_module_autoload(net); - else - nf_tables_module_autoload_cleanup(net); - - return 0; + return err; } static int nf_tables_abort(struct net *net, struct sk_buff *skb, @@ -8955,6 +9000,16 @@ static int nf_tables_abort(struct net *net, struct sk_buff *skb, ret = __nf_tables_abort(net, action); nft_gc_seq_end(nft_net, gc_seq); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + /* module autoload needs to happen after GC sequence update because it + * temporarily releases and grabs mutex again. + */ + if (action == NFNL_ABORT_AUTOLOAD) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + mutex_unlock(&nft_net->commit_mutex); return ret; @@ -9336,16 +9391,10 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.code = ntohl(nla_get_be32(tb[NFTA_VERDICT_CODE])); switch (data->verdict.code) { - default: - switch (data->verdict.code & NF_VERDICT_MASK) { - case NF_ACCEPT: - case NF_DROP: - case NF_QUEUE: - break; - default: - return -EINVAL; - } - fallthrough; + case NF_ACCEPT: + case NF_DROP: + case NF_QUEUE: + break; case NFT_CONTINUE: case NFT_BREAK: case NFT_RETURN: @@ -9380,6 +9429,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, data->verdict.chain = chain; break; + default: + return -EINVAL; } desc->len = sizeof(data->verdict); @@ -9693,8 +9744,11 @@ static void __net_exit nf_tables_exit_net(struct net *net) gc_seq = nft_gc_seq_begin(nft_net); - if (!list_empty(&nft_net->commit_list)) - __nf_tables_abort(net, NFNL_ABORT_NONE); + WARN_ON_ONCE(!list_empty(&nft_net->commit_list)); + + if (!list_empty(&nft_net->module_list)) + nf_tables_module_autoload_cleanup(net); + __nft_release_tables(net); nft_gc_seq_end(nft_net, gc_seq); @@ -9778,6 +9832,7 @@ static void __exit nf_tables_module_exit(void) unregister_netdevice_notifier(&nf_tables_flowtable_notifier); nft_chain_filter_fini(); nft_chain_route_fini(); + nf_tables_trans_destroy_flush_work(); unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_gc_work); cancel_work_sync(&trans_destroy_work); diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 7b0b8fecb..9d250bd60 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -38,20 +38,21 @@ void nft_byteorder_eval(const struct nft_expr *expr, switch (priv->size) { case 8: { + u64 *dst64 = (void *)dst; u64 src64; switch (priv->op) { case NFT_BYTEORDER_NTOH: for (i = 0; i < priv->len / 8; i++) { src64 = nft_reg_load64(&src[i]); - nft_reg_store64(&dst[i], be64_to_cpu(src64)); + nft_reg_store64(&dst64[i], be64_to_cpu(src64)); } break; case NFT_BYTEORDER_HTON: for (i = 0; i < priv->len / 8; i++) { src64 = (__force __u64) cpu_to_be64(nft_reg_load64(&src[i])); - nft_reg_store64(&dst[i], src64); + nft_reg_store64(&dst64[i], src64); } break; } diff --git a/net/netfilter/nft_chain_filter.c b/net/netfilter/nft_chain_filter.c index 7a9aa57b1..aad676402 100644 --- a/net/netfilter/nft_chain_filter.c +++ b/net/netfilter/nft_chain_filter.c @@ -339,7 +339,9 @@ static void nft_netdev_event(unsigned long event, struct net_device *dev, return; if (n > 1) { - nf_unregister_net_hook(ctx->net, &found->ops); + if (!(ctx->chain->table->flags & NFT_TABLE_F_DORMANT)) + nf_unregister_net_hook(ctx->net, &found->ops); + list_del_rcu(&found->list); kfree_rcu(found, rcu); return; @@ -358,9 +360,10 @@ static int nf_tables_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) { struct net_device *dev = netdev_notifier_info_to_dev(ptr); + struct nft_base_chain *basechain; struct nftables_pernet *nft_net; - struct nft_table *table; struct nft_chain *chain, *nr; + struct nft_table *table; struct nft_ctx ctx = { .net = dev_net(dev), }; @@ -372,7 +375,8 @@ static int nf_tables_netdev_event(struct notifier_block *this, nft_net = net_generic(ctx.net, nf_tables_net_id); mutex_lock(&nft_net->commit_mutex); list_for_each_entry(table, &nft_net->tables, list) { - if (table->family != NFPROTO_NETDEV) + if (table->family != NFPROTO_NETDEV && + table->family != NFPROTO_INET) continue; ctx.family = table->family; @@ -381,6 +385,11 @@ static int nf_tables_netdev_event(struct notifier_block *this, if (!nft_is_base_chain(chain)) continue; + basechain = nft_base_chain(chain); + if (table->family == NFPROTO_INET && + basechain->ops.hooknum != NF_INET_INGRESS) + continue; + ctx.chain = chain; nft_netdev_event(event, dev, &ctx); } diff --git a/net/netfilter/nft_compat.c b/net/netfilter/nft_compat.c index b8dbd20a6..3e0a6e793 100644 --- a/net/netfilter/nft_compat.c +++ b/net/netfilter/nft_compat.c @@ -192,6 +192,7 @@ static const struct nla_policy nft_rule_compat_policy[NFTA_RULE_COMPAT_MAX + 1] static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) { struct nlattr *tb[NFTA_RULE_COMPAT_MAX+1]; + u32 l4proto; u32 flags; int err; @@ -204,12 +205,18 @@ static int nft_parse_compat(const struct nlattr *attr, u16 *proto, bool *inv) return -EINVAL; flags = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_FLAGS])); - if (flags & ~NFT_RULE_COMPAT_F_MASK) + if (flags & NFT_RULE_COMPAT_F_UNUSED || + flags & ~NFT_RULE_COMPAT_F_MASK) return -EINVAL; if (flags & NFT_RULE_COMPAT_F_INV) *inv = true; - *proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + l4proto = ntohl(nla_get_be32(tb[NFTA_RULE_COMPAT_PROTO])); + if (l4proto > U16_MAX) + return -EINVAL; + + *proto = l4proto; + return 0; } @@ -327,6 +334,22 @@ static int nft_target_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); @@ -569,6 +592,22 @@ static int nft_match_validate(const struct nft_ctx *ctx, unsigned int hook_mask = 0; int ret; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET && + ctx->family != NFPROTO_BRIDGE && + ctx->family != NFPROTO_ARP) + return -EOPNOTSUPP; + + ret = nft_chain_validate_hooks(ctx->chain, + (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_IN) | + (1 << NF_INET_FORWARD) | + (1 << NF_INET_LOCAL_OUT) | + (1 << NF_INET_POST_ROUTING)); + if (ret) + return ret; + if (nft_is_base_chain(ctx->chain)) { const struct nft_base_chain *basechain = nft_base_chain(ctx->chain); diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 14093d86e..2a8dfa68f 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -482,6 +482,9 @@ static int nft_ct_get_init(const struct nft_ctx *ctx, break; #endif case NFT_CT_ID: + if (tb[NFTA_CT_DIRECTION]) + return -EINVAL; + len = sizeof(u32); break; default: @@ -1182,7 +1185,30 @@ static int nft_ct_expect_obj_init(const struct nft_ctx *ctx, if (tb[NFTA_CT_EXPECT_L3PROTO]) priv->l3num = ntohs(nla_get_be16(tb[NFTA_CT_EXPECT_L3PROTO])); + switch (priv->l3num) { + case NFPROTO_IPV4: + case NFPROTO_IPV6: + if (priv->l3num == ctx->family || ctx->family == NFPROTO_INET) + break; + + return -EINVAL; + case NFPROTO_INET: /* tuple.src.l3num supports NFPROTO_IPV4/6 only */ + default: + return -EAFNOSUPPORT; + } + priv->l4proto = nla_get_u8(tb[NFTA_CT_EXPECT_L4PROTO]); + switch (priv->l4proto) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_UDPLITE: + case IPPROTO_DCCP: + case IPPROTO_SCTP: + break; + default: + return -EOPNOTSUPP; + } + priv->dport = nla_get_be16(tb[NFTA_CT_EXPECT_DPORT]); priv->timeout = nla_get_u32(tb[NFTA_CT_EXPECT_TIMEOUT]); priv->size = nla_get_u8(tb[NFTA_CT_EXPECT_SIZE]); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index a44340dd3..c2a5d05f5 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -150,6 +150,11 @@ static int nft_flow_offload_validate(const struct nft_ctx *ctx, { unsigned int hook_mask = (1 << NF_INET_FORWARD); + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, hook_mask); } diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 44d9b38e5..cb5bb0e21 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -63,7 +63,7 @@ nft_meta_get_eval_time(enum nft_meta_keys key, { switch (key) { case NFT_META_TIME_NS: - nft_reg_store64(dest, ktime_get_real_ns()); + nft_reg_store64((u64 *)dest, ktime_get_real_ns()); break; case NFT_META_TIME_DAY: nft_reg_store8(dest, nft_meta_weekday()); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index cd4eb4996..2e1ee7d9d 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -142,6 +142,11 @@ static int nft_nat_validate(const struct nft_ctx *ctx, struct nft_nat *priv = nft_expr_priv(expr); int err; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + err = nft_chain_validate_dependency(ctx->chain, NFT_CHAIN_T_NAT); if (err < 0) return err; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index bcd01a63e..f4a96164a 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -166,6 +166,11 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp const struct nft_rt *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->key) { case NFT_RT_NEXTHOP4: case NFT_RT_NEXTHOP6: diff --git a/net/netfilter/nft_set_pipapo.c b/net/netfilter/nft_set_pipapo.c index bc30bd121..5a8521abd 100644 --- a/net/netfilter/nft_set_pipapo.c +++ b/net/netfilter/nft_set_pipapo.c @@ -342,9 +342,6 @@ #include "nft_set_pipapo_avx2.h" #include "nft_set_pipapo.h" -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_scratch_index); - /** * pipapo_refill() - For each set bit, set bits from selected mapping table item * @map: Bitmap to be scanned for set bits @@ -412,6 +409,7 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); + struct nft_pipapo_scratch *scratch; unsigned long *res_map, *fill_map; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; @@ -422,15 +420,17 @@ bool nft_pipapo_lookup(const struct net *net, const struct nft_set *set, local_bh_disable(); - map_index = raw_cpu_read(nft_pipapo_scratch_index); - m = rcu_dereference(priv->match); if (unlikely(!m || !*raw_cpu_ptr(m->scratch))) goto out; - res_map = *raw_cpu_ptr(m->scratch) + (map_index ? m->bsize_max : 0); - fill_map = *raw_cpu_ptr(m->scratch) + (map_index ? 0 : m->bsize_max); + scratch = *raw_cpu_ptr(m->scratch); + + map_index = scratch->map_index; + + res_map = scratch->map + (map_index ? m->bsize_max : 0); + fill_map = scratch->map + (map_index ? 0 : m->bsize_max); memset(res_map, 0xff, m->bsize_max * sizeof(*res_map)); @@ -460,7 +460,7 @@ next_match: b = pipapo_refill(res_map, f->bsize, f->rules, fill_map, f->mt, last); if (b < 0) { - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return false; @@ -477,7 +477,7 @@ next_match: * current inactive bitmap is clean and can be reused as * *next* bitmap (not initial) for the next packet. */ - raw_cpu_write(nft_pipapo_scratch_index, map_index); + scratch->map_index = map_index; local_bh_enable(); return true; @@ -1102,6 +1102,25 @@ static void pipapo_map(struct nft_pipapo_match *m, } /** + * pipapo_free_scratch() - Free per-CPU map at original (not aligned) address + * @m: Matching data + * @cpu: CPU number + */ +static void pipapo_free_scratch(const struct nft_pipapo_match *m, unsigned int cpu) +{ + struct nft_pipapo_scratch *s; + void *mem; + + s = *per_cpu_ptr(m->scratch, cpu); + if (!s) + return; + + mem = s; + mem -= s->align_off; + kfree(mem); +} + +/** * pipapo_realloc_scratch() - Reallocate scratch maps for partial match results * @clone: Copy of matching data with pending insertions and deletions * @bsize_max: Maximum bucket size, scratch maps cover two buckets @@ -1114,12 +1133,13 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, int i; for_each_possible_cpu(i) { - unsigned long *scratch; + struct nft_pipapo_scratch *scratch; #ifdef NFT_PIPAPO_ALIGN - unsigned long *scratch_aligned; + void *scratch_aligned; + u32 align_off; #endif - - scratch = kzalloc_node(bsize_max * sizeof(*scratch) * 2 + + scratch = kzalloc_node(struct_size(scratch, map, + bsize_max * 2) + NFT_PIPAPO_ALIGN_HEADROOM, GFP_KERNEL, cpu_to_node(i)); if (!scratch) { @@ -1133,14 +1153,25 @@ static int pipapo_realloc_scratch(struct nft_pipapo_match *clone, return -ENOMEM; } - kfree(*per_cpu_ptr(clone->scratch, i)); - - *per_cpu_ptr(clone->scratch, i) = scratch; + pipapo_free_scratch(clone, i); #ifdef NFT_PIPAPO_ALIGN - scratch_aligned = NFT_PIPAPO_LT_ALIGN(scratch); - *per_cpu_ptr(clone->scratch_aligned, i) = scratch_aligned; + /* Align &scratch->map (not the struct itself): the extra + * %NFT_PIPAPO_ALIGN_HEADROOM bytes passed to kzalloc_node() + * above guarantee we can waste up to those bytes in order + * to align the map field regardless of its offset within + * the struct. + */ + BUILD_BUG_ON(offsetof(struct nft_pipapo_scratch, map) > NFT_PIPAPO_ALIGN_HEADROOM); + + scratch_aligned = NFT_PIPAPO_LT_ALIGN(&scratch->map); + scratch_aligned -= offsetof(struct nft_pipapo_scratch, map); + align_off = scratch_aligned - (void *)scratch; + + scratch = scratch_aligned; + scratch->align_off = align_off; #endif + *per_cpu_ptr(clone->scratch, i) = scratch; } return 0; @@ -1294,11 +1325,6 @@ static struct nft_pipapo_match *pipapo_clone(struct nft_pipapo_match *old) if (!new->scratch) goto out_scratch; -#ifdef NFT_PIPAPO_ALIGN - new->scratch_aligned = alloc_percpu(*new->scratch_aligned); - if (!new->scratch_aligned) - goto out_scratch; -#endif for_each_possible_cpu(i) *per_cpu_ptr(new->scratch, i) = NULL; @@ -1350,10 +1376,7 @@ out_lt: } out_scratch_realloc: for_each_possible_cpu(i) - kfree(*per_cpu_ptr(new->scratch, i)); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(new->scratch_aligned); -#endif + pipapo_free_scratch(new, i); out_scratch: free_percpu(new->scratch); kfree(new); @@ -1635,13 +1658,9 @@ static void pipapo_free_match(struct nft_pipapo_match *m) int i; for_each_possible_cpu(i) - kfree(*per_cpu_ptr(m->scratch, i)); + pipapo_free_scratch(m, i); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); - pipapo_free_fields(m); kfree(m); @@ -1961,6 +1980,8 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, rules_fx = rules_f0; nft_pipapo_for_each_field(f, i, m) { + bool last = i == m->field_count - 1; + if (!pipapo_match_field(f, start, rules_fx, match_start, match_end)) break; @@ -1973,16 +1994,18 @@ static void nft_pipapo_remove(const struct net *net, const struct nft_set *set, match_start += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); match_end += NFT_PIPAPO_GROUPS_PADDED_SIZE(f); - } - if (i == m->field_count) { - priv->dirty = true; - pipapo_drop(m, rulemap); - return; + if (last && f->mt[rulemap[i].to].e == e) { + priv->dirty = true; + pipapo_drop(m, rulemap); + return; + } } first_rule += rules_f0; } + + WARN_ON_ONCE(1); /* elem_priv not found */ } /** @@ -2118,7 +2141,7 @@ static int nft_pipapo_init(const struct nft_set *set, m->field_count = field_count; m->bsize_max = 0; - m->scratch = alloc_percpu(unsigned long *); + m->scratch = alloc_percpu(struct nft_pipapo_scratch *); if (!m->scratch) { err = -ENOMEM; goto out_scratch; @@ -2126,16 +2149,6 @@ static int nft_pipapo_init(const struct nft_set *set, for_each_possible_cpu(i) *per_cpu_ptr(m->scratch, i) = NULL; -#ifdef NFT_PIPAPO_ALIGN - m->scratch_aligned = alloc_percpu(unsigned long *); - if (!m->scratch_aligned) { - err = -ENOMEM; - goto out_free; - } - for_each_possible_cpu(i) - *per_cpu_ptr(m->scratch_aligned, i) = NULL; -#endif - rcu_head_init(&m->rcu); nft_pipapo_for_each_field(f, i, m) { @@ -2166,9 +2179,6 @@ static int nft_pipapo_init(const struct nft_set *set, return 0; out_free: -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif free_percpu(m->scratch); out_scratch: kfree(m); @@ -2220,13 +2230,8 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (m) { rcu_barrier(); - nft_set_pipapo_match_destroy(ctx, set, m); - -#ifdef NFT_PIPAPO_ALIGN - free_percpu(m->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(m->scratch, cpu)); + pipapo_free_scratch(m, cpu); free_percpu(m->scratch); pipapo_free_fields(m); kfree(m); @@ -2236,14 +2241,10 @@ static void nft_pipapo_destroy(const struct nft_ctx *ctx, if (priv->clone) { m = priv->clone; - if (priv->dirty) - nft_set_pipapo_match_destroy(ctx, set, m); + nft_set_pipapo_match_destroy(ctx, set, m); -#ifdef NFT_PIPAPO_ALIGN - free_percpu(priv->clone->scratch_aligned); -#endif for_each_possible_cpu(cpu) - kfree(*per_cpu_ptr(priv->clone->scratch, cpu)); + pipapo_free_scratch(priv->clone, cpu); free_percpu(priv->clone->scratch); pipapo_free_fields(priv->clone); diff --git a/net/netfilter/nft_set_pipapo.h b/net/netfilter/nft_set_pipapo.h index d84afb8fa..2e709ae01 100644 --- a/net/netfilter/nft_set_pipapo.h +++ b/net/netfilter/nft_set_pipapo.h @@ -131,20 +131,28 @@ struct nft_pipapo_field { }; /** + * struct nft_pipapo_scratch - percpu data used for lookup and matching + * @map_index: Current working bitmap index, toggled between field matches + * @align_off: Offset to get the originally allocated address + * @map: store partial matching results during lookup + */ +struct nft_pipapo_scratch { + u8 map_index; + u32 align_off; + unsigned long map[]; +}; + +/** * struct nft_pipapo_match - Data used for lookup and matching * @field_count Amount of fields in set * @scratch: Preallocated per-CPU maps for partial matching results - * @scratch_aligned: Version of @scratch aligned to NFT_PIPAPO_ALIGN bytes * @bsize_max: Maximum lookup table bucket size of all fields, in longs * @rcu Matching data is swapped on commits * @f: Fields, with lookup and mapping tables */ struct nft_pipapo_match { int field_count; -#ifdef NFT_PIPAPO_ALIGN - unsigned long * __percpu *scratch_aligned; -#endif - unsigned long * __percpu *scratch; + struct nft_pipapo_scratch * __percpu *scratch; size_t bsize_max; struct rcu_head rcu; struct nft_pipapo_field f[]; diff --git a/net/netfilter/nft_set_pipapo_avx2.c b/net/netfilter/nft_set_pipapo_avx2.c index 10332178d..60fb8bc0f 100644 --- a/net/netfilter/nft_set_pipapo_avx2.c +++ b/net/netfilter/nft_set_pipapo_avx2.c @@ -71,9 +71,6 @@ #define NFT_PIPAPO_AVX2_ZERO(reg) \ asm volatile("vpxor %ymm" #reg ", %ymm" #reg ", %ymm" #reg) -/* Current working bitmap index, toggled between field matches */ -static DEFINE_PER_CPU(bool, nft_pipapo_avx2_scratch_index); - /** * nft_pipapo_avx2_prepare() - Prepare before main algorithm body * @@ -1123,11 +1120,12 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, const u32 *key, const struct nft_set_ext **ext) { struct nft_pipapo *priv = nft_set_priv(set); - unsigned long *res, *fill, *scratch; + struct nft_pipapo_scratch *scratch; u8 genmask = nft_genmask_cur(net); const u8 *rp = (const u8 *)key; struct nft_pipapo_match *m; struct nft_pipapo_field *f; + unsigned long *res, *fill; bool map_index; int i, ret = 0; @@ -1139,15 +1137,16 @@ bool nft_pipapo_avx2_lookup(const struct net *net, const struct nft_set *set, /* This also protects access to all data related to scratch maps */ kernel_fpu_begin(); - scratch = *raw_cpu_ptr(m->scratch_aligned); + scratch = *raw_cpu_ptr(m->scratch); if (unlikely(!scratch)) { kernel_fpu_end(); return false; } - map_index = raw_cpu_read(nft_pipapo_avx2_scratch_index); - res = scratch + (map_index ? m->bsize_max : 0); - fill = scratch + (map_index ? 0 : m->bsize_max); + map_index = scratch->map_index; + + res = scratch->map + (map_index ? m->bsize_max : 0); + fill = scratch->map + (map_index ? 0 : m->bsize_max); /* Starting map doesn't need to be set for this implementation */ @@ -1219,7 +1218,7 @@ next_match: out: if (i % 2) - raw_cpu_write(nft_pipapo_avx2_scratch_index, !map_index); + scratch->map_index = !map_index; kernel_fpu_end(); return ret >= 0; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 12d9d0d0c..18c0d163d 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -237,7 +237,7 @@ static void nft_rbtree_gc_remove(struct net *net, struct nft_set *set, static const struct nft_rbtree_elem * nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, - struct nft_rbtree_elem *rbe, u8 genmask) + struct nft_rbtree_elem *rbe) { struct nft_set *set = (struct nft_set *)__set; struct rb_node *prev = rb_prev(&rbe->node); @@ -256,7 +256,7 @@ nft_rbtree_gc_elem(const struct nft_set *__set, struct nft_rbtree *priv, while (prev) { rbe_prev = rb_entry(prev, struct nft_rbtree_elem, node); if (nft_rbtree_interval_end(rbe_prev) && - nft_set_elem_active(&rbe_prev->ext, genmask)) + nft_set_elem_active(&rbe_prev->ext, NFT_GENMASK_ANY)) break; prev = rb_prev(prev); @@ -367,7 +367,7 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, nft_set_elem_active(&rbe->ext, cur_genmask)) { const struct nft_rbtree_elem *removed_end; - removed_end = nft_rbtree_gc_elem(set, priv, rbe, genmask); + removed_end = nft_rbtree_gc_elem(set, priv, rbe); if (IS_ERR(removed_end)) return PTR_ERR(removed_end); diff --git a/net/netfilter/nft_socket.c b/net/netfilter/nft_socket.c index f6d517185..826e5f8c7 100644 --- a/net/netfilter/nft_socket.c +++ b/net/netfilter/nft_socket.c @@ -166,6 +166,11 @@ static int nft_socket_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | diff --git a/net/netfilter/nft_synproxy.c b/net/netfilter/nft_synproxy.c index 1133e06f3..0806813d3 100644 --- a/net/netfilter/nft_synproxy.c +++ b/net/netfilter/nft_synproxy.c @@ -186,7 +186,6 @@ static int nft_synproxy_do_init(const struct nft_ctx *ctx, break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: err = nf_synproxy_ipv4_init(snet, ctx->net); if (err) goto nf_ct_failure; @@ -219,7 +218,6 @@ static void nft_synproxy_do_destroy(const struct nft_ctx *ctx) break; #endif case NFPROTO_INET: - case NFPROTO_BRIDGE: nf_synproxy_ipv4_fini(snet, ctx->net); nf_synproxy_ipv6_fini(snet, ctx->net); break; @@ -253,6 +251,11 @@ static int nft_synproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_FORWARD)); } diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f8d277e05..6b606e83c 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -293,6 +293,11 @@ static int nft_tproxy_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nft_data **data) { + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + return nft_chain_validate_hooks(ctx->chain, 1 << NF_INET_PRE_ROUTING); } diff --git a/net/netfilter/nft_xfrm.c b/net/netfilter/nft_xfrm.c index cbbbc4eca..7f762fc42 100644 --- a/net/netfilter/nft_xfrm.c +++ b/net/netfilter/nft_xfrm.c @@ -233,6 +233,11 @@ static int nft_xfrm_validate(const struct nft_ctx *ctx, const struct nft_expr *e const struct nft_xfrm *priv = nft_expr_priv(expr); unsigned int hooks; + if (ctx->family != NFPROTO_IPV4 && + ctx->family != NFPROTO_IPV6 && + ctx->family != NFPROTO_INET) + return -EOPNOTSUPP; + switch (priv->dir) { case XFRM_POLICY_IN: hooks = (1 << NF_INET_FORWARD) | diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 901358a5b..a2b14434d 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -157,7 +157,7 @@ static inline u32 netlink_group_mask(u32 group) static struct sk_buff *netlink_to_full_skb(const struct sk_buff *skb, gfp_t gfp_mask) { - unsigned int len = skb_end_offset(skb); + unsigned int len = skb->len; struct sk_buff *new; new = alloc_skb(len, gfp_mask); @@ -366,7 +366,7 @@ static void netlink_skb_destructor(struct sk_buff *skb) if (is_vmalloc_addr(skb->head)) { if (!skb->cloned || !atomic_dec_return(&(skb_shinfo(skb)->dataref))) - vfree(skb->head); + vfree_atomic(skb->head); skb->head = NULL; } diff --git a/net/netrom/af_netrom.c b/net/netrom/af_netrom.c index 247471631..37d0bf6ca 100644 --- a/net/netrom/af_netrom.c +++ b/net/netrom/af_netrom.c @@ -453,16 +453,16 @@ static int nr_create(struct net *net, struct socket *sock, int protocol, nr_init_timers(sk); nr->t1 = - msecs_to_jiffies(sysctl_netrom_transport_timeout); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_timeout)); nr->t2 = - msecs_to_jiffies(sysctl_netrom_transport_acknowledge_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_acknowledge_delay)); nr->n2 = - msecs_to_jiffies(sysctl_netrom_transport_maximum_tries); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_maximum_tries)); nr->t4 = - msecs_to_jiffies(sysctl_netrom_transport_busy_delay); + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_busy_delay)); nr->idle = - msecs_to_jiffies(sysctl_netrom_transport_no_activity_timeout); - nr->window = sysctl_netrom_transport_requested_window_size; + msecs_to_jiffies(READ_ONCE(sysctl_netrom_transport_no_activity_timeout)); + nr->window = READ_ONCE(sysctl_netrom_transport_requested_window_size); nr->bpqext = 1; nr->state = NR_STATE_0; @@ -954,7 +954,7 @@ int nr_rx_frame(struct sk_buff *skb, struct net_device *dev) * G8PZT's Xrouter which is sending packets with command type 7 * as an extension of the protocol. */ - if (sysctl_netrom_reset_circuit && + if (READ_ONCE(sysctl_netrom_reset_circuit) && (frametype != NR_RESET || flags != 0)) nr_transmit_reset(skb, 1); diff --git a/net/netrom/nr_dev.c b/net/netrom/nr_dev.c index 29e418c8c..4caee8754 100644 --- a/net/netrom/nr_dev.c +++ b/net/netrom/nr_dev.c @@ -81,7 +81,7 @@ static int nr_header(struct sk_buff *skb, struct net_device *dev, buff[6] |= AX25_SSSID_SPARE; buff += AX25_ADDR_LEN; - *buff++ = sysctl_netrom_network_ttl_initialiser; + *buff++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); *buff++ = NR_PROTO_IP; *buff++ = NR_PROTO_IP; diff --git a/net/netrom/nr_in.c b/net/netrom/nr_in.c index 69e58906c..034f79d11 100644 --- a/net/netrom/nr_in.c +++ b/net/netrom/nr_in.c @@ -97,7 +97,7 @@ static int nr_state1_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -128,7 +128,7 @@ static int nr_state2_machine(struct sock *sk, struct sk_buff *skb, break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; @@ -263,7 +263,7 @@ static int nr_state3_machine(struct sock *sk, struct sk_buff *skb, int frametype break; case NR_RESET: - if (sysctl_netrom_reset_circuit) + if (READ_ONCE(sysctl_netrom_reset_circuit)) nr_disconnect(sk, ECONNRESET); break; diff --git a/net/netrom/nr_out.c b/net/netrom/nr_out.c index 44929657f..5e531394a 100644 --- a/net/netrom/nr_out.c +++ b/net/netrom/nr_out.c @@ -204,7 +204,7 @@ void nr_transmit_buffer(struct sock *sk, struct sk_buff *skb) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (!nr_route_frame(skb, NULL)) { kfree_skb(skb); diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index 78da5eab2..895702337 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -153,7 +153,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, nr_neigh->digipeat = NULL; nr_neigh->ax25 = NULL; nr_neigh->dev = dev; - nr_neigh->quality = sysctl_netrom_default_path_quality; + nr_neigh->quality = READ_ONCE(sysctl_netrom_default_path_quality); nr_neigh->locked = 0; nr_neigh->count = 0; nr_neigh->number = nr_neigh_no++; @@ -725,7 +725,7 @@ void nr_link_failed(ax25_cb *ax25, int reason) nr_neigh->ax25 = NULL; ax25_cb_put(ax25); - if (++nr_neigh->failed < sysctl_netrom_link_fails_count) { + if (++nr_neigh->failed < READ_ONCE(sysctl_netrom_link_fails_count)) { nr_neigh_put(nr_neigh); return; } @@ -763,7 +763,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) if (ax25 != NULL) { ret = nr_add_node(nr_src, "", &ax25->dest_addr, ax25->digipeat, ax25->ax25_dev->dev, 0, - sysctl_netrom_obsolescence_count_initialiser); + READ_ONCE(sysctl_netrom_obsolescence_count_initialiser)); if (ret) return ret; } @@ -777,7 +777,7 @@ int nr_route_frame(struct sk_buff *skb, ax25_cb *ax25) return ret; } - if (!sysctl_netrom_routing_control && ax25 != NULL) + if (!READ_ONCE(sysctl_netrom_routing_control) && ax25 != NULL) return 0; /* Its Time-To-Live has expired */ diff --git a/net/netrom/nr_subr.c b/net/netrom/nr_subr.c index e2d2af924..c3bbd5880 100644 --- a/net/netrom/nr_subr.c +++ b/net/netrom/nr_subr.c @@ -182,7 +182,8 @@ void nr_write_internal(struct sock *sk, int frametype) *dptr++ = nr->my_id; *dptr++ = frametype; *dptr++ = nr->window; - if (nr->bpqext) *dptr++ = sysctl_netrom_network_ttl_initialiser; + if (nr->bpqext) + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); break; case NR_DISCREQ: @@ -236,7 +237,7 @@ void __nr_transmit_reply(struct sk_buff *skb, int mine, unsigned char cmdflags) dptr[6] |= AX25_SSSID_SPARE; dptr += AX25_ADDR_LEN; - *dptr++ = sysctl_netrom_network_ttl_initialiser; + *dptr++ = READ_ONCE(sysctl_netrom_network_ttl_initialiser); if (mine) { *dptr++ = 0; diff --git a/net/nfc/nci/core.c b/net/nfc/nci/core.c index 4c931bd1c..d8002065b 100644 --- a/net/nfc/nci/core.c +++ b/net/nfc/nci/core.c @@ -1197,6 +1197,10 @@ void nci_free_device(struct nci_dev *ndev) { nfc_free_device(ndev->nfc_dev); nci_hci_deallocate(ndev); + + /* drop partial rx data packet if present */ + if (ndev->rx_data_reassembly) + kfree_skb(ndev->rx_data_reassembly); kfree(ndev); } EXPORT_SYMBOL(nci_free_device); @@ -1498,6 +1502,11 @@ static void nci_rx_work(struct work_struct *work) nfc_send_to_raw_sock(ndev->nfc_dev, skb, RAW_PAYLOAD_NCI, NFC_DIRECTION_RX); + if (!nci_plen(skb->data)) { + kfree_skb(skb); + break; + } + /* Process frame */ switch (nci_mt(skb->data)) { case NCI_MT_RSP_PKT: diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 0f0f380e8..30f5e4140 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -1692,8 +1692,9 @@ int ovs_ct_copy_action(struct net *net, const struct nlattr *attr, if (ct_info.timeout[0]) { if (nf_ct_set_timeout(net, ct_info.ct, family, key->ip.proto, ct_info.timeout)) - pr_info_ratelimited("Failed to associated timeout " - "policy `%s'\n", ct_info.timeout); + OVS_NLERR(log, + "Failed to associated timeout policy '%s'", + ct_info.timeout); else ct_info.nf_ct_timeout = rcu_dereference( nf_ct_timeout_find(ct_info.ct)->timeout); @@ -1901,9 +1902,9 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) for (i = 0; i < CT_LIMIT_HASH_BUCKETS; ++i) { struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; + struct hlist_node *next; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node, - lockdep_ovsl_is_held()) + hlist_for_each_entry_safe(ct_limit, next, head, hlist_node) kfree_rcu(ct_limit, rcu); } kfree(info->limits); diff --git a/net/openvswitch/flow_netlink.c b/net/openvswitch/flow_netlink.c index 293a798e8..cff18a5bb 100644 --- a/net/openvswitch/flow_netlink.c +++ b/net/openvswitch/flow_netlink.c @@ -47,6 +47,7 @@ struct ovs_len_tbl { #define OVS_ATTR_NESTED -1 #define OVS_ATTR_VARIABLE -2 +#define OVS_COPY_ACTIONS_MAX_DEPTH 16 static bool actions_may_change_flow(const struct nlattr *actions) { @@ -2514,13 +2515,15 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log); + u32 mpls_label_count, bool log, + u32 depth); static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { const struct nlattr *attrs[OVS_SAMPLE_ATTR_MAX + 1]; const struct nlattr *probability, *actions; @@ -2571,7 +2574,8 @@ static int validate_and_copy_sample(struct net *net, const struct nlattr *attr, return err; err = __ovs_nla_copy_actions(net, actions, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2586,7 +2590,8 @@ static int validate_and_copy_dec_ttl(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { const struct nlattr *attrs[OVS_DEC_TTL_ATTR_MAX + 1]; int start, action_start, err, rem; @@ -2619,7 +2624,8 @@ static int validate_and_copy_dec_ttl(struct net *net, return action_start; err = __ovs_nla_copy_actions(net, actions, key, sfa, eth_type, - vlan_tci, mpls_label_count, log); + vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -2633,7 +2639,8 @@ static int validate_and_copy_clone(struct net *net, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log, bool last) + u32 mpls_label_count, bool log, bool last, + u32 depth) { int start, err; u32 exec; @@ -2653,7 +2660,8 @@ static int validate_and_copy_clone(struct net *net, return err; err = __ovs_nla_copy_actions(net, attr, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3022,7 +3030,7 @@ static int validate_and_copy_check_pkt_len(struct net *net, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, u32 mpls_label_count, - bool log, bool last) + bool log, bool last, u32 depth) { const struct nlattr *acts_if_greater, *acts_if_lesser_eq; struct nlattr *a[OVS_CHECK_PKT_LEN_ATTR_MAX + 1]; @@ -3070,7 +3078,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_lesser_eq, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3083,7 +3092,8 @@ static int validate_and_copy_check_pkt_len(struct net *net, return nested_acts_start; err = __ovs_nla_copy_actions(net, acts_if_greater, key, sfa, - eth_type, vlan_tci, mpls_label_count, log); + eth_type, vlan_tci, mpls_label_count, log, + depth + 1); if (err) return err; @@ -3111,12 +3121,16 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, const struct sw_flow_key *key, struct sw_flow_actions **sfa, __be16 eth_type, __be16 vlan_tci, - u32 mpls_label_count, bool log) + u32 mpls_label_count, bool log, + u32 depth) { u8 mac_proto = ovs_key_mac_proto(key); const struct