diff options
Diffstat (limited to 'net')
418 files changed, 6457 insertions, 3329 deletions
diff --git a/net/8021q/vlan.h b/net/8021q/vlan.h index c46daf09a501..bb7ec1a3915d 100644 --- a/net/8021q/vlan.h +++ b/net/8021q/vlan.h @@ -126,6 +126,7 @@ int vlan_check_real_dev(struct net_device *real_dev, void vlan_setup(struct net_device *dev); int register_vlan_dev(struct net_device *dev, struct netlink_ext_ack *extack); void unregister_vlan_dev(struct net_device *dev, struct list_head *head); +void vlan_dev_uninit(struct net_device *dev); bool vlan_dev_inherit_address(struct net_device *dev, struct net_device *real_dev); diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index a0b2d8b9def7..2ab1107ef19f 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -617,7 +617,8 @@ static int vlan_dev_init(struct net_device *dev) return 0; } -static void vlan_dev_uninit(struct net_device *dev) +/* Note: this function might be called multiple times for the same device. */ +void vlan_dev_uninit(struct net_device *dev) { struct vlan_priority_tci_mapping *pm; struct vlan_dev_priv *vlan = vlan_dev_priv(dev); diff --git a/net/8021q/vlan_netlink.c b/net/8021q/vlan_netlink.c index c482a6fe9393..0db85aeb119b 100644 --- a/net/8021q/vlan_netlink.c +++ b/net/8021q/vlan_netlink.c @@ -108,11 +108,13 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], struct ifla_vlan_flags *flags; struct ifla_vlan_qos_mapping *m; struct nlattr *attr; - int rem; + int rem, err; if (data[IFLA_VLAN_FLAGS]) { flags = nla_data(data[IFLA_VLAN_FLAGS]); - vlan_dev_change_flags(dev, flags->flags, flags->mask); + err = vlan_dev_change_flags(dev, flags->flags, flags->mask); + if (err) + return err; } if (data[IFLA_VLAN_INGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_INGRESS_QOS], rem) { @@ -123,7 +125,9 @@ static int vlan_changelink(struct net_device *dev, struct nlattr *tb[], if (data[IFLA_VLAN_EGRESS_QOS]) { nla_for_each_nested(attr, data[IFLA_VLAN_EGRESS_QOS], rem) { m = nla_data(attr); - vlan_dev_set_egress_priority(dev, m->from, m->to); + err = vlan_dev_set_egress_priority(dev, m->from, m->to); + if (err) + return err; } } return 0; @@ -179,10 +183,11 @@ static int vlan_newlink(struct net *src_net, struct net_device *dev, return -EINVAL; err = vlan_changelink(dev, tb, data, extack); - if (err < 0) - return err; - - return register_vlan_dev(dev, extack); + if (!err) + err = register_vlan_dev(dev, extack); + if (err) + vlan_dev_uninit(dev); + return err; } static inline size_t vlan_qos_map_size(unsigned int n) diff --git a/net/9p/trans_fd.c b/net/9p/trans_fd.c index 13cd683a658a..12ecacf0c55f 100644 --- a/net/9p/trans_fd.c +++ b/net/9p/trans_fd.c @@ -362,6 +362,10 @@ static void p9_read_work(struct work_struct *work) if (m->rreq->status == REQ_STATUS_SENT) { list_del(&m->rreq->req_list); p9_client_cb(m->client, m->rreq, REQ_STATUS_RCVD); + } else if (m->rreq->status == REQ_STATUS_FLSHD) { + /* Ignore replies associated with a cancelled request. */ + p9_debug(P9_DEBUG_TRANS, + "Ignore replies associated with a cancelled request\n"); } else { spin_unlock(&m->client->lock); p9_debug(P9_DEBUG_ERROR, @@ -703,11 +707,20 @@ static int p9_fd_cancelled(struct p9_client *client, struct p9_req_t *req) { p9_debug(P9_DEBUG_TRANS, "client %p req %p\n", client, req); + spin_lock(&client->lock); + /* Ignore cancelled request if message has been received + * before lock. + */ + if (req->status == REQ_STATUS_RCVD) { + spin_unlock(&client->lock); + return 0; + } + /* we haven't received a response for oldreq, * remove it from the list. */ - spin_lock(&client->lock); list_del(&req->req_list); + req->status = REQ_STATUS_FLSHD; spin_unlock(&client->lock); p9_req_put(req); @@ -803,20 +816,28 @@ static int p9_fd_open(struct p9_client *client, int rfd, int wfd) return -ENOMEM; ts->rd = fget(rfd); + if (!ts->rd) + goto out_free_ts; + if (!(ts->rd->f_mode & FMODE_READ)) + goto out_put_rd; ts->wr = fget(wfd); - if (!ts->rd || !ts->wr) { - if (ts->rd) - fput(ts->rd); - if (ts->wr) - fput(ts->wr); - kfree(ts); - return -EIO; - } + if (!ts->wr) + goto out_put_rd; + if (!(ts->wr->f_mode & FMODE_WRITE)) + goto out_put_wr; client->trans = ts; client->status = Connected; return 0; + +out_put_wr: + fput(ts->wr); +out_put_rd: + fput(ts->rd); +out_free_ts: + kfree(ts); + return -EIO; } static int p9_socket_open(struct p9_client *client, struct socket *csocket) diff --git a/net/Kconfig b/net/Kconfig index d122f53c6fa2..539f08416ccf 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -52,6 +52,9 @@ config NET_INGRESS config NET_EGRESS bool +config NET_REDIRECT + bool + config SKB_EXTENSIONS bool diff --git a/net/appletalk/atalk_proc.c b/net/appletalk/atalk_proc.c index 550c6ca007cc..9c1241292d1d 100644 --- a/net/appletalk/atalk_proc.c +++ b/net/appletalk/atalk_proc.c @@ -229,6 +229,8 @@ int __init atalk_proc_init(void) sizeof(struct aarp_iter_state), NULL)) goto out; + return 0; + out: remove_proc_subtree("atalk", init_net.proc_net); return -ENOMEM; diff --git a/net/atm/common.c b/net/atm/common.c index b7528e77997c..0ce530af534d 100644 --- a/net/atm/common.c +++ b/net/atm/common.c @@ -668,7 +668,7 @@ __poll_t vcc_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* writable? */ diff --git a/net/ax25/af_ax25.c b/net/ax25/af_ax25.c index bb222b882b67..2fdb1b573e8c 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -635,8 +635,10 @@ static int ax25_setsockopt(struct socket *sock, int level, int optname, break; case SO_BINDTODEVICE: - if (optlen > IFNAMSIZ) - optlen = IFNAMSIZ; + if (optlen > IFNAMSIZ - 1) + optlen = IFNAMSIZ - 1; + + memset(devname, 0, sizeof(devname)); if (copy_from_user(devname, optval, optlen)) { res = -EFAULT; @@ -1185,7 +1187,10 @@ static int __must_check ax25_connect(struct socket *sock, if (addr_len > sizeof(struct sockaddr_ax25) && fsa->fsa_ax25.sax25_ndigis != 0) { /* Valid number of digipeaters ? */ - if (fsa->fsa_ax25.sax25_ndigis < 1 || fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS) { + if (fsa->fsa_ax25.sax25_ndigis < 1 || + fsa->fsa_ax25.sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * fsa->fsa_ax25.sax25_ndigis) { err = -EINVAL; goto out_release; } @@ -1505,7 +1510,10 @@ static int ax25_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) struct full_sockaddr_ax25 *fsa = (struct full_sockaddr_ax25 *)usax; /* Valid number of digipeaters ? */ - if (usax->sax25_ndigis < 1 || usax->sax25_ndigis > AX25_MAX_DIGIS) { + if (usax->sax25_ndigis < 1 || + usax->sax25_ndigis > AX25_MAX_DIGIS || + addr_len < sizeof(struct sockaddr_ax25) + + sizeof(ax25_address) * usax->sax25_ndigis) { err = -EINVAL; goto out; } diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index d78938e3e008..d88a4de02237 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -22,6 +22,8 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/lockdep.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/netlink.h> #include <linux/pkt_sched.h> @@ -193,14 +195,18 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) unsigned char *ogm_buff; u32 random_seqno; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + /* randomize initial seqno to avoid collision */ get_random_bytes(&random_seqno, sizeof(random_seqno)); atomic_set(&hard_iface->bat_iv.ogm_seqno, random_seqno); hard_iface->bat_iv.ogm_buff_len = BATADV_OGM_HLEN; ogm_buff = kmalloc(hard_iface->bat_iv.ogm_buff_len, GFP_ATOMIC); - if (!ogm_buff) + if (!ogm_buff) { + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); return -ENOMEM; + } hard_iface->bat_iv.ogm_buff = ogm_buff; @@ -212,35 +218,59 @@ static int batadv_iv_ogm_iface_enable(struct batadv_hard_iface *hard_iface) batadv_ogm_packet->reserved = 0; batadv_ogm_packet->tq = BATADV_TQ_MAX_VALUE; + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); + return 0; } static void batadv_iv_ogm_iface_disable(struct batadv_hard_iface *hard_iface) { + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + kfree(hard_iface->bat_iv.ogm_buff); hard_iface->bat_iv.ogm_buff = NULL; + + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_iface_update_mac(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; ether_addr_copy(batadv_ogm_packet->orig, hard_iface->net_dev->dev_addr); ether_addr_copy(batadv_ogm_packet->prev_sender, hard_iface->net_dev->dev_addr); + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } static void batadv_iv_ogm_primary_iface_set(struct batadv_hard_iface *hard_iface) { struct batadv_ogm_packet *batadv_ogm_packet; - unsigned char *ogm_buff = hard_iface->bat_iv.ogm_buff; + void *ogm_buff; - batadv_ogm_packet = (struct batadv_ogm_packet *)ogm_buff; + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + + ogm_buff = hard_iface->bat_iv.ogm_buff; + if (!ogm_buff) + goto unlock; + + batadv_ogm_packet = ogm_buff; batadv_ogm_packet->ttl = BATADV_TTL; + +unlock: + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); } /* when do we schedule our own ogm to be sent */ @@ -742,7 +772,11 @@ batadv_iv_ogm_slide_own_bcast_window(struct batadv_hard_iface *hard_iface) } } -static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +/** + * batadv_iv_ogm_schedule_buff() - schedule submission of hardif ogm buffer + * @hard_iface: interface whose ogm buffer should be transmitted + */ +static void batadv_iv_ogm_schedule_buff(struct batadv_hard_iface *hard_iface) { struct batadv_priv *bat_priv = netdev_priv(hard_iface->soft_iface); unsigned char **ogm_buff = &hard_iface->bat_iv.ogm_buff; @@ -753,8 +787,10 @@ static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) u16 tvlv_len = 0; unsigned long send_time; - if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || - hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + lockdep_assert_held(&hard_iface->bat_iv.ogm_buff_mutex); + + /* interface already disabled by batadv_iv_ogm_iface_disable */ + if (!*ogm_buff) return; /* the interface gets activated here to avoid race conditions between @@ -823,6 +859,17 @@ out: batadv_hardif_put(primary_if); } +static void batadv_iv_ogm_schedule(struct batadv_hard_iface *hard_iface) +{ + if (hard_iface->if_status == BATADV_IF_NOT_IN_USE || + hard_iface->if_status == BATADV_IF_TO_BE_REMOVED) + return; + + mutex_lock(&hard_iface->bat_iv.ogm_buff_mutex); + batadv_iv_ogm_schedule_buff(hard_iface); + mutex_unlock(&hard_iface->bat_iv.ogm_buff_mutex); +} + /** * batadv_iv_orig_ifinfo_sum() - Get bcast_own sum for originator over iterface * @orig_node: originator which reproadcasted the OGMs directly diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2614a9caee00..a39af0eefad3 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -120,20 +120,7 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) rtnl_lock(); ret = __ethtool_get_link_ksettings(hard_iface->net_dev, &link_settings); rtnl_unlock(); - - /* Virtual interface drivers such as tun / tap interfaces, VLAN, etc - * tend to initialize the interface throughput with some value for the - * sake of having a throughput number to export via ethtool. This - * exported throughput leaves batman-adv to conclude the interface - * throughput is genuine (reflecting reality), thus no measurements - * are necessary. - * - * Based on the observation that those interface types also tend to set - * the link auto-negotiation to 'off', batman-adv shall check this - * setting to differentiate between genuine link throughput information - * and placeholders installed by virtual interfaces. - */ - if (ret == 0 && link_settings.base.autoneg == AUTONEG_ENABLE) { + if (ret == 0) { /* link characteristics might change over time */ if (link_settings.base.duplex == DUPLEX_FULL) hard_iface->bat_v.flags |= BATADV_FULL_DUPLEX; diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index bc06e3cdfa84..47d7a4f267cd 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -703,7 +703,7 @@ static void batadv_v_ogm_process(const struct sk_buff *skb, int ogm_offset, orig_node = batadv_v_ogm_orig_get(bat_priv, ogm_packet->orig); if (!orig_node) - return; + goto out; neigh_node = batadv_neigh_node_get_or_create(orig_node, if_incoming, ethhdr->h_source); diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b0af3a11d406..ec7bf5a4a9fc 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -285,6 +285,7 @@ static u32 batadv_hash_dat(const void *data, u32 size) u32 hash = 0; const struct batadv_dat_entry *dat = data; const unsigned char *key; + __be16 vid; u32 i; key = (const unsigned char *)&dat->ip; @@ -294,7 +295,8 @@ static u32 batadv_hash_dat(const void *data, u32 size) hash ^= (hash >> 6); } - key = (const unsigned char *)&dat->vid; + vid = htons(dat->vid); + key = (__force const unsigned char *)&vid; for (i = 0; i < sizeof(dat->vid); i++) { hash += key[i]; hash += (hash << 10); diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 3719cfd026f0..62b926dd4aae 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -17,6 +17,7 @@ #include <linux/kernel.h> #include <linux/kref.h> #include <linux/list.h> +#include <linux/mutex.h> #include <linux/netdevice.h> #include <linux/printk.h> #include <linux/rculist.h> @@ -930,6 +931,7 @@ batadv_hardif_add_interface(struct net_device *net_dev) INIT_LIST_HEAD(&hard_iface->list); INIT_HLIST_HEAD(&hard_iface->neigh_list); + mutex_init(&hard_iface->bat_iv.ogm_buff_mutex); spin_lock_init(&hard_iface->neigh_list_lock); kref_init(&hard_iface->refcount); diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index c5e7906045f3..b7f3d9ef83cf 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1009,15 +1009,8 @@ static struct batadv_nc_path *batadv_nc_get_path(struct batadv_priv *bat_priv, */ static u8 batadv_nc_random_weight_tq(u8 tq) { - u8 rand_val, rand_tq; - - get_random_bytes(&rand_val, sizeof(rand_val)); - /* randomize the estimated packet loss (max TQ - estimated TQ) */ - rand_tq = rand_val * (BATADV_TQ_MAX_VALUE - tq); - - /* normalize the randomized packet loss */ - rand_tq /= BATADV_TQ_MAX_VALUE; + u8 rand_tq = prandom_u32_max(BATADV_TQ_MAX_VALUE + 1 - tq); /* convert to (randomized) estimated tq again */ return BATADV_TQ_MAX_VALUE - rand_tq; diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 80fc3253c336..34e9948fbd45 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1149,7 +1149,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, ret = batadv_parse_throughput(net_dev, buff, "throughput_override", &tp_override); if (!ret) - return count; + goto out; old_tp_override = atomic_read(&hard_iface->bat_v.throughput_override); if (old_tp_override == tp_override) @@ -1189,6 +1189,7 @@ static ssize_t batadv_show_throughput_override(struct kobject *kobj, tp_override = atomic_read(&hard_iface->bat_v.throughput_override); + batadv_hardif_put(hard_iface); return sprintf(buff, "%u.%u MBit\n", tp_override / 10, tp_override % 10); } diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index e0b25104cbfa..64f448852132 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -79,6 +79,9 @@ struct batadv_hard_iface_bat_iv { /** @ogm_seqno: OGM sequence number - used to identify each OGM */ atomic_t ogm_seqno; + + /** @ogm_buff_mutex: lock protecting ogm_buff and ogm_buff_len */ + struct mutex ogm_buff_mutex; }; /** diff --git a/net/bluetooth/6lowpan.c b/net/bluetooth/6lowpan.c index 9001bf331d56..120529290d99 100644 --- a/net/bluetooth/6lowpan.c +++ b/net/bluetooth/6lowpan.c @@ -50,6 +50,7 @@ static bool enable_6lowpan; /* We are listening incoming connections via this channel */ static struct l2cap_chan *listen_chan; +static DEFINE_MUTEX(set_lock); struct lowpan_peer { struct list_head list; @@ -1075,12 +1076,14 @@ static void do_enable_set(struct work_struct *work) enable_6lowpan = set_enable->flag; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); } listen_chan = bt_6lowpan_listen(); + mutex_unlock(&set_lock); kfree(set_enable); } @@ -1132,11 +1135,13 @@ static ssize_t lowpan_control_write(struct file *fp, if (ret == -EINVAL) return ret; + mutex_lock(&set_lock); if (listen_chan) { l2cap_chan_close(listen_chan, 0); l2cap_chan_put(listen_chan); listen_chan = NULL; } + mutex_unlock(&set_lock); if (conn) { struct lowpan_peer *peer; diff --git a/net/bluetooth/af_bluetooth.c b/net/bluetooth/af_bluetooth.c index 94ddf19998c7..5f508c50649d 100644 --- a/net/bluetooth/af_bluetooth.c +++ b/net/bluetooth/af_bluetooth.c @@ -460,7 +460,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == BT_LISTEN) return bt_accept_poll(sk); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -470,7 +470,7 @@ __poll_t bt_sock_poll(struct file *file, struct socket *sock, if (sk->sk_shutdown == SHUTDOWN_MASK) mask |= EPOLLHUP; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == BT_CLOSED) diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 15d1cb5aee18..db735d0d931e 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -931,6 +931,14 @@ static void hci_req_directed_advertising(struct hci_request *req, return; memset(&cp, 0, sizeof(cp)); + + /* Some controllers might reject command if intervals are not + * within range for undirected advertising. + * BCM20702A0 is known to be affected by this. + */ + cp.min_interval = cpu_to_le16(0x0020); + cp.max_interval = cpu_to_le16(0x0020); + cp.type = LE_ADV_DIRECT_IND; cp.own_address_type = own_addr_type; cp.direct_addr_type = conn->dst_type; @@ -1165,8 +1173,10 @@ struct hci_conn *hci_connect_le_scan(struct hci_dev *hdev, bdaddr_t *dst, if (!conn) return ERR_PTR(-ENOMEM); - if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) + if (hci_explicit_conn_params_set(hdev, dst, dst_type) < 0) { + hci_conn_del(conn); return ERR_PTR(-EBUSY); + } conn->state = BT_CONNECT; set_bit(HCI_CONN_SCANNING, &conn->flags); diff --git a/net/bluetooth/hci_core.c b/net/bluetooth/hci_core.c index b81bf53c5ac4..90846751ce43 100644 --- a/net/bluetooth/hci_core.c +++ b/net/bluetooth/hci_core.c @@ -842,8 +842,8 @@ static int hci_init4_req(struct hci_request *req, unsigned long opt) if (hdev->le_features[0] & HCI_LE_DATA_LEN_EXT) { struct hci_cp_le_write_def_data_len cp; - cp.tx_len = hdev->le_max_tx_len; - cp.tx_time = hdev->le_max_tx_time; + cp.tx_len = cpu_to_le16(hdev->le_max_tx_len); + cp.tx_time = cpu_to_le16(hdev->le_max_tx_time); hci_req_add(req, HCI_OP_LE_WRITE_DEF_DATA_LEN, sizeof(cp), &cp); } @@ -1444,11 +1444,20 @@ static int hci_dev_do_open(struct hci_dev *hdev) if (hci_dev_test_flag(hdev, HCI_SETUP) || test_bit(HCI_QUIRK_NON_PERSISTENT_SETUP, &hdev->quirks)) { + bool invalid_bdaddr; + hci_sock_dev_event(hdev, HCI_DEV_SETUP); if (hdev->setup) ret = hdev->setup(hdev); + /* The transport driver can set the quirk to mark the + * BD_ADDR invalid before creating the HCI device or in + * its setup callback. + */ + invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR, + &hdev->quirks); + if (ret) goto setup_failed; @@ -1457,20 +1466,33 @@ static int hci_dev_do_open(struct hci_dev *hdev) hci_dev_get_bd_addr_from_property(hdev); if (bacmp(&hdev->public_addr, BDADDR_ANY) && - hdev->set_bdaddr) + hdev->set_bdaddr) { ret = hdev->set_bdaddr(hdev, &hdev->public_addr); + + /* If setting of the BD_ADDR from the device + * property succeeds, then treat the address + * as valid even if the invalid BD_ADDR + * quirk indicates otherwise. + */ + if (!ret) + invalid_bdaddr = false; + } } setup_failed: /* The transport driver can set these quirks before * creating the HCI device or in its setup callback. * + * For the invalid BD_ADDR quirk it is possible that + * it becomes a valid address if the bootloader does + * provide it (see above). + * * In case any of them is set, the controller has to * start up as unconfigured. */ if (test_bit(HCI_QUIRK_EXTERNAL_CONFIG, &hdev->quirks) || - test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks)) + invalid_bdaddr) hci_dev_set_flag(hdev, HCI_UNCONFIGURED); /* For an unconfigured controller it is required to @@ -4437,7 +4459,14 @@ static void hci_rx_work(struct work_struct *work) hci_send_to_sock(hdev, skb); } - if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL)) { + /* If the device has been opened in HCI_USER_CHANNEL, + * the userspace has exclusive access to device. + * When device is HCI_INIT, we still need to process + * the data packets to the driver in order + * to complete its setup(). + */ + if (hci_dev_test_flag(hdev, HCI_USER_CHANNEL) && + !test_bit(HCI_INIT, &hdev->flags)) { kfree_skb(skb); continue; } diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 9e4fcf406d9c..b323c65a4485 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -1229,6 +1229,9 @@ static void store_pending_adv_report(struct hci_dev *hdev, bdaddr_t *bdaddr, { struct discovery_state *d = &hdev->discovery; + if (len > HCI_MAX_AD_LENGTH) + return; + bacpy(&d->last_adv_addr, bdaddr); d->last_adv_addr_type = bdaddr_type; d->last_adv_rssi = rssi; @@ -2396,7 +2399,7 @@ static void hci_inquiry_result_evt(struct hci_dev *hdev, struct sk_buff *skb) BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -3992,6 +3995,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, struct inquiry_info_with_rssi_and_pscan_mode *info; info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4013,6 +4019,9 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } else { struct inquiry_info_with_rssi *info = (void *) (skb->data + 1); + if (skb->len < num_rsp * sizeof(*info) + 1) + goto unlock; + for (; num_rsp; num_rsp--, info++) { u32 flags; @@ -4033,6 +4042,7 @@ static void hci_inquiry_result_with_rssi_evt(struct hci_dev *hdev, } } +unlock: hci_dev_unlock(hdev); } @@ -4144,6 +4154,7 @@ static void hci_sync_conn_complete_evt(struct hci_dev *hdev, case 0x11: /* Unsupported Feature or Parameter Value */ case 0x1c: /* SCO interval rejected */ case 0x1a: /* Unsupported Remote Feature */ + case 0x1e: /* Invalid LMP Parameters */ case 0x1f: /* Unspecified error */ case 0x20: /* Unsupported LMP Parameter value */ if (conn->out) { @@ -4194,7 +4205,7 @@ static void hci_extended_inquiry_result_evt(struct hci_dev *hdev, BT_DBG("%s num_rsp %d", hdev->name, num_rsp); - if (!num_rsp) + if (!num_rsp || skb->len < num_rsp * sizeof(*info) + 1) return; if (hci_dev_test_flag(hdev, HCI_PERIODIC_INQ)) @@ -5158,7 +5169,8 @@ static struct hci_conn *check_pending_le_conn(struct hci_dev *hdev, static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, u8 bdaddr_type, bdaddr_t *direct_addr, - u8 direct_addr_type, s8 rssi, u8 *data, u8 len) + u8 direct_addr_type, s8 rssi, u8 *data, u8 len, + bool ext_adv) { struct discovery_state *d = &hdev->discovery; struct smp_irk *irk; @@ -5180,6 +5192,11 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } + if (!ext_adv && len > HCI_MAX_AD_LENGTH) { + bt_dev_err_ratelimited(hdev, "legacy adv larger than 31 bytes"); + return; + } + /* Find the end of the data in case the report contains padded zero * bytes at the end causing an invalid length value. * @@ -5239,7 +5256,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, */ conn = check_pending_le_conn(hdev, bdaddr, bdaddr_type, type, direct_addr); - if (conn && type == LE_ADV_IND) { + if (!ext_adv && conn && type == LE_ADV_IND && len <= HCI_MAX_AD_LENGTH) { /* Store report for later inclusion by * mgmt_device_connected */ @@ -5293,7 +5310,7 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, * event or send an immediate device found event if the data * should not be stored for later. */ - if (!has_pending_adv_report(hdev)) { + if (!ext_adv && !has_pending_adv_report(hdev)) { /* If the report will trigger a SCAN_REQ store it for * later merging. */ @@ -5328,7 +5345,8 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, /* If the new report will trigger a SCAN_REQ store it for * later merging. */ - if (type == LE_ADV_IND || type == LE_ADV_SCAN_IND) { + if (!ext_adv && (type == LE_ADV_IND || + type == LE_ADV_SCAN_IND)) { store_pending_adv_report(hdev, bdaddr, bdaddr_type, rssi, flags, data, len); return; @@ -5368,7 +5386,7 @@ static void hci_le_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) rssi = ev->data[ev->length]; process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, rssi, - ev->data, ev->length); + ev->data, ev->length, false); } else { bt_dev_err(hdev, "Dropping invalid advertising data"); } @@ -5442,7 +5460,8 @@ static void hci_le_ext_adv_report_evt(struct hci_dev *hdev, struct sk_buff *skb) if (legacy_evt_type != LE_ADV_INVALID) { process_adv_report(hdev, legacy_evt_type, &ev->bdaddr, ev->bdaddr_type, NULL, 0, ev->rssi, - ev->data, ev->length); + ev->data, ev->length, + !(evt_type & LE_EXT_ADV_LEGACY_PDU)); } ptr += sizeof(*ev) + ev->length; @@ -5640,7 +5659,8 @@ static void hci_le_direct_adv_report_evt(struct hci_dev *hdev, process_adv_report(hdev, ev->evt_type, &ev->bdaddr, ev->bdaddr_type, &ev->direct_addr, - ev->direct_addr_type, ev->rssi, NULL, 0); + ev->direct_addr_type, ev->rssi, NULL, 0, + false); ptr += sizeof(*ev); } diff --git a/net/bluetooth/hci_request.c b/net/bluetooth/hci_request.c index e9a95ed65491..367be6f02166 100644 --- a/net/bluetooth/hci_request.c +++ b/net/bluetooth/hci_request.c @@ -1258,6 +1258,14 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) instance_flags = get_adv_instance_flags(hdev, instance); + /* If instance already has the flags set skip adding it once + * again. + */ + if (adv_instance && eir_get_data(adv_instance->adv_data, + adv_instance->adv_data_len, EIR_FLAGS, + NULL)) + goto skip_flags; + /* The Add Advertising command allows userspace to set both the general * and limited discoverable flags. */ @@ -1290,6 +1298,7 @@ static u8 create_instance_adv_data(struct hci_dev *hdev, u8 instance, u8 *ptr) } } +skip_flags: if (adv_instance) { memcpy(ptr, adv_instance->adv_data, adv_instance->adv_data_len); diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index d32077b28433..8159b344deef 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -831,6 +831,8 @@ static int hci_sock_release(struct socket *sock) if (!sk) return 0; + lock_sock(sk); + switch (hci_pi(sk)->channel) { case HCI_CHANNEL_MONITOR: atomic_dec(&monitor_promisc); @@ -878,6 +880,7 @@ static int hci_sock_release(struct socket *sock) skb_queue_purge(&sk->sk_receive_queue); skb_queue_purge(&sk->sk_write_queue); + release_sock(sk); sock_put(sk); return 0; } diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index 771e3e17bb6a..2c8ff1854beb 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -4928,10 +4928,8 @@ void __l2cap_physical_cfm(struct l2cap_chan *chan, int result) BT_DBG("chan %p, result %d, local_amp_id %d, remote_amp_id %d", chan, result, local_amp_id, remote_amp_id); - if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) { - l2cap_chan_unlock(chan); + if (chan->state == BT_DISCONN || chan->state == BT_CLOSED) return; - } if (chan->state != BT_CONNECTED) { l2cap_do_create(chan, result, local_amp_id, remote_amp_id); diff --git a/net/bluetooth/rfcomm/tty.c b/net/bluetooth/rfcomm/tty.c index 0c7d31c6c18c..a58584949a95 100644 --- a/net/bluetooth/rfcomm/tty.c +++ b/net/bluetooth/rfcomm/tty.c @@ -413,10 +413,8 @@ static int __rfcomm_create_dev(struct sock *sk, void __user *arg) dlc = rfcomm_dlc_exists(&req.src, &req.dst, req.channel); if (IS_ERR(dlc)) return PTR_ERR(dlc); - else if (dlc) { - rfcomm_dlc_put(dlc); + if (dlc) return -EBUSY; - } dlc = rfcomm_dlc_alloc(GFP_KERNEL); if (!dlc) return -ENOMEM; diff --git a/net/bridge/br_arp_nd_proxy.c b/net/bridge/br_arp_nd_proxy.c index 37908561a64b..b18cdf03edb3 100644 --- a/net/bridge/br_arp_nd_proxy.c +++ b/net/bridge/br_arp_nd_proxy.c @@ -276,6 +276,10 @@ static void br_nd_send(struct net_bridge *br, struct net_bridge_port *p, ns_olen = request->len - (skb_network_offset(request) + sizeof(struct ipv6hdr)) - sizeof(*ns); for (i = 0; i < ns_olen - 1; i += (ns->opt[i + 1] << 3)) { + if (!ns->opt[i + 1]) { + kfree_skb(reply); + return; + } if (ns->opt[i] == ND_OPT_SOURCE_LL_ADDR) { daddr = ns->opt + i + sizeof(struct nd_opt_hdr); break; diff --git a/net/bridge/br_device.c b/net/bridge/br_device.c index c05def8fd9cd..82f9400a4d69 100644 --- a/net/bridge/br_device.c +++ b/net/bridge/br_device.c @@ -252,6 +252,12 @@ static int br_set_mac_address(struct net_device *dev, void *p) if (!is_valid_ether_addr(addr->sa_data)) return -EADDRNOTAVAIL; + /* dev_set_mac_addr() can be called by a master device on bridge's + * NETDEV_UNREGISTER, but since it's being destroyed do nothing + */ + if (dev->reg_state != NETREG_REGISTERED) + return -EBUSY; + spin_lock_bh(&br->lock); if (!ether_addr_equal(dev->dev_addr, addr->sa_data)) { /* Mac address will be changed in br_stp_change_bridge_id(). */ diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index f8cac3702712..9e3e46bbb06e 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -991,7 +991,7 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); if (skb_transport_offset(skb) + ipv6_transport_len(skb) < - nsrcs_offset + sizeof(_nsrcs)) + nsrcs_offset + sizeof(__nsrcs)) return -EINVAL; _nsrcs = skb_header_pointer(skb, nsrcs_offset, diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index 34fa72c72ad8..4aa30ad782bd 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -630,6 +630,9 @@ static unsigned int br_nf_forward_arp(void *priv, nf_bridge_pull_encap_header(skb); } + if (unlikely(!pskb_may_pull(skb, sizeof(struct arphdr)))) + return NF_DROP; + if (arp_hdr(skb)->ar_pln != 4) { if (IS_VLAN_ARP(skb)) nf_bridge_push_encap_header(skb); diff --git a/net/bridge/br_nf_core.c b/net/bridge/br_nf_core.c index 2cdfc5d6c25d..8c69f0c95a8e 100644 --- a/net/bridge/br_nf_core.c +++ b/net/bridge/br_nf_core.c @@ -22,7 +22,8 @@ #endif static void fake_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index 9564a953bdf9..a36a3ba20460 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -207,8 +207,8 @@ struct net_bridge_port_group { struct rcu_head rcu; struct timer_list timer; struct br_ip addr; + unsigned char eth_addr[ETH_ALEN] __aligned(2); unsigned char flags; - unsigned char eth_addr[ETH_ALEN]; }; struct net_bridge_mdb_entry { diff --git a/net/bridge/netfilter/ebt_dnat.c b/net/bridge/netfilter/ebt_dnat.c index eeae23a73c6a..d448846111e7 100644 --- a/net/bridge/netfilter/ebt_dnat.c +++ b/net/bridge/netfilter/ebt_dnat.c @@ -20,7 +20,6 @@ static unsigned int ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct ebt_nat_info *info = par->targinfo; - struct net_device *dev; if (!skb_make_writable(skb, 0)) return EBT_DROP; @@ -33,10 +32,22 @@ ebt_dnat_tg(struct sk_buff *skb, const struct xt_action_param *par) else skb->pkt_type = PACKET_MULTICAST; } else { - if (xt_hooknum(par) != NF_BR_BROUTING) - dev = br_port_get_rcu(xt_in(par))->br->dev; - else + const struct net_device *dev; + + switch (xt_hooknum(par)) { + case NF_BR_BROUTING: dev = xt_in(par); + break; + case NF_BR_PRE_ROUTING: + dev = br_port_get_rcu(xt_in(par))->br->dev; + break; + default: + dev = NULL; + break; + } + + if (!dev) /* NF_BR_LOCAL_OUT */ + return info->target; if (ether_addr_equal(info->mac, dev->dev_addr)) skb->pkt_type = PACKET_HOST; diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 4096d8a74a2b..e1256e03a9a8 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -1867,7 +1867,7 @@ static int ebt_buf_count(struct ebt_entries_buf_state *state, unsigned int sz) } static int ebt_buf_add(struct ebt_entries_buf_state *state, - void *data, unsigned int sz) + const void *data, unsigned int sz) { if (state->buf_kern_start == NULL) goto count_only; @@ -1901,7 +1901,7 @@ enum compat_mwt { EBT_COMPAT_TARGET, }; -static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, +static int compat_mtw_from_user(const struct compat_ebt_entry_mwt *mwt, enum compat_mwt compat_mwt, struct ebt_entries_buf_state *state, const unsigned char *base) @@ -1979,22 +1979,23 @@ static int compat_mtw_from_user(struct compat_ebt_entry_mwt *mwt, /* return size of all matches, watchers or target, including necessary * alignment and padding. */ -static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, +static int ebt_size_mwt(const struct compat_ebt_entry_mwt *match32, unsigned int size_left, enum compat_mwt type, struct ebt_entries_buf_state *state, const void *base) { + const char *buf = (const char *)match32; int growth = 0; - char *buf; if (size_left == 0) return 0; - buf = (char *) match32; - - while (size_left >= sizeof(*match32)) { + do { struct ebt_entry_match *match_kern; int ret; + if (size_left < sizeof(*match32)) + return -EINVAL; + match_kern = (struct ebt_entry_match *) state->buf_kern_start; if (match_kern) { char *tmp; @@ -2031,22 +2032,18 @@ static int ebt_size_mwt(struct compat_ebt_entry_mwt *match32, if (match_kern) match_kern->match_size = ret; - /* rule should have no remaining data after target */ - if (type == EBT_COMPAT_TARGET && size_left) - return -EINVAL; - match32 = (struct compat_ebt_entry_mwt *) buf; - } + } while (size_left); return growth; } /* called for all ebt_entry structures. */ -static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, +static int size_entry_mwt(const struct ebt_entry *entry, const unsigned char *base, unsigned int *total, struct ebt_entries_buf_state *state) { - unsigned int i, j, startoff, new_offset = 0; + unsigned int i, j, startoff, next_expected_off, new_offset = 0; /* stores match/watchers/targets & offset of next struct ebt_entry: */ unsigned int offsets[4]; unsigned int *offsets_update = NULL; @@ -2132,11 +2129,13 @@ static int size_entry_mwt(struct ebt_entry *entry, const unsigned char *base, return ret; } - startoff = state->buf_user_offset - startoff; + next_expected_off = state->buf_user_offset - startoff; + if (next_expected_off != entry->next_offset) + return -EINVAL; - if (WARN_ON(*total < startoff)) + if (*total < entry->next_offset) return -EINVAL; - *total -= startoff; + *total -= entry->next_offset; return 0; } diff --git a/net/bridge/netfilter/nft_reject_bridge.c b/net/bridge/netfilter/nft_reject_bridge.c index b325b569e761..f48cf4cfb80f 100644 --- a/net/bridge/netfilter/nft_reject_bridge.c +++ b/net/bridge/netfilter/nft_reject_bridge.c @@ -31,6 +31,12 @@ static void nft_reject_br_push_etherhdr(struct sk_buff *oldskb, ether_addr_copy(eth->h_dest, eth_hdr(oldskb)->h_source); eth->h_proto = eth_hdr(oldskb)->h_proto; skb_pull(nskb, ETH_HLEN); + + if (skb_vlan_tag_present(oldskb)) { + u16 vid = skb_vlan_tag_get(oldskb); + + __vlan_hwaccel_put_tag(nskb, oldskb->vlan_proto, vid); + } } static int nft_bridge_iphdr_validate(struct sk_buff *skb) diff --git a/net/caif/caif_socket.c b/net/caif/caif_socket.c index 13ea920600ae..ef14da50a981 100644 --- a/net/caif/caif_socket.c +++ b/net/caif/caif_socket.c @@ -953,7 +953,7 @@ static __poll_t caif_poll(struct file *file, mask |= EPOLLRDHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) mask |= EPOLLIN | EPOLLRDNORM; diff --git a/net/ceph/messenger.c b/net/ceph/messenger.c index cd0b094468b6..f207eb7aabce 100644 --- a/net/ceph/messenger.c +++ b/net/ceph/messenger.c @@ -3241,12 +3241,16 @@ static struct ceph_msg_data *ceph_msg_data_add(struct ceph_msg *msg) static void ceph_msg_data_destroy(struct ceph_msg_data *data) { - if (data->type == CEPH_MSG_DATA_PAGELIST) + if (data->type == CEPH_MSG_DATA_PAGES && data->own_pages) { + int num_pages = calc_pages_for(data->alignment, data->length); + ceph_release_page_vector(data->pages, num_pages); + } else if (data->type == CEPH_MSG_DATA_PAGELIST) { ceph_pagelist_release(data->pagelist); + } } void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, - size_t length, size_t alignment) + size_t length, size_t alignment, bool own_pages) { struct ceph_msg_data *data; @@ -3258,6 +3262,7 @@ void ceph_msg_data_add_pages(struct ceph_msg *msg, struct page **pages, data->pages = pages; data->length = length; data->alignment = alignment & ~PAGE_MASK; + data->own_pages = own_pages; msg->data_length += length; } diff --git a/net/ceph/osd_client.c b/net/ceph/osd_client.c index 565ea889673c..bb85787f9237 100644 --- a/net/ceph/osd_client.c +++ b/net/ceph/osd_client.c @@ -453,6 +453,7 @@ static void target_copy(struct ceph_osd_request_target *dest, dest->size = src->size; dest->min_size = src->min_size; dest->sort_bitwise = src->sort_bitwise; + dest->recovery_deletes = src->recovery_deletes; dest->flags = src->flags; dest->paused = src->paused; @@ -953,7 +954,7 @@ static void ceph_osdc_msg_data_add(struct ceph_msg *msg, BUG_ON(length > (u64) SIZE_MAX); if (length) ceph_msg_data_add_pages(msg, osd_data->pages, - length, osd_data->alignment); + length, osd_data->alignment, false); } else if (osd_data->type == CEPH_OSD_DATA_TYPE_PAGELIST) { BUG_ON(!length); ceph_msg_data_add_pagelist(msg, osd_data->pagelist); @@ -3636,7 +3637,9 @@ static void handle_reply(struct ceph_osd *osd, struct ceph_msg *msg) * supported. */ req->r_t.target_oloc.pool = m.redirect.oloc.pool; - req->r_flags |= CEPH_OSD_FLAG_REDIRECTED; + req->r_flags |= CEPH_OSD_FLAG_REDIRECTED | + CEPH_OSD_FLAG_IGNORE_OVERLAY | + CEPH_OSD_FLAG_IGNORE_CACHE; req->r_tid = 0; __submit_request(req, false); goto out_unlock_osdc; @@ -4421,9 +4424,7 @@ static void handle_watch_notify(struct ceph_osd_client *osdc, CEPH_MSG_DATA_PAGES); *lreq->preply_pages = data->pages; *lreq->preply_len = data->length; - } else { - ceph_release_page_vector(data->pages, - calc_pages_for(0, data->length)); + data->own_pages = false; } } lreq->notify_finish_error = return_code; @@ -5461,9 +5462,6 @@ out_unlock_osdc: return m; } -/* - * TODO: switch to a msg-owned pagelist - */ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) { struct ceph_msg *m; @@ -5477,7 +5475,6 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) if (data_len) { struct page **pages; - struct ceph_osd_data osd_data; pages = ceph_alloc_page_vector(calc_pages_for(0, data_len), GFP_NOIO); @@ -5486,9 +5483,7 @@ static struct ceph_msg *alloc_msg_with_page_vector(struct ceph_msg_header *hdr) return NULL; } - ceph_osd_data_pages_init(&osd_data, pages, data_len, 0, false, - false); - ceph_osdc_msg_data_add(m, &osd_data); + ceph_msg_data_add_pages(m, pages, data_len, 0, true); } return m; diff --git a/net/ceph/osdmap.c b/net/ceph/osdmap.c index 48a31dc9161c..f6a366eb8aa5 100644 --- a/net/ceph/osdmap.c +++ b/net/ceph/osdmap.c @@ -710,6 +710,15 @@ int ceph_pg_poolid_by_name(struct ceph_osdmap *map, const char *name) } EXPORT_SYMBOL(ceph_pg_poolid_by_name); +u64 ceph_pg_pool_flags(struct ceph_osdmap *map, u64 id) +{ + struct ceph_pg_pool_info *pi; + + pi = __lookup_pg_pool(&map->pg_pools, id); + return pi ? pi->flags : 0; +} +EXPORT_SYMBOL(ceph_pg_pool_flags); + static void __remove_pg_pool(struct rb_root *root, struct ceph_pg_pool_info *pi) { rb_erase(&pi->node, root); diff --git a/net/compat.c b/net/compat.c index 3f9ce609397f..24906536870f 100644 --- a/net/compat.c +++ b/net/compat.c @@ -290,6 +290,7 @@ void scm_detach_fds_compat(struct msghdr *kmsg, struct scm_cookie *scm) break; } /* Bump the usage count and install the file. */ + __receive_sock(fp[i]); fd_install(new_fd, get_file(fp[i])); } diff --git a/net/core/bpf_sk_storage.c b/net/core/bpf_sk_storage.c index d1c4e1f3be2c..e013639b23c7 100644 --- a/net/core/bpf_sk_storage.c +++ b/net/core/bpf_sk_storage.c @@ -633,9 +633,10 @@ static struct bpf_map *bpf_sk_storage_map_alloc(union bpf_attr *attr) return ERR_PTR(-ENOMEM); bpf_map_init_from_attr(&smap->map, attr); + nbuckets = roundup_pow_of_two(num_possible_cpus()); /* Use at least 2 buckets, select_bucket() is undefined behavior with 1 bucket */ - smap->bucket_log = max_t(u32, 1, ilog2(roundup_pow_of_two(num_possible_cpus()))); - nbuckets = 1U << smap->bucket_log; + nbuckets = max_t(u32, 2, nbuckets); + smap->bucket_log = ilog2(nbuckets); smap->buckets = kvcalloc(sizeof(*smap->buckets), nbuckets, GFP_USER | __GFP_NOWARN); if (!smap->buckets) { diff --git a/net/core/datagram.c b/net/core/datagram.c index 45a162ef5e02..acb7d2b04a07 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -51,6 +51,7 @@ #include <linux/slab.h> #include <linux/pagemap.h> #include <linux/uio.h> +#include <linux/indirect_call_wrapper.h> #include <net/protocol.h> #include <linux/skbuff.h> @@ -97,7 +98,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, if (error) goto out_err; - if (sk->sk_receive_queue.prev != skb) + if (READ_ONCE(sk->sk_receive_queue.prev) != skb) goto out; /* Socket shut down? */ @@ -278,7 +279,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (sk->sk_receive_queue.prev != *last); + } while (READ_ONCE(sk->sk_receive_queue.prev) != *last); error = -EAGAIN; @@ -407,6 +408,11 @@ int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags) } EXPORT_SYMBOL(skb_kill_datagram); +INDIRECT_CALLABLE_DECLARE(static size_t simple_copy_to_iter(const void *addr, + size_t bytes, + void *data __always_unused, + struct iov_iter *i)); + static int __skb_datagram_iter(const struct sk_buff *skb, int offset, struct iov_iter *to, int len, bool fault_short, size_t (*cb)(const void *, size_t, void *, @@ -420,7 +426,8 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, if (copy > 0) { if (copy > len) copy = len; - n = cb(skb->data + offset, copy, data, to); + n = INDIRECT_CALL_1(cb, simple_copy_to_iter, + skb->data + offset, copy, data, to); offset += n; if (n != copy) goto short_copy; @@ -442,8 +449,9 @@ static int __skb_datagram_iter(const struct sk_buff *skb, int offset, if (copy > len) copy = len; - n = cb(vaddr + frag->page_offset + - offset - start, copy, data, to); + n = INDIRECT_CALL_1(cb, simple_copy_to_iter, + vaddr + frag->page_offset + offset - start, + copy, data, to); kunmap(page); offset += n; if (n != copy) @@ -640,7 +648,7 @@ int __zerocopy_sg_from_iter(struct sock *sk, struct sk_buff *skb, skb->len += copied; skb->truesize += truesize; if (sk && sk->sk_type == SOCK_STREAM) { - sk->sk_wmem_queued += truesize; + sk_wmem_queued_add(sk, truesize); sk_mem_charge(sk, truesize); } else { refcount_add(truesize, &skb->sk->sk_wmem_alloc); @@ -767,7 +775,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -777,7 +785,7 @@ __poll_t datagram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ diff --git a/net/core/dev.c b/net/core/dev.c index 828ecca03c07..cff7f1d91bf3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -79,6 +79,7 @@ #include <linux/sched.h> #include <linux/sched/mm.h> #include <linux/mutex.h> +#include <linux/rwsem.h> #include <linux/string.h> #include <linux/mm.h> #include <linux/socket.h> @@ -194,7 +195,7 @@ static DEFINE_SPINLOCK(napi_hash_lock); static unsigned int napi_gen_id = NR_CPUS; static DEFINE_READ_MOSTLY_HASHTABLE(napi_hash, 8); -static seqcount_t devnet_rename_seq; +static DECLARE_RWSEM(devnet_rename_sem); static inline void dev_base_seq_inc(struct net *net) { @@ -898,33 +899,28 @@ EXPORT_SYMBOL(dev_get_by_napi_id); * @net: network namespace * @name: a pointer to the buffer where the name will be stored. * @ifindex: the ifindex of the interface to get the name from. - * - * The use of raw_seqcount_begin() and cond_resched() before - * retrying is required as we want to give the writers a chance - * to complete when CONFIG_PREEMPT is not set. */ int netdev_get_name(struct net *net, char *name, int ifindex) { struct net_device *dev; - unsigned int seq; + int ret; -retry: - seq = raw_seqcount_begin(&devnet_rename_seq); + down_read(&devnet_rename_sem); rcu_read_lock(); + dev = dev_get_by_index_rcu(net, ifindex); if (!dev) { - rcu_read_unlock(); - return -ENODEV; + ret = -ENODEV; + goto out; } strcpy(name, dev->name); - rcu_read_unlock(); - if (read_seqcount_retry(&devnet_rename_seq, seq)) { - cond_resched(); - goto retry; - } - return 0; + ret = 0; +out: + rcu_read_unlock(); + up_read(&devnet_rename_sem); + return ret; } /** @@ -1197,10 +1193,10 @@ int dev_change_name(struct net_device *dev, const char *newname) likely(!(dev->priv_flags & IFF_LIVE_RENAME_OK))) return -EBUSY; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); if (strncmp(newname, dev->name, IFNAMSIZ) == 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return 0; } @@ -1208,7 +1204,7 @@ int dev_change_name(struct net_device *dev, const char *newname) err = dev_get_valid_name(net, dev, newname); if (err < 0) { - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return err; } @@ -1223,11 +1219,11 @@ rollback: if (ret) { memcpy(dev->name, oldname, IFNAMSIZ); dev->name_assign_type = old_assign_type; - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); return ret; } - write_seqcount_end(&devnet_rename_seq); + up_write(&devnet_rename_sem); netdev_adjacent_rename_links(dev, oldname); @@ -1248,7 +1244,7 @@ rollback: /* err >= 0 after dev_alloc_name() or stores the first errno */ if (err >= 0) { err = ret; - write_seqcount_begin(&devnet_rename_seq); + down_write(&devnet_rename_sem); memcpy(dev->name, oldname, IFNAMSIZ); memcpy(oldname, newname, IFNAMSIZ); dev->name_assign_type = old_assign_type; @@ -2877,6 +2873,8 @@ static u16 skb_tx_hash(const struct net_device *dev, if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); + if (hash >= qoffset) + hash -= qoffset; while (unlikely(hash >= qcount)) hash -= qcount; return hash + qoffset; @@ -3475,26 +3473,8 @@ static inline int __dev_xmit_skb(struct sk_buff *skb, struct Qdisc *q, qdisc_calculate_pkt_len(skb, q); if (q->flags & TCQ_F_NOLOCK) { - if ((q->flags & TCQ_F_CAN_BYPASS) && q->empty && - qdisc_run_begin(q)) { - if (unlikely(test_bit(__QDISC_STATE_DEACTIVATED, - &q->state))) { - __qdisc_drop(skb, &to_free); - rc = NET_XMIT_DROP; - goto end_run; - } - qdisc_bstats_cpu_update(q, skb); - - rc = NET_XMIT_SUCCESS; - if (sch_direct_xmit(skb, q, dev, txq, NULL, true)) - __qdisc_run(q); - -end_run: - qdisc_run_end(q); - } else { - rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; - qdisc_run(q); - } + rc = q->enqueue(skb, q, &to_free) & NET_XMIT_MASK; + qdisc_run(q); if (unlikely(to_free)) kfree_skb_list(to_free); @@ -3942,10 +3922,12 @@ int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) local_bh_disable(); + dev_xmit_recursion_inc(); HARD_TX_LOCK(dev, txq, smp_processor_id()); if (!netif_xmit_frozen_or_drv_stopped(txq)) ret = netdev_start_xmit(skb, dev, txq, false); HARD_TX_UNLOCK(dev, txq); + dev_xmit_recursion_dec(); local_bh_enable(); @@ -3969,7 +3951,8 @@ EXPORT_SYMBOL(netdev_max_backlog); int netdev_tstamp_prequeue __read_mostly = 1; int netdev_budget __read_mostly = 300; -unsigned int __read_mostly netdev_budget_usecs = 2000; +/* Must be at least 2 jiffes to guarantee 1 jiffy timeout */ +unsigned int __read_mostly netdev_budget_usecs = 2 * USEC_PER_SEC / HZ; int weight_p __read_mostly = 64; /* old backlog weight */ int dev_weight_rx_bias __read_mostly = 1; /* bias for backlog weight */ int dev_weight_tx_bias __read_mostly = 1; /* bias for output_queue quota */ @@ -4343,14 +4326,14 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, /* Reinjected packets coming from act_mirred or similar should * not get XDP generic processing. */ - if (skb_cloned(skb) || skb_is_tc_redirected(skb)) + if (skb_is_redirected(skb)) return XDP_PASS; /* XDP packets must be linear and must have sufficient headroom * of XDP_PACKET_HEADROOM bytes. This is the guarantee that also * native XDP provides, thus we need to do it here as well. */ - if (skb_is_nonlinear(skb) || + if (skb_cloned(skb) || skb_is_nonlinear(skb) || skb_headroom(skb) < XDP_PACKET_HEADROOM) { int hroom = XDP_PACKET_HEADROOM - skb_headroom(skb); int troom = skb->tail + skb->data_len - skb->end; @@ -4818,11 +4801,12 @@ static inline int nf_ingress(struct sk_buff *skb, struct packet_type **pt_prev, return 0; } -static int __netif_receive_skb_core(struct sk_buff *skb, bool pfmemalloc, +static int __netif_receive_skb_core(struct sk_buff **pskb, bool pfmemalloc, struct packet_type **ppt_prev) { struct packet_type *ptype, *pt_prev; rx_handler_func_t *rx_handler; + struct sk_buff *skb = *pskb; struct net_device *orig_dev; bool deliver_exact = false; int ret = NET_RX_DROP; @@ -4853,8 +4837,10 @@ another_round: ret2 = do_xdp_generic(rcu_dereference(skb->dev->xdp_prog), skb); preempt_enable(); - if (ret2 != XDP_PASS) - return NET_RX_DROP; + if (ret2 != XDP_PASS) { + ret = NET_RX_DROP; + goto out; + } skb_reset_mac_len(skb); } @@ -4894,7 +4880,7 @@ skip_taps: goto out; } #endif - skb_reset_tc(skb); + skb_reset_redirect(skb); skip_classify: if (pfmemalloc && !skb_pfmemalloc_protocol(skb)) goto drop; @@ -5004,6 +4990,13 @@ drop: } out: + /* The invariant here is that if *ppt_prev is not NULL + * then skb should also be non-NULL. + * + * Apparently *ppt_prev assignment above holds this invariant due to + * skb dereferencing near it. + */ + *pskb = skb; return ret; } @@ -5013,7 +5006,7 @@ static int __netif_receive_skb_one_core(struct sk_buff *skb, bool pfmemalloc) struct packet_type *pt_prev = NULL; int ret; - ret = __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); + ret = __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (pt_prev) ret = INDIRECT_CALL_INET(pt_prev->func, ipv6_rcv, ip_rcv, skb, skb->dev, pt_prev, orig_dev); @@ -5091,7 +5084,7 @@ static void __netif_receive_skb_list_core(struct list_head *head, bool pfmemallo struct packet_type *pt_prev = NULL; skb_list_del_init(skb); - __netif_receive_skb_core(skb, pfmemalloc, &pt_prev); + __netif_receive_skb_core(&skb, pfmemalloc, &pt_prev); if (!pt_prev) continue; if (pt_curr != pt_prev || od_curr != orig_dev) { @@ -5326,7 +5319,7 @@ static void flush_backlog(struct work_struct *work) skb_queue_walk_safe(&sd->input_pkt_queue, skb, tmp) { if (skb->dev->reg_state == NETREG_UNREGISTERING) { __skb_unlink(skb, &sd->input_pkt_queue); - kfree_skb(skb); + dev_kfree_skb_irq(skb); input_queue_head_incr(sd); } } @@ -6616,6 +6609,21 @@ struct net_device *netdev_upper_get_next_dev_rcu(struct net_device *dev, } EXPORT_SYMBOL(netdev_upper_get_next_dev_rcu); +static struct net_device *netdev_next_upper_dev(struct net_device *dev, + struct list_head **iter) +{ + struct netdev_adjacent *upper; + + upper = list_entry((*iter)->next, struct netdev_adjacent, list); + + if (&upper->list == &dev->adj_list.upper) + return NULL; + + *iter = &upper->list; + + return upper->dev; +} + static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, struct list_head **iter) { @@ -6633,28 +6641,93 @@ static struct net_device *netdev_next_upper_dev_rcu(struct net_device *dev, return upper->dev; } +static int netdev_walk_all_upper_dev(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.upper; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; + } + + return 0; +} + int netdev_walk_all_upper_dev_rcu(struct net_device *dev, int (*fn)(struct net_device *dev, void *data), void *data) { - struct net_device *udev; - struct list_head *iter; - int ret; + struct net_device *udev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.upper, - udev = netdev_next_upper_dev_rcu(dev, &iter); - udev; - udev = netdev_next_upper_dev_rcu(dev, &iter)) { - /* first is the upper device itself */ - ret = fn(udev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.upper; - /* then look at all of its upper devices */ - ret = netdev_walk_all_upper_dev_rcu(udev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + udev = netdev_next_upper_dev_rcu(now, &iter); + if (!udev) + break; + + next = udev; + niter = &udev->adj_list.upper; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -6762,31 +6835,50 @@ int netdev_walk_all_lower_dev(struct net_device *dev, void *data), void *data) { - struct net_device *ldev; - struct list_head *iter; - int ret; + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; - for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev(dev, &iter); - ldev; - ldev = netdev_next_lower_dev(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + now = dev; + iter = &dev->adj_list.lower; - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev(ldev, fn, data); - if (ret) - return ret; + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; } EXPORT_SYMBOL_GPL(netdev_walk_all_lower_dev); -static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, - struct list_head **iter) +struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, + struct list_head **iter) { struct netdev_adjacent *lower; @@ -6798,29 +6890,95 @@ static struct net_device *netdev_next_lower_dev_rcu(struct net_device *dev, return lower->dev; } +EXPORT_SYMBOL(netdev_next_lower_dev_rcu); -int netdev_walk_all_lower_dev_rcu(struct net_device *dev, - int (*fn)(struct net_device *dev, - void *data), - void *data) +static u8 __netdev_upper_depth(struct net_device *dev) +{ + struct net_device *udev; + struct list_head *iter; + u8 max_depth = 0; + + for (iter = &dev->adj_list.upper, + udev = netdev_next_upper_dev(dev, &iter); + udev; + udev = netdev_next_upper_dev(dev, &iter)) { + if (max_depth < udev->upper_level) + max_depth = udev->upper_level; + } + + return max_depth; +} + +static u8 __netdev_lower_depth(struct net_device *dev) { struct net_device *ldev; struct list_head *iter; - int ret; + u8 max_depth = 0; for (iter = &dev->adj_list.lower, - ldev = netdev_next_lower_dev_rcu(dev, &iter); + ldev = netdev_next_lower_dev(dev, &iter); ldev; - ldev = netdev_next_lower_dev_rcu(dev, &iter)) { - /* first is the lower device itself */ - ret = fn(ldev, data); - if (ret) - return ret; + ldev = netdev_next_lower_dev(dev, &iter)) { + if (max_depth < ldev->lower_level) + max_depth = ldev->lower_level; + } - /* then look at all of its lower devices */ - ret = netdev_walk_all_lower_dev_rcu(ldev, fn, data); - if (ret) - return ret; + return max_depth; +} + +static int __netdev_update_upper_level(struct net_device *dev, void *data) +{ + dev->upper_level = __netdev_upper_depth(dev) + 1; + return 0; +} + +static int __netdev_update_lower_level(struct net_device *dev, void *data) +{ + dev->lower_level = __netdev_lower_depth(dev) + 1; + return 0; +} + +int netdev_walk_all_lower_dev_rcu(struct net_device *dev, + int (*fn)(struct net_device *dev, + void *data), + void *data) +{ + struct net_device *ldev, *next, *now, *dev_stack[MAX_NEST_DEV + 1]; + struct list_head *niter, *iter, *iter_stack[MAX_NEST_DEV + 1]; + int ret, cur = 0; + + now = dev; + iter = &dev->adj_list.lower; + + while (1) { + if (now != dev) { + ret = fn(now, data); + if (ret) + return ret; + } + + next = NULL; + while (1) { + ldev = netdev_next_lower_dev_rcu(now, &iter); + if (!ldev) + break; + + next = ldev; + niter = &ldev->adj_list.lower; + dev_stack[cur] = now; + iter_stack[cur++] = iter; + break; + } + + if (!next) { + if (!cur) + return 0; + next = dev_stack[--cur]; + niter = iter_stack[cur]; + } + + now = next; + iter = niter; } return 0; @@ -7077,6 +7235,9 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (netdev_has_upper_dev(upper_dev, dev)) return -EBUSY; + if ((dev->lower_level + upper_dev->upper_level) > MAX_NEST_DEV) + return -EMLINK; + if (!master) { if (netdev_has_upper_dev(dev, upper_dev)) return -EEXIST; @@ -7103,6 +7264,12 @@ static int __netdev_upper_dev_link(struct net_device *dev, if (ret) goto rollback; + __netdev_update_upper_level(dev, NULL); + netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL); + return 0; rollback: @@ -7185,6 +7352,12 @@ void netdev_upper_dev_unlink(struct net_device *dev, call_netdevice_notifiers_info(NETDEV_CHANGEUPPER, &changeupper_info.info); + + __netdev_update_upper_level(dev, NULL); + netdev_walk_all_lower_dev(dev, __netdev_update_upper_level, NULL); + + __netdev_update_lower_level(upper_dev, NULL); + netdev_walk_all_upper_dev(upper_dev, __netdev_update_lower_level, NULL); } EXPORT_SYMBOL(netdev_upper_dev_unlink); @@ -7672,11 +7845,28 @@ int __dev_set_mtu(struct net_device *dev, int new_mtu) if (ops->ndo_change_mtu) return ops->ndo_change_mtu(dev, new_mtu); - dev->mtu = new_mtu; + /* Pairs with all the lockless reads of dev->mtu in the stack */ + WRITE_ONCE(dev->mtu, new_mtu); return 0; } EXPORT_SYMBOL(__dev_set_mtu); +int dev_validate_mtu(struct net_device *dev, int new_mtu, + struct netlink_ext_ack *extack) +{ + /* MTU must be positive, and in range */ + if (new_mtu < 0 || new_mtu < dev->min_mtu) { + NL_SET_ERR_MSG(extack, "mtu less than device minimum"); + return -EINVAL; + } + + if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { + NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); + return -EINVAL; + } + return 0; +} + /** * dev_set_mtu_ext - Change maximum transfer unit * @dev: device @@ -7693,16 +7883,9 @@ int dev_set_mtu_ext(struct net_device *dev, int new_mtu, if (new_mtu == dev->mtu) return 0; - /* MTU must be positive, and in range */ - if (new_mtu < 0 || new_mtu < dev->min_mtu) { - NL_SET_ERR_MSG(extack, "mtu less than device minimum"); - return -EINVAL; - } - - if (dev->max_mtu > 0 && new_mtu > dev->max_mtu) { - NL_SET_ERR_MSG(extack, "mtu greater than device maximum"); - return -EINVAL; - } + err = dev_validate_mtu(dev, new_mtu, extack); + if (err) + return err; if (!netif_device_present(dev)) return -ENODEV; @@ -8291,11 +8474,13 @@ static void netdev_sync_lower_features(struct net_device *upper, netdev_dbg(upper, "Disabling feature %pNF on lower dev %s.