nlattr *a; int rem, err; + if (depth > OVS_COPY_ACTIONS_MAX_DEPTH) + return -EOVERFLOW; + nla_for_each_nested(a, attr, rem) { /* Expected argument lengths, (u32)-1 for variable length. */ static const u32 action_lens[OVS_ACTION_ATTR_MAX + 1] = { @@ -3311,7 +3325,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_sample(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3382,7 +3396,7 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, err = validate_and_copy_clone(net, a, key, sfa, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, depth); if (err) return err; skip_copy = true; @@ -3396,7 +3410,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, eth_type, vlan_tci, mpls_label_count, - log, last); + log, last, + depth); if (err) return err; skip_copy = true; @@ -3406,7 +3421,8 @@ static int __ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, case OVS_ACTION_ATTR_DEC_TTL: err = validate_and_copy_dec_ttl(net, a, key, sfa, eth_type, vlan_tci, - mpls_label_count, log); + mpls_label_count, log, + depth); if (err) return err; skip_copy = true; @@ -3446,7 +3462,8 @@ int ovs_nla_copy_actions(struct net *net, const struct nlattr *attr, (*sfa)->orig_len = nla_len(attr); err = __ovs_nla_copy_actions(net, attr, key, sfa, key->eth.type, - key->eth.vlan.tci, mpls_label_count, log); + key->eth.vlan.tci, mpls_label_count, log, + 0); if (err) ovs_nla_free_flow_actions(*sfa); diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index b292d58fd..db5d16c5d 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -1871,7 +1871,7 @@ static int packet_rcv_spkt(struct sk_buff *skb, struct net_device *dev, */ spkt->spkt_family = dev->type; - strlcpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); + strscpy(spkt->spkt_device, dev->name, sizeof(spkt->spkt_device)); spkt->spkt_protocol = skb->protocol; /* @@ -3252,7 +3252,7 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, int addr_len) { struct sock *sk = sock->sk; - char name[sizeof(uaddr->sa_data) + 1]; + char name[sizeof(uaddr->sa_data_min) + 1]; /* * Check legality @@ -3263,8 +3263,8 @@ static int packet_bind_spkt(struct socket *sock, struct sockaddr *uaddr, /* uaddr->sa_data comes from the userspace, it's not guaranteed to be * zero-terminated. */ - memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data)); - name[sizeof(uaddr->sa_data)] = 0; + memcpy(name, uaddr->sa_data, sizeof(uaddr->sa_data_min)); + name[sizeof(uaddr->sa_data_min)] = 0; return packet_do_bind(sk, name, 0, 0); } @@ -3536,11 +3536,11 @@ static int packet_getname_spkt(struct socket *sock, struct sockaddr *uaddr, return -EOPNOTSUPP; uaddr->sa_family = AF_PACKET; - memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data)); + memset(uaddr->sa_data, 0, sizeof(uaddr->sa_data_min)); rcu_read_lock(); dev = dev_get_by_index_rcu(sock_net(sk), READ_ONCE(pkt_sk(sk)->ifindex)); if (dev) - strlcpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data)); + strscpy(uaddr->sa_data, dev->name, sizeof(uaddr->sa_data_min)); rcu_read_unlock(); return sizeof(*uaddr); @@ -3951,7 +3951,7 @@ packet_setsockopt(struct socket *sock, int level, int optname, sockptr_t optval, if (val < 0 || val > 1) return -EINVAL; - po->prot_hook.ignore_outgoing = !!val; + WRITE_ONCE(po->prot_hook.ignore_outgoing, !!val); return 0; } case PACKET_TX_HAS_OFF: @@ -4083,7 +4083,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, 0); break; case PACKET_IGNORE_OUTGOING: - val = po->prot_hook.ignore_outgoing; + val = READ_ONCE(po->prot_hook.ignore_outgoing); break; case PACKET_ROLLOVER_STATS: if (!po->rollover) diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index b239120dd..0ec0ae148 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -419,7 +419,7 @@ static int rds_recv_track_latency(struct rds_sock *rs, sockptr_t optval, rs->rs_rx_traces = trace.rx_traces; for (i = 0; i < rs->rs_rx_traces; i++) { - if (trace.rx_trace_pos[i] > RDS_MSG_RX_DGRAM_TRACE_MAX) { + if (trace.rx_trace_pos[i] >= RDS_MSG_RX_DGRAM_TRACE_MAX) { rs->rs_rx_traces = 0; return -EFAULT; } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 6f1a50d50..3df0affff 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -301,6 +301,9 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, kfree(sg); } ret = PTR_ERR(trans_private); + /* Trigger connection so that its ready for the next retry */ + if (ret == -ENODEV && cp) + rds_conn_connect_if_down(cp->cp_conn); goto out; } diff --git a/net/rds/send.c b/net/rds/send.c index 985d0b771..1923eaa91 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -103,13 +103,12 @@ EXPORT_SYMBOL_GPL(rds_send_path_reset); static int acquire_in_xmit(struct rds_conn_path *cp) { - return test_and_set_bit(RDS_IN_XMIT, &cp->cp_flags) == 0; + return test_and_set_bit_lock(RDS_IN_XMIT, &cp->cp_flags) == 0; } static void release_in_xmit(struct rds_conn_path *cp) { - clear_bit(RDS_IN_XMIT, &cp->cp_flags); - smp_mb__after_atomic(); + clear_bit_unlock(RDS_IN_XMIT, &cp->cp_flags); /* * We don't use wait_on_bit()/wake_up_bit() because our waking is in a * hot path and finding waiters is very rare. We don't want to walk @@ -1314,12 +1313,8 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Parse any control messages the user may have included. */ ret = rds_cmsg_send(rs, rm, msg, &allocated_mr, &vct); - if (ret) { - /* Trigger connection so that its ready for the next retry */ - if (ret == -EAGAIN) - rds_conn_connect_if_down(conn); + if (ret) goto out; - } if (rm->rdma.op_active && !conn->c_trans->xmit_rdma) { printk_ratelimited(KERN_NOTICE "rdma_op %p conn xmit_rdma %p\n", diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index aff184145..9081e8429 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -41,6 +41,14 @@ static void rxrpc_conn_retransmit_call(struct rxrpc_connection *conn, _enter("%d", conn->debug_id); + if (sp && sp->hdr.type == RXRPC_PACKET_TYPE_ACK) { + if (skb_copy_bits(skb, sizeof(struct rxrpc_wire_header), + &pkt.ack, sizeof(pkt.ack)) < 0) + return; + if (pkt.ack.reason == RXRPC_ACK_PING_RESPONSE) + return; + } + chan = &conn->channels[channel]; /* If the last call got moved on whilst we were waiting to run, just diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index 68508166b..af0e95ef9 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -31,7 +31,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, struct rxrpc_conn_proto k; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); struct rb_node *p; - unsigned int seq = 0; + unsigned int seq = 1; k.epoch = sp->hdr.epoch; k.cid = sp->hdr.cid & RXRPC_CIDMASK; @@ -41,6 +41,7 @@ struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *peer, * under just the RCU read lock, so we have to check for * changes. */ + seq++; /* 2 on the 1st/lockless path, otherwise odd */ read_seqbegin_or_lock(&peer->service_conn_lock, &seq); p = rcu_dereference_raw(peer->service_conns.rb_node); diff --git a/net/sched/Kconfig b/net/sched/Kconfig index 2046c16b2..e5f7675e5 100644 --- a/net/sched/Kconfig +++ b/net/sched/Kconfig @@ -45,23 +45,6 @@ if NET_SCHED comment "Queueing/Scheduling" -config NET_SCH_CBQ - tristate "Class Based Queueing (CBQ)" - help - Say Y here if you want to use the Class-Based Queueing (CBQ) packet - scheduling algorithm. This algorithm classifies the waiting packets - into a tree-like hierarchy of classes; the leaves of this tree are - in turn scheduled by separate algorithms. - - See the top of <file:net/sched/sch_cbq.c> for more details. - - CBQ is a commonly used scheduler, so if you're unsure, you should - say Y here. Then say Y to all the queueing algorithms below that you - want to use as leaf disciplines. - - To compile this code as a module, choose M here: the - module will be called sch_cbq. - config NET_SCH_HTB tristate "Hierarchical Token Bucket (HTB)" help @@ -85,20 +68,6 @@ config NET_SCH_HFSC To compile this code as a module, choose M here: the module will be called sch_hfsc. -config NET_SCH_ATM - tristate "ATM Virtual Circuits (ATM)" - depends on ATM - help - Say Y here if you want to use the ATM pseudo-scheduler. This - provides a framework for invoking classifiers, which in turn - select classes of this queuing discipline. Each class maps - the flow(s) it is handling to a given virtual circuit. - - See the top of <file:net/sched/sch_atm.c> for more details. - - To compile this code as a module, choose M here: the - module will be called sch_atm. - config NET_SCH_PRIO tristate "Multi Band Priority Queueing (PRIO)" help @@ -217,17 +186,6 @@ config NET_SCH_GRED To compile this code as a module, choose M here: the module will be called sch_gred. -config NET_SCH_DSMARK - tristate "Differentiated Services marker (DSMARK)" - help - Say Y if you want to schedule packets according to the - Differentiated Services architecture proposed in RFC 2475. - Technical information on this method, with pointers to associated - RFCs, is available at <http://www.gta.ufrj.br/diffserv/>. - - To compile this code as a module, choose M here: the - module will be called sch_dsmark. - config NET_SCH_NETEM tristate "Network emulator (NETEM)" help diff --git a/net/sched/Makefile b/net/sched/Makefile index df2bcd785..1b8d0fc66 100644 --- a/net/sched/Makefile +++ b/net/sched/Makefile @@ -32,20 +32,17 @@ obj-$(CONFIG_NET_ACT_TUNNEL_KEY)+= act_tunnel_key.o obj-$(CONFIG_NET_ACT_CT) += act_ct.o obj-$(CONFIG_NET_ACT_GATE) += act_gate.o obj-$(CONFIG_NET_SCH_FIFO) += sch_fifo.o -obj-$(CONFIG_NET_SCH_CBQ) += sch_cbq.o obj-$(CONFIG_NET_SCH_HTB) += sch_htb.o obj-$(CONFIG_NET_SCH_HFSC) += sch_hfsc.o obj-$(CONFIG_NET_SCH_RED) += sch_red.o obj-$(CONFIG_NET_SCH_GRED) += sch_gred.o obj-$(CONFIG_NET_SCH_INGRESS) += sch_ingress.o -obj-$(CONFIG_NET_SCH_DSMARK) += sch_dsmark.o obj-$(CONFIG_NET_SCH_SFB) += sch_sfb.o obj-$(CONFIG_NET_SCH_SFQ) += sch_sfq.o obj-$(CONFIG_NET_SCH_TBF) += sch_tbf.o obj-$(CONFIG_NET_SCH_TEQL) += sch_teql.o obj-$(CONFIG_NET_SCH_PRIO) += sch_prio.o obj-$(CONFIG_NET_SCH_MULTIQ) += sch_multiq.o -obj-$(CONFIG_NET_SCH_ATM) += sch_atm.o obj-$(CONFIG_NET_SCH_NETEM) += sch_netem.o obj-$(CONFIG_NET_SCH_DRR) += sch_drr.o obj-$(CONFIG_NET_SCH_PLUG) += sch_plug.o diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index aa98dcac9..934765a2e 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -219,13 +219,13 @@ static int tcf_skbmod_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_skbmod *d = to_skbmod(a); unsigned char *b = skb_tail_pointer(skb); struct tcf_skbmod_params *p; - struct tc_skbmod opt = { - .index = d->tcf_index, - .refcnt = refcount_read(&d->tcf_refcnt) - ref, - .bindcnt = atomic_read(&d->tcf_bindcnt) - bind, - }; + struct tc_skbmod opt; struct tcf_t t; + memset(&opt, 0, sizeof(opt)); + opt.index = d->tcf_index; + opt.refcnt = refcount_read(&d->tcf_refcnt) - ref, + opt.bindcnt = atomic_read(&d->tcf_bindcnt) - bind; spin_lock_bh(&d->tcf_lock); opt.action = d->tcf_action; p = rcu_dereference_protected(d->skbmod_p, diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c deleted file mode 100644 index 95967ce1f..000000000 --- a/net/sched/sch_atm.c +++ /dev/null @@ -1,709 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_atm.c - ATM VC selection "queueing discipline" */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/init.h> -#include <linux/interrupt.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/atmdev.h> -#include <linux/atmclip.h> -#include <linux/rtnetlink.h> -#include <linux/file.h> /* for fput */ -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - -/* - * The ATM queuing discipline provides a framework for invoking classifiers - * (aka "filters"), which in turn select classes of this queuing discipline. - * Each class maps the flow(s) it is handling to a given VC. Multiple classes - * may share the same VC. - * - * When creating a class, VCs are specified by passing the number of the open - * socket descriptor by which the calling process references the VC. The kernel - * keeps the VC open at least until all classes using it are removed. - * - * In this file, most functions are named atm_tc_* to avoid confusion with all - * the atm_* in net/atm. This naming convention differs from what's used in the - * rest of net/sched. - * - * Known bugs: - * - sometimes messes up the IP stack - * - any manipulations besides the few operations described in the README, are - * untested and likely to crash the system - * - should lock the flow while there is data in the queue (?) - */ - -#define VCC2FLOW(vcc) ((struct atm_flow_data *) ((vcc)->user_back)) - -struct atm_flow_data { - struct Qdisc_class_common common; - struct Qdisc *q; /* FIFO, TBF, etc. */ - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct atm_vcc *vcc; /* VCC; NULL if VCC is closed */ - void (*old_pop)(struct atm_vcc *vcc, - struct sk_buff *skb); /* chaining */ - struct atm_qdisc_data *parent; /* parent qdisc */ - struct socket *sock; /* for closing */ - int ref; /* reference count */ - struct gnet_stats_basic_packed bstats; - struct gnet_stats_queue qstats; - struct list_head list; - struct atm_flow_data *excess; /* flow for excess traffic; - NULL to set CLP instead */ - int hdr_len; - unsigned char hdr[]; /* header data; MUST BE LAST */ -}; - -struct atm_qdisc_data { - struct atm_flow_data link; /* unclassified skbs go here */ - struct list_head flows; /* NB: "link" is also on this - list */ - struct tasklet_struct task; /* dequeue tasklet */ -}; - -/* ------------------------- Class/flow operations ------------------------- */ - -static inline struct atm_flow_data *lookup_flow(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - list_for_each_entry(flow, &p->flows, list) { - if (flow->common.classid == classid) - return flow; - } - return NULL; -} - -static int atm_tc_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_graft(sch %p,[qdisc %p],flow %p,new %p,old %p)\n", - sch, p, flow, new, old); - if (list_empty(&flow->list)) - return -EINVAL; - if (!new) - new = &noop_qdisc; - *old = flow->q; - flow->q = new; - if (*old) - qdisc_reset(*old); - return 0; -} - -static struct Qdisc *atm_tc_leaf(struct Qdisc *sch, unsigned long cl) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_leaf(sch %p,flow %p)\n", sch, flow); - return flow ? flow->q : NULL; -} - -static unsigned long atm_tc_find(struct Qdisc *sch, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -static unsigned long atm_tc_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - struct atm_qdisc_data *p __maybe_unused = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", __func__, sch, p, classid); - flow = lookup_flow(sch, classid); - if (flow) - flow->ref++; - pr_debug("%s: flow %p\n", __func__, flow); - return (unsigned long)flow; -} - -/* - * atm_tc_put handles all destructions, including the ones that are explicitly - * requested (atm_tc_destroy, etc.). The assumption here is that we never drop - * anything that still seems to be in use. - */ -static void atm_tc_put(struct Qdisc *sch, unsigned long cl) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_put(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (--flow->ref) - return; - pr_debug("atm_tc_put: destroying\n"); - list_del_init(&flow->list); - pr_debug("atm_tc_put: qdisc %p\n", flow->q); - qdisc_put(flow->q); - tcf_block_put(flow->block); - if (flow->sock) { - pr_debug("atm_tc_put: f_count %ld\n", - file_count(flow->sock->file)); - flow->vcc->pop = flow->old_pop; - sockfd_put(flow->sock); - } - if (flow->excess) - atm_tc_put(sch, (unsigned long)flow->excess); - if (flow != &p->link) - kfree(flow); - /* - * If flow == &p->link, the qdisc no longer works at this point and - * needs to be removed. (By the caller of atm_tc_put.) - */ -} - -static void sch_atm_pop(struct atm_vcc *vcc, struct sk_buff *skb) -{ - struct atm_qdisc_data *p = VCC2FLOW(vcc)->parent; - - pr_debug("sch_atm_pop(vcc %p,skb %p,[qdisc %p])\n", vcc, skb, p); - VCC2FLOW(vcc)->old_pop(vcc, skb); - tasklet_schedule(&p->task); -} - -static const u8 llc_oui_ip[] = { - 0xaa, /* DSAP: non-ISO */ - 0xaa, /* SSAP: non-ISO */ - 0x03, /* Ctrl: Unnumbered Information Command PDU */ - 0x00, /* OUI: EtherType */ - 0x00, 0x00, - 0x08, 0x00 -}; /* Ethertype IP (0800) */ - -static const struct nla_policy atm_policy[TCA_ATM_MAX + 1] = { - [TCA_ATM_FD] = { .type = NLA_U32 }, - [TCA_ATM_EXCESS] = { .type = NLA_U32 }, -}; - -static int atm_tc_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)*arg; - struct atm_flow_data *excess = NULL; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_ATM_MAX + 1]; - struct socket *sock; - int fd, error, hdr_len; - void *hdr; - - pr_debug("atm_tc_change(sch %p,[qdisc %p],classid %x,parent %x," - "flow %p,opt %p)\n", sch, p, classid, parent, flow, opt); - /* - * The concept of parents doesn't apply for this qdisc. - */ - if (parent && parent != TC_H_ROOT && parent != sch->handle) - return -EINVAL; - /* - * ATM classes cannot be changed. In order to change properties of the - * ATM connection, that socket needs to be modified directly (via the - * native ATM API. In order to send a flow to a different VC, the old - * class needs to be removed and a new one added. (This may be changed - * later.) - */ - if (flow) - return -EBUSY; - if (opt == NULL) - return -EINVAL; - - error = nla_parse_nested_deprecated(tb, TCA_ATM_MAX, opt, atm_policy, - NULL); - if (error < 0) - return error; - - if (!tb[TCA_ATM_FD]) - return -EINVAL; - fd = nla_get_u32(tb[TCA_ATM_FD]); - pr_debug("atm_tc_change: fd %d\n", fd); - if (tb[TCA_ATM_HDR]) { - hdr_len = nla_len(tb[TCA_ATM_HDR]); - hdr = nla_data(tb[TCA_ATM_HDR]); - } else { - hdr_len = RFC1483LLC_LEN; - hdr = NULL; /* default LLC/SNAP for IP */ - } - if (!tb[TCA_ATM_EXCESS]) - excess = NULL; - else { - excess = (struct atm_flow_data *) - atm_tc_find(sch, nla_get_u32(tb[TCA_ATM_EXCESS])); - if (!excess) - return -ENOENT; - } - pr_debug("atm_tc_change: type %d, payload %d, hdr_len %d\n", - opt->nla_type, nla_len(opt), hdr_len); - sock = sockfd_lookup(fd, &error); - if (!sock) - return error; /* f_count++ */ - pr_debug("atm_tc_change: f_count %ld\n", file_count(sock->file)); - if (sock->ops->family != PF_ATMSVC && sock->ops->family != PF_ATMPVC) { - error = -EPROTOTYPE; - goto err_out; - } - /* @@@ should check if the socket is really operational or we'll crash - on vcc->send */ - if (classid) { - if (TC_H_MAJ(classid ^ sch->handle)) { - pr_debug("atm_tc_change: classid mismatch\n"); - error = -EINVAL; - goto err_out; - } - } else { - int i; - unsigned long cl; - - for (i = 1; i < 0x8000; i++) { - classid = TC_H_MAKE(sch->handle, 0x8000 | i); - cl = atm_tc_find(sch, classid); - if (!cl) - break; - } - } - pr_debug("atm_tc_change: new id %x\n", classid); - flow = kzalloc(sizeof(struct atm_flow_data) + hdr_len, GFP_KERNEL); - pr_debug("atm_tc_change: flow %p\n", flow); - if (!flow) { - error = -ENOBUFS; - goto err_out; - } - - error = tcf_block_get(&flow->block, &flow->filter_list, sch, - extack); - if (error) { - kfree(flow); - goto err_out; - } - - flow->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - extack); - if (!flow->q) - flow->q = &noop_qdisc; - pr_debug("atm_tc_change: qdisc %p\n", flow->q); - flow->sock = sock; - flow->vcc = ATM_SD(sock); /* speedup */ - flow->vcc->user_back = flow; - pr_debug("atm_tc_change: vcc %p\n", flow->vcc); - flow->old_pop = flow->vcc->pop; - flow->parent = p; - flow->vcc->pop = sch_atm_pop; - flow->common.classid = classid; - flow->ref = 1; - flow->excess = excess; - list_add(&flow->list, &p->link.list); - flow->hdr_len = hdr_len; - if (hdr) - memcpy(flow->hdr, hdr, hdr_len); - else - memcpy(flow->hdr, llc_oui_ip, sizeof(llc_oui_ip)); - *arg = (unsigned long)flow; - return 0; -err_out: - sockfd_put(sock); - return error; -} - -static int atm_tc_delete(struct Qdisc *sch, unsigned long arg) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - pr_debug("atm_tc_delete(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - if (list_empty(&flow->list)) - return -EINVAL; - if (rcu_access_pointer(flow->filter_list) || flow == &p->link) - return -EBUSY; - /* - * Reference count must be 2: one for "keepalive" (set at class - * creation), and one for the reference held when calling delete. - */ - if (flow->ref < 2) { - pr_err("atm_tc_delete: flow->ref == %d\n", flow->ref); - return -EINVAL; - } - if (flow->ref > 2) - return -EBUSY; /* catch references via excess, etc. */ - atm_tc_put(sch, arg); - return 0; -} - -static void atm_tc_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_walk(sch %p,[qdisc %p],walker %p)\n", sch, p, walker); - if (walker->stop) - return; - list_for_each_entry(flow, &p->flows, list) { - if (walker->count >= walker->skip && - walker->fn(sch, (unsigned long)flow, walker) < 0) { - walker->stop = 1; - break; - } - walker->count++; - } -} - -static struct tcf_block *atm_tc_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - - pr_debug("atm_tc_find_tcf(sch %p,[qdisc %p],flow %p)\n", sch, p, flow); - return flow ? flow->block : p->link.block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int atm_tc_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct tcf_result res; - int result; - int ret = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - - pr_debug("atm_tc_enqueue(skb %p,sch %p,[qdisc %p])\n", skb, sch, p); - result = TC_ACT_OK; /* be nice to gcc */ - flow = NULL; - if (TC_H_MAJ(skb->priority) != sch->handle || - !(flow = (struct atm_flow_data *)atm_tc_find(sch, skb->priority))) { - struct tcf_proto *fl; - - list_for_each_entry(flow, &p->flows, list) { - fl = rcu_dereference_bh(flow->filter_list); - if (fl) { - result = tcf_classify(skb, fl, &res, true); - if (result < 0) - continue; - if (result == TC_ACT_SHOT) - goto done; - - flow = (struct atm_flow_data *)res.class; - if (!flow) - flow = lookup_flow(sch, res.classid); - goto drop; - } - } - flow = NULL; -done: - ; - } - if (!flow) { - flow = &p->link; - } else { - if (flow->vcc) - ATM_SKB(skb)->atm_options = flow->vcc->atm_options; - /*@@@ looks good ... but it's not supposed to work :-) */ -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - case TC_ACT_SHOT: - __qdisc_drop(skb, to_free); - goto drop; - case TC_ACT_RECLASSIFY: - if (flow->excess) - flow = flow->excess; - else - ATM_SKB(skb)->atm_options |= ATM_ATMOPT_CLP; - break; - } -#endif - } - - ret = qdisc_enqueue(skb, flow->q, to_free); - if (ret != NET_XMIT_SUCCESS) { -drop: __maybe_unused - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - if (flow) - flow->qstats.drops++; - } - return ret; - } - /* - * Okay, this may seem weird. We pretend we've dropped the packet if - * it goes via ATM. The reason for this is that the outer qdisc - * expects to be able to q->dequeue the packet later on if we return - * success at this place. Also, sch->q.qdisc needs to reflect whether - * there is a packet egligible for dequeuing or not. Note that the - * statistics of the outer qdisc are necessarily wrong because of all - * this. There's currently no correct solution for this. - */ - if (flow == &p->link) { - sch->q.qlen++; - return NET_XMIT_SUCCESS; - } - tasklet_schedule(&p->task); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -/* - * Dequeue packets and send them over ATM. Note that we quite deliberately - * avoid checking net_device's flow control here, simply because sch_atm - * uses its own channels, which have nothing to do with any CLIP/LANE/or - * non-ATM interfaces. - */ - -static void sch_atm_dequeue(unsigned long data) -{ - struct Qdisc *sch = (struct Qdisc *)data; - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - struct sk_buff *skb; - - pr_debug("sch_atm_dequeue(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - if (flow == &p->link) - continue; - /* - * If traffic is properly shaped, this won't generate nasty - * little bursts. Otherwise, it may ... (but that's okay) - */ - while ((skb = flow->q->ops->peek(flow->q))) { - if (!atm_may_send(flow->vcc, skb->truesize)) - break; - - skb = qdisc_dequeue_peeked(flow->q); - if (unlikely(!skb)) - break; - - qdisc_bstats_update(sch, skb); - bstats_update(&flow->bstats, skb); - pr_debug("atm_tc_dequeue: sending on class %p\n", flow); - /* remove any LL header somebody else has attached */ - skb_pull(skb, skb_network_offset(skb)); - if (skb_headroom(skb) < flow->hdr_len) { - struct sk_buff *new; - - new = skb_realloc_headroom(skb, flow->hdr_len); - dev_kfree_skb(skb); - if (!new) - continue; - skb = new; - } - pr_debug("sch_atm_dequeue: ip %p, data %p\n", - skb_network_header(skb), skb->data); - ATM_SKB(skb)->vcc = flow->vcc; - memcpy(skb_push(skb, flow->hdr_len), flow->hdr, - flow->hdr_len); - refcount_add(skb->truesize, - &sk_atm(flow->vcc)->sk_wmem_alloc); - /* atm.atm_options are already set by atm_tc_enqueue */ - flow->vcc->send(flow->vcc, skb); - } - } -} - -static struct sk_buff *atm_tc_dequeue(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - - pr_debug("atm_tc_dequeue(sch %p,[qdisc %p])\n", sch, p); - tasklet_schedule(&p->task); - skb = qdisc_dequeue_peeked(p->link.q); - if (skb) - sch->q.qlen--; - return skb; -} - -static struct sk_buff *atm_tc_peek(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - - pr_debug("atm_tc_peek(sch %p,[qdisc %p])\n", sch, p); - - return p->link.q->ops->peek(p->link.q); -} - -static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("atm_tc_init(sch %p,[qdisc %p],opt %p)\n", sch, p, opt); - INIT_LIST_HEAD(&p->flows); - INIT_LIST_HEAD(&p->link.list); - list_add(&p->link.list, &p->flows); - p->link.q = qdisc_create_dflt(sch->dev_queue, - &pfifo_qdisc_ops, sch->handle, extack); - if (!p->link.q) - p->link.q = &noop_qdisc; - pr_debug("atm_tc_init: link (%p) qdisc %p\n", &p->link, p->link.q); - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; - - err = tcf_block_get(&p->link.block, &p->link.filter_list, sch, - extack); - if (err) - return err; - - tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); - return 0; -} - -static void atm_tc_reset(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow; - - pr_debug("atm_tc_reset(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) - qdisc_reset(flow->q); -} - -static void atm_tc_destroy(struct Qdisc *sch) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow, *tmp; - - pr_debug("atm_tc_destroy(sch %p,[qdisc %p])\n", sch, p); - list_for_each_entry(flow, &p->flows, list) { - tcf_block_put(flow->block); - flow->block = NULL; - } - - list_for_each_entry_safe(flow, tmp, &p->flows, list) { - if (flow->ref > 1) - pr_err("atm_destroy: %p->ref = %d\n", flow, flow->ref); - atm_tc_put(sch, (unsigned long)flow); - } - tasklet_kill(&p->task); -} - -static int atm_tc_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct atm_qdisc_data *p = qdisc_priv(sch); - struct atm_flow_data *flow = (struct atm_flow_data *)cl; - struct nlattr *nest; - - pr_debug("atm_tc_dump_class(sch %p,[qdisc %p],flow %p,skb %p,tcm %p)\n", - sch, p, flow, skb, tcm); - if (list_empty(&flow->list)) - return -EINVAL; - tcm->tcm_handle = flow->common.classid; - tcm->tcm_info = flow->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - - if (nla_put(skb, TCA_ATM_HDR, flow->hdr_len, flow->hdr)) - goto nla_put_failure; - if (flow->vcc) { - struct sockaddr_atmpvc pvc; - int state; - - memset(&pvc, 0, sizeof(pvc)); - pvc.sap_family = AF_ATMPVC; - pvc.sap_addr.itf = flow->vcc->dev ? flow->vcc->dev->number : -1; - pvc.sap_addr.vpi = flow->vcc->vpi; - pvc.sap_addr.vci = flow->vcc->vci; - if (nla_put(skb, TCA_ATM_ADDR, sizeof(pvc), &pvc)) - goto nla_put_failure; - state = ATM_VF2VS(flow->vcc->flags); - if (nla_put_u32(skb, TCA_ATM_STATE, state)) - goto nla_put_failure; - } - if (flow->excess) { - if (nla_put_u32(skb, TCA_ATM_EXCESS, flow->common.classid)) - goto nla_put_failure; - } else { - if (nla_put_u32(skb, TCA_ATM_EXCESS, 0)) - goto nla_put_failure; - } - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} -static int -atm_tc_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct atm_flow_data *flow = (struct atm_flow_data *)arg; - - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &flow->bstats) < 0 || - gnet_stats_copy_queue(d, NULL, &flow->qstats, flow->q->q.qlen) < 0) - return -1; - - return 0; -} - -static int atm_tc_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - return 0; -} - -static const struct Qdisc_class_ops atm_class_ops = { - .graft = atm_tc_graft, - .leaf = atm_tc_leaf, - .find = atm_tc_find, - .change = atm_tc_change, - .delete = atm_tc_delete, - .walk = atm_tc_walk, - .tcf_block = atm_tc_tcf_block, - .bind_tcf = atm_tc_bind_filter, - .unbind_tcf = atm_tc_put, - .dump = atm_tc_dump_class, - .dump_stats = atm_tc_dump_class_stats, -}; - -static struct Qdisc_ops atm_qdisc_ops __read_mostly = { - .cl_ops = &atm_class_ops, - .id = "atm", - .priv_size = sizeof(struct atm_qdisc_data), - .enqueue = atm_tc_enqueue, - .dequeue = atm_tc_dequeue, - .peek = atm_tc_peek, - .init = atm_tc_init, - .reset = atm_tc_reset, - .destroy = atm_tc_destroy, - .dump = atm_tc_dump, - .owner = THIS_MODULE, -}; - -static int __init atm_init(void) -{ - return register_qdisc(&atm_qdisc_ops); -} - -static void __exit atm_exit(void) -{ - unregister_qdisc(&atm_qdisc_ops); -} - -module_init(atm_init) -module_exit(atm_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_cbq.c b/net/sched/sch_cbq.c deleted file mode 100644 index 3da5eb313..000000000 --- a/net/sched/sch_cbq.c +++ /dev/null @@ -1,1816 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-or-later -/* - * net/sched/sch_cbq.c Class-Based Queueing discipline. - * - * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - */ - -#include <linux/module.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/kernel.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <net/netlink.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> - - -/* Class-Based Queueing (CBQ) algorithm. - ======================================= - - Sources: [1] Sally Floyd and Van Jacobson, "Link-sharing and Resource - Management Models for Packet Networks", - IEEE/ACM Transactions on Networking, Vol.3, No.4, 1995 - - [2] Sally Floyd, "Notes on CBQ and Guaranteed Service", 1995 - - [3] Sally Floyd, "Notes on Class-Based Queueing: Setting - Parameters", 1996 - - [4] Sally Floyd and Michael Speer, "Experimental Results - for Class-Based Queueing", 1998, not published. - - ----------------------------------------------------------------------- - - Algorithm skeleton was taken from NS simulator cbq.cc. - If someone wants to check this code against the LBL version, - he should take into account that ONLY the skeleton was borrowed, - the implementation is different. Particularly: - - --- The WRR algorithm is different. Our version looks more - reasonable (I hope) and works when quanta are allowed to be - less than MTU, which is always the case when real time classes - have small rates. Note, that the statement of [3] is - incomplete, delay may actually be estimated even if class - per-round allotment is less than MTU. Namely, if per-round - allotment is W*r_i, and r_1+...