\n", &feature, lower->name); lower->wanted_features &= ~feature; - netdev_update_features(lower); + __netdev_update_features(lower); if (unlikely(lower->features & feature)) netdev_WARN(upper, "failed to disable %pNF on %s!\n", &feature, lower->name); + else + netdev_features_change(lower); } } } @@ -8740,8 +8925,10 @@ int register_netdevice(struct net_device *dev) goto err_uninit; ret = netdev_register_kobject(dev); - if (ret) + if (ret) { + dev->reg_state = NETREG_UNREGISTERED; goto err_uninit; + } dev->reg_state = NETREG_REGISTERED; __netdev_update_features(dev); @@ -8775,6 +8962,13 @@ int register_netdevice(struct net_device *dev) rcu_barrier(); dev->reg_state = NETREG_UNREGISTERED; + /* We should put the kobject that hold in + * netdev_unregister_kobject(), otherwise + * the net device cannot be freed when + * driver calls free_netdev(), because the + * kobject is being hold. + */ + kobject_put(&dev->dev.kobj); } /* * Prevent userspace races by waiting until the network @@ -9173,6 +9367,8 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_MAX_SIZE; dev->gso_max_segs = GSO_MAX_SEGS; + dev->upper_level = 1; + dev->lower_level = 1; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); @@ -9421,7 +9617,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char call_netdevice_notifiers(NETDEV_UNREGISTER, dev); rcu_barrier(); - new_nsid = peernet2id_alloc(dev_net(dev), net); + new_nsid = peernet2id_alloc(dev_net(dev), net, GFP_KERNEL); /* If there is an ifindex conflict assign a new one */ if (__dev_get_by_index(net, dev->ifindex)) new_ifindex = dev_new_index(net); diff --git a/net/core/devlink.c b/net/core/devlink.c index 132f4b757963..119d203b0723 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -3068,34 +3068,41 @@ devlink_param_value_get_from_info(const struct devlink_param *param, struct genl_info *info, union devlink_param_value *value) { + struct nlattr *param_data; int len; - if (param->type != DEVLINK_PARAM_TYPE_BOOL && - !info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) + param_data = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]; + + if (param->type != DEVLINK_PARAM_TYPE_BOOL && !param_data) return -EINVAL; switch (param->type) { case DEVLINK_PARAM_TYPE_U8: - value->vu8 = nla_get_u8(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u8)) + return -EINVAL; + value->vu8 = nla_get_u8(param_data); break; case DEVLINK_PARAM_TYPE_U16: - value->vu16 = nla_get_u16(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u16)) + return -EINVAL; + value->vu16 = nla_get_u16(param_data); break; case DEVLINK_PARAM_TYPE_U32: - value->vu32 = nla_get_u32(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]); + if (nla_len(param_data) != sizeof(u32)) + return -EINVAL; + value->vu32 = nla_get_u32(param_data); break; case DEVLINK_PARAM_TYPE_STRING: - len = strnlen(nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]), - nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); - if (len == nla_len(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA]) || + len = strnlen(nla_data(param_data), nla_len(param_data)); + if (len == nla_len(param_data) || len >= __DEVLINK_PARAM_MAX_STRING_VALUE) return -EINVAL; - strcpy(value->vstr, - nla_data(info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA])); + strcpy(value->vstr, nla_data(param_data)); break; case DEVLINK_PARAM_TYPE_BOOL: - value->vbool = info->attrs[DEVLINK_ATTR_PARAM_VALUE_DATA] ? - true : false; + if (param_data && nla_len(param_data)) + return -EINVAL; + value->vbool = nla_get_flag(param_data); break; } return 0; @@ -3700,6 +3707,12 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto out_unlock; } + /* return 0 if there is no further data to read */ + if (start_offset >= region->size) { + err = 0; + goto out_unlock; + } + hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); @@ -3731,6 +3744,11 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, end_offset = nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR]); end_offset += nla_get_u64(attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]); dump = false; + + if (start_offset == end_offset) { + err = 0; + goto nla_put_failure; + } } err = devlink_nl_region_read_snapshot_fill(skb, devlink, @@ -4979,6 +4997,8 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_REGION_CHUNK_ADDR] = { .type = NLA_U64 }, + [DEVLINK_ATTR_REGION_CHUNK_LEN] = { .type = NLA_U64 }, [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, diff --git a/net/core/drop_monitor.c b/net/core/drop_monitor.c index 4ea4347f5062..6a5cca21cab5 100644 --- a/net/core/drop_monitor.c +++ b/net/core/drop_monitor.c @@ -155,6 +155,7 @@ static void sched_send_work(struct timer_list *t) static void trace_drop_common(struct sk_buff *skb, void *location) { struct net_dm_alert_msg *msg; + struct net_dm_drop_point *point; struct nlmsghdr *nlh; struct nlattr *nla; int i; @@ -173,11 +174,13 @@ static void trace_drop_common(struct sk_buff *skb, void *location) nlh = (struct nlmsghdr *)dskb->data; nla = genlmsg_data(nlmsg_data(nlh)); msg = nla_data(nla); + point = msg->points; for (i = 0; i < msg->entries; i++) { - if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) { - msg->points[i].count++; + if (!memcmp(&location, &point->pc, sizeof(void *))) { + point->count++; goto out; } + point++; } if (msg->entries == dm_hit_limit) goto out; @@ -186,8 +189,8 @@ static void trace_drop_common(struct sk_buff *skb, void *location) */ __nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point)); nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point)); - memcpy(msg->points[msg->entries].pc, &location, sizeof(void *)); - msg->points[msg->entries].count = 1; + memcpy(point->pc, &location, sizeof(void *)); + point->count = 1; msg->entries++; if (!timer_pending(&data->send_timer)) { diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 4d1011b2e24f..427ae856a8ac 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -1395,11 +1395,13 @@ static int ethtool_reset(struct net_device *dev, char __user *useraddr) static int ethtool_get_wol(struct net_device *dev, char __user *useraddr) { - struct ethtool_wolinfo wol = { .cmd = ETHTOOL_GWOL }; + struct ethtool_wolinfo wol; if (!dev->ethtool_ops->get_wol) return -EOPNOTSUPP; + memset(&wol, 0, sizeof(struct ethtool_wolinfo)); + wol.cmd = ETHTOOL_GWOL; dev->ethtool_ops->get_wol(dev, &wol); if (copy_to_user(useraddr, &wol, sizeof(wol))) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index dd220ce7ca7a..bb11fc87bbae 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -967,7 +967,7 @@ static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule, frh = nlmsg_data(nlh); frh->family = ops->family; - frh->table = rule->table; + frh->table = rule->table < 256 ? rule->table : RT_TABLE_COMPAT; if (nla_put_u32(skb, FRA_TABLE, rule->table)) goto nla_put_failure; if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen)) diff --git a/net/core/filter.c b/net/core/filter.c index 7aee6f368754..633b048792b2 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -1765,25 +1765,27 @@ BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, u32, offset, void *, to, u32, len, u32, start_header) { u8 *end = skb_tail_pointer(skb); - u8 *net = skb_network_header(skb); - u8 *mac = skb_mac_header(skb); - u8 *ptr; + u8 *start, *ptr; - if (unlikely(offset > 0xffff || len > (end - mac))) + if (unlikely(offset > 0xffff)) goto err_clear; switch (start_header) { case BPF_HDR_START_MAC: - ptr = mac + offset; + if (unlikely(!skb_mac_header_was_set(skb))) + goto err_clear; + start = skb_mac_header(skb); break; case BPF_HDR_START_NET: - ptr = net + offset; + start = skb_network_header(skb); break; default: goto err_clear; } - if (likely(ptr >= mac && ptr + len <= end)) { + ptr = start + offset; + + if (likely(ptr + len <= end)) { memcpy(to, ptr, len); return 0; } @@ -2054,6 +2056,7 @@ static inline int __bpf_tx_skb(struct net_device *dev, struct sk_buff *skb) } skb->dev = dev; + skb->tstamp = 0; dev_xmit_recursion_inc(); ret = dev_queue_xmit(skb); @@ -2229,10 +2232,10 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, /* First find the starting scatterlist element */ i = msg->sg.start; do { + offset += len; len = sk_msg_elem(msg, i)->length; if (start < offset + len) break; - offset += len; sk_msg_iter_var_next(i); } while (i != msg->sg.end); @@ -2244,7 +2247,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, * account for the headroom. */ bytes_sg_total = start - offset + bytes; - if (!msg->sg.copy[i] && bytes_sg_total <= len) + if (!test_bit(i, &msg->sg.copy) && bytes_sg_total <= len) goto out; /* At this point we need to linearize multiple scatterlist @@ -2298,7 +2301,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, WARN_ON_ONCE(last_sge == first_sge); shift = last_sge > first_sge ? last_sge - first_sge - 1 : - MAX_SKB_FRAGS - first_sge + last_sge - 1; + NR_MSG_FRAG_IDS - first_sge + last_sge - 1; if (!shift) goto out; @@ -2307,8 +2310,8 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, do { u32 move_from; - if (i + shift >= MAX_MSG_FRAGS) - move_from = i + shift - MAX_MSG_FRAGS; + if (i + shift >= NR_MSG_FRAG_IDS) + move_from = i + shift - NR_MSG_FRAG_IDS; else move_from = i + shift; if (move_from == msg->sg.end) @@ -2322,7 +2325,7 @@ BPF_CALL_4(bpf_msg_pull_data, struct sk_msg *, msg, u32, start, } while (1); msg->sg.end = msg->sg.end - shift > msg->sg.end ? - msg->sg.end - shift + MAX_MSG_FRAGS : + msg->sg.end - shift + NR_MSG_FRAG_IDS : msg->sg.end - shift; out: msg->data = sg_virt(&msg->sg.data[first_sge]) + start - offset; @@ -2344,7 +2347,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { struct scatterlist sge, nsge, nnsge, rsge = {0}, *psge; - u32 new, i = 0, l, space, copy = 0, offset = 0; + u32 new, i = 0, l = 0, space, copy = 0, offset = 0; u8 *raw, *to, *from; struct page *page; @@ -2354,11 +2357,11 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* First find the starting scatterlist element */ i = msg->sg.start; do { + offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; - offset += l; sk_msg_iter_var_next(i); } while (i != msg->sg.end); @@ -2413,6 +2416,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, sk_msg_iter_var_next(i); sg_unmark_end(psge); + sg_unmark_end(&rsge); sk_msg_iter_next(msg, end); } @@ -2449,7 +2453,7 @@ BPF_CALL_4(bpf_msg_push_data, struct sk_msg *, msg, u32, start, /* Place newly allocated data buffer */ sk_mem_charge(msg->sk, len); msg->sg.size += len; - msg->sg.copy[new] = false; + __clear_bit(new, &msg->sg.copy); sg_set_page(&msg->sg.data[new], page, len + copy, 0); if (rsge.length) { get_page(sg_page(&rsge)); @@ -2504,7 +2508,7 @@ static void sk_msg_shift_right(struct sk_msg *msg, int i) BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, u32, len, u64, flags) { - u32 i = 0, l, space, offset = 0; + u32 i = 0, l = 0, space, offset = 0; u64 last = start + len; int pop; @@ -2514,11 +2518,11 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, /* First find the starting scatterlist element */ i = msg->sg.start; do { + offset += l; l = sk_msg_elem(msg, i)->length; if (start < offset + l) break; - offset += l; sk_msg_iter_var_next(i); } while (i != msg->sg.end); @@ -2587,8 +2591,8 @@ BPF_CALL_4(bpf_msg_pop_data, struct sk_msg *, msg, u32, start, } pop = 0; } else if (pop >= sge->length - a) { - sge->length = a; pop -= (sge->length - a); + sge->length = a; } } @@ -2912,7 +2916,7 @@ static int bpf_skb_proto_6_to_4(struct sk_buff *skb) static int bpf_skb_proto_xlat(struct sk_buff *skb, __be16 to_proto) { - __be16 from_proto = skb->protocol; + __be16 from_proto = skb_protocol(skb, true); if (from_proto == htons(ETH_P_IP) && to_proto == htons(ETH_P_IPV6)) @@ -2985,7 +2989,7 @@ static const struct bpf_func_proto bpf_skb_change_type_proto = { static u32 bpf_skb_net_base_len(const struct sk_buff *skb) { - switch (skb->protocol) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return sizeof(struct iphdr); case htons(ETH_P_IPV6): @@ -3153,7 +3157,7 @@ BPF_CALL_4(bpf_skb_adjust_room, struct sk_buff *, skb, s32, len_diff, u32 len_cur, len_diff_abs = abs(len_diff); u32 len_min = bpf_skb_net_base_len(skb); u32 len_max = __bpf_skb_max_len(skb); - __be16 proto = skb->protocol; + __be16 proto = skb_protocol(skb, true); bool shrink = len_diff < 0; u32 off; int ret; @@ -3541,7 +3545,7 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, return err; } default: - break; + return -EBADRQC; } return 0; } @@ -4244,12 +4248,14 @@ BPF_CALL_5(bpf_setsockopt, struct bpf_sock_ops_kern *, bpf_sock, case SO_RCVBUF: val = min_t(u32, val, sysctl_rmem_max); sk->sk_userlocks |= SOCK_RCVBUF_LOCK; - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_SNDBUF: val = min_t(u32, val, sysctl_wmem_max); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); break; case SO_MAX_PACING_RATE: /* 32bit version */ if (val != ~0U) @@ -4916,7 +4922,7 @@ static int bpf_push_seg6_encap(struct sk_buff *skb, u32 type, void *hdr, u32 len switch (type) { case BPF_LWT_ENCAP_SEG6_INLINE: - if (skb->protocol != htons(ETH_P_IPV6)) + if (skb_protocol(skb, true) != htons(ETH_P_IPV6)) return -EBADMSG; err = seg6_do_srh_inline(skb, srh); @@ -5342,8 +5348,7 @@ __bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, if (sk) { sk = sk_to_full_sk(sk); if (!sk_fullsock(sk)) { - if (!sock_flag(sk, SOCK_RCU_FREE)) - sock_gen_put(sk); + sock_gen_put(sk); return NULL; } } @@ -5380,8 +5385,7 @@ bpf_sk_lookup(struct sk_buff *skb, struct bpf_sock_tuple *tuple, u32 len, if (sk) { sk = sk_to_full_sk(sk); if (!sk_fullsock(sk)) { - if (!sock_flag(sk, SOCK_RCU_FREE)) - sock_gen_put(sk); + sock_gen_put(sk); return NULL; } } @@ -5448,7 +5452,8 @@ static const struct bpf_func_proto bpf_sk_lookup_udp_proto = { BPF_CALL_1(bpf_sk_release, struct sock *, sk) { - if (!sock_flag(sk, SOCK_RCU_FREE)) + /* Only full sockets have sk->sk_flags. */ + if (!sk_fullsock(sk) || !sock_flag(sk, SOCK_RCU_FREE)) sock_gen_put(sk); return 0; } diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index b15c0c0f6e55..11c23403b3f3 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -125,12 +125,10 @@ int skb_flow_dissector_bpf_prog_attach(const union bpf_attr *attr, return 0; } -int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +static int flow_dissector_bpf_prog_detach(struct net *net) { struct bpf_prog *attached; - struct net *net; - net = current->nsproxy->net_ns; mutex_lock(&flow_dissector_mutex); attached = rcu_dereference_protected(net->flow_dissector_prog, lockdep_is_held(&flow_dissector_mutex)); @@ -165,6 +163,24 @@ static __be16 skb_flow_get_be16(const struct sk_buff *skb, int poff, return 0; } +int skb_flow_dissector_bpf_prog_detach(const union bpf_attr *attr) +{ + return flow_dissector_bpf_prog_detach(current->nsproxy->net_ns); +} + +static void __net_exit flow_dissector_pernet_pre_exit(struct net *net) +{ + /* We're not racing with attach/detach because there are no + * references to netns left when pre_exit gets called. + */ + if (rcu_access_pointer(net->flow_dissector_prog)) + flow_dissector_bpf_prog_detach(net); +} + +static struct pernet_operations flow_dissector_pernet_ops __net_initdata = { + .pre_exit = flow_dissector_pernet_pre_exit, +}; + /** * __skb_flow_get_ports - extract the upper layer ports and return them * @skb: sk_buff to extract the ports from @@ -793,9 +809,10 @@ bool __skb_flow_dissect(const struct net *net, nhoff = skb_network_offset(skb); hlen = skb_headlen(skb); #if IS_ENABLED(CONFIG_NET_DSA) - if (unlikely(skb->dev && netdev_uses_dsa(skb->dev))) { + if (unlikely(skb->dev && netdev_uses_dsa(skb->dev) && + proto == htons(ETH_P_XDSA))) { const struct dsa_device_ops *ops; - int offset; + int offset = 0; ops = skb->dev->dsa_ptr->tag_ops; if (ops->flow_dissect && @@ -1281,30 +1298,21 @@ out_bad: } EXPORT_SYMBOL(__skb_flow_dissect); -static u32 hashrnd __read_mostly; +static siphash_key_t hashrnd __read_mostly; static __always_inline void __flow_hash_secret_init(void) { net_get_random_once(&hashrnd, sizeof(hashrnd)); } -static __always_inline u32 __flow_hash_words(const u32 *words, u32 length, - u32 keyval) -{ - return jhash2(words, length, keyval); -} - -static inline const u32 *flow_keys_hash_start(const struct flow_keys *flow) +static const void *flow_keys_hash_start(const struct flow_keys *flow) { - const void *p = flow; - - BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % sizeof(u32)); - return (const u32 *)(p + FLOW_KEYS_HASH_OFFSET); + BUILD_BUG_ON(FLOW_KEYS_HASH_OFFSET % SIPHASH_ALIGNMENT); + return &flow->FLOW_KEYS_HASH_START_FIELD; } static inline size_t flow_keys_hash_length(const struct flow_keys *flow) { size_t diff = FLOW_KEYS_HASH_OFFSET + sizeof(flow->addrs); - BUILD_BUG_ON((sizeof(*flow) - FLOW_KEYS_HASH_OFFSET) % sizeof(u32)); BUILD_BUG_ON(offsetof(typeof(*flow), addrs) != sizeof(*flow) - sizeof(flow->addrs)); @@ -1319,7 +1327,7 @@ static inline size_t flow_keys_hash_length(const struct flow_keys *flow) diff -= sizeof(flow->addrs.tipckey); break; } - return (sizeof(*flow) - diff) / sizeof(u32); + return sizeof(*flow) - diff; } __be32 flow_get_u32_src(const struct flow_keys *flow) @@ -1385,14 +1393,15 @@ static inline void __flow_hash_consistentify(struct flow_keys *keys) } } -static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) +static inline u32 __flow_hash_from_keys(struct flow_keys *keys, + const siphash_key_t *keyval) { u32 hash; __flow_hash_consistentify(keys); - hash = __flow_hash_words(flow_keys_hash_start(keys), - flow_keys_hash_length(keys), keyval); + hash = siphash(flow_keys_hash_start(keys), + flow_keys_hash_length(keys), keyval); if (!hash) hash = 1; @@ -1402,12 +1411,13 @@ static inline u32 __flow_hash_from_keys(struct flow_keys *keys, u32 keyval) u32 flow_hash_from_keys(struct flow_keys *keys) { __flow_hash_secret_init(); - return __flow_hash_from_keys(keys, hashrnd); + return __flow_hash_from_keys(keys, &hashrnd); } EXPORT_SYMBOL(flow_hash_from_keys); static inline u32 ___skb_get_hash(const struct sk_buff *skb, - struct flow_keys *keys, u32 keyval) + struct flow_keys *keys, + const siphash_key_t *keyval) { skb_flow_dissect_flow_keys(skb, keys, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); @@ -1455,7 +1465,7 @@ u32 __skb_get_hash_symmetric(const struct sk_buff *skb) &keys, NULL, 0, 0, 0, FLOW_DISSECTOR_F_STOP_AT_FLOW_LABEL); - return __flow_hash_from_keys(&keys, hashrnd); + return __flow_hash_from_keys(&keys, &hashrnd); } EXPORT_SYMBOL_GPL(__skb_get_hash_symmetric); @@ -1475,13 +1485,14 @@ void __skb_get_hash(struct sk_buff *skb) __flow_hash_secret_init(); - hash = ___skb_get_hash(skb, &keys, hashrnd); + hash = ___skb_get_hash(skb, &keys, &hashrnd); __skb_set_sw_hash(skb, hash, flow_keys_have_l4(&keys)); } EXPORT_SYMBOL(__skb_get_hash); -__u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) +__u32 skb_get_hash_perturb(const struct sk_buff *skb, + const siphash_key_t *perturb) { struct flow_keys keys; @@ -1669,7 +1680,7 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_basic_dissector, flow_keys_basic_dissector_keys, ARRAY_SIZE(flow_keys_basic_dissector_keys)); - return 0; -} + return register_pernet_subsys(&flow_dissector_pernet_ops); +} core_initcall(init_default_flow_dissectors); diff --git a/net/core/lwt_bpf.c b/net/core/lwt_bpf.c index f93785e5833c..99a6de52b21d 100644 --- a/net/core/lwt_bpf.c +++ b/net/core/lwt_bpf.c @@ -88,11 +88,16 @@ static int bpf_lwt_input_reroute(struct sk_buff *skb) int err = -EINVAL; if (skb->protocol == htons(ETH_P_IP)) { + struct net_device *dev = skb_dst(skb)->dev; struct iphdr *iph = ip_hdr(skb); + dev_hold(dev); + skb_dst_drop(skb); err = ip_route_input_noref(skb, iph->daddr, iph->saddr, - iph->tos, skb_dst(skb)->dev); + iph->tos, dev); + dev_put(dev); } else if (skb->protocol == htons(ETH_P_IPV6)) { + skb_dst_drop(skb); err = ipv6_stub->ipv6_route_input(skb); } else { err = -EAFNOSUPPORT; @@ -225,9 +230,7 @@ static int bpf_lwt_xmit_reroute(struct sk_buff *skb) fl6.daddr = iph6->daddr; fl6.saddr = iph6->saddr; - err = ipv6_stub->ipv6_dst_lookup(net, skb->sk, &dst, &fl6); - if (unlikely(err)) - goto err; + dst = ipv6_stub->ipv6_dst_lookup_flow(net, skb->sk, &fl6, NULL); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto err; diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 5bb0a1aee50e..6cdb1159f17b 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -98,9 +98,6 @@ static int neigh_blackhole(struct neighbour *neigh, struct sk_buff *skb) static void neigh_cleanup_and_release(struct neighbour *neigh) { - if (neigh->parms->neigh_cleanup) - neigh->parms->neigh_cleanup(neigh); - trace_neigh_cleanup_and_release(neigh, 0); __neigh_notify(neigh, RTM_DELNEIGH, 0, 0); call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, neigh); @@ -1195,7 +1192,7 @@ static void neigh_update_hhs(struct neighbour *neigh) if (update) { hh = &neigh->hh; - if (hh->hh_len) { + if (READ_ONCE(hh->hh_len)) { write_seqlock_bh(&hh->hh_lock); update(hh, neigh->dev, neigh->ha); write_sequnlock_bh(&hh->hh_lock); @@ -1474,7 +1471,7 @@ int neigh_resolve_output(struct neighbour *neigh, struct sk_buff *skb) struct net_device *dev = neigh->dev; unsigned int seq; - if (dev->header_ops->cache && !neigh->hh.hh_len) + if (dev->header_ops->cache && !READ_ONCE(neigh->hh.hh_len)) neigh_hh_init(neigh); do { @@ -1955,6 +1952,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, NEIGH_UPDATE_F_OVERRIDE_ISROUTER); } + if (protocol) + neigh->protocol = protocol; + if (ndm->ndm_flags & NTF_EXT_LEARNED) flags |= NEIGH_UPDATE_F_EXT_LEARNED; @@ -1968,9 +1968,6 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, err = __neigh_update(neigh, lladdr, ndm->ndm_state, flags, NETLINK_CB(skb).portid, extack); - if (protocol) - neigh->protocol = protocol; - neigh_release(neigh); out: @@ -2050,8 +2047,8 @@ static int neightbl_fill_info(struct sk_buff *skb, struct neigh_table *tbl, goto nla_put_failure; { unsigned long now = jiffies; - unsigned int flush_delta = now - tbl->last_flush; - unsigned int rand_delta = now - tbl->last_rand; + long flush_delta = now - tbl->last_flush; + long rand_delta = now - tbl->last_rand; struct neigh_hash_table *nht; struct ndt_config ndc = { .ndtc_key_len = tbl->key_len, diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 865ba6ca16eb..229ecf256f4e 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -1031,7 +1031,7 @@ static ssize_t tx_timeout_show(struct netdev_queue *queue, char *buf) trans_timeout = queue->trans_timeout; spin_unlock_irq(&queue->_xmit_lock); - return sprintf(buf, "%lu", trans_timeout); + return sprintf(buf, fmt_ulong, trans_timeout); } static unsigned int get_netdev_queue_index(struct netdev_queue *queue) diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 15f68842ac6b..e31ab1f9c91d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -145,6 +145,17 @@ static void ops_free(const struct pernet_operations *ops, struct net *net) } } +static void ops_pre_exit_list(const struct pernet_operations *ops, + struct list_head *net_exit_list) +{ + struct net *net; + + if (ops->pre_exit) { + list_for_each_entry(net, net_exit_list, exit_list) + ops->pre_exit(net); + } +} + static void ops_exit_list(const struct pernet_operations *ops, struct list_head *net_exit_list) { @@ -227,11 +238,11 @@ static int __peernet2id(struct net *net, struct net *peer) return __peernet2id_alloc(net, peer, &no); } -static void rtnl_net_notifyid(struct net *net, int cmd, int id); +static void rtnl_net_notifyid(struct net *net, int cmd, int id, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will * be allocated and returned. */ -int peernet2id_alloc(struct net *net, struct net *peer) +int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { bool alloc = false, alive = false; int id; @@ -250,7 +261,7 @@ int peernet2id_alloc(struct net *net, struct net *peer) id = __peernet2id_alloc(net, peer, &alloc); spin_unlock_bh(&net->nsid_lock); if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id); + rtnl_net_notifyid(net, RTM_NEWNSID, id, gfp); if (alive) put_net(peer); return id; @@ -330,6 +341,12 @@ out_undo: list_add(&net->exit_list, &net_exit_list); saved_ops = ops; list_for_each_entry_continue_reverse(ops, &pernet_list, list) + ops_pre_exit_list(ops, &net_exit_list); + + synchronize_rcu(); + + ops = saved_ops; + list_for_each_entry_continue_reverse(ops, &pernet_list, list) ops_exit_list(ops, &net_exit_list); ops = saved_ops; @@ -496,7 +513,8 @@ static void unhash_nsid(struct net *net, struct net *last) idr_remove(&tmp->netns_ids, id); spin_unlock_bh(&tmp->nsid_lock); if (id >= 0) - rtnl_net_notifyid(tmp, RTM_DELNSID, id); + rtnl_net_notifyid(tmp, RTM_DELNSID, id, + GFP_KERNEL); if (tmp == last) break; } @@ -541,10 +559,15 @@ static void cleanup_net(struct work_struct *work) list_add_tail(&net->exit_list, &net_exit_list); } + /* Run all of the network namespace pre_exit methods */ + list_for_each_entry_reverse(ops, &pernet_list, list) + ops_pre_exit_list(ops, &net_exit_list); + /* * Another CPU might be rcu-iterating the list, wait for it. * This needs to be before calling the exit() notifiers, so * the rcu_barrier() below isn't sufficient alone. + * Also the pre_exit() and exit() methods need this barrier. */ synchronize_rcu(); @@ -722,7 +745,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, err = alloc_netid(net, peer, nsid); spin_unlock_bh(&net->nsid_lock); if (err >= 0) { - rtnl_net_notifyid(net, RTM_NEWNSID, err); + rtnl_net_notifyid(net, RTM_NEWNSID, err, GFP_KERNEL); err = 0; } else if (err == -ENOSPC && nsid >= 0) { err = -EEXIST; @@ -1009,7 +1032,7 @@ end: return err < 0 ? err : skb->len; } -static void rtnl_net_notifyid(struct net *net, int cmd, int id) +static void rtnl_net_notifyid(struct net *net, int cmd, int id, gfp_t gfp) { struct net_fill_args fillargs = { .cmd = cmd, @@ -1018,7 +1041,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id) struct sk_buff *msg; int err = -ENOMEM; - msg = nlmsg_new(rtnl_net_get_size(), GFP_KERNEL); + msg = nlmsg_new(rtnl_net_get_size(), gfp); if (!msg) goto out; @@ -1026,7 +1049,7 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id) if (err < 0) goto err_out; - rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, 0); + rtnl_notify(msg, net, 0, RTNLGRP_NSID, NULL, gfp); return; err_out: @@ -1101,6 +1124,8 @@ static int __register_pernet_operations(struct list_head *list, out_undo: /* If I have an error cleanup all namespaces I initialized */ list_del(&ops->list); + ops_pre_exit_list(ops, &net_exit_list); + synchronize_rcu(); ops_exit_list(ops, &net_exit_list); ops_free_list(ops, &net_exit_list); return error; @@ -1115,6 +1140,8 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) /* See comment in __register_pernet_operations() */ for_each_net(net) list_add_tail(&net->exit_list, &net_exit_list); + ops_pre_exit_list(ops, &net_exit_list); + synchronize_rcu(); ops_exit_list(ops, &net_exit_list); ops_free_list(ops, &net_exit_list); } @@ -1139,6 +1166,8 @@ static void __unregister_pernet_operations(struct pernet_operations *ops) } else { LIST_HEAD(net_exit_list); list_add(&init_net.exit_list, &net_exit_list); + ops_pre_exit_list(ops, &net_exit_list); + synchronize_rcu(); ops_exit_list(ops, &net_exit_list); ops_free_list(ops, &net_exit_list); } diff --git a/net/core/netclassid_cgroup.c b/net/core/netclassid_cgroup.c index 0642f91c4038..41b24cd31562 100644 --- a/net/core/netclassid_cgroup.c +++ b/net/core/netclassid_cgroup.c @@ -53,30 +53,60 @@ static void cgrp_css_free(struct cgroup_subsys_state *css) kfree(css_cls_state(css)); } +/* + * To avoid freezing of sockets creation for tasks with big number of threads + * and opened sockets lets release file_lock every 1000 iterated descriptors. + * New sockets will already have been created with new classid. + */ + +struct update_classid_context { + u32 classid; + unsigned int batch; +}; + +#define UPDATE_CLASSID_BATCH 1000 + static int update_classid_sock(const void *v, struct file *file, unsigned n) { int err; + struct update_classid_context *ctx = (void *)v; struct socket *sock = sock_from_file(file, &err); if (sock) { spin_lock(&cgroup_sk_update_lock); - sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, - (unsigned long)v); + sock_cgroup_set_classid(&sock->sk->sk_cgrp_data, ctx->classid); spin_unlock(&cgroup_sk_update_lock); } + if (--ctx->batch == 0) { + ctx->batch = UPDATE_CLASSID_BATCH; + return n + 1; + } return 0; } +static void update_classid_task(struct task_struct *p, u32 classid) +{ + struct update_classid_context ctx = { + .classid = classid, + .batch = UPDATE_CLASSID_BATCH + }; + unsigned int fd = 0; + + do { + task_lock(p); + fd = iterate_fd(p->files, fd, update_classid_sock, &ctx); + task_unlock(p); + cond_resched(); + } while (fd); +} + static void cgrp_attach(struct cgroup_taskset *tset) { struct cgroup_subsys_state *css; struct task_struct *p; cgroup_taskset_for_each(p, css, tset) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)css_cls_state(css)->classid); - task_unlock(p); + update_classid_task(p, css_cls_state(css)->classid); } } @@ -97,13 +127,8 @@ static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft, cs->classid = (u32)value; css_task_iter_start(css, 0, &it); - while ((p = css_task_iter_next(&it))) { - task_lock(p); - iterate_fd(p->files, 0, update_classid_sock, - (void *)(unsigned long)cs->classid); - task_unlock(p); - cond_resched(); - } + while ((p = css_task_iter_next(&it))) + update_classid_task(p, cs->classid); css_task_iter_end(&it); return 0; diff --git a/net/core/netprio_cgroup.c b/net/core/netprio_cgroup.c index 256b7954b720..8618242c677a 100644 --- a/net/core/netprio_cgroup.c +++ b/net/core/netprio_cgroup.c @@ -236,6 +236,8 @@ static void net_prio_attach(struct cgroup_taskset *tset) struct task_struct *p; struct cgroup_subsys_state *css; + cgroup_sk_alloc_disable(); + cgroup_taskset_for_each(p, css, tset) { void *v = (void *)(unsigned long)css->cgroup->id; diff --git a/net/core/pktgen.c b/net/core/pktgen.c index f975c5e2a369..52d27ac4023b 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3362,7 +3362,7 @@ static void pktgen_xmit(struct pktgen_dev *pkt_dev) /* skb was 'freed' by stack, so clean few * bits and reuse it */ - skb_reset_tc(skb); + skb_reset_redirect(skb); } while (--burst > 0); goto out; /* Skips xmit_mode M_START_XMIT */ } else if (pkt_dev->xmit_mode == M_QUEUE_XMIT) { diff --git a/net/core/request_sock.c b/net/core/request_sock.c index c9bb00008528..f35c2e998406 100644 --- a/net/core/request_sock.c +++ b/net/core/request_sock.c @@ -96,7 +96,7 @@ void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req, fastopenq = &inet_csk(lsk)->icsk_accept_queue.fastopenq; - tcp_sk(sk)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(sk)->fastopen_rsk, NULL); spin_lock_bh(&fastopenq->lock); fastopenq->qlen--; tcp_rsk(req)->tfo_listener = false; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index cec60583931f..9a504779c4f5 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1515,7 +1515,7 @@ static noinline_for_stack int nla_put_ifalias(struct sk_buff *skb, static int rtnl_fill_link_netnsid(struct sk_buff *skb, const struct net_device *dev, - struct net *src_net) + struct net *src_net, gfp_t gfp) { bool put_iflink = false; @@ -1523,7 +1523,7 @@ static int rtnl_fill_link_netnsid(struct sk_buff *skb, struct net *link_net = dev->rtnl_link_ops->get_link_net(dev); if (!net_eq(dev_net(dev), link_net)) { - int id = peernet2id_alloc(src_net, link_net); + int id = peernet2id_alloc(src_net, link_net, gfp); if (nla_put_s32(skb, IFLA_LINK_NETNSID, id)) return -EMSGSIZE; @@ -1581,7 +1581,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, int type, u32 pid, u32 seq, u32 change, unsigned int flags, u32 ext_filter_mask, u32 event, int *new_nsid, int new_ifindex, - int tgt_netnsid) + int tgt_netnsid, gfp_t gfp) { struct ifinfomsg *ifm; struct nlmsghdr *nlh; @@ -1673,7 +1673,7 @@ static int rtnl_fill_ifinfo(struct sk_buff *skb, goto nla_put_failure; } - if (rtnl_fill_link_netnsid(skb, dev, src_net)) + if (rtnl_fill_link_netnsid(skb, dev, src_net, gfp)) goto nla_put_failure; if (new_nsid && @@ -1992,7 +1992,7 @@ walk_entries: NETLINK_CB(cb->skb).portid, nlh->nlmsg_seq, 0, flags, ext_filter_mask, 0, NULL, 0, - netnsid); + netnsid, GFP_KERNEL); if (err < 0) { if (likely(skb->len)) @@ -2186,6 +2186,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_MAC]) { struct ifla_vf_mac *ivm = nla_data(tb[IFLA_VF_MAC]); + if (ivm->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_mac) err = ops->ndo_set_vf_mac(dev, ivm->vf, @@ -2197,6 +2199,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_VLAN]) { struct ifla_vf_vlan *ivv = nla_data(tb[IFLA_VF_VLAN]); + if (ivv->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_vlan) err = ops->ndo_set_vf_vlan(dev, ivv->vf, ivv->vlan, @@ -2229,6 +2233,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (len == 0) return -EINVAL; + if (ivvl[0]->vf >= INT_MAX) + return -EINVAL; err = ops->ndo_set_vf_vlan(dev, ivvl[0]->vf, ivvl[0]->vlan, ivvl[0]->qos, ivvl[0]->vlan_proto); if (err < 0) @@ -2239,6 +2245,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) struct ifla_vf_tx_rate *ivt = nla_data(tb[IFLA_VF_TX_RATE]); struct ifla_vf_info ivf; + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_get_vf_config) err = ops->ndo_get_vf_config(dev, ivt->vf, &ivf); @@ -2257,6 +2265,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_RATE]) { struct ifla_vf_rate *ivt = nla_data(tb[IFLA_VF_RATE]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_rate) err = ops->ndo_set_vf_rate(dev, ivt->vf, @@ -2269,6 +2279,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_SPOOFCHK]) { struct ifla_vf_spoofchk *ivs = nla_data(tb[IFLA_VF_SPOOFCHK]); + if (ivs->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_spoofchk) err = ops->ndo_set_vf_spoofchk(dev, ivs->vf, @@ -2280,6 +2292,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_LINK_STATE]) { struct ifla_vf_link_state *ivl = nla_data(tb[IFLA_VF_LINK_STATE]); + if (ivl->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_link_state) err = ops->ndo_set_vf_link_state(dev, ivl->vf, @@ -2293,6 +2307,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) err = -EOPNOTSUPP; ivrssq_en = nla_data(tb[IFLA_VF_RSS_QUERY_EN]); + if (ivrssq_en->vf >= INT_MAX) + return -EINVAL; if (ops->ndo_set_vf_rss_query_en) err = ops->ndo_set_vf_rss_query_en(dev, ivrssq_en->vf, ivrssq_en->setting); @@ -2303,6 +2319,8 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_TRUST]) { struct ifla_vf_trust *ivt = nla_data(tb[IFLA_VF_TRUST]); + if (ivt->vf >= INT_MAX) + return -EINVAL; err = -EOPNOTSUPP; if (ops->ndo_set_vf_trust) err = ops->ndo_set_vf_trust(dev, ivt->vf, ivt->setting); @@ -2313,15 +2331,18 @@ static int do_setvfinfo(struct net_device *dev, struct nlattr **tb) if (tb[IFLA_VF_IB_NODE_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_NODE_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; - return handle_vf_guid(dev, ivt, IFLA_VF_IB_NODE_GUID); } if (tb[IFLA_VF_IB_PORT_GUID]) { struct ifla_vf_guid *ivt = nla_data(tb[IFLA_VF_IB_PORT_GUID]); + if (ivt->vf >= INT_MAX) + return -EINVAL; if (!ops->ndo_set_vf_guid) return -EOPNOTSUPP; @@ -2928,8 +2949,17 @@ struct net_device *rtnl_create_link(struct net *net, const char *ifname, dev->rtnl_link_ops = ops; dev->rtnl_link_state = RTNL_LINK_INITIALIZING; - if (tb[IFLA_MTU]) - dev->mtu = nla_get_u32(tb[IFLA_MTU]); + if (tb[IFLA_MTU]) { + u32 mtu = nla_get_u32(tb[IFLA_MTU]); + int err; + + err = dev_validate_mtu(dev, mtu, extack); + if (err) { + free_netdev(dev); + return ERR_PTR(err); + } + dev->mtu = mtu; + } if (tb[IFLA_ADDRESS]) { memcpy(dev->dev_addr, nla_data(tb[IFLA_ADDRESS]), nla_len(tb[IFLA_ADDRESS])); @@ -3191,7 +3221,8 @@ replay: */ if (err < 0) { /* If device is not registered at all, free it now */ - if (dev->reg_state == NETREG_UNINITIALIZED) + if (dev->reg_state == NETREG_UNINITIALIZED || + dev->reg_state == NETREG_UNREGISTERED) free_netdev(dev); goto out; } @@ -3350,7 +3381,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, err = rtnl_fill_ifinfo(nskb, dev, net, RTM_NEWLINK, NETLINK_CB(skb).portid, nlh->nlmsg_seq, 0, 0, ext_filter_mask, - 0, NULL, 0, netnsid); + 0, NULL, 0, netnsid, GFP_KERNEL); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size */ WARN_ON(err == -EMSGSIZE); @@ -3462,7 +3493,7 @@ struct sk_buff *rtmsg_ifinfo_build_skb(int type, struct net_device *dev, err = rtnl_fill_ifinfo(skb, dev, dev_net(dev), type, 0, 0, change, 0, 0, event, - new_nsid, new_ifindex, -1); + new_nsid, new_ifindex, -1, flags); if (err < 0) { /* -EMSGSIZE implies BUG in if_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -3907,7 +3938,7 @@ static int valid_fdb_dump_strict(const struct nlmsghdr *nlh, ndm = nlmsg_data(nlh); if (ndm->ndm_pad1 || ndm->ndm_pad2 || ndm->ndm_state || ndm->ndm_flags || ndm->ndm_type) { - NL_SET_ERR_MSG(extack, "Invalid values in header for fbd dump request"); + NL_SET_ERR_MSG(extack, "Invalid values in header for fdb dump request"); return -EINVAL; } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 74efd63f15e2..57f879316ab4 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -4270,7 +4270,7 @@ static void skb_set_err_queue(struct sk_buff *skb) int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb) { if (atomic_read(&sk->sk_rmem_alloc) + skb->truesize >= - (unsigned int)sk->sk_rcvbuf) + (unsigned int)READ_ONCE(sk->sk_rcvbuf)) return -ENOMEM; skb_orphan(skb); diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 93bffaad2135..e16f985631ae 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -7,6 +7,7 @@ #include <net/sock.h> #include <net/tcp.h> +#include <net/tls.h> static bool sk_msg_try_coalesce_ok(struct sk_msg *msg, int elem_first_coalesce) { @@ -271,18 +272,28 @@ void sk_msg_trim(struct sock *sk, struct sk_msg *msg, int len) msg->sg.data[i].length -= trim; sk_mem_uncharge(sk, trim); + /* Adjust copybreak if it falls into the trimmed part of last buf */ + if (msg->sg.curr == i && msg->sg.copybreak > msg->sg.data[i].length) + msg->sg.copybreak = msg->sg.data[i].length; out: - /* If we trim data before curr pointer update copybreak and current - * so that any future copy operations start at new copy location. + sk_msg_iter_var_next(i); + msg->sg.end = i; + + /* If we trim data a full sg elem before curr pointer update + * copybreak and current so that any future copy operations + * start at new copy location. * However trimed data that has not yet been used in a copy op * does not require an update. */ - if (msg->sg.curr >= i) { + if (!msg->sg.size) { + msg->sg.curr = msg->sg.start; + msg->sg.copybreak = 0; + } else if (sk_msg_iter_dist(msg->sg.start, msg->sg.curr) >= + sk_msg_iter_dist(msg->sg.start, msg->sg.end)) { + sk_msg_iter_var_prev(i); msg->sg.curr = i; msg->sg.copybreak = msg->sg.data[i].length; } - sk_msg_iter_var_next(i); - msg->sg.end = i; } EXPORT_SYMBOL_GPL(sk_msg_trim); @@ -412,7 +423,7 @@ static int sk_psock_skb_ingress(struct sk_psock *psock, struct sk_buff *skb) copied = skb->len; msg->sg.start = 0; msg->sg.size = copied; - msg->sg.end = num_sge == MAX_MSG_FRAGS ? 0 : num_sge; + msg->sg.end = num_sge; msg->skb = skb; sk_psock_queue_msg(psock, msg); @@ -677,13 +688,74 @@ static struct sk_psock *sk_psock_from_strp(struct strparser *strp) return container_of(parser, struct sk_psock, parser); } -static void sk_psock_verdict_apply(struct sk_psock *psock, - struct sk_buff *skb, int verdict) +static void sk_psock_skb_redirect(struct sk_buff *skb) { struct sk_psock *psock_other; struct sock *sk_other; bool ingress; + sk_other = tcp_skb_bpf_redirect_fetch(skb); + if (unlikely(!sk_other)) { + kfree_skb(skb); + return; + } + psock_other = sk_psock(sk_other); + if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || + !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) { + kfree_skb(skb); + return; + } + + ingress = tcp_skb_bpf_ingress(skb); + if ((!ingress && sock_writeable(sk_other)) || + (ingress && + atomic_read(&sk_other->sk_rmem_alloc) <= + sk_other->sk_rcvbuf)) { + if (!ingress) + skb_set_owner_w(skb, sk_other); + skb_queue_tail(&psock_other->ingress_skb, skb); + schedule_work(&psock_other->work); + } else { + kfree_skb(skb); + } +} + +static void sk_psock_tls_verdict_apply(struct sk_buff *skb, int verdict) +{ + switch (verdict) { + case __SK_REDIRECT: + sk_psock_skb_redirect(skb); + break; + case __SK_PASS: + case __SK_DROP: + default: + break; + } +} + +int sk_psock_tls_strp_read(struct sk_psock *psock, struct sk_buff *skb) +{ + struct bpf_prog *prog; + int ret = __SK_PASS; + + rcu_read_lock(); + prog = READ_ONCE(psock->progs.skb_verdict); + if (likely(prog)) { + tcp_skb_bpf_redirect_clear(skb); + ret = sk_psock_bpf_run(psock, prog, skb); + ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); + } + sk_psock_tls_verdict_apply(skb, ret); + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL_GPL(sk_psock_tls_strp_read); + +static void sk_psock_verdict_apply(struct sk_psock *psock, + struct sk_buff *skb, int verdict) +{ + struct sock *sk_other; + switch (verdict) { case __SK_PASS: sk_other = psock->sk; @@ -702,25 +774,8 @@ static void sk_psock_verdict_apply(struct sk_psock *psock, } goto out_free; case __SK_REDIRECT: - sk_other = tcp_skb_bpf_redirect_fetch(skb); - if (unlikely(!sk_other)) - goto out_free; - psock_other = sk_psock(sk_other); - if (!psock_other || sock_flag(sk_other, SOCK_DEAD) || - !sk_psock_test_state(psock_other, SK_PSOCK_TX_ENABLED)) - goto out_free; - ingress = tcp_skb_bpf_ingress(skb); - if ((!ingress && sock_writeable(sk_other)) || - (ingress && - atomic_read(&sk_other->sk_rmem_alloc) <= - sk_other->sk_rcvbuf)) { - if (!ingress) - skb_set_owner_w(skb, sk_other); - skb_queue_tail(&psock_other->ingress_skb, skb); - schedule_work(&psock_other->work); - break; - } - /* fall-through */ + sk_psock_skb_redirect(skb); + break; case __SK_DROP: /* fall-through */ default: @@ -731,11 +786,18 @@ out_free: static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) { - struct sk_psock *psock = sk_psock_from_strp(strp); + struct sk_psock *psock; struct bpf_prog *prog; int ret = __SK_DROP; + struct sock *sk; rcu_read_lock(); + sk = strp->sk; + psock = sk_psock(sk); + if (unlikely(!psock)) { + kfree_skb(skb); + goto out; + } prog = READ_ONCE(psock->progs.skb_verdict); if (likely(prog)) { skb_orphan(skb); @@ -743,8 +805,9 @@ static void sk_psock_strp_read(struct strparser *strp, struct sk_buff *skb) ret = sk_psock_bpf_run(psock, prog, skb); ret = sk_psock_map_verd(ret, tcp_skb_bpf_redirect_fetch(skb)); } - rcu_read_unlock(); sk_psock_verdict_apply(psock, skb, ret); +out: + rcu_read_unlock(); } static int sk_psock_strp_read_done(struct strparser *strp, int err) @@ -774,9 +837,13 @@ static void sk_psock_strp_data_ready(struct sock *sk) rcu_read_lock(); psock = sk_psock(sk); if (likely(psock)) { - write_lock_bh(&sk->sk_callback_lock); - strp_data_ready(&psock->parser.strp); - write_unlock_bh(&sk->sk_callback_lock); + if (tls_sw_has_ctx_rx(sk)) { + psock->parser.saved_data_ready(sk); + } else { + write_lock_bh(&sk->sk_callback_lock); + strp_data_ready(&psock->parser.strp); + write_unlock_bh(&sk->sk_callback_lock); + } } rcu_read_unlock(); } @@ -784,15 +851,18 @@ static void sk_psock_strp_data_ready(struct sock *sk) static void sk_psock_write_space(struct sock *sk) { struct sk_psock *psock; - void (*write_space)(struct sock *sk); + void (*write_space)(struct sock *sk) = NULL; rcu_read_lock(); psock = sk_psock(sk); - if (likely(psock && sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED))) - schedule_work(&psock->work); - write_space = psock->saved_write_space; + if (likely(psock)) { + if (sk_psock_test_state(psock, SK_PSOCK_TX_ENABLED)) + schedule_work(&psock->work); + write_space = psock->saved_write_space; + } rcu_read_unlock(); - write_space(sk); + if (write_space) + write_space(sk); } int sk_psock_init_strp(struct sock *sk, struct sk_psock *psock) diff --git a/net/core/sock.c b/net/core/sock.c index 3d54153b8325..fb83335a5abb 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -709,7 +709,7 @@ bool sk_mc_loop(struct sock *sk) return inet6_sk(sk)->mc_loop; #endif } - WARN_ON(1); + WARN_ON_ONCE(1); return true; } EXPORT_SYMBOL(sk_mc_loop); @@ -785,7 +785,8 @@ set_sndbuf: */ val = min_t(int, val, INT_MAX / 2); sk->sk_userlocks |= SOCK_SNDBUF_LOCK; - sk->sk_sndbuf = max_t(int, val * 2, SOCK_MIN_SNDBUF); + WRITE_ONCE(sk->sk_sndbuf, + max_t(int, val * 2, SOCK_MIN_SNDBUF)); /* Wake up sending tasks if we upped the value. */ sk->sk_write_space(sk); break; @@ -831,7 +832,8 @@ set_rcvbuf: * returning the value we actually used in getsockopt * is the most desirable behavior. */ - sk->sk_rcvbuf = max_t(int, val * 2, SOCK_MIN_RCVBUF); + WRITE_ONCE(sk->sk_rcvbuf, + max_t(int, val * 2, SOCK_MIN_RCVBUF)); break; case SO_RCVBUFFORCE: @@ -1121,7 +1123,7 @@ set_rcvbuf: break; } case SO_INCOMING_CPU: - sk->sk_incoming_cpu = val; + WRITE_ONCE(sk->sk_incoming_cpu, val); break; case SO_CNX_ADVICE: @@ -1470,7 +1472,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_INCOMING_CPU: - v.val = sk->sk_incoming_cpu; + v.val = READ_ONCE(sk->sk_incoming_cpu); break; case SO_MEMINFO: @@ -1673,6 +1675,7 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, cgroup_sk_alloc(&sk->sk_cgrp_data); sock_update_classid(&sk->sk_cgrp_data); sock_update_netprioidx(&sk->sk_cgrp_data); + sk_tx_queue_clear(sk); } return sk; @@ -1826,8 +1829,11 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) atomic_set(&newsk->sk_zckey, 0); sock_reset_flag(newsk, SOCK_DONE); - mem_cgroup_sk_alloc(newsk); - cgroup_sk_alloc(&newsk->sk_cgrp_data); + + /* sk->sk_memcg will be populated at accept() time */ + newsk->sk_memcg = NULL; + + cgroup_sk_clone(&newsk->sk_cgrp_data); rcu_read_lock(); filter = rcu_dereference(sk->sk_filter); @@ -1883,6 +1889,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) */ sk_refcnt_debug_inc(newsk); sk_set_socket(newsk, NULL); + sk_tx_queue_clear(newsk); RCU_INIT_POINTER(newsk->sk_wq, NULL); if (newsk->sk_prot->sockets_allocated) @@ -2081,8 +2088,10 @@ EXPORT_SYMBOL(sock_i_ino); struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { - if (force || refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { + if (force || + refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) { struct sk_buff *skb = alloc_skb(size, priority); + if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -2183,7 +2192,7 @@ static long sock_wait_for_wmem(struct sock *sk, long timeo) break; set_bit(SOCK_NOSPACE, &sk->sk_socket->flags); prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE); - if (refcount_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) + if (refcount_read(&sk->sk_wmem_alloc) < READ_ONCE(sk->sk_sndbuf)) break; if (sk->sk_shutdown & SEND_SHUTDOWN) break; @@ -2218,7 +2227,7 @@ struct sk_buff *sock_alloc_send_pskb(struct sock *sk, unsigned long header_len, if (sk->sk_shutdown & SEND_SHUTDOWN) goto failure; - if (sk_wmem_alloc_get(sk) < sk->sk_sndbuf) + if (sk_wmem_alloc_get(sk) < READ_ONCE(sk->sk_sndbuf)) break; sk_set_bit(SOCKWQ_ASYNC_NOSPACE, sk); @@ -2720,6 +2729,27 @@ int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct * } EXPORT_SYMBOL(sock_no_mmap); +/* + * When a file is received (via SCM_RIGHTS, etc), we must bump the + * various sock-based usage counts. + */ +void __receive_sock(struct file *file) +{ + struct socket *sock; + int error; + + /* + * The resulting value of "error" is ignored here since we only + * need to take action when the file is a socket and testing + * "sock" for NULL is sufficient. + */ + sock = sock_from_file(file, &error); + if (sock) { + sock_update_netprioidx(&sock->sk->sk_cgrp_data); + sock_update_classid(&sock->sk->sk_cgrp_data); + } +} + ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { ssize_t res; @@ -2799,7 +2829,7 @@ static void sock_def_write_space(struct sock *sk) /* Do not wake up a writer until he can make "significant" * progress. --DaveM */ - if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= sk->sk_sndbuf) { + if ((refcount_read(&sk->sk_wmem_alloc) << 1) <= READ_ONCE(sk->sk_sndbuf)) { wq = rcu_dereference(sk->sk_wq); if (skwq_has_sleeper(wq)) wake_up_interruptible_sync_poll(&wq->wait, EPOLLOUT | @@ -2907,7 +2937,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_max_pacing_rate = ~0UL; sk->sk_pacing_rate = ~0UL; - sk->sk_pacing_shift = 10; + WRITE_ONCE(sk->sk_pacing_shift, 10); sk->sk_incoming_cpu = -1; sk_rx_queue_clear(sk); @@ -3197,13 +3227,13 @@ void sk_get_meminfo(const struct sock *sk, u32 *mem) memset(mem, 0, sizeof(*mem) * SK_MEMINFO_VARS); mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk); - mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf; + mem[SK_MEMINFO_RCVBUF] = READ_ONCE(sk->sk_rcvbuf); mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk); - mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf; + mem[SK_MEMINFO_SNDBUF] = READ_ONCE(sk->sk_sndbuf); mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; - mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; + mem[SK_MEMINFO_WMEM_QUEUED] = READ_ONCE(sk->sk_wmem_queued); mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); } @@ -3578,7 +3608,7 @@ bool sk_busy_loop_end(void *p, unsigned long start_time) { struct sock *sk = p; - return !skb_queue_empty(&sk->sk_receive_queue) || + return !skb_queue_empty_lockless(&sk->sk_receive_queue) || sk_busy_loop_timeout(sk, start_time); } EXPORT_SYMBOL(sk_busy_loop_end); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index 3b14de0e36d2..285976f79cba 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -238,20 +238,26 @@ static void sock_map_free(struct bpf_map *map) struct bpf_stab *stab = container_of(map, struct bpf_stab, map); int i; + /* After the sync no updates or deletes will be in-flight so it + * is safe to walk map and remove entries without risking a race + * in EEXIST update case. + */ synchronize_rcu(); - rcu_read_lock(); - raw_spin_lock_bh(&stab->lock); for (i = 0; i < stab->map.max_entries; i++) { struct sock **psk = &stab->sks[i]; struct sock *sk; sk = xchg(psk, NULL); - if (sk) + if (sk) { + lock_sock(sk); + rcu_read_lock(); sock_map_unref(sk, psk); + release_sock(sk); + rcu_read_unlock(); + } } - raw_spin_unlock_bh(&stab->lock); - rcu_read_unlock(); + /* wait for psock readers accessing its map link */ synchronize_rcu(); bpf_map_area_free(stab->sks); @@ -418,14 +424,16 @@ static int sock_map_update_elem(struct bpf_map *map, void *key, ret = -EINVAL; goto out; } - if (!sock_map_sk_is_suitable(sk) || - sk->sk_state != TCP_ESTABLISHED) { + if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); - ret = sock_map_update_common(map, idx, sk, flags); + if (sk->sk_state != TCP_ESTABLISHED) + ret = -EOPNOTSUPP; + else + ret = sock_map_update_common(map, idx, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); @@ -741,14 +749,16 @@ static int sock_hash_update_elem(struct bpf_map *map, void *key, ret = -EINVAL; goto out; } - if (!sock_map_sk_is_suitable(sk) || - sk->sk_state != TCP_ESTABLISHED) { + if (!sock_map_sk_is_suitable(sk)) { ret = -EOPNOTSUPP; goto out; } sock_map_sk_acquire(sk); - ret = sock_hash_update_common(map, key, sk, flags); + if (sk->sk_state != TCP_ESTABLISHED) + ret = -EOPNOTSUPP; + else + ret = sock_hash_update_common(map, key, sk, flags); sock_map_sk_release(sk); out: fput(sock->file); @@ -856,22 +866,49 @@ static void sock_hash_free(struct bpf_map *map) { struct bpf_htab *htab = container_of(map, struct bpf_htab, map); struct bpf_htab_bucket *bucket; + struct hlist_head unlink_list; struct bpf_htab_elem *elem; struct hlist_node *node; int i; + /* After the sync no updates or deletes will be in-flight so it + * is safe to walk map and remove entries without risking a race + * in EEXIST update case. + */ synchronize_rcu(); - rcu_read_lock(); for (i = 0; i < htab->buckets_num; i++) { bucket = sock_hash_select_bucket(htab, i); + + /* We are racing with sock_hash_delete_from_link to + * enter the spin-lock critical section. Every socket on + * the list is still linked to sockhash. Since link + * exists, psock exists and holds a ref to socket. That + * lets us to grab a socket ref too. + */ raw_spin_lock_bh(&bucket->lock); - hlist_for_each_entry_safe(elem, node, &bucket->head, node) { - hlist_del_rcu(&elem->node); + hlist_for_each_entry(elem, &bucket->head, node) + sock_hold(elem->sk); + hlist_move_list(&bucket->head, &unlink_list); + raw_spin_unlock_bh(&bucket->lock); + + /* Process removed entries out of atomic context to + * block for socket lock before deleting the psock's + * link to sockhash. + */ + hlist_for_each_entry_safe(elem, node, &unlink_list, node) { + hlist_del(&elem->node); + rcu_read_lock(); + lock_sock(elem->sk); sock_map_unref(elem->sk, elem); + release_sock(elem->sk); + sock_put(elem->sk); + sock_hash_free_elem(htab, elem); + rcu_read_unlock(); } - raw_spin_unlock_bh(&bucket->lock); } - rcu_read_unlock(); + + /* wait for psock readers accessing its map link */ + synchronize_rcu(); bpf_map_area_free(htab->buckets); kfree(htab); diff --git a/net/core/sock_reuseport.c b/net/core/sock_reuseport.c index 2f89777763ad..3f1fe0958ff6 100644 --- a/net/core/sock_reuseport.c +++ b/net/core/sock_reuseport.c @@ -112,6 +112,7 @@ static struct sock_reuseport *reuseport_grow(struct sock_reuseport *reuse) more_reuse->prog = reuse->prog; more_reuse->reuseport_id = reuse->reuseport_id; more_reuse->bind_inany = reuse->bind_inany; + more_reuse->has_conns = reuse->has_conns; memcpy(more_reuse->socks, reuse->socks, reuse->num_socks * sizeof(struct sock *)); diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index f9204719aeee..50eeb0ef320e 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -290,6 +290,7 @@ static int proc_dointvec_minmax_bpf_enable(struct ctl_table *table, int write, return ret; } +# ifdef CONFIG_HAVE_EBPF_JIT static int proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, @@ -300,6 +301,7 @@ proc_dointvec_minmax_bpf_restricted(struct ctl_table *table, int write, return proc_dointvec_minmax(table, write, buffer, lenp, ppos); } +# endif /* CONFIG_HAVE_EBPF_JIT */ static int proc_dolongvec_minmax_bpf_restricted(struct ctl_table *table, int write, diff --git a/net/core/utils.c b/net/core/utils.c index 6b6e51db9f3b..1f31a39236d5 100644 --- a/net/core/utils.c +++ b/net/core/utils.c @@ -438,6 +438,23 @@ void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb, } EXPORT_SYMBOL(inet_proto_csum_replace4); +/** + * inet_proto_csum_replace16 - update layer 4 header checksum field + * @sum: Layer 4 header checksum field + * @skb: sk_buff for the packet + * @from: old IPv6 address + * @to: new IPv6 address + * @pseudohdr: True if layer 4 header checksum includes pseudoheader + * + * Update layer 4 header as per the update in IPv6 src/dst address. + * + * There is no need to update skb->csum in this function, because update in two + * fields a.) IPv6 src/dst address and b.) L4 header checksum cancels each other + * for skb->csum calculation. Whereas inet_proto_csum_replace4 function needs to + * update skb->csum, because update in 3 fields a.) IPv4 src/dst address, + * b.) IPv4 Header checksum and c.) L4 header checksum results in same diff as + * L4 Header checksum for skb->csum calculation. + */ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, const __be32 *from, const __be32 *to, bool pseudohdr) @@ -449,9 +466,6 @@ void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { *sum = csum_fold(csum_partial(diff, sizeof(diff), ~csum_unfold(*sum))); - if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr) - skb->csum = ~csum_partial(diff, sizeof(diff), - ~skb->csum); } else if (pseudohdr) *sum = ~csum_fold(csum_partial(diff, sizeof(diff), csum_unfold(*sum))); diff --git a/net/dccp/ipv4.c b/net/dccp/ipv4.c index b685bc82f8d0..6b8a602849dd 100644 --- a/net/dccp/ipv4.c +++ b/net/dccp/ipv4.c @@ -117,7 +117,7 @@ int dccp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) inet->inet_daddr, inet->inet_sport, inet->inet_dport); - inet->inet_id = dp->dccps_iss ^ jiffies; + inet->inet_id = prandom_u32(); err = dccp_connect(sk); rt = NULL; @@ -416,7 +416,7 @@ struct sock *dccp_v4_request_recv_sock(const struct sock *sk, RCU_INIT_POINTER(newinet->inet_opt, rcu_dereference(ireq->ireq_opt)); newinet->mc_index = inet_iif(skb); newinet->mc_ttl = ip_hdr(skb)->ttl; - newinet->inet_id = jiffies; + newinet->inet_id = prandom_u32(); if (dst == NULL && (dst = inet_csk_route_child_sock(sk, newsk, req)) == NULL) goto put_and_exit; diff --git a/net/dccp/ipv6.c b/net/dccp/ipv6.c index 85c10c8f50bd..65d5354f3e4f 100644 --- a/net/dccp/ipv6.c +++ b/net/dccp/ipv6.c @@ -210,7 +210,7 @@ static int dccp_v6_send_response(const struct sock *sk, struct request_sock *req final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); dst = NULL; @@ -281,7 +281,7 @@ static void dccp_v6_ctl_send_reset(const struct sock *sk, struct sk_buff *rxskb) security_skb_classify_flow(rxskb, flowi6_to_flowi(&fl6)); /* sk = NULL, but it is safe for now. RST socket required. */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(skb, dst); ip6_xmit(ctl_sk, skb, &fl6, 0, NULL, 0); @@ -911,7 +911,7 @@ static int dccp_v6_connect(struct sock *sk, struct sockaddr *uaddr, opt = rcu_dereference_protected(np->opt, lockdep_sock_is_held(sk)); final_p = fl6_update_dst(&fl6, opt, &final); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; diff --git a/net/dccp/proto.c b/net/dccp/proto.c index 5bad08dc4316..cb61a9d281f6 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -1139,14 +1139,14 @@ static int __init dccp_init(void) inet_hashinfo_init(&dccp_hashinfo); rc = inet_hashinfo2_init_mod(&dccp_hashinfo); if (rc) - goto out_fail; + goto out_free_percpu; rc = -ENOBUFS; dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out_free_percpu; + goto out_free_hashinfo2; /* * Size and allocate the main established and bind bucket @@ -1242,6 +1242,8 @@ out_free_dccp_ehash: free_pages((unsigned long)dccp_hashinfo.ehash, ehash_order); out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); +out_free_hashinfo2: + inet_hashinfo2_free_mod(&dccp_hashinfo); out_free_percpu: percpu_counter_destroy(&dccp_orphan_count); out_fail: @@ -1265,6 +1267,7 @@ static void __exit dccp_fini(void) kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_ackvec_exit(); dccp_sysctl_exit(); + inet_hashinfo2_free_mod(&dccp_hashinfo); percpu_counter_destroy(&dccp_orphan_count); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index 0ea75286abf4..3349ea81f901 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -1205,7 +1205,7 @@ static __poll_t dn_poll(struct file *file, struct socket *sock, poll_table *wai struct dn_scp *scp = DN_SK(sk); __poll_t mask = datagram_poll(file, sock, wait); - if (!skb_queue_empty(&scp->other_receive_queue)) + if (!skb_queue_empty_lockless(&scp->other_receive_queue)) mask |= EPOLLRDBAND; return mask; diff --git a/net/decnet/dn_route.c b/net/decnet/dn_route.c index aea918135ec3..08c3dc45f1a4 100644 --- a/net/decnet/dn_route.c +++ b/net/decnet/dn_route.c @@ -110,7 +110,8 @@ static void dn_dst_ifdown(struct dst_entry *, struct net_device *dev, int how); static struct dst_entry *dn_dst_negative_advice(struct dst_entry *); static void dn_dst_link_failure(struct sk_buff *); static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb , u32 mtu); + struct sk_buff *skb , u32 mtu, + bool confirm_neigh); static void dn_dst_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static struct neighbour *dn_dst_neigh_lookup(const struct dst_entry *dst, @@ -251,7 +252,8 @@ static int dn_dst_gc(struct dst_ops *ops) * advertise to the other end). */ static void dn_dst_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct dn_route *rt = (struct dn_route *) dst; struct neighbour *n = rt->n; diff --git a/net/dns_resolver/dns_key.c b/net/dns_resolver/dns_key.c index a65d553e730d..b13599277601 100644 --- a/net/dns_resolver/dns_key.c +++ b/net/dns_resolver/dns_key.c @@ -302,7 +302,7 @@ static void dns_resolver_describe(const struct key *key, struct seq_file *m) * - the key's semaphore is read-locked */ static long dns_resolver_read(const struct key *key, - char __user *buffer, size_t buflen) + char *buffer, size_t buflen) { int err = PTR_ERR(key->payload.data[dns_key_error]); diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index 1739b98a8f4b..1f2ef2922b96 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -46,7 +46,7 @@ static struct dsa_switch_tree *dsa_tree_alloc(int index) dst->index = index; INIT_LIST_HEAD(&dst->list); - list_add_tail(&dsa_tree_list, &dst->list); + list_add_tail(&dst->list, &dsa_tree_list); kref_init(&dst->refcount); @@ -426,7 +426,7 @@ static int dsa_tree_setup_switches(struct dsa_switch_tree *dst) err = dsa_port_setup(dp); if (err) - return err; + continue; } } diff --git a/net/dsa/master.c b/net/dsa/master.c index 4b52f8bac5e1..9f29a90cd66c 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -193,7 +193,8 @@ static void dsa_master_ndo_teardown(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; - dev->netdev_ops = cpu_dp->orig_ndo_ops; + if (cpu_dp->orig_ndo_ops) + dev->netdev_ops = cpu_dp->orig_ndo_ops; cpu_dp->orig_ndo_ops = NULL; } diff --git a/net/dsa/tag_brcm.c b/net/dsa/tag_brcm.c index 9c3114179690..9169b63a89e3 100644 --- a/net/dsa/tag_brcm.c +++ b/net/dsa/tag_brcm.c @@ -140,6 +140,8 @@ static struct sk_buff *brcm_tag_rcv_ll(struct sk_buff *skb, /* Remove Broadcom tag and update checksum */ skb_pull_rcsum(skb, BRCM_TAG_LEN); + skb->offload_fwd_mark = 1; + return skb; } #endif diff --git a/net/dsa/tag_gswip.c b/net/dsa/tag_gswip.c index b678160bbd66..408d4af390a0 100644 --- a/net/dsa/tag_gswip.c +++ b/net/dsa/tag_gswip.c @@ -104,7 +104,7 @@ static struct sk_buff *gswip_tag_rcv(struct sk_buff *skb, } static const struct dsa_device_ops gswip_netdev_ops = { - .name = "gwsip", + .name = "gswip", .proto = DSA_TAG_PROTO_GSWIP, .xmit = gswip_tag_xmit, .rcv = gswip_tag_rcv, diff --git a/net/dsa/tag_mtk.c b/net/dsa/tag_mtk.c index b5705cba8318..d6619edd53e5 100644 --- a/net/dsa/tag_mtk.c +++ b/net/dsa/tag_mtk.c @@ -15,6 +15,7 @@ #define MTK_HDR_XMIT_TAGGED_TPID_8100 1 #define MTK_HDR_RECV_SOURCE_PORT_MASK GENMASK(2, 0) #define MTK_HDR_XMIT_DP_BIT_MASK GENMASK(5, 0) +#define MTK_HDR_XMIT_SA_DIS BIT(6) static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct net_device *dev) @@ -22,6 +23,9 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, struct dsa_port *dp = dsa_slave_to_port(dev); u8 *mtk_tag; bool is_vlan_skb = true; + unsigned char *dest = eth_hdr(skb)->h_dest; + bool is_multicast_skb = is_multicast_ether_addr(dest) && + !is_broadcast_ether_addr(dest); /* Build the special tag after the MAC Source Address. If VLAN header * is present, it's required that VLAN header and special tag is @@ -47,6 +51,10 @@ static struct sk_buff *mtk_tag_xmit(struct sk_buff *skb, MTK_HDR_XMIT_UNTAGGED; mtk_tag[1] = (1 << dp->index) & MTK_HDR_XMIT_DP_BIT_MASK; + /* Disable SA learning for multicast frames */ + if (unlikely(is_multicast_skb)) + mtk_tag[1] |= MTK_HDR_XMIT_SA_DIS; + /* Tag control information is kept for 802.1Q */ if (!is_vlan_skb) { mtk_tag[2] = 0; @@ -61,6 +69,9 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, { int port; __be16 *phdr, hdr; + unsigned char *dest = eth_hdr(skb)->h_dest; + bool is_multicast_skb = is_multicast_ether_addr(dest) && + !is_broadcast_ether_addr(dest); if (unlikely(!pskb_may_pull(skb, MTK_HDR_LEN))) return NULL; @@ -86,6 +97,10 @@ static struct sk_buff *mtk_tag_rcv(struct sk_buff *skb, struct net_device *dev, if (!skb->dev) return NULL; + /* Only unicast or broadcast frames are offloaded */ + if (likely(!is_multicast_skb)) + skb->offload_fwd_mark = 1; + return skb; } diff --git a/net/dsa/tag_qca.c b/net/dsa/tag_qca.c index c95885215525..70db7c909f74 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -33,10 +33,7 @@ static struct sk_buff *qca_tag_xmit(struct sk_buff *skb, struct net_device *dev) struct dsa_port *dp = dsa_slave_to_port(dev); u16 *phdr, hdr; - dev->stats.tx_packets++; - dev->stats.tx_bytes += skb->len; - - if (skb_cow_head(skb, 0) < 0) + if (skb_cow_head(skb, QCA_HDR_LEN) < 0) return NULL; skb_push(skb, QCA_HDR_LEN); diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index 20b0bcb7e9e3..c5a729118052 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -244,7 +244,12 @@ int eth_header_cache(const struct neighbour *neigh, struct hh_cache *hh, __be16 eth->h_proto = type; memcpy(eth->h_source, dev->dev_addr, ETH_ALEN); memcpy(eth->h_dest, neigh->ha, ETH_ALEN); - hh->hh_len = ETH_HLEN; + + /* Pairs with READ_ONCE() in neigh_resolve_output(), + * neigh_hh_output() and neigh_update_hhs(). + */ + smp_store_release(&hh->hh_len, ETH_HLEN); + return 0; } EXPORT_SYMBOL(eth_header_cache); diff --git a/net/hsr/hsr_debugfs.c b/net/hsr/hsr_debugfs.c index 94447974a3c0..d5f709b940ff 100644 --- a/net/hsr/hsr_debugfs.c +++ b/net/hsr/hsr_debugfs.c @@ -20,6 +20,8 @@ #include "hsr_main.h" #include "hsr_framereg.h" +static struct dentry *hsr_debugfs_root_dir; + static void print_mac_address(struct seq_file *sfp, unsigned char *mac) { seq_printf(sfp, "%02x:%02x:%02x:%02x:%02x:%02x:", @@ -63,8 +65,20 @@ hsr_node_table_open(struct inode *inode, struct file *filp) return single_open(filp, hsr_node_table_show, inode->i_private); } +void hsr_debugfs_rename(struct net_device *dev) +{ + struct hsr_priv *priv = netdev_priv(dev); + struct dentry *d; + + d = debugfs_rename(hsr_debugfs_root_dir, priv->node_tbl_root, + hsr_debugfs_root_dir, dev->name); + if (IS_ERR(d)) + netdev_warn(dev, "failed to rename\n"); + else + priv->node_tbl_root = d; +} + static const struct file_operations hsr_fops = { - .owner = THIS_MODULE, .open = hsr_node_table_open, .read = seq_read, .llseek = seq_lseek, @@ -78,15 +92,14 @@ static const struct file_operations hsr_fops = { * When debugfs is configured this routine sets up the node_table file per * hsr device for dumping the node_table entries */ -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) { - int rc = -1; struct dentry *de = NULL; - de = debugfs_create_dir(hsr_dev->name, NULL); - if (!de) { - pr_err("Cannot create hsr debugfs root\n"); - return rc; + de = debugfs_create_dir(hsr_dev->name, hsr_debugfs_root_dir); + if (IS_ERR(de)) { + pr_err("Cannot create hsr debugfs directory\n"); + return; } priv->node_tbl_root = de; @@ -94,13 +107,13 @@ int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev) de = debugfs_create_file("node_table", S_IFREG | 0444, priv->node_tbl_root, priv, &hsr_fops); - if (!de) { - pr_err("Cannot create hsr node_table directory\n"); - return rc; + if (IS_ERR(de)) { + pr_err("Cannot create hsr node_table file\n"); + debugfs_remove(priv->node_tbl_root); + priv->node_tbl_root = NULL; + return; } priv->node_tbl_file = de; - - return 0; } /* hsr_debugfs_term - Tear down debugfs intrastructure @@ -117,3 +130,18 @@ hsr_debugfs_term(struct hsr_priv *priv) debugfs_remove(priv->node_tbl_root); priv->node_tbl_root = NULL; } + +void hsr_debugfs_create_root(void) +{ + hsr_debugfs_root_dir = debugfs_create_dir("hsr", NULL); + if (IS_ERR(hsr_debugfs_root_dir)) { + pr_err("Cannot create hsr debugfs root directory\n"); + hsr_debugfs_root_dir = NULL; + } +} + +void hsr_debugfs_remove_root(void) +{ + /* debugfs_remove() internally checks NULL and ERROR */ + debugfs_remove(hsr_debugfs_root_dir); +} diff --git a/net/hsr/hsr_device.c b/net/hsr/hsr_device.c index 08c02dbb3d69..acda3aa994c2 100644 --- a/net/hsr/hsr_device.c +++ b/net/hsr/hsr_device.c @@ -227,8 +227,13 @@ static int hsr_dev_xmit(struct sk_buff *skb, struct net_device *dev) struct hsr_port *master; master = hsr_port_get_hsr(hsr, HSR_PT_MASTER); - skb->dev = master->dev; - hsr_forward_skb(skb, master); + if (master) { + skb->dev = master->dev; + hsr_forward_skb(skb, master); + } else { + atomic_long_inc(&dev->tx_dropped); + dev_kfree_skb_any(skb); + } return NETDEV_TX_OK; } @@ -267,6 +272,8 @@ static void send_hsr_supervision_frame(struct hsr_port *master, skb->dev->dev_addr, skb->len) <= 0) goto out; skb_reset_mac_header(skb); + skb_reset_network_header(skb); + skb_reset_transport_header(skb); if (hsr_ver > 0) { hsr_tag = skb_put(skb, sizeof(struct hsr_tag)); @@ -362,7 +369,7 @@ static void hsr_dev_destroy(struct net_device *hsr_dev) del_timer_sync(&hsr->prune_timer); del_timer_sync(&hsr->announce_timer); - hsr_del_self_node(&hsr->self_node_db); + hsr_del_self_node(hsr); hsr_del_nodes(&hsr->node_db); } @@ -433,11 +440,12 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], INIT_LIST_HEAD(&hsr->ports); INIT_LIST_HEAD(&hsr->node_db); INIT_LIST_HEAD(&hsr->self_node_db); + spin_lock_init(&hsr->list_lock); ether_addr_copy(hsr_dev->dev_addr, slave[0]->dev_addr); /* Make sure we recognize frames from ourselves in hsr_rcv() */ - res = hsr_create_self_node(&hsr->self_node_db, hsr_dev->dev_addr, + res = hsr_create_self_node(hsr, hsr_dev->dev_addr, slave[1]->dev_addr); if (res < 0) return res; @@ -470,31 +478,32 @@ int hsr_dev_finalize(struct net_device *hsr_dev, struct net_device *slave[2], res = hsr_add_port(hsr, hsr_dev, HSR_PT_MASTER); if (res) - goto err_add_port; + goto err_add_master; res = register_netdevice(hsr_dev); if (res) - goto fail; + goto err_unregister; res = hsr_add_port(hsr, slave[0], HSR_PT_SLAVE_A); if (res) - goto fail; + goto err_add_slaves; + res = hsr_add_port(hsr, slave[1], HSR_PT_SLAVE_B); if (res) - goto fail; + goto err_add_slaves; + hsr_debugfs_init(hsr, hsr_dev); mod_timer(&hsr->prune_timer, jiffies + msecs_to_jiffies(PRUNE_PERIOD)); - res = hsr_debugfs_init(hsr, hsr_dev); - if (res) - goto fail; return 0; -fail: +err_add_slaves: + unregister_netdevice(hsr_dev); +err_unregister: hsr_for_each_port(hsr, port) hsr_del_port(port); -err_add_port: - hsr_del_self_node(&hsr->self_node_db); +err_add_master: + hsr_del_self_node(hsr); return res; } diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 292be446007b..002f341f3564 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -75,10 +75,11 @@ static struct hsr_node *find_node_by_addr_A(struct list_head *node_db, /* Helper for device init; the self_node_db is used in hsr_rcv() to recognize * frames from self that's been looped over the HSR ring. */ -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node, *oldnode; node = kmalloc(sizeof(*node), GFP_KERNEL); @@ -88,33 +89,33 @@ int hsr_create_self_node(struct list_head *self_node_db, ether_addr_copy(node->macaddress_A, addr_a); ether_addr_copy(node->macaddress_B, addr_b); - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); oldnode = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); if (oldnode) { list_replace_rcu(&oldnode->mac_list, &node->mac_list); - rcu_read_unlock(); - synchronize_rcu(); - kfree(oldnode); + spin_unlock_bh(&hsr->list_lock); + kfree_rcu(oldnode, rcu_head); } else { - rcu_read_unlock(); list_add_tail_rcu(&node->mac_list, self_node_db); + spin_unlock_bh(&hsr->list_lock); } return 0; } -void hsr_del_self_node(struct list_head *self_node_db) +void hsr_del_self_node(struct hsr_priv *hsr) { + struct list_head *self_node_db = &hsr->self_node_db; struct hsr_node *node; - rcu_read_lock(); + spin_lock_bh(&hsr->list_lock); node = list_first_or_null_rcu(self_node_db, struct hsr_node, mac_list); - rcu_read_unlock(); if (node) { list_del_rcu(&node->mac_list); - kfree(node); + kfree_rcu(node, rcu_head); } + spin_unlock_bh(&hsr->list_lock); } void hsr_del_nodes(struct list_head *node_db) @@ -130,30 +131,43 @@ void hsr_del_nodes(struct list_head *node_db) * seq_out is used to initialize filtering of outgoing duplicate frames * originating from the newly added node. */ -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out) +static struct hsr_node *hsr_add_node(struct hsr_priv *hsr, + struct list_head *node_db, + unsigned char addr[], + u16 seq_out) { - struct hsr_node *node; + struct hsr_node *new_node, *node; unsigned long now; int i; - node = kzalloc(sizeof(*node), GFP_ATOMIC); - if (!node) + new_node = kzalloc(sizeof(*new_node), GFP_ATOMIC); + if (!new_node) return NULL; - ether_addr_copy(node->macaddress_A, addr); + ether_addr_copy(new_node->macaddress_A, addr); /* We are only interested in time diffs here, so use current jiffies * as initialization. (0 could trigger an spurious ring error warning). */ now = jiffies; for (i = 0; i < HSR_PT_PORTS; i++) - node->time_in[i] = now; + new_node->time_in[i] = now; for (i = 0; i < HSR_PT_PORTS; i++) - node->seq_out[i] = seq_out; - - list_add_tail_rcu(&node->mac_list, node_db); + new_node->seq_out[i] = seq_out; + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_rcu(node, node_db, mac_list) { + if (ether_addr_equal(node->macaddress_A, addr)) + goto out; + if (ether_addr_equal(node->macaddress_B, addr)) + goto out; + } + list_add_tail_rcu(&new_node->mac_list, node_db); + spin_unlock_bh(&hsr->list_lock); + return new_node; +out: + spin_unlock_bh(&hsr->list_lock); + kfree(new_node); return node; } @@ -163,6 +177,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup) { struct list_head *node_db = &port->hsr->node_db; + struct hsr_priv *hsr = port->hsr; struct hsr_node *node; struct ethhdr *ethhdr; u16 seq_out; @@ -196,7 +211,7 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, seq_out = HSR_SEQNR_START; } - return hsr_add_node(node_db, ethhdr->h_source, seq_out); + return hsr_add_node(hsr, node_db, ethhdr->h_source, seq_out); } /* Use the Supervision frame's info about an eventual macaddress_B for merging @@ -206,10 +221,11 @@ struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, struct hsr_port *port_rcv) { - struct ethhdr *ethhdr; - struct hsr_node *node_real; + struct hsr_priv *hsr = port_rcv->hsr; struct hsr_sup_payload *hsr_sp; + struct hsr_node *node_real; struct list_head *node_db; + struct ethhdr *ethhdr; int i; ethhdr = (struct ethhdr *)skb_mac_header(skb); @@ -231,7 +247,7 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, node_real = find_node_by_addr_A(node_db, hsr_sp->macaddress_A); if (!node_real) /* No frame received from AddrA of this node yet */ - node_real = hsr_add_node(node_db, hsr_sp->macaddress_A, + node_real = hsr_add_node(hsr, node_db, hsr_sp->macaddress_A, HSR_SEQNR_START - 1); if (!node_real) goto done; /* No mem */ @@ -252,7 +268,9 @@ void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, } node_real->addr_B_port = port_rcv->type; + spin_lock_bh(&hsr->list_lock); list_del_rcu(&node_curr->mac_list); + spin_unlock_bh(&hsr->list_lock); kfree_rcu(node_curr, rcu_head); done: @@ -368,12 +386,13 @@ void hsr_prune_nodes(struct timer_list *t) { struct hsr_priv *hsr = from_timer(hsr, t, prune_timer); struct hsr_node *node; + struct hsr_node *tmp; struct hsr_port *port; unsigned long timestamp; unsigned long time_a, time_b; - rcu_read_lock(); - list_for_each_entry_rcu(node, &hsr->node_db, mac_list) { + spin_lock_bh(&hsr->list_lock); + list_for_each_entry_safe(node, tmp, &hsr->node_db, mac_list) { /* Don't prune own node. Neither time_in[HSR_PT_SLAVE_A] * nor time_in[HSR_PT_SLAVE_B], will ever be updated for * the master port. Thus the master node will be repeatedly @@ -421,7 +440,7 @@ void hsr_prune_nodes(struct timer_list *t) kfree_rcu(node, rcu_head); } } - rcu_read_unlock(); + spin_unlock_bh(&hsr->list_lock); /* Restart timer */ mod_timer(&hsr->prune_timer, @@ -463,12 +482,9 @@ int hsr_get_node_data(struct hsr_priv *hsr, struct hsr_port *port; unsigned long tdiff; - rcu_read_lock(); node = find_node_by_addr_A(&hsr->node_db, addr); - if (!node) { - rcu_read_unlock(); - return -ENOENT; /* No such entry */ - } + if (!node) + return -ENOENT; ether_addr_copy(addr_b, node->macaddress_B); @@ -503,7 +519,5 @@ int hsr_get_node_data(struct hsr_priv *hsr, *addr_b_ifindex = -1; } - rcu_read_unlock(); - return 0; } diff --git a/net/hsr/hsr_framereg.h b/net/hsr/hsr_framereg.h index 89a3ce38151d..0f0fa12b4329 100644 --- a/net/hsr/hsr_framereg.h +++ b/net/hsr/hsr_framereg.h @@ -12,10 +12,8 @@ struct hsr_node; -void hsr_del_self_node(struct list_head *self_node_db); +void hsr_del_self_node(struct hsr_priv *hsr); void hsr_del_nodes(struct list_head *node_db); -struct hsr_node *hsr_add_node(struct list_head *node_db, unsigned char addr[], - u16 seq_out); struct hsr_node *hsr_get_node(struct hsr_port *port, struct sk_buff *skb, bool is_sup); void hsr_handle_sup_frame(struct sk_buff *skb, struct hsr_node *node_curr, @@ -33,7 +31,7 @@ int hsr_register_frame_out(struct hsr_port *port, struct hsr_node *node, void hsr_prune_nodes(struct timer_list *t); -int hsr_create_self_node(struct list_head *self_node_db, +int hsr_create_self_node(struct hsr_priv *hsr, unsigned char addr_a[ETH_ALEN], unsigned char addr_b[ETH_ALEN]); diff --git a/net/hsr/hsr_main.c b/net/hsr/hsr_main.c index b9988a662ee1..9e389accbfc7 100644 --- a/net/hsr/hsr_main.c +++ b/net/hsr/hsr_main.c @@ -45,6 +45,10 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, case NETDEV_CHANGE: /* Link (carrier) state changes */ hsr_check_carrier_and_operstate(hsr); break; + case NETDEV_CHANGENAME: + if (is_hsr_master(dev)) + hsr_debugfs_rename(dev); + break; case NETDEV_CHANGEADDR: if (port->type == HSR_PT_MASTER) { /* This should not happen since there's no @@ -64,7 +68,7 @@ static int hsr_netdev_notify(struct notifier_block *nb, unsigned long event, /* Make sure we recognize frames from ourselves in hsr_rcv() */ port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); - res = hsr_create_self_node(&hsr->self_node_db, + res = hsr_create_self_node(hsr, master->dev->dev_addr, port ? port->dev->dev_addr : @@ -123,6 +127,7 @@ static void __exit hsr_exit(void) { unregister_netdevice_notifier(&hsr_nb); hsr_netlink_exit(); + hsr_debugfs_remove_root(); } module_init(hsr_init); diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index 96fac696a1e1..754d84b217f0 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -160,8 +160,9 @@ struct hsr_priv { int announce_count; u16 sequence_nr; u16 sup_sequence_nr; /* For HSRv1 separate seq_nr for supervision */ - u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ - spinlock_t seqnr_lock; /* locking for sequence_nr */ + u8 prot_version; /* Indicate if HSRv0 or HSRv1. */ + spinlock_t seqnr_lock; /* locking for sequence_nr */ + spinlock_t list_lock; /* locking for node list */ unsigned char sup_multicast_addr[ETH_ALEN]; #ifdef CONFIG_DEBUG_FS struct dentry *node_tbl_root; @@ -184,17 +185,24 @@ static inline u16 hsr_get_skb_sequence_nr(struct sk_buff *skb) } #if IS_ENABLED(CONFIG_DEBUG_FS) -int hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); +void hsr_debugfs_rename(struct net_device *dev); +void hsr_debugfs_init(struct hsr_priv *priv, struct net_device *hsr_dev); void hsr_debugfs_term(struct hsr_priv *priv); +void hsr_debugfs_create_root(void); +void hsr_debugfs_remove_root(void); #else -static inline int hsr_debugfs_init(struct hsr_priv *priv, - struct net_device *hsr_dev) +static inline void hsr_debugfs_rename(struct net_device *dev) { - return 0; } - +static inline void hsr_debugfs_init(struct hsr_priv *priv, + struct net_device *hsr_dev) +{} static inline void hsr_debugfs_term(struct hsr_priv *priv) {} +static inline void hsr_debugfs_create_root(void) +{} +static inline void hsr_debugfs_remove_root(void) +{} #endif #endif /* __HSR_PRIVATE_H */ diff --git a/net/hsr/hsr_netlink.c b/net/hsr/hsr_netlink.c index 8f8337f893ba..55c0b2e872a5 100644 --- a/net/hsr/hsr_netlink.c +++ b/net/hsr/hsr_netlink.c @@ -61,10 +61,16 @@ static int hsr_newlink(struct net *src_net, struct net_device *dev, else multicast_spec = nla_get_u8(data[IFLA_HSR_MULTICAST_SPEC]); - if (!data[IFLA_HSR_VERSION]) + if (!data[IFLA_HSR_VERSION]) { hsr_version = 0; - else + } else { hsr_version = nla_get_u8(data[IFLA_HSR_VERSION]); + if (hsr_version > 1) { + NL_SET_ERR_MSG_MOD(extack, + "Only versions 0..1 are supported"); + return -EINVAL; + } + } return hsr_dev_finalize(dev, link, multicast_spec, hsr_version); } @@ -251,15 +257,16 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) if (!na) goto invalid; - hsr_dev = __dev_get_by_index(genl_info_net(info), - nla_get_u32(info->attrs[HSR_A_IFINDEX])); + rcu_read_lock(); + hsr_dev = dev_get_by_index_rcu(genl_info_net(info), + nla_get_u32(info->attrs[HSR_A_IFINDEX])); if (!hsr_dev) - goto invalid; + goto rcu_unlock; if (!is_hsr_master(hsr_dev)) - goto invalid; + goto rcu_unlock; /* Send reply */ - skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_ATOMIC); if (!skb_out) { res = -ENOMEM; goto fail; @@ -313,12 +320,10 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) res = nla_put_u16(skb_out, HSR_A_IF1_SEQ, hsr_node_if1_seq); if (res < 0) goto nla_put_failure; - rcu_read_lock(); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_A); if (port) res = nla_put_u32(skb_out, HSR_A_IF1_IFINDEX, port->dev->ifindex); - rcu_read_unlock(); if (res < 0) goto nla_put_failure; @@ -328,20 +333,22 @@ static int hsr_get_node_status(struct sk_buff *skb_in, struct genl_info *info) res = nla_put_u16(skb_out, HSR_A_IF2_SEQ, hsr_node_if2_seq); if (res < 0) goto nla_put_failure; - rcu_read_lock(); port = hsr_port_get_hsr(hsr, HSR_PT_SLAVE_B); if (port) res = nla_put_u32(skb_out, HSR_A_IF2_IFINDEX, port->dev->ifindex); - rcu_read_unlock(); if (res < 0) goto nla_put_failure; + rcu_read_unlock(); + genlmsg_end(skb_out, msg_head); genlmsg_unicast(genl_info_net(info), skb_out, info->snd_portid); return 0; +rcu_unlock: + rcu_read_unlock(); invalid: netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL); return 0; @@ -351,6 +358,7 @@ nla_put_failure: /* Fall through */ fail: + rcu_read_unlock(); return res; } @@ -358,16 +366,14 @@ fail: */ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) { - /* For receiving */ - struct nlattr *na; + unsigned char addr[ETH_ALEN]; struct net_device *hsr_dev; - - /* For sending */ struct sk_buff *skb_out; - void *msg_head; struct hsr_priv *hsr; - void *pos; - unsigned char addr[ETH_ALEN]; + bool restart = false; + struct nlattr *na; + void *pos = NULL; + void *msg_head; int res; if (!info) @@ -377,15 +383,17 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) if (!na) goto invalid; - hsr_dev = __dev_get_by_index(genl_info_net(info), - nla_get_u32(info->attrs[HSR_A_IFINDEX])); + rcu_read_lock(); + hsr_dev = dev_get_by_index_rcu(genl_info_net(info), + nla_get_u32(info->attrs[HSR_A_IFINDEX])); if (!hsr_dev) - goto invalid; + goto rcu_unlock; if (!is_hsr_master(hsr_dev)) - goto invalid; + goto rcu_unlock; +restart: /* Send reply */ - skb_out = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL); + skb_out = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_ATOMIC); if (!skb_out) { res = -ENOMEM; goto fail; @@ -399,18 +407,26 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) goto nla_put_failure; } - res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex); - if (res < 0) - goto nla_put_failure; + if (!restart) { + res = nla_put_u32(skb_out, HSR_A_IFINDEX, hsr_dev->ifindex); + if (res < 0) + goto nla_put_failure; + } hsr = netdev_priv(hsr_dev); - rcu_read_lock(); - pos = hsr_get_next_node(hsr, NULL, addr); + if (!pos) + pos = hsr_get_next_node(hsr, NULL, addr); while (pos) { res = nla_put(skb_out, HSR_A_NODE_ADDR, ETH_ALEN, addr); if (res < 0) { - rcu_read_unlock(); + if (res == -EMSGSIZE) { + genlmsg_end(skb_out, msg_head); + genlmsg_unicast(genl_info_net(info), skb_out, + info->snd_portid); + restart = true; + goto restart; + } goto nla_put_failure; } pos = hsr_get_next_node(hsr, pos, addr); @@ -422,15 +438,18 @@ static int hsr_get_node_list(struct sk_buff *skb_in, struct genl_info *info) return 0; +rcu_unlock: + rcu_read_unlock(); invalid: netlink_ack(skb_in, nlmsg_hdr(skb_in), -EINVAL, NULL); return 0; nla_put_failure: - kfree_skb(skb_out); + nlmsg_free(skb_out); /* Fall through */ fail: + rcu_read_unlock(); return res; } @@ -457,6 +476,7 @@ static struct genl_family hsr_genl_family __ro_after_init = { .version = 1, .maxattr = HSR_A_MAX, .policy = hsr_genl_policy, + .netnsok = true, .module = THIS_MODULE, .ops = hsr_ops, .n_ops = ARRAY_SIZE(hsr_ops), @@ -476,6 +496,7 @@ int __init hsr_netlink_init(void) if (rc) goto fail_genl_register_family; + hsr_debugfs_create_root(); return 0; fail_genl_register_family: diff --git a/net/hsr/hsr_slave.c b/net/hsr/hsr_slave.c index 88b6705ded83..279f2503d157 100644 --- a/net/hsr/hsr_slave.c +++ b/net/hsr/hsr_slave.c @@ -27,6 +27,8 @@ static rx_handler_result_t hsr_handle_frame(struct sk_buff **pskb) rcu_read_lock(); /* hsr->node_db, hsr->ports */ port = hsr_port_get_rcu(skb->dev); + if (!port) + goto finish_pass; if (hsr_addr_is_self(port->hsr, eth_hdr(skb)->h_source)) { /* Directly kill frames sent by ourselves */ @@ -143,16 +145,16 @@ int hsr_add_port(struct hsr_priv *hsr, struct net_device *dev, if (!port) return -ENOMEM; + port->hsr = hsr; + port->dev = dev; + port->type = type; + if (type != HSR_PT_MASTER) { res = hsr_portdev_setup(dev, port); if (res) goto fail_dev_setup; } - port->hsr = hsr; - port->dev = dev; - port->type = type; - list_add_tail_rcu(&port->port_list, &hsr->ports); synchronize_rcu(); diff --git a/net/ieee802154/nl_policy.c b/net/ieee802154/nl_policy.c index 2c7a38d76a3a..0672b2f01586 100644 --- a/net/ieee802154/nl_policy.c +++ b/net/ieee802154/nl_policy.c @@ -21,7 +21,13 @@ const struct nla_policy ieee802154_policy[IEEE802154_ATTR_MAX + 1] = { [IEEE802154_ATTR_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_PAN_ID] = { .type = NLA_U16, }, [IEEE802154_ATTR_CHANNEL] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BCN_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_SF_ORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_PAN_COORD] = { .type = NLA_U8, }, + [IEEE802154_ATTR_BAT_EXT] = { .type = NLA_U8, }, + [IEEE802154_ATTR_COORD_REALIGN] = { .type = NLA_U8, }, [IEEE802154_ATTR_PAGE] = { .type = NLA_U8, }, + [IEEE802154_ATTR_DEV_TYPE] = { .type = NLA_U8, }, [IEEE802154_ATTR_COORD_SHORT_ADDR] = { .type = NLA_U16, }, [IEEE802154_ATTR_COORD_HW_ADDR] = { .type = NLA_HW_ADDR, }, [IEEE802154_ATTR_COORD_PAN_ID] = { .type = NLA_U16, }, diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 974de4d20f25..955a7a3fcc42 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -303,6 +303,7 @@ config SYN_COOKIES config NET_IPVTI tristate "Virtual (secure) IP: tunneling" + depends on IPV6 || IPV6=n select INET_TUNNEL select NET_IP_TUNNEL select XFRM diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 376882215919..a23094b050f8 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -1258,7 +1258,8 @@ static int cipso_v4_parsetag_rbm(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; @@ -1439,7 +1440,8 @@ static int cipso_v4_parsetag_rng(const struct cipso_v4_doi *doi_def, return ret_val; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } return 0; @@ -1724,6 +1726,7 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) { unsigned char optbuf[sizeof(struct ip_options) + 40]; struct ip_options *opt = (struct ip_options *)optbuf; + int res; if (ip_hdr(skb)->protocol == IPPROTO_ICMP || error != -EACCES) return; @@ -1735,7 +1738,11 @@ void cipso_v4_error(struct sk_buff *skb, int error, u32 gateway) memset(opt, 0, sizeof(struct ip_options)); opt->optlen = ip_hdr(skb)->ihl*4 - sizeof(struct iphdr); - if (__ip_options_compile(dev_net(skb->dev), opt, skb, NULL)) + rcu_read_lock(); + res = __ip_options_compile(dev_net(skb->dev), opt, skb, NULL); + rcu_read_unlock(); + + if (res) return; if (gateway) diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 9a0fe0c2fa02..4a8550c49202 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -73,7 +73,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len reuseport_has_conns(sk, true); sk->sk_state = TCP_ESTABLISHED; sk_set_txhash(sk); - inet->inet_id = jiffies; + inet->inet_id = prandom_u32(); sk_dst_set(sk, &rt->dst); err = 0; diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c5ebfa199794..03c058aea500 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -275,6 +275,7 @@ static struct in_device *inetdev_init(struct net_device *dev) err = devinet_sysctl_register(in_dev); if (err) { in_dev->dead = 1; + neigh_parms_release(&arp_tbl, in_dev->arp_parms); in_dev_put(in_dev); in_dev = NULL; goto out; @@ -593,12 +594,15 @@ struct in_ifaddr *inet_ifa_byprefix(struct in_device *in_dev, __be32 prefix, return NULL; } -static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) +static int ip_mc_autojoin_config(struct net *net, bool join, + const struct in_ifaddr *ifa) { +#if defined(CONFIG_IP_MULTICAST) struct ip_mreqn mreq = { .imr_multiaddr.s_addr = ifa->ifa_address, .imr_ifindex = ifa->ifa_dev->dev->ifindex, }; + struct sock *sk = net->ipv4.mc_autojoin_sk; int ret; ASSERT_RTNL(); @@ -611,6 +615,9 @@ static int ip_mc_config(struct sock *sk, bool join, const struct in_ifaddr *ifa) release_sock(sk); return ret; +#else + return -EOPNOTSUPP; +#endif } static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -652,7 +659,7 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, continue; if (ipv4_is_multicast(ifa->ifa_address)) - ip_mc_config(net->ipv4.mc_autojoin_sk, false, ifa); + ip_mc_autojoin_config(net, false, ifa); __inet_del_ifa(in_dev, ifap, 1, nlh, NETLINK_CB(skb).portid); return 0; } @@ -914,8 +921,7 @@ static int inet_rtm_newaddr(struct sk_buff *skb, struct nlmsghdr *nlh, */ set_ifa_lifetime(ifa, valid_lft, prefered_lft); if (ifa->ifa_flags & IFA_F_MCAUTOJOIN) { - int ret = ip_mc_config(net->ipv4.mc_autojoin_sk, - true, ifa); + int ret = ip_mc_autojoin_config(net, true, ifa); if (ret < 0) { inet_free_ifa(ifa); @@ -1449,11 +1455,6 @@ skip: } } -static bool inetdev_valid_mtu(unsigned int mtu) -{ - return mtu >= IPV4_MIN_MTU; -} - static void inetdev_send_gratuitous_arp(struct net_device *dev, struct in_device *in_dev) diff --git a/net/ipv4/esp4_offload.c b/net/ipv4/esp4_offload.c index 2e5e377f50a1..80570e2504db 100644 --- a/net/ipv4/esp4_offload.c +++ b/net/ipv4/esp4_offload.c @@ -57,14 +57,14 @@ static struct sk_buff *esp4_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; xo = xfrm_offload(skb); - if (!xo) { - xfrm_state_put(x); + if (!xo) goto out_reset; - } } xo->flags |= XFRM_GRO; diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index e54c2bcbb465..dc0dbf06f354 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -886,7 +886,6 @@ int ip_valid_fib_dump_req(struct net *net, const struct nlmsghdr *nlh, return -EINVAL; } - filter->dump_all_families = (rtm->rtm_family == AF_UNSPEC); filter->flags = rtm->rtm_flags; filter->protocol = rtm->rtm_protocol; filter->rt_type = rtm->rtm_type; @@ -957,14 +956,16 @@ static int inet_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (filter.table_id) { tb = fib_get_table(net, filter.table_id); if (!tb) { - if (filter.dump_all_families) + if (rtnl_msg_family(cb->nlh) != PF_INET) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: FIB table does not exist"); return -ENOENT; } + rcu_read_lock(); err = fib_table_dump(tb, skb, cb, &filter); + rcu_read_unlock(); return skb->len ? : err; } @@ -1105,7 +1106,7 @@ void fib_modify_prefix_metric(struct in_ifaddr *ifa, u32 new_metric) if (!(dev->flags & IFF_UP) || ifa->ifa_flags & (IFA_F_SECONDARY | IFA_F_NOPREFIXROUTE) || ipv4_is_zeronet(prefix) || - prefix == ifa->ifa_local || ifa->ifa_prefixlen == 32) + (prefix == ifa->ifa_local && ifa->ifa_prefixlen == 32)) return; /* add the new */ diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index bfa49a88d03a..332b9c481fa4 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1008,7 +1008,7 @@ static int fib_check_nh_v4_gw(struct net *net, struct fib_nh *nh, u32 table, if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - if (table) + if (table && table != RT_TABLE_MAIN) tbl = fib_get_table(net, table); if (tbl) @@ -1652,8 +1652,8 @@ int fib_sync_down_addr(struct net_device *dev, __be32 local) int ret = 0; unsigned int hash = fib_laddr_hashfn(local); struct hlist_head *head = &fib_info_laddrhash[hash]; + int tb_id = l3mdev_fib_table(dev) ? : RT_TABLE_MAIN; struct net *net = dev_net(dev); - int tb_id = l3mdev_fib_table(dev); struct fib_info *fi; if (!fib_info_laddrhash || local == 0) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 868c74771fa9..4c6f04b6afba 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1738,7 +1738,7 @@ struct fib_table *fib_trie_unmerge(struct fib_table *oldtb) while ((l = leaf_walk_rcu(&tp, key)) != NULL) { struct key_vector *local_l = NULL, *local_tp; - hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + hlist_for_each_entry(fa, &l->leaf, fa_list) { struct fib_alias *new_fa; if (local_tb->tb_id != fa->tb_id) @@ -2067,6 +2067,12 @@ int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, int count = cb->args[2]; t_key key = cb->args[3]; + /* First time here, count and key are both always 0. Count > 0 + * and key == 0 means the dump has wrapped around and we are done. + */ + if (count && !key) + return skb->len; + while ((l = leaf_walk_rcu(&tp, key)) != NULL) { int err; @@ -2341,6 +2347,7 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) " %zd bytes, size of tnode: %zd bytes.\n", LEAF_SIZE, TNODE_SIZE(0)); + rcu_read_lock(); for (h = 0; h < FIB_TABLE_HASHSZ; h++) { struct hlist_head *head = &net->ipv4.fib_table_hash[h]; struct fib_table *tb; @@ -2360,7 +2367,9 @@ static int fib_triestat_seq_show(struct seq_file *seq, void *v) trie_show_usage(seq, t->stats); #endif } + cond_resched_rcu(); } + rcu_read_unlock(); return 0; } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 30fa771d382a..dcc79ff54b41 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -662,8 +662,8 @@ static const struct nla_policy fou_nl_policy[FOU_ATTR_MAX + 1] = { [FOU_ATTR_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG, }, [FOU_ATTR_LOCAL_V4] = { .type = NLA_U32, }, [FOU_ATTR_PEER_V4] = { .type = NLA_U32, }, - [FOU_ATTR_LOCAL_V6] = { .type = sizeof(struct in6_addr), }, - [FOU_ATTR_PEER_V6] = { .type = sizeof(struct in6_addr), }, + [FOU_ATTR_LOCAL_V6] = { .len = sizeof(struct in6_addr), }, + [FOU_ATTR_PEER_V6] = { .len = sizeof(struct in6_addr), }, [FOU_ATTR_PEER_PORT] = { .type = NLA_U16, }, [FOU_ATTR_IFINDEX] = { .type = NLA_S32, }, }; diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 293acfb36376..7fd73e4258bf 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -56,7 +56,9 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -/* Fills in tpi and returns header length to be pulled. */ +/* Fills in tpi and returns header length to be pulled. + * Note that caller must use pskb_may_pull() before pulling GRE header. + */ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, bool *csum_err, __be16 proto, int nhs) { @@ -110,8 +112,14 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header */ if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + u8 _val, *val; + + val = skb_header_pointer(skb, nhs + hdr_len, + sizeof(_val), &_val); + if (!val) + return -EINVAL; tpi->proto = proto; - if ((*(u8 *)options & 0xF0) != 0x40) + if ((*val & 0xF0) != 0x40) hdr_len += 4; } tpi->hdr_len = hdr_len; @@ -127,7 +135,7 @@ int gre_parse_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, if (!pskb_may_pull(skb, nhs + hdr_len + sizeof(*ershdr))) return -EINVAL; - ershdr = (struct erspan_base_hdr *)options; + ershdr = (struct erspan_base_hdr *)(skb->data + nhs + hdr_len); tpi->key = cpu_to_be32(get_session_id(ershdr)); } diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c index 4de7e962d3da..c840141876bc 100644 --- a/net/ipv4/gre_offload.c +++ b/net/ipv4/gre_offload.c @@ -15,12 +15,12 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, netdev_features_t features) { int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + bool need_csum, need_recompute_csum, gso_partial; struct sk_buff *segs = ERR_PTR(-EINVAL); u16 mac_offset = skb->mac_header; __be16 protocol = skb->protocol; u16 mac_len = skb->mac_len; int gre_offset, outer_hlen; - bool need_csum, gso_partial; if (!skb->encapsulation) goto out; @@ -41,6 +41,7 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, skb->protocol = skb->inner_protocol; need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM); + need_recompute_csum = skb->csum_not_inet; skb->encap_hdr_csum = need_csum; features &= skb->dev->hw_enc_features; @@ -98,7 +99,15 @@ static struct sk_buff *gre_gso_segment(struct sk_buff *skb, } *(pcsum + 1) = 0; - *pcsum = gso_make_checksum(skb, 0); + if (need_recompute_csum && !skb_is_gso(skb)) { + __wsum csum; + + csum = skb_checksum(skb, gre_offset, + skb->len - gre_offset, 0); + *pcsum = csum_fold(csum); + } else { + *pcsum = gso_make_checksum(skb, 0); + } } while ((skb = skb->next)); out: return segs; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 92b3d2d1139e..432a5fc4890a 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -249,10 +249,11 @@ bool icmp_global_allow(void) bool rc = false; /* Check if token bucket is empty and cannot be refilled - * without taking the spinlock. + * without taking the spinlock. The READ_ONCE() are paired + * with the following WRITE_ONCE() in this same function. */ - if (!icmp_global.credit) { - delta = min_t(u32, now - icmp_global.stamp, HZ); + if (!READ_ONCE(icmp_global.credit)) { + delta = min_t(u32, now - READ_ONCE(icmp_global.stamp), HZ); if (delta < HZ / 50) return false; } @@ -262,14 +263,14 @@ bool icmp_global_allow(void) if (delta >= HZ / 50) { incr = sysctl_icmp_msgs_per_sec * delta / HZ ; if (incr) - icmp_global.stamp = now; + WRITE_ONCE(icmp_global.stamp, now); } credit = min_t(u32, icmp_global.credit + incr, sysctl_icmp_msgs_burst); if (credit) { credit--; rc = true; } - icmp_global.credit = credit; + WRITE_ONCE(icmp_global.credit, credit); spin_unlock(&icmp_global.lock); return rc; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index e4fa9e5833e4..92b31d251da8 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -24,17 +24,19 @@ #include <net/addrconf.h> #if IS_ENABLED(CONFIG_IPV6) -/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 - * only, and any IPv4 addresses if not IPv6 only - * match_wildcard == false: addresses must be exactly the same, i.e. - * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, - * and 0.0.0.0 equals to 0.0.0.0 only +/* match_sk*_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses + * if IPv6 only, and any IPv4 addresses + * if not IPv6 only + * match_sk*_wildcard == false: addresses must be exactly the same, i.e. + * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, + * and 0.0.0.0 equals to 0.0.0.0 only */ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, const struct in6_addr *sk2_rcv_saddr6, __be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, bool sk1_ipv6only, bool sk2_ipv6only, - bool match_wildcard) + bool match_sk1_wildcard, + bool match_sk2_wildcard) { int addr_type = ipv6_addr_type(sk1_rcv_saddr6); int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; @@ -44,8 +46,8 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; - if (!sk1_rcv_saddr || !sk2_rcv_saddr) - return match_wildcard; + return (match_sk1_wildcard && !sk1_rcv_saddr) || + (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } @@ -53,11 +55,11 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) return true; - if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && + if (addr_type2 == IPV6_ADDR_ANY && match_sk2_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return true; - if (addr_type == IPV6_ADDR_ANY && match_wildcard && + if (addr_type == IPV6_ADDR_ANY && match_sk1_wildcard && !(sk1_ipv6only && addr_type2 == IPV6_ADDR_MAPPED)) return true; @@ -69,18 +71,19 @@ static bool ipv6_rcv_saddr_equal(const struct in6_addr *sk1_rcv_saddr6, } #endif -/* match_wildcard == true: 0.0.0.0 equals to any IPv4 addresses - * match_wildcard == false: addresses must be exactly the same, i.e. - * 0.0.0.0 only equals to 0.0.0.0 +/* match_sk*_wildcard == true: 0.0.0.0 equals to any IPv4 addresses + * match_sk*_wildcard == false: addresses must be exactly the same, i.e. + * 0.0.0.0 only equals to 0.0.0.0 */ static bool ipv4_rcv_saddr_equal(__be32 sk1_rcv_saddr, __be32 sk2_rcv_saddr, - bool sk2_ipv6only, bool match_wildcard) + bool sk2_ipv6only, bool match_sk1_wildcard, + bool match_sk2_wildcard) { if (!sk2_ipv6only) { if (sk1_rcv_saddr == sk2_rcv_saddr) return true; - if (!sk1_rcv_saddr || !sk2_rcv_saddr) - return match_wildcard; + return (match_sk1_wildcard && !sk1_rcv_saddr) || + (match_sk2_wildcard && !sk2_rcv_saddr); } return false; } @@ -96,10 +99,12 @@ bool inet_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, sk2->sk_rcv_saddr, ipv6_only_sock(sk), ipv6_only_sock(sk2), + match_wildcard, match_wildcard); #endif return ipv4_rcv_saddr_equal(sk->sk_rcv_saddr, sk2->sk_rcv_saddr, - ipv6_only_sock(sk2), match_wildcard); + ipv6_only_sock(sk2), match_wildcard, + match_wildcard); } EXPORT_SYMBOL(inet_rcv_saddr_equal); @@ -273,10 +278,61 @@ static inline int sk_reuseport_match(struct inet_bind_bucket *tb, tb->fast_rcv_saddr, sk->sk_rcv_saddr, tb->fast_ipv6_only, - ipv6_only_sock(sk), true); + ipv6_only_sock(sk), true, false); #endif return ipv4_rcv_saddr_equal(tb->fast_rcv_saddr, sk->sk_rcv_saddr, - ipv6_only_sock(sk), true); + ipv6_only_sock(sk), true, false); +} + +void inet_csk_update_fastreuse(struct inet_bind_bucket *tb, + struct sock *sk) +{ + kuid_t uid = sock_i_uid(sk); + bool reuse = sk->sk_reuse && sk->sk_state != TCP_LISTEN; + + if (hlist_empty(&tb->owners)) { + tb->fastreuse = reuse; + if (sk->sk_reuseport) { + tb->fastreuseport = FASTREUSEPORT_ANY; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } else { + tb->fastreuseport = 0; + } + } else { + if (!reuse) + tb->fastreuse = 0; + if (sk->sk_reuseport) { + /* We didn't match or we don't have fastreuseport set on + * the tb, but we have sk_reuseport set on this socket + * and we know that there are no bind conflicts with + * this socket in this tb, so reset our tb's reuseport + * settings so that any subsequent sockets that match + * our current socket will be put on the fast path. + * + * If we reset we need to set FASTREUSEPORT_STRICT so we + * do extra checking for all subsequent sk_reuseport + * socks. + */ + if (!sk_reuseport_match(tb, sk)) { + tb->fastreuseport = FASTREUSEPORT_STRICT; + tb->fastuid = uid; + tb->fast_rcv_saddr = sk->sk_rcv_saddr; + tb->fast_ipv6_only = ipv6_only_sock(sk); + tb->fast_sk_family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; +#endif + } + } else { + tb->fastreuseport = 0; + } + } } /* Obtain a reference to a local port for the given sock, @@ -291,7 +347,6 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) struct inet_bind_hashbucket *head; struct net *net = sock_net(sk); struct inet_bind_bucket *tb = NULL; - kuid_t uid = sock_i_uid(sk); int l3mdev; l3mdev = inet_sk_bound_l3mdev(sk); @@ -328,49 +383,8 @@ tb_found: goto fail_unlock; } success: - if (hlist_empty(&tb->owners)) { - tb->fastreuse = reuse; - if (sk->sk_reuseport) { - tb->fastreuseport = FASTREUSEPORT_ANY; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } else { - tb->fastreuseport = 0; - } - } else { - if (!reuse) - tb->fastreuse = 0; - if (sk->sk_reuseport) { - /* We didn't match or we don't have fastreuseport set on - * the tb, but we have sk_reuseport set on this socket - * and we know that there are no bind conflicts with - * this socket in this tb, so reset our tb's reuseport - * settings so that any subsequent sockets that match - * our current socket will be put on the fast path. - * - * If we reset we need to set FASTREUSEPORT_STRICT so we - * do extra checking for all subsequent sk_reuseport - * socks. - */ - if (!sk_reuseport_match(tb, sk)) { - tb->fastreuseport = FASTREUSEPORT_STRICT; - tb->fastuid = uid; - tb->fast_rcv_saddr = sk->sk_rcv_saddr; - tb->fast_ipv6_only = ipv6_only_sock(sk); - tb->fast_sk_family = sk->sk_family; -#if IS_ENABLED(CONFIG_IPV6) - tb->fast_v6_rcv_saddr = sk->sk_v6_rcv_saddr; -#endif - } - } else { - tb->fastreuseport = 0; - } - } + inet_csk_update_fastreuse(tb, sk); + if (!inet_csk(sk)->icsk_bind_hash) inet_bind_hash(sk, tb, port); WARN_ON(inet_csk(sk)->icsk_bind_hash != tb); @@ -482,8 +496,28 @@ struct sock *inet_csk_accept(struct sock *sk, int flags, int *err, bool kern) } spin_unlock_bh(&queue->fastopenq.lock); } + out: release_sock(sk); + if (newsk && mem_cgroup_sockets_enabled) { + int amt; + + /* atomically get the memory usage, set and charge the + * newsk->sk_memcg. + */ + lock_sock(newsk); + + /* The socket has not been accepted yet, no need to look at + * newsk->sk_wmem_queued. + */ + amt = sk_mem_pages(newsk->sk_forward_alloc + + atomic_read(&newsk->sk_rmem_alloc)); + mem_cgroup_sk_alloc(newsk); + if (newsk->sk_memcg && amt) + mem_cgroup_charge_skmem(newsk->sk_memcg, amt); + + release_sock(newsk); + } if (req) reqsk_put(req); return newsk; @@ -907,7 +941,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, percpu_counter_inc(sk->sk_prot->orphan_count); if (sk->sk_protocol == IPPROTO_TCP && tcp_rsk(req)->tfo_listener) { - BUG_ON(tcp_sk(child)->fastopen_rsk != req); + BUG_ON(rcu_access_pointer(tcp_sk(child)->fastopen_rsk) != req); BUG_ON(sk != req->rsk_listener); /* Paranoid, to prevent race condition if @@ -916,7 +950,7 @@ static void inet_child_forget(struct sock *sk, struct request_sock *req, * Also to satisfy an assertion in * tcp_v4_destroy_sock(). */ - tcp_sk(child)->fastopen_rsk = NULL; + RCU_INIT_POINTER(tcp_sk(child)->fastopen_rsk, NULL); } inet_csk_destroy_sock(child); } @@ -1087,7 +1121,7 @@ struct dst_entry *inet_csk_update_pmtu(struct sock *sk, u32 mtu) if (!dst) goto out; } - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = __sk_dst_check(sk, 0); if (!dst) diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index bbb005eb5218..5b68bdaa8bff 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -100,13 +100,9 @@ static size_t inet_sk_attr_size(struct sock *sk, aux = handler->idiag_get_aux_size(sk, net_admin); return nla_total_size(sizeof(struct tcp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(SK_MEMINFO_VARS * sizeof(u32)) + nla_total_size(TCP_CA_NAME_MAX) + nla_total_size(sizeof(struct tcpvegas_info)) @@ -147,6 +143,24 @@ int inet_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, if (net_admin && nla_put_u32(skb, INET_DIAG_MARK, sk->sk_mark)) goto errout; + if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || + ext & (1 << (INET_DIAG_TCLASS - 1))) { + u32 classid = 0; + +#ifdef CONFIG_SOCK_CGROUP_DATA + classid = sock_cgroup_classid(&sk->sk_cgrp_data); +#endif + /* Fallback to socket priority if class id isn't set. + * Classful qdiscs use it as direct reference to class. + * For cgroup2 classid is always zero. + */ + if (!classid) + classid = sk->sk_priority; + + if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) + goto errout; + } + r->idiag_uid = from_kuid_munged(user_ns, sock_i_uid(sk)); r->idiag_inode = sock_i_ino(sk); @@ -193,7 +207,7 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, if (ext & (1 << (INET_DIAG_MEMINFO - 1))) { struct inet_diag_meminfo minfo = { .idiag_rmem = sk_rmem_alloc_get(sk), - .idiag_wmem = sk->sk_wmem_queued, + .idiag_wmem = READ_ONCE(sk->sk_wmem_queued), .idiag_fmem = sk->sk_forward_alloc, .idiag_tmem = sk_wmem_alloc_get(sk), }; @@ -284,24 +298,6 @@ int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, goto errout; } - if (ext & (1 << (INET_DIAG_CLASS_ID - 1)) || - ext & (1 << (INET_DIAG_TCLASS - 1))) { - u32 classid = 0; - -#ifdef CONFIG_SOCK_CGROUP_DATA - classid = sock_cgroup_classid(&sk->sk_cgrp_data); -#endif - /* Fallback to socket priority if class id isn't set. - * Classful qdiscs use it as direct reference to class. - * For cgroup2 classid is always zero. - */ - if (!classid) - classid = sk->sk_priority; - - if (nla_put_u32(skb, INET_DIAG_CLASS_ID, classid)) - goto errout; - } - out: nlmsg_end(skb, nlh); return 0; @@ -914,11 +910,12 @@ void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; num = 0; ilb = &hashinfo->listening_hash[i]; spin_lock(&ilb->lock); - sk_for_each(sk, &ilb->head) { + sk_nulls_for_each(sk, node, &ilb->nulls_head) { struct inet_sock *inet = inet_sk(sk); if (!net_eq(sock_net(sk), net)) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index c4503073248b..7a4e50f060ae 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -163,6 +163,7 @@ int __inet_inherit_port(const struct sock *sk, struct sock *child) return -ENOMEM; } } + inet_csk_update_fastreuse(tb, child); } inet_bind_hash(child, tb, port); spin_unlock(&head->lock); @@ -240,7 +241,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = sk->sk_family == PF_INET ? 