+r_k = r < 1 - - delay_i <= ([MTU/(W*r_i)]*W*r + W*r + k*MTU)/B - - In the worst case we have IntServ estimate with D = W*r+k*MTU - and C = MTU*r. The proof (if correct at all) is trivial. - - - --- It seems that cbq-2.0 is not very accurate. At least, I cannot - interpret some places, which look like wrong translations - from NS. Anyone is advised to find these differences - and explain to me, why I am wrong 8). - - --- Linux has no EOI event, so that we cannot estimate true class - idle time. Workaround is to consider the next dequeue event - as sign that previous packet is finished. This is wrong because of - internal device queueing, but on a permanently loaded link it is true. - Moreover, combined with clock integrator, this scheme looks - very close to an ideal solution. */ - -struct cbq_sched_data; - - -struct cbq_class { - struct Qdisc_class_common common; - struct cbq_class *next_alive; /* next class with backlog in this priority band */ - -/* Parameters */ - unsigned char priority; /* class priority */ - unsigned char priority2; /* priority to be used after overlimit */ - unsigned char ewma_log; /* time constant for idle time calculation */ - - u32 defmap; - - /* Link-sharing scheduler parameters */ - long maxidle; /* Class parameters: see below. */ - long offtime; - long minidle; - u32 avpkt; - struct qdisc_rate_table *R_tab; - - /* General scheduler (WRR) parameters */ - long allot; - long quantum; /* Allotment per WRR round */ - long weight; /* Relative allotment: see below */ - - struct Qdisc *qdisc; /* Ptr to CBQ discipline */ - struct cbq_class *split; /* Ptr to split node */ - struct cbq_class *share; /* Ptr to LS parent in the class tree */ - struct cbq_class *tparent; /* Ptr to tree parent in the class tree */ - struct cbq_class *borrow; /* NULL if class is bandwidth limited; - parent otherwise */ - struct cbq_class *sibling; /* Sibling chain */ - struct cbq_class *children; /* Pointer to children chain */ - - struct Qdisc *q; /* Elementary queueing discipline */ - - -/* Variables */ - unsigned char cpriority; /* Effective priority */ - unsigned char delayed; - unsigned char level; /* level of the class in hierarchy: - 0 for leaf classes, and maximal - level of children + 1 for nodes. - */ - - psched_time_t last; /* Last end of service */ - psched_time_t undertime; - long avgidle; - long deficit; /* Saved deficit for WRR */ - psched_time_t penalized; - struct gnet_stats_basic_packed bstats; - struct gnet_stats_queue qstats; - struct net_rate_estimator __rcu *rate_est; - struct tc_cbq_xstats xstats; - - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - - int filters; - - struct cbq_class *defaults[TC_PRIO_MAX + 1]; -}; - -struct cbq_sched_data { - struct Qdisc_class_hash clhash; /* Hash table of all classes */ - int nclasses[TC_CBQ_MAXPRIO + 1]; - unsigned int quanta[TC_CBQ_MAXPRIO + 1]; - - struct cbq_class link; - - unsigned int activemask; - struct cbq_class *active[TC_CBQ_MAXPRIO + 1]; /* List of all classes - with backlog */ - -#ifdef CONFIG_NET_CLS_ACT - struct cbq_class *rx_class; -#endif - struct cbq_class *tx_class; - struct cbq_class *tx_borrowed; - int tx_len; - psched_time_t now; /* Cached timestamp */ - unsigned int pmask; - - struct hrtimer delay_timer; - struct qdisc_watchdog watchdog; /* Watchdog timer, - started when CBQ has - backlog, but cannot - transmit just now */ - psched_tdiff_t wd_expires; - int toplevel; - u32 hgenerator; -}; - - -#define L2T(cl, len) qdisc_l2t((cl)->R_tab, len) - -static inline struct cbq_class * -cbq_class_lookup(struct cbq_sched_data *q, u32 classid) -{ - struct Qdisc_class_common *clc; - - clc = qdisc_class_find(&q->clhash, classid); - if (clc == NULL) - return NULL; - return container_of(clc, struct cbq_class, common); -} - -#ifdef CONFIG_NET_CLS_ACT - -static struct cbq_class * -cbq_reclassify(struct sk_buff *skb, struct cbq_class *this) -{ - struct cbq_class *cl; - - for (cl = this->tparent; cl; cl = cl->tparent) { - struct cbq_class *new = cl->defaults[TC_PRIO_BESTEFFORT]; - - if (new != NULL && new != this) - return new; - } - return NULL; -} - -#endif - -/* Classify packet. The procedure is pretty complicated, but - * it allows us to combine link sharing and priority scheduling - * transparently. - * - * Namely, you can put link sharing rules (f.e. route based) at root of CBQ, - * so that it resolves to split nodes. Then packets are classified - * by logical priority, or a more specific classifier may be attached - * to the split node. - */ - -static struct cbq_class * -cbq_classify(struct sk_buff *skb, struct Qdisc *sch, int *qerr) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *head = &q->link; - struct cbq_class **defmap; - struct cbq_class *cl = NULL; - u32 prio = skb->priority; - struct tcf_proto *fl; - struct tcf_result res; - - /* - * Step 1. If skb->priority points to one of our classes, use it. - */ - if (TC_H_MAJ(prio ^ sch->handle) == 0 && - (cl = cbq_class_lookup(q, prio)) != NULL) - return cl; - - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; - for (;;) { - int result = 0; - defmap = head->defaults; - - fl = rcu_dereference_bh(head->filter_list); - /* - * Step 2+n. Apply classifier. - */ - result = tcf_classify(skb, fl, &res, true); - if (!fl || result < 0) - goto fallback; - if (result == TC_ACT_SHOT) - return NULL; - - cl = (void *)res.class; - if (!cl) { - if (TC_H_MAJ(res.classid)) - cl = cbq_class_lookup(q, res.classid); - else if ((cl = defmap[res.classid & TC_PRIO_MAX]) == NULL) - cl = defmap[TC_PRIO_BESTEFFORT]; - - if (cl == NULL) - goto fallback; - } - if (cl->level >= head->level) - goto fallback; -#ifdef CONFIG_NET_CLS_ACT - switch (result) { - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - *qerr = NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - fallthrough; - case TC_ACT_RECLASSIFY: - return cbq_reclassify(skb, cl); - } -#endif - if (cl->level == 0) - return cl; - - /* - * Step 3+n. If classifier selected a link sharing class, - * apply agency specific classifier. - * Repeat this procdure until we hit a leaf node. - */ - head = cl; - } - -fallback: - cl = head; - - /* - * Step 4. No success... - */ - if (TC_H_MAJ(prio) == 0 && - !(cl = head->defaults[prio & TC_PRIO_MAX]) && - !(cl = head->defaults[TC_PRIO_BESTEFFORT])) - return head; - - return cl; -} - -/* - * A packet has just been enqueued on the empty class. - * cbq_activate_class adds it to the tail of active class list - * of its priority band. - */ - -static inline void cbq_activate_class(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - int prio = cl->cpriority; - struct cbq_class *cl_tail; - - cl_tail = q->active[prio]; - q->active[prio] = cl; - - if (cl_tail != NULL) { - cl->next_alive = cl_tail->next_alive; - cl_tail->next_alive = cl; - } else { - cl->next_alive = cl; - q->activemask |= (1<<prio); - } -} - -/* - * Unlink class from active chain. - * Note that this same procedure is done directly in cbq_dequeue* - * during round-robin procedure. - */ - -static void cbq_deactivate_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - int prio = this->cpriority; - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - - do { - cl = cl_prev->next_alive; - if (cl == this) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - return; - } - } - return; - } - } while ((cl_prev = cl) != q->active[prio]); -} - -static void -cbq_mark_toplevel(struct cbq_sched_data *q, struct cbq_class *cl) -{ - int toplevel = q->toplevel; - - if (toplevel > cl->level) { - psched_time_t now = psched_get_time(); - - do { - if (cl->undertime < now) { - q->toplevel = cl->level; - return; - } - } while ((cl = cl->borrow) != NULL && toplevel > cl->level); - } -} - -static int -cbq_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - int ret; - struct cbq_class *cl = cbq_classify(skb, sch, &ret); - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = cl; -#endif - if (cl == NULL) { - if (ret & __NET_XMIT_BYPASS) - qdisc_qstats_drop(sch); - __qdisc_drop(skb, to_free); - return ret; - } - - ret = qdisc_enqueue(skb, cl->q, to_free); - if (ret == NET_XMIT_SUCCESS) { - sch->q.qlen++; - cbq_mark_toplevel(q, cl); - if (!cl->next_alive) - cbq_activate_class(cl); - return ret; - } - - if (net_xmit_drop_count(ret)) { - qdisc_qstats_drop(sch); - cbq_mark_toplevel(q, cl); - cl->qstats.drops++; - } - return ret; -} - -/* Overlimit action: penalize leaf class by adding offtime */ -static void cbq_overlimit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - psched_tdiff_t delay = cl->undertime - q->now; - - if (!cl->delayed) { - delay += cl->offtime; - - /* - * Class goes to sleep, so that it will have no - * chance to work avgidle. Let's forgive it 8) - * - * BTW cbq-2.0 has a crap in this - * place, apparently they forgot to shift it by cl->ewma_log. - */ - if (cl->avgidle < 0) - delay -= (-cl->avgidle) - ((-cl->avgidle) >> cl->ewma_log); - if (cl->avgidle < cl->minidle) - cl->avgidle = cl->minidle; - if (delay <= 0) - delay = 1; - cl->undertime = q->now + delay; - - cl->xstats.overactions++; - cl->delayed = 1; - } - if (q->wd_expires == 0 || q->wd_expires > delay) - q->wd_expires = delay; - - /* Dirty work! We must schedule wakeups based on - * real available rate, rather than leaf rate, - * which may be tiny (even zero). - */ - if (q->toplevel == TC_CBQ_MAXLEVEL) { - struct cbq_class *b; - psched_tdiff_t base_delay = q->wd_expires; - - for (b = cl->borrow; b; b = b->borrow) { - delay = b->undertime - q->now; - if (delay < base_delay) { - if (delay <= 0) - delay = 1; - base_delay = delay; - } - } - - q->wd_expires = base_delay; - } -} - -static psched_tdiff_t cbq_undelay_prio(struct cbq_sched_data *q, int prio, - psched_time_t now) -{ - struct cbq_class *cl; - struct cbq_class *cl_prev = q->active[prio]; - psched_time_t sched = now; - - if (cl_prev == NULL) - return 0; - - do { - cl = cl_prev->next_alive; - if (now - cl->penalized > 0) { - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - cl->cpriority = cl->priority; - cl->delayed = 0; - cbq_activate_class(cl); - - if (cl == q->active[prio]) { - q->active[prio] = cl_prev; - if (cl == q->active[prio]) { - q->active[prio] = NULL; - return 0; - } - } - - cl = cl_prev->next_alive; - } else if (sched - cl->penalized > 0) - sched = cl->penalized; - } while ((cl_prev = cl) != q->active[prio]); - - return sched - now; -} - -static enum hrtimer_restart cbq_undelay(struct hrtimer *timer) -{ - struct cbq_sched_data *q = container_of(timer, struct cbq_sched_data, - delay_timer); - struct Qdisc *sch = q->watchdog.qdisc; - psched_time_t now; - psched_tdiff_t delay = 0; - unsigned int pmask; - - now = psched_get_time(); - - pmask = q->pmask; - q->pmask = 0; - - while (pmask) { - int prio = ffz(~pmask); - psched_tdiff_t tmp; - - pmask &= ~(1<<prio); - - tmp = cbq_undelay_prio(q, prio, now); - if (tmp > 0) { - q->pmask |= 1<<prio; - if (tmp < delay || delay == 0) - delay = tmp; - } - } - - if (delay) { - ktime_t time; - - time = 0; - time = ktime_add_ns(time, PSCHED_TICKS2NS(now + delay)); - hrtimer_start(&q->delay_timer, time, HRTIMER_MODE_ABS_PINNED); - } - - __netif_schedule(qdisc_root(sch)); - return HRTIMER_NORESTART; -} - -/* - * It is mission critical procedure. - * - * We "regenerate" toplevel cutoff, if transmitting class - * has backlog and it is not regulated. It is not part of - * original CBQ description, but looks more reasonable. - * Probably, it is wrong. This question needs further investigation. - */ - -static inline void -cbq_update_toplevel(struct cbq_sched_data *q, struct cbq_class *cl, - struct cbq_class *borrowed) -{ - if (cl && q->toplevel >= borrowed->level) { - if (cl->q->q.qlen > 1) { - do { - if (borrowed->undertime == PSCHED_PASTPERFECT) { - q->toplevel = borrowed->level; - return; - } - } while ((borrowed = borrowed->borrow) != NULL); - } -#if 0 - /* It is not necessary now. Uncommenting it - will save CPU cycles, but decrease fairness. - */ - q->toplevel = TC_CBQ_MAXLEVEL; -#endif - } -} - -static void -cbq_update(struct cbq_sched_data *q) -{ - struct cbq_class *this = q->tx_class; - struct cbq_class *cl = this; - int len = q->tx_len; - psched_time_t now; - - q->tx_class = NULL; - /* Time integrator. We calculate EOS time - * by adding expected packet transmission time. - */ - now = q->now + L2T(&q->link, len); - - for ( ; cl; cl = cl->share) { - long avgidle = cl->avgidle; - long idle; - - cl->bstats.packets++; - cl->bstats.bytes += len; - - /* - * (now - last) is total time between packet right edges. - * (last_pktlen/rate) is "virtual" busy time, so that - * - * idle = (now - last) - last_pktlen/rate - */ - - idle = now - cl->last; - if ((unsigned long)idle > 128*1024*1024) { - avgidle = cl->maxidle; - } else { - idle -= L2T(cl, len); - - /* true_avgidle := (1-W)*true_avgidle + W*idle, - * where W=2^{-ewma_log}. But cl->avgidle is scaled: - * cl->avgidle == true_avgidle/W, - * hence: - */ - avgidle += idle - (avgidle>>cl->ewma_log); - } - - if (avgidle <= 0) { - /* Overlimit or at-limit */ - - if (avgidle < cl->minidle) - avgidle = cl->minidle; - - cl->avgidle = avgidle; - - /* Calculate expected time, when this class - * will be allowed to send. - * It will occur, when: - * (1-W)*true_avgidle + W*delay = 0, i.e. - * idle = (1/W - 1)*(-true_avgidle) - * or - * idle = (1 - W)*(-cl->avgidle); - */ - idle = (-avgidle) - ((-avgidle) >> cl->ewma_log); - - /* - * That is not all. - * To maintain the rate allocated to the class, - * we add to undertime virtual clock, - * necessary to complete transmitted packet. - * (len/phys_bandwidth has been already passed - * to the moment of cbq_update) - */ - - idle -= L2T(&q->link, len); - idle += L2T(cl, len); - - cl->undertime = now + idle; - } else { - /* Underlimit */ - - cl->undertime = PSCHED_PASTPERFECT; - if (avgidle > cl->maxidle) - cl->avgidle = cl->maxidle; - else - cl->avgidle = avgidle; - } - if ((s64)(now - cl->last) > 0) - cl->last = now; - } - - cbq_update_toplevel(q, this, q->tx_borrowed); -} - -static inline struct cbq_class * -cbq_under_limit(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *this_cl = cl; - - if (cl->tparent == NULL) - return cl; - - if (cl->undertime == PSCHED_PASTPERFECT || q->now >= cl->undertime) { - cl->delayed = 0; - return cl; - } - - do { - /* It is very suspicious place. Now overlimit - * action is generated for not bounded classes - * only if link is completely congested. - * Though it is in agree with ancestor-only paradigm, - * it looks very stupid. Particularly, - * it means that this chunk of code will either - * never be called or result in strong amplification - * of burstiness. Dangerous, silly, and, however, - * no another solution exists. - */ - cl = cl->borrow; - if (!cl) { - this_cl->qstats.overlimits++; - cbq_overlimit(this_cl); - return NULL; - } - if (cl->level > q->toplevel) - return NULL; - } while (cl->undertime != PSCHED_PASTPERFECT && q->now < cl->undertime); - - cl->delayed = 0; - return cl; -} - -static inline struct sk_buff * -cbq_dequeue_prio(struct Qdisc *sch, int prio) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl_tail, *cl_prev, *cl; - struct sk_buff *skb; - int deficit; - - cl_tail = cl_prev = q->active[prio]; - cl = cl_prev->next_alive; - - do { - deficit = 0; - - /* Start round */ - do { - struct cbq_class *borrow = cl; - - if (cl->q->q.qlen && - (borrow = cbq_under_limit(cl)) == NULL) - goto skip_class; - - if (cl->deficit <= 0) { - /* Class exhausted its allotment per - * this round. Switch to the next one. - */ - deficit = 1; - cl->deficit += cl->quantum; - goto next_class; - } - - skb = cl->q->dequeue(cl->q); - - /* Class did not give us any skb :-( - * It could occur even if cl->q->q.qlen != 0 - * f.e. if cl->q == "tbf" - */ - if (skb == NULL) - goto skip_class; - - cl->deficit -= qdisc_pkt_len(skb); - q->tx_class = cl; - q->tx_borrowed = borrow; - if (borrow != cl) { -#ifndef CBQ_XSTATS_BORROWS_BYTES - borrow->xstats.borrows++; - cl->xstats.borrows++; -#else - borrow->xstats.borrows += qdisc_pkt_len(skb); - cl->xstats.borrows += qdisc_pkt_len(skb); -#endif - } - q->tx_len = qdisc_pkt_len(skb); - - if (cl->deficit <= 0) { - q->active[prio] = cl; - cl = cl->next_alive; - cl->deficit += cl->quantum; - } - return skb; - -skip_class: - if (cl->q->q.qlen == 0 || prio != cl->cpriority) { - /* Class is empty or penalized. - * Unlink it from active chain. - */ - cl_prev->next_alive = cl->next_alive; - cl->next_alive = NULL; - - /* Did cl_tail point to it? */ - if (cl == cl_tail) { - /* Repair it! */ - cl_tail = cl_prev; - - /* Was it the last class in this band? */ - if (cl == cl_tail) { - /* Kill the band! */ - q->active[prio] = NULL; - q->activemask &= ~(1<<prio); - if (cl->q->q.qlen) - cbq_activate_class(cl); - return NULL; - } - - q->active[prio] = cl_tail; - } - if (cl->q->q.qlen) - cbq_activate_class(cl); - - cl = cl_prev; - } - -next_class: - cl_prev = cl; - cl = cl->next_alive; - } while (cl_prev != cl_tail); - } while (deficit); - - q->active[prio] = cl_prev; - - return NULL; -} - -static inline struct sk_buff * -cbq_dequeue_1(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct sk_buff *skb; - unsigned int activemask; - - activemask = q->activemask & 0xFF; - while (activemask) { - int prio = ffz(~activemask); - activemask &= ~(1<<prio); - skb = cbq_dequeue_prio(sch, prio); - if (skb) - return skb; - } - return NULL; -} - -static struct sk_buff * -cbq_dequeue(struct Qdisc *sch) -{ - struct sk_buff *skb; - struct cbq_sched_data *q = qdisc_priv(sch); - psched_time_t now; - - now = psched_get_time(); - - if (q->tx_class) - cbq_update(q); - - q->now = now; - - for (;;) { - q->wd_expires = 0; - - skb = cbq_dequeue_1(sch); - if (skb) { - qdisc_bstats_update(sch, skb); - sch->q.qlen--; - return skb; - } - - /* All the classes are overlimit. - * - * It is possible, if: - * - * 1. Scheduler is empty. - * 2. Toplevel cutoff inhibited borrowing. - * 3. Root class is overlimit. - * - * Reset 2d and 3d conditions and retry. - * - * Note, that NS and cbq-2.0 are buggy, peeking - * an arbitrary class is appropriate for ancestor-only - * sharing, but not for toplevel algorithm. - * - * Our version is better, but slower, because it requires - * two passes, but it is unavoidable with top-level sharing. - */ - - if (q->toplevel == TC_CBQ_MAXLEVEL && - q->link.undertime == PSCHED_PASTPERFECT) - break; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->link.undertime = PSCHED_PASTPERFECT; - } - - /* No packets in scheduler or nobody wants to give them to us :-( - * Sigh... start watchdog timer in the last case. - */ - - if (sch->q.qlen) { - qdisc_qstats_overlimit(sch); - if (q->wd_expires) - qdisc_watchdog_schedule(&q->watchdog, - now + q->wd_expires); - } - return NULL; -} - -/* CBQ class maintanance routines */ - -static void cbq_adjust_levels(struct cbq_class *this) -{ - if (this == NULL) - return; - - do { - int level = 0; - struct cbq_class *cl; - - cl = this->children; - if (cl) { - do { - if (cl->level > level) - level = cl->level; - } while ((cl = cl->sibling) != this->children); - } - this->level = level + 1; - } while ((this = this->tparent) != NULL); -} - -static void cbq_normalize_quanta(struct cbq_sched_data *q, int prio) -{ - struct cbq_class *cl; - unsigned int h; - - if (q->quanta[prio] == 0) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - /* BUGGGG... Beware! This expression suffer of - * arithmetic overflows! - */ - if (cl->priority == prio) { - cl->quantum = (cl->weight*cl->allot*q->nclasses[prio])/ - q->quanta[prio]; - } - if (cl->quantum <= 0 || - cl->quantum > 32*qdisc_dev(cl->qdisc)->mtu) { - pr_warn("CBQ: class %08x has bad quantum==%ld, repaired.