2 : 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; @@ -516,10 +517,11 @@ static int inet_reuseport_add_sock(struct sock *sk, struct inet_listen_hashbucket *ilb) { struct inet_bind_bucket *tb = inet_csk(sk)->icsk_bind_hash; + const struct hlist_nulls_node *node; struct sock *sk2; kuid_t uid = sock_i_uid(sk); - sk_for_each_rcu(sk2, &ilb->head) { + sk_nulls_for_each_rcu(sk2, node, &ilb->nulls_head) { if (sk2 != sk && sk2->sk_family == sk->sk_family && ipv6_only_sock(sk2) == ipv6_only_sock(sk) && @@ -555,9 +557,9 @@ int __inet_hash(struct sock *sk, struct sock *osk) } if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && sk->sk_family == AF_INET6) - hlist_add_tail_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_tail_rcu(sk, &ilb->nulls_head); else - hlist_add_head_rcu(&sk->sk_node, &ilb->head); + __sk_nulls_add_node_rcu(sk, &ilb->nulls_head); inet_hash2(hashinfo, sk); ilb->count++; sock_set_flag(sk, SOCK_RCU_FREE); @@ -606,11 +608,9 @@ void inet_unhash(struct sock *sk) reuseport_detach_sock(sk); if (ilb) { inet_unhash2(hashinfo, sk); - __sk_del_node_init(sk); - ilb->count--; - } else { - __sk_nulls_del_node_init_rcu(sk); + ilb->count--; } + __sk_nulls_del_node_init_rcu(sk); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); unlock: spin_unlock_bh(lock); @@ -750,7 +750,8 @@ void inet_hashinfo_init(struct inet_hashinfo *h) for (i = 0; i < INET_LHTABLE_SIZE; i++) { spin_lock_init(&h->listening_hash[i].lock); - INIT_HLIST_HEAD(&h->listening_hash[i].head); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].nulls_head, + i + LISTENING_NULLS_BASE); h->listening_hash[i].count = 0; } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index be778599bfed..ff327a62c9ce 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -160,7 +160,12 @@ static void inet_peer_gc(struct inet_peer_base *base, base->total / inet_peer_threshold * HZ; for (i = 0; i < gc_cnt; i++) { p = gc_stack[i]; - delta = (__u32)jiffies - p->dtime; + + /* The READ_ONCE() pairs with the WRITE_ONCE() + * in inet_putpeer() + */ + delta = (__u32)jiffies - READ_ONCE(p->dtime); + if (delta < ttl || !refcount_dec_if_one(&p->refcnt)) gc_stack[i] = NULL; } @@ -237,7 +242,10 @@ EXPORT_SYMBOL_GPL(inet_getpeer); void inet_putpeer(struct inet_peer *p) { - p->dtime = (__u32)jiffies; + /* The WRITE_ONCE() pairs with itself (we run lockless) + * and the READ_ONCE() in inet_peer_gc() + */ + WRITE_ONCE(p->dtime, (__u32)jiffies); if (refcount_dec_and_test(&p->refcnt)) call_rcu(&p->rcu, inetpeer_free_rcu); diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 52690bb3e40f..85ba1453ba5c 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -509,9 +509,9 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto err_free_skb; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto err_free_skb; + md = ip_tunnel_info_opts(tun_info); /* ERSPAN has fixed 8 byte GRE header */ version = md->version; @@ -1149,6 +1149,24 @@ static int ipgre_netlink_parms(struct net_device *dev, if (data[IFLA_GRE_FWMARK]) *fwmark = nla_get_u32(data[IFLA_GRE_FWMARK]); + return 0; +} + +static int erspan_netlink_parms(struct net_device *dev, + struct nlattr *data[], + struct nlattr *tb[], + struct ip_tunnel_parm *parms, + __u32 *fwmark) +{ + struct ip_tunnel *t = netdev_priv(dev); + int err; + + err = ipgre_netlink_parms(dev, data, tb, parms, fwmark); + if (err) + return err; + if (!data) + return 0; + if (data[IFLA_GRE_ERSPAN_VER]) { t->erspan_ver = nla_get_u8(data[IFLA_GRE_ERSPAN_VER]); @@ -1272,45 +1290,70 @@ static void ipgre_tap_setup(struct net_device *dev) ip_tunnel_setup(dev, gre_tap_net_id); } -static int ipgre_newlink(struct net *src_net, struct net_device *dev, - struct nlattr *tb[], struct nlattr *data[], - struct netlink_ext_ack *extack) +static int +ipgre_newlink_encap_setup(struct net_device *dev, struct nlattr *data[]) { - struct ip_tunnel_parm p; struct ip_tunnel_encap ipencap; - __u32 fwmark = 0; - int err; if (ipgre_netlink_encap_parms(data, &ipencap)) { struct ip_tunnel *t = netdev_priv(dev); - err = ip_tunnel_encap_setup(t, &ipencap); + int err = ip_tunnel_encap_setup(t, &ipencap); if (err < 0) return err; } + return 0; +} + +static int ipgre_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel_parm p; + __u32 fwmark = 0; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) return err; return ip_tunnel_newlink(dev, tb, &p, fwmark); } +static int erspan_newlink(struct net *src_net, struct net_device *dev, + struct nlattr *tb[], struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel_parm p; + __u32 fwmark = 0; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + + err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); + if (err) + return err; + return ip_tunnel_newlink(dev, tb, &p, fwmark); +} + static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) { struct ip_tunnel *t = netdev_priv(dev); - struct ip_tunnel_encap ipencap; __u32 fwmark = t->fwmark; struct ip_tunnel_parm p; int err; - if (ipgre_netlink_encap_parms(data, &ipencap)) { - err = ip_tunnel_encap_setup(t, &ipencap); - - if (err < 0) - return err; - } + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; err = ipgre_netlink_parms(dev, data, tb, &p, &fwmark); if (err < 0) @@ -1323,8 +1366,34 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], t->parms.i_flags = p.i_flags; t->parms.o_flags = p.o_flags; - if (strcmp(dev->rtnl_link_ops->kind, "erspan")) - ipgre_link_update(dev, !tb[IFLA_MTU]); + ipgre_link_update(dev, !tb[IFLA_MTU]); + + return 0; +} + +static int erspan_changelink(struct net_device *dev, struct nlattr *tb[], + struct nlattr *data[], + struct netlink_ext_ack *extack) +{ + struct ip_tunnel *t = netdev_priv(dev); + __u32 fwmark = t->fwmark; + struct ip_tunnel_parm p; + int err; + + err = ipgre_newlink_encap_setup(dev, data); + if (err) + return err; + + err = erspan_netlink_parms(dev, data, tb, &p, &fwmark); + if (err < 0) + return err; + + err = ip_tunnel_changelink(dev, tb, &p, fwmark); + if (err < 0) + return err; + + t->parms.i_flags = p.i_flags; + t->parms.o_flags = p.o_flags; return 0; } @@ -1515,8 +1584,8 @@ static struct rtnl_link_ops erspan_link_ops __read_mostly = { .priv_size = sizeof(struct ip_tunnel), .setup = erspan_setup, .validate = erspan_validate, - .newlink = ipgre_newlink, - .changelink = ipgre_changelink, + .newlink = erspan_newlink, + .changelink = erspan_changelink, .dellink = ip_tunnel_dellink, .get_size = ipgre_get_size, .fill_info = ipgre_fill_info, diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index b6f3a9f0b8be..c6c761617cce 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1173,15 +1173,18 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, cork->addr = ipc->addr; } - /* - * We steal reference to this route, caller should not release it - */ - *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? - dst_mtu(&rt->dst) : rt->dst.dev->mtu; + 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; + /* We stole this route, caller should not release it. */ + *rtp = NULL; + cork->length = 0; cork->ttl = ipc->ttl; cork->tos = ipc->tos; diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 38c02bb62e2c..a0b4dc54f8a6 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -85,9 +85,10 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, __be32 remote, __be32 local, __be32 key) { - unsigned int hash; struct ip_tunnel *t, *cand = NULL; struct hlist_head *head; + struct net_device *ndev; + unsigned int hash; hash = ip_tunnel_hash(key, remote); head = &itn->tunnels[hash]; @@ -142,11 +143,8 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, cand = t; } - if (flags & TUNNEL_NO_KEY) - goto skip_key_lookup; - hlist_for_each_entry_rcu(t, head, hash_node) { - if (t->parms.i_key != key || + if ((!(flags & TUNNEL_NO_KEY) && t->parms.i_key != key) || t->parms.iph.saddr != 0 || t->parms.iph.daddr != 0 || !(t->dev->flags & IFF_UP)) @@ -158,7 +156,6 @@ struct ip_tunnel *ip_tunnel_lookup(struct ip_tunnel_net *itn, cand = t; } -skip_key_lookup: if (cand) return cand; @@ -166,8 +163,9 @@ skip_key_lookup: if (t && t->dev->flags & IFF_UP) return t; - if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) - return netdev_priv(itn->fb_tunnel_dev); + ndev = READ_ONCE(itn->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -505,7 +503,7 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, mtu = skb_valid_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; if (skb_valid_dst(skb)) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { if (!skb_is_gso(skb) && @@ -1236,10 +1234,8 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; - if (tunnel->collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (tunnel->collect_md) netif_keep_dst(dev); - } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); @@ -1251,9 +1247,9 @@ void ip_tunnel_uninit(struct net_device *dev) struct ip_tunnel_net *itn; itn = net_generic(net, tunnel->ip_tnl_net_id); - /* fb_tunnel_dev will be unregisted in net-exit call. */ - if (itn->fb_tunnel_dev != dev) - ip_tunnel_del(itn, netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); + if (itn->fb_tunnel_dev == dev) + WRITE_ONCE(itn->fb_tunnel_dev, NULL); dst_cache_reset(&tunnel->dst_cache); } diff --git a/net/ipv4/ip_vti.c b/net/ipv4/ip_vti.c index cfb025606793..bd41354ed8c1 100644 --- a/net/ipv4/ip_vti.c +++ b/net/ipv4/ip_vti.c @@ -93,7 +93,28 @@ static int vti_rcv_proto(struct sk_buff *skb) static int vti_rcv_tunnel(struct sk_buff *skb) { - return vti_rcv(skb, ip_hdr(skb)->saddr, true); + struct ip_tunnel_net *itn = net_generic(dev_net(skb->dev), vti_net_id); + const struct iphdr *iph = ip_hdr(skb); + struct ip_tunnel *tunnel; + + tunnel = ip_tunnel_lookup(itn, skb->dev->ifindex, TUNNEL_NO_KEY, + iph->saddr, iph->daddr, 0); + if (tunnel) { + struct tnl_ptk_info tpi = { + .proto = htons(ETH_P_IP), + }; + + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) + goto drop; + if (iptunnel_pull_header(skb, 0, tpi.proto, false)) + goto drop; + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, false); + } + + return -EINVAL; +drop: + kfree_skb(skb); + return 0; } static int vti_rcv_cb(struct sk_buff *skb, int err) @@ -187,8 +208,39 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, int mtu; if (!dst) { - dev->stats.tx_carrier_errors++; - goto tx_error_icmp; + switch (skb->protocol) { + case htons(ETH_P_IP): { + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + dst = &rt->dst; + skb_dst_set(skb, dst); + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case htons(ETH_P_IPV6): + fl->u.ip6.flowi6_oif = dev->ifindex; + fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); + if (dst->error) { + dst_release(dst); + dst = NULL; + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } + skb_dst_set(skb, dst); + break; +#endif + default: + dev->stats.tx_carrier_errors++; + goto tx_error_icmp; + } } dst_hold(dst); @@ -214,7 +266,7 @@ static netdev_tx_t vti_xmit(struct sk_buff *skb, struct net_device *dev, mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IP)) { icmp_send(skb, ICMP_DEST_UNREACH, ICMP_FRAG_NEEDED, htonl(mtu)); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 2f01cf6fa0de..678575adaf3b 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -698,7 +698,7 @@ out: rtnl_link_failed: #if IS_ENABLED(CONFIG_MPLS) - xfrm4_tunnel_deregister(&mplsip_handler, AF_INET); + xfrm4_tunnel_deregister(&mplsip_handler, AF_MPLS); xfrm_tunnel_mplsip_failed: #endif diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index c07bc82cbbe9..0fa250635b0c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -2289,7 +2289,8 @@ int ipmr_get_route(struct net *net, struct sk_buff *skb, rcu_read_unlock(); return -ENODEV; } - skb2 = skb_clone(skb, GFP_ATOMIC); + + skb2 = skb_realloc_headroom(skb, sizeof(struct iphdr)); if (!skb2) { read_unlock(&mrt_lock); rcu_read_unlock(); @@ -2608,7 +2609,7 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) mrt = ipmr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { - if (filter.dump_all_families) + if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IPMR) return skb->len; NL_SET_ERR_MSG(cb->extack, "ipv4: MR table does not exist"); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 214154b47d56..f1f78a742b36 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -384,10 +384,11 @@ next: ; return 1; } -static inline int check_target(struct arpt_entry *e, const char *name) +static int check_target(struct arpt_entry *e, struct net *net, const char *name) { struct xt_entry_target *t = arpt_get_target(e); struct xt_tgchk_param par = { + .net = net, .table = name, .entryinfo = e, .target = t->u.kernel.target, @@ -399,8 +400,9 @@ static inline int check_target(struct arpt_entry *e, const char *name) return xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); } -static inline int -find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, +static int +find_check_entry(struct arpt_entry *e, struct net *net, const char *name, + unsigned int size, struct xt_percpu_counter_alloc_state *alloc_state) { struct xt_entry_target *t; @@ -419,7 +421,7 @@ find_check_entry(struct arpt_entry *e, const char *name, unsigned int size, } t->u.kernel.target = target; - ret = check_target(e, name); + ret = check_target(e, net, name); if (ret) goto err; return 0; @@ -494,12 +496,13 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, return 0; } -static inline void cleanup_entry(struct arpt_entry *e) +static void cleanup_entry(struct arpt_entry *e, struct net *net) { struct xt_tgdtor_param par; struct xt_entry_target *t; t = arpt_get_target(e); + par.net = net; par.target = t->u.kernel.target; par.targinfo = t->data; par.family = NFPROTO_ARP; @@ -512,7 +515,9 @@ static inline void cleanup_entry(struct arpt_entry *e) /* Checks and translates the user-supplied table segment (held in * newinfo). */ -static int translate_table(struct xt_table_info *newinfo, void *entry0, +static int translate_table(struct net *net, + struct xt_table_info *newinfo, + void *entry0, const struct arpt_replace *repl) { struct xt_percpu_counter_alloc_state alloc_state = { 0 }; @@ -569,7 +574,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, /* Finally, each sanity check must pass */ i = 0; xt_entry_foreach(iter, entry0, newinfo->size) { - ret = find_check_entry(iter, repl->name, repl->size, + ret = find_check_entry(iter, net, repl->name, repl->size, &alloc_state); if (ret != 0) break; @@ -580,7 +585,7 @@ static int translate_table(struct xt_table_info *newinfo, void *entry0, xt_entry_foreach(iter, entry0, newinfo->size) { if (i-- == 0) break; - cleanup_entry(iter); + cleanup_entry(iter, net); } return ret; } @@ -923,7 +928,7 @@ static int __do_replace(struct net *net, const char *name, /* Decrease module usage counts and free resource */ loc_cpu_old_entry = oldinfo->entries; xt_entry_foreach(iter, loc_cpu_old_entry, oldinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); xt_free_table_info(oldinfo); if (copy_to_user(counters_ptr, counters, @@ -974,7 +979,7 @@ static int do_replace(struct net *net, const void __user *user, goto free_newinfo; } - ret = translate_table(newinfo, loc_cpu_entry, &tmp); + ret = translate_table(net, newinfo, loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -986,7 +991,7 @@ static int do_replace(struct net *net, const void __user *user, free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1149,7 +1154,8 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, } } -static int translate_compat_table(struct xt_table_info **pinfo, +static int translate_compat_table(struct net *net, + struct xt_table_info **pinfo, void **pentry0, const struct compat_arpt_replace *compatr) { @@ -1217,7 +1223,7 @@ static int translate_compat_table(struct xt_table_info **pinfo, repl.num_counters = 0; repl.counters = NULL; repl.size = newinfo->size; - ret = translate_table(newinfo, entry1, &repl); + ret = translate_table(net, newinfo, entry1, &repl); if (ret) goto free_newinfo; @@ -1270,7 +1276,7 @@ static int compat_do_replace(struct net *net, void __user *user, goto free_newinfo; } - ret = translate_compat_table(&newinfo, &loc_cpu_entry, &tmp); + ret = translate_compat_table(net, &newinfo, &loc_cpu_entry, &tmp); if (ret != 0) goto free_newinfo; @@ -1282,7 +1288,7 @@ static int compat_do_replace(struct net *net, void __user *user, free_newinfo_untrans: xt_entry_foreach(iter, loc_cpu_entry, newinfo->size) - cleanup_entry(iter); + cleanup_entry(iter, net); free_newinfo: xt_free_table_info(newinfo); return ret; @@ -1509,7 +1515,7 @@ static int do_arpt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len return ret; } -static void __arpt_unregister_table(struct xt_table *table) +static void __arpt_unregister_table(struct net *net, struct xt_table *table) { struct xt_table_info *private; void *loc_cpu_entry; @@ -1521,7 +1527,7 @@ static void __arpt_unregister_table(struct xt_table *table) /* Decrease module usage counts and free resources */ loc_cpu_entry = private->entries; xt_entry_foreach(iter, loc_cpu_entry, private->size) - cleanup_entry(iter); + cleanup_entry(iter, net); if (private->number > private->initial_entries) module_put(table_owner); xt_free_table_info(private); @@ -1546,7 +1552,7 @@ int arpt_register_table(struct net *net, loc_cpu_entry = newinfo->entries; memcpy(loc_cpu_entry, repl->entries, repl->size); - ret = translate_table(newinfo, loc_cpu_entry, repl); + ret = translate_table(net, newinfo, loc_cpu_entry, repl); if (ret != 0) goto out_free; @@ -1561,7 +1567,7 @@ int arpt_register_table(struct net *net, ret = nf_register_net_hooks(net, ops, hweight32(table->valid_hooks)); if (ret != 0) { - __arpt_unregister_table(new_table); + __arpt_unregister_table(net, new_table); *res = NULL; } @@ -1576,7 +1582,7 @@ void arpt_unregister_table(struct net *net, struct xt_table *table, const struct nf_hook_ops *ops) { nf_unregister_net_hooks(net, ops, hweight32(table->valid_hooks)); - __arpt_unregister_table(table); + __arpt_unregister_table(net, table); } /* The built-in targets: standard (NULL) and error. */ diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index b2aeb7bf5dac..2a1e10f4ae93 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -166,8 +166,7 @@ pptp_outbound_pkt(struct sk_buff *skb, break; default: pr_debug("unknown outbound packet 0x%04x:%s\n", msg, - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : - pptp_msg_name[0]); + pptp_msg_name(msg)); /* fall through */ case PPTP_SET_LINK_INFO: /* only need to NAT in case PAC is behind NAT box */ @@ -268,9 +267,7 @@ pptp_inbound_pkt(struct sk_buff *skb, pcid_off = offsetof(union pptp_ctrl_union, setlink.peersCallID); break; default: - pr_debug("unknown inbound packet %s\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : - pptp_msg_name[0]); + pr_debug("unknown inbound packet %s\n", pptp_msg_name(msg)); /* fall through */ case PPTP_START_SESSION_REQUEST: case PPTP_START_SESSION_REPLY: diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 9d24ef5c5d8f..ce723a526b73 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -786,6 +786,9 @@ static int ping_v4_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) inet_sk_flowi_flags(sk), faddr, saddr, 0, 0, sk->sk_uid); + fl4.fl4_icmp_type = user_icmph.type; + fl4.fl4_icmp_code = user_icmph.code; + security_sk_classify_flow(sk, flowi4_to_flowi(&fl4)); rt = ip_route_output_flow(net, &fl4, sk); if (IS_ERR(rt)) { diff --git a/net/ipv4/raw_diag.c b/net/ipv4/raw_diag.c index e35736b99300..a93e7d1e1251 100644 --- a/net/ipv4/raw_diag.c +++ b/net/ipv4/raw_diag.c @@ -100,8 +100,9 @@ static int raw_diag_dump_one(struct sk_buff *in_skb, if (IS_ERR(sk)) return PTR_ERR(sk); - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) { sock_put(sk); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 697744127a66..53615c5a8664 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -138,7 +138,8 @@ static unsigned int ipv4_mtu(const struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void ip_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static void ipv4_dst_destroy(struct dst_entry *dst); @@ -447,7 +448,7 @@ static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, n = ip_neigh_gw4(dev, pkey); } - if (n && !refcount_inc_not_zero(&n->refcnt)) + if (!IS_ERR(n) && !refcount_inc_not_zero(&n->refcnt)) n = NULL; rcu_read_unlock_bh(); @@ -488,18 +489,16 @@ u32 ip_idents_reserve(u32 hash, int segs) atomic_t *p_id = ip_idents + hash % IP_IDENTS_SZ; u32 old = READ_ONCE(*p_tstamp); u32 now = (u32)jiffies; - u32 new, delta = 0; + u32 delta = 0; if (old != now && cmpxchg(p_tstamp, old, now) == old) delta = prandom_u32_max(now - old); - /* Do not use atomic_add_return() as it makes UBSAN unhappy */ - do { - old = (u32)atomic_read(p_id); - new = old + delta + segs; - } while (atomic_cmpxchg(p_id, old, new) != old); - - return new - segs; + /* If UBSAN reports an error there, please make sure your compiler + * supports -fno-strict-overflow before reporting it that was a bug + * in UBSAN, and it has been fixed in GCC-8. + */ + return atomic_add_return(segs + delta, p_id) - segs; } EXPORT_SYMBOL(ip_idents_reserve); @@ -912,7 +911,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) /* Check for load limit; set rate_last to the latest sent * redirect. */ - if (peer->rate_tokens == 0 || + if (peer->n_redirects == 0 || time_after(jiffies, (peer->rate_last + (ip_rt_redirect_load << peer->n_redirects)))) { @@ -1042,7 +1041,8 @@ static void __ip_rt_update_pmtu(struct rtable *rt, struct flowi4 *fl4, u32 mtu) } static void ip_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct rtable *rt = (struct rtable *) dst; struct flowi4 fl4; @@ -2618,7 +2618,8 @@ static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index b2f0d2988a8e..86ae03c1c54b 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -450,8 +450,8 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_sync_mss = tcp_sync_mss; - sk->sk_sndbuf = sock_net(sk)->ipv4.sysctl_tcp_wmem[1]; - sk->sk_rcvbuf = sock_net(sk)->ipv4.sysctl_tcp_rmem[1]; + WRITE_ONCE(sk->sk_sndbuf, sock_net(sk)->ipv4.sysctl_tcp_wmem[1]); + WRITE_ONCE(sk->sk_rcvbuf, sock_net(sk)->ipv4.sysctl_tcp_rmem[1]); sk_sockets_allocated_inc(sk); sk->sk_route_forced_caps = NETIF_F_GSO; @@ -477,9 +477,17 @@ static void tcp_tx_timestamp(struct sock *sk, u16 tsflags) static inline bool tcp_stream_is_readable(const struct tcp_sock *tp, int target, struct sock *sk) { - return (tp->rcv_nxt - tp->copied_seq >= target) || - (sk->sk_prot->stream_memory_read ? - sk->sk_prot->stream_memory_read(sk) : false); + int avail = READ_ONCE(tp->rcv_nxt) - READ_ONCE(tp->copied_seq); + + if (avail > 0) { + if (avail >= target) + return true; + if (tcp_rmem_pressure(sk)) + return true; + } + if (sk->sk_prot->stream_memory_read) + return sk->sk_prot->stream_memory_read(sk); + return false; } /* @@ -543,10 +551,10 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) /* Connected or passive Fast Open socket? */ if (state != TCP_SYN_SENT && - (state != TCP_SYN_RECV || tp->fastopen_rsk)) { + (state != TCP_SYN_RECV || rcu_access_pointer(tp->fastopen_rsk))) { int target = sock_rcvlowat(sk, 0, INT_MAX); - if (tp->urg_seq == tp->copied_seq && + if (READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq) && !sock_flag(sk, SOCK_URGINLINE) && tp->urg_data) target++; @@ -584,7 +592,7 @@ __poll_t tcp_poll(struct file *file, struct socket *sock, poll_table *wait) } /* This barrier is coupled with smp_wmb() in tcp_reset() */ smp_rmb(); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR; return mask; @@ -607,7 +615,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) unlock_sock_fast(sk, slow); break; case SIOCATMARK: - answ = tp->urg_data && tp->urg_seq == tp->copied_seq; + answ = tp->urg_data && + READ_ONCE(tp->urg_seq) == READ_ONCE(tp->copied_seq); break; case SIOCOUTQ: if (sk->sk_state == TCP_LISTEN) @@ -616,7 +625,7 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_una; + answ = READ_ONCE(tp->write_seq) - tp->snd_una; break; case SIOCOUTQNSD: if (sk->sk_state == TCP_LISTEN) @@ -625,7 +634,8 @@ int tcp_ioctl(struct sock *sk, int cmd, unsigned long arg) if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) answ = 0; else - answ = tp->write_seq - tp->snd_nxt; + answ = READ_ONCE(tp->write_seq) - + READ_ONCE(tp->snd_nxt); break; default: return -ENOIOCTLCMD; @@ -657,7 +667,7 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) tcb->sacked = 0; __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; @@ -1032,10 +1042,10 @@ new_segment: skb->len += copy; skb->data_len += copy; skb->truesize += copy; - sk->sk_wmem_queued += copy; + sk_wmem_queued_add(sk, copy); sk_mem_charge(sk, copy); skb->ip_summed = CHECKSUM_PARTIAL; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1085,8 +1095,7 @@ do_error: goto out; out_err: /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1361,7 +1370,7 @@ new_segment: if (!copied) TCP_SKB_CB(skb)->tcp_flags &= ~TCPHDR_PSH; - tp->write_seq += copy; + WRITE_ONCE(tp->write_seq, tp->write_seq + copy); TCP_SKB_CB(skb)->end_seq += copy; tcp_skb_pcount_set(skb, 0); @@ -1416,8 +1425,7 @@ out_err: sock_zerocopy_put_abort(uarg, true); err = sk_stream_error(sk, flags, err); /* make sure we wake any epoll edge trigger waiter */ - if (unlikely(skb_queue_len(&sk->sk_write_queue) == 0 && - err == -EAGAIN)) { + if (unlikely(tcp_rtx_and_write_queues_empty(sk) && err == -EAGAIN)) { sk->sk_write_space(sk); tcp_chrono_stop(sk, TCP_CHRONO_SNDBUF_LIMITED); } @@ -1667,9 +1675,9 @@ int tcp_read_sock(struct sock *sk, read_descriptor_t *desc, sk_eat_skb(sk, skb); if (!desc->count) break; - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); } - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); @@ -1708,7 +1716,7 @@ int tcp_set_rcvlowat(struct sock *sk, int val) val <<= 1; if (val > sk->sk_rcvbuf) { - sk->sk_rcvbuf = val; + WRITE_ONCE(sk->sk_rcvbuf, val); tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); } return 0; @@ -1756,10 +1764,11 @@ static int tcp_zerocopy_receive(struct sock *sk, down_read(¤t->mm->mmap_sem); - ret = -EINVAL; vma = find_vma(current->mm, address); - if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) - goto out; + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) { + up_read(¤t->mm->mmap_sem); + return -EINVAL; + } zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); tp = tcp_sk(sk); @@ -1818,7 +1827,7 @@ static int tcp_zerocopy_receive(struct sock *sk, out: up_read(¤t->mm->mmap_sem); if (length) { - tp->copied_seq = seq; + WRITE_ONCE(tp->copied_seq, seq); tcp_rcv_space_adjust(sk); /* Clean up data we have read: This will do ACK frames. */ @@ -1955,13 +1964,12 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, struct sk_buff *skb, *last; u32 urg_hole = 0; struct scm_timestamping_internal tss; - bool has_tss = false; - bool has_cmsg; + int cmsg_flags; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); - if (sk_can_busy_loop(sk) && skb_queue_empty(&sk->sk_receive_queue) && + if (sk_can_busy_loop(sk) && skb_queue_empty_lockless(&sk->sk_receive_queue) && (sk->sk_state == TCP_ESTABLISHED)) sk_busy_loop(sk, nonblock); @@ -1971,7 +1979,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (sk->sk_state == TCP_LISTEN) goto out; - has_cmsg = tp->recvmsg_inq; + cmsg_flags = tp->recvmsg_inq ? 1 : 0; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -2116,7 +2124,7 @@ found_ok_skb: if (urg_offset < used) { if (!urg_offset) { if (!sock_flag(sk, SOCK_URGINLINE)) { - ++*seq; + WRITE_ONCE(*seq, *seq + 1); urg_hole++; offset++; used--; @@ -2138,7 +2146,7 @@ found_ok_skb: } } - *seq += used; + WRITE_ONCE(*seq, *seq + used); copied += used; len -= used; @@ -2149,14 +2157,15 @@ skip_copy: tp->urg_data = 0; tcp_fast_path_check(sk); } - if (used + offset < skb->len) - continue; if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); - has_tss = true; - has_cmsg = true; + cmsg_flags |= 2; } + + if (used + offset < skb->len) + continue; + if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; if (!(flags & MSG_PEEK)) @@ -2165,7 +2174,7 @@ skip_copy: found_fin_ok: /* Process the FIN. */ - ++*seq; + WRITE_ONCE(*seq, *seq + 1); if (!(flags & MSG_PEEK)) sk_eat_skb(sk, skb); break; @@ -2180,10 +2189,10 @@ found_fin_ok: release_sock(sk); - if (has_cmsg) { - if (has_tss) + if (cmsg_flags) { + if (cmsg_flags & 2) tcp_recv_timestamp(msg, sk, &tss); - if (tp->recvmsg_inq) { + if (cmsg_flags & 1) { inq = tcp_inq_hint(sk); put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); } @@ -2486,7 +2495,10 @@ adjudge_to_death: } if (sk->sk_state == TCP_CLOSE) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); /* We could get here with a non-NULL req if the socket is * aborted (e.g., closed with unread data) before 3WHS * finishes. @@ -2518,6 +2530,7 @@ static void tcp_rtx_queue_purge(struct sock *sk) { struct rb_node *p = rb_first(&sk->tcp_rtx_queue); + tcp_sk(sk)->highest_sack = NULL; while (p) { struct sk_buff *skb = rb_to_skb(p); @@ -2558,6 +2571,7 @@ int tcp_disconnect(struct sock *sk, int flags) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); int old_state = sk->sk_state; + u32 seq; if (old_state != TCP_CLOSE) tcp_set_state(sk, TCP_CLOSE); @@ -2584,7 +2598,7 @@ int tcp_disconnect(struct sock *sk, int flags) __kfree_skb(sk->sk_rx_skb_cache); sk->sk_rx_skb_cache = NULL; } - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->urg_data = 0; tcp_write_queue_purge(sk); tcp_fastopen_active_disable_ofo_check(sk); @@ -2600,9 +2614,12 @@ int tcp_disconnect(struct sock *sk, int flags) tp->srtt_us = 0; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; - tp->write_seq += tp->max_window + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + + seq = tp->write_seq + tp->max_window + 2; + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); + icsk->icsk_backoff = 0; tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; @@ -2611,10 +2628,15 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered = 0; tp->delivered_ce = 0; + if (icsk->icsk_ca_ops->release) + icsk->icsk_ca_ops->release(sk); + memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); + tp->total_retrans = 0; inet_csk_delack_init(sk); /* Initialize rcv_mss to TCP_MIN_MSS to avoid division by 0 * issue in __tcp_select_window() @@ -2626,10 +2648,14 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_rx_dst = NULL; tcp_saved_syn_free(tp); tp->compressed_ack = 0; + tp->segs_in = 0; + tp->segs_out = 0; tp->bytes_sent = 0; tp->bytes_acked = 0; tp->bytes_received = 0; tp->bytes_retrans = 0; + tp->data_segs_in = 0; + tp->data_segs_out = 0; tp->duplicate_sack[0].start_seq = 0; tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; @@ -2905,9 +2931,11 @@ static int do_tcp_setsockopt(struct sock *sk, int level, if (sk->sk_state != TCP_CLOSE) err = -EPERM; else if (tp->repair_queue == TCP_SEND_QUEUE) - tp->write_seq = val; - else if (tp->repair_queue == TCP_RECV_QUEUE) - tp->rcv_nxt = val; + WRITE_ONCE(tp->write_seq, val); + else if (tp->repair_queue == TCP_RECV_QUEUE) { + WRITE_ONCE(tp->rcv_nxt, val); + WRITE_ONCE(tp->copied_seq, val); + } else err = -EINVAL; break; @@ -3035,10 +3063,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, #ifdef CONFIG_TCP_MD5SIG case TCP_MD5SIG: case TCP_MD5SIG_EXT: - if ((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN)) - err = tp->af_specific->md5_parse(sk, optname, optval, optlen); - else - err = -EINVAL; + err = tp->af_specific->md5_parse(sk, optname, optval, optlen); break; #endif case TCP_USER_TIMEOUT: @@ -3781,10 +3806,13 @@ EXPORT_SYMBOL(tcp_md5_hash_skb_data); int tcp_md5_hash_key(struct tcp_md5sig_pool *hp, const struct tcp_md5sig_key *key) { + u8 keylen = READ_ONCE(key->keylen); /* paired with WRITE_ONCE() in tcp_md5_do_add */ struct scatterlist sg; - sg_init_one(&sg, key->key, key->keylen); - ahash_request_set_crypt(hp->md5_req, &sg, NULL, key->keylen); + sg_init_one(&sg, key->key, keylen); + ahash_request_set_crypt(hp->md5_req, &sg, NULL, keylen); + + /* tcp_md5_do_add() might change key->key under us */ return crypto_ahash_update(hp->md5_req); } EXPORT_SYMBOL(tcp_md5_hash_key); @@ -3793,7 +3821,13 @@ EXPORT_SYMBOL(tcp_md5_hash_key); void tcp_done(struct sock *sk) { - struct request_sock *req = tcp_sk(sk)->fastopen_rsk; + struct request_sock *req; + + /* We might be called with a new socket, after + * inet_csk_prepare_forced_close() has been called + * so we can not use lockdep_sock_is_held(sk) + */ + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, 1); if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS(sock_net(sk), TCP_MIB_ATTEMPTFAILS); diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 00ade9c185ea..1c0d2815ec54 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -306,7 +306,8 @@ static u32 bbr_tso_segs_goal(struct sock *sk) /* Sort of tcp_tso_autosize() but ignoring * driver provided sk_gso_max_size. */ - bytes = min_t(unsigned long, sk->sk_pacing_rate >> sk->sk_pacing_shift, + bytes = min_t(unsigned long, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), GSO_MAX_SIZE - 1 - MAX_TCP_HEADER); segs = max_t(u32, bytes / tp->mss_cache, bbr_min_tso_segs(sk)); @@ -776,8 +777,7 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) * bandwidth sample. Delivered is in packets and interval_us in uS and * ratio will be <<1 for most connections. So delivered is first scaled. */ - bw = (u64)rs->delivered * BW_UNIT; - do_div(bw, rs->interval_us); + bw = div64_long((u64)rs->delivered * BW_UNIT, rs->interval_us); /* If this sample is application-limited, it is likely to have a very * low delivered count that represents application behavior rather than diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index 8a56e09cfb0e..ad9f38202731 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -96,6 +96,9 @@ int __tcp_bpf_recvmsg(struct sock *sk, struct sk_psock *psock, } while (i != msg_rx->sg.end); if (unlikely(peek)) { + if (msg_rx == list_last_entry(&psock->ingress_msg, + struct sk_msg, list)) + break; msg_rx = list_next_entry(msg_rx, list); continue; } @@ -123,12 +126,15 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); - if (!skb_queue_empty(&sk->sk_receive_queue)) - return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); psock = sk_psock_get(sk); if (unlikely(!psock)) return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue) && + sk_psock_queue_empty(psock)) { + sk_psock_put(sk, psock); + return tcp_recvmsg(sk, msg, len, nonblock, flags, addr_len); + } lock_sock(sk); msg_bytes_ready: copied = __tcp_bpf_recvmsg(sk, psock, msg, len, flags); @@ -139,7 +145,7 @@ msg_bytes_ready: timeo = sock_rcvtimeo(sk, nonblock); data = tcp_bpf_wait_data(sk, psock, flags, timeo, &err); if (data) { - if (skb_queue_empty(&sk->sk_receive_queue)) + if (!sk_psock_queue_empty(psock)) goto msg_bytes_ready; release_sock(sk); sk_psock_put(sk, psock); @@ -200,7 +206,6 @@ static int bpf_tcp_ingress(struct sock *sk, struct sk_psock *psock, if (!ret) { msg->sg.start = i; - msg->sg.size -= apply_bytes; sk_psock_queue_msg(psock, tmp); sk_psock_data_ready(sk, psock); } else { @@ -301,7 +306,7 @@ EXPORT_SYMBOL_GPL(tcp_bpf_sendmsg_redir); static int tcp_bpf_send_verdict(struct sock *sk, struct sk_psock *psock, struct sk_msg *msg, int *copied, int flags) { - bool cork = false, enospc = msg->sg.start == msg->sg.end; + bool cork = false, enospc = sk_msg_full(msg); struct sock *sk_redir; u32 tosend, delta = 0; int ret; @@ -315,10 +320,7 @@ more_data: */ delta = msg->sg.size; psock->eval = sk_psock_msg_verdict(sk, psock, msg); - if (msg->sg.size < delta) - delta -= msg->sg.size; - else - delta = 0; + delta -= msg->sg.size; } if (msg->cork_bytes && diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index c445a81d144e..d7a1f2ef6c52 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -197,7 +197,7 @@ static void tcp_reinit_congestion_control(struct sock *sk, icsk->icsk_ca_setsockopt = 1; memset(icsk->icsk_ca_priv, 0, sizeof(icsk->icsk_ca_priv)); - if (sk->sk_state != TCP_CLOSE) + if (!((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_LISTEN))) tcp_init_congestion_control(sk); } diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 1b3d032a4df2..c7bf5b26bf0c 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -40,8 +40,8 @@ /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 -#define HYSTART_DELAY_MIN (4U<<3) -#define HYSTART_DELAY_MAX (16U<<3) +#define HYSTART_DELAY_MIN (4000U) /* 4 ms */ +#define HYSTART_DELAY_MAX (16000U) /* 16 ms */ #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) static int fast_convergence __read_mostly = 1; @@ -53,7 +53,7 @@ static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; -static int hystart_ack_delta __read_mostly = 2; +static int hystart_ack_delta_us __read_mostly = 2000; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; @@ -77,8 +77,8 @@ MODULE_PARM_DESC(hystart_detect, "hybrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); -module_param(hystart_ack_delta, int, 0644); -MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)"); +module_param(hystart_ack_delta_us, int, 0644); +MODULE_PARM_DESC(hystart_ack_delta_us, "spacing between ack's indicating train (usecs)"); /* BIC TCP Parameters */ struct bictcp { @@ -89,7 +89,7 @@ struct bictcp { u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ - u32 delay_min; /* min delay (msec << 3) */ + u32 delay_min; /* min delay (usec) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ @@ -117,13 +117,9 @@ static inline void bictcp_reset(struct bictcp *ca) ca->found = 0; } -static inline u32 bictcp_clock(void) +static inline u32 bictcp_clock_us(const struct sock *sk) { -#if HZ < 1000 - return ktime_to_ms(ktime_get_real()); -#else - return jiffies_to_msecs(jiffies); -#endif + return tcp_sk(sk)->tcp_mstamp; } static inline void bictcp_hystart_reset(struct sock *sk) @@ -131,9 +127,9 @@ static inline void bictcp_hystart_reset(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - ca->round_start = ca->last_ack = bictcp_clock(); + ca->round_start = ca->last_ack = bictcp_clock_us(sk); ca->end_seq = tp->snd_nxt; - ca->curr_rtt = 0; + ca->curr_rtt = ~0U; ca->sample_cnt = 0; } @@ -276,7 +272,7 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd, u32 acked) */ t = (s32)(tcp_jiffies32 - ca->epoch_start); - t += msecs_to_jiffies(ca->delay_min >> 3); + t += usecs_to_jiffies(ca->delay_min); /* change the unit from HZ to bictcp_HZ */ t <<= BICTCP_HZ; do_div(t, HZ); @@ -376,22 +372,54 @@ static void bictcp_state(struct sock *sk, u8 new_state) } } +/* Account for TSO/GRO delays. + * Otherwise short RTT flows could get too small ssthresh, since during + * slow start we begin with small TSO packets and ca->delay_min would + * not account for long aggregation delay when TSO packets get bigger. + * Ideally even with a very small RTT we would like to have at least one + * TSO packet being sent and received by GRO, and another one in qdisc layer. + * We apply another 100% factor because @rate is doubled at this point. + * We cap the cushion to 1ms. + */ +static u32 hystart_ack_delay(struct sock *sk) +{ + unsigned long rate; + + rate = READ_ONCE(sk->sk_pacing_rate); + if (!rate) + return 0; + return min_t(u64, USEC_PER_MSEC, + div64_ul((u64)GSO_MAX_SIZE * 4 * USEC_PER_SEC, rate)); +} + static void hystart_update(struct sock *sk, u32 delay) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - - if (ca->found & hystart_detect) - return; + u32 threshold; if (hystart_detect & HYSTART_ACK_TRAIN) { - u32 now = bictcp_clock(); + u32 now = bictcp_clock_us(sk); /* first detection parameter - ack-train detection */ - if ((s32)(now - ca->last_ack) <= hystart_ack_delta) { + if ((s32)(now - ca->last_ack) <= hystart_ack_delta_us) { ca->last_ack = now; - if ((s32)(now - ca->round_start) > ca->delay_min >> 4) { - ca->found |= HYSTART_ACK_TRAIN; + + threshold = ca->delay_min + hystart_ack_delay(sk); + + /* Hystart ack train triggers if we get ack past + * ca->delay_min/2. + * Pacing might have delayed packets up to RTT/2 + * during slow start. + */ + if (sk->sk_pacing_status == SK_PACING_NONE) + threshold >>= 1; + + if ((s32)(now - ca->round_start) > threshold) { + ca->found = 1; + pr_debug("hystart_ack_train (%u > %u) delay_min %u (+ ack_delay %u) cwnd %u\n", + now - ca->round_start, threshold, + ca->delay_min, hystart_ack_delay(sk), tp->snd_cwnd); NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTTRAINDETECT); NET_ADD_STATS(sock_net(sk), @@ -404,15 +432,14 @@ static void hystart_update(struct sock *sk, u32 delay) if (hystart_detect & HYSTART_DELAY) { /* obtain the minimum delay of more than sampling packets */ + if (ca->curr_rtt > delay) + ca->curr_rtt = delay; if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { - if (ca->curr_rtt == 0 || ca->curr_rtt > delay) - ca->curr_rtt = delay; - ca->sample_cnt++; } else { if (ca->curr_rtt > ca->delay_min + HYSTART_DELAY_THRESH(ca->delay_min >> 3)) { - ca->found |= HYSTART_DELAY; + ca->found = 1; NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPHYSTARTDELAYDETECT); NET_ADD_STATS(sock_net(sk), @@ -424,9 +451,6 @@ static void hystart_update(struct sock *sk, u32 delay) } } -/* Track delayed acknowledgment ratio using sliding window - * ratio = (15*ratio + sample) / 16 - */ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) { const struct tcp_sock *tp = tcp_sk(sk); @@ -441,7 +465,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) if (ca->epoch_start && (s32)(tcp_jiffies32 - ca->epoch_start) < HZ) return; - delay = (sample->rtt_us << 3) / USEC_PER_MSEC; + delay = sample->rtt_us; if (delay == 0) delay = 1; @@ -450,7 +474,7 @@ static void bictcp_acked(struct sock *sk, const struct ack_sample *sample) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tcp_in_slow_start(tp) && + if (!ca->found && tcp_in_slow_start(tp) && hystart && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index a3a386236d93..89b8de350b10 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -26,8 +26,9 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, } else if (sk->sk_type == SOCK_STREAM) { const struct tcp_sock *tp = tcp_sk(sk); - r->idiag_rqueue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); - r->idiag_wqueue = tp->write_seq - tp->snd_una; + r->idiag_rqueue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); + r->idiag_wqueue = READ_ONCE(tp->write_seq) - tp->snd_una; } if (info) tcp_get_info(sk, info); diff --git a/net/ipv4/tcp_fastopen.c b/net/ipv4/tcp_fastopen.c index f5a45e1e1182..35679b308615 100644 --- a/net/ipv4/tcp_fastopen.c +++ b/net/ipv4/tcp_fastopen.c @@ -236,7 +236,7 @@ static struct sock *tcp_fastopen_create_child(struct sock *sk, */ tp = tcp_sk(child); - tp->fastopen_rsk = req; + rcu_assign_pointer(tp->fastopen_rsk, req); tcp_rsk(req)->tfo_listener = true; /* RFC1323: The window in SYN & SYN/ACK segments is never diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 21ed010d7551..755b44c7506a 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -260,7 +260,8 @@ static void tcp_ecn_accept_cwr(struct sock *sk, const struct sk_buff *skb) * cwnd may be very low (even just 1 packet), so we should ACK * immediately. */ - inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; + if (TCP_SKB_CB(skb)->seq != TCP_SKB_CB(skb)->end_seq) + inet_csk(sk)->icsk_ack.pending |= ICSK_ACK_NOW; } } @@ -359,7 +360,8 @@ static void tcp_sndbuf_expand(struct sock *sk) sndmem *= nr_segs * per_mss; if (sk->sk_sndbuf < sndmem) - sk->sk_sndbuf = min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2]); + WRITE_ONCE(sk->sk_sndbuf, + min(sndmem, sock_net(sk)->ipv4.sysctl_tcp_wmem[2])); } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -483,8 +485,9 @@ static void tcp_clamp_window(struct sock *sk) !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_under_memory_pressure(sk) && sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { - sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), - net->ipv4.sysctl_tcp_rmem[2]); + WRITE_ONCE(sk->sk_rcvbuf, + min(atomic_read(&sk->sk_rmem_alloc), + net->ipv4.sysctl_tcp_rmem[2])); } if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf) tp->rcv_ssthresh = min(tp->window_clamp, 2U * tp->advmss); @@ -648,7 +651,7 @@ void tcp_rcv_space_adjust(struct sock *sk) rcvbuf = min_t(u64, rcvwin * rcvmem, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); if (rcvbuf > sk->sk_rcvbuf) { - sk->sk_rcvbuf = rcvbuf; + WRITE_ONCE(sk->sk_rcvbuf, rcvbuf); /* Make the window clamp follow along. */ tp->window_clamp = tcp_win_from_space(sk, rcvbuf); @@ -909,9 +912,10 @@ static void tcp_check_sack_reordering(struct sock *sk, const u32 low_seq, /* This must be called before lost_out is incremented */ static void tcp_verify_retransmit_hint(struct tcp_sock *tp, struct sk_buff *skb) { - if (!tp->retransmit_skb_hint || - before(TCP_SKB_CB(skb)->seq, - TCP_SKB_CB(tp->retransmit_skb_hint)->seq)) + if ((!tp->retransmit_skb_hint && tp->retrans_out >= tp->lost_out) || + (tp->retransmit_skb_hint && + before(TCP_SKB_CB(skb)->seq, + TCP_SKB_CB(tp->retransmit_skb_hint)->seq))) tp->retransmit_skb_hint = skb; } @@ -1721,8 +1725,11 @@ tcp_sacktag_write_queue(struct sock *sk, const struct sk_buff *ack_skb, } /* Ignore very old stuff early */ - if (!after(sp[used_sacks].end_seq, prior_snd_una)) + if (!after(sp[used_sacks].end_seq, prior_snd_una)) { + if (i == 0) + first_sack_index = -1; continue; + } used_sacks++; } @@ -2662,7 +2669,7 @@ static void tcp_process_loss(struct sock *sk, int flag, int num_dupack, struct tcp_sock *tp = tcp_sk(sk); bool recovered = !before(tp->snd_una, tp->high_seq); - if ((flag & FLAG_SND_UNA_ADVANCED || tp->fastopen_rsk) && + if ((flag & FLAG_SND_UNA_ADVANCED || rcu_access_pointer(tp->fastopen_rsk)) && tcp_try_undo_loss(sk, false)) return; @@ -2933,6 +2940,8 @@ static bool tcp_ack_update_rtt(struct sock *sk, const int flag, u32 delta = tcp_time_stamp(tp) - tp->rx_opt.rcv_tsecr; if (likely(delta < INT_MAX / (USEC_PER_SEC / TCP_TS_HZ))) { + if (!delta) + delta = 1; seq_rtt_us = delta * (USEC_PER_SEC / TCP_TS_HZ); ca_rtt_us = seq_rtt_us; } @@ -2986,7 +2995,7 @@ void tcp_rearm_rto(struct sock *sk) /* If the retrans timer is currently being used by Fast Open * for SYN-ACK retrans purpose, stay put. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return; if (!tp->packets_out) { @@ -3154,6 +3163,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, u32 prior_fack, tp->retransmit_skb_hint = NULL; if (unlikely(skb == tp->lost_skb_hint)) tp->lost_skb_hint = NULL; + tcp_highest_sack_replace(sk, skb, next); tcp_rtx_queue_unlink_and_free(skb, sk); } @@ -3358,7 +3368,7 @@ static void tcp_rcv_nxt_update(struct tcp_sock *tp, u32 seq) sock_owned_by_me((struct sock *)tp); tp->bytes_received += delta; - tp->rcv_nxt = seq; + WRITE_ONCE(tp->rcv_nxt, seq); } /* Update our send window. @@ -3493,10 +3503,8 @@ static void tcp_replace_ts_recent(struct tcp_sock *tp, u32 seq) } } -/* This routine deals with acks during a TLP episode. - * We mark the end of a TLP episode on receiving TLP dupack or when - * ack is after tlp_high_seq. - * Ref: loss detection algorithm in draft-dukkipati-tcpm-tcp-loss-probe. +/* This routine deals with acks during a TLP episode and ends an episode by + * resetting tlp_high_seq. Ref: TLP algorithm in draft-ietf-tcpm-rack */ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) { @@ -3505,7 +3513,10 @@ static void tcp_process_tlp_ack(struct sock *sk, u32 ack, int flag) if (before(ack, tp->tlp_high_seq)) return; - if (flag & FLAG_DSACKING_ACK) { + if (!tp->tlp_retrans) { + /* TLP of new data has been acknowledged */ + tp->tlp_high_seq = 0; + } else if (flag & FLAG_DSACKING_ACK) { /* This DSACK means original and TLP probe arrived; no loss */ tp->tlp_high_seq = 0; } else if (after(ack, tp->tlp_high_seq)) { @@ -3671,6 +3682,15 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) tcp_in_ack_event(sk, ack_ev_flags); } + /* This is a deviation from RFC3168 since it states that: + * "When the TCP data sender is ready to set the CWR bit after reducing + * the congestion window, it SHOULD set the CWR bit only on the first + * new data packet that it transmits." + * We accept CWR on pure ACKs to be more robust + * with widely-deployed TCP implementations that do this. + */ + tcp_ecn_accept_cwr(sk, skb); + /* We passed data and got it acked, remove any soft error * log. Something worked... */ @@ -4500,6 +4520,7 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (unlikely(tcp_try_rmem_schedule(sk, skb, skb->truesize))) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPOFODROP); + sk->sk_data_ready(sk); tcp_drop(sk, skb); return; } @@ -4532,7 +4553,11 @@ static void tcp_data_queue_ofo(struct sock *sk, struct sk_buff *skb) if (tcp_ooo_try_coalesce(sk, tp->ooo_last_skb, skb, &fragstolen)) { coalesce_done: - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); kfree_skb_partial(skb, fragstolen); skb = NULL; goto add_sack; @@ -4616,7 +4641,11 @@ add_sack: tcp_sack_new_ofo_skb(sk, seq, end_seq); end: if (skb) { - tcp_grow_window(sk, skb); + /* For non sack flows, do not grow window to force DUPACK + * and trigger fast retransmit. + */ + if (tcp_is_sack(tp)) + tcp_grow_window(sk, skb); skb_condense(skb); skb_set_owner_r(skb, sk); } @@ -4696,7 +4725,8 @@ void tcp_data_ready(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int avail = tp->rcv_nxt - tp->copied_seq; - if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + if (avail < sk->sk_rcvlowat && !tcp_rmem_pressure(sk) && + !sock_flag(sk, SOCK_DONE)) return; sk->sk_data_ready(sk); @@ -4715,8 +4745,6 @@ static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) skb_dst_drop(skb); __skb_pull(skb, tcp_hdr(skb)->doff * 4); - tcp_ecn_accept_cwr(sk, skb); - tp->rx_opt.dsack = 0; /* Queue data for delivery to the user. @@ -4735,6 +4763,7 @@ queue_and_out: sk_forced_mem_schedule(sk, skb->truesize); else if (tcp_try_rmem_schedule(sk, skb, skb->truesize)) { NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPRCVQDROP); + sk->sk_data_ready(sk); goto drop; } @@ -5308,7 +5337,7 @@ static void tcp_check_urg(struct sock *sk, const struct tcphdr *th) } tp->urg_data = TCP_URG_NOTYET; - tp->urg_seq = ptr; + WRITE_ONCE(tp->urg_seq, ptr); /* Disable header prediction. */ tp->pred_flags = 0; @@ -5884,7 +5913,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Ok.. it's good. Set up sequence numbers and * move to established. */ - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -5913,7 +5942,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, /* Remember, tcp_poll() does not lock socket! * Change state from SYN-SENT only after copied_seq * is initialized. */ - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); smc_check_reset_syn(tp); @@ -5987,8 +6016,8 @@ discard: tp->tcp_header_len = sizeof(struct tcphdr); } - tp->rcv_nxt = TCP_SKB_CB(skb)->seq + 1; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->rcv_nxt, TCP_SKB_CB(skb)->seq + 1); + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); tp->rcv_wup = TCP_SKB_CB(skb)->seq + 1; /* RFC1323: The window in SYN & SYN/ACK segments is @@ -6039,7 +6068,13 @@ reset_and_undo: static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) { - tcp_try_undo_loss(sk, false); + struct request_sock *req; + + /* If we are still handling the SYNACK RTO, see if timestamp ECR allows + * undo. If peer SACKs triggered fast recovery, we can't undo here. + */ + if (inet_csk(sk)->icsk_ca_state == TCP_CA_Loss) + tcp_try_undo_loss(sk, false); /* Reset rtx states to prevent spurious retransmits_timed_out() */ tcp_sk(sk)->retrans_stamp = 0; @@ -6048,7 +6083,9 @@ static void tcp_rcv_synrecv_state_fastopen(struct sock *sk) /* Once we leave TCP_SYN_RECV or TCP_FIN_WAIT_1, * we no longer need req so release it. */ - reqsk_fastopen_remove(sk, tcp_sk(sk)->fastopen_rsk, false); + req = rcu_dereference_protected(tcp_sk(sk)->fastopen_rsk, + lockdep_sock_is_held(sk)); + reqsk_fastopen_remove(sk, req, false); /* Re-arm the timer because data may have been sent out. * This is similar to the regular data transmission case @@ -6123,7 +6160,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_mstamp_refresh(tp); tp->rx_opt.saw_tstamp = 0; - req = tp->fastopen_rsk; + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); if (req) { bool req_stolen; @@ -6163,7 +6201,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) tcp_try_undo_spurious_syn(sk); tp->retrans_stamp = 0; tcp_init_transfer(sk, BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB); - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); } smp_mb(); tcp_set_state(sk, TCP_ESTABLISHED); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cfa81190a1b1..ef4aa931d044 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -164,9 +164,11 @@ int tcp_twsk_unique(struct sock *sk, struct sock *sktw, void *twp) * without appearing to create any others. */ if (likely(!tp->repair)) { - tp->write_seq = tcptw->tw_snd_nxt + 65535 + 2; - if (tp->write_seq == 0) - tp->write_seq = 1; + u32 seq = tcptw->tw_snd_nxt + 65535 + 2; + + if (!seq) + seq = 1; + WRITE_ONCE(tp->write_seq, seq); tp->rx_opt.ts_recent = tcptw->tw_ts_recent; tp->rx_opt.ts_recent_stamp = tcptw->tw_ts_recent_stamp; } @@ -253,7 +255,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; if (likely(!tp->repair)) - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } inet->inet_dport = usin->sin_port; @@ -291,16 +293,17 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcp_seq(inet->inet_saddr, - inet->inet_daddr, - inet->inet_sport, - usin->sin_port); + WRITE_ONCE(tp->write_seq, + secure_tcp_seq(inet->inet_saddr, + inet->inet_daddr, + inet->inet_sport, + usin->sin_port)); tp->tsoffset = secure_tcp_ts_off(sock_net(sk), inet->inet_saddr, inet->inet_daddr); } - inet->inet_id = tp->write_seq ^ jiffies; + inet->inet_id = prandom_u32(); if (tcp_fastopen_defer_connect(sk, &err)) return err; @@ -478,7 +481,7 @@ int tcp_v4_err(struct sk_buff *icmp_skb, u32 info) icsk = inet_csk(sk); tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -1064,9 +1067,18 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, key = tcp_md5_do_lookup_exact(sk, addr, family, prefixlen); if (key) { - /* Pre-existing entry - just update that one. */ + /* Pre-existing entry - just update that one. + * Note that the key might be used concurrently. + */ memcpy(key->key, newkey, newkeylen); - key->keylen = newkeylen; + + /* Pairs with READ_ONCE() in tcp_md5_hash_key(). + * Also note that a reader could catch new key->keylen value + * but old key->key[], this is the reason we use __GFP_ZERO + * at sock_kmalloc() time below these lines. + */ + WRITE_ONCE(key->keylen, newkeylen); + return 0; } @@ -1082,7 +1094,7 @@ int tcp_md5_do_add(struct sock *sk, const union tcp_md5_addr *addr, rcu_assign_pointer(tp->md5sig_info, md5sig); } - key = sock_kmalloc(sk, sizeof(*key), gfp); + key = sock_kmalloc(sk, sizeof(*key), gfp | __GFP_ZERO); if (!key) return -ENOMEM; if (!tcp_alloc_md5sig_pool()) { @@ -1437,7 +1449,7 @@ struct sock *tcp_v4_syn_recv_sock(const struct sock *sk, struct sk_buff *skb, inet_csk(newsk)->icsk_ext_hdr_len = 0; if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; - newinet->inet_id = newtp->write_seq ^ jiffies; + newinet->inet_id = prandom_u32(); if (!dst) { dst = inet_csk_route_child_sock(sk, newsk, req); @@ -2096,7 +2108,7 @@ void tcp_v4_destroy_sock(struct sock *sk) if (inet_csk(sk)->icsk_bind_hash) inet_put_port(sk); - BUG_ON(tp->fastopen_rsk); + BUG_ON(rcu_access_pointer(tp->fastopen_rsk)); /* If socket is aborted during connect operation */ tcp_free_fastopen_req(tp); @@ -2121,13 +2133,14 @@ static void *listening_get_next(struct seq_file *seq, void *cur) struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); struct inet_listen_hashbucket *ilb; + struct hlist_nulls_node *node; struct sock *sk = cur; if (!sk) { get_head: ilb = &tcp_hashinfo.listening_hash[st->bucket]; spin_lock(&ilb->lock); - sk = sk_head(&ilb->head); + sk = sk_nulls_head(&ilb->nulls_head); st->offset = 0; goto get_sk; } @@ -2135,9 +2148,9 @@ get_head: ++st->num; ++st->offset; - sk = sk_next(sk); + sk = sk_nulls_next(sk); get_sk: - sk_for_each_from(sk) { + sk_nulls_for_each_from(sk, node) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == afinfo->family) @@ -2430,12 +2443,13 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(f, "%4d: %08X:%04X %08X:%04X %02X %08X:%08X %02X:%08lX " "%08X %5u %8d %lu %d %pK %lu %lu %u %u %d", i, src, srcp, dest, destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 7c35731816e2..bf7b3c8e338c 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -460,6 +460,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, struct tcp_request_sock *treq = tcp_rsk(req); struct inet_connection_sock *newicsk; struct tcp_sock *oldtp, *newtp; + u32 seq; if (!newsk) return NULL; @@ -473,12 +474,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, /* Now setup tcp_sock */ newtp->pred_flags = 0; - newtp->rcv_wup = newtp->copied_seq = - newtp->rcv_nxt = treq->rcv_isn + 1; + seq = treq->rcv_isn + 1; + newtp->rcv_wup = seq; + WRITE_ONCE(newtp->copied_seq, seq); + WRITE_ONCE(newtp->rcv_nxt, seq); newtp->segs_in = 1; - newtp->snd_sml = newtp->snd_una = - newtp->snd_nxt = newtp->snd_up = treq->snt_isn + 1; + seq = treq->snt_isn + 1; + newtp->snd_sml = newtp->snd_una = seq; + WRITE_ONCE(newtp->snd_nxt, seq); + newtp->snd_up = seq; INIT_LIST_HEAD(&newtp->tsq_node); INIT_LIST_HEAD(&newtp->tsorted_sent_queue); @@ -493,7 +498,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->total_retrans = req->num_retrans; tcp_init_xmit_timers(newsk); - newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; + WRITE_ONCE(newtp->write_seq, newtp->pushed_seq = treq->snt_isn + 1); if (sock_flag(newsk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(newsk, @@ -539,7 +544,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->rx_opt.mss_clamp = req->mss; tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; - newtp->fastopen_rsk = NULL; + RCU_INIT_POINTER(newtp->fastopen_rsk, NULL); __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 37c2f1204c1a..807dc290fb7d 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -67,11 +67,14 @@ static void tcp_event_new_data_sent(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); unsigned int prior_packets = tp->packets_out; - tp->snd_nxt = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(skb)->end_seq); __skb_unlink(skb, &sk->sk_write_queue); tcp_rbtree_insert(&sk->tcp_rtx_queue, skb); + if (tp->highest_sack == NULL) + tp->highest_sack = skb; + tp->packets_out += tcp_skb_pcount(skb); if (!prior_packets || icsk->icsk_pending == ICSK_TIME_LOSS_PROBE) tcp_rearm_rto(sk); @@ -659,7 +662,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, unsigned int mss, struct sk_buff *skb, struct tcp_out_options *opts, const struct tcp_md5sig_key *md5, - struct tcp_fastopen_cookie *foc) + struct tcp_fastopen_cookie *foc, + enum tcp_synack_type synack_type) { struct inet_request_sock *ireq = inet_rsk(req); unsigned int remaining = MAX_TCP_OPTION_SPACE; @@ -674,7 +678,8 @@ static unsigned int tcp_synack_options(const struct sock *sk, * rather than TS in order to fit in better with old, * buggy kernels, but that was deemed to be unnecessary. */ - ireq->tstamp_ok &= !ireq->sack_ok; + if (synack_type != TCP_SYNACK_COOKIE) + ireq->tstamp_ok &= !ireq->sack_ok; } #endif @@ -755,8 +760,9 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + if (likely(opts->num_sack_blocks)) + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -1183,10 +1189,10 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); /* Advance write_seq and place onto the write_queue. */ - tp->write_seq = TCP_SKB_CB(skb)->end_seq; + WRITE_ONCE(tp->write_seq, TCP_SKB_CB(skb)->end_seq); __skb_header_release(skb); tcp_add_write_queue_tail(sk, skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); } @@ -1320,7 +1326,7 @@ int tcp_fragment(struct sock *sk, enum tcp_queue tcp_queue, return -ENOMEM; /* We'll just try again later. */ skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); nlen = skb->len - len - nsize; buff->truesize += nlen; @@ -1430,7 +1436,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (delta_truesize) { skb->truesize -= delta_truesize; - sk->sk_wmem_queued -= delta_truesize; + sk_wmem_queued_add(sk, -delta_truesize); sk_mem_uncharge(sk, delta_truesize); sock_set_flag(sk, SOCK_QUEUE_SHRUNK); } @@ -1711,7 +1717,7 @@ static u32 tcp_tso_autosize(const struct sock *sk, unsigned int mss_now, u32 bytes, segs; bytes = min_t(unsigned long, - sk->sk_pacing_rate >> sk->sk_pacing_shift, + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift), sk->sk_gso_max_size - 1 - MAX_TCP_HEADER); /* Goal is to send at least one packet per ms, @@ -1875,7 +1881,7 @@ static int tso_fragment(struct sock *sk, struct sk_buff *skb, unsigned int len, return -ENOMEM; skb_copy_decrypted(buff, skb); - sk->sk_wmem_queued += buff->truesize; + sk_wmem_queued_add(sk, buff->truesize); sk_mem_charge(sk, buff->truesize); buff->truesize += nlen; skb->truesize -= nlen; @@ -2139,7 +2145,7 @@ static int tcp_mtu_probe(struct sock *sk) nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC, false); if (!nskb) return -1; - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = tcp_send_head(sk); @@ -2246,7 +2252,7 @@ static bool tcp_small_queue_check(struct sock *sk, const struct sk_buff *skb, limit = max_t(unsigned long, 2 * skb->truesize, - sk->sk_pacing_rate >> sk->sk_pacing_shift); + sk->sk_pacing_rate >> READ_ONCE(sk->sk_pacing_shift)); if (sk->sk_pacing_status == SK_PACING_NONE) limit = min_t(unsigned long, limit, sock_net(sk)->ipv4.sysctl_tcp_limit_output_bytes); @@ -2412,6 +2418,14 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, if (tcp_small_queue_check(sk, skb, 0)) break; + /* Argh, we hit an empty skb(), presumably a thread + * is sleeping in sendmsg()/sk_stream_wait_memory(). + * We do not want to send a pure-ack packet and have + * a strange looking rtx queue with empty packet(s). + */ + if (TCP_SKB_CB(skb)->end_seq == TCP_SKB_CB(skb)->seq) + break; + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; @@ -2457,7 +2471,7 @@ bool tcp_schedule_loss_probe(struct sock *sk, bool advancing_rto) /* Don't do any loss probe on a Fast Open connection before 3WHS * finishes. */ - if (tp->fastopen_rsk) + if (rcu_access_pointer(tp->fastopen_rsk)) return false; early_retrans = sock_net(sk)->ipv4.sysctl_tcp_early_retrans; @@ -2521,6 +2535,11 @@ void tcp_send_loss_probe(struct sock *sk) int pcount; int mss = tcp_current_mss(sk); + /* At most one outstanding TLP */ + if (tp->tlp_high_seq) + goto rearm_timer; + + tp->tlp_retrans = 0; skb = tcp_send_head(sk); if (skb && tcp_snd_wnd_test(tp, skb, mss)) { pcount = tp->packets_out; @@ -2538,10 +2557,6 @@ void tcp_send_loss_probe(struct sock *sk) return; } - /* At most one outstanding TLP retransmission. */ - if (tp->tlp_high_seq) - goto rearm_timer; - if (skb_still_in_host_queue(sk, skb)) goto rearm_timer; @@ -2563,10 +2578,12 @@ void tcp_send_loss_probe(struct sock *sk) if (__tcp_retransmit_skb(sk, skb, 1)) goto rearm_timer; + tp->tlp_retrans = 1; + +probe_sent: /* Record snd_nxt for loss detection. */ tp->tlp_high_seq = tp->snd_nxt; -probe_sent: NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); /* Reset s.t. tcp_rearm_rto will restart timer from now */ inet_csk(sk)->icsk_pending = 0; @@ -3117,7 +3134,7 @@ void tcp_send_fin(struct sock *sk) * if FIN had been sent. This is because retransmit path * does not change tp->snd_nxt. */ - tp->snd_nxt++; + WRITE_ONCE(tp->snd_nxt, tp->snd_nxt + 1); return; } } else { @@ -3194,10 +3211,11 @@ int tcp_send_synack(struct sock *sk) if (!nskb) return -ENOMEM; INIT_LIST_HEAD(&nskb->tcp_tsorted_anchor); + tcp_highest_sack_replace(sk, skb, nskb); tcp_rtx_queue_unlink_and_free(skb, sk); __skb_header_release(nskb); tcp_rbtree_insert(&sk->tcp_rtx_queue, nskb); - sk->sk_wmem_queued += nskb->truesize; + sk_wmem_queued_add(sk, nskb->truesize); sk_mem_charge(sk, nskb->truesize); skb = nskb; } @@ -3278,7 +3296,7 @@ struct sk_buff *tcp_make_synack(const struct sock *sk, struct dst_entry *dst, #endif skb_set_hash(skb, tcp_rsk(req)->txhash, PKT_HASH_TYPE_L4); tcp_header_size = tcp_synack_options(sk, req, mss, skb, &opts, md5, - foc) + sizeof(*th); + foc, synack_type) + sizeof(*th); skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -3398,14 +3416,14 @@ static void tcp_connect_init(struct sock *sk) tp->snd_una = tp->write_seq; tp->snd_sml = tp->write_seq; tp->snd_up = tp->write_seq; - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); if (likely(!tp->repair)) tp->rcv_nxt = 0; else tp->rcv_tstamp = tcp_jiffies32; tp->rcv_wup = tp->rcv_nxt; - tp->copied_seq = tp->rcv_nxt; + WRITE_ONCE(tp->copied_seq, tp->rcv_nxt); inet_csk(sk)->icsk_rto = tcp_timeout_init(sk); inet_csk(sk)->icsk_retransmits = 0; @@ -3419,9 +3437,9 @@ static void tcp_connect_queue_skb(struct sock *sk, struct sk_buff *skb) tcb->end_seq += skb->len; __skb_header_release(skb); - sk->sk_wmem_queued += skb->truesize; + sk_wmem_queued_add(sk, skb->truesize); sk_mem_charge(sk, skb->truesize); - tp->write_seq = tcb->end_seq; + WRITE_ONCE(tp->write_seq, tcb->end_seq); tp->packets_out += tcp_skb_pcount(skb); } @@ -3558,11 +3576,11 @@ int tcp_connect(struct sock *sk) /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. */ - tp->snd_nxt = tp->write_seq; + WRITE_ONCE(tp->snd_nxt, tp->write_seq); tp->pushed_seq = tp->write_seq; buff = tcp_send_head(sk); if (unlikely(buff)) { - tp->snd_nxt = TCP_SKB_CB(buff)->seq; + WRITE_ONCE(tp->snd_nxt, TCP_SKB_CB(buff)->seq); tp->pushed_seq = TCP_SKB_CB(buff)->seq; } TCP_INC_STATS(sock_net(sk), TCP_MIB_ACTIVEOPENS); diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 483323332d74..ace48d4e0801 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -386,15 +386,13 @@ abort: tcp_write_err(sk); * Timer for Fast Open socket to retransmit SYNACK. Note that the * sk here is the child socket, not the parent (listener) socket. */ -static void tcp_fastopen_synack_timer(struct sock *sk) +static void tcp_fastopen_synack_timer(struct sock *sk, struct request_sock *req) { struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req; - req = tcp_sk(sk)->fastopen_rsk; req->rsk_ops->syn_ack_timeout(req); if (req->num_timeout >= max_retries) { @@ -435,11 +433,14 @@ void tcp_retransmit_timer(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); struct inet_connection_sock *icsk = inet_csk(sk); + struct request_sock *req; - if (tp->fastopen_rsk) { + req = rcu_dereference_protected(tp->fastopen_rsk, + lockdep_sock_is_held(sk)); + if (req) { WARN_ON_ONCE(sk->sk_state != TCP_SYN_RECV && sk->sk_state != TCP_FIN_WAIT1); - tcp_fastopen_synack_timer(sk); + tcp_fastopen_synack_timer(sk, req); /* Before we receive ACK to our SYN-ACK don't retransmit * anything else (e.g., data or FIN segments). */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 665f26e32d77..1009a9e1b779 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -399,7 +399,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score += 4; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; } @@ -424,7 +424,7 @@ static struct sock *udp4_lib_lookup2(struct net *net, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -434,17 +434,20 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif, exact_dif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } + + result = reuseport_result ? : sk; badness = score; - result = sk; } } return result; @@ -1328,6 +1331,20 @@ static void udp_set_dev_scratch(struct sk_buff *skb) scratch->_tsize_state |= UDP_SKB_IS_STATELESS; } +static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) +{ + /* We come here after udp_lib_checksum_complete() returned 0. + * This means that __skb_checksum_complete() might have + * set skb->csum_valid to 1. + * On 64bit platforms, we can set csum_unnecessary + * to true, but only if the skb is not shared. + */ +#if BITS_PER_LONG == 64 + if (!skb_shared(skb)) + udp_skb_scratch(skb)->csum_unnecessary = true; +#endif +} + static int udp_skb_truesize(struct sk_buff *skb) { return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; @@ -1349,7 +1366,8 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, if (likely(partial)) { up->forward_deficit += size; size = up->forward_deficit; - if (size < (sk->sk_rcvbuf >> 2)) + if (size < (sk->sk_rcvbuf >> 2) && + !skb_queue_empty(&up->reader_queue)) return; } else { size += up->forward_deficit; @@ -1456,7 +1474,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) * queue contains some other skb */ rmem = atomic_add_return(size, &sk->sk_rmem_alloc); - if (rmem > (size + sk->sk_rcvbuf)) + if (rmem > (size + (unsigned int)sk->sk_rcvbuf)) goto uncharge_drop; spin_lock(&list->lock); @@ -1562,10 +1580,7 @@ static struct sk_buff *__first_packet_length(struct sock *sk, *total += skb->truesize; kfree_skb(skb); } else { - /* the csum related bits could be changed, refresh - * the scratch area - */ - udp_set_dev_scratch(skb); + udp_skb_csum_unnecessary_set(skb); break; } } @@ -1589,7 +1604,7 @@ static int first_packet_length(struct sock *sk) spin_lock_bh(&rcvq->lock); skb = __first_packet_length(sk, rcvq, &total); - if (!skb && !skb_queue_empty(sk_queue)) { + if (!skb && !skb_queue_empty_lockless(sk_queue)) { spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, rcvq); spin_unlock(&sk_queue->lock); @@ -1662,7 +1677,7 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, return skb; } - if (skb_queue_empty(sk_queue)) { + if (skb_queue_empty_lockless(sk_queue)) { spin_unlock_bh(&queue->lock); goto busy_check; } @@ -1688,7 +1703,7 @@ busy_check: break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (!skb_queue_empty(sk_queue)); + } while (!skb_queue_empty_lockless(sk_queue)); /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && @@ -1839,8 +1854,12 @@ int __udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); @@ -2024,7 +2043,7 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are @@ -2725,7 +2744,7 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - if (!skb_queue_empty(&udp_sk(sk)->reader_queue)) + if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Check for false positives due to checksum errors */ diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c index 910555a4d9fe..dccd2286bc28 100644 --- a/net/ipv4/udp_diag.c +++ b/net/ipv4/udp_diag.c @@ -64,8 +64,9 @@ static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, goto out; err = -ENOMEM; - rep = nlmsg_new(sizeof(struct inet_diag_msg) + - sizeof(struct inet_diag_meminfo) + 64, + rep = nlmsg_new(nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64, GFP_KERNEL); if (!rep) goto out; diff --git a/net/ipv4/xfrm4_output.c b/net/ipv4/xfrm4_output.c index ecff3fce9807..ab343ae686d4 100644 --- a/net/ipv4/xfrm4_output.c +++ b/net/ipv4/xfrm4_output.c @@ -58,9 +58,7 @@ int xfrm4_output_finish(struct sock *sk, struct sk_buff *skb) { memset(IPCB(skb), 0, sizeof(*IPCB(skb))); -#ifdef CONFIG_NETFILTER IPCB(skb)->flags |= IPSKB_XFRM_TRANSFORMED; -#endif return xfrm_output(sk, skb); } diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 35b84b52b702..9ebd54752e03 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -100,12 +100,13 @@ static int xfrm4_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm4_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm4_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index c94bc461e268..a18e52f9776c 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -1226,11 +1226,13 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) } static void -cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) +cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, + bool del_rt, bool del_peer) { struct fib6_info *f6i; - f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, + f6i = addrconf_get_prefix_route(del_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (f6i) { if (del_rt) @@ -1293,7 +1295,7 @@ static void ipv6_del_addr(struct inet6_ifaddr *ifp) if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, expires, - action == CLEANUP_PREFIX_RT_DEL); + action == CLEANUP_PREFIX_RT_DEL, false); } /* clean up prefsrc entries */ @@ -3292,6 +3294,10 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) if (netif_is_l3_master(idev->dev)) return; + /* no link local addresses on devices flagged as slaves */ + if (idev->dev->flags & IFF_SLAVE) + return; + ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); switch (idev->cnf.addr_gen_mode) { @@ -3343,6 +3349,10 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_NONE) && (dev->type != ARPHRD_RAWIP)) { /* Alas, we support only Ethernet autoconfiguration. */ + idev = __in6_dev_get(dev); + if (!IS_ERR_OR_NULL(idev) && dev->flags & IFF_UP && + dev->flags & IFF_MULTICAST) + ipv6_mc_up(idev); return; } @@ -4584,12 +4594,14 @@ inet6_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, } static int modify_prefix_route(struct inet6_ifaddr *ifp, - unsigned long expires, u32 flags) + unsigned long expires, u32 flags, + bool modify_peer) { struct fib6_info *f6i; u32 prio; - f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, + f6i = addrconf_get_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->idev->dev, 0, RTF_DEFAULT, true); if (!f6i) return -ENOENT; @@ -4600,7 +4612,8 @@ static int modify_prefix_route(struct inet6_ifaddr *ifp, ip6_del_rt(dev_net(ifp->idev->dev), f6i); /* add new one */ - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + addrconf_prefix_route(modify_peer ? &ifp->peer_addr : &ifp->addr, + ifp->prefix_len, ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } else { @@ -4622,6 +4635,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) unsigned long timeout; bool was_managetempaddr; bool had_prefixroute; + bool new_peer = false; ASSERT_RTNL(); @@ -4653,6 +4667,13 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) cfg->preferred_lft = timeout; } + if (cfg->peer_pfx && + memcmp(&ifp->peer_addr, cfg->peer_pfx, sizeof(struct in6_addr))) { + if (!ipv6_addr_any(&ifp->peer_addr)) + cleanup_prefix_route(ifp, expires, true, true); + new_peer = true; + } + spin_lock_bh(&ifp->lock); was_managetempaddr = ifp->flags & IFA_F_MANAGETEMPADDR; had_prefixroute = ifp->flags & IFA_F_PERMANENT && @@ -4668,6 +4689,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) if (cfg->rt_priority && cfg->rt_priority != ifp->rt_priority) ifp->rt_priority = cfg->rt_priority; + if (new_peer) + ifp->peer_addr = *cfg->peer_pfx; + spin_unlock_bh(&ifp->lock); if (!(ifp->flags&IFA_F_TENTATIVE)) ipv6_ifa_notify(0, ifp); @@ -4676,7 +4700,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) int rc = -ENOENT; if (had_prefixroute) - rc = modify_prefix_route(ifp, expires, flags); + rc = modify_prefix_route(ifp, expires, flags, false); /* prefix route could have been deleted; if so restore it */ if (rc == -ENOENT) { @@ -4684,6 +4708,15 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) ifp->rt_priority, ifp->idev->dev, expires, flags, GFP_KERNEL); } + + if (had_prefixroute && !ipv6_addr_any(&ifp->peer_addr)) + rc = modify_prefix_route(ifp, expires, flags, true); + + if (rc == -ENOENT && !ipv6_addr_any(&ifp->peer_addr)) { + addrconf_prefix_route(&ifp->peer_addr, ifp->prefix_len, + ifp->rt_priority, ifp->idev->dev, + expires, flags, GFP_KERNEL); + } } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; @@ -4694,7 +4727,7 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, struct ifa6_config *cfg) if (action != CLEANUP_PREFIX_RT_NOP) { cleanup_prefix_route(ifp, rt_expires, - action == CLEANUP_PREFIX_RT_DEL); + action == CLEANUP_PREFIX_RT_DEL, false); } } @@ -5229,16 +5262,16 @@ static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, return -EINVAL; } + if (!netlink_strict_get_check(skb)) + return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + ifm = nlmsg_data(nlh); if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); return -EINVAL; } - if (!netlink_strict_get_check(skb)) - return nlmsg_parse_deprecated(nlh, sizeof(*ifm), tb, IFA_MAX, - ifa_ipv6_policy, extack); - err = nlmsg_parse_deprecated_strict(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, extack); if (err) @@ -5717,6 +5750,9 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) struct nlattr *tb[IFLA_INET6_MAX + 1]; int err; + if (!idev) + return -EAFNOSUPPORT; + if (nla_parse_nested_deprecated(tb, IFLA_INET6_MAX, nla, NULL, NULL) < 0) BUG(); @@ -5979,9 +6015,9 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) - addrconf_prefix_route(&ifp->peer_addr, 128, 0, - ifp->idev->dev, 0, 0, - GFP_ATOMIC); + addrconf_prefix_route(&ifp->peer_addr, 128, + ifp->rt_priority, ifp->idev->dev, + 0, 0, GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) diff --git a/net/ipv6/addrconf_core.c b/net/ipv6/addrconf_core.c index 5b1246635e02..0ceb8943d648 100644 --- a/net/ipv6/addrconf_core.c +++ b/net/ipv6/addrconf_core.c @@ -128,11 +128,12 @@ int inet6addr_validator_notifier_call_chain(unsigned long val, void *v) } EXPORT_SYMBOL(inet6addr_validator_notifier_call_chain); -static int eafnosupport_ipv6_dst_lookup(struct net *net, struct sock *u1, - struct dst_entry **u2, - struct flowi6 *u3) +static struct dst_entry *eafnosupport_ipv6_dst_lookup_flow(struct net *net, + const struct sock *sk, + struct flowi6 *fl6, + const struct in6_addr *final_dst) { - return -EAFNOSUPPORT; + return ERR_PTR(-EAFNOSUPPORT); } static int eafnosupport_ipv6_route_input(struct sk_buff *skb) @@ -184,7 +185,7 @@ static int eafnosupport_fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, } const struct ipv6_stub *ipv6_stub __read_mostly = &(struct ipv6_stub) { - .ipv6_dst_lookup = eafnosupport_ipv6_dst_lookup, + .ipv6_dst_lookup_flow = eafnosupport_ipv6_dst_lookup_flow, .ipv6_route_input = eafnosupport_ipv6_route_input, .fib6_get_table = eafnosupport_fib6_get_table, .fib6_table_lookup = eafnosupport_fib6_table_lookup, diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 5352708b7b2d..1c4bb0c73307 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -732,7 +732,7 @@ int inet6_sk_rebuild_header(struct sock *sk) &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { sk->sk_route_caps = 0; sk->sk_err_soft = -PTR_ERR(dst); @@ -913,7 +913,7 @@ static int ipv6_route_input(struct sk_buff *skb) static const struct ipv6_stub ipv6_stub_impl = { .ipv6_sock_mc_join = ipv6_sock_mc_join, .ipv6_sock_mc_drop = ipv6_sock_mc_drop, - .ipv6_dst_lookup = ip6_dst_lookup, + .ipv6_dst_lookup_flow = ip6_dst_lookup_flow, .ipv6_route_input = ipv6_route_input, .fib6_get_table = fib6_get_table, .fib6_table_lookup = fib6_table_lookup, diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index fed91ab7ec46..cf3a88a10ddd 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -183,7 +183,7 @@ int ipv6_sock_ac_drop(struct sock *sk, int ifindex, const struct in6_addr *addr) return 0; } -void ipv6_sock_ac_close(struct sock *sk) +void __ipv6_sock_ac_close(struct sock *sk) { struct ipv6_pinfo *np = inet6_sk(sk); struct net_device *dev = NULL; @@ -191,10 +191,7 @@ void ipv6_sock_ac_close(struct sock *sk) struct net *net = sock_net(sk); int prev_index; - if (!np->ipv6_ac_list) - return; - - rtnl_lock(); + ASSERT_RTNL(); pac = np->ipv6_ac_list; np->ipv6_ac_list = NULL; @@ -211,6 +208,16 @@ void ipv6_sock_ac_close(struct sock *sk) sock_kfree_s(sk, pac, sizeof(*pac)); pac = next; } +} + +void ipv6_sock_ac_close(struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + if (!np->ipv6_ac_list) + return; + rtnl_lock(); + __ipv6_sock_ac_close(sk); rtnl_unlock(); } diff --git a/net/ipv6/calipso.c b/net/ipv6/calipso.c index 221c81f85cbf..8d3f66c310db 100644 --- a/net/ipv6/calipso.c +++ b/net/ipv6/calipso.c @@ -1047,7 +1047,8 @@ static int calipso_opt_getattr(const unsigned char *calipso, goto getattr_return; } - secattr->flags |= NETLBL_SECATTR_MLS_CAT; + if (secattr->attr.mls.cat) + secattr->flags |= NETLBL_SECATTR_MLS_CAT; } secattr->type = NETLBL_NLTYPE_CALIPSO; diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index 694168e2302e..655500d88dd4 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -85,7 +85,7 @@ int ip6_datagram_dst_update(struct sock *sk, bool fix_sk_saddr) final_p = fl6_update_dst(&fl6, opt, &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/esp6_offload.c b/net/ipv6/esp6_offload.c index d0d8528b294a..454fd8ac06d3 100644 --- a/net/ipv6/esp6_offload.c +++ b/net/ipv6/esp6_offload.c @@ -79,14 +79,14 @@ static struct sk_buff *esp6_gro_receive(struct list_head *head, if (!x) goto out_reset; + skb->mark = xfrm_smark_get(skb->mark, x); + sp->xvec[sp->len++] = x; sp->olen++; xo = xfrm_offload(skb); - if (!xo) { - xfrm_state_put(x); + if (!xo) goto out_reset; - } } xo->flags |= XFRM_GRO; @@ -121,9 +121,16 @@ static void esp6_gso_encap(struct xfrm_state *x, struct sk_buff *skb) struct ip_esp_hdr *esph; struct ipv6hdr *iph = ipv6_hdr(skb); struct xfrm_offload *xo = xfrm_offload(skb); - int proto = iph->nexthdr; + u8 proto = iph->nexthdr; skb_push(skb, -skb_network_offset(skb)); + + if (x->outer_mode.encap == XFRM_MODE_TRANSPORT) { + __be16 frag; + + ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &proto, &frag); + } + esph = ip_esp_hdr(skb); *skb_mac_header(skb) = IPPROTO_ESP; diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index 4da24aa6c696..eb0ce481bf6e 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -48,7 +48,7 @@ struct dst_entry *inet6_csk_route_req(const struct sock *sk, fl6->flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(fl6)); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(dst)) return NULL; @@ -103,7 +103,7 @@ static struct dst_entry *inet6_csk_route_socket(struct sock *sk, dst = __inet6_csk_dst_check(sk, np->dst_cookie); if (!dst) { - dst = ip6_dst_lookup_flow(sk, fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (!IS_ERR(dst)) ip6_dst_store(sk, dst, NULL, NULL); @@ -146,7 +146,7 @@ struct dst_entry *inet6_csk_update_pmtu(struct sock *sk, u32 mtu) if (IS_ERR(dst)) return NULL; - dst->ops->update_pmtu(dst, sk, NULL, mtu); + dst->ops->update_pmtu(dst, sk, NULL, mtu, true); dst = inet6_csk_route_socket(sk, &fl6); return IS_ERR(dst) ? NULL : dst; diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index b2a55f300318..df28da487303 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -105,7 +105,7 @@ static inline int compute_score(struct sock *sk, struct net *net, return -1; score = 1; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; } return score; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index 455f1292e479..82a6c4c4a6e2 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -611,7 +611,7 @@ static int inet6_dump_fib(struct sk_buff *skb, struct netlink_callback *cb) if (arg.filter.table_id) { tb = fib6_get_table(net, arg.filter.table_id); if (!tb) { - if (arg.filter.dump_all_families) + if (rtnl_msg_family(cb->nlh) != PF_INET6) goto out; NL_SET_ERR_MSG_MOD(cb->extack, "FIB table does not exist"); @@ -1004,8 +1004,7 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, found++; break; } - if (rt_can_ecmp) - fallback_ins = fallback_ins ?: ins; + fallback_ins = fallback_ins ?: ins; goto next_iter; } @@ -1048,7 +1047,9 @@ next_iter: } if (fallback_ins && !found) { - /* No ECMP-able route found, replace first non-ECMP one */ + /* No matching route with same ecmp-able-ness found, replace + * first matching route + */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, lockdep_is_held(&rt->fib6_table->tb6_lock)); diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index d5779d6a6065..8d48f7f9fdc6 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -127,6 +127,7 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, gre_proto == htons(ETH_P_ERSPAN2)) ? ARPHRD_ETHER : ARPHRD_IP6GRE; int score, cand_score = 4; + struct net_device *ndev; for_each_ip_tunnel_rcu(t, ign->tunnels_r_l[h0 ^ h1]) { if (!ipv6_addr_equal(local, &t->parms.laddr) || @@ -238,9 +239,9 @@ static struct ip6_tnl *ip6gre_tunnel_lookup(struct net_device *dev, if (t && t->dev->flags & IFF_UP) return t; - dev = ign->fb_tunnel_dev; - if (dev && dev->flags & IFF_UP) - return netdev_priv(dev); + ndev = READ_ONCE(ign->fb_tunnel_dev); + if (ndev && ndev->flags & IFF_UP) + return netdev_priv(ndev); return NULL; } @@ -413,6 +414,8 @@ static void ip6gre_tunnel_uninit(struct net_device *dev) ip6gre_tunnel_unlink_md(ign, t); ip6gre_tunnel_unlink(ign, t); + if (ign->fb_tunnel_dev == dev) + WRITE_ONCE(ign->fb_tunnel_dev, NULL); dst_cache_reset(&t->dst_cache); dev_put(dev); } @@ -980,9 +983,9 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, dsfield = key->tos; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) goto tx_err; - md = ip_tunnel_info_opts(tun_info); - if (!md) + if (tun_info->options_len < sizeof(*md)) goto tx_err; + md = ip_tunnel_info_opts(tun_info); tun_id = tunnel_id_to_key32(key->tun_id); if (md->version == 1) { @@ -1040,7 +1043,7 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, /* TooBig packet may have updated dst->dev's mtu */ if (!t->parms.collect_md && dst && dst_mtu(dst) > dst->dev->mtu) - dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu); + dst->ops->update_pmtu(dst, NULL, skb, dst->dev->mtu, false); err = ip6_tnl_xmit(skb, dev, dsfield, &fl6, encap_limit, &mtu, NEXTHDR_GRE); @@ -1466,7 +1469,6 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) dev->mtu -= 8; if (tunnel->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; netif_keep_dst(dev); } ip6gre_tnl_init_features(dev); @@ -1558,17 +1560,18 @@ static void ip6gre_destroy_tunnels(struct net *net, struct list_head *head) static int __net_init ip6gre_init_net(struct net *net) { struct ip6gre_net *ign = net_generic(net, ip6gre_net_id); + struct net_device *ndev; int err; if (!net_has_fallback_tunnels(net)) return 0; - ign->fb_tunnel_dev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", - NET_NAME_UNKNOWN, - ip6gre_tunnel_setup); - if (!ign->fb_tunnel_dev) { + ndev = alloc_netdev(sizeof(struct ip6_tnl), "ip6gre0", + NET_NAME_UNKNOWN, ip6gre_tunnel_setup); + if (!ndev) { err = -ENOMEM; goto err_alloc_dev; } + ign->fb_tunnel_dev = ndev; dev_net_set(ign->fb_tunnel_dev, net); /* FB netdevice is special: we have one, and only one per netns. * Allowing to move it to another netns is clearly unsafe. @@ -1588,7 +1591,7 @@ static int __net_init ip6gre_init_net(struct net *net) return 0; err_reg_dev: - free_netdev(ign->fb_tunnel_dev); + free_netdev(ndev); err_alloc_dev: return err; } @@ -1894,7 +1897,6 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); @@ -2196,7 +2198,6 @@ static void ip6erspan_tap_setup(struct net_device *dev) dev->needs_free_netdev = true; dev->priv_destructor = ip6gre_dev_free; - dev->features |= NETIF_F_NETNS_LOCAL; dev->priv_flags &= ~IFF_TX_SKB_SHARING; dev->priv_flags |= IFF_LIVE_ADDR_CHANGE; netif_keep_dst(dev); diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 21efcd02f337..d3a0f577d9ec 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1081,19 +1081,19 @@ EXPORT_SYMBOL_GPL(ip6_dst_lookup); * It returns a valid dst pointer on success, or a pointer encoded * error code. */ -struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, +struct dst_entry *ip6_dst_lookup_flow(struct net *net, const struct sock *sk, struct flowi6 *fl6, const struct in6_addr *final_dst) { struct dst_entry *dst = NULL; int err; - err = ip6_dst_lookup_tail(sock_net(sk), sk, &dst, fl6); + err = ip6_dst_lookup_tail(net, sk, &dst, fl6); if (err) return ERR_PTR(err); if (final_dst) fl6->daddr = *final_dst; - return xfrm_lookup_route(sock_net(sk), dst, flowi6_to_flowi(fl6), sk, 0); + return xfrm_lookup_route(net, dst, flowi6_to_flowi(fl6), sk, 0); } EXPORT_SYMBOL_GPL(ip6_dst_lookup_flow); @@ -1125,7 +1125,7 @@ struct dst_entry *ip6_sk_dst_lookup_flow(struct sock *sk, struct flowi6 *fl6, if (dst) return dst; - dst = ip6_dst_lookup_flow(sk, fl6, final_dst); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_dst); if (connected && !IS_ERR(dst)) ip6_sk_dst_store_flow(sk, dst_clone(dst), fl6); diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index d10a9e40729f..a1134dcb75e1 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -640,7 +640,7 @@ ip4ip6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, if (rel_info > dst_mtu(skb_dst(skb2))) goto out; - skb_dst_update_pmtu(skb2, rel_info); + skb_dst_update_pmtu_no_confirm(skb2, rel_info); } icmp_send(skb2, rel_type, rel_code, htonl(rel_info)); @@ -1132,7 +1132,7 @@ route_lookup: mtu = max(mtu, skb->protocol == htons(ETH_P_IPV6) ? IPV6_MIN_MTU : IPV4_MIN_MTU); - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len - t->tun_hlen - eth_hlen > mtu && !skb_is_gso(skb)) { *pmtu = mtu; err = -EMSGSIZE; @@ -1877,10 +1877,8 @@ static int ip6_tnl_dev_init(struct net_device *dev) if (err) return err; ip6_tnl_link_config(t); - if (t->parms.collect_md) { - dev->features |= NETIF_F_NETNS_LOCAL; + if (t->parms.collect_md) netif_keep_dst(dev); - } return 0; } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index 024db17386d2..cc6180e08a4f 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -311,7 +311,7 @@ static int vti6_rcv(struct sk_buff *skb) if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); - return 0; + goto discard; } ipv6h = ipv6_hdr(skb); @@ -449,8 +449,35 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) int err = -1; int mtu; - if (!dst) - goto tx_err_link_failure; + if (!dst) { + switch (skb->protocol) { + case htons(ETH_P_IP): { + struct rtable *rt; + + fl->u.ip4.flowi4_oif = dev->ifindex; + fl->u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl->u.ip4); + if (IS_ERR(rt)) + goto tx_err_link_failure; + dst = &rt->dst; + skb_dst_set(skb, dst); + break; + } + case htons(ETH_P_IPV6): + fl->u.ip6.flowi6_oif = dev->ifindex; + fl->u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl->u.ip6); + if (dst->error) { + dst_release(dst); + dst = NULL; + goto tx_err_link_failure; + } + skb_dst_set(skb, dst); + break; + default: + goto tx_err_link_failure; + } + } dst_hold(dst); dst = xfrm_lookup(t->net, dst, fl, NULL, 0); @@ -479,7 +506,7 @@ vti6_xmit(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index e80d36c5073d..da7ab5ac07fb 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -2498,7 +2498,7 @@ static int ip6mr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) mrt = ip6mr_get_table(sock_net(skb->sk), filter.table_id); if (!mrt) { - if (filter.dump_all_families) + if (rtnl_msg_family(cb->nlh) != RTNL_FAMILY_IP6MR) return skb->len; NL_SET_ERR_MSG_MOD(cb->extack, "MR table does not exist"); diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 264c292e7dcc..0716282ea85d 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -183,8 +183,14 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, retv = -EBUSY; break; } - } else if (sk->sk_protocol != IPPROTO_TCP) + } else if (sk->sk_protocol == IPPROTO_TCP) { + if (sk->sk_prot != &tcpv6_prot) { + retv = -EBUSY; + break; + } + } else { break; + } if (sk->sk_state != TCP_ESTABLISHED) { retv = -ENOTCONN; @@ -199,6 +205,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, fl6_free_socklist(sk); __ipv6_sock_mc_close(sk); + __ipv6_sock_ac_close(sk); /* * Sock is moving from IPv6 to IPv4 (sk_prot), so diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index eaa4c2cc2fbb..c875c9b6edbe 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2618,6 +2618,7 @@ void ipv6_mc_destroy_dev(struct inet6_dev *idev) idev->mc_list = i->next; write_unlock_bh(&idev->lock); + ip6_mc_clear_src(i); ma_put(i); write_lock_bh(&idev->lock); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 70693bc7ad9d..f3cf6ef5ce9e 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -923,7 +923,7 @@ static int rawv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6a6e403c71ac..a71b115e65fe 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -95,7 +95,8 @@ static int ip6_pkt_prohibit(struct sk_buff *skb); static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff *skb); static void ip6_link_failure(struct sk_buff *skb); static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu); + struct sk_buff *skb, u32 mtu, + bool confirm_neigh); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); static int rt6_score_route(const struct fib6_nh *nh, u32 fib6_flags, int oif, @@ -264,7 +265,8 @@ static unsigned int ip6_blackhole_mtu(const struct dst_entry *dst) } static void ip6_rt_blackhole_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { } @@ -546,6 +548,7 @@ static void rt6_probe(struct fib6_nh *fib6_nh) { struct __rt6_probe_work *work = NULL; const struct in6_addr *nh_gw; + unsigned long last_probe; struct neighbour *neigh; struct net_device *dev; struct inet6_dev *idev; @@ -558,12 +561,13 @@ static void rt6_probe(struct fib6_nh *fib6_nh) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - if (fib6_nh->fib_nh_gw_family) + if (!fib6_nh->fib_nh_gw_family) return; nh_gw = &fib6_nh->fib_nh_gw6; dev = fib6_nh->fib_nh_dev; rcu_read_lock_bh(); + last_probe = READ_ONCE(fib6_nh->last_probe); idev = __in6_dev_get(dev); neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { @@ -579,13 +583,15 @@ static void rt6_probe(struct fib6_nh *fib6_nh) __neigh_set_probe_once(neigh); } write_unlock(&neigh->lock); - } else if (time_after(jiffies, fib6_nh->last_probe + + } else if (time_after(jiffies, last_probe + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); } - if (work) { - fib6_nh->last_probe = jiffies; + if (!work || cmpxchg(&fib6_nh->last_probe, + last_probe, jiffies) != last_probe) { + kfree(work); + } else { INIT_WORK(&work->work, rt6_probe_deferred); work->target = *nh_gw; dev_hold(dev); @@ -2343,13 +2349,16 @@ static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, - const struct ipv6hdr *iph, u32 mtu) + const struct ipv6hdr *iph, u32 mtu, + bool confirm_neigh) { const struct in6_addr *daddr, *saddr; struct rt6_info *rt6 = (struct rt6_info *)dst; - if (dst_metric_locked(dst, RTAX_MTU)) - return; + /* Note: do *NOT* check dst_metric_locked(dst, RTAX_MTU) + * IPv6 pmtu discovery isn't optional, so 'mtu lock' cannot disable it. + * [see also comment in rt6_mtu_change_route()] + */ if (iph) { daddr = &iph->daddr; @@ -2361,7 +2370,10 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, daddr = NULL; saddr = NULL; } - dst_confirm_neigh(dst, daddr); + + if (confirm_neigh) + dst_confirm_neigh(dst, daddr); + mtu = max_t(u32, mtu, IPV6_MIN_MTU); if (mtu >= dst_mtu(dst)) return; @@ -2396,9 +2408,11 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, } static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { - __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu); + __ip6_rt_update_pmtu(dst, sk, skb ? ipv6_hdr(skb) : NULL, mtu, + confirm_neigh); } void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, @@ -2417,7 +2431,7 @@ void ip6_update_pmtu(struct sk_buff *skb, struct net *net, __be32 mtu, dst = ip6_route_output(net, NULL, &fl6); if (!dst->error) - __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu)); + __ip6_rt_update_pmtu(dst, NULL, iph, ntohl(mtu), true); dst_release(dst); } EXPORT_SYMBOL_GPL(ip6_update_pmtu); @@ -2975,7 +2989,7 @@ static bool fib6_is_reject(u32 flags, struct net_device *dev, int addr_type) if ((flags & RTF_REJECT) || (dev && (dev->flags & IFF_LOOPBACK) && !(addr_type & IPV6_ADDR_LOOPBACK) && - !(flags & RTF_LOCAL))) + !(flags & (RTF_ANYCAST | RTF_LOCAL)))) return true; return false; @@ -2991,6 +3005,9 @@ int fib6_nh_init(struct net *net, struct fib6_nh *fib6_nh, int err; fib6_nh->fib_nh_family = AF_INET6; +#ifdef CONFIG_IPV6_ROUTER_PREF + fib6_nh->last_probe = jiffies; +#endif err = -ENODEV; if (cfg->fc_ifindex) { @@ -4544,6 +4561,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, */ cfg->fc_nlinfo.nlh->nlmsg_flags &= ~(NLM_F_EXCL | NLM_F_REPLACE); + cfg->fc_nlinfo.nlh->nlmsg_flags |= NLM_F_CREATE; nhn++; } diff --git a/net/ipv6/seg6_local.c b/net/ipv6/seg6_local.c index 9d4f75e0d33a..af1091451316 100644 --- a/net/ipv6/seg6_local.c +++ b/net/ipv6/seg6_local.c @@ -23,6 +23,7 @@ #include <net/addrconf.h> #include <net/ip6_route.h> #include <net/dst_cache.h> +#include <net/ip_tunnels.h> #ifdef CONFIG_IPV6_SEG6_HMAC #include <net/seg6_hmac.h> #endif @@ -130,7 +131,8 @@ static bool decap_and_validate(struct sk_buff *skb, int proto) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->encapsulation = 0; + if (iptunnel_pull_offloads(skb)) + return false; return true; } diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index 80610899a323..91a89c662f1a 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -939,7 +939,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (tunnel->parms.iph.daddr) - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->len > mtu && !skb_is_gso(skb)) { icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 16632e02e9b0..30915f6f31e3 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -235,7 +235,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.flowi6_uid = sk->sk_uid; security_req_classify_flow(req, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) goto out_free; } diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7a14ea37d2df..70b36dc26f62 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -215,7 +215,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, !ipv6_addr_equal(&sk->sk_v6_daddr, &usin->sin6_addr)) { tp->rx_opt.ts_recent = 0; tp->rx_opt.ts_recent_stamp = 0; - tp->write_seq = 0; + WRITE_ONCE(tp->write_seq, 0); } sk->sk_v6_daddr = usin->sin6_addr; @@ -275,7 +275,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, security_sk_classify_flow(sk, flowi6_to_flowi(&fl6)); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto failure; @@ -311,10 +311,11 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (likely(!tp->repair)) { if (!tp->write_seq) - tp->write_seq = secure_tcpv6_seq(np->saddr.s6_addr32, - sk->sk_v6_daddr.s6_addr32, - inet->inet_sport, - inet->inet_dport); + WRITE_ONCE(tp->write_seq, + secure_tcpv6_seq(np->saddr.s6_addr32, + sk->sk_v6_daddr.s6_addr32, + inet->inet_sport, + inet->inet_dport)); tp->tsoffset = secure_tcpv6_ts_off(sock_net(sk), np->saddr.s6_addr32, sk->sk_v6_daddr.s6_addr32); @@ -406,7 +407,7 @@ static int tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, tp = tcp_sk(sk); /* XXX (TFO) - tp->snd_una should be ISN (tcp_create_openreq_child() */ - fastopen = tp->fastopen_rsk; + fastopen = rcu_dereference(tp->fastopen_rsk); snd_una = fastopen ? tcp_rsk(fastopen)->snt_isn : tp->snd_una; if (sk->sk_state != TCP_LISTEN && !between(seq, snd_una, tp->snd_nxt)) { @@ -896,7 +897,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 * Underlying function will use this to retrieve the network * namespace */ - dst = ip6_dst_lookup_flow(ctl_sk, &fl6, NULL); + dst = ip6_dst_lookup_flow(sock_net(ctl_sk), ctl_sk, &fl6, NULL); if (!IS_ERR(dst)) { skb_dst_set(buff, dst); ip6_xmit(ctl_sk, buff, &fl6, fl6.flowi6_mark, NULL, tclass); @@ -1852,7 +1853,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) /* Because we don't lock the socket, * we might find a transient negative value. */ - rx_queue = max_t(int, tp->rcv_nxt - tp->copied_seq, 0); + rx_queue = max_t(int, READ_ONCE(tp->rcv_nxt) - + READ_ONCE(tp->copied_seq), 0); seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " @@ -1863,7 +1865,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest->s6_addr32[0], dest->s6_addr32[1], dest->s6_addr32[2], dest->s6_addr32[3], destp, state, - tp->write_seq - tp->snd_una, + READ_ONCE(tp->write_seq) - tp->snd_una, rx_queue, timer_active, jiffies_delta_to_clock_t(timer_expires - jiffies), diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index f0b5edd861d0..e0ff2f60f53c 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -145,7 +145,7 @@ static int compute_score(struct sock *sk, struct net *net, return -1; score++; - if (sk->sk_incoming_cpu == raw_smp_processor_id()) + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; return score; @@ -158,7 +158,7 @@ static struct sock *udp6_lib_lookup2(struct net *net, int dif, int sdif, bool exact_dif, struct udp_hslot *hslot2, struct sk_buff *skb) { - struct sock *sk, *result; + struct sock *sk, *result, *reuseport_result; int score, badness; u32 hash = 0; @@ -168,17 +168,20 @@ static struct sock *udp6_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif, exact_dif); if (score > badness) { + reuseport_result = NULL; + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; + reuseport_result = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (reuseport_result && !reuseport_has_conns(sk, false)) + return reuseport_result; } - result = sk; + + result = reuseport_result ? : sk; badness = score; } } @@ -655,7 +658,7 @@ static int udpv6_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets (see net/ipv4/udp.c). */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { if (up->pcrlen == 0) { /* full coverage was set */ net_dbg_ratelimited("UDPLITE6: partial coverage %d while full coverage %d requested\n", diff --git a/net/ipv6/xfrm6_output.c b/net/ipv6/xfrm6_output.c index eecac1b7148e..cf2a0ce15c1c 100644 --- a/net/ipv6/xfrm6_output.c +++ b/net/ipv6/xfrm6_output.c @@ -111,9 +111,7 @@ int xfrm6_output_finish(struct sock *sk, struct sk_buff *skb) { memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); -#ifdef CONFIG_NETFILTER IP6CB(skb)->flags |= IP6SKB_XFRM_TRANSFORMED; -#endif return xfrm_output(sk, skb); } diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 699e0730ce8e..af7a4b8b1e9c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -98,12 +98,13 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, } static void xfrm6_update_pmtu(struct dst_entry *dst, struct sock *sk, - struct sk_buff *skb, u32 mtu) + struct sk_buff *skb, u32 mtu, + bool confirm_neigh) { struct xfrm_dst *xdst = (struct xfrm_dst *)dst; struct dst_entry *path = xdst->route; - path->ops->update_pmtu(path, sk, skb, mtu); + path->ops->update_pmtu(path, sk, skb, mtu, confirm_neigh); } static void xfrm6_redirect(struct dst_entry *dst, struct sock *sk, diff --git a/net/key/af_key.c b/net/key/af_key.c index fe5fc4bab7ee..d38988087ead 100644 --- a/net/key/af_key.c +++ b/net/key/af_key.c @@ -2402,7 +2402,7 @@ static int pfkey_spddelete(struct sock *sk, struct sk_buff *skb, const struct sa return err; } - xp = xfrm_policy_bysel_ctx(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_bysel_ctx(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, pol->sadb_x_policy_dir - 1, &sel, pol_ctx, 1, &err); security_xfrm_policy_free(pol_ctx); @@ -2653,7 +2653,7 @@ static int pfkey_spdget(struct sock *sk, struct sk_buff *skb, const struct sadb_ return -EINVAL; delete = (hdr->sadb_msg_type == SADB_X_SPDDELETE2); - xp = xfrm_policy_byid(net, DUMMY_MARK, 0, XFRM_POLICY_TYPE_MAIN, + xp = xfrm_policy_byid(net, &dummy_mark, 0, XFRM_POLICY_TYPE_MAIN, dir, pol->sadb_x_policy_id, delete, &err); if (xp == NULL) return -ENOENT; diff --git a/net/l2tp/l2tp_core.c b/net/l2tp/l2tp_core.c index 105e5a7092e7..4399c8466fe0 100644 --- a/net/l2tp/l2tp_core.c +++ b/net/l2tp/l2tp_core.c @@ -322,8 +322,13 @@ int l2tp_session_register(struct l2tp_session *session, spin_lock_bh(&pn->l2tp_session_hlist_lock); + /* IP encap expects session IDs to be globally unique, while + * UDP encap doesn't. + */ hlist_for_each_entry(session_walk, g_head, global_hlist) - if (session_walk->session_id == session->session_id) { + if (session_walk->session_id == session->session_id && + (session_walk->tunnel->encap == L2TP_ENCAPTYPE_IP || + tunnel->encap == L2TP_ENCAPTYPE_IP)) { err = -EEXIST; goto err_tlock_pnlock; } @@ -1025,6 +1030,7 @@ static void l2tp_xmit_core(struct l2tp_session *session, struct sk_buff *skb, /* Queue the packet to IP for output */ skb->ignore_df = 1; + skb_dst_drop(skb); #if IS_ENABLED(CONFIG_IPV6) if (l2tp_sk_is_v6(tunnel->sock)) error = inet6_csk_xmit(tunnel->sock, skb, NULL); @@ -1096,10 +1102,6 @@ int l2tp_xmit_skb(struct l2tp_session *session, struct sk_buff *skb, int hdr_len goto out_unlock; } - /* Get routing info from the tunnel socket */ - skb_dst_drop(skb); - skb_dst_set(skb, sk_dst_check(sk, 0)); - inet = inet_sk(sk); fl = &inet->cork.fl; switch (tunnel->encap) { @@ -1455,6 +1457,9 @@ static int l2tp_validate_socket(const struct sock *sk, const struct net *net, if (sk->sk_type != SOCK_DGRAM) return -EPROTONOSUPPORT; + if (sk->sk_family != PF_INET && sk->sk_family != PF_INET6) + return -EPROTONOSUPPORT; + if ((encap == L2TP_ENCAPTYPE_UDP && sk->sk_protocol != IPPROTO_UDP) || (encap == L2TP_ENCAPTYPE_IP && sk->sk_protocol != IPPROTO_L2TP)) return -EPROTONOSUPPORT; diff --git a/net/l2tp/l2tp_ip.c b/net/l2tp/l2tp_ip.c index 622833317dcb..ec33c3768727 100644 --- a/net/l2tp/l2tp_ip.c +++ b/net/l2tp/l2tp_ip.c @@ -20,7 +20,6 @@ #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> -#include <net/inet_hashtables.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> @@ -209,15 +208,31 @@ discard: return 0; } -static int l2tp_ip_open(struct sock *sk) +static int l2tp_ip_hash(struct sock *sk) { - /* Prevent autobind. We don't have ports. */ - inet_sk(sk)->inet_num = IPPROTO_L2TP; + if (sk_unhashed(sk)) { + write_lock_bh(&l2tp_ip_lock); + sk_add_node(sk, &l2tp_ip_table); + write_unlock_bh(&l2tp_ip_lock); + } + return 0; +} +static void l2tp_ip_unhash(struct sock *sk) +{ + if (sk_unhashed(sk)) + return; write_lock_bh(&l2tp_ip_lock); - sk_add_node(sk, &l2tp_ip_table); + sk_del_node_init(sk); write_unlock_bh(&l2tp_ip_lock); +} + +static int l2tp_ip_open(struct sock *sk) +{ + /* Prevent autobind. We don't have ports. */ + inet_sk(sk)->inet_num = IPPROTO_L2TP; + l2tp_ip_hash(sk); return 0; } @@ -594,8 +609,8 @@ static struct proto l2tp_ip_prot = { .sendmsg = l2tp_ip_sendmsg, .recvmsg = l2tp_ip_recvmsg, .backlog_rcv = l2tp_ip_backlog_recv, - .hash = inet_hash, - .unhash = inet_unhash, + .hash = l2tp_ip_hash, + .unhash = l2tp_ip_unhash, .obj_size = sizeof(struct l2tp_ip_sock), #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ip_setsockopt, diff --git a/net/l2tp/l2tp_ip6.c b/net/l2tp/l2tp_ip6.c index 1a76a0a4e3ab..e2d44e8b77d0 100644 --- a/net/l2tp/l2tp_ip6.c +++ b/net/l2tp/l2tp_ip6.c @@ -20,8 +20,6 @@ #include <net/icmp.h> #include <net/udp.h> #include <net/inet_common.h> -#include <net/inet_hashtables.h> -#include <net/inet6_hashtables.h> #include <net/tcp_states.h> #include <net/protocol.h> #include <net/xfrm.h> @@ -222,15 +220,31 @@ discard: return 0; } -static int l2tp_ip6_open(struct sock *sk) +static int l2tp_ip6_hash(struct sock *sk) { - /* Prevent autobind. We don't have ports. */ - inet_sk(sk)->inet_num = IPPROTO_L2TP; + if (sk_unhashed(sk)) { + write_lock_bh(&l2tp_ip6_lock); + sk_add_node(sk, &l2tp_ip6_table); + write_unlock_bh(&l2tp_ip6_lock); + } + return 0; +} +static void l2tp_ip6_unhash(struct sock *sk) +{ + if (sk_unhashed(sk)) + return; write_lock_bh(&l2tp_ip6_lock); - sk_add_node(sk, &l2tp_ip6_table); + sk_del_node_init(sk); write_unlock_bh(&l2tp_ip6_lock); +} + +static int l2tp_ip6_open(struct sock *sk) +{ + /* Prevent autobind. We don't have ports. */ + inet_sk(sk)->inet_num = IPPROTO_L2TP; + l2tp_ip6_hash(sk); return 0; } @@ -615,7 +629,7 @@ static int l2tp_ip6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) fl6.flowlabel = ip6_make_flowinfo(ipc6.tclass, fl6.flowlabel); - dst = ip6_dst_lookup_flow(sk, &fl6, final_p); + dst = ip6_dst_lookup_flow(sock_net(sk), sk, &fl6, final_p); if (IS_ERR(dst)) { err = PTR_ERR(dst); goto out; @@ -728,8 +742,8 @@ static struct proto l2tp_ip6_prot = { .sendmsg = l2tp_ip6_sendmsg, .recvmsg = l2tp_ip6_recvmsg, .backlog_rcv = l2tp_ip6_backlog_recv, - .hash = inet6_hash, - .unhash = inet_unhash, + .hash = l2tp_ip6_hash, + .unhash = l2tp_ip6_unhash, .obj_size = sizeof(struct l2tp_ip6_sock), #ifdef CONFIG_COMPAT .compat_setsockopt = compat_ipv6_setsockopt, diff --git a/net/l2tp/l2tp_netlink.c b/net/l2tp/l2tp_netlink.c index f5a9bdc4980c..ebb381c3f1b9 100644 --- a/net/l2tp/l2tp_netlink.c +++ b/net/l2tp/l2tp_netlink.c @@ -920,51 +920,51 @@ static const struct genl_ops l2tp_nl_ops[] = { .cmd = L2TP_CMD_TUNNEL_CREATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_create, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_delete, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_MODIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_modify, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_TUNNEL_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_tunnel_get, .dumpit = l2tp_nl_cmd_tunnel_dump, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_CREATE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_create, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_DELETE, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_delete, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_MODIFY, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_modify, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, { .cmd = L2TP_CMD_SESSION_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, .doit = l2tp_nl_cmd_session_get, .dumpit = l2tp_nl_cmd_session_dump, - .flags = GENL_ADMIN_PERM, + .flags = GENL_UNS_ADMIN_PERM, }, }; diff --git a/net/llc/af_llc.c b/net/llc/af_llc.c index 2017b7d780f5..e56b3ef0d5bc 100644 --- a/net/llc/af_llc.c +++ b/net/llc/af_llc.c @@ -269,6 +269,10 @@ static int llc_ui_autobind(struct socket *sock, struct sockaddr_llc *addr) if (!sock_flag(sk, SOCK_ZAPPED)) goto out; + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (addr->sllc_arphrd != ARPHRD_ETHER) + goto out; rc = -ENODEV; if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index(&init_net, sk->sk_bound_dev_if); @@ -324,7 +328,9 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (unlikely(!sock_flag(sk, SOCK_ZAPPED) || addrlen != sizeof(*addr))) goto out; rc = -EAFNOSUPPORT; - if (unlikely(addr->sllc_family != AF_LLC)) + if (!addr->sllc_arphrd) + addr->sllc_arphrd = ARPHRD_ETHER; + if (unlikely(addr->sllc_family != AF_LLC || addr->sllc_arphrd != ARPHRD_ETHER)) goto out; dprintk("%s: binding %02X\n", __func__, addr->sllc_sap); rc = -ENODEV; @@ -332,8 +338,6 @@ static int llc_ui_bind(struct socket *sock, struct sockaddr *uaddr, int addrlen) if (sk->sk_bound_dev_if) { llc->dev = dev_get_by_index_rcu(&init_net, sk->sk_bound_dev_if); if (llc->dev) { - if (!addr->sllc_arphrd) - addr->sllc_arphrd = llc->dev->type; if (is_zero_ether_addr(addr->sllc_mac)) memcpy(addr->sllc_mac, llc->dev->dev_addr, IFHWADDRLEN); diff --git a/net/llc/llc_c_ac.c b/net/llc/llc_c_ac.c index 4d78375f9872..647c0554d04c 100644 --- a/net/llc/llc_c_ac.c +++ b/net/llc/llc_c_ac.c @@ -372,6 +372,7 @@ int llc_conn_ac_send_i_cmd_p_set_1(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 1, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -389,7 +390,8 @@ static int llc_conn_ac_send_i_cmd_p_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; @@ -406,6 +408,7 @@ int llc_conn_ac_send_i_xxx_x_set_0(struct sock *sk, struct sk_buff *skb) llc_pdu_init_as_i_cmd(skb, 0, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { + skb_get(skb); llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } @@ -916,7 +919,8 @@ static int llc_conn_ac_send_i_rsp_f_set_ackpf(struct sock *sk, llc_pdu_init_as_i_cmd(skb, llc->ack_pf, llc->vS, llc->vR); rc = llc_mac_hdr_init(skb, llc->dev->dev_addr, llc->daddr.mac); if (likely(!rc)) { - rc = llc_conn_send_pdu(sk, skb); + skb_get(skb); + llc_conn_send_pdu(sk, skb); llc_conn_ac_inc_vs_by_1(sk, skb); } return rc; diff --git a/net/llc/llc_conn.c b/net/llc/llc_conn.c index 4ff89cb7c86f..ed2aca12460c 100644 --- a/net/llc/llc_conn.c +++ b/net/llc/llc_conn.c @@ -30,7 +30,7 @@ #endif static int llc_find_offset(int state, int ev_type); -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *skb); +static void llc_conn_send_pdus(struct sock *sk); static int llc_conn_service(struct sock *sk, struct sk_buff *skb); static int llc_exec_conn_trans_actions(struct sock *sk, struct llc_conn_state_trans *trans, @@ -193,11 +193,11 @@ out_skb_put: return rc; } -int llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) +void llc_conn_send_pdu(struct sock *sk, struct sk_buff *skb) { /* queue PDU to send to MAC layer */ skb_queue_tail(&sk->sk_write_queue, skb); - return llc_conn_send_pdus(sk, skb); + llc_conn_send_pdus(sk); } /** @@ -255,7 +255,7 @@ void llc_conn_resend_i_pdu_as_cmd(struct sock *sk, u8 nr, u8 first_p_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -296,7 +296,7 @@ void llc_conn_resend_i_pdu_as_rsp(struct sock *sk, u8 nr, u8 first_f_bit) if (howmany_resend > 0) llc->vS = (llc->vS + 1) % LLC_2_SEQ_NBR_MODULO; /* any PDUs to re-send are queued up; start sending to MAC */ - llc_conn_send_pdus(sk, NULL); + llc_conn_send_pdus(sk); out:; } @@ -340,16 +340,12 @@ out: /** * llc_conn_send_pdus - Sends queued PDUs * @sk: active connection - * @hold_skb: the skb held by caller, or NULL if does not care * - * Sends queued pdus to MAC layer for transmission. When @hold_skb is - * NULL, always return 0. Otherwise, return 0 if @hold_skb is sent - * successfully, or 1 for failure. + * Sends queued pdus to MAC layer for transmission. */ -static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) +static void llc_conn_send_pdus(struct sock *sk) { struct sk_buff *skb; - int ret = 0; while ((skb = skb_dequeue(&sk->sk_write_queue)) != NULL) { struct llc_pdu_sn *pdu = llc_pdu_sn_hdr(skb); @@ -361,20 +357,10 @@ static int llc_conn_send_pdus(struct sock *sk, struct sk_buff *hold_skb) skb_queue_tail(&llc_sk(sk)->pdu_unack_q, skb); if (!skb2) break; - dev_queue_xmit(skb2); - } else { - bool is_target = skb == hold_skb; - int rc; - - if (is_target) - skb_get(skb); - rc = dev_queue_xmit(skb); - if (is_target) - ret = rc; + skb = skb2; } + dev_queue_xmit(skb); } - - return ret; } /** diff --git a/net/llc/llc_s_ac.c b/net/llc/llc_s_ac.c index a94bd56bcac6..7ae4cc684d3a 100644 --- a/net/llc/llc_s_ac.c +++ b/net/llc/llc_s_ac.c @@ -58,8 +58,10 @@ int llc_sap_action_send_ui(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_ui_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -81,8 +83,10 @@ int llc_sap_action_send_xid_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_xid_cmd(skb, LLC_XID_NULL_CLASS_2, 0); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } @@ -135,8 +139,10 @@ int llc_sap_action_send_test_c(struct llc_sap *sap, struct sk_buff *skb) ev->daddr.lsap, LLC_PDU_CMD); llc_pdu_init_as_test_cmd(skb); rc = llc_mac_hdr_init(skb, ev->saddr.mac, ev->daddr.mac); - if (likely(!rc)) + if (likely(!rc)) { + skb_get(skb); rc = dev_queue_xmit(skb); + } return rc; } diff --git a/net/llc/llc_sap.c b/net/llc/llc_sap.c index a7f7b8ff4729..be419062e19a 100644 --- a/net/llc/llc_sap.c +++ b/net/llc/llc_sap.c @@ -197,29 +197,22 @@ out: * After executing actions of the event, upper layer will be indicated * if needed(on receiving an UI frame). sk can be null for the * datalink_proto case. + * + * This function always consumes a reference to the skb. */ static void llc_sap_state_process(struct llc_sap *sap, struct sk_buff *skb) { struct llc_sap_state_ev *ev = llc_sap_ev(skb); - /* - * We have to hold the skb, because llc_sap_next_state - * will kfree it in the sending path and we need to - * look at the skb->cb, where we encode llc_sap_state_ev. - */ - skb_get(skb); ev->ind_cfm_flag = 0; llc_sap_next_state(sap, skb); - if (ev->ind_cfm_flag == LLC_IND) { - if (skb->sk->sk_state == TCP_LISTEN) - kfree_skb(skb); - else { - llc_save_primitive(skb->sk, skb, ev->prim); - /* queue skb to the user. */ - if (sock_queue_rcv_skb(skb->sk, skb)) - kfree_skb(skb); - } + if (ev->ind_cfm_flag == LLC_IND && skb->sk->sk_state != TCP_LISTEN) { + llc_save_primitive(skb->sk, skb, ev->prim); + + /* queue skb to the user. */ + if (sock_queue_rcv_skb(skb->sk, skb) == 0) + return; } kfree_skb(skb); } diff --git a/net/llc/llc_station.c b/net/llc/llc_station.c index 204a8351efff..c29170e767a8 100644 --- a/net/llc/llc_station.c +++ b/net/llc/llc_station.c @@ -32,7 +32,7 @@ static int llc_stat_ev_rx_null_dsap_xid_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_XID && - !pdu->dsap ? 0 : 1; /* NULL DSAP value */ + !pdu->dsap; /* NULL DSAP value */ } static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) @@ -42,7 +42,7 @@ static int llc_stat_ev_rx_null_dsap_test_c(struct sk_buff *skb) return LLC_PDU_IS_CMD(pdu) && /* command PDU */ LLC_PDU_TYPE_IS_U(pdu) && /* U type PDU */ LLC_U_PDU_CMD(pdu) == LLC_1_PDU_CMD_TEST && - !pdu->dsap ? 0 : 1; /* NULL DSAP */ + !pdu->dsap; /* NULL DSAP */ } static int llc_station_ac_send_xid_r(struct sk_buff *skb) diff --git a/net/mac80211/Kconfig b/net/mac80211/Kconfig index 0227cce9685e..0c93b1b7a826 100644 --- a/net/mac80211/Kconfig +++ b/net/mac80211/Kconfig @@ -3,7 +3,7 @@ config MAC80211 tristate "Generic IEEE 802.11 Networking Stack (mac80211)" depends on CFG80211 select CRYPTO - select CRYPTO_ARC4 + select CRYPTO_LIB_ARC4 select CRYPTO_AES select CRYPTO_CCM select CRYPTO_GCM diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 1c55d3b7bc15..573b7de8a870 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -14,6 +14,7 @@ #include <linux/slab.h> #include <net/net_namespace.h> #include <linux/rcupdate.h> +#include <linux/fips.h> #include <linux/if_ether.h> #include <net/cfg80211.h> #include "ieee80211_i.h" @@ -402,9 +403,8 @@ static int ieee80211_add_key(struct wiphy *wiphy, struct net_device *dev, case WLAN_CIPHER_SUITE_WEP40: case WLAN_CIPHER_SUITE_TKIP: case WLAN_CIPHER_SUITE_WEP104: - if (IS_ERR(local->wep_tx_tfm)) + if (WARN_ON_ONCE(fips_enabled)) return -EINVAL; - break; case WLAN_CIPHER_SUITE_CCMP: case WLAN_CIPHER_SUITE_CCMP_256: case WLAN_CIPHER_SUITE_AES_CMAC: @@ -1526,7 +1526,6 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, struct sta_info *sta; struct ieee80211_sub_if_data *sdata; int err; - int layer2_update; if (params->vlan) { sdata = IEEE80211_DEV_TO_SUB_IF(params->vlan); @@ -1570,18 +1569,12 @@ static int ieee80211_add_station(struct wiphy *wiphy, struct net_device *dev, test_sta_flag(sta, WLAN_STA_ASSOC)) rate_control_rate_init(sta); - layer2_update = sdata->vif.type == NL80211_IFTYPE_AP_VLAN || - sdata->vif.type == NL80211_IFTYPE_AP; - err = sta_info_insert_rcu(sta); if (err) { rcu_read_unlock(); return err; } - if (layer2_update) - cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); - rcu_read_unlock(); return 0; @@ -1679,10 +1672,11 @@ static int ieee80211_change_station(struct wiphy *wiphy, sta->sdata = vlansdata; ieee80211_check_fast_xmit(sta); - if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) + if (test_sta_flag(sta, WLAN_STA_AUTHORIZED)) { ieee80211_vif_inc_num_mcast(sta->sdata); - - cfg80211_send_layer2_update(sta->sdata->dev, sta->sta.addr); + cfg80211_send_layer2_update(sta->sdata->dev, + sta->sta.addr); + } } err = sta_apply_parameters(local, sta, params); @@ -2140,6 +2134,7 @@ static int ieee80211_leave_mesh(struct wiphy *wiphy, struct net_device *dev) ieee80211_stop_mesh(sdata); mutex_lock(&sdata->local->mtx); ieee80211_vif_release_channel(sdata); + kfree(sdata->u.mesh.ie); mutex_unlock(&sdata->local->mtx); return 0; @@ -2954,6 +2949,28 @@ static int ieee80211_start_radar_detection(struct wiphy *wiphy, return err; } +static void ieee80211_end_cac(struct wiphy *wiphy, + struct net_device *dev) +{ + struct ieee80211_sub_if_data *sdata = IEEE80211_DEV_TO_SUB_IF(dev); + struct ieee80211_local *local = sdata->local; + + mutex_lock(&local->mtx); + list_for_each_entry(sdata, &local->interfaces, list) { + /* it might be waiting for the local->mtx, but then + * by the time it gets it, sdata->wdev.cac_started + * will no longer be true + */ + cancel_delayed_work(&sdata->dfs_cac_timer_work); + + if (sdata->wdev.cac_started) { + ieee80211_vif_release_channel(sdata); + sdata->wdev.cac_started = false; + } + } + mutex_unlock(&local->mtx); +} + static struct cfg80211_beacon_data * cfg80211_beacon_dup(struct cfg80211_beacon_data *beacon) { @@ -4023,6 +4040,7 @@ const struct cfg80211_ops mac80211_config_ops = { #endif .get_channel = ieee80211_cfg_get_channel, .start_radar_detection = ieee80211_start_radar_detection, + .end_cac = ieee80211_end_cac, .channel_switch = ieee80211_channel_switch, .set_qos_map = ieee80211_set_qos_map, .set_ap_chanwidth = ieee80211_set_ap_chanwidth, diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 6396d46a9a71..004e2e3adb88 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -1255,8 +1255,8 @@ struct ieee80211_local { struct rate_control_ref *rate_ctrl; - struct crypto_cipher *wep_tx_tfm; - struct crypto_cipher *wep_rx_tfm; + struct arc4_ctx wep_tx_ctx; + struct arc4_ctx wep_rx_ctx; u32 wep_iv; /* see iface.c */ diff --git a/net/mac80211/key.c b/net/mac80211/key.c index 157ff5f890d2..baa91b4aacd3 100644 --- a/net/mac80211/key.c +++ b/net/mac80211/key.c @@ -781,7 +781,7 @@ int ieee80211_key_link(struct ieee80211_key *key, /* Non-pairwise keys must also not switch the cipher on rekey */ if (!pairwise) { - if (key && old_key && old_key->conf.cipher != key->conf.cipher) + if (old_key && old_key->conf.cipher != key->conf.cipher) goto out; } diff --git a/net/mac80211/key.h b/net/mac80211/key.h index be118c39433f..b8b9cd743bf4 100644 --- a/net/mac80211/key.h +++ b/net/mac80211/key.h @@ -11,6 +11,7 @@ #include <linux/list.h> #include <linux/crypto.h> #include <linux/rcupdate.h> +#include <crypto/arc4.h> #include <net/mac80211.h> #define NUM_DEFAULT_KEYS 4 diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 55583b71ffaf..27045a9b4785 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -10,6 +10,7 @@ #include <net/mac80211.h> #include <linux/module.h> +#include <linux/fips.h> #include <linux/init.h> #include <linux/netdevice.h> #include <linux/types.h> @@ -730,8 +731,7 @@ EXPORT_SYMBOL(ieee80211_alloc_hw_nm); static int ieee80211_init_cipher_suites(struct ieee80211_local *local) { - bool have_wep = !(IS_ERR(local->wep_tx_tfm) || - IS_ERR(local->wep_rx_tfm)); + bool have_wep = !fips_enabled; /* FIPS does not permit the use of RC4 */ bool have_mfp = ieee80211_hw_check(&local->hw, MFP_CAPABLE); int n_suites = 0, r = 0, w = 0; u32 *suites; @@ -1044,7 +1044,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->signal_type = CFG80211_SIGNAL_TYPE_UNSPEC; if (hw->max_signal <= 0) { result = -EINVAL; - goto fail_wiphy_register; + goto fail_workqueue; } } @@ -1112,7 +1112,7 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) result = ieee80211_init_cipher_suites(local); if (result < 0) - goto fail_wiphy_register; + goto fail_workqueue; if (!local->ops->remain_on_channel) local->hw.wiphy->max_remain_on_channel_duration = 5000; @@ -1138,10 +1138,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->hw.wiphy->max_num_csa_counters = IEEE80211_MAX_CSA_COUNTERS_NUM; - result = wiphy_register(local->hw.wiphy); - if (result < 0) - goto fail_wiphy_register; - /* * We use the number of queues for feature tests (QoS, HT) internally * so restrict them appropriately. @@ -1164,8 +1160,6 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->tx_headroom = max_t(unsigned int , local->hw.extra_tx_headroom, IEEE80211_TX_STATUS_HEADROOM); - debugfs_hw_add(local); - /* * if the driver doesn't specify a max listen interval we * use 5 which should be a safe default @@ -1197,9 +1191,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) goto fail_flows; rtnl_lock(); - result = ieee80211_init_rate_ctrl_alg(local, hw->rate_control_algorithm); + rtnl_unlock(); if (result < 0) { wiphy_debug(local->hw.wiphy, "Failed to initialize rate control algorithm\n"); @@ -1253,6 +1247,15 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) local->sband_allocated |= BIT(band); } + result = wiphy_register(local->hw.wiphy); + if (result < 0) + goto fail_wiphy_register; + + debugfs_hw_add(local); + rate_control_add_debugfs(local); + + rtnl_lock(); + /* add one default STA interface if supported */ if (local->hw.wiphy->interface_modes & BIT(NL80211_IFTYPE_STATION) && !ieee80211_hw_check(hw, NO_AUTO_VIF)) { @@ -1292,18 +1295,17 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) #if defined(CONFIG_INET) || defined(CONFIG_IPV6) fail_ifa: #endif + wiphy_unregister(local->hw.wiphy); + fail_wiphy_register: rtnl_lock(); rate_control_deinitialize(local); ieee80211_remove_interfaces(local); - fail_rate: rtnl_unlock(); - ieee80211_led_exit(local); - ieee80211_wep_free(local); + fail_rate: fail_flows: + ieee80211_led_exit(local); destroy_workqueue(local->workqueue); fail_workqueue: - wiphy_unregister(local->hw.wiphy); - fail_wiphy_register: if (local->wiphy_ciphers_allocated) kfree(local->hw.wiphy->cipher_suites); kfree(local->int_scan_req); @@ -1353,9 +1355,8 @@ void ieee80211_unregister_hw(struct ieee80211_hw *hw) skb_queue_purge(&local->skb_queue_unreliable); skb_queue_purge(&local->skb_queue_tdls_chsw); - destroy_workqueue(local->workqueue); wiphy_unregister(local->hw.wiphy); - ieee80211_wep_free(local); + destroy_workqueue(local->workqueue); ieee80211_led_exit(local); kfree(local->int_scan_req); } diff --git a/net/mac80211/mesh.c b/net/mac80211/mesh.c index 2e7fa743c892..13ec12d64428 100644 --- a/net/mac80211/mesh.c +++ b/net/mac80211/mesh.c @@ -1195,15 +1195,15 @@ static void ieee80211_mesh_rx_bcn_presp(struct ieee80211_sub_if_data *sdata, sdata->u.mesh.mshcfg.rssi_threshold < rx_status->signal) mesh_neighbour_update(sdata, mgmt->sa, &elems, rx_status); + + if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && + !sdata->vif.csa_active) + ieee80211_mesh_process_chnswitch(sdata, &elems, true); } if (ifmsh->sync_ops) ifmsh->sync_ops->rx_bcn_presp(sdata, stype, mgmt, &elems, rx_status); - - if (ifmsh->csa_role != IEEE80211_MESH_CSA_ROLE_INIT && - !sdata->vif.csa_active) - ieee80211_mesh_process_chnswitch(sdata, &elems, true); } int ieee80211_mesh_finish_csa(struct ieee80211_sub_if_data *sdata) @@ -1311,6 +1311,9 @@ static void mesh_rx_csa_frame(struct ieee80211_sub_if_data *sdata, ieee802_11_parse_elems(pos, len - baselen, true, &elems, mgmt->bssid, NULL); + if (!mesh_matches_local(sdata, &elems)) + return; + ifmsh->chsw_ttl = elems.mesh_chansw_params_ie->mesh_ttl; if (!--ifmsh->chsw_ttl) fwd_csa = false; diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 68af62306385..aa5150929996 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -328,6 +328,9 @@ u32 airtime_link_metric_get(struct ieee80211_local *local, unsigned long fail_avg = ewma_mesh_fail_avg_read(&sta->mesh->fail_avg); + if (sta->mesh->plink_state != NL80211_PLINK_ESTAB) + return MAX_METRIC; + /* Try to get rate based on HW/SW RC algorithm. * Rate is returned in units of Kbps, correct this * to comply with airtime calculation units @@ -1100,7 +1103,14 @@ void mesh_path_start_discovery(struct ieee80211_sub_if_data *sdata) mesh_path_sel_frame_tx(MPATH_PREQ, 0, sdata->vif.addr, ifmsh->sn, target_flags, mpath->dst, mpath->sn, da, 0, ttl, lifetime, 0, ifmsh->preq_id++, sdata); + + spin_lock_bh(&mpath->state_lock); + if (mpath->flags & MESH_PATH_DELETED) { + spin_unlock_bh(&mpath->state_lock); + goto enddiscovery; + } mod_timer(&mpath->timer, jiffies + mpath->discovery_timeout); + spin_unlock_bh(&mpath->state_lock); enddiscovery: rcu_read_unlock(); @@ -1149,7 +1159,8 @@ int mesh_nexthop_resolve(struct ieee80211_sub_if_data *sdata, } } - if (!(mpath->flags & MESH_PATH_RESOLVING)) + if (!(mpath->flags & MESH_PATH_RESOLVING) && + mesh_path_sel_is_hwmp(sdata)) mesh_queue_preq(mpath, PREQ_Q_F_START); if (skb_queue_len(&mpath->frame_queue) >= MESH_FRAME_QUEUE_LEN) diff --git a/net/mac80211/mesh_pathtbl.c b/net/mac80211/mesh_pathtbl.c index 117519bf33d6..aca608ae313f 100644 --- a/net/mac80211/mesh_pathtbl.c +++ b/net/mac80211/mesh_pathtbl.c @@ -521,6 +521,7 @@ static void mesh_path_free_rcu(struct mesh_table *tbl, del_timer_sync(&mpath->timer); atomic_dec(&sdata->u.mesh.mpaths); atomic_dec(&tbl->entries); + mesh_path_flush_pending(mpath); kfree_rcu(mpath, rcu); } diff --git a/net/mac80211/mlme.c b/net/mac80211/mlme.c index e75f1b4b3ce3..6377a5145106 100644 --- a/net/mac80211/mlme.c +++ b/net/mac80211/mlme.c @@ -8,10 +8,11 @@ * Copyright 2007, Michael Wu <flamingice@sourmilk.net> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 - 2019 Intel Corporation + * Copyright (C) 2018 - 2020 Intel Corporation */ #include <linux/delay.h> +#include <linux/fips.h> #include <linux/if_ether.h> #include <linux/skbuff.h> #include <linux/if_arp.h> @@ -1310,7 +1311,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, if (!res) { ch_switch.timestamp = timestamp; ch_switch.device_timestamp = device_timestamp; - ch_switch.block_tx = beacon ? csa_ie.mode : 0; + ch_switch.block_tx = csa_ie.mode; ch_switch.chandef = csa_ie.chandef; ch_switch.count = csa_ie.count; ch_switch.delay = csa_ie.max_switch_time; @@ -1403,7 +1404,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, sdata->vif.csa_active = true; sdata->csa_chandef = csa_ie.chandef; - sdata->csa_block_tx = ch_switch.block_tx; + sdata->csa_block_tx = csa_ie.mode; ifmgd->csa_ignored_same_chan = false; if (sdata->csa_block_tx) @@ -1437,7 +1438,7 @@ ieee80211_sta_process_chanswitch(struct ieee80211_sub_if_data *sdata, * reset when the disconnection worker runs. */ sdata->vif.csa_active = true; - sdata->csa_block_tx = ch_switch.block_tx; + sdata->csa_block_tx = csa_ie.mode; ieee80211_queue_work(&local->hw, &ifmgd->csa_connection_drop_work); mutex_unlock(&local->chanctx_mtx); @@ -2458,7 +2459,7 @@ void ieee80211_sta_tx_notify(struct ieee80211_sub_if_data *sdata, if (!ieee80211_is_data(hdr->frame_control)) return; - if (ieee80211_is_nullfunc(hdr->frame_control) && + if (ieee80211_is_any_nullfunc(hdr->frame_control) && sdata->u.mgd.probe_send_count > 0) { if (ack) ieee80211_sta_reset_conn_monitor(sdata); @@ -2954,7 +2955,7 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, (auth_transaction == 2 && ifmgd->auth_data->expected_transaction == 2)) { if (!ieee80211_mark_sta_auth(sdata, bssid)) - goto out_err; + return; /* ignore frame -- wait for timeout */ } else if (ifmgd->auth_data->algorithm == WLAN_AUTH_SAE && auth_transaction == 2) { sdata_info(sdata, "SAE peer confirmed\n"); @@ -2962,10 +2963,6 @@ static void ieee80211_rx_mgmt_auth(struct ieee80211_sub_if_data *sdata, } cfg80211_rx_mlme_mgmt(sdata->dev, (u8 *)mgmt, len); - return; - out_err: - mutex_unlock(&sdata->local->sta_mtx); - /* ignore frame -- wait for timeout */ } #define case_WLAN(type) \ @@ -5056,7 +5053,7 @@ int ieee80211_mgd_auth(struct ieee80211_sub_if_data *sdata, auth_alg = WLAN_AUTH_OPEN; break; case NL80211_AUTHTYPE_SHARED_KEY: - if (IS_ERR(local->wep_tx_tfm)) + if (fips_enabled) return -EOPNOTSUPP; auth_alg = WLAN_AUTH_SHARED_KEY; break; diff --git a/net/mac80211/rate.c b/net/mac80211/rate.c index 47ee36677c2b..39954e77aaca 100644 --- a/net/mac80211/rate.c +++ b/net/mac80211/rate.c @@ -214,17 +214,16 @@ static ssize_t rcname_read(struct file *file, char __user *userbuf, ref->ops->name, len); } -static const struct file_operations rcname_ops = { +const struct file_operations rcname_ops = { .read = rcname_read, .open = simple_open, .llseek = default_llseek, }; #endif -static struct rate_control_ref *rate_control_alloc(const char *name, - struct ieee80211_local *local) +static struct rate_control_ref * +rate_control_alloc(const char *name, struct ieee80211_local *local) { - struct dentry *debugfsdir = NULL; struct rate_control_ref *ref; ref = kmalloc(sizeof(struct rate_control_ref), GFP_KERNEL); @@ -234,13 +233,7 @@ static struct rate_control_ref *rate_control_alloc(const char *name, if (!ref->ops) goto free; -#ifdef CONFIG_MAC80211_DEBUGFS - debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); - local->debugfs.rcdir = debugfsdir; - debugfs_create_file("name", 0400, debugfsdir, ref, &rcname_ops); -#endif - - ref->priv = ref->ops->alloc(&local->hw, debugfsdir); + ref->priv = ref->ops->alloc(&local->hw); if (!ref->priv) goto free; return ref; diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h index 5d5348bc41ec..db96d2da5c55 100644 --- a/net/mac80211/rate.h +++ b/net/mac80211/rate.h @@ -69,6 +69,29 @@ static inline void rate_control_remove_sta_debugfs(struct sta_info *sta) #endif } +extern const struct file_operations rcname_ops; + +static inline void rate_control_add_debugfs(struct ieee80211_local *local) +{ +#ifdef CONFIG_MAC80211_DEBUGFS + struct dentry *debugfsdir; + + if (!local->rate_ctrl) + return; + + if (!local->rate_ctrl->ops->add_debugfs) + return; + + debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir); + local->debugfs.rcdir = debugfsdir; + debugfs_create_file("name", 0400, debugfsdir, + local->rate_ctrl, &rcname_ops); + + local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv, + debugfsdir); +#endif +} + void ieee80211_check_rate_mask(struct ieee80211_sub_if_data *sdata); /* Get a reference to the rate control algorithm. If `name' is NULL, get the diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index 298a1acb3ce5..1c5e843dede2 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -1431,7 +1431,7 @@ minstrel_ht_init_cck_rates(struct minstrel_priv *mp) } static void * -minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) +minstrel_ht_alloc(struct ieee80211_hw *hw) { struct minstrel_priv *mp; @@ -1466,16 +1466,22 @@ minstrel_ht_alloc(struct ieee80211_hw *hw, struct dentry *debugfsdir) mp->hw = hw; mp->update_interval = 100; + minstrel_ht_init_cck_rates(mp); + + return mp; +} + #ifdef CONFIG_MAC80211_DEBUGFS +static void minstrel_ht_add_debugfs(struct ieee80211_hw *hw, void *priv, + struct dentry *debugfsdir) +{ + struct minstrel_priv *mp = priv; + mp->fixed_rate_idx = (u32) -1; debugfs_create_u32("fixed_rate_idx", S_IRUGO | S_IWUGO, debugfsdir, &mp->fixed_rate_idx); -#endif - - minstrel_ht_init_cck_rates(mp); - - return mp; } +#endif static void minstrel_ht_free(void *priv) @@ -1514,6 +1520,7 @@ static const struct rate_control_ops mac80211_minstrel_ht = { .alloc = minstrel_ht_alloc, .free = minstrel_ht_free, #ifdef CONFIG_MAC80211_DEBUGFS + .add_debugfs = minstrel_ht_add_debugfs, .add_sta_debugfs = minstrel_ht_add_sta_debugfs, #endif .get_expected_throughput = minstrel_ht_get_expected_throughput, diff --git a/net/mac80211/rx.c b/net/mac80211/rx.c index 768d14c9a716..5062532a4028 100644 --- a/net/mac80211/rx.c +++ b/net/mac80211/rx.c @@ -1450,8 +1450,7 @@ ieee80211_rx_h_check_dup(struct ieee80211_rx_data *rx) return RX_CONTINUE; if (ieee80211_is_ctl(hdr->frame_control) || - ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control) || + ieee80211_is_any_nullfunc(hdr->frame_control) || is_multicast_ether_addr(hdr->addr1)) return RX_CONTINUE; @@ -1838,8 +1837,7 @@ ieee80211_rx_h_sta_process(struct ieee80211_rx_data *rx) * Drop (qos-)data::nullfunc frames silently, since they * are used only to control station power saving mode. */ - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) { + if (ieee80211_is_any_nullfunc(hdr->frame_control)) { I802_DEBUG_INC(rx->local->rx_handlers_drop_nullfunc); /* @@ -2307,6 +2305,7 @@ static int ieee80211_802_1x_port_control(struct ieee80211_rx_data *rx) static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) { + struct ieee80211_hdr *hdr = (void *)rx->skb->data; struct sk_buff *skb = rx->skb; struct ieee80211_rx_status *status = IEEE80211_SKB_RXCB(skb); @@ -2317,9 +2316,34 @@ static int ieee80211_drop_unencrypted(struct ieee80211_rx_data *rx, __le16 fc) if (status->flag & RX_FLAG_DECRYPTED) return 0; + /* check mesh EAPOL frames first */ + if (unlikely(rx->sta && ieee80211_vif_is_mesh(&rx->sdata->vif) && + ieee80211_is_data(fc))) { + struct ieee80211s_hdr *mesh_hdr; + u16 hdr_len = ieee80211_hdrlen(fc); + u16 ethertype_offset; + __be16 ethertype; + + if (!ether_addr_equal(hdr->addr1, rx->sdata->vif.addr)) + goto drop_check; + + /* make sure fixed part of mesh header is there, also checks skb len */ + if (!pskb_may_pull(rx->skb, hdr_len + 6)) + goto drop_check; + + mesh_hdr = (struct ieee80211s_hdr *)(skb->data + hdr_len); + ethertype_offset = hdr_len + ieee80211_get_mesh_hdrlen(mesh_hdr) + + sizeof(rfc1042_header); + + if (skb_copy_bits(rx->skb, ethertype_offset, ðertype, 2) == 0 && + ethertype == rx->sdata->control_port_protocol) + return 0; + } + +drop_check: /* Drop unencrypted frames if key is set. */ if (unlikely(!ieee80211_has_protected(fc) && - !ieee80211_is_nullfunc(fc) && + !ieee80211_is_any_nullfunc(fc) && ieee80211_is_data(fc) && rx->key)) return -EACCES; @@ -4105,7 +4129,7 @@ void __ieee80211_check_fast_rx_iface(struct ieee80211_sub_if_data *sdata) lockdep_assert_held(&local->sta_mtx); - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry(sta, &local->sta_list, list) { if (sdata != sta->sdata && (!sta->sdata->bss || sta->sdata->bss != sdata->bss)) continue; diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index 187f62a48b2b..2e217664f146 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -4,7 +4,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2013-2014 Intel Mobile Communications GmbH * Copyright (C) 2015 - 2017 Intel Deutschland GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018-2020 Intel Corporation */ #include <linux/module.h> @@ -217,7 +217,8 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata, struct sta_info *sta; int i = 0; - list_for_each_entry_rcu(sta, &local->sta_list, list) { + list_for_each_entry_rcu(sta, &local->sta_list, list, + lockdep_is_held(&local->sta_mtx)) { if (sdata != sta->sdata) continue; if (i < idx) { @@ -991,6 +992,11 @@ static void __sta_info_destroy_part2(struct sta_info *sta) might_sleep(); lockdep_assert_held(&local->sta_mtx); + if (sta->sta_state == IEEE80211_STA_AUTHORIZED) { + ret = sta_info_move_state(sta, IEEE80211_STA_ASSOC); + WARN_ON_ONCE(ret); + } + /* now keys can no longer be reached */ ieee80211_free_sta_keys(local, sta); @@ -1938,6 +1944,10 @@ int sta_info_move_state(struct sta_info *sta, ieee80211_check_fast_xmit(sta); ieee80211_check_fast_rx(sta); } + if (sta->sdata->vif.type == NL80211_IFTYPE_AP_VLAN || + sta->sdata->vif.type == NL80211_IFTYPE_AP) + cfg80211_send_layer2_update(sta->sdata->dev, + sta->sta.addr); break; default: break; @@ -2410,7 +2420,8 @@ unsigned long ieee80211_sta_last_active(struct sta_info *sta) { struct ieee80211_sta_rx_stats *stats = sta_get_last_rx_stats(sta); - if (time_after(stats->last_rx, sta->status_stats.last_ack)) + if (!sta->status_stats.last_ack || + time_after(stats->last_rx, sta->status_stats.last_ack)) return stats->last_rx; return sta->status_stats.last_ack; } diff --git a/net/mac80211/status.c b/net/mac80211/status.c index a88e3bf17e9d..e541cee51208 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -484,8 +484,7 @@ static void ieee80211_report_ack_skb(struct ieee80211_local *local, rcu_read_lock(); sdata = ieee80211_sdata_from_skb(local, skb); if (sdata) { - if (ieee80211_is_nullfunc(hdr->frame_control) || - ieee80211_is_qos_nullfunc(hdr->frame_control)) + if (ieee80211_is_any_nullfunc(hdr->frame_control)) cfg80211_probe_status(sdata->dev, hdr->addr1, cookie, acked, info->status.ack_signal, @@ -870,7 +869,8 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, I802_DEBUG_INC(local->dot11FailedCount); } - if (ieee80211_is_nullfunc(fc) && ieee80211_has_pm(fc) && + if (ieee80211_is_any_nullfunc(fc) && + ieee80211_has_pm(fc) && ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS) && !(info->flags & IEEE80211_TX_CTL_INJECTED) && local->ps_sdata && !(local->scanning)) { diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 7914b8e3ce8c..e7f57bb18f6e 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -219,7 +219,7 @@ EXPORT_SYMBOL(ieee80211_get_tkip_p2k); * @payload_len is the length of payload (_not_ including IV/ICV length). * @ta is the transmitter addresses. */ -int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, +int ieee80211_tkip_encrypt_data(struct arc4_ctx *ctx, struct ieee80211_key *key, struct sk_buff *skb, u8 *payload, size_t payload_len) @@ -228,7 +228,7 @@ int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, ieee80211_get_tkip_p2k(&key->conf, skb, rc4key); - return ieee80211_wep_encrypt_data(tfm, rc4key, 16, + return ieee80211_wep_encrypt_data(ctx, rc4key, 16, payload, payload_len); } @@ -236,7 +236,7 @@ int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, * beginning of the buffer containing IEEE 802.11 header payload, i.e., * including IV, Ext. IV, real data, Michael MIC, ICV. @payload_len is the * length of payload, including IV, Ext. IV, MIC, ICV. */ -int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, +int ieee80211_tkip_decrypt_data(struct arc4_ctx *ctx, struct ieee80211_key *key, u8 *payload, size_t payload_len, u8 *ta, u8 *ra, int only_iv, int queue, @@ -263,9 +263,21 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, if ((keyid >> 6) != key->conf.keyidx) return TKIP_DECRYPT_INVALID_KEYIDX; - if (rx_ctx->ctx.state != TKIP_STATE_NOT_INIT && - (iv32 < rx_ctx->iv32 || - (iv32 == rx_ctx->iv32 && iv16 <= rx_ctx->iv16))) + /* Reject replays if the received TSC is smaller than or equal to the + * last received value in a valid message, but with an exception for + * the case where a new key has been set and no valid frame using that + * key has yet received and the local RSC was initialized to 0. This + * exception allows the very first frame sent by the transmitter to be + * accepted even if that transmitter were to use TSC 0 (IEEE 802.11 + * described TSC to be initialized to 1 whenever a new key is taken into + * use). + */ + if (iv32 < rx_ctx->iv32 || + (iv32 == rx_ctx->iv32 && + (iv16 < rx_ctx->iv16 || + (iv16 == rx_ctx->iv16 && + (rx_ctx->iv32 || rx_ctx->iv16 || + rx_ctx->ctx.state != TKIP_STATE_NOT_INIT))))) return TKIP_DECRYPT_REPLAY; if (only_iv) { @@ -294,7 +306,7 @@ int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, tkip_mixing_phase2(tk, &rx_ctx->ctx, iv16, rc4key); - res = ieee80211_wep_decrypt_data(tfm, rc4key, 16, pos, payload_len - 12); + res = ieee80211_wep_decrypt_data(ctx, rc4key, 16, pos, payload_len - 12); done: if (res == TKIP_DECRYPT_OK) { /* diff --git a/net/mac80211/tkip.h b/net/mac80211/tkip.h index 676a7babdf5d..9d2f8bd36cc7 100644 --- a/net/mac80211/tkip.h +++ b/net/mac80211/tkip.h @@ -10,7 +10,7 @@ #include <linux/crypto.h> #include "key.h" -int ieee80211_tkip_encrypt_data(struct crypto_cipher *tfm, +int ieee80211_tkip_encrypt_data(struct arc4_ctx *ctx, struct ieee80211_key *key, struct sk_buff *skb, u8 *payload, size_t payload_len); @@ -21,7 +21,7 @@ enum { TKIP_DECRYPT_INVALID_KEYIDX = -2, TKIP_DECRYPT_REPLAY = -3, }; -int ieee80211_tkip_decrypt_data(struct crypto_cipher *tfm, +int ieee80211_tkip_decrypt_data(struct arc4_ctx *ctx, struct ieee80211_key *key, u8 *payload, size_t payload_len, u8 *ta, u8 *ra, int only_iv, int queue, diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index f13eb2f61ccf..86c0159c0a6f 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -5,7 +5,7 @@ * Copyright 2006-2007 Jiri Benc <jbenc@suse.cz> * Copyright 2007 Johannes Berg <johannes@sipsolutions.net> * Copyright 2013-2014 Intel Mobile Communications GmbH - * Copyright (C) 2018 Intel Corporation + * Copyright (C) 2018, 2020 Intel Corporation * * Transmit and frame generation functions. */ @@ -296,7 +296,7 @@ ieee80211_tx_h_check_assoc(struct ieee80211_tx_data *tx) if (unlikely(test_bit(SCAN_SW_SCANNING, &tx->local->scanning)) && test_bit(SDATA_STATE_OFFCHANNEL, &tx->sdata->state) && !ieee80211_is_probe_req(hdr->frame_control) && - !ieee80211_is_nullfunc(hdr->frame_control)) + !ieee80211_is_any_nullfunc(hdr->frame_control)) /* * When software scanning only nullfunc frames (to notify * the sleep state to the AP) and probe requests (for the @@ -2262,6 +2262,15 @@ netdev_tx_t ieee80211_monitor_start_xmit(struct sk_buff *skb, payload[7]); } + /* + * Initialize skb->priority for QoS frames. This is put in the TID field + * of the frame before passing it to the driver. + */ + if (ieee80211_is_data_qos(hdr->frame_control)) { + u8 *p = ieee80211_get_qos_ctl(hdr); + skb->priority = *p & IEEE80211_QOS_CTL_TAG1D_MASK; + } + memset(info, 0, sizeof(*info)); info->flags = IEEE80211_TX_CTL_REQ_TX_STATUS | @@ -3578,8 +3587,26 @@ begin: tx.skb = skb; tx.sdata = vif_to_sdata(info->control.vif); - if (txq->sta) + if (txq->sta) { tx.sta = container_of(txq->sta, struct sta_info, sta); + /* + * Drop unicast frames to unauthorised stations unless they are + * EAPOL frames from the local station. + */ + if (unlikely(ieee80211_is_data(hdr->frame_control) && + !ieee80211_vif_is_mesh(&tx.sdata->vif) && + tx.sdata->vif.type != NL80211_IFTYPE_OCB && + !is_multicast_ether_addr(hdr->addr1) && + !test_sta_flag(tx.sta, WLAN_STA_AUTHORIZED) && + (!(info->control.flags & + IEEE80211_TX_CTRL_PORT_CTRL_PROTO) || + !ether_addr_equal(tx.sdata->vif.addr, + hdr->addr2)))) { + I802_DEBUG_INC(local->tx_handlers_drop_unauth_port); + ieee80211_free_txskb(&local->hw, skb); + goto begin; + } + } /* * The key can be removed while the packet was queued, so need to call @@ -5048,6 +5075,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, struct ieee80211_local *local = sdata->local; struct sk_buff *skb; struct ethhdr *ehdr; + u32 ctrl_flags = 0; u32 flags; /* Only accept CONTROL_PORT_PROTOCOL configured in CONNECT/ASSOCIATE @@ -5057,6 +5085,9 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, proto != cpu_to_be16(ETH_P_PREAUTH)) return -EINVAL; + if (proto == sdata->control_port_protocol) + ctrl_flags |= IEEE80211_TX_CTRL_PORT_CTRL_PROTO; + if (unencrypted) flags = IEEE80211_TX_INTFL_DONT_ENCRYPT; else @@ -5082,7 +5113,7 @@ int ieee80211_tx_control_port(struct wiphy *wiphy, struct net_device *dev, skb_reset_mac_header(skb); local_bh_disable(); - __ieee80211_subif_start_xmit(skb, skb->dev, flags, 0); + __ieee80211_subif_start_xmit(skb, skb->dev, flags, ctrl_flags); local_bh_enable(); return 0; diff --git a/net/mac80211/util.c b/net/mac80211/util.c index 21212faec6d0..cf1952193712 100644 --- a/net/mac80211/util.c +++ b/net/mac80211/util.c @@ -1063,16 +1063,22 @@ _ieee802_11_parse_elems_crc(const u8 *start, size_t len, bool action, elem_parse_failed = true; break; case WLAN_EID_VHT_OPERATION: - if (elen >= sizeof(struct ieee80211_vht_operation)) + if (elen >= sizeof(struct ieee80211_vht_operation)) { elems->vht_operation = (void *)pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_OPMODE_NOTIF: - if (elen > 0) + if (elen > 0) { elems->opmode_notif = pos; - else - elem_parse_failed = true; + if (calc_crc) + crc = crc32_be(crc, pos - 2, elen + 2); + break; + } + elem_parse_failed = true; break; case WLAN_EID_MESH_ID: elems->mesh_id = pos; @@ -2930,10 +2936,22 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, int cf0, cf1; int ccfs0, ccfs1, ccfs2; int ccf0, ccf1; + u32 vht_cap; + bool support_80_80 = false; + bool support_160 = false; if (!oper || !htop) return false; + vht_cap = hw->wiphy->bands[chandef->chan->band]->vht_cap.cap; + support_160 = (vht_cap & (IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_MASK | + IEEE80211_VHT_CAP_EXT_NSS_BW_MASK)); + support_80_80 = ((vht_cap & + IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160_80PLUS80MHZ) || + (vht_cap & IEEE80211_VHT_CAP_SUPP_CHAN_WIDTH_160MHZ && + vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) || + ((vht_cap & IEEE80211_VHT_CAP_EXT_NSS_BW_MASK) >> + IEEE80211_VHT_CAP_EXT_NSS_BW_SHIFT > 1)); ccfs0 = oper->center_freq_seg0_idx; ccfs1 = oper->center_freq_seg1_idx; ccfs2 = (le16_to_cpu(htop->operation_mode) & @@ -2961,10 +2979,10 @@ bool ieee80211_chandef_vht_oper(struct ieee80211_hw *hw, unsigned int diff; diff = abs(ccf1 - ccf0); - if (diff == 8) { + if ((diff == 8) && support_160) { new.width = NL80211_CHAN_WIDTH_160; new.center_freq1 = cf1; - } else if (diff > 8) { + } else if ((diff > 8) && support_80_80) { new.width = NL80211_CHAN_WIDTH_80P80; new.center_freq2 = cf1; } diff --git a/net/mac80211/wep.c b/net/mac80211/wep.c index 3d9e92867ef0..b75c2c54e665 100644 --- a/net/mac80211/wep.c +++ b/net/mac80211/wep.c @@ -27,30 +27,9 @@ int ieee80211_wep_init(struct ieee80211_local *local) /* start WEP IV from a random value */ get_random_bytes(&local->wep_iv, IEEE80211_WEP_IV_LEN); - local->wep_tx_tfm = crypto_alloc_cipher("arc4", 0, 0); - if (IS_ERR(local->wep_tx_tfm)) { - local->wep_rx_tfm = ERR_PTR(-EINVAL); - return PTR_ERR(local->wep_tx_tfm); - } - - local->wep_rx_tfm = crypto_alloc_cipher("arc4", 0, 0); - if (IS_ERR(local->wep_rx_tfm)) { - crypto_free_cipher(local->wep_tx_tfm); - local->wep_tx_tfm = ERR_PTR(-EINVAL); - return PTR_ERR(local->wep_rx_tfm); - } - return 0; } -void ieee80211_wep_free(struct ieee80211_local *local) -{ - if (!IS_ERR(local->wep_tx_tfm)) - crypto_free_cipher(local->wep_tx_tfm); - if (!IS_ERR(local->wep_rx_tfm)) - crypto_free_cipher(local->wep_rx_tfm); -} - static inline bool ieee80211_wep_weak_iv(u32 iv, int keylen) { /* @@ -128,21 +107,17 @@ static void ieee80211_wep_remove_iv(struct ieee80211_local *local, /* Perform WEP encryption using given key. data buffer must have tailroom * for 4-byte ICV. data_len must not include this ICV. Note: this function * does _not_ add IV. data = RC4(data | CRC32(data)) */ -int ieee80211_wep_encrypt_data(struct crypto_cipher *tfm, u8 *rc4key, +int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len) { __le32 icv; - int i; - - if (IS_ERR(tfm)) - return -1; icv = cpu_to_le32(~crc32_le(~0, data, data_len)); put_unaligned(icv, (__le32 *)(data + data_len)); - crypto_cipher_setkey(tfm, rc4key, klen); - for (i = 0; i < data_len + IEEE80211_WEP_ICV_LEN; i++) - crypto_cipher_encrypt_one(tfm, data + i, data + i); + arc4_setkey(ctx, rc4key, klen); + arc4_crypt(ctx, data, data, data_len + IEEE80211_WEP_ICV_LEN); + memzero_explicit(ctx, sizeof(*ctx)); return 0; } @@ -181,7 +156,7 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, /* Add room for ICV */ skb_put(skb, IEEE80211_WEP_ICV_LEN); - return ieee80211_wep_encrypt_data(local->wep_tx_tfm, rc4key, keylen + 3, + return ieee80211_wep_encrypt_data(&local->wep_tx_ctx, rc4key, keylen + 3, iv + IEEE80211_WEP_IV_LEN, len); } @@ -189,18 +164,14 @@ int ieee80211_wep_encrypt(struct ieee80211_local *local, /* Perform WEP decryption using given key. data buffer includes encrypted * payload, including 4-byte ICV, but _not_ IV. data_len must not include ICV. * Return 0 on success and -1 on ICV mismatch. */ -int ieee80211_wep_decrypt_data(struct crypto_cipher *tfm, u8 *rc4key, +int ieee80211_wep_decrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len) { __le32 crc; - int i; - - if (IS_ERR(tfm)) - return -1; - crypto_cipher_setkey(tfm, rc4key, klen); - for (i = 0; i < data_len + IEEE80211_WEP_ICV_LEN; i++) - crypto_cipher_decrypt_one(tfm, data + i, data + i); + arc4_setkey(ctx, rc4key, klen); + arc4_crypt(ctx, data, data, data_len + IEEE80211_WEP_ICV_LEN); + memzero_explicit(ctx, sizeof(*ctx)); crc = cpu_to_le32(~crc32_le(~0, data, data_len)); if (memcmp(&crc, data + data_len, IEEE80211_WEP_ICV_LEN) != 0) @@ -253,7 +224,7 @@ static int ieee80211_wep_decrypt(struct ieee80211_local *local, /* Copy rest of the WEP key (the secret part) */ memcpy(rc4key + 3, key->conf.key, key->conf.keylen); - if (ieee80211_wep_decrypt_data(local->wep_rx_tfm, rc4key, klen, + if (ieee80211_wep_decrypt_data(&local->wep_rx_ctx, rc4key, klen, skb->data + hdrlen + IEEE80211_WEP_IV_LEN, len)) ret = -1; diff --git a/net/mac80211/wep.h b/net/mac80211/wep.h index 866a6798c9ef..997a034233c2 100644 --- a/net/mac80211/wep.h +++ b/net/mac80211/wep.h @@ -14,13 +14,12 @@ #include "key.h" int ieee80211_wep_init(struct ieee80211_local *local); -void ieee80211_wep_free(struct ieee80211_local *local); -int ieee80211_wep_encrypt_data(struct crypto_cipher *tfm, u8 *rc4key, +int ieee80211_wep_encrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len); int ieee80211_wep_encrypt(struct ieee80211_local *local, struct sk_buff *skb, const u8 *key, int keylen, int keyidx); -int ieee80211_wep_decrypt_data(struct crypto_cipher *tfm, u8 *rc4key, +int ieee80211_wep_decrypt_data(struct arc4_ctx *ctx, u8 *rc4key, size_t klen, u8 *data, size_t data_len); ieee80211_rx_result diff --git a/net/mac80211/wpa.c b/net/mac80211/wpa.c index a51c7909366e..ee72779729e5 100644 --- a/net/mac80211/wpa.c +++ b/net/mac80211/wpa.c @@ -239,7 +239,7 @@ static int tkip_encrypt_skb(struct ieee80211_tx_data *tx, struct sk_buff *skb) /* Add room for ICV */ skb_put(skb, IEEE80211_TKIP_ICV_LEN); - return ieee80211_tkip_encrypt_data(tx->local->wep_tx_tfm, + return ieee80211_tkip_encrypt_data(&tx->local->wep_tx_ctx, key, skb, pos, len); } @@ -290,7 +290,7 @@ ieee80211_crypto_tkip_decrypt(struct ieee80211_rx_data *rx) if (status->flag & RX_FLAG_DECRYPTED) hwaccel = 1; - res = ieee80211_tkip_decrypt_data(rx->local->wep_rx_tfm, + res = ieee80211_tkip_decrypt_data(&rx->local->wep_rx_ctx, key, skb->data + hdrlen, skb->len - hdrlen, rx->sta->sta.addr, hdr->addr1, hwaccel, rx->security_idx, diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 198ec4fe4148..8ff1c6120b1e 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -619,16 +619,15 @@ static struct net_device *inet6_fib_lookup_dev(struct net *net, struct net_device *dev; struct dst_entry *dst; struct flowi6 fl6; - int err; if (!ipv6_stub) return ERR_PTR(-EAFNOSUPPORT); memset(&fl6, 0, sizeof(fl6)); memcpy(&fl6.daddr, addr, sizeof(struct in6_addr)); - err = ipv6_stub->ipv6_dst_lookup(net, NULL, &dst, &fl6); - if (err) - return ERR_PTR(err); + dst = ipv6_stub->ipv6_dst_lookup_flow(net, NULL, &fl6, NULL); + if (IS_ERR(dst)) + return ERR_CAST(dst); dev = dst->dev; dev_hold(dev); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 8acc4e173167..ecb3d67b41bf 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -61,9 +61,9 @@ mtype_destroy(struct ip_set *set) if (SET_WITH_TIMEOUT(set)) del_timer_sync(&map->gc); - ip_set_free(map->members); if (set->dsize && set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); + ip_set_free(map->members); ip_set_free(map); set->data = NULL; @@ -76,7 +76,7 @@ mtype_flush(struct ip_set *set) if (set->extensions & IPSET_EXT_DESTROY) mtype_ext_cleanup(set); - memset(map->members, 0, map->memsize); + bitmap_zero(map->members, map->elements); set->elements = 0; set->ext_size = 0; } diff --git a/net/netfilter/ipset/ip_set_bitmap_ip.c b/net/netfilter/ipset/ip_set_bitmap_ip.c index e3884b0cca91..79d1a8e554dc 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ip.c +++ b/net/netfilter/ipset/ip_set_bitmap_ip.c @@ -37,7 +37,7 @@ MODULE_ALIAS("ip_set_bitmap:ip"); /* Type structure */ struct bitmap_ip { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -220,7 +220,7 @@ init_map_ip(struct ip_set *set, struct bitmap_ip *map, u32 first_ip, u32 last_ip, u32 elements, u32 hosts, u8 netmask) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -310,11 +310,11 @@ bitmap_ip_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ip; if (!init_map_ip(set, map, first_ip, last_ip, elements, hosts, netmask)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_ipmac.c b/net/netfilter/ipset/ip_set_bitmap_ipmac.c index cfe7b556775f..0aac330ef78b 100644 --- a/net/netfilter/ipset/ip_set_bitmap_ipmac.c +++ b/net/netfilter/ipset/ip_set_bitmap_ipmac.c @@ -43,7 +43,7 @@ enum { /* Type structure */ struct bitmap_ipmac { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u32 first_ip; /* host byte order, included in range */ u32 last_ip; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -300,7 +300,7 @@ static bool init_map_ipmac(struct ip_set *set, struct bitmap_ipmac *map, u32 first_ip, u32 last_ip, u32 elements) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_ip = first_ip; @@ -361,10 +361,10 @@ bitmap_ipmac_create(struct net *net, struct ip_set *set, struct nlattr *tb[], if (!map) return -ENOMEM; - map->memsize = bitmap_bytes(0, elements - 1); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_ipmac; if (!init_map_ipmac(set, map, first_ip, last_ip, elements)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_bitmap_port.c b/net/netfilter/ipset/ip_set_bitmap_port.c index d8c140553379..044310ccf0a4 100644 --- a/net/netfilter/ipset/ip_set_bitmap_port.c +++ b/net/netfilter/ipset/ip_set_bitmap_port.c @@ -31,7 +31,7 @@ MODULE_ALIAS("ip_set_bitmap:port"); /* Type structure */ struct bitmap_port { - void *members; /* the set members */ + unsigned long *members; /* the set members */ u16 first_port; /* host byte order, included in range */ u16 last_port; /* host byte order, included in range */ u32 elements; /* number of max elements in the set */ @@ -205,7 +205,7 @@ static bool init_map_port(struct ip_set *set, struct bitmap_port *map, u16 first_port, u16 last_port) { - map->members = ip_set_alloc(map->memsize); + map->members = bitmap_zalloc(map->elements, GFP_KERNEL | __GFP_NOWARN); if (!map->members) return false; map->first_port = first_port; @@ -245,10 +245,10 @@ bitmap_port_create(struct net *net, struct ip_set *set, struct nlattr *tb[], return -ENOMEM; map->elements = elements; - map->memsize = bitmap_bytes(0, map->elements); + map->memsize = BITS_TO_LONGS(elements) * sizeof(unsigned long); set->variant = &bitmap_port; if (!init_map_port(set, map, first_port, last_port)) { - kfree(map); + ip_set_free(map); return -ENOMEM; } if (tb[IPSET_ATTR_TIMEOUT]) { diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index e103c875383a..cb1930fd803d 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -296,7 +296,8 @@ ip_set_get_ipaddr4(struct nlattr *nla, __be32 *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV4))) return -IPSET_ERR_PROTOCOL; @@ -314,7 +315,8 @@ ip_set_get_ipaddr6(struct nlattr *nla, union nf_inet_addr *ipaddr) if (unlikely(!flag_nested(nla))) return -IPSET_ERR_PROTOCOL; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_IPADDR_MAX, nla, ipaddr_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_IPADDR_MAX, nla, + ipaddr_policy, NULL)) return -IPSET_ERR_PROTOCOL; if (unlikely(!ip_set_attr_netorder(tb, IPSET_ATTR_IPADDR_IPV6))) return -IPSET_ERR_PROTOCOL; @@ -380,6 +382,8 @@ ip_set_elem_len(struct ip_set *set, struct nlattr *tb[], size_t len, for (id = 0; id < IPSET_EXT_ID_MAX; id++) { if (!add_extension(id, cadt_flags, tb)) continue; + if (align < ip_set_extensions[id].align) + align = ip_set_extensions[id].align; len = ALIGN(len, ip_set_extensions[id].align); set->offset[id] = len; set->extensions |= ip_set_extensions[id].type; @@ -555,6 +559,20 @@ ip_set_rcu_get(struct net *net, ip_set_id_t index) return set; } +static inline void +ip_set_lock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_lock_bh(&set->lock); +} + +static inline void +ip_set_unlock(struct ip_set *set) +{ + if (!set->variant->region_lock) + spin_unlock_bh(&set->lock); +} + int ip_set_test(ip_set_id_t index, const struct sk_buff *skb, const struct xt_action_param *par, struct ip_set_adt_opt *opt) @@ -576,9 +594,9 @@ ip_set_test(ip_set_id_t index, const struct sk_buff *skb, if (ret == -EAGAIN) { /* Type requests element to be completed */ pr_debug("element must be completed, ADD is triggered\n"); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); ret = 1; } else { /* --return-nomatch: invert matched element */ @@ -607,9 +625,9 @@ ip_set_add(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_ADD, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -629,9 +647,9 @@ ip_set_del(ip_set_id_t index, const struct sk_buff *skb, !