\n", - cl->common.classid, cl->quantum); - cl->quantum = qdisc_dev(cl->qdisc)->mtu/2 + 1; - } - } - } -} - -static void cbq_sync_defmap(struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - struct cbq_class *split = cl->split; - unsigned int h; - int i; - - if (split == NULL) - return; - - for (i = 0; i <= TC_PRIO_MAX; i++) { - if (split->defaults[i] == cl && !(cl->defmap & (1<<i))) - split->defaults[i] = NULL; - } - - for (i = 0; i <= TC_PRIO_MAX; i++) { - int level = split->level; - - if (split->defaults[i]) - continue; - - for (h = 0; h < q->clhash.hashsize; h++) { - struct cbq_class *c; - - hlist_for_each_entry(c, &q->clhash.hash[h], - common.hnode) { - if (c->split == split && c->level < level && - c->defmap & (1<<i)) { - split->defaults[i] = c; - level = c->level; - } - } - } - } -} - -static void cbq_change_defmap(struct cbq_class *cl, u32 splitid, u32 def, u32 mask) -{ - struct cbq_class *split = NULL; - - if (splitid == 0) { - split = cl->split; - if (!split) - return; - splitid = split->common.classid; - } - - if (split == NULL || split->common.classid != splitid) { - for (split = cl->tparent; split; split = split->tparent) - if (split->common.classid == splitid) - break; - } - - if (split == NULL) - return; - - if (cl->split != split) { - cl->defmap = 0; - cbq_sync_defmap(cl); - cl->split = split; - cl->defmap = def & mask; - } else - cl->defmap = (cl->defmap & ~mask) | (def & mask); - - cbq_sync_defmap(cl); -} - -static void cbq_unlink_class(struct cbq_class *this) -{ - struct cbq_class *cl, **clp; - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - - qdisc_class_hash_remove(&q->clhash, &this->common); - - if (this->tparent) { - clp = &this->sibling; - cl = *clp; - do { - if (cl == this) { - *clp = cl->sibling; - break; - } - clp = &cl->sibling; - } while ((cl = *clp) != this->sibling); - - if (this->tparent->children == this) { - this->tparent->children = this->sibling; - if (this->sibling == this) - this->tparent->children = NULL; - } - } else { - WARN_ON(this->sibling != this); - } -} - -static void cbq_link_class(struct cbq_class *this) -{ - struct cbq_sched_data *q = qdisc_priv(this->qdisc); - struct cbq_class *parent = this->tparent; - - this->sibling = this; - qdisc_class_hash_insert(&q->clhash, &this->common); - - if (parent == NULL) - return; - - if (parent->children == NULL) { - parent->children = this; - } else { - this->sibling = parent->children->sibling; - parent->children->sibling = this; - } -} - -static void -cbq_reset(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - int prio; - unsigned int h; - - q->activemask = 0; - q->pmask = 0; - q->tx_class = NULL; - q->tx_borrowed = NULL; - qdisc_watchdog_cancel(&q->watchdog); - hrtimer_cancel(&q->delay_timer); - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - for (prio = 0; prio <= TC_CBQ_MAXPRIO; prio++) - q->active[prio] = NULL; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - qdisc_reset(cl->q); - - cl->next_alive = NULL; - cl->undertime = PSCHED_PASTPERFECT; - cl->avgidle = cl->maxidle; - cl->deficit = cl->quantum; - cl->cpriority = cl->priority; - } - } -} - - -static int cbq_set_lss(struct cbq_class *cl, struct tc_cbq_lssopt *lss) -{ - if (lss->change & TCF_CBQ_LSS_FLAGS) { - cl->share = (lss->flags & TCF_CBQ_LSS_ISOLATED) ? NULL : cl->tparent; - cl->borrow = (lss->flags & TCF_CBQ_LSS_BOUNDED) ? NULL : cl->tparent; - } - if (lss->change & TCF_CBQ_LSS_EWMA) - cl->ewma_log = lss->ewma_log; - if (lss->change & TCF_CBQ_LSS_AVPKT) - cl->avpkt = lss->avpkt; - if (lss->change & TCF_CBQ_LSS_MINIDLE) - cl->minidle = -(long)lss->minidle; - if (lss->change & TCF_CBQ_LSS_MAXIDLE) { - cl->maxidle = lss->maxidle; - cl->avgidle = lss->maxidle; - } - if (lss->change & TCF_CBQ_LSS_OFFTIME) - cl->offtime = lss->offtime; - return 0; -} - -static void cbq_rmprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]--; - q->quanta[cl->priority] -= cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static void cbq_addprio(struct cbq_sched_data *q, struct cbq_class *cl) -{ - q->nclasses[cl->priority]++; - q->quanta[cl->priority] += cl->weight; - cbq_normalize_quanta(q, cl->priority); -} - -static int cbq_set_wrr(struct cbq_class *cl, struct tc_cbq_wrropt *wrr) -{ - struct cbq_sched_data *q = qdisc_priv(cl->qdisc); - - if (wrr->allot) - cl->allot = wrr->allot; - if (wrr->weight) - cl->weight = wrr->weight; - if (wrr->priority) { - cl->priority = wrr->priority - 1; - cl->cpriority = cl->priority; - if (cl->priority >= cl->priority2) - cl->priority2 = TC_CBQ_MAXPRIO - 1; - } - - cbq_addprio(q, cl); - return 0; -} - -static int cbq_set_fopt(struct cbq_class *cl, struct tc_cbq_fopt *fopt) -{ - cbq_change_defmap(cl, fopt->split, fopt->defmap, fopt->defchange); - return 0; -} - -static const struct nla_policy cbq_policy[TCA_CBQ_MAX + 1] = { - [TCA_CBQ_LSSOPT] = { .len = sizeof(struct tc_cbq_lssopt) }, - [TCA_CBQ_WRROPT] = { .len = sizeof(struct tc_cbq_wrropt) }, - [TCA_CBQ_FOPT] = { .len = sizeof(struct tc_cbq_fopt) }, - [TCA_CBQ_OVL_STRATEGY] = { .len = sizeof(struct tc_cbq_ovl) }, - [TCA_CBQ_RATE] = { .len = sizeof(struct tc_ratespec) }, - [TCA_CBQ_RTAB] = { .type = NLA_BINARY, .len = TC_RTAB_SIZE }, - [TCA_CBQ_POLICE] = { .len = sizeof(struct tc_cbq_police) }, -}; - -static int cbq_opt_parse(struct nlattr *tb[TCA_CBQ_MAX + 1], - struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - int err; - - if (!opt) { - NL_SET_ERR_MSG(extack, "CBQ options are required for this operation"); - return -EINVAL; - } - - err = nla_parse_nested_deprecated(tb, TCA_CBQ_MAX, opt, - cbq_policy, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_WRROPT]) { - const struct tc_cbq_wrropt *wrr = nla_data(tb[TCA_CBQ_WRROPT]); - - if (wrr->priority > TC_CBQ_MAXPRIO) { - NL_SET_ERR_MSG(extack, "priority is bigger than TC_CBQ_MAXPRIO"); - err = -EINVAL; - } - } - return err; -} - -static int cbq_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct tc_ratespec *r; - int err; - - qdisc_watchdog_init(&q->watchdog, sch); - hrtimer_init(&q->delay_timer, CLOCK_MONOTONIC, HRTIMER_MODE_ABS_PINNED); - q->delay_timer.function = cbq_undelay; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (!tb[TCA_CBQ_RTAB] || !tb[TCA_CBQ_RATE]) { - NL_SET_ERR_MSG(extack, "Rate specification missing or incomplete"); - return -EINVAL; - } - - r = nla_data(tb[TCA_CBQ_RATE]); - - q->link.R_tab = qdisc_get_rtab(r, tb[TCA_CBQ_RTAB], extack); - if (!q->link.R_tab) - return -EINVAL; - - err = tcf_block_get(&q->link.block, &q->link.filter_list, sch, extack); - if (err) - goto put_rtab; - - err = qdisc_class_hash_init(&q->clhash); - if (err < 0) - goto put_block; - - q->link.sibling = &q->link; - q->link.common.classid = sch->handle; - q->link.qdisc = sch; - q->link.q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (!q->link.q) - q->link.q = &noop_qdisc; - else - qdisc_hash_add(q->link.q, true); - - q->link.priority = TC_CBQ_MAXPRIO - 1; - q->link.priority2 = TC_CBQ_MAXPRIO - 1; - q->link.cpriority = TC_CBQ_MAXPRIO - 1; - q->link.allot = psched_mtu(qdisc_dev(sch)); - q->link.quantum = q->link.allot; - q->link.weight = q->link.R_tab->rate.rate; - - q->link.ewma_log = TC_CBQ_DEF_EWMA; - q->link.avpkt = q->link.allot/2; - q->link.minidle = -0x7FFFFFFF; - - q->toplevel = TC_CBQ_MAXLEVEL; - q->now = psched_get_time(); - - cbq_link_class(&q->link); - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(&q->link, nla_data(tb[TCA_CBQ_LSSOPT])); - - cbq_addprio(q, &q->link); - return 0; - -put_block: - tcf_block_put(q->link.block); - -put_rtab: - qdisc_put_rtab(q->link.R_tab); - return err; -} - -static int cbq_dump_rate(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - - if (nla_put(skb, TCA_CBQ_RATE, sizeof(cl->R_tab->rate), &cl->R_tab->rate)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_lss(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_lssopt opt; - - opt.flags = 0; - if (cl->borrow == NULL) - opt.flags |= TCF_CBQ_LSS_BOUNDED; - if (cl->share == NULL) - opt.flags |= TCF_CBQ_LSS_ISOLATED; - opt.ewma_log = cl->ewma_log; - opt.level = cl->level; - opt.avpkt = cl->avpkt; - opt.maxidle = cl->maxidle; - opt.minidle = (u32)(-cl->minidle); - opt.offtime = cl->offtime; - opt.change = ~0; - if (nla_put(skb, TCA_CBQ_LSSOPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_wrr(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_wrropt opt; - - memset(&opt, 0, sizeof(opt)); - opt.flags = 0; - opt.allot = cl->allot; - opt.priority = cl->priority + 1; - opt.cpriority = cl->cpriority + 1; - opt.weight = cl->weight; - if (nla_put(skb, TCA_CBQ_WRROPT, sizeof(opt), &opt)) - goto nla_put_failure; - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_fopt(struct sk_buff *skb, struct cbq_class *cl) -{ - unsigned char *b = skb_tail_pointer(skb); - struct tc_cbq_fopt opt; - - if (cl->split || cl->defmap) { - opt.split = cl->split ? cl->split->common.classid : 0; - opt.defmap = cl->defmap; - opt.defchange = ~0; - if (nla_put(skb, TCA_CBQ_FOPT, sizeof(opt), &opt)) - goto nla_put_failure; - } - return skb->len; - -nla_put_failure: - nlmsg_trim(skb, b); - return -1; -} - -static int cbq_dump_attr(struct sk_buff *skb, struct cbq_class *cl) -{ - if (cbq_dump_lss(skb, cl) < 0 || - cbq_dump_rate(skb, cl) < 0 || - cbq_dump_wrr(skb, cl) < 0 || - cbq_dump_fopt(skb, cl) < 0) - return -1; - return 0; -} - -static int cbq_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct nlattr *nest; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, &q->link) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_stats(struct Qdisc *sch, struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - q->link.xstats.avgidle = q->link.avgidle; - return gnet_stats_copy_app(d, &q->link.xstats, sizeof(q->link.xstats)); -} - -static int -cbq_dump_class(struct Qdisc *sch, unsigned long arg, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - struct nlattr *nest; - - if (cl->tparent) - tcm->tcm_parent = cl->tparent->common.classid; - else - tcm->tcm_parent = TC_H_ROOT; - tcm->tcm_handle = cl->common.classid; - tcm->tcm_info = cl->q->handle; - - nest = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (nest == NULL) - goto nla_put_failure; - if (cbq_dump_attr(skb, cl) < 0) - goto nla_put_failure; - return nla_nest_end(skb, nest); - -nla_put_failure: - nla_nest_cancel(skb, nest); - return -1; -} - -static int -cbq_dump_class_stats(struct Qdisc *sch, unsigned long arg, - struct gnet_dump *d) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - __u32 qlen; - - cl->xstats.avgidle = cl->avgidle; - cl->xstats.undertime = 0; - qdisc_qstats_qlen_backlog(cl->q, &qlen, &cl->qstats.backlog); - - if (cl->undertime != PSCHED_PASTPERFECT) - cl->xstats.undertime = cl->undertime - q->now; - - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl->bstats) < 0 || - gnet_stats_copy_rate_est(d, &cl->rate_est) < 0 || - gnet_stats_copy_queue(d, NULL, &cl->qstats, qlen) < 0) - return -1; - - return gnet_stats_copy_app(d, &cl->xstats, sizeof(cl->xstats)); -} - -static int cbq_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, - struct Qdisc **old, struct netlink_ext_ack *extack) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - cl->common.classid, extack); - if (new == NULL) - return -ENOBUFS; - } - - *old = qdisc_replace(sch, new, &cl->q); - return 0; -} - -static struct Qdisc *cbq_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - return cl->q; -} - -static void cbq_qlen_notify(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cbq_deactivate_class(cl); -} - -static unsigned long cbq_find(struct Qdisc *sch, u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - return (unsigned long)cbq_class_lookup(q, classid); -} - -static void cbq_destroy_class(struct Qdisc *sch, struct cbq_class *cl) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - - WARN_ON(cl->filters); - - tcf_block_put(cl->block); - qdisc_put(cl->q); - qdisc_put_rtab(cl->R_tab); - gen_kill_estimator(&cl->rate_est); - if (cl != &q->link) - kfree(cl); -} - -static void cbq_destroy(struct Qdisc *sch) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct hlist_node *next; - struct cbq_class *cl; - unsigned int h; - -#ifdef CONFIG_NET_CLS_ACT - q->rx_class = NULL; -#endif - /* - * Filters must be destroyed first because we don't destroy the - * classes from root to leafs which means that filters can still - * be bound to classes which have been destroyed already. --TGR '04 - */ - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - tcf_block_put(cl->block); - cl->block = NULL; - } - } - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry_safe(cl, next, &q->clhash.hash[h], - common.hnode) - cbq_destroy_class(sch, cl); - } - qdisc_class_hash_destroy(&q->clhash); -} - -static int -cbq_change_class(struct Qdisc *sch, u32 classid, u32 parentid, struct nlattr **tca, - unsigned long *arg, struct netlink_ext_ack *extack) -{ - int err; - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)*arg; - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_CBQ_MAX + 1]; - struct cbq_class *parent; - struct qdisc_rate_table *rtab = NULL; - - err = cbq_opt_parse(tb, opt, extack); - if (err < 0) - return err; - - if (tb[TCA_CBQ_OVL_STRATEGY] || tb[TCA_CBQ_POLICE]) { - NL_SET_ERR_MSG(extack, "Neither overlimit strategy nor policing attributes can be used for changing class params"); - return -EOPNOTSUPP; - } - - if (cl) { - /* Check parent */ - if (parentid) { - if (cl->tparent && - cl->tparent->common.classid != parentid) { - NL_SET_ERR_MSG(extack, "Invalid parent id"); - return -EINVAL; - } - if (!cl->tparent && parentid != TC_H_ROOT) { - NL_SET_ERR_MSG(extack, "Parent must be root"); - return -EINVAL; - } - } - - if (tb[TCA_CBQ_RATE]) { - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), - tb[TCA_CBQ_RTAB], extack); - if (rtab == NULL) - return -EINVAL; - } - - if (tca[TCA_RATE]) { - err = gen_replace_estimator(&cl->bstats, NULL, - &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Failed to replace specified rate estimator"); - qdisc_put_rtab(rtab); - return err; - } - } - - /* Change class parameters */ - sch_tree_lock(sch); - - if (cl->next_alive != NULL) - cbq_deactivate_class(cl); - - if (rtab) { - qdisc_put_rtab(cl->R_tab); - cl->R_tab = rtab; - } - - if (tb[TCA_CBQ_LSSOPT]) - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - - if (tb[TCA_CBQ_WRROPT]) { - cbq_rmprio(q, cl); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - } - - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - - if (cl->q->q.qlen) - cbq_activate_class(cl); - - sch_tree_unlock(sch); - - return 0; - } - - if (parentid == TC_H_ROOT) - return -EINVAL; - - if (!tb[TCA_CBQ_WRROPT] || !tb[TCA_CBQ_RATE] || !tb[TCA_CBQ_LSSOPT]) { - NL_SET_ERR_MSG(extack, "One of the following attributes MUST be specified: WRR, rate or link sharing"); - return -EINVAL; - } - - rtab = qdisc_get_rtab(nla_data(tb[TCA_CBQ_RATE]), tb[TCA_CBQ_RTAB], - extack); - if (rtab == NULL) - return -EINVAL; - - if (classid) { - err = -EINVAL; - if (TC_H_MAJ(classid ^ sch->handle) || - cbq_class_lookup(q, classid)) { - NL_SET_ERR_MSG(extack, "Specified class not found"); - goto failure; - } - } else { - int i; - classid = TC_H_MAKE(sch->handle, 0x8000); - - for (i = 0; i < 0x8000; i++) { - if (++q->hgenerator >= 0x8000) - q->hgenerator = 1; - if (cbq_class_lookup(q, classid|q->hgenerator) == NULL) - break; - } - err = -ENOSR; - if (i >= 0x8000) { - NL_SET_ERR_MSG(extack, "Unable to generate classid"); - goto failure; - } - classid = classid|q->hgenerator; - } - - parent = &q->link; - if (parentid) { - parent = cbq_class_lookup(q, parentid); - err = -EINVAL; - if (!parent) { - NL_SET_ERR_MSG(extack, "Failed to find parentid"); - goto failure; - } - } - - err = -ENOBUFS; - cl = kzalloc(sizeof(*cl), GFP_KERNEL); - if (cl == NULL) - goto failure; - - err = tcf_block_get(&cl->block, &cl->filter_list, sch, extack); - if (err) { - kfree(cl); - goto failure; - } - - if (tca[TCA_RATE]) { - err = gen_new_estimator(&cl->bstats, NULL, &cl->rate_est, - NULL, - qdisc_root_sleeping_running(sch), - tca[TCA_RATE]); - if (err) { - NL_SET_ERR_MSG(extack, "Couldn't create new estimator"); - tcf_block_put(cl->block); - kfree(cl); - goto failure; - } - } - - cl->R_tab = rtab; - rtab = NULL; - cl->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, classid, - NULL); - if (!cl->q) - cl->q = &noop_qdisc; - else - qdisc_hash_add(cl->q, true); - - cl->common.classid = classid; - cl->tparent = parent; - cl->qdisc = sch; - cl->allot = parent->allot; - cl->quantum = cl->allot; - cl->weight = cl->R_tab->rate.rate; - - sch_tree_lock(sch); - cbq_link_class(cl); - cl->borrow = cl->tparent; - if (cl->tparent != &q->link) - cl->share = cl->tparent; - cbq_adjust_levels(parent); - cl->minidle = -0x7FFFFFFF; - cbq_set_lss(cl, nla_data(tb[TCA_CBQ_LSSOPT])); - cbq_set_wrr(cl, nla_data(tb[TCA_CBQ_WRROPT])); - if (cl->ewma_log == 0) - cl->ewma_log = q->link.ewma_log; - if (cl->maxidle == 0) - cl->maxidle = q->link.maxidle; - if (cl->avpkt == 0) - cl->avpkt = q->link.avpkt; - if (tb[TCA_CBQ_FOPT]) - cbq_set_fopt(cl, nla_data(tb[TCA_CBQ_FOPT])); - sch_tree_unlock(sch); - - qdisc_class_hash_grow(sch, &q->clhash); - - *arg = (unsigned long)cl; - return 0; - -failure: - qdisc_put_rtab(rtab); - return err; -} - -static int cbq_delete(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl->filters || cl->children || cl == &q->link) - return -EBUSY; - - sch_tree_lock(sch); - - qdisc_purge_queue(cl->q); - - if (cl->next_alive) - cbq_deactivate_class(cl); - - if (q->tx_borrowed == cl) - q->tx_borrowed = q->tx_class; - if (q->tx_class == cl) { - q->tx_class = NULL; - q->tx_borrowed = NULL; - } -#ifdef CONFIG_NET_CLS_ACT - if (q->rx_class == cl) - q->rx_class = NULL; -#endif - - cbq_unlink_class(cl); - cbq_adjust_levels(cl->tparent); - cl->defmap = 0; - cbq_sync_defmap(cl); - - cbq_rmprio(q, cl); - sch_tree_unlock(sch); - - cbq_destroy_class(sch, cl); - return 0; -} - -static struct tcf_block *cbq_tcf_block(struct Qdisc *sch, unsigned long arg, - struct netlink_ext_ack *extack) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl = (struct cbq_class *)arg; - - if (cl == NULL) - cl = &q->link; - - return cl->block; -} - -static unsigned long cbq_bind_filter(struct Qdisc *sch, unsigned long parent, - u32 classid) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *p = (struct cbq_class *)parent; - struct cbq_class *cl = cbq_class_lookup(q, classid); - - if (cl) { - if (p && p->level <= cl->level) - return 0; - cl->filters++; - return (unsigned long)cl; - } - return 0; -} - -static void cbq_unbind_filter(struct Qdisc *sch, unsigned long arg) -{ - struct cbq_class *cl = (struct cbq_class *)arg; - - cl->filters--; -} - -static void cbq_walk(struct Qdisc *sch, struct qdisc_walker *arg) -{ - struct cbq_sched_data *q = qdisc_priv(sch); - struct cbq_class *cl; - unsigned int h; - - if (arg->stop) - return; - - for (h = 0; h < q->clhash.hashsize; h++) { - hlist_for_each_entry(cl, &q->clhash.hash[h], common.hnode) { - if (arg->count < arg->skip) { - arg->count++; - continue; - } - if (arg->fn(sch, (unsigned long)cl, arg) < 0) { - arg->stop = 1; - return; - } - arg->count++; - } - } -} - -static const struct Qdisc_class_ops cbq_class_ops = { - .graft = cbq_graft, - .leaf = cbq_leaf, - .qlen_notify = cbq_qlen_notify, - .find = cbq_find, - .change = cbq_change_class, - .delete = cbq_delete, - .walk = cbq_walk, - .tcf_block = cbq_tcf_block, - .bind_tcf = cbq_bind_filter, - .unbind_tcf = cbq_unbind_filter, - .dump = cbq_dump_class, - .dump_stats = cbq_dump_class_stats, -}; - -static struct Qdisc_ops cbq_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &cbq_class_ops, - .id = "cbq", - .priv_size = sizeof(struct cbq_sched_data), - .enqueue = cbq_enqueue, - .dequeue = cbq_dequeue, - .peek = qdisc_peek_dequeued, - .init = cbq_init, - .reset = cbq_reset, - .destroy = cbq_destroy, - .change = NULL, - .dump = cbq_dump, - .dump_stats = cbq_dump_stats, - .owner = THIS_MODULE, -}; - -static int __init cbq_module_init(void) -{ - return register_qdisc(&cbq_qdisc_ops); -} -static void __exit cbq_module_exit(void) -{ - unregister_qdisc(&cbq_qdisc_ops); -} -module_init(cbq_module_init) -module_exit(cbq_module_exit) -MODULE_LICENSE("GPL"); diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c deleted file mode 100644 index a75bc7f80..000000000 --- a/net/sched/sch_dsmark.c +++ /dev/null @@ -1,521 +0,0 @@ -// SPDX-License-Identifier: GPL-2.0-only -/* net/sched/sch_dsmark.c - Differentiated Services field marker */ - -/* Written 1998-2000 by Werner Almesberger, EPFL ICA */ - - -#include <linux/module.h> -#include <linux/init.h> -#include <linux/slab.h> -#include <linux/types.h> -#include <linux/string.h> -#include <linux/errno.h> -#include <linux/skbuff.h> -#include <linux/rtnetlink.h> -#include <linux/bitops.h> -#include <net/pkt_sched.h> -#include <net/pkt_cls.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <asm/byteorder.h> - -/* - * classid class marking - * ------- ----- ------- - * n/a 0 n/a - * x:0 1 use entry [0] - * ... ... ... - * x:y y>0 y+1 use entry [y] - * ... ... ... - * x:indices-1 indices use entry [indices-1] - * ... ... ... - * x:y y+1 use entry [y & (indices-1)] - * ... ... ... - * 0xffff 0x10000 use entry [indices-1] - */ - - -#define NO_DEFAULT_INDEX (1 << 16) - -struct mask_value { - u8 mask; - u8 value; -}; - -struct dsmark_qdisc_data { - struct Qdisc *q; - struct tcf_proto __rcu *filter_list; - struct tcf_block *block; - struct mask_value *mv; - u16 indices; - u8 set_tc_index; - u32 default_index; /* index range is 0...0xffff */ -#define DSMARK_EMBEDDED_SZ 16 - struct mask_value embedded[DSMARK_EMBEDDED_SZ]; -}; - -static inline int dsmark_valid_index(struct dsmark_qdisc_data *p, u16 index) -{ - return index <= p->indices && index > 0; -} - -/* ------------------------- Class/flow operations ------------------------- */ - -static int dsmark_graft(struct Qdisc *sch, unsigned long arg, - struct Qdisc *new, struct Qdisc **old, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p],new %p,old %p)\n", - __func__, sch, p, new, old); - - if (new == NULL) { - new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, - sch->handle, NULL); - if (new == NULL) - new = &noop_qdisc; - } - - *old = qdisc_replace(sch, new, &p->q); - return 0; -} - -static struct Qdisc *dsmark_leaf(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - return p->q; -} - -static unsigned long dsmark_find(struct Qdisc *sch, u32 classid) -{ - return TC_H_MIN(classid) + 1; -} - -static unsigned long dsmark_bind_filter(struct Qdisc *sch, - unsigned long parent, u32 classid) -{ - pr_debug("%s(sch %p,[qdisc %p],classid %x)\n", - __func__, sch, qdisc_priv(sch), classid); - - return dsmark_find(sch, classid); -} - -static void dsmark_unbind_filter(struct Qdisc *sch, unsigned long cl) -{ -} - -static const struct nla_policy dsmark_policy[TCA_DSMARK_MAX + 1] = { - [TCA_DSMARK_INDICES] = { .type = NLA_U16 }, - [TCA_DSMARK_DEFAULT_INDEX] = { .type = NLA_U16 }, - [TCA_DSMARK_SET_TC_INDEX] = { .type = NLA_FLAG }, - [TCA_DSMARK_MASK] = { .type = NLA_U8 }, - [TCA_DSMARK_VALUE] = { .type = NLA_U8 }, -}; - -static int dsmark_change(struct Qdisc *sch, u32 classid, u32 parent, - struct nlattr **tca, unsigned long *arg, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opt = tca[TCA_OPTIONS]; - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - - pr_debug("%s(sch %p,[qdisc %p],classid %x,parent %x), arg 0x%lx\n", - __func__, sch, p, classid, parent, *arg); - - if (!dsmark_valid_index(p, *arg)) { - err = -ENOENT; - goto errout; - } - - if (!opt) - goto errout; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - if (tb[TCA_DSMARK_VALUE]) - p->mv[*arg - 1].value = nla_get_u8(tb[TCA_DSMARK_VALUE]); - - if (tb[TCA_DSMARK_MASK]) - p->mv[*arg - 1].mask = nla_get_u8(tb[TCA_DSMARK_MASK]); - - err = 0; - -errout: - return err; -} - -static int dsmark_delete(struct Qdisc *sch, unsigned long arg) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - if (!dsmark_valid_index(p, arg)) - return -EINVAL; - - p->mv[arg - 1].mask = 0xff; - p->mv[arg - 1].value = 0; - - return 0; -} - -static void dsmark_walk(struct Qdisc *sch, struct qdisc_walker *walker) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int i; - - pr_debug("%s(sch %p,[qdisc %p],walker %p)\n", - __func__, sch, p, walker); - - if (walker->stop) - return; - - for (i = 0; i < p->indices; i++) { - if (p->mv[i].mask == 0xff && !p->mv[i].value) - goto ignore; - if (walker->count >= walker->skip) { - if (walker->fn(sch, i + 1, walker) < 0) { - walker->stop = 1; - break; - } - } -ignore: - walker->count++; - } -} - -static struct tcf_block *dsmark_tcf_block(struct Qdisc *sch, unsigned long cl, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - return p->block; -} - -/* --------------------------- Qdisc operations ---------------------------- */ - -static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, - struct sk_buff **to_free) -{ - unsigned int len = qdisc_pkt_len(skb); - struct dsmark_qdisc_data *p = qdisc_priv(sch); - int err; - - pr_debug("%s(skb %p,sch %p,[qdisc %p])\n", __func__, skb, sch, p); - - if (p->set_tc_index) { - int wlen = skb_network_offset(skb); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - wlen += sizeof(struct iphdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv4_get_dsfield(ip_hdr(skb)) - & ~INET_ECN_MASK; - break; - - case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) - goto drop; - - skb->tc_index = ipv6_get_dsfield(ipv6_hdr(skb)) - & ~INET_ECN_MASK; - break; - default: - skb->tc_index = 0; - break; - } - } - - if (TC_H_MAJ(skb->priority) == sch->handle) - skb->tc_index = TC_H_MIN(skb->priority); - else { - struct tcf_result res; - struct tcf_proto *fl = rcu_dereference_bh(p->filter_list); - int result = tcf_classify(skb, fl, &res, false); - - pr_debug("result %d class 0x%04x\n", result, res.classid); - - switch (result) { -#ifdef CONFIG_NET_CLS_ACT - case TC_ACT_QUEUED: - case TC_ACT_STOLEN: - case TC_ACT_TRAP: - __qdisc_drop(skb, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_STOLEN; - - case TC_ACT_SHOT: - goto drop; -#endif - case TC_ACT_OK: - skb->tc_index = TC_H_MIN(res.classid); - break; - - default: - if (p->default_index != NO_DEFAULT_INDEX) - skb->tc_index = p->default_index; - break; - } - } - - err = qdisc_enqueue(skb, p->q, to_free); - if (err != NET_XMIT_SUCCESS) { - if (net_xmit_drop_count(err)) - qdisc_qstats_drop(sch); - return err; - } - - sch->qstats.backlog += len; - sch->q.qlen++; - - return NET_XMIT_SUCCESS; - -drop: - qdisc_drop(skb, sch, to_free); - return NET_XMIT_SUCCESS | __NET_XMIT_BYPASS; -} - -static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct sk_buff *skb; - u32 index; - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - skb = qdisc_dequeue_peeked(p->q); - if (skb == NULL) - return NULL; - - qdisc_bstats_update(sch, skb); - qdisc_qstats_backlog_dec(sch, skb); - sch->q.qlen--; - - index = skb->tc_index & (p->indices - 1); - pr_debug("index %d->%d\n", skb->tc_index, index); - - switch (skb_protocol(skb, true)) { - case htons(ETH_P_IP): - ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - case htons(ETH_P_IPV6): - ipv6_change_dsfield(ipv6_hdr(skb), p->mv[index].mask, - p->mv[index].value); - break; - default: - /* - * Only complain if a change was actually attempted. - * This way, we can send non-IP traffic through dsmark - * and don't need yet another qdisc as a bypass. - */ - if (p->mv[index].mask != 0xff || p->mv[index].value) - pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(skb_protocol(skb, true))); - break; - } - - return skb; -} - -static struct sk_buff *dsmark_peek(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - return p->q->ops->peek(p->q); -} - -static int dsmark_init(struct Qdisc *sch, struct nlattr *opt, - struct netlink_ext_ack *extack) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *tb[TCA_DSMARK_MAX + 1]; - int err = -EINVAL; - u32 default_index = NO_DEFAULT_INDEX; - u16 indices; - int i; - - pr_debug("%s(sch %p,[qdisc %p],opt %p)\n", __func__, sch, p, opt); - - if (!opt) - goto errout; - - err = tcf_block_get(&p->block, &p->filter_list, sch, extack); - if (err) - return err; - - err = nla_parse_nested_deprecated(tb, TCA_DSMARK_MAX, opt, - dsmark_policy, NULL); - if (err < 0) - goto errout; - - err = -EINVAL; - if (!tb[TCA_DSMARK_INDICES]) - goto errout; - indices = nla_get_u16(tb[TCA_DSMARK_INDICES]); - - if (hweight32(indices) != 1) - goto errout; - - if (tb[TCA_DSMARK_DEFAULT_INDEX]) - default_index = nla_get_u16(tb[TCA_DSMARK_DEFAULT_INDEX]); - - if (indices <= DSMARK_EMBEDDED_SZ) - p->mv = p->embedded; - else - p->mv = kmalloc_array(indices, sizeof(*p->mv), GFP_KERNEL); - if (!p->mv) { - err = -ENOMEM; - goto errout; - } - for (i = 0; i < indices; i++) { - p->mv[i].mask = 0xff; - p->mv[i].value = 0; - } - p->indices = indices; - p->default_index = default_index; - p->set_tc_index = nla_get_flag(tb[TCA_DSMARK_SET_TC_INDEX]); - - p->q = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, sch->handle, - NULL); - if (p->q == NULL) - p->q = &noop_qdisc; - else - qdisc_hash_add(p->q, true); - - pr_debug("%s: qdisc %p\n", __func__, p->q); - - err = 0; -errout: - return err; -} - -static void dsmark_reset(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - if (p->q) - qdisc_reset(p->q); -} - -static void dsmark_destroy(struct Qdisc *sch) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - - pr_debug("%s(sch %p,[qdisc %p])\n", __func__, sch, p); - - tcf_block_put(p->block); - qdisc_put(p->q); - if (p->mv != p->embedded) - kfree(p->mv); -} - -static int dsmark_dump_class(struct Qdisc *sch, unsigned long cl, - struct sk_buff *skb, struct tcmsg *tcm) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - pr_debug("%s(sch %p,[qdisc %p],class %ld\n", __func__, sch, p, cl); - - if (!dsmark_valid_index(p, cl)) - return -EINVAL; - - tcm->tcm_handle = TC_H_MAKE(TC_H_MAJ(sch->handle), cl - 1); - tcm->tcm_info = p->q->handle; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u8(skb, TCA_DSMARK_MASK, p->mv[cl - 1].mask) || - nla_put_u8(skb, TCA_DSMARK_VALUE, p->mv[cl - 1].value)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static int dsmark_dump(struct Qdisc *sch, struct sk_buff *skb) -{ - struct dsmark_qdisc_data *p = qdisc_priv(sch); - struct nlattr *opts = NULL; - - opts = nla_nest_start_noflag(skb, TCA_OPTIONS); - if (opts == NULL) - goto nla_put_failure; - if (nla_put_u16(skb, TCA_DSMARK_INDICES, p->indices)) - goto nla_put_failure; - - if (p->default_index != NO_DEFAULT_INDEX && - nla_put_u16(skb, TCA_DSMARK_DEFAULT_INDEX, p->default_index)) - goto nla_put_failure; - - if (p->set_tc_index && - nla_put_flag(skb, TCA_DSMARK_SET_TC_INDEX)) - goto nla_put_failure; - - return nla_nest_end(skb, opts); - -nla_put_failure: - nla_nest_cancel(skb, opts); - return -EMSGSIZE; -} - -static const struct Qdisc_class_ops dsmark_class_ops = { - .graft = dsmark_graft, - .leaf = dsmark_leaf, - .find = dsmark_find, - .change = dsmark_change, - .delete = dsmark_delete, - .walk = dsmark_walk, - .tcf_block = dsmark_tcf_block, - .bind_tcf = dsmark_bind_filter, - .unbind_tcf = dsmark_unbind_filter, - .dump = dsmark_dump_class, -}; - -static struct Qdisc_ops dsmark_qdisc_ops __read_mostly = { - .next = NULL, - .cl_ops = &dsmark_class_ops, - .id = "dsmark", - .priv_size = sizeof(struct dsmark_qdisc_data), - .enqueue = dsmark_enqueue, - .dequeue = dsmark_dequeue, - .peek = dsmark_peek, - .init = dsmark_init, - .reset = dsmark_reset, - .destroy = dsmark_destroy, - .change = NULL, - .dump = dsmark_dump, - .owner = THIS_MODULE, -}; - -static int __init dsmark_module_init(void) -{ - return register_qdisc(&dsmark_qdisc_ops); -} - -static void __exit dsmark_module_exit(void) -{ - unregister_qdisc(&dsmark_qdisc_ops); -} - -module_init(dsmark_module_init) -module_exit(dsmark_module_exit) - -MODULE_LICENSE("GPL"); diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index f15fca59b..7c921760d 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -177,7 +177,7 @@ static int __smc_diag_dump(struct sock *sk, struct sk_buff *skb, } if (smc->conn.lgr && smc->conn.lgr->is_smcd && (req->diag_ext & (1 << (SMC_DIAG_DMBINFO - 1))) && - !list_empty(&smc->conn.lgr->list)) { + !list_empty(&smc->conn.lgr->list) && smc->conn.rmb_desc) { struct smc_connection *conn = &smc->conn; struct smcd_diag_dmbinfo dinfo; diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 30bae60d6..ed9cfa11b 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -797,6 +797,16 @@ static void smc_pnet_create_pnetids_list(struct net *net) u8 ndev_pnetid[SMC_MAX_PNETID_LEN]; struct net_device *dev; + /* Newly created netns do not have devices. + * Do not even acquire rtnl. + */ + if (list_empty(&net->dev_base_head)) + return; + + /* Note: This might not be needed, because smc_pnet_netdev_event() + * is also calling smc_pnet_add_base_pnetid() when handling + * NETDEV_UP event. + */ rtnl_lock(); for_each_netdev(net, dev) smc_pnet_add_base_pnetid(net, dev, ndev_pnetid); diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d435bffc6..97ff11973 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -284,10 +284,10 @@ char *rpc_sockaddr2uaddr(const struct sockaddr *sap, gfp_t gfp_flags) } if (snprintf(portbuf, sizeof(portbuf), - ".%u.%u", port >> 8, port & 0xff) > (int)sizeof(portbuf)) + ".%u.%u", port >> 8, port & 0xff) >= (int)sizeof(portbuf)) return NULL; - if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) > sizeof(addrbuf)) + if (strlcat(addrbuf, portbuf, sizeof(addrbuf)) >= sizeof(addrbuf)) return NULL; return kstrdup(addrbuf, gfp_flags); diff --git a/net/sunrpc/auth_gss/gss_rpc_xdr.c b/net/sunrpc/auth_gss/gss_rpc_xdr.c index 2ff7b7083..e265b8d38 100644 --- a/net/sunrpc/auth_gss/gss_rpc_xdr.c +++ b/net/sunrpc/auth_gss/gss_rpc_xdr.c @@ -250,8 +250,8 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, creds = kzalloc(sizeof(struct svc_cred), GFP_KERNEL); if (!creds) { - kfree(oa->data); - return -ENOMEM; + err = -ENOMEM; + goto free_oa; } oa->data[0].option.data = CREDS_VALUE; @@ -265,29 +265,40 @@ static int gssx_dec_option_array(struct xdr_stream *xdr, /* option buffer */ p = xdr_inline_decode(xdr, 4); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } length = be32_to_cpup(p); p = xdr_inline_decode(xdr, length); - if (unlikely(p == NULL)) - return -ENOSPC; + if (unlikely(p == NULL)) { + err = -ENOSPC; + goto free_creds; + } if (length == sizeof(CREDS_VALUE) && memcmp(p, CREDS_VALUE, sizeof(CREDS_VALUE)) == 0) { /* We have creds here. parse them */ err = gssx_dec_linux_creds(xdr, creds); if (err) - return err; + goto free_creds; oa->data[0].value.len = 1; /* presence */ } else { /* consume uninteresting buffer */ err = gssx_dec_buffer(xdr, &dummy); if (err) - return err; + goto free_creds; } } return 0; + +free_creds: + kfree(creds); +free_oa: + kfree(oa->data); + oa->data = NULL; + return err; } static int gssx_dec_status(struct xdr_stream *xdr, diff --git a/net/sunrpc/xprtmultipath.c b/net/sunrpc/xprtmultipath.c index 78c075a68..a11e80d17 100644 --- a/net/sunrpc/xprtmultipath.c +++ b/net/sunrpc/xprtmultipath.c @@ -253,8 +253,9 @@ struct rpc_xprt *xprt_iter_current_entry(struct rpc_xprt_iter *xpi) return xprt_switch_find_current_entry(head, xpi->xpi_cursor); } -bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, - const struct sockaddr *sap) +static +bool __rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) { struct list_head *head; struct rpc_xprt *pos; @@ -273,6 +274,18 @@ bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, return false; } +bool rpc_xprt_switch_has_addr(struct rpc_xprt_switch *xps, + const struct sockaddr *sap) +{ + bool res; + + rcu_read_lock(); + res = __rpc_xprt_switch_has_addr(xps, sap); + rcu_read_unlock(); + + return res; +} + static struct rpc_xprt *xprt_switch_find_next_entry(struct list_head *head, const struct rpc_xprt *cur) diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index df6aba224..2511718b8 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -1072,6 +1072,12 @@ int tipc_nl_bearer_add(struct sk_buff *skb, struct genl_info *info) #ifdef CONFIG_TIPC_MEDIA_UDP if (attrs[TIPC_NLA_BEARER_UDP_OPTS]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) { + rtnl_unlock(); + NL_SET_ERR_MSG(info->extack, "UDP option is unsupported"); + return -EINVAL; + } + err = tipc_udp_nl_bearer_add(b, attrs[TIPC_NLA_BEARER_UDP_OPTS]); if (err) { diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 7ee3c8b03..2bbacd9b9 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -800,7 +800,7 @@ static void tls_update(struct sock *sk, struct proto *p, } } -static int tls_get_info(const struct sock *sk, struct sk_buff *skb) +static int tls_get_info(struct sock *sk, struct sk_buff *skb) { u16 version, cipher_type; struct tls_context *ctx; diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index dd980438f..46f1c19f7 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -1754,6 +1754,7 @@ int tls_sw_recvmsg(struct sock *sk, struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct tls_prot_info *prot = &tls_ctx->prot_info; struct sk_psock *psock; + int num_async, pending; unsigned char control = 0; ssize_t decrypted = 0; struct strp_msg *rxm; @@ -1766,8 +1767,6 @@ int tls_sw_recvmsg(struct sock *sk, bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool is_peek = flags & MSG_PEEK; bool bpf_strp_enabled; - int num_async = 0; - int pending; flags |= nonblock; @@ -1784,17 +1783,18 @@ int tls_sw_recvmsg(struct sock *sk, if (err < 0) { tls_err_abort(sk, err); goto end; - } else { - copied = err; } - if (len <= copied) - goto recv_end; + copied = err; + if (len <= copied || (copied && control != TLS_RECORD_TYPE_DATA)) + goto end; target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); len = len - copied; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + decrypted = 0; + num_async = 0; while (len && (decrypted + copied < target || ctx->recv_pkt)) { bool retain_skb = false; bool zc = false; diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 237488b1b..224b1fdc8 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -817,11 +817,11 @@ static struct sock *unix_create1(struct net *net, struct socket *sock, int kern) sk->sk_write_space = unix_write_space; sk->sk_max_ack_backlog = net->unx.sysctl_max_dgram_qlen; sk->sk_destruct = unix_sock_destructor; - u = unix_sk(sk); + u = unix_sk(sk); + u->inflight = 0; u->path.dentry = NULL; u->path.mnt = NULL; spin_lock_init(&u->lock); - atomic_long_set(&u->inflight, 0); INIT_LIST_HEAD(&u->link); mutex_init(&u->iolock); /* single task reading lock */ mutex_init(&u->bindlock); /* single task binding lock */ @@ -1126,13 +1126,11 @@ static void unix_state_double_lock(struct sock *sk1, struct sock *sk2) unix_state_lock(sk1); return; } - if (sk1 < sk2) { - unix_state_lock(sk1); - unix_state_lock_nested(sk2); - } else { - unix_state_lock(sk2); - unix_state_lock_nested(sk1); - } + if (sk1 > sk2) + swap(sk1, sk2); + + unix_state_lock(sk1); + unix_state_lock_nested(sk2, U_LOCK_SECOND); } static void unix_state_double_unlock(struct sock *sk1, struct sock *sk2) @@ -1352,7 +1350,7 @@ restart: goto out_unlock; } - unix_state_lock_nested(sk); + unix_state_lock_nested(sk, U_LOCK_SECOND); if (sk->sk_state != st) { unix_state_unlock(sk); diff --git a/net/unix/diag.c b/net/unix/diag.c index 951b33fa8..2975e7a06 100644 --- a/net/unix/diag.c +++ b/net/unix/diag.c @@ -83,7 +83,7 @@ static int sk_diag_dump_icons(struct sock *sk, struct sk_buff *nlskb) * queue lock. With the other's queue locked it's * OK to lock the state. */ - unix_state_lock_nested(req); + unix_state_lock_nested(req, U_LOCK_DIAG); peer = unix_sk(req)->peer; buf[i++] = (peer ? sock_i_ino(peer) : 0); unix_state_unlock(req); diff --git a/net/unix/garbage.c b/net/unix/garbage.c index dc2763540..133ba5be4 100644 --- a/net/unix/garbage.c +++ b/net/unix/garbage.c @@ -166,17 +166,18 @@ static void scan_children(struct sock *x, void (*func)(struct unix_sock *), static void dec_inflight(struct unix_sock *usk) { - atomic_long_dec(&usk->inflight); + usk->inflight--; } static void inc_inflight(struct unix_sock *usk) { - atomic_long_inc(&usk->inflight); + usk->inflight++; } static void inc_inflight_move_tail(struct unix_sock *u) { - atomic_long_inc(&u->inflight); + u->inflight++; + /* If this still might be part of a cycle, move it to the end * of the list, so that it's checked even if it was already * passed over @@ -198,7 +199,7 @@ void wait_for_unix_gc(void) if (READ_ONCE(unix_tot_inflight) > UNIX_INFLIGHT_TRIGGER_GC && !READ_ONCE(gc_in_progress)) unix_gc(); - wait_event(unix_gc_wait, gc_in_progress == false); + wait_event(unix_gc_wait, !READ_ONCE(gc_in_progress)); } /* The external entry point: unix_gc() */ @@ -234,20 +235,34 @@ void unix_gc(void) * receive queues. Other, non candidate sockets _can_ be * added to queue, so we must make sure only to touch * candidates. + * + * Embryos, though never candidates themselves, affect which + * candidates are reachable by the garbage collector. Before + * being added to a listener's queue, an embryo may already + * receive data carrying SCM_RIGHTS, potentially making the + * passed socket a candidate that is not yet reachable by the + * collector. It becomes reachable once the embryo is + * enqueued. Therefore, we must ensure that no SCM-laden + * embryo appears in a (candidate) listener's queue between + * consecutive scan_children() calls. */ list_for_each_entry_safe(u, next, &gc_inflight_list, link) { + struct sock *sk = &u->sk; long total_refs; - long inflight_refs; - total_refs = file_count(u->sk.sk_socket->file); - inflight_refs = atomic_long_read(&u->inflight); + total_refs = file_count(sk->sk_socket->file); - BUG_ON(inflight_refs < 1); - BUG_ON(total_refs < inflight_refs); - if (total_refs == inflight_refs) { + BUG_ON(!u->inflight); + BUG_ON(total_refs < u->inflight); + if (total_refs == u->inflight) { list_move_tail(&u->link, &gc_candidates); __set_bit(UNIX_GC_CANDIDATE, &u->gc_flags); __set_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); + + if (sk->sk_state == TCP_LISTEN) { + unix_state_lock_nested(sk, U_LOCK_GC_LISTENER); + unix_state_unlock(sk); + } } } @@ -271,7 +286,7 @@ void unix_gc(void) /* Move cursor to after the current position. */ list_move(&cursor, &u->link); - if (atomic_long_read(&u->inflight) > 0) { + if (u->inflight) { list_move_tail(&u->link, ¬_cycle_list); __clear_bit(UNIX_GC_MAYBE_CYCLE, &u->gc_flags); scan_children(&u->sk, inc_inflight_move_tail, NULL); diff --git a/net/unix/scm.c b/net/unix/scm.c index e8e2a00bb..4eff7da9f 100644 --- a/net/unix/scm.c +++ b/net/unix/scm.c @@ -34,10 +34,8 @@ struct sock *unix_get_socket(struct file *filp) /* PF_UNIX ? */ if (s && sock->ops && sock->ops->family == PF_UNIX) u_sock = s; - } else { - /* Could be an io_uring instance */ - u_sock = io_uring_get_socket(filp); } + return u_sock; } EXPORT_SYMBOL(unix_get_socket); @@ -54,12 +52,13 @@ void unix_inflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - if (atomic_long_inc_return(&u->inflight) == 1) { + if (!u->inflight) { BUG_ON(!list_empty(&u->link)); list_add_tail(&u->link, &gc_inflight_list); } else { BUG_ON(list_empty(&u->link)); } + u->inflight++; /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight + 1); } @@ -76,10 +75,11 @@ void unix_notinflight(struct user_struct *user, struct file *fp) if (s) { struct unix_sock *u = unix_sk(s); - BUG_ON(!atomic_long_read(&u->inflight)); + BUG_ON(!u->inflight); BUG_ON(list_empty(&u->link)); - if (atomic_long_dec_and_test(&u->inflight)) + u->inflight--; + if (!u->inflight) list_del_init(&u->link); /* Paired with READ_ONCE() in wait_for_unix_gc() */ WRITE_ONCE(unix_tot_inflight, unix_tot_inflight - 1); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 0ac829c8f..933591f97 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -3595,6 +3595,7 @@ static int nl80211_dump_interface(struct sk_buff *skb, struct netlink_callback * if_idx++; } + if_start = 0; wp_idx++; } out: @@ -3771,6 +3772,8 @@ static int nl80211_set_interface(struct sk_buff *skb, struct genl_info *info) if (ntype != NL80211_IFTYPE_MESH_POINT) return -EINVAL; + if (otype != NL80211_IFTYPE_MESH_POINT) + return -EINVAL; if (netif_running(dev)) return -EBUSY; diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 1e6dfe204..a6c289a61 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -1801,8 +1801,12 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, list_add(&new->hidden_list, &hidden->hidden_list); hidden->refcount++; + + ies = (void *)rcu_access_pointer(new->pub.beacon_ies); rcu_assign_pointer(new->pub.beacon_ies, hidden->pub.beacon_ies); + if (ies) + kfree_rcu(ies, rcu_head); } } else { /* diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 161dc194e..a7ecf2956 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -470,12 +470,12 @@ static int x25_getsockopt(struct socket *sock, int level, int optname, if (get_user(len, optlen)) goto out; - len = min_t(unsigned int, len, sizeof(int)); - rc = -EINVAL; if (len < 0) goto out; + len = min_t(unsigned int, len, sizeof(int)); + rc = -EFAULT; if (put_user(len, optlen)) goto out; diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index d04f91f4d..562d69f17 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -895,6 +895,8 @@ static int xsk_setsockopt(struct socket *sock, int level, int optname, struct xsk_queue **q; int entries; + if (optlen < sizeof(entries)) + return -EINVAL; if (copy_from_sockptr(&entries, optval, sizeof(entries))) return -EFAULT; diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index 8fce2e93b..070946d09 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -1753,6 +1753,9 @@ static int copy_to_user_tmpl(struct xfrm_policy *xp, struct sk_buff *skb) if (xp->xfrm_nr == 0) return 0; + if (xp->xfrm_nr > XFRM_MAX_DEPTH) + return -ENOBUFS; + for (i = 0; i < xp->xfrm_nr; i++) { struct xfrm_user_tmpl *up = &vec[i]; struct xfrm_tmpl *kp = &xp->xfrm_vec[i]; |