(opt->family == set->family || set->family == NFPROTO_UNSPEC)) return -IPSET_ERR_TYPE_MISMATCH; - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->kadt(set, skb, par, IPSET_DEL, opt); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); return ret; } @@ -934,7 +952,8 @@ static int ip_set_create(struct net *net, struct sock *ctnl, /* Without holding any locks, create private part. */ if (attr[IPSET_ATTR_DATA] && - nla_parse_nested_deprecated(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], set->type->create_policy, NULL)) { + nla_parse_nested(tb, IPSET_ATTR_CREATE_MAX, attr[IPSET_ATTR_DATA], + set->type->create_policy, NULL)) { ret = -IPSET_ERR_PROTOCOL; goto put_out; } @@ -1095,9 +1114,9 @@ ip_set_flush_set(struct ip_set *set) { pr_debug("set: %s\n", set->name); - spin_lock_bh(&set->lock); + ip_set_lock(set); set->variant->flush(set); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); } static int ip_set_flush(struct net *net, struct sock *ctnl, struct sk_buff *skb, @@ -1281,30 +1300,43 @@ dump_attrs(struct nlmsghdr *nlh) } } +static const struct nla_policy +ip_set_dump_policy[IPSET_ATTR_CMD_MAX + 1] = { + [IPSET_ATTR_PROTOCOL] = { .type = NLA_U8 }, + [IPSET_ATTR_SETNAME] = { .type = NLA_NUL_STRING, + .len = IPSET_MAXNAMELEN - 1 }, + [IPSET_ATTR_FLAGS] = { .type = NLA_U32 }, +}; + static int -dump_init(struct netlink_callback *cb, struct ip_set_net *inst) +ip_set_dump_start(struct netlink_callback *cb) { struct nlmsghdr *nlh = nlmsg_hdr(cb->skb); int min_len = nlmsg_total_size(sizeof(struct nfgenmsg)); struct nlattr *cda[IPSET_ATTR_CMD_MAX + 1]; struct nlattr *attr = (void *)nlh + min_len; + struct sk_buff *skb = cb->skb; + struct ip_set_net *inst = ip_set_pernet(sock_net(skb->sk)); u32 dump_type; - ip_set_id_t index; + int ret; - /* Second pass, so parser can't fail */ - nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, attr, - nlh->nlmsg_len - min_len, ip_set_setname_policy, - NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, attr, + nlh->nlmsg_len - min_len, + ip_set_dump_policy, NULL); + if (ret) + goto error; cb->args[IPSET_CB_PROTO] = nla_get_u8(cda[IPSET_ATTR_PROTOCOL]); if (cda[IPSET_ATTR_SETNAME]) { + ip_set_id_t index; struct ip_set *set; set = find_set_and_id(inst, nla_data(cda[IPSET_ATTR_SETNAME]), &index); - if (!set) - return -ENOENT; - + if (!set) { + ret = -ENOENT; + goto error; + } dump_type = DUMP_ONE; cb->args[IPSET_CB_INDEX] = index; } else { @@ -1320,10 +1352,17 @@ dump_init(struct netlink_callback *cb, struct ip_set_net *inst) cb->args[IPSET_CB_DUMP] = dump_type; return 0; + +error: + /* We have to create and send the error message manually :-( */ + if (nlh->nlmsg_flags & NLM_F_ACK) { + netlink_ack(cb->skb, nlh, ret, NULL); + } + return ret; } static int -ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) +ip_set_dump_do(struct sk_buff *skb, struct netlink_callback *cb) { ip_set_id_t index = IPSET_INVALID_ID, max; struct ip_set *set = NULL; @@ -1334,18 +1373,8 @@ ip_set_dump_start(struct sk_buff *skb, struct netlink_callback *cb) bool is_destroyed; int ret = 0; - if (!cb->args[IPSET_CB_DUMP]) { - ret = dump_init(cb, inst); - if (ret < 0) { - nlh = nlmsg_hdr(cb->skb); - /* We have to create and send the error message - * manually :-( - */ - if (nlh->nlmsg_flags & NLM_F_ACK) - netlink_ack(cb->skb, nlh, ret, NULL); - return ret; - } - } + if (!cb->args[IPSET_CB_DUMP]) + return -EINVAL; if (cb->args[IPSET_CB_INDEX] >= inst->ip_set_max) goto out; @@ -1481,7 +1510,8 @@ static int ip_set_dump(struct net *net, struct sock *ctnl, struct sk_buff *skb, { struct netlink_dump_control c = { - .dump = ip_set_dump_start, + .start = ip_set_dump_start, + .dump = ip_set_dump_do, .done = ip_set_dump_done, }; return netlink_dump_start(ctnl, skb, nlh, &c); @@ -1509,9 +1539,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, bool eexist = flags & IPSET_FLAG_EXIST, retried = false; do { - spin_lock_bh(&set->lock); + ip_set_lock(set); ret = set->variant->uadt(set, tb, adt, &lineno, flags, retried); - spin_unlock_bh(&set->lock); + ip_set_unlock(set); retried = true; } while (ret == -EAGAIN && set->variant->resize && @@ -1541,9 +1571,9 @@ call_ad(struct sock *ctnl, struct sk_buff *skb, struct ip_set *set, memcpy(&errmsg->msg, nlh, nlh->nlmsg_len); cmdattr = (void *)&errmsg->msg + min_len; - ret = nla_parse_deprecated(cda, IPSET_ATTR_CMD_MAX, cmdattr, - nlh->nlmsg_len - min_len, - ip_set_adt_policy, NULL); + ret = nla_parse(cda, IPSET_ATTR_CMD_MAX, cmdattr, + nlh->nlmsg_len - min_len, ip_set_adt_policy, + NULL); if (ret) { nlmsg_free(skb2); @@ -1592,7 +1622,9 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb, use_lineno = !!attr[IPSET_ATTR_LINENO]; if (attr[IPSET_ATTR_DATA]) { - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, + attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, IPSET_ADD, flags, use_lineno); @@ -1603,7 +1635,8 @@ static int ip_set_uadd(struct net *net, struct sock *ctnl, struct sk_buff *skb, memset(tb, 0, sizeof(tb)); if (nla_type(nla) != IPSET_ATTR_DATA || !flag_nested(nla) || - nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, nla, set->type->adt_policy, NULL)) + nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, nla, + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; ret = call_ad(ctnl, skb, set, tb, IPSET_ADD, flags, use_lineno); @@ -1675,6 +1708,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, struct ip_set *set; struct nlattr *tb[IPSET_ATTR_ADT_MAX + 1] = {}; int ret = 0; + u32 lineno; if (unlikely(protocol_min_failed(attr) || !attr[IPSET_ATTR_SETNAME] || @@ -1686,11 +1720,12 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, if (!set) return -ENOENT; - if (nla_parse_nested_deprecated(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], set->type->adt_policy, NULL)) + if (nla_parse_nested(tb, IPSET_ATTR_ADT_MAX, attr[IPSET_ATTR_DATA], + set->type->adt_policy, NULL)) return -IPSET_ERR_PROTOCOL; rcu_read_lock_bh(); - ret = set->variant->uadt(set, tb, IPSET_TEST, NULL, 0, 0); + ret = set->variant->uadt(set, tb, IPSET_TEST, &lineno, 0, 0); rcu_read_unlock_bh(); /* Userspace can't trigger element to be re-added */ if (ret == -EAGAIN) @@ -1992,7 +2027,7 @@ static const struct nfnl_callback ip_set_netlink_subsys_cb[IPSET_MSG_MAX] = { [IPSET_CMD_LIST] = { .call = ip_set_dump, .attr_count = IPSET_ATTR_CMD_MAX, - .policy = ip_set_setname_policy, + .policy = ip_set_dump_policy, }, [IPSET_CMD_SAVE] = { .call = ip_set_dump, @@ -2100,8 +2135,9 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } req_version->version = IPSET_PROTOCOL; - ret = copy_to_user(user, req_version, - sizeof(struct ip_set_req_version)); + if (copy_to_user(user, req_version, + sizeof(struct ip_set_req_version))) + ret = -EFAULT; goto done; } case IP_SET_OP_GET_BYNAME: { @@ -2160,7 +2196,8 @@ ip_set_sockfn_get(struct sock *sk, int optval, void __user *user, int *len) } /* end of switch(op) */ copy: - ret = copy_to_user(user, data, copylen); + if (copy_to_user(user, data, copylen)) + ret = -EFAULT; done: vfree(data); diff --git a/net/netfilter/ipset/ip_set_hash_gen.h b/net/netfilter/ipset/ip_set_hash_gen.h index 175f8fedcfaf..f970ff99f61b 100644 --- a/net/netfilter/ipset/ip_set_hash_gen.h +++ b/net/netfilter/ipset/ip_set_hash_gen.h @@ -8,13 +8,21 @@ #include <linux/rcupdate.h> #include <linux/jhash.h> #include <linux/types.h> +#include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/ipset/ip_set_timeout.h> -#define __ipset_dereference_protected(p, c) rcu_dereference_protected(p, c) -#define ipset_dereference_protected(p, set) \ - __ipset_dereference_protected(p, lockdep_is_held(&(set)->lock)) - -#define rcu_dereference_bh_nfnl(p) rcu_dereference_bh_check(p, 1) +#define __ipset_dereference(p) \ + rcu_dereference_protected(p, 1) +#define ipset_dereference_nfnl(p) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) +#define ipset_dereference_set(p, set) \ + rcu_dereference_protected(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET) || \ + lockdep_is_held(&(set)->lock)) +#define ipset_dereference_bh_nfnl(p) \ + rcu_dereference_bh_check(p, \ + lockdep_nfnl_is_held(NFNL_SUBSYS_IPSET)) /* Hashing which uses arrays to resolve clashing. The hash table is resized * (doubled) when searching becomes too long. @@ -73,11 +81,35 @@ struct hbucket { __aligned(__alignof__(u64)); }; +/* Region size for locking == 2^HTABLE_REGION_BITS */ +#define HTABLE_REGION_BITS 10 +#define ahash_numof_locks(htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 1 \ + : jhash_size((htable_bits) - HTABLE_REGION_BITS)) +#define ahash_sizeof_regions(htable_bits) \ + (ahash_numof_locks(htable_bits) * sizeof(struct ip_set_region)) +#define ahash_region(n, htable_bits) \ + ((n) % ahash_numof_locks(htable_bits)) +#define ahash_bucket_start(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? 0 \ + : (h) * jhash_size(HTABLE_REGION_BITS)) +#define ahash_bucket_end(h, htable_bits) \ + ((htable_bits) < HTABLE_REGION_BITS ? jhash_size(htable_bits) \ + : ((h) + 1) * jhash_size(HTABLE_REGION_BITS)) + +struct htable_gc { + struct delayed_work dwork; + struct ip_set *set; /* Set the gc belongs to */ + u32 region; /* Last gc run position */ +}; + /* The hash table: the table size stored here in order to make resizing easy */ struct htable { atomic_t ref; /* References for resizing */ - atomic_t uref; /* References for dumping */ + atomic_t uref; /* References for dumping and gc */ u8 htable_bits; /* size of hash table == 2^htable_bits */ + u32 maxelem; /* Maxelem per region */ + struct ip_set_region *hregion; /* Region locks and ext sizes */ struct hbucket __rcu *bucket[0]; /* hashtable buckets */ }; @@ -163,6 +195,10 @@ htable_bits(u32 hashsize) #define NLEN 0 #endif /* IP_SET_HASH_WITH_NETS */ +#define SET_ELEM_EXPIRED(set, d) \ + (SET_WITH_TIMEOUT(set) && \ + ip_set_timeout_expired(ext_timeout(d, set))) + #endif /* _IP_SET_HASH_GEN_H */ #ifndef MTYPE @@ -206,10 +242,12 @@ htable_bits(u32 hashsize) #undef mtype_test_cidrs #undef mtype_test #undef mtype_uref -#undef mtype_expire #undef mtype_resize +#undef mtype_ext_size +#undef mtype_resize_ad #undef mtype_head #undef mtype_list +#undef mtype_gc_do #undef mtype_gc #undef mtype_gc_init #undef mtype_variant @@ -248,10 +286,12 @@ htable_bits(u32 hashsize) #define mtype_test_cidrs IPSET_TOKEN(MTYPE, _test_cidrs) #define mtype_test IPSET_TOKEN(MTYPE, _test) #define mtype_uref IPSET_TOKEN(MTYPE, _uref) -#define mtype_expire IPSET_TOKEN(MTYPE, _expire) #define mtype_resize IPSET_TOKEN(MTYPE, _resize) +#define mtype_ext_size IPSET_TOKEN(MTYPE, _ext_size) +#define mtype_resize_ad IPSET_TOKEN(MTYPE, _resize_ad) #define mtype_head IPSET_TOKEN(MTYPE, _head) #define mtype_list IPSET_TOKEN(MTYPE, _list) +#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_variant IPSET_TOKEN(MTYPE, _variant) @@ -276,8 +316,7 @@ htable_bits(u32 hashsize) /* The generic hash structure */ struct htype { struct htable __rcu *table; /* the hash table */ - struct timer_list gc; /* garbage collection when timeout enabled */ - struct ip_set *set; /* attached to this ip_set */ + struct htable_gc gc; /* gc workqueue */ u32 maxelem; /* max elements in the hash */ u32 initval; /* random jhash init value */ #ifdef IP_SET_HASH_WITH_MARKMASK @@ -289,21 +328,33 @@ struct htype { #ifdef IP_SET_HASH_WITH_NETMASK u8 netmask; /* netmask value for subnets to store */ #endif + struct list_head ad; /* Resize add|del backlist */ struct mtype_elem next; /* temporary storage for uadd */ #ifdef IP_SET_HASH_WITH_NETS struct net_prefixes nets[NLEN]; /* book-keeping of prefixes */ #endif }; +/* ADD|DEL entries saved during resize */ +struct mtype_resize_ad { + struct list_head list; + enum ipset_adt ad; /* ADD|DEL element */ + struct mtype_elem d; /* Element value */ + struct ip_set_ext ext; /* Extensions for ADD */ + struct ip_set_ext mext; /* Target extensions for ADD */ + u32 flags; /* Flags for ADD */ +}; + #ifdef IP_SET_HASH_WITH_NETS /* Network cidr size book keeping when the hash stores different * sized networks. cidr == real cidr + 1 to support /0. */ static void -mtype_add_cidr(struct htype *h, u8 cidr, u8 n) +mtype_add_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { int i, j; + spin_lock_bh(&set->lock); /* Add in increasing prefix order, so larger cidr first */ for (i = 0, j = -1; i < NLEN && h->nets[i].cidr[n]; i++) { if (j != -1) { @@ -312,7 +363,7 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) j = i; } else if (h->nets[i].cidr[n] == cidr) { h->nets[CIDR_POS(cidr)].nets[n]++; - return; + goto unlock; } } if (j != -1) { @@ -321,24 +372,29 @@ mtype_add_cidr(struct htype *h, u8 cidr, u8 n) } h->nets[i].cidr[n] = cidr; h->nets[CIDR_POS(cidr)].nets[n] = 1; +unlock: + spin_unlock_bh(&set->lock); } static void -mtype_del_cidr(struct htype *h, u8 cidr, u8 n) +mtype_del_cidr(struct ip_set *set, struct htype *h, u8 cidr, u8 n) { u8 i, j, net_end = NLEN - 1; + spin_lock_bh(&set->lock); for (i = 0; i < NLEN; i++) { if (h->nets[i].cidr[n] != cidr) continue; h->nets[CIDR_POS(cidr)].nets[n]--; if (h->nets[CIDR_POS(cidr)].nets[n] > 0) - return; + goto unlock; for (j = i; j < net_end && h->nets[j].cidr[n]; j++) h->nets[j].cidr[n] = h->nets[j + 1].cidr[n]; h->nets[j].cidr[n] = 0; - return; + goto unlock; } +unlock: + spin_unlock_bh(&set->lock); } #endif @@ -346,7 +402,7 @@ mtype_del_cidr(struct htype *h, u8 cidr, u8 n) static size_t mtype_ahash_memsize(const struct htype *h, const struct htable *t) { - return sizeof(*h) + sizeof(*t); + return sizeof(*h) + sizeof(*t) + ahash_sizeof_regions(t->htable_bits); } /* Get the ith element from the array block n */ @@ -370,24 +426,29 @@ mtype_flush(struct ip_set *set) struct htype *h = set->data; struct htable *t; struct hbucket *n; - u32 i; - - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); - if (!n) - continue; - if (set->extensions & IPSET_EXT_DESTROY) - mtype_ext_cleanup(set, n); - /* FIXME: use slab cache */ - rcu_assign_pointer(hbucket(t, i), NULL); - kfree_rcu(n, rcu); + u32 r, i; + + t = ipset_dereference_nfnl(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); + if (!n) + continue; + if (set->extensions & IPSET_EXT_DESTROY) + mtype_ext_cleanup(set, n); + /* FIXME: use slab cache */ + rcu_assign_pointer(hbucket(t, i), NULL); + kfree_rcu(n, rcu); + } + t->hregion[r].ext_size = 0; + t->hregion[r].elements = 0; + spin_unlock_bh(&t->hregion[r].lock); } #ifdef IP_SET_HASH_WITH_NETS memset(h->nets, 0, sizeof(h->nets)); #endif - set->elements = 0; - set->ext_size = 0; } /* Destroy the hashtable part of the set */ @@ -398,7 +459,7 @@ 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_protected(hbucket(t, i), 1); + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; if (set->extensions & IPSET_EXT_DESTROY && ext_destroy) @@ -407,6 +468,7 @@ mtype_ahash_destroy(struct ip_set *set, struct htable *t, bool ext_destroy) kfree(n); } + ip_set_free(t->hregion); ip_set_free(t); } @@ -415,28 +477,21 @@ static void mtype_destroy(struct ip_set *set) { struct htype *h = set->data; + struct list_head *l, *lt; if (SET_WITH_TIMEOUT(set)) - del_timer_sync(&h->gc); + cancel_delayed_work_sync(&h->gc.dwork); - mtype_ahash_destroy(set, - __ipset_dereference_protected(h->table, 1), true); + mtype_ahash_destroy(set, ipset_dereference_nfnl(h->table), true); + list_for_each_safe(l, lt, &h->ad) { + list_del(l); + kfree(l); + } kfree(h); set->data = NULL; } -static void -mtype_gc_init(struct ip_set *set, void (*gc)(struct timer_list *t)) -{ - struct htype *h = set->data; - - timer_setup(&h->gc, gc, 0); - mod_timer(&h->gc, jiffies + IPSET_GC_PERIOD(set->timeout) * HZ); - pr_debug("gc initialized, run in every %u\n", - IPSET_GC_PERIOD(set->timeout)); -} - static bool mtype_same_set(const struct ip_set *a, const struct ip_set *b) { @@ -455,11 +510,9 @@ mtype_same_set(const struct ip_set *a, const struct ip_set *b) a->extensions == b->extensions; } -/* Delete expired elements from the hashtable */ static void -mtype_expire(struct ip_set *set, struct htype *h) +mtype_gc_do(struct ip_set *set, struct htype *h, struct htable *t, u32 r) { - struct htable *t; struct hbucket *n, *tmp; struct mtype_elem *data; u32 i, j, d; @@ -467,10 +520,12 @@ mtype_expire(struct ip_set *set, struct htype *h) #ifdef IP_SET_HASH_WITH_NETS u8 k; #endif + u8 htable_bits = t->htable_bits; - t = ipset_dereference_protected(h->table, set); - for (i = 0; i < jhash_size(t->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(t, i), 1); + spin_lock_bh(&t->hregion[r].lock); + for (i = ahash_bucket_start(r, htable_bits); + i < ahash_bucket_end(r, htable_bits); i++) { + n = __ipset_dereference(hbucket(t, i)); if (!n) continue; for (j = 0, d = 0; j < n->pos; j++) { @@ -486,58 +541,100 @@ mtype_expire(struct ip_set *set, struct htype *h) smp_mb__after_atomic(); #ifdef IP_SET_HASH_WITH_NETS for (k = 0; k < IPSET_NET_COUNT; k++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, k)), k); #endif + t->hregion[r].elements--; ip_set_ext_destroy(set, data); - set->elements--; d++; } if (d >= AHASH_INIT_SIZE) { if (d >= n->size) { + t->hregion[r].ext_size -= + ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, i), NULL); kfree_rcu(n, rcu); continue; } tmp = kzalloc(sizeof(*tmp) + - (n->size - AHASH_INIT_SIZE) * dsize, - GFP_ATOMIC); + (n->size - AHASH_INIT_SIZE) * dsize, + GFP_ATOMIC); if (!tmp) - /* Still try to delete expired elements */ + /* Still try to delete expired elements. */ continue; tmp->size = n->size - AHASH_INIT_SIZE; for (j = 0, d = 0; j < n->pos; j++) { if (!test_bit(j, n->used)) continue; data = ahash_data(n, j, dsize); - memcpy(tmp->value + d * dsize, data, dsize); + memcpy(tmp->value + d * dsize, + data, dsize); set_bit(d, tmp->used); d++; } tmp->pos = d; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, i), tmp); kfree_rcu(n, rcu); } } + spin_unlock_bh(&t->hregion[r].lock); } static void -mtype_gc(struct timer_list *t) +mtype_gc(struct work_struct *work) { - struct htype *h = from_timer(h, t, gc); - struct ip_set *set = h->set; + struct htable_gc *gc; + struct ip_set *set; + struct htype *h; + struct htable *t; + u32 r, numof_locks; + unsigned int next_run; + + gc = container_of(work, struct htable_gc, dwork.work); + set = gc->set; + h = set->data; - pr_debug("called\n"); spin_lock_bh(&set->lock); - mtype_expire(set, h); + t = ipset_dereference_set(h->table, set); + atomic_inc(&t->uref); + numof_locks = ahash_numof_locks(t->htable_bits); + r = gc->region++; + if (r >= numof_locks) { + r = gc->region = 0; + } + next_run = (IPSET_GC_PERIOD(set->timeout) * HZ) / numof_locks; + if (next_run < HZ/10) + next_run = HZ/10; spin_unlock_bh(&set->lock); - h->gc.expires = jiffies + IPSET_GC_PERIOD(set->timeout) * HZ; - add_timer(&h->gc); + mtype_gc_do(set, h, t, r); + + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by expire: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + + queue_delayed_work(system_power_efficient_wq, &gc->dwork, next_run); + +} + +static void +mtype_gc_init(struct htable_gc *gc) +{ + INIT_DEFERRABLE_WORK(&gc->dwork, mtype_gc); + queue_delayed_work(system_power_efficient_wq, &gc->dwork, HZ); } +static int +mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); +static int +mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, + struct ip_set_ext *mext, u32 flags); + /* Resize a hash: create a new hash table with doubling the hashsize * and inserting the elements to it. Repeat until we succeed or * fail due to memory pressures. @@ -548,7 +645,7 @@ mtype_resize(struct ip_set *set, bool retried) struct htype *h = set->data; struct htable *t, *orig; u8 htable_bits; - size_t extsize, dsize = set->dsize; + size_t dsize = set->dsize; #ifdef IP_SET_HASH_WITH_NETS u8 flags; struct mtype_elem *tmp; @@ -556,7 +653,9 @@ mtype_resize(struct ip_set *set, bool retried) struct mtype_elem *data; struct mtype_elem *d; struct hbucket *n, *m; - u32 i, j, key; + struct list_head *l, *lt; + struct mtype_resize_ad *x; + u32 i, j, r, nr, key; int ret; #ifdef IP_SET_HASH_WITH_NETS @@ -564,10 +663,8 @@ mtype_resize(struct ip_set *set, bool retried) if (!tmp) return -ENOMEM; #endif - rcu_read_lock_bh(); - orig = rcu_dereference_bh_nfnl(h->table); + orig = ipset_dereference_bh_nfnl(h->table); htable_bits = orig->htable_bits; - rcu_read_unlock_bh(); retry: ret = 0; @@ -584,88 +681,124 @@ retry: ret = -ENOMEM; goto out; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(htable_bits)); + if (!t->hregion) { + ip_set_free(t); + ret = -ENOMEM; + goto out; + } t->htable_bits = htable_bits; + t->maxelem = h->maxelem / ahash_numof_locks(htable_bits); + for (i = 0; i < ahash_numof_locks(htable_bits); i++) + spin_lock_init(&t->hregion[i].lock); - spin_lock_bh(&set->lock); - orig = __ipset_dereference_protected(h->table, 1); - /* There can't be another parallel resizing, but dumping is possible */ + /* There can't be another parallel resizing, + * but dumping, gc, kernel side add/del are possible + */ + orig = ipset_dereference_bh_nfnl(h->table); atomic_set(&orig->ref, 1); atomic_inc(&orig->uref); - extsize = 0; pr_debug("attempt to resize set %s from %u to %u, t %p\n", set->name, orig->htable_bits, htable_bits, orig); - for (i = 0; i < jhash_size(orig->htable_bits); i++) { - n = __ipset_dereference_protected(hbucket(orig, i), 1); - if (!n) - continue; - for (j = 0; j < n->pos; j++) { - if (!test_bit(j, n->used)) + for (r = 0; r < ahash_numof_locks(orig->htable_bits); r++) { + /* Expire may replace a hbucket with another one */ + rcu_read_lock_bh(); + for (i = ahash_bucket_start(r, orig->htable_bits); + i < ahash_bucket_end(r, orig->htable_bits); i++) { + n = __ipset_dereference(hbucket(orig, i)); + if (!n) continue; - data = ahash_data(n, j, dsize); + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, dsize); + if (SET_ELEM_EXPIRED(set, data)) + continue; #ifdef IP_SET_HASH_WITH_NETS - /* We have readers running parallel with us, - * so the live data cannot be modified. - */ - flags = 0; - memcpy(tmp, data, dsize); - data = tmp; - mtype_data_reset_flags(data, &flags); + /* We have readers running parallel with us, + * so the live data cannot be modified. + */ + flags = 0; + memcpy(tmp, data, dsize); + data = tmp; + mtype_data_reset_flags(data, &flags); #endif - key = HKEY(data, h->initval, htable_bits); - m = __ipset_dereference_protected(hbucket(t, key), 1); - if (!m) { - m = kzalloc(sizeof(*m) + + key = HKEY(data, h->initval, htable_bits); + m = __ipset_dereference(hbucket(t, key)); + nr = ahash_region(key, htable_bits); + if (!m) { + m = kzalloc(sizeof(*m) + AHASH_INIT_SIZE * dsize, GFP_ATOMIC); - if (!m) { - ret = -ENOMEM; - goto cleanup; - } - m->size = AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - RCU_INIT_POINTER(hbucket(t, key), m); - } else if (m->pos >= m->size) { - struct hbucket *ht; - - if (m->size >= AHASH_MAX(h)) { - ret = -EAGAIN; - } else { - ht = kzalloc(sizeof(*ht) + + if (!m) { + ret = -ENOMEM; + goto cleanup; + } + m->size = AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + RCU_INIT_POINTER(hbucket(t, key), m); + } else if (m->pos >= m->size) { + struct hbucket *ht; + + if (m->size >= AHASH_MAX(h)) { + ret = -EAGAIN; + } else { + ht = kzalloc(sizeof(*ht) + (m->size + AHASH_INIT_SIZE) * dsize, GFP_ATOMIC); - if (!ht) - ret = -ENOMEM; + if (!ht) + ret = -ENOMEM; + } + if (ret < 0) + goto cleanup; + memcpy(ht, m, sizeof(struct hbucket) + + m->size * dsize); + ht->size = m->size + AHASH_INIT_SIZE; + t->hregion[nr].ext_size += + ext_size(AHASH_INIT_SIZE, + dsize); + kfree(m); + m = ht; + RCU_INIT_POINTER(hbucket(t, key), ht); } - if (ret < 0) - goto cleanup; - memcpy(ht, m, sizeof(struct hbucket) + - m->size * dsize); - ht->size = m->size + AHASH_INIT_SIZE; - extsize += ext_size(AHASH_INIT_SIZE, dsize); - kfree(m); - m = ht; - RCU_INIT_POINTER(hbucket(t, key), ht); - } - d = ahash_data(m, m->pos, dsize); - memcpy(d, data, dsize); - set_bit(m->pos++, m->used); + d = ahash_data(m, m->pos, dsize); + memcpy(d, data, dsize); + set_bit(m->pos++, m->used); + t->hregion[nr].elements++; #ifdef IP_SET_HASH_WITH_NETS - mtype_data_reset_flags(d, &flags); + mtype_data_reset_flags(d, &flags); #endif + } } + rcu_read_unlock_bh(); } - rcu_assign_pointer(h->table, t); - set->ext_size = extsize; - spin_unlock_bh(&set->lock); + /* There can't be any other writer. */ + rcu_assign_pointer(h->table, t); /* Give time to other readers of the set */ synchronize_rcu(); pr_debug("set %s resized from %u (%p) to %u (%p)\n", set->name, orig->htable_bits, orig, t->htable_bits, t); - /* If there's nobody else dumping the table, destroy it */ + /* Add/delete elements processed by the SET target during resize. + * Kernel-side add cannot trigger a resize and userspace actions + * are serialized by the mutex. + */ + list_for_each_safe(l, lt, &h->ad) { + x = list_entry(l, struct mtype_resize_ad, list); + if (x->ad == IPSET_ADD) { + mtype_add(set, &x->d, &x->ext, &x->mext, x->flags); + } else { + mtype_del(set, &x->d, NULL, NULL, 0); + } + list_del(l); + kfree(l); + } + /* If there's nobody else using the table, destroy it */ if (atomic_dec_and_test(&orig->uref)) { pr_debug("Table destroy by resize %p\n", orig); mtype_ahash_destroy(set, orig, false); @@ -678,15 +811,44 @@ out: return ret; cleanup: + rcu_read_unlock_bh(); atomic_set(&orig->ref, 0); atomic_dec(&orig->uref); - spin_unlock_bh(&set->lock); mtype_ahash_destroy(set, t, false); if (ret == -EAGAIN) goto retry; goto out; } +/* Get the current number of elements and ext_size in the set */ +static void +mtype_ext_size(struct ip_set *set, u32 *elements, size_t *ext_size) +{ + struct htype *h = set->data; + const struct htable *t; + u32 i, j, r; + struct hbucket *n; + struct mtype_elem *data; + + t = rcu_dereference_bh(h->table); + for (r = 0; r < ahash_numof_locks(t->htable_bits); r++) { + for (i = ahash_bucket_start(r, t->htable_bits); + i < ahash_bucket_end(r, t->htable_bits); i++) { + n = rcu_dereference_bh(hbucket(t, i)); + if (!n) + continue; + for (j = 0; j < n->pos; j++) { + if (!test_bit(j, n->used)) + continue; + data = ahash_data(n, j, set->dsize); + if (!SET_ELEM_EXPIRED(set, data)) + (*elements)++; + } + } + *ext_size += t->hregion[r].ext_size; + } +} + /* Add an element to a hash and update the internal counters when succeeded, * otherwise report the proper error code. */ @@ -699,32 +861,49 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n, *old = ERR_PTR(-ENOENT); - int i, j = -1; + int i, j = -1, ret; bool flag_exist = flags & IPSET_FLAG_EXIST; bool deleted = false, forceadd = false, reuse = false; - u32 key, multi = 0; + u32 r, key, multi = 0, elements, maxelem; - if (set->elements >= h->maxelem) { - if (SET_WITH_TIMEOUT(set)) - /* FIXME: when set is full, we slow down here */ - mtype_expire(set, h); - if (set->elements >= h->maxelem && SET_WITH_FORCEADD(set)) + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); + key = HKEY(value, h->initval, t->htable_bits); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + elements = t->hregion[r].elements; + maxelem = t->maxelem; + if (elements >= maxelem) { + u32 e; + if (SET_WITH_TIMEOUT(set)) { + rcu_read_unlock_bh(); + mtype_gc_do(set, h, t, r); + rcu_read_lock_bh(); + } + maxelem = h->maxelem; + elements = 0; + for (e = 0; e < ahash_numof_locks(t->htable_bits); e++) + elements += t->hregion[e].elements; + if (elements >= maxelem && SET_WITH_FORCEADD(set)) forceadd = true; } + rcu_read_unlock_bh(); - t = ipset_dereference_protected(h->table, set); - key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) { - if (forceadd || set->elements >= h->maxelem) + if (forceadd || elements >= maxelem) goto set_full; old = NULL; n = kzalloc(sizeof(*n) + AHASH_INIT_SIZE * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } n->size = AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); goto copy_elem; } for (i = 0; i < n->pos; i++) { @@ -738,38 +917,37 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, } data = ahash_data(n, i, set->dsize); if (mtype_data_equal(data, d, &multi)) { - if (flag_exist || - (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)))) { + if (flag_exist || SET_ELEM_EXPIRED(set, data)) { /* Just the extensions could be overwritten */ j = i; goto overwrite_extensions; } - return -IPSET_ERR_EXIST; + ret = -IPSET_ERR_EXIST; + goto unlock; } /* Reuse first timed out entry */ - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set)) && - j == -1) { + if (SET_ELEM_EXPIRED(set, data) && j == -1) { j = i; reuse = true; } } if (reuse || forceadd) { + if (j == -1) + j = 0; data = ahash_data(n, j, set->dsize); if (!deleted) { #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_del_cidr(h, + mtype_del_cidr(set, h, NCIDR_PUT(DCIDR_GET(data->cidr, i)), i); #endif ip_set_ext_destroy(set, data); - set->elements--; + t->hregion[r].elements--; } goto copy_data; } - if (set->elements >= h->maxelem) + if (elements >= maxelem) goto set_full; /* Create a new slot */ if (n->pos >= n->size) { @@ -777,28 +955,32 @@ mtype_add(struct ip_set *set, void *value, const struct ip_set_ext *ext, if (n->size >= AHASH_MAX(h)) { /* Trigger rehashing */ mtype_data_next(&h->next, d); - return -EAGAIN; + ret = -EAGAIN; + goto resize; } old = n; n = kzalloc(sizeof(*n) + (old->size + AHASH_INIT_SIZE) * set->dsize, GFP_ATOMIC); - if (!n) - return -ENOMEM; + if (!n) { + ret = -ENOMEM; + goto unlock; + } memcpy(n, old, sizeof(struct hbucket) + old->size * set->dsize); n->size = old->size + AHASH_INIT_SIZE; - set->ext_size += ext_size(AHASH_INIT_SIZE, set->dsize); + t->hregion[r].ext_size += + ext_size(AHASH_INIT_SIZE, set->dsize); } copy_elem: j = n->pos++; data = ahash_data(n, j, set->dsize); copy_data: - set->elements++; + t->hregion[r].elements++; #ifdef IP_SET_HASH_WITH_NETS for (i = 0; i < IPSET_NET_COUNT; i++) - mtype_add_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); + mtype_add_cidr(set, h, NCIDR_PUT(DCIDR_GET(d->cidr, i)), i); #endif memcpy(data, d, sizeof(struct mtype_elem)); overwrite_extensions: @@ -821,13 +1003,41 @@ overwrite_extensions: if (old) kfree_rcu(old, rcu); } + ret = 0; +resize: + spin_unlock_bh(&t->hregion[r].lock); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side add, save values */ + struct mtype_resize_ad *x; + + x = kzalloc(sizeof(struct mtype_resize_ad), GFP_ATOMIC); + if (!x) + /* Don't bother */ + goto out; + x->ad = IPSET_ADD; + memcpy(&x->d, value, sizeof(struct mtype_elem)); + memcpy(&x->ext, ext, sizeof(struct ip_set_ext)); + memcpy(&x->mext, mext, sizeof(struct ip_set_ext)); + x->flags = flags; + spin_lock_bh(&set->lock); + list_add_tail(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + goto out; - return 0; set_full: if (net_ratelimit()) pr_warn("Set %s is full, maxelem %u reached\n", - set->name, h->maxelem); - return -IPSET_ERR_HASH_FULL; + set->name, maxelem); + ret = -IPSET_ERR_HASH_FULL; +unlock: + spin_unlock_bh(&t->hregion[r].lock); +out: + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by add: %p\n", t); + mtype_ahash_destroy(set, t, false); + } + return ret; } /* Delete an element from the hash and free up space if possible. @@ -841,13 +1051,23 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, const struct mtype_elem *d = value; struct mtype_elem *data; struct hbucket *n; - int i, j, k, ret = -IPSET_ERR_EXIST; + struct mtype_resize_ad *x = NULL; + int i, j, k, r, ret = -IPSET_ERR_EXIST; u32 key, multi = 0; size_t dsize = set->dsize; - t = ipset_dereference_protected(h->table, set); + /* Userspace add and resize is excluded by the mutex. + * Kernespace add does not trigger resize. + */ + rcu_read_lock_bh(); + t = rcu_dereference_bh(h->table); key = HKEY(value, h->initval, t->htable_bits); - n = __ipset_dereference_protected(hbucket(t, key), 1); + r = ahash_region(key, t->htable_bits); + atomic_inc(&t->uref); + rcu_read_unlock_bh(); + + spin_lock_bh(&t->hregion[r].lock); + n = rcu_dereference_bh(hbucket(t, key)); if (!n) goto out; for (i = 0, k = 0; i < n->pos; i++) { @@ -858,8 +1078,7 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, data = ahash_data(n, i, dsize); if (!mtype_data_equal(data, d, &multi)) continue; - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(data, set))) + if (SET_ELEM_EXPIRED(set, data)) goto out; ret = 0; @@ -867,20 +1086,33 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, smp_mb__after_atomic(); if (i + 1 == n->pos) n->pos--; - set->elements--; + t->hregion[r].elements--; #ifdef IP_SET_HASH_WITH_NETS for (j = 0; j < IPSET_NET_COUNT; j++) - mtype_del_cidr(h, NCIDR_PUT(DCIDR_GET(d->cidr, j)), - j); + mtype_del_cidr(set, h, + NCIDR_PUT(DCIDR_GET(d->cidr, j)), j); #endif ip_set_ext_destroy(set, data); + if (atomic_read(&t->ref) && ext->target) { + /* Resize is in process and kernel side del, + * save values + */ + x = kzalloc(sizeof(struct mtype_resize_ad), + GFP_ATOMIC); + if (x) { + x->ad = IPSET_DEL; + memcpy(&x->d, value, + sizeof(struct mtype_elem)); + x->flags = flags; + } + } for (; i < n->pos; i++) { if (!test_bit(i, n->used)) k++; } if (n->pos == 0 && k == 0) { - set->ext_size -= ext_size(n->size, dsize); + t->hregion[r].ext_size -= ext_size(n->size, dsize); rcu_assign_pointer(hbucket(t, key), NULL); kfree_rcu(n, rcu); } else if (k >= AHASH_INIT_SIZE) { @@ -899,7 +1131,8 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, k++; } tmp->pos = k; - set->ext_size -= ext_size(AHASH_INIT_SIZE, dsize); + t->hregion[r].ext_size -= + ext_size(AHASH_INIT_SIZE, dsize); rcu_assign_pointer(hbucket(t, key), tmp); kfree_rcu(n, rcu); } @@ -907,6 +1140,16 @@ mtype_del(struct ip_set *set, void *value, const struct ip_set_ext *ext, } out: + spin_unlock_bh(&t->hregion[r].lock); + if (x) { + spin_lock_bh(&set->lock); + list_add(&x->list, &h->ad); + spin_unlock_bh(&set->lock); + } + if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { + pr_debug("Table destroy after resize by del: %p\n", t); + mtype_ahash_destroy(set, t, false); + } return ret; } @@ -992,6 +1235,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, int i, ret = 0; u32 key, multi = 0; + rcu_read_lock_bh(); t = rcu_dereference_bh(h->table); #ifdef IP_SET_HASH_WITH_NETS /* If we test an IP address and not a network address, @@ -1023,6 +1267,7 @@ mtype_test(struct ip_set *set, void *value, const struct ip_set_ext *ext, goto out; } out: + rcu_read_unlock_bh(); return ret; } @@ -1034,23 +1279,14 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) const struct htable *t; struct nlattr *nested; size_t memsize; + u32 elements = 0; + size_t ext_size = 0; u8 htable_bits; - /* If any members have expired, set->elements will be wrong - * mytype_expire function will update it with the right count. - * we do not hold set->lock here, so grab it first. - * set->elements can still be incorrect in the case of a huge set, - * because elements might time out during the listing. - */ - if (SET_WITH_TIMEOUT(set)) { - spin_lock_bh(&set->lock); - mtype_expire(set, h); - spin_unlock_bh(&set->lock); - } - rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); - memsize = mtype_ahash_memsize(h, t) + set->ext_size; + t = rcu_dereference_bh(h->table); + mtype_ext_size(set, &elements, &ext_size); + memsize = mtype_ahash_memsize(h, t) + ext_size + set->ext_size; htable_bits = t->htable_bits; rcu_read_unlock_bh(); @@ -1072,7 +1308,7 @@ mtype_head(struct ip_set *set, struct sk_buff *skb) #endif if (nla_put_net32(skb, IPSET_ATTR_REFERENCES, htonl(set->ref)) || nla_put_net32(skb, IPSET_ATTR_MEMSIZE, htonl(memsize)) || - nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(set->elements))) + nla_put_net32(skb, IPSET_ATTR_ELEMENTS, htonl(elements))) goto nla_put_failure; if (unlikely(ip_set_put_flags(skb, set))) goto nla_put_failure; @@ -1092,15 +1328,15 @@ mtype_uref(struct ip_set *set, struct netlink_callback *cb, bool start) if (start) { rcu_read_lock_bh(); - t = rcu_dereference_bh_nfnl(h->table); + t = ipset_dereference_bh_nfnl(h->table); atomic_inc(&t->uref); cb->args[IPSET_CB_PRIVATE] = (unsigned long)t; rcu_read_unlock_bh(); } else if (cb->args[IPSET_CB_PRIVATE]) { t = (struct htable *)cb->args[IPSET_CB_PRIVATE]; if (atomic_dec_and_test(&t->uref) && atomic_read(&t->ref)) { - /* Resizing didn't destroy the hash table */ - pr_debug("Table destroy by dump: %p\n", t); + pr_debug("Table destroy after resize " + " by dump: %p\n", t); mtype_ahash_destroy(set, t, false); } cb->args[IPSET_CB_PRIVATE] = 0; @@ -1142,8 +1378,7 @@ mtype_list(const struct ip_set *set, if (!test_bit(i, n->used)) continue; e = ahash_data(n, i, set->dsize); - if (SET_WITH_TIMEOUT(set) && - ip_set_timeout_expired(ext_timeout(e, set))) + if (SET_ELEM_EXPIRED(set, e)) continue; pr_debug("list hash %lu hbucket %p i %u, data %p\n", cb->args[IPSET_CB_ARG0], n, i, e); @@ -1209,6 +1444,7 @@ static const struct ip_set_type_variant mtype_variant = { .uref = mtype_uref, .resize = mtype_resize, .same_set = mtype_same_set, + .region_lock = true, }; #ifdef IP_SET_EMIT_CREATE @@ -1227,6 +1463,7 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, size_t hsize; struct htype *h; struct htable *t; + u32 i; pr_debug("Create set %s with family %s\n", set->name, set->family == NFPROTO_IPV4 ? "inet" : "inet6"); @@ -1295,6 +1532,15 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, kfree(h); return -ENOMEM; } + t->hregion = ip_set_alloc(ahash_sizeof_regions(hbits)); + if (!t->hregion) { + ip_set_free(t); + kfree(h); + return -ENOMEM; + } + h->gc.set = set; + for (i = 0; i < ahash_numof_locks(hbits); i++) + spin_lock_init(&t->hregion[i].lock); h->maxelem = maxelem; #ifdef IP_SET_HASH_WITH_NETMASK h->netmask = netmask; @@ -1305,9 +1551,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, get_random_bytes(&h->initval, sizeof(h->initval)); t->htable_bits = hbits; + t->maxelem = h->maxelem / ahash_numof_locks(hbits); RCU_INIT_POINTER(h->table, t); - h->set = set; + INIT_LIST_HEAD(&h->ad); set->data = h; #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) { @@ -1330,12 +1577,10 @@ IPSET_TOKEN(HTYPE, _create)(struct net *net, struct ip_set *set, #ifndef IP_SET_PROTO_UNDEF if (set->family == NFPROTO_IPV4) #endif - IPSET_TOKEN(HTYPE, 4_gc_init)(set, - IPSET_TOKEN(HTYPE, 4_gc)); + IPSET_TOKEN(HTYPE, 4_gc_init)(&h->gc); #ifndef IP_SET_PROTO_UNDEF else - IPSET_TOKEN(HTYPE, 6_gc_init)(set, - IPSET_TOKEN(HTYPE, 6_gc)); + IPSET_TOKEN(HTYPE, 6_gc_init)(&h->gc); #endif } pr_debug("create %s hashsize %u (%u) maxelem %u: %p(%p)\n", diff --git a/net/netfilter/ipset/ip_set_hash_ipmac.c b/net/netfilter/ipset/ip_set_hash_ipmac.c index 24d8f4df4230..4ce563eb927d 100644 --- a/net/netfilter/ipset/ip_set_hash_ipmac.c +++ b/net/netfilter/ipset/ip_set_hash_ipmac.c @@ -209,7 +209,7 @@ hash_ipmac6_kadt(struct ip_set *set, const struct sk_buff *skb, (skb_mac_header(skb) + ETH_HLEN) > skb->data) return -EINVAL; - if (opt->flags & IPSET_DIM_ONE_SRC) + if (opt->flags & IPSET_DIM_TWO_SRC) ether_addr_copy(e.ether, eth_hdr(skb)->h_source); else ether_addr_copy(e.ether, eth_hdr(skb)->h_dest); diff --git a/net/netfilter/ipset/ip_set_hash_net.c b/net/netfilter/ipset/ip_set_hash_net.c index 06c91e49bf25..471e69928e8e 100644 --- a/net/netfilter/ipset/ip_set_hash_net.c +++ b/net/netfilter/ipset/ip_set_hash_net.c @@ -369,6 +369,7 @@ static struct ip_set_type hash_net_type __read_mostly = { [IPSET_ATTR_IP_TO] = { .type = NLA_NESTED }, [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipset/ip_set_hash_netnet.c b/net/netfilter/ipset/ip_set_hash_netnet.c index 832e4f5491cb..975ba1892ae4 100644 --- a/net/netfilter/ipset/ip_set_hash_netnet.c +++ b/net/netfilter/ipset/ip_set_hash_netnet.c @@ -476,6 +476,7 @@ static struct ip_set_type hash_netnet_type __read_mostly = { [IPSET_ATTR_CIDR] = { .type = NLA_U8 }, [IPSET_ATTR_CIDR2] = { .type = NLA_U8 }, [IPSET_ATTR_TIMEOUT] = { .type = NLA_U32 }, + [IPSET_ATTR_LINENO] = { .type = NLA_U32 }, [IPSET_ATTR_CADT_FLAGS] = { .type = NLA_U32 }, [IPSET_ATTR_BYTES] = { .type = NLA_U64 }, [IPSET_ATTR_PACKETS] = { .type = NLA_U64 }, diff --git a/net/netfilter/ipset/ip_set_list_set.c b/net/netfilter/ipset/ip_set_list_set.c index 8ada318bf09d..eb9a8d97e65a 100644 --- a/net/netfilter/ipset/ip_set_list_set.c +++ b/net/netfilter/ipset/ip_set_list_set.c @@ -60,7 +60,7 @@ list_set_ktest(struct ip_set *set, const struct sk_buff *skb, /* Don't lookup sub-counters at all */ opt->cmdflags &= ~IPSET_FLAG_MATCH_COUNTERS; if (opt->cmdflags & IPSET_FLAG_SKIP_SUBCOUNTER_UPDATE) - opt->cmdflags &= ~IPSET_FLAG_SKIP_COUNTER_UPDATE; + opt->cmdflags |= IPSET_FLAG_SKIP_COUNTER_UPDATE; list_for_each_entry_rcu(e, &map->members, list) { ret = ip_set_test(e->id, skb, par, opt); if (ret <= 0) diff --git a/net/netfilter/ipvs/ip_vs_app.c b/net/netfilter/ipvs/ip_vs_app.c index bfd4365a8d73..fce55eacf583 100644 --- a/net/netfilter/ipvs/ip_vs_app.c +++ b/net/netfilter/ipvs/ip_vs_app.c @@ -193,21 +193,29 @@ struct ip_vs_app *register_ip_vs_app(struct netns_ipvs *ipvs, struct ip_vs_app * mutex_lock(&__ip_vs_app_mutex); + /* increase the module use count */ + if (!ip_vs_use_count_inc()) { + err = -ENOENT; + goto out_unlock; + } + list_for_each_entry(a, &ipvs->app_list, a_list) { if (!strcmp(app->name, a->name)) { err = -EEXIST; + /* decrease the module use count */ + ip_vs_use_count_dec(); goto out_unlock; } } a = kmemdup(app, sizeof(*app), GFP_KERNEL); if (!a) { err = -ENOMEM; + /* decrease the module use count */ + ip_vs_use_count_dec(); goto out_unlock; } INIT_LIST_HEAD(&a->incs_list); list_add(&a->a_list, &ipvs->app_list); - /* increase the module use count */ - ip_vs_use_count_inc(); out_unlock: mutex_unlock(&__ip_vs_app_mutex); diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index d5103a9eb302..c85752f8bd1a 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1955,14 +1955,14 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { - bool uses_ct = false, resched = false; + bool old_ct = false, resched = false; if (unlikely(sysctl_expire_nodest_conn(ipvs)) && cp->dest && unlikely(!atomic_read(&cp->dest->weight))) { resched = true; - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); } else if (is_new_conn_expected(cp, conn_reuse_mode)) { - uses_ct = ip_vs_conn_uses_conntrack(cp, skb); + old_ct = ip_vs_conn_uses_old_conntrack(cp, skb); if (!atomic_read(&cp->n_control)) { resched = true; } else { @@ -1970,15 +1970,17 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int * that uses conntrack while it is still * referenced by controlled connection(s). */ - resched = !uses_ct; + resched = !old_ct; } } if (resched) { + if (!old_ct) + cp->flags &= ~IP_VS_CONN_F_NFCT; if (!atomic_read(&cp->n_control)) ip_vs_conn_expire_now(cp); __ip_vs_conn_put(cp); - if (uses_ct) + if (old_ct) return NF_DROP; cp = NULL; } diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 741d91aa4a8d..2e3b59d79ffb 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -93,7 +93,6 @@ static bool __ip_vs_addr_is_local_v6(struct net *net, static void update_defense_level(struct netns_ipvs *ipvs) { struct sysinfo i; - static int old_secure_tcp = 0; int availmem; int nomem; int to_change = -1; @@ -174,35 +173,35 @@ static void update_defense_level(struct netns_ipvs *ipvs) spin_lock(&ipvs->securetcp_lock); switch (ipvs->sysctl_secure_tcp) { case 0: - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; break; case 1: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; ipvs->sysctl_secure_tcp = 2; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; } break; case 2: if (nomem) { - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; } else { - if (old_secure_tcp >= 2) + if (ipvs->old_secure_tcp >= 2) to_change = 0; ipvs->sysctl_secure_tcp = 1; } break; case 3: - if (old_secure_tcp < 2) + if (ipvs->old_secure_tcp < 2) to_change = 1; break; } - old_secure_tcp = ipvs->sysctl_secure_tcp; + ipvs->old_secure_tcp = ipvs->sysctl_secure_tcp; if (to_change >= 0) ip_vs_protocol_timeout_change(ipvs, ipvs->sysctl_secure_tcp > 1); @@ -1217,7 +1216,8 @@ ip_vs_add_service(struct netns_ipvs *ipvs, struct ip_vs_service_user_kern *u, struct ip_vs_service *svc = NULL; /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOPROTOOPT; /* Lookup the scheduler by 'u->sched_name' */ if (strcmp(u->sched_name, "none")) { @@ -2377,9 +2377,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) if (copy_from_user(arg, user, len) != 0) return -EFAULT; - /* increase the module use count */ - ip_vs_use_count_inc(); - /* Handle daemons since they have another lock */ if (cmd == IP_VS_SO_SET_STARTDAEMON || cmd == IP_VS_SO_SET_STOPDAEMON) { @@ -2392,13 +2389,13 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) ret = -EINVAL; if (strscpy(cfg.mcast_ifn, dm->mcast_ifn, sizeof(cfg.mcast_ifn)) <= 0) - goto out_dec; + return ret; cfg.syncid = dm->syncid; ret = start_sync_thread(ipvs, &cfg, dm->state); } else { ret = stop_sync_thread(ipvs, dm->state); } - goto out_dec; + return ret; } mutex_lock(&__ip_vs_mutex); @@ -2493,10 +2490,6 @@ do_ip_vs_set_ctl(struct sock *sk, int cmd, void __user *user, unsigned int len) out_unlock: mutex_unlock(&__ip_vs_mutex); - out_dec: - /* decrease the module use count */ - ip_vs_use_count_dec(); - return ret; } diff --git a/net/netfilter/ipvs/ip_vs_pe.c b/net/netfilter/ipvs/ip_vs_pe.c index 8e104dff7abc..166c669f0763 100644 --- a/net/netfilter/ipvs/ip_vs_pe.c +++ b/net/netfilter/ipvs/ip_vs_pe.c @@ -68,7 +68,8 @@ int register_ip_vs_pe(struct ip_vs_pe *pe) struct ip_vs_pe *tmp; /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOENT; mutex_lock(&ip_vs_pe_mutex); /* Make sure that the pe with this name doesn't exist diff --git a/net/netfilter/ipvs/ip_vs_sched.c b/net/netfilter/ipvs/ip_vs_sched.c index 2f9d5cd5daee..d4903723be7e 100644 --- a/net/netfilter/ipvs/ip_vs_sched.c +++ b/net/netfilter/ipvs/ip_vs_sched.c @@ -179,7 +179,8 @@ int register_ip_vs_scheduler(struct ip_vs_scheduler *scheduler) } /* increase the module use count */ - ip_vs_use_count_inc(); + if (!ip_vs_use_count_inc()) + return -ENOENT; mutex_lock(&ip_vs_sched_mutex); diff --git a/net/netfilter/ipvs/ip_vs_sync.c b/net/netfilter/ipvs/ip_vs_sync.c index a4a78c4b06de..0c1bc654245c 100644 --- a/net/netfilter/ipvs/ip_vs_sync.c +++ b/net/netfilter/ipvs/ip_vs_sync.c @@ -1717,6 +1717,8 @@ static int sync_thread_backup(void *data) { struct ip_vs_sync_thread_data *tinfo = data; struct netns_ipvs *ipvs = tinfo->ipvs; + struct sock *sk = tinfo->sock->sk; + struct udp_sock *up = udp_sk(sk); int len; pr_info("sync thread started: state = BACKUP, mcast_ifn = %s, " @@ -1724,12 +1726,14 @@ static int sync_thread_backup(void *data) ipvs->bcfg.mcast_ifn, ipvs->bcfg.syncid, tinfo->id); while (!kthread_should_stop()) { - wait_event_interruptible(*sk_sleep(tinfo->sock->sk), - !skb_queue_empty(&tinfo->sock->sk->sk_receive_queue) - || kthread_should_stop()); + wait_event_interruptible(*sk_sleep(sk), + !skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue) || + kthread_should_stop()); /* do we have data now? */ - while (!skb_queue_empty(&(tinfo->sock->sk->sk_receive_queue))) { + while (!skb_queue_empty_lockless(&sk->sk_receive_queue) || + !skb_queue_empty_lockless(&up->reader_queue)) { len = ip_vs_receive(tinfo->sock, tinfo->buf, ipvs->bcfg.sync_maxlen); if (len <= 0) { @@ -1762,6 +1766,10 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, IP_VS_DBG(7, "Each ip_vs_sync_conn entry needs %zd bytes\n", sizeof(struct ip_vs_sync_conn_v0)); + /* increase the module use count */ + if (!ip_vs_use_count_inc()) + return -ENOPROTOOPT; + /* Do not hold one mutex and then to block on another */ for (;;) { rtnl_lock(); @@ -1892,9 +1900,6 @@ int start_sync_thread(struct netns_ipvs *ipvs, struct ipvs_sync_daemon_cfg *c, mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); - /* increase the module use count */ - ip_vs_use_count_inc(); - return 0; out: @@ -1924,11 +1929,17 @@ out: } kfree(ti); } + + /* decrease the module use count */ + ip_vs_use_count_dec(); return result; out_early: mutex_unlock(&ipvs->sync_mutex); rtnl_unlock(); + + /* decrease the module use count */ + ip_vs_use_count_dec(); return result; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index e101eda05d55..0ee2c15b049b 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -206,7 +206,7 @@ static inline void maybe_update_pmtu(int skb_af, struct sk_buff *skb, int mtu) struct rtable *ort = skb_rtable(skb); if (!skb->dev && sk && sk_fullsock(sk)) - ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu); + ort->dst.ops->update_pmtu(&ort->dst, sk, NULL, mtu, true); } static inline bool ensure_mtu_is_adequate(struct netns_ipvs *ipvs, int skb_af, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index e343a030ec26..63618729d84d 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -1381,9 +1381,9 @@ __nf_conntrack_alloc(struct net *net, ct->status = 0; ct->timeout = 0; write_pnet(&ct->ct_net, net); - memset(&ct->__nfct_init_offset[0], 0, + memset(&ct->__nfct_init_offset, 0, offsetof(struct nf_conn, proto) - - offsetof(struct nf_conn, __nfct_init_offset[0])); + offsetof(struct nf_conn, __nfct_init_offset)); nf_ct_zone_add(ct, zone); @@ -1792,8 +1792,8 @@ void __nf_ct_refresh_acct(struct nf_conn *ct, if (nf_ct_is_confirmed(ct)) extra_jiffies += nfct_time_stamp; - if (ct->timeout != extra_jiffies) - ct->timeout = extra_jiffies; + if (READ_ONCE(ct->timeout) != extra_jiffies) + WRITE_ONCE(ct->timeout, extra_jiffies); acct: if (do_acct) nf_ct_acct_update(ct, ctinfo, skb->len); @@ -1881,22 +1881,18 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) nf_conntrack_get(skb_nfct(nskb)); } -static int nf_conntrack_update(struct net *net, struct sk_buff *skb) +static int __nf_conntrack_update(struct net *net, struct sk_buff *skb, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) { struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; - enum ip_conntrack_info ctinfo; struct nf_nat_hook *nat_hook; unsigned int status; - struct nf_conn *ct; int dataoff; u16 l3num; u8 l4num; - ct = nf_ct_get(skb, &ctinfo); - if (!ct || nf_ct_is_confirmed(ct)) - return 0; - l3num = nf_ct_l3num(ct); dataoff = get_l4proto(skb, skb_network_offset(skb), l3num, &l4num); @@ -1953,6 +1949,78 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) return 0; } +/* This packet is coming from userspace via nf_queue, complete the packet + * processing after the helper invocation in nf_confirm(). + */ +static int nf_confirm_cthelper(struct sk_buff *skb, struct nf_conn *ct, + enum ip_conntrack_info ctinfo) +{ + const struct nf_conntrack_helper *helper; + const struct nf_conn_help *help; + int protoff; + + help = nfct_help(ct); + if (!help) + return 0; + + helper = rcu_dereference(help->helper); + if (!(helper->flags & NF_CT_HELPER_F_USERSPACE)) + return 0; + + switch (nf_ct_l3num(ct)) { + case NFPROTO_IPV4: + protoff = skb_network_offset(skb) + ip_hdrlen(skb); + break; +#if IS_ENABLED(CONFIG_IPV6) + case NFPROTO_IPV6: { + __be16 frag_off; + u8 pnum; + + pnum = ipv6_hdr(skb)->nexthdr; + protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, + &frag_off); + if (protoff < 0 || (frag_off & htons(~0x7)) != 0) + return 0; + break; + } +#endif + default: + return 0; + } + + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return -1; + } + } + + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb) == NF_DROP ? - 1 : 0; +} + +static int nf_conntrack_update(struct net *net, struct sk_buff *skb) +{ + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + int err; + + ct = nf_ct_get(skb, &ctinfo); + if (!ct) + return 0; + + if (!nf_ct_is_confirmed(ct)) { + err = __nf_conntrack_update(net, skb, ct, ctinfo); + if (err < 0) + return err; + + ct = nf_ct_get(skb, &ctinfo); + } + + return nf_confirm_cthelper(skb, ct, ctinfo); +} + static bool nf_conntrack_get_tuple_skb(struct nf_conntrack_tuple *dst_tuple, const struct sk_buff *skb) { diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1b77444d5b52..47eb42649639 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -3599,6 +3599,9 @@ static void __net_exit ctnetlink_net_exit_batch(struct list_head *net_exit_list) list_for_each_entry(net, net_exit_list, exit_list) ctnetlink_net_exit(net); + + /* wait for other cpus until they are done with ctnl_notifiers */ + synchronize_rcu(); } static struct pernet_operations ctnetlink_net_ops = { diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index b22042ad0fca..584c606e7fe0 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -72,24 +72,32 @@ EXPORT_SYMBOL_GPL(nf_nat_pptp_hook_expectfn); #if defined(DEBUG) || defined(CONFIG_DYNAMIC_DEBUG) /* PptpControlMessageType names */ -const char *const pptp_msg_name[] = { - "UNKNOWN_MESSAGE", - "START_SESSION_REQUEST", - "START_SESSION_REPLY", - "STOP_SESSION_REQUEST", - "STOP_SESSION_REPLY", - "ECHO_REQUEST", - "ECHO_REPLY", - "OUT_CALL_REQUEST", - "OUT_CALL_REPLY", - "IN_CALL_REQUEST", - "IN_CALL_REPLY", - "IN_CALL_CONNECT", - "CALL_CLEAR_REQUEST", - "CALL_DISCONNECT_NOTIFY", - "WAN_ERROR_NOTIFY", - "SET_LINK_INFO" +static const char *const pptp_msg_name_array[PPTP_MSG_MAX + 1] = { + [0] = "UNKNOWN_MESSAGE", + [PPTP_START_SESSION_REQUEST] = "START_SESSION_REQUEST", + [PPTP_START_SESSION_REPLY] = "START_SESSION_REPLY", + [PPTP_STOP_SESSION_REQUEST] = "STOP_SESSION_REQUEST", + [PPTP_STOP_SESSION_REPLY] = "STOP_SESSION_REPLY", + [PPTP_ECHO_REQUEST] = "ECHO_REQUEST", + [PPTP_ECHO_REPLY] = "ECHO_REPLY", + [PPTP_OUT_CALL_REQUEST] = "OUT_CALL_REQUEST", + [PPTP_OUT_CALL_REPLY] = "OUT_CALL_REPLY", + [PPTP_IN_CALL_REQUEST] = "IN_CALL_REQUEST", + [PPTP_IN_CALL_REPLY] = "IN_CALL_REPLY", + [PPTP_IN_CALL_CONNECT] = "IN_CALL_CONNECT", + [PPTP_CALL_CLEAR_REQUEST] = "CALL_CLEAR_REQUEST", + [PPTP_CALL_DISCONNECT_NOTIFY] = "CALL_DISCONNECT_NOTIFY", + [PPTP_WAN_ERROR_NOTIFY] = "WAN_ERROR_NOTIFY", + [PPTP_SET_LINK_INFO] = "SET_LINK_INFO" }; + +const char *pptp_msg_name(u_int16_t msg) +{ + if (msg > PPTP_MSG_MAX) + return pptp_msg_name_array[0]; + + return pptp_msg_name_array[msg]; +} EXPORT_SYMBOL(pptp_msg_name); #endif @@ -276,7 +284,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, typeof(nf_nat_pptp_hook_inbound) nf_nat_pptp_inbound; msg = ntohs(ctlh->messageType); - pr_debug("inbound control message %s\n", pptp_msg_name[msg]); + pr_debug("inbound control message %s\n", pptp_msg_name(msg)); switch (msg) { case PPTP_START_SESSION_REPLY: @@ -311,7 +319,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, pcid = pptpReq->ocack.peersCallID; if (info->pns_call_id != pcid) goto invalid; - pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name[msg], + pr_debug("%s, CID=%X, PCID=%X\n", pptp_msg_name(msg), ntohs(cid), ntohs(pcid)); if (pptpReq->ocack.resultCode == PPTP_OUTCALL_CONNECT) { @@ -328,7 +336,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, goto invalid; cid = pptpReq->icreq.callID; - pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid)); info->cstate = PPTP_CALL_IN_REQ; info->pac_call_id = cid; break; @@ -347,7 +355,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, if (info->pns_call_id != pcid) goto invalid; - pr_debug("%s, PCID=%X\n", pptp_msg_name[msg], ntohs(pcid)); + pr_debug("%s, PCID=%X\n", pptp_msg_name(msg), ntohs(pcid)); info->cstate = PPTP_CALL_IN_CONF; /* we expect a GRE connection from PAC to PNS */ @@ -357,7 +365,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, case PPTP_CALL_DISCONNECT_NOTIFY: /* server confirms disconnect */ cid = pptpReq->disc.callID; - pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid)); info->cstate = PPTP_CALL_NONE; /* untrack this call id, unexpect GRE packets */ @@ -384,7 +392,7 @@ pptp_inbound_pkt(struct sk_buff *skb, unsigned int protoff, invalid: pr_debug("invalid %s: type=%d cid=%u pcid=%u " "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0], + pptp_msg_name(msg), msg, ntohs(cid), ntohs(pcid), info->cstate, info->sstate, ntohs(info->pns_call_id), ntohs(info->pac_call_id)); return NF_ACCEPT; @@ -404,7 +412,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, typeof(nf_nat_pptp_hook_outbound) nf_nat_pptp_outbound; msg = ntohs(ctlh->messageType); - pr_debug("outbound control message %s\n", pptp_msg_name[msg]); + pr_debug("outbound control message %s\n", pptp_msg_name(msg)); switch (msg) { case PPTP_START_SESSION_REQUEST: @@ -426,7 +434,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, info->cstate = PPTP_CALL_OUT_REQ; /* track PNS call id */ cid = pptpReq->ocreq.callID; - pr_debug("%s, CID=%X\n", pptp_msg_name[msg], ntohs(cid)); + pr_debug("%s, CID=%X\n", pptp_msg_name(msg), ntohs(cid)); info->pns_call_id = cid; break; @@ -440,7 +448,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, pcid = pptpReq->icack.peersCallID; if (info->pac_call_id != pcid) goto invalid; - pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name[msg], + pr_debug("%s, CID=%X PCID=%X\n", pptp_msg_name(msg), ntohs(cid), ntohs(pcid)); if (pptpReq->icack.resultCode == PPTP_INCALL_ACCEPT) { @@ -480,7 +488,7 @@ pptp_outbound_pkt(struct sk_buff *skb, unsigned int protoff, invalid: pr_debug("invalid %s: type=%d cid=%u pcid=%u " "cstate=%d sstate=%d pns_cid=%u pac_cid=%u\n", - msg <= PPTP_MSG_MAX ? pptp_msg_name[msg] : pptp_msg_name[0], + pptp_msg_name(msg), msg, ntohs(cid), ntohs(pcid), info->cstate, info->sstate, ntohs(info->pns_call_id), ntohs(info->pac_call_id)); return NF_ACCEPT; diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index b6b14db3955b..b3f4a334f9d7 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -677,6 +677,9 @@ static int dccp_timeout_nlattr_to_obj(struct nlattr *tb[], unsigned int *timeouts = data; int i; + if (!timeouts) + timeouts = dn->dccp_timeout; + /* set default DCCP timeouts. */ for (i=0; i<CT_DCCP_MAX; i++) timeouts[i] = dn->dccp_timeout[i]; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index 522c08c23600..8ddcd5100638 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -114,7 +114,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { { /* ORIGINAL */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ -/* init */ {sCW, sCW, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, +/* init */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCW, sHA}, /* init_ack */ {sCL, sCL, sCW, sCE, sES, sSS, sSR, sSA, sCL, sHA}, /* abort */ {sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sCL}, /* shutdown */ {sCL, sCL, sCW, sCE, sSS, sSS, sSR, sSA, sCL, sSS}, @@ -130,7 +130,7 @@ static const u8 sctp_conntracks[2][11][SCTP_CONNTRACK_MAX] = { /* REPLY */ /* sNO, sCL, sCW, sCE, sES, sSS, sSR, sSA, sHS, sHA */ /* init */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA},/* INIT in sCL Big TODO */ -/* init_ack */ {sIV, sCL, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, +/* init_ack */ {sIV, sCW, sCW, sCE, sES, sSS, sSR, sSA, sIV, sHA}, /* abort */ {sIV, sCL, sCL, sCL, sCL, sCL, sCL, sCL, sIV, sCL}, /* shutdown */ {sIV, sCL, sCW, sCE, sSR, sSS, sSR, sSA, sIV, sSR}, /* shutdown_ack */ {sIV, sCL, sCW, sCE, sES, sSA, sSA, sSA, sIV, sHA}, @@ -316,7 +316,7 @@ sctp_new(struct nf_conn *ct, const struct sk_buff *skb, ct->proto.sctp.vtag[IP_CT_DIR_REPLY] = sh->vtag; } - ct->proto.sctp.state = new_state; + ct->proto.sctp.state = SCTP_CONNTRACK_NONE; } return true; @@ -594,6 +594,9 @@ static int sctp_timeout_nlattr_to_obj(struct nlattr *tb[], struct nf_sctp_net *sn = nf_sctp_pernet(net); int i; + if (!timeouts) + timeouts = sn->timeouts; + /* set default SCTP timeouts. */ for (i=0; i<SCTP_CONNTRACK_MAX; i++) timeouts[i] = sn->timeouts[i]; diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index 0006503d2da9..199e00cc6ec3 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -411,7 +411,7 @@ static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu + 1; return per_cpu_ptr(net->ct.stat, cpu); } - + (*pos)++; return NULL; } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 55106bebf2b5..750fd60dad6f 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -202,6 +202,8 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, nf_flow_offload_rhash_params); @@ -218,7 +220,6 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index b9e7dd6e60ce..e92aa6b7eb80 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -189,6 +189,7 @@ static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, if (!pskb_may_pull(skb, thoff + sizeof(*ports))) return -1; + iph = ip_hdr(skb); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v4.s_addr = iph->saddr; @@ -449,6 +450,7 @@ static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, if (!pskb_may_pull(skb, thoff + sizeof(*ports))) return -1; + ip6h = ipv6_hdr(skb); ports = (struct flow_ports *)(skb_network_header(skb) + thoff); tuple->src_v6 = ip6h->saddr; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 83a24cc5753b..28d3313db8f9 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -68,15 +68,13 @@ static bool udp_manip_pkt(struct sk_buff *skb, enum nf_nat_manip_type maniptype) { struct udphdr *hdr; - bool do_csum; if (!skb_make_writable(skb, hdroff + sizeof(*hdr))) return false; hdr = (struct udphdr *)(skb->data + hdroff); - do_csum = hdr->check || skb->ip_summed == CHECKSUM_PARTIAL; + __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, !!hdr->check); - __udp_manip_pkt(skb, iphdroff, hdr, tuple, maniptype, do_csum); return true; } @@ -233,6 +231,19 @@ icmp_manip_pkt(struct sk_buff *skb, return false; hdr = (struct icmphdr *)(skb->data + hdroff); + switch (hdr->type) { + case ICMP_ECHO: + case ICMP_ECHOREPLY: + case ICMP_TIMESTAMP: + case ICMP_TIMESTAMPREPLY: + case ICMP_INFO_REQUEST: + case ICMP_INFO_REPLY: + case ICMP_ADDRESS: + case ICMP_ADDRESSREPLY: + break; + default: + return true; + } inet_proto_csum_replace2(&hdr->checksum, skb, hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; @@ -1022,8 +1033,8 @@ int nf_nat_inet_register_fn(struct net *net, const struct nf_hook_ops *ops) ret = nf_nat_register_fn(net, NFPROTO_IPV4, ops, nf_nat_ipv4_ops, ARRAY_SIZE(nf_nat_ipv4_ops)); if (ret) - nf_nat_ipv6_unregister_fn(net, ops); - + nf_nat_unregister_fn(net, NFPROTO_IPV6, ops, + ARRAY_SIZE(nf_nat_ipv6_ops)); return ret; } EXPORT_SYMBOL_GPL(nf_nat_inet_register_fn); diff --git a/net/netfilter/nf_queue.c b/net/netfilter/nf_queue.c index 2c440015ff0c..3d8aca9ac06d 100644 --- a/net/netfilter/nf_queue.c +++ b/net/netfilter/nf_queue.c @@ -190,7 +190,7 @@ static int __nf_queue(struct sk_buff *skb, const struct nf_hook_state *state, goto err; } - if (!skb_dst_force(skb) && state->hook != NF_INET_PRE_ROUTING) { + if (skb_dst(skb) && !skb_dst_force(skb)) { status = -ENETDOWN; goto err; } diff --git a/net/netfilter/nf_synproxy_core.c b/net/netfilter/nf_synproxy_core.c index 8ce74ed985c0..969efcc725cb 100644 --- a/net/netfilter/nf_synproxy_core.c +++ b/net/netfilter/nf_synproxy_core.c @@ -270,7 +270,7 @@ static void *synproxy_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) *pos = cpu + 1; return per_cpu_ptr(snet->stats, cpu); } - + (*pos)++; return NULL; } diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 4d8714d78192..dd8d4bb1145c 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -21,6 +21,8 @@ #include <net/net_namespace.h> #include <net/sock.h> +#define NFT_MODULE_AUTOLOAD_LIMIT (MODULE_NAME_LEN - sizeof("nft-expr-255-")) + static LIST_HEAD(nf_tables_expressions); static LIST_HEAD(nf_tables_objects); static LIST_HEAD(nf_tables_flowtables); @@ -485,46 +487,70 @@ static inline u64 nf_tables_alloc_handle(struct nft_table *table) static const struct nft_chain_type *chain_type[NFPROTO_NUMPROTO][NFT_CHAIN_T_MAX]; static const struct nft_chain_type * +__nft_chain_type_get(u8 family, enum nft_chain_types type) +{ + if (family >= NFPROTO_NUMPROTO || + type >= NFT_CHAIN_T_MAX) + return NULL; + + return chain_type[family][type]; +} + +static const struct nft_chain_type * __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) { + const struct nft_chain_type *type; int i; for (i = 0; i < NFT_CHAIN_T_MAX; i++) { - if (chain_type[family][i] != NULL && - !nla_strcmp(nla, chain_type[family][i]->name)) - return chain_type[family][i]; + type = __nft_chain_type_get(family, i); + if (!type) + continue; + if (!nla_strcmp(nla, type->name)) + return type; } return NULL; } -/* - * Loading a module requires dropping mutex that guards the - * transaction. - * We first need to abort any pending transactions as once - * mutex is unlocked a different client could start a new - * transaction. It must not see any 'future generation' - * changes * as these changes will never happen. - */ -#ifdef CONFIG_MODULES -static int __nf_tables_abort(struct net *net); +struct nft_module_request { + struct list_head list; + char module[MODULE_NAME_LEN]; + bool done; +}; -static void nft_request_module(struct net *net, const char *fmt, ...) +#ifdef CONFIG_MODULES +static int nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; + struct nft_module_request *req; va_list args; int ret; - __nf_tables_abort(net); - va_start(args, fmt); ret = vsnprintf(module_name, MODULE_NAME_LEN, fmt, args); va_end(args); - if (WARN(ret >= MODULE_NAME_LEN, "truncated: '%s' (len %d)", module_name, ret)) - return; + if (ret >= MODULE_NAME_LEN) + return 0; - mutex_unlock(&net->nft.commit_mutex); - request_module("%s", module_name); - mutex_lock(&net->nft.commit_mutex); + list_for_each_entry(req, &net->nft.module_list, list) { + if (!strcmp(req->module, module_name)) { + if (req->done) + return 0; + + /* A request to load this module already exists. */ + return -EAGAIN; + } + } + + req = kmalloc(sizeof(*req), GFP_KERNEL); + if (!req) + return -ENOMEM; + + req->done = false; + strlcpy(req->module, module_name, MODULE_NAME_LEN); + list_add_tail(&req->list, &net->nft.module_list); + + return -EAGAIN; } #endif @@ -548,10 +574,9 @@ nf_tables_chain_type_lookup(struct net *net, const struct nlattr *nla, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (autoload) { - nft_request_module(net, "nft-chain-%u-%.*s", family, - nla_len(nla), (const char *)nla_data(nla)); - type = __nf_tables_chain_type_lookup(nla, family); - if (type != NULL) + if (nft_request_module(net, "nft-chain-%u-%.*s", family, + nla_len(nla), + (const char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -976,12 +1001,18 @@ static int nft_flush_table(struct nft_ctx *ctx) } list_for_each_entry_safe(flowtable, nft, &ctx->table->flowtables, list) { + if (!nft_is_active_next(ctx->net, flowtable)) + continue; + err = nft_delflowtable(ctx, flowtable); if (err < 0) goto out; } list_for_each_entry_safe(obj, ne, &ctx->table->objects, list) { + if (!nft_is_active_next(ctx->net, obj)) + continue; + err = nft_delobj(ctx, obj); if (err < 0) goto out; @@ -1084,11 +1115,8 @@ static void nf_tables_table_destroy(struct nft_ctx *ctx) void nft_register_chain_type(const struct nft_chain_type *ctype) { - if (WARN_ON(ctype->family >= NFPROTO_NUMPROTO)) - return; - nfnl_lock(NFNL_SUBSYS_NFTABLES); - if (WARN_ON(chain_type[ctype->family][ctype->type] != NULL)) { + if (WARN_ON(__nft_chain_type_get(ctype->family, ctype->type))) { nfnl_unlock(NFNL_SUBSYS_NFTABLES); return; } @@ -1172,7 +1200,8 @@ static const struct nla_policy nft_chain_policy[NFTA_CHAIN_MAX + 1] = { .len = NFT_CHAIN_MAXNAMELEN - 1 }, [NFTA_CHAIN_HOOK] = { .type = NLA_NESTED }, [NFTA_CHAIN_POLICY] = { .type = NLA_U32 }, - [NFTA_CHAIN_TYPE] = { .type = NLA_STRING }, + [NFTA_CHAIN_TYPE] = { .type = NLA_STRING, + .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_CHAIN_COUNTERS] = { .type = NLA_NESTED }, }; @@ -1545,7 +1574,10 @@ static int nft_chain_parse_hook(struct net *net, hook->num = ntohl(nla_get_be32(ha[NFTA_HOOK_HOOKNUM])); hook->priority = ntohl(nla_get_be32(ha[NFTA_HOOK_PRIORITY])); - type = chain_type[family][NFT_CHAIN_T_DEFAULT]; + type = __nft_chain_type_get(family, NFT_CHAIN_T_DEFAULT); + if (!type) + return -EOPNOTSUPP; + if (nla[NFTA_CHAIN_TYPE]) { type = nf_tables_chain_type_lookup(net, nla[NFTA_CHAIN_TYPE], family, autoload); @@ -2031,6 +2063,18 @@ static const struct nft_expr_type *__nft_expr_type_get(u8 family, return NULL; } +#ifdef CONFIG_MODULES +static int nft_expr_type_request_module(struct net *net, u8 family, + struct nlattr *nla) +{ + if (nft_request_module(net, "nft-expr-%u-%.*s", family, + nla_len(nla), (char *)nla_data(nla)) == -EAGAIN) + return -EAGAIN; + + return 0; +} +#endif + static const struct nft_expr_type *nft_expr_type_get(struct net *net, u8 family, struct nlattr *nla) @@ -2047,14 +2091,12 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nft-expr-%u-%.*s", family, - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_expr_type_request_module(net, family, nla) == -EAGAIN) return ERR_PTR(-EAGAIN); - nft_request_module(net, "nft-expr-%.*s", - nla_len(nla), (char *)nla_data(nla)); - if (__nft_expr_type_get(family, nla)) + if (nft_request_module(net, "nft-expr-%.*s", + nla_len(nla), + (char *)nla_data(nla)) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -2062,7 +2104,8 @@ static const struct nft_expr_type *nft_expr_type_get(struct net *net, } static const struct nla_policy nft_expr_policy[NFTA_EXPR_MAX + 1] = { - [NFTA_EXPR_NAME] = { .type = NLA_STRING }, + [NFTA_EXPR_NAME] = { .type = NLA_STRING, + .len = NFT_MODULE_AUTOLOAD_LIMIT }, [NFTA_EXPR_DATA] = { .type = NLA_NESTED }, }; @@ -2142,6 +2185,13 @@ static int nf_tables_expr_parse(const struct nft_ctx *ctx, (const struct nlattr * const *)info->tb); if (IS_ERR(ops)) { err = PTR_ERR(ops); +#ifdef CONFIG_MODULES + if (err == -EAGAIN) + if (nft_expr_type_request_module(ctx->net, + ctx->family, + tb[NFTA_EXPR_NAME]) != -EAGAIN) + err = -ENOENT; +#endif goto err1; } } else @@ -2967,8 +3017,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (list_empty(&nf_tables_set_types)) { - nft_request_module(ctx->net, "nft-set"); - if (!list_empty(&nf_tables_set_types)) + if (nft_request_module(ctx->net, "nft-set") == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -3519,7 +3568,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, NFT_SET_INTERVAL | NFT_SET_TIMEOUT | NFT_SET_MAP | NFT_SET_EVAL | NFT_SET_OBJECT)) - return -EINVAL; + return -EOPNOTSUPP; /* Only one of these operations is supported */ if ((flags & (NFT_SET_MAP | NFT_SET_OBJECT)) == (NFT_SET_MAP | NFT_SET_OBJECT)) @@ -3557,7 +3606,7 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, objtype = ntohl(nla_get_be32(nla[NFTA_SET_OBJ_TYPE])); if (objtype == NFT_OBJECT_UNSPEC || objtype > NFT_OBJECT_MAX) - return -EINVAL; + return -EOPNOTSUPP; } else if (flags & NFT_SET_OBJECT) return -EINVAL; else @@ -3888,7 +3937,8 @@ static const struct nla_policy nft_set_elem_policy[NFTA_SET_ELEM_MAX + 1] = { [NFTA_SET_ELEM_USERDATA] = { .type = NLA_BINARY, .len = NFT_USERDATA_MAXLEN }, [NFTA_SET_ELEM_EXPR] = { .type = NLA_NESTED }, - [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING }, + [NFTA_SET_ELEM_OBJREF] = { .type = NLA_STRING, + .len = NFT_OBJ_MAXNAMELEN - 1 }, }; static const struct nla_policy nft_set_elem_list_policy[NFTA_SET_ELEM_LIST_MAX + 1] = { @@ -4209,8 +4259,10 @@ static int nft_get_set_elem(struct nft_ctx *ctx, struct nft_set *set, return err; err = -EINVAL; - if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) + if (desc.type != NFT_DATA_VALUE || desc.len != set->klen) { + nft_data_release(&elem.key.val, desc.type); return err; + } priv = set->ops->get(ctx->net, set, &elem, flags); if (IS_ERR(priv)) @@ -4443,14 +4495,20 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_DATA] == NULL && !(flags & NFT_SET_ELEM_INTERVAL_END)) return -EINVAL; - if (nla[NFTA_SET_ELEM_DATA] != NULL && - flags & NFT_SET_ELEM_INTERVAL_END) - return -EINVAL; } else { if (nla[NFTA_SET_ELEM_DATA] != NULL) return -EINVAL; } + if ((flags & NFT_SET_ELEM_INTERVAL_END) && + (nla[NFTA_SET_ELEM_DATA] || + nla[NFTA_SET_ELEM_OBJREF] || + nla[NFTA_SET_ELEM_TIMEOUT] || + nla[NFTA_SET_ELEM_EXPIRATION] || + nla[NFTA_SET_ELEM_USERDATA] || + nla[NFTA_SET_ELEM_EXPR])) + return -EINVAL; + timeout = 0; if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) @@ -5071,8 +5129,7 @@ nft_obj_type_get(struct net *net, u32 objtype) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nft-obj-%u", objtype); - if (__nft_obj_type_get(objtype)) + if (nft_request_module(net, "nft-obj-%u", objtype) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -5634,8 +5691,7 @@ nft_flowtable_type_get(struct net *net, u8 family) lockdep_nfnl_nft_mutex_not_held(); #ifdef CONFIG_MODULES if (type == NULL) { - nft_request_module(net, "nf-flowtable-%u", family); - if (__nft_flowtable_type_get(family)) + if (nft_request_module(net, "nf-flowtable-%u", family) == -EAGAIN) return ERR_PTR(-EAGAIN); } #endif @@ -6567,6 +6623,18 @@ static void nft_chain_del(struct nft_chain *chain) list_del_rcu(&chain->list); } +static void nf_tables_module_autoload_cleanup(struct net *net) +{ + struct nft_module_request *req, *next; + + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); + list_for_each_entry_safe(req, next, &net->nft.module_list, list) { + WARN_ON_ONCE(!req->done); + list_del(&req->list); + kfree(req); + } +} + static void nf_tables_commit_release(struct net *net) { struct nft_trans *trans; @@ -6579,6 +6647,7 @@ static void nf_tables_commit_release(struct net *net) * to prevent expensive synchronize_rcu() in commit phase. */ if (list_empty(&net->nft.commit_list)) { + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); return; } @@ -6593,6 +6662,7 @@ static void nf_tables_commit_release(struct net *net) list_splice_tail_init(&net->nft.commit_list, &nf_tables_destroy_list); spin_unlock(&nf_tables_destroy_list_lock); + nf_tables_module_autoload_cleanup(net); mutex_unlock(&net->nft.commit_mutex); schedule_work(&trans_destroy_work); @@ -6771,6 +6841,21 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) return 0; } +static void nf_tables_module_autoload(struct net *net) +{ + struct nft_module_request *req, *next; + LIST_HEAD(module_list); + + list_splice_init(&net->nft.module_list, &module_list); + mutex_unlock(&net->nft.commit_mutex); + list_for_each_entry_safe(req, next, &module_list, list) { + request_module("%s", req->module); + req->done = true; + } + mutex_lock(&net->nft.commit_mutex); + list_splice(&module_list, &net->nft.module_list); +} + static void nf_tables_abort_release(struct nft_trans *trans) { switch (trans->msg_type) { @@ -6800,7 +6885,7 @@ static void nf_tables_abort_release(struct nft_trans *trans) kfree(trans); } -static int __nf_tables_abort(struct net *net) +static int __nf_tables_abort(struct net *net, bool autoload) { struct nft_trans *trans, *next; struct nft_trans_elem *te; @@ -6917,6 +7002,11 @@ static int __nf_tables_abort(struct net *net) nf_tables_abort_release(trans); } + if (autoload) + nf_tables_module_autoload(net); + else + nf_tables_module_autoload_cleanup(net); + return 0; } @@ -6925,9 +7015,9 @@ static void nf_tables_cleanup(struct net *net) nft_validate_state_update(net, NFT_VALIDATE_SKIP); } -static int nf_tables_abort(struct net *net, struct sk_buff *skb) +static int nf_tables_abort(struct net *net, struct sk_buff *skb, bool autoload) { - int ret = __nf_tables_abort(net); + int ret = __nf_tables_abort(net, autoload); mutex_unlock(&net->nft.commit_mutex); @@ -7522,6 +7612,7 @@ static int __net_init nf_tables_init_net(struct net *net) { INIT_LIST_HEAD(&net->nft.tables); INIT_LIST_HEAD(&net->nft.commit_list); + INIT_LIST_HEAD(&net->nft.module_list); mutex_init(&net->nft.commit_mutex); net->nft.base_seq = 1; net->nft.validate_state = NFT_VALIDATE_SKIP; @@ -7533,10 +7624,11 @@ static void __net_exit nf_tables_exit_net(struct net *net) { mutex_lock(&net->nft.commit_mutex); if (!list_empty(&net->nft.commit_list)) - __nf_tables_abort(net); + __nf_tables_abort(net, false); __nft_release_tables(net); mutex_unlock(&net->nft.commit_mutex); WARN_ON_ONCE(!list_empty(&net->nft.tables)); + WARN_ON_ONCE(!list_empty(&net->nft.module_list)); } static struct pernet_operations nf_tables_net_ops = { diff --git a/net/netfilter/nfnetlink.c b/net/netfilter/nfnetlink.c index 4abbb452cf6c..99127e2d95a8 100644 --- a/net/netfilter/nfnetlink.c +++ b/net/netfilter/nfnetlink.c @@ -476,7 +476,7 @@ ack: } done: if (status & NFNL_BATCH_REPLAY) { - ss->abort(net, oskb); + ss->abort(net, oskb, true); nfnl_err_reset(&err_list); kfree_skb(skb); module_put(ss->owner); @@ -487,11 +487,11 @@ done: status |= NFNL_BATCH_REPLAY; goto done; } else if (err) { - ss->abort(net, oskb); + ss->abort(net, oskb, false); netlink_ack(oskb, nlmsg_hdr(oskb), err, NULL); } } else { - ss->abort(net, oskb); + ss->abort(net, oskb, false); } if (ss->cleanup) ss->cleanup(net); diff --git a/net/netfilter/nfnetlink_cthelper.c b/net/netfilter/nfnetlink_cthelper.c index 7525063c25f5..81406b93f126 100644 --- a/net/netfilter/nfnetlink_cthelper.c +++ b/net/netfilter/nfnetlink_cthelper.c @@ -103,7 +103,7 @@ nfnl_cthelper_from_nlattr(struct nlattr *attr, struct nf_conn *ct) if (help->helper->data_len == 0) return -EINVAL; - nla_memcpy(help->data, nla_data(attr), sizeof(help->data)); + nla_memcpy(help->data, attr, sizeof(help->data)); return 0; } @@ -240,6 +240,7 @@ nfnl_cthelper_create(const struct nlattr * const tb[], ret = -ENOMEM; goto err2; } + helper->data_len = size; helper->flags |= NF_CT_HELPER_F_USERSPACE; memcpy(&helper->tuple, tuple, sizeof(struct nf_conntrack_tuple)); @@ -742,6 +743,8 @@ static const struct nla_policy nfnl_cthelper_policy[NFCTH_MAX+1] = { [NFCTH_NAME] = { .type = NLA_NUL_STRING, .len = NF_CT_HELPER_NAME_LEN-1 }, [NFCTH_QUEUE_NUM] = { .type = NLA_U32, }, + [NFCTH_PRIV_DATA_LEN] = { .type = NLA_U32, }, + [NFCTH_STATUS] = { .type = NLA_U32, }, }; static const struct nfnl_callback nfnl_cthelper_cb[NFNL_MSG_CTHELPER_MAX] = { diff --git a/net/netfilter/nfnetlink_osf.c b/net/netfilter/nfnetlink_osf.c index f42326b40d6f..2e7ced752ef1 100644 --- a/net/netfilter/nfnetlink_osf.c +++ b/net/netfilter/nfnetlink_osf.c @@ -166,12 +166,12 @@ static bool nf_osf_match_one(const struct sk_buff *skb, static const struct tcphdr *nf_osf_hdr_ctx_init(struct nf_osf_hdr_ctx *ctx, const struct sk_buff *skb, const struct iphdr *ip, - unsigned char *opts) + unsigned char *opts, + struct tcphdr *_tcph) { const struct tcphdr *tcp; - struct tcphdr _tcph; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), _tcph); if (!tcp) return NULL; @@ -206,10 +206,11 @@ nf_osf_match(const struct sk_buff *skb, u_int8_t family, int fmatch = FMATCH_WRONG; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; @@ -266,10 +267,11 @@ bool nf_osf_find(const struct sk_buff *skb, const struct nf_osf_finger *kf; struct nf_osf_hdr_ctx ctx; const struct tcphdr *tcp; + struct tcphdr _tcph; memset(&ctx, 0, sizeof(ctx)); - tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts); + tcp = nf_osf_hdr_ctx_init(&ctx, skb, ip, opts, &_tcph); if (!tcp) return false; diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index b310b637b550..143b13b28a59 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -79,7 +79,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_MASK]); if (err < 0) return err; - if (d1.len != priv->len) { + if (d1.type != NFT_DATA_VALUE || d1.len != priv->len) { err = -EINVAL; goto err1; } @@ -88,7 +88,7 @@ static int nft_bitwise_init(const struct nft_ctx *ctx, tb[NFTA_BITWISE_XOR]); if (err < 0) goto err1; - if (d2.len != priv->len) { + if (d2.type != NFT_DATA_VALUE || d2.len != priv->len) { err = -EINVAL; goto err2; } diff --git a/net/netfilter/nft_chain_nat.c b/net/netfilter/nft_chain_nat.c index ff9ac8ae0031..eac4a901233f 100644 --- a/net/netfilter/nft_chain_nat.c +++ b/net/netfilter/nft_chain_nat.c @@ -89,6 +89,7 @@ static const struct nft_chain_type nft_chain_nat_inet = { .name = "nat", .type = NFT_CHAIN_T_NAT, .family = NFPROTO_INET, + .owner = THIS_MODULE, .hook_mask = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_IN) | (1 << NF_INET_LOCAL_OUT) | diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 411c0cf741e3..abd7be110f80 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -79,6 +79,12 @@ static int nft_cmp_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (err < 0) return err; + if (desc.type != NFT_DATA_VALUE) { + err = -EINVAL; + nft_data_release(&priv->data, desc.type); + return err; + } + priv->sreg = nft_parse_register(tb[NFTA_CMP_SREG]); err = nft_validate_register_load(priv->sreg, desc.len); if (err < 0) diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index 01705ad74a9a..da21b771a259 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -179,9 +179,6 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, static void nft_flow_offload_destroy(const struct nft_ctx *ctx, const struct nft_expr *expr) { - struct nft_flow_offload *priv = nft_expr_priv(expr); - - priv->flowtable->use--; nf_ct_netns_put(ctx->net, ctx->family); } diff --git a/net/netfilter/nft_fwd_netdev.c b/net/netfilter/nft_fwd_netdev.c index 61b7f93ac681..42afcd2bc6f8 100644 --- a/net/netfilter/nft_fwd_netdev.c +++ b/net/netfilter/nft_fwd_netdev.c @@ -27,6 +27,9 @@ static void nft_fwd_netdev_eval(const struct nft_expr *expr, struct nft_fwd_netdev *priv = nft_expr_priv(expr); int oif = regs->data[priv->sreg_dev]; + /* This is used by ifb only. */ + skb_set_redirected(pkt->skb, true); + nf_fwd_netdev_egress(pkt, oif); regs->verdict.code = NF_STOLEN; } @@ -179,6 +182,13 @@ nla_put_failure: return -1; } +static int nft_fwd_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) +{ + return nft_chain_validate_hooks(ctx->chain, (1 << NF_NETDEV_INGRESS)); +} + static struct nft_expr_type nft_fwd_netdev_type; static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = { .type = &nft_fwd_netdev_type, @@ -186,6 +196,7 @@ static const struct nft_expr_ops nft_fwd_neigh_netdev_ops = { .eval = nft_fwd_neigh_eval, .init = nft_fwd_neigh_init, .dump = nft_fwd_neigh_dump, + .validate = nft_fwd_validate, }; static const struct nft_expr_ops nft_fwd_netdev_ops = { @@ -194,6 +205,7 @@ static const struct nft_expr_ops nft_fwd_netdev_ops = { .eval = nft_fwd_netdev_eval, .init = nft_fwd_netdev_init, .dump = nft_fwd_netdev_dump, + .validate = nft_fwd_validate, }; static const struct nft_expr_ops * diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index a54329b8634a..b34231cd82ac 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -544,6 +544,10 @@ nft_meta_select_ops(const struct nft_ctx *ctx, if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) return ERR_PTR(-EINVAL); +#if defined(CONFIG_NF_TABLES_BRIDGE) && IS_MODULE(CONFIG_NFT_BRIDGE_META) + if (ctx->family == NFPROTO_BRIDGE) + return ERR_PTR(-EAGAIN); +#endif if (tb[NFTA_META_DREG]) return &nft_meta_get_ops; diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index c3c93e95b46e..243e8107f456 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -129,7 +129,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, priv->type = NF_NAT_MANIP_DST; break; default: - return -EINVAL; + return -EOPNOTSUPP; } if (tb[NFTA_NAT_FAMILY] == NULL) @@ -196,7 +196,7 @@ static int nft_nat_init(const struct nft_ctx *ctx, const struct nft_expr *expr, if (tb[NFTA_NAT_FLAGS]) { priv->flags = ntohl(nla_get_be32(tb[NFTA_NAT_FLAGS])); if (priv->flags & ~NF_NAT_RANGE_MASK) - return -EINVAL; + return -EOPNOTSUPP; } return nf_ct_netns_get(ctx->net, family); diff --git a/net/netfilter/nft_osf.c b/net/netfilter/nft_osf.c index f54d6ae15bb1..b42247aa48a9 100644 --- a/net/netfilter/nft_osf.c +++ b/net/netfilter/nft_osf.c @@ -61,6 +61,9 @@ static int nft_osf_init(const struct nft_ctx *ctx, int err; u8 ttl; + if (!tb[NFTA_OSF_DREG]) + return -EINVAL; + if (tb[NFTA_OSF_TTL]) { ttl = nla_get_u8(tb[NFTA_OSF_TTL]); if (ttl > 2) diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index 680bd9f38a81..f2ab0066e7a7 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -118,6 +118,7 @@ static const struct nla_policy nft_payload_policy[NFTA_PAYLOAD_MAX + 1] = { [NFTA_PAYLOAD_LEN] = { .type = NLA_U32 }, [NFTA_PAYLOAD_CSUM_TYPE] = { .type = NLA_U32 }, [NFTA_PAYLOAD_CSUM_OFFSET] = { .type = NLA_U32 }, + [NFTA_PAYLOAD_CSUM_FLAGS] = { .type = NLA_U32 }, }; static int nft_payload_init(const struct nft_ctx *ctx, diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index 4701fa8a45e7..89efcc5a533d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -66,11 +66,21 @@ static int nft_range_init(const struct nft_ctx *ctx, const struct nft_expr *expr if (err < 0) return err; + if (desc_from.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err1; + } + err = nft_data_init(NULL, &priv->data_to, sizeof(priv->data_to), &desc_to, tb[NFTA_RANGE_TO_DATA]); if (err < 0) goto err1; + if (desc_to.type != NFT_DATA_VALUE) { + err = -EINVAL; + goto err2; + } + if (desc_from.len != desc_to.len) { err = -EINVAL; goto err2; diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index 419d58ef802b..34ae80ea96ae 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -33,6 +33,11 @@ static bool nft_rbtree_interval_end(const struct nft_rbtree_elem *rbe) (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END); } +static bool nft_rbtree_interval_start(const struct nft_rbtree_elem *rbe) +{ + return !nft_rbtree_interval_end(rbe); +} + static bool nft_rbtree_equal(const struct nft_set *set, const void *this, const struct nft_rbtree_elem *interval) { @@ -64,7 +69,7 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (interval && nft_rbtree_equal(set, this, interval) && nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(interval)) + nft_rbtree_interval_start(interval)) continue; interval = rbe; } else if (d > 0) @@ -74,8 +79,17 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set parent = rcu_dereference_raw(parent->rb_left); continue; } - if (nft_rbtree_interval_end(rbe)) - goto out; + + if (nft_set_elem_expired(&rbe->ext)) + return false; + + if (nft_rbtree_interval_end(rbe)) { + if (nft_set_is_anonymous(set)) + return false; + parent = rcu_dereference_raw(parent->rb_left); + interval = NULL; + continue; + } *ext = &rbe->ext; return true; @@ -84,11 +98,12 @@ static bool __nft_rbtree_lookup(const struct net *net, const struct nft_set *set if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && - !nft_rbtree_interval_end(interval)) { + !nft_set_elem_expired(&interval->ext) && + nft_rbtree_interval_start(interval)) { *ext = &interval->ext; return true; } -out: + return false; } @@ -139,8 +154,13 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, if (flags & NFT_SET_ELEM_INTERVAL_END) interval = rbe; } else { - if (!nft_set_elem_active(&rbe->ext, genmask)) + if (!nft_set_elem_active(&rbe->ext, genmask)) { parent = rcu_dereference_raw(parent->rb_left); + continue; + } + + if (nft_set_elem_expired(&rbe->ext)) + return false; if (!nft_set_ext_exists(&rbe->ext, NFT_SET_EXT_FLAGS) || (*nft_set_ext_flags(&rbe->ext) & NFT_SET_ELEM_INTERVAL_END) == @@ -148,12 +168,17 @@ static bool __nft_rbtree_get(const struct net *net, const struct nft_set *set, *elem = rbe; return true; } - return false; + + if (nft_rbtree_interval_end(rbe)) + interval = NULL; + + parent = rcu_dereference_raw(parent->rb_left); } } if (set->flags & NFT_SET_INTERVAL && interval != NULL && nft_set_elem_active(&interval->ext, genmask) && + !nft_set_elem_expired(&interval->ext) && ((!nft_rbtree_interval_end(interval) && !(flags & NFT_SET_ELEM_INTERVAL_END)) || (nft_rbtree_interval_end(interval) && @@ -213,9 +238,9 @@ static int __nft_rbtree_insert(const struct net *net, const struct nft_set *set, p = &parent->rb_right; else { if (nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(new)) { + nft_rbtree_interval_start(new)) { p = &parent->rb_left; - } else if (!nft_rbtree_interval_end(rbe) && + } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(new)) { p = &parent->rb_right; } else if (nft_set_elem_active(&rbe->ext, genmask)) { @@ -306,10 +331,10 @@ static void *nft_rbtree_deactivate(const struct net *net, parent = parent->rb_right; else { if (nft_rbtree_interval_end(rbe) && - !nft_rbtree_interval_end(this)) { + nft_rbtree_interval_start(this)) { parent = parent->rb_left; continue; - } else if (!nft_rbtree_interval_end(rbe) && + } else if (nft_rbtree_interval_start(rbe) && nft_rbtree_interval_end(this)) { parent = parent->rb_right; continue; @@ -339,6 +364,8 @@ static void nft_rbtree_walk(const struct nft_ctx *ctx, if (iter->count < iter->skip) goto cont; + if (nft_set_elem_expired(&rbe->ext)) + goto cont; if (!nft_set_elem_active(&rbe->ext, iter->genmask)) goto cont; diff --git a/net/netfilter/nft_tproxy.c b/net/netfilter/nft_tproxy.c index f92a82c73880..95980154ef02 100644 --- a/net/netfilter/nft_tproxy.c +++ b/net/netfilter/nft_tproxy.c @@ -50,7 +50,7 @@ static void nft_tproxy_eval_v4(const struct nft_expr *expr, taddr = nf_tproxy_laddr4(skb, taddr, iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; @@ -117,7 +117,7 @@ static void nft_tproxy_eval_v6(const struct nft_expr *expr, taddr = *nf_tproxy_laddr6(skb, &taddr, &iph->daddr); if (priv->sreg_port) - tport = regs->data[priv->sreg_port]; + tport = nft_reg_load16(®s->data[priv->sreg_port]); if (!tport) tport = hp->dest; diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 3d4c2ae605a8..1effd4878619 100644 --- a/net/netfilter/nft_tunnel.c +++ b/net/netfilter/nft_tunnel.c @@ -76,7 +76,7 @@ static int nft_tunnel_get_init(const struct nft_ctx *ctx, struct nft_tunnel *priv = nft_expr_priv(expr); u32 len; - if (!tb[NFTA_TUNNEL_KEY] && + if (!tb[NFTA_TUNNEL_KEY] || !tb[NFTA_TUNNEL_DREG]) return -EINVAL; @@ -248,8 +248,9 @@ static int nft_tunnel_obj_vxlan_init(const struct nlattr *attr, } static const struct nla_policy nft_tunnel_opts_erspan_policy[NFTA_TUNNEL_KEY_ERSPAN_MAX + 1] = { + [NFTA_TUNNEL_KEY_ERSPAN_VERSION] = { .type = NLA_U32 }, [NFTA_TUNNEL_KEY_ERSPAN_V1_INDEX] = { .type = NLA_U32 }, - [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, + [NFTA_TUNNEL_KEY_ERSPAN_V2_DIR] = { .type = NLA_U8 }, [NFTA_TUNNEL_KEY_ERSPAN_V2_HWID] = { .type = NLA_U8 }, }; @@ -266,6 +267,9 @@ static int nft_tunnel_obj_erspan_init(const struct nlattr *attr, if (err < 0) return err; + if (!tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION]) + return -EINVAL; + version = ntohl(nla_get_be32(tb[NFTA_TUNNEL_KEY_ERSPAN_VERSION])); switch (version) { case ERSPAN_VERSION: @@ -335,6 +339,8 @@ static const struct nla_policy nft_tunnel_key_policy[NFTA_TUNNEL_KEY_MAX + 1] = [NFTA_TUNNEL_KEY_FLAGS] = { .type = NLA_U32, }, [NFTA_TUNNEL_KEY_TOS] = { .type = NLA_U8, }, [NFTA_TUNNEL_KEY_TTL] = { .type = NLA_U8, }, + [NFTA_TUNNEL_KEY_SPORT] = { .type = NLA_U16, }, + [NFTA_TUNNEL_KEY_DPORT] = { .type = NLA_U16, }, [NFTA_TUNNEL_KEY_OPTS] = { .type = NLA_NESTED, }, }; @@ -501,8 +507,8 @@ static int nft_tunnel_opts_dump(struct sk_buff *skb, static int nft_tunnel_ports_dump(struct sk_buff *skb, struct ip_tunnel_info *info) { - if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, htons(info->key.tp_src)) < 0 || - nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, htons(info->key.tp_dst)) < 0) + if (nla_put_be16(skb, NFTA_TUNNEL_KEY_SPORT, info->key.tp_src) < 0 || + nla_put_be16(skb, NFTA_TUNNEL_KEY_DPORT, info->key.tp_dst) < 0) return -1; return 0; diff --git a/net/netfilter/x_tables.c b/net/netfilter/x_tables.c index ce70c2576bb2..44f971f31992 100644 --- a/net/netfilter/x_tables.c +++ b/net/netfilter/x_tables.c @@ -1551,6 +1551,9 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, uint8_t nfproto = (unsigned long)PDE_DATA(file_inode(seq->file)); struct nf_mttg_trav *trav = seq->private; + if (ppos != NULL) + ++(*ppos); + switch (trav->class) { case MTTG_TRAV_INIT: trav->class = MTTG_TRAV_NFP_UNSPEC; @@ -1576,9 +1579,6 @@ static void *xt_mttg_seq_next(struct seq_file *seq, void *v, loff_t *ppos, default: return NULL; } - - if (ppos != NULL) - ++*ppos; return trav; } diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index 2d2691dd51e0..6be05be8ed47 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -36,6 +36,7 @@ #include <linux/netfilter_ipv6/ip6_tables.h> #include <linux/netfilter/xt_hashlimit.h> #include <linux/mutex.h> +#include <linux/refcount.h> #include <linux/kernel.h> MODULE_LICENSE("GPL"); @@ -109,7 +110,7 @@ struct dsthash_ent { struct xt_hashlimit_htable { struct hlist_node node; /* global list of all htables */ - int use; + refcount_t use; u_int8_t family; bool rnd_initialized; @@ -310,7 +311,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, for (i = 0; i < hinfo->cfg.size; i++) INIT_HLIST_HEAD(&hinfo->hash[i]); - hinfo->use = 1; + refcount_set(&hinfo->use, 1); hinfo->count = 0; hinfo->family = family; hinfo->rnd_initialized = false; @@ -352,21 +353,7 @@ static int htable_create(struct net *net, struct hashlimit_cfg3 *cfg, return 0; } -static bool select_all(const struct xt_hashlimit_htable *ht, - const struct dsthash_ent *he) -{ - return true; -} - -static bool select_gc(const struct xt_hashlimit_htable *ht, - const struct dsthash_ent *he) -{ - return time_after_eq(jiffies, he->expires); -} - -static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, - bool (*select)(const struct xt_hashlimit_htable *ht, - const struct dsthash_ent *he)) +static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, bool select_all) { unsigned int i; @@ -376,7 +363,7 @@ static void htable_selective_cleanup(struct xt_hashlimit_htable *ht, spin_lock_bh(&ht->lock); hlist_for_each_entry_safe(dh, n, &ht->hash[i], node) { - if ((*select)(ht, dh)) + if (time_after_eq(jiffies, dh->expires) || select_all) dsthash_free(ht, dh); } spin_unlock_bh(&ht->lock); @@ -390,7 +377,7 @@ static void htable_gc(struct work_struct *work) ht = container_of(work, struct xt_hashlimit_htable, gc_work.work); - htable_selective_cleanup(ht, select_gc); + htable_selective_cleanup(ht, false); queue_delayed_work(system_power_efficient_wq, &ht->gc_work, msecs_to_jiffies(ht->cfg.gc_interval)); @@ -410,15 +397,6 @@ static void htable_remove_proc_entry(struct xt_hashlimit_htable *hinfo) remove_proc_entry(hinfo->name, parent); } -static void htable_destroy(struct xt_hashlimit_htable *hinfo) -{ - cancel_delayed_work_sync(&hinfo->gc_work); - htable_remove_proc_entry(hinfo); - htable_selective_cleanup(hinfo, select_all); - kfree(hinfo->name); - vfree(hinfo); -} - static struct xt_hashlimit_htable *htable_find_get(struct net *net, const char *name, u_int8_t family) @@ -429,7 +407,7 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, hlist_for_each_entry(hinfo, &hashlimit_net->htables, node) { if (!strcmp(name, hinfo->name) && hinfo->family == family) { - hinfo->use++; + refcount_inc(&hinfo->use); return hinfo; } } @@ -438,12 +416,16 @@ static struct xt_hashlimit_htable *htable_find_get(struct net *net, static void htable_put(struct xt_hashlimit_htable *hinfo) { - mutex_lock(&hashlimit_mutex); - if (--hinfo->use == 0) { + if (refcount_dec_and_mutex_lock(&hinfo->use, &hashlimit_mutex)) { hlist_del(&hinfo->node); - htable_destroy(hinfo); + htable_remove_proc_entry(hinfo); + mutex_unlock(&hashlimit_mutex); + + cancel_delayed_work_sync(&hinfo->gc_work); + htable_selective_cleanup(hinfo, true); + kfree(hinfo->name); + vfree(hinfo); } - mutex_unlock(&hashlimit_mutex); } /* The algorithm used is the Simple Token Bucket Filter (TBF) @@ -846,6 +828,8 @@ hashlimit_mt(const struct sk_buff *skb, struct xt_action_param *par) return hashlimit_mt_common(skb, par, hinfo, &info->cfg, 3); } +#define HASHLIMIT_MAX_SIZE 1048576 + static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, struct xt_hashlimit_htable **hinfo, struct hashlimit_cfg3 *cfg, @@ -856,6 +840,14 @@ static int hashlimit_mt_check_common(const struct xt_mtchk_param *par, if (cfg->gc_interval == 0 || cfg->expire == 0) return -EINVAL; + if (cfg->size > HASHLIMIT_MAX_SIZE) { + cfg->size = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("size too large, truncated to %u\n", cfg->size); + } + if (cfg->max > HASHLIMIT_MAX_SIZE) { + cfg->max = HASHLIMIT_MAX_SIZE; + pr_info_ratelimited("max too large, truncated to %u\n", cfg->max); + } if (par->family == NFPROTO_IPV4) { if (cfg->srcmask > 32 || cfg->dstmask > 32) return -EINVAL; diff --git a/net/netfilter/xt_recent.c b/net/netfilter/xt_recent.c index 781e0b482189..6c2582a19766 100644 --- a/net/netfilter/xt_recent.c +++ b/net/netfilter/xt_recent.c @@ -492,12 +492,12 @@ static void *recent_seq_next(struct seq_file *seq, void *v, loff_t *pos) const struct recent_entry *e = v; const struct list_head *head = e->list.next; + (*pos)++; while (head == &t->iphash[st->bucket]) { if (++st->bucket >= ip_list_hash_size) return NULL; head = t->iphash[st->bucket].next; } - (*pos)++; return list_entry(head, struct recent_entry, list); } diff --git a/net/netlabel/netlabel_kapi.c b/net/netlabel/netlabel_kapi.c index 2b0ef55cf89e..52389a25d76d 100644 --- a/net/netlabel/netlabel_kapi.c +++ b/net/netlabel/netlabel_kapi.c @@ -734,6 +734,12 @@ int netlbl_catmap_getlong(struct netlbl_lsm_catmap *catmap, if ((off & (BITS_PER_LONG - 1)) != 0) return -EINVAL; + /* a null catmap is equivalent to an empty one */ + if (!catmap) { + *offset = (u32)-1; + return 0; + } + if (off < catmap->startbit) { off = catmap->startbit; *offset = off; diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index e9ddfd782d16..b7db1f99fc70 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1019,7 +1019,8 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, if (nlk->netlink_bind && groups) { int group; - for (group = 0; group < nlk->ngroups; group++) { + /* nl_groups is a u32, so cap the maximum groups we can bind */ + for (group = 0; group < BITS_PER_TYPE(u32); group++) { if (!test_bit(group, &groups)) continue; err = nlk->netlink_bind(net, group + 1); @@ -1038,7 +1039,7 @@ static int netlink_bind(struct socket *sock, struct sockaddr *addr, netlink_insert(sk, nladdr->nl_pid) : netlink_autobind(sock); if (err) { - netlink_undo_bind(nlk->ngroups, groups, sk); + netlink_undo_bind(BITS_PER_TYPE(u32), groups, sk); goto unlock; } } @@ -2438,7 +2439,7 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err, in_skb->len)) WARN_ON(nla_put_u32(skb, NLMSGERR_ATTR_OFFS, (u8 *)extack->bad_attr - - in_skb->data)); + (u8 *)nlh)); } else { if (extack->cookie_len) WARN_ON(nla_put(skb, NLMSGERR_ATTR_COOKIE, diff --git a/net/netlink/genetlink.c b/net/netlink/genetlink.c index efccd1ac9a66..102b8d6b5612 100644 --- a/net/netlink/genetlink.c +++ b/net/netlink/genetlink.c @@ -989,60 +989,11 @@ static struct genl_family genl_ctrl __ro_after_init = { .netnsok = true, }; -static int genl_bind(struct net *net, int group) -{ - struct genl_family *f; - int err = -ENOENT; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (!f->netnsok && net != &init_net) - err = -ENOENT; - else if (f->mcast_bind) - err = f->mcast_bind(net, fam_grp); - else - err = 0; - break; - } - } - up_read(&cb_lock); - - return err; -} - -static void genl_unbind(struct net *net, int group) -{ - struct genl_family *f; - unsigned int id; - - down_read(&cb_lock); - - idr_for_each_entry(&genl_fam_idr, f, id) { - if (group >= f->mcgrp_offset && - group < f->mcgrp_offset + f->n_mcgrps) { - int fam_grp = group - f->mcgrp_offset; - - if (f->mcast_unbind) - f->mcast_unbind(net, fam_grp); - break; - } - } - up_read(&cb_lock); -} - static int __net_init genl_pernet_init(struct net *net) { struct netlink_kernel_cfg cfg = { .input = genl_rcv, .flags = NL_CFG_F_NONROOT_RECV, - .bind = genl_bind, - .unbind = genl_unbind, }; /* we'll bump the group number right afterwards */ diff --git a/net/netrom/nr_route.c b/net/netrom/nr_route.c index d41335bad1f8..89cd9de21594 100644 --- a/net/netrom/nr_route.c +++ b/net/netrom/nr_route.c @@ -208,6 +208,7 @@ static int __must_check nr_add_node(ax25_address *nr, const char *mnemonic, /* refcount initialized at 1 */ spin_unlock_bh(&nr_node_list_lock); + nr_neigh_put(nr_neigh); return 0; } nr_node_lock(nr_node); diff --git a/net/nfc/hci/core.c b/net/nfc/hci/core.c index 6f1b096e601c..43811b5219b5 100644 --- a/net/nfc/hci/core.c +++ b/net/nfc/hci/core.c @@ -181,13 +181,20 @@ exit: void nfc_hci_cmd_received(struct nfc_hci_dev *hdev, u8 pipe, u8 cmd, struct sk_buff *skb) { - u8 gate = hdev->pipes[pipe].gate; u8 status = NFC_HCI_ANY_OK; struct hci_create_pipe_resp *create_info; struct hci_delete_pipe_noti *delete_info; struct hci_all_pipe_cleared_noti *cleared_info; + u8 gate; - pr_debug("from gate %x pipe %x cmd %x\n", gate, pipe, cmd); + pr_debug("from pipe %x cmd %x\n", pipe, cmd); + + if (pipe >= NFC_HCI_MAX_PIPES) { + status = NFC_HCI_ANY_E_NOK; + goto exit; + } + + gate = hdev->pipes[pipe].gate; switch (cmd) { case NFC_HCI_ADM_NOTIFY_PIPE_CREATED: @@ -375,8 +382,14 @@ void nfc_hci_event_received(struct nfc_hci_dev *hdev, u8 pipe, u8 event, struct sk_buff *skb) { int r = 0; - u8 gate = hdev->pipes[pipe].gate; + u8 gate; + + if (pipe >= NFC_HCI_MAX_PIPES) { + pr_err("Discarded event %x to invalid pipe %x\n", event, pipe); + goto exit; + } + gate = hdev->pipes[pipe].gate; if (gate == NFC_HCI_INVALID_GATE) { pr_err("Discarded event %x to unopened pipe %x\n", event, pipe); goto exit; diff --git a/net/nfc/llcp_sock.c b/net/nfc/llcp_sock.c index ccdd790e163a..28604414dec1 100644 --- a/net/nfc/llcp_sock.c +++ b/net/nfc/llcp_sock.c @@ -554,11 +554,11 @@ static __poll_t llcp_sock_poll(struct file *file, struct socket *sock, if (sk->sk_state == LLCP_LISTEN) return llcp_accept_poll(sk); - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; if (sk->sk_state == LLCP_CLOSED) diff --git a/net/nfc/nci/uart.c b/net/nfc/nci/uart.c index 78fe622eba65..11b554ce07ff 100644 --- a/net/nfc/nci/uart.c +++ b/net/nfc/nci/uart.c @@ -346,7 +346,7 @@ static int nci_uart_default_recv_buf(struct nci_uart *nu, const u8 *data, nu->rx_packet_len = -1; nu->rx_skb = nci_skb_alloc(nu->ndev, NCI_MAX_PACKET_SIZE, - GFP_KERNEL); + GFP_ATOMIC); if (!nu->rx_skb) return -ENOMEM; } diff --git a/net/nfc/netlink.c b/net/nfc/netlink.c index 17e6ca62f1be..1b261375722e 100644 --- a/net/nfc/netlink.c +++ b/net/nfc/netlink.c @@ -32,6 +32,7 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_DEVICE_NAME] = { .type = NLA_STRING, .len = NFC_DEVICE_NAME_MAXSIZE }, [NFC_ATTR_PROTOCOLS] = { .type = NLA_U32 }, + [NFC_ATTR_TARGET_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_COMM_MODE] = { .type = NLA_U8 }, [NFC_ATTR_RF_MODE] = { .type = NLA_U8 }, [NFC_ATTR_DEVICE_POWERED] = { .type = NLA_U8 }, @@ -43,7 +44,10 @@ static const struct nla_policy nfc_genl_policy[NFC_ATTR_MAX + 1] = { [NFC_ATTR_LLC_SDP] = { .type = NLA_NESTED }, [NFC_ATTR_FIRMWARE_NAME] = { .type = NLA_STRING, .len = NFC_FIRMWARE_NAME_MAXSIZE }, + [NFC_ATTR_SE_INDEX] = { .type = NLA_U32 }, [NFC_ATTR_SE_APDU] = { .type = NLA_BINARY }, + [NFC_ATTR_VENDOR_ID] = { .type = NLA_U32 }, + [NFC_ATTR_VENDOR_SUBCMD] = { .type = NLA_U32 }, [NFC_ATTR_VENDOR_DATA] = { .type = NLA_BINARY }, }; @@ -1099,7 +1103,6 @@ static int nfc_genl_llc_set_params(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } @@ -1159,7 +1162,6 @@ static int nfc_genl_llc_sdreq(struct sk_buff *skb, struct genl_info *info) local = nfc_llcp_find_local(dev); if (!local) { - nfc_put_device(dev); rc = -ENODEV; goto exit; } diff --git a/net/nfc/rawsock.c b/net/nfc/rawsock.c index ba5ffd3badd3..b5c867fe3232 100644 --- a/net/nfc/rawsock.c +++ b/net/nfc/rawsock.c @@ -332,10 +332,13 @@ static int rawsock_create(struct net *net, struct socket *sock, if ((sock->type != SOCK_SEQPACKET) && (sock->type != SOCK_RAW)) return -ESOCKTNOSUPPORT; - if (sock->type == SOCK_RAW) + if (sock->type == SOCK_RAW) { + if (!capable(CAP_NET_RAW)) + return -EPERM; sock->ops = &rawsock_raw_ops; - else + } else { sock->ops = &rawsock_ops; + } sk = sk_alloc(net, PF_NFC, GFP_ATOMIC, nfc_proto->proto, kern); if (!sk) diff --git a/net/openvswitch/actions.c b/net/openvswitch/actions.c index bd131469e4ca..7c541eb9ec5f 100644 --- a/net/openvswitch/actions.c +++ b/net/openvswitch/actions.c @@ -1206,9 +1206,10 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, struct sw_flow_key *key, const struct nlattr *attr, bool last) { + struct ovs_skb_cb *ovs_cb = OVS_CB(skb); const struct nlattr *actions, *cpl_arg; + int len, max_len, rem = nla_len(attr); const struct check_pkt_len_arg *arg; - int rem = nla_len(attr); bool clone_flow_key; /* The first netlink attribute in 'attr' is always @@ -1217,7 +1218,11 @@ static int execute_check_pkt_len(struct datapath *dp, struct sk_buff *skb, cpl_arg = nla_data(attr); arg = nla_data(cpl_arg); - if (skb->len <= arg->pkt_len) { + len = ovs_cb->mru ? ovs_cb->mru + skb->mac_len : skb->len; + max_len = arg->pkt_len; + + if ((skb_is_gso(skb) && skb_gso_validate_mac_len(skb, max_len)) || + len <= max_len) { /* Second netlink attribute in 'attr' is always * 'OVS_CHECK_PKT_LEN_ATTR_ACTIONS_IF_LESS_EQUAL'. */ diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index 4d7896135e73..8d66222a65df 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -276,10 +276,6 @@ void ovs_ct_fill_key(const struct sk_buff *skb, struct sw_flow_key *key) ovs_ct_update_key(skb, NULL, key, false, false); } -#define IN6_ADDR_INITIALIZER(ADDR) \ - { (ADDR).s6_addr32[0], (ADDR).s6_addr32[1], \ - (ADDR).s6_addr32[2], (ADDR).s6_addr32[3] } - int ovs_ct_put_key(const struct sw_flow_key *swkey, const struct sw_flow_key *output, struct sk_buff *skb) { @@ -301,24 +297,30 @@ int ovs_ct_put_key(const struct sw_flow_key *swkey, if (swkey->ct_orig_proto) { if (swkey->eth.type == htons(ETH_P_IP)) { - struct ovs_key_ct_tuple_ipv4 orig = { - output->ipv4.ct_orig.src, - output->ipv4.ct_orig.dst, - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv4 orig; + + memset(&orig, 0, sizeof(orig)); + orig.ipv4_src = output->ipv4.ct_orig.src; + orig.ipv4_dst = output->ipv4.ct_orig.dst; + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv4_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV4, sizeof(orig), &orig)) return -EMSGSIZE; } else if (swkey->eth.type == htons(ETH_P_IPV6)) { - struct ovs_key_ct_tuple_ipv6 orig = { - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.src), - IN6_ADDR_INITIALIZER(output->ipv6.ct_orig.dst), - output->ct.orig_tp.src, - output->ct.orig_tp.dst, - output->ct_orig_proto, - }; + struct ovs_key_ct_tuple_ipv6 orig; + + memset(&orig, 0, sizeof(orig)); + memcpy(orig.ipv6_src, output->ipv6.ct_orig.src.s6_addr32, + sizeof(orig.ipv6_src)); + memcpy(orig.ipv6_dst, output->ipv6.ct_orig.dst.s6_addr32, + sizeof(orig.ipv6_dst)); + orig.src_port = output->ct.orig_tp.src; + orig.dst_port = output->ct.orig_tp.dst; + orig.ipv6_proto = output->ct_orig_proto; + if (nla_put(skb, OVS_KEY_ATTR_CT_ORIG_TUPLE_IPV6, sizeof(orig), &orig)) return -EMSGSIZE; @@ -898,6 +900,17 @@ static int ovs_ct_nat(struct net *net, struct sw_flow_key *key, } err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, maniptype); + if (err == NF_ACCEPT && + ct->status & IPS_SRC_NAT && ct->status & IPS_DST_NAT) { + if (maniptype == NF_NAT_MANIP_SRC) + maniptype = NF_NAT_MANIP_DST; + else + maniptype = NF_NAT_MANIP_SRC; + + err = ovs_ct_nat_execute(skb, ct, ctinfo, &info->range, + maniptype); + } + /* Mark NAT done if successful and update the flow key. */ if (err == NF_ACCEPT) ovs_nat_update_key(key, skb, maniptype); @@ -1574,7 +1587,7 @@ static int parse_ct(const struct nlattr *attr, struct ovs_conntrack_info *info, case OVS_CT_ATTR_TIMEOUT: memcpy(info->timeout, nla_data(a), nla_len(a)); if (!memchr(info->timeout, '\0', nla_len(a))) { - OVS_NLERR(log, "Invalid conntrack helper"); + OVS_NLERR(log, "Invalid conntrack timeout"); return -EINVAL; } break; @@ -1874,7 +1887,8 @@ static void ovs_ct_limit_exit(struct net *net, struct ovs_net *ovs_net) struct hlist_head *head = &info->limits[i]; struct ovs_ct_limit *ct_limit; - hlist_for_each_entry_rcu(ct_limit, head, hlist_node) + hlist_for_each_entry_rcu(ct_limit, head, hlist_node, + lockdep_ovsl_is_held()) kfree_rcu(ct_limit, rcu); } kfree(ovs_net->ct_limit_info->limits); diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index c29e9f766bd3..fc46a08b068e 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -701,9 +701,13 @@ static size_t ovs_flow_cmd_msg_size(const struct sw_flow_actions *acts, { size_t len = NLMSG_ALIGN(sizeof(struct ovs_header)); - /* OVS_FLOW_ATTR_UFID */ + /* OVS_FLOW_ATTR_UFID, or unmasked flow key as fallback + * see ovs_nla_put_identifier() + */ if (sfid && ovs_identifier_is_ufid(sfid)) len += nla_total_size(sfid->ufid_len); + else + len += nla_total_size(ovs_key_attr_size()); /* OVS_FLOW_ATTR_KEY */ if (!sfid || should_fill_key(sfid, ufid_flags)) @@ -879,7 +883,10 @@ static struct sk_buff *ovs_flow_cmd_build_info(const struct sw_flow *flow, retval = ovs_flow_cmd_fill_info(flow, dp_ifindex, skb, info->snd_portid, info->snd_seq, 0, cmd, ufid_flags); - BUG_ON(retval < 0); + if (WARN_ON_ONCE(retval < 0)) { + kfree_skb(skb); + skb = ERR_PTR(retval); + } return skb; } @@ -1342,7 +1349,10 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) OVS_FLOW_CMD_DEL, ufid_flags); rcu_read_unlock(); - BUG_ON(err < 0); + if (WARN_ON_ONCE(err < 0)) { + kfree_skb(reply); + goto out_free; + } ovs_notify(&dp_flow_genl_family, reply, info); } else { @@ -1350,6 +1360,7 @@ static int ovs_flow_cmd_del(struct sk_buff *skb, struct genl_info *info) } } +out_free: ovs_flow_free(flow, true); return 0; unlock: @@ -1849,7 +1860,7 @@ static struct genl_family dp_datapath_genl_family __ro_after_init = { /* Called with ovs_mutex or RCU read lock. */ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, struct net *net, u32 portid, u32 seq, - u32 flags, u8 cmd) + u32 flags, u8 cmd, gfp_t gfp) { struct ovs_header *ovs_header; struct ovs_vport_stats vport_stats; @@ -1870,7 +1881,7 @@ static int ovs_vport_cmd_fill_info(struct vport *vport, struct sk_buff *skb, goto nla_put_failure; if (!net_eq(net, dev_net(vport->dev))) { - int id = peernet2id_alloc(net, dev_net(vport->dev)); + int id = peernet2id_alloc(net, dev_net(vport->dev), gfp); if (nla_put_s32(skb, OVS_VPORT_ATTR_NETNSID, id)) goto nla_put_failure; @@ -1911,11 +1922,12 @@ struct sk_buff *ovs_vport_cmd_build_info(struct vport *vport, struct net *net, struct sk_buff *skb; int retval; - skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC); + skb = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!skb) return ERR_PTR(-ENOMEM); - retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd); + retval = ovs_vport_cmd_fill_info(vport, skb, net, portid, seq, 0, cmd, + GFP_KERNEL); BUG_ON(retval < 0); return skb; @@ -2048,7 +2060,7 @@ restart: err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_NEW); + OVS_VPORT_CMD_NEW, GFP_KERNEL); if (netdev_get_fwd_headroom(vport->dev) > dp->max_headroom) update_headroom(dp); @@ -2107,7 +2119,7 @@ static int ovs_vport_cmd_set(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_SET); + OVS_VPORT_CMD_SET, GFP_KERNEL); BUG_ON(err < 0); ovs_unlock(); @@ -2146,7 +2158,7 @@ static int ovs_vport_cmd_del(struct sk_buff *skb, struct genl_info *info) err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_DEL); + OVS_VPORT_CMD_DEL, GFP_KERNEL); BUG_ON(err < 0); /* the vport deletion may trigger dp headroom update */ @@ -2188,7 +2200,7 @@ static int ovs_vport_cmd_get(struct sk_buff *skb, struct genl_info *info) goto exit_unlock_free; err = ovs_vport_cmd_fill_info(vport, reply, genl_info_net(info), info->snd_portid, info->snd_seq, 0, - OVS_VPORT_CMD_GET); + OVS_VPORT_CMD_GET, GFP_ATOMIC); BUG_ON(err < 0); rcu_read_unlock(); @@ -2224,7 +2236,8 @@ static int ovs_vport_cmd_dump(struct sk_buff *skb, struct netlink_callback *cb) NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - OVS_VPORT_CMD_GET) < 0) + OVS_VPORT_CMD_GET, + GFP_ATOMIC) < 0) goto out; j++; @@ -2368,8 +2381,10 @@ static void __net_exit ovs_exit_net(struct net *dnet) struct net *net; LIST_HEAD(head); - ovs_ct_exit(dnet); ovs_lock(); + + ovs_ct_exit(dnet); + list_for_each_entry_safe(dp, dp_next, &ovs_net->dps, list_node) __dp_destroy(dp); diff --git a/net/openvswitch/vport-internal_dev.c b/net/openvswitch/vport-internal_dev.c index d2437b5b2f6a..baa33103108a 100644 --- a/net/openvswitch/vport-internal_dev.c +++ b/net/openvswitch/vport-internal_dev.c @@ -137,7 +137,7 @@ static void do_setup(struct net_device *netdev) netdev->priv_flags |= IFF_LIVE_ADDR_CHANGE | IFF_OPENVSWITCH | IFF_NO_QUEUE; netdev->needs_free_netdev = true; - netdev->priv_destructor = internal_dev_destructor; + netdev->priv_destructor = NULL; netdev->ethtool_ops = &internal_dev_ethtool_ops; netdev->rtnl_link_ops = &internal_dev_link_ops; @@ -159,7 +159,6 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) struct internal_dev *internal_dev; struct net_device *dev; int err; - bool free_vport = true; vport = ovs_vport_alloc(0, &ovs_internal_vport_ops, parms); if (IS_ERR(vport)) { @@ -190,10 +189,9 @@ static struct vport *internal_dev_create(const struct vport_parms *parms) rtnl_lock(); err = register_netdevice(vport->dev); - if (err) { - free_vport = false; + if (err) goto error_unlock; - } + vport->dev->priv_destructor = internal_dev_destructor; dev_set_promiscuity(vport->dev, 1); rtnl_unlock(); @@ -207,8 +205,7 @@ error_unlock: error_free_netdev: free_netdev(dev); error_free_vport: - if (free_vport) - ovs_vport_free(vport); + ovs_vport_free(vport); error: return ERR_PTR(err); } diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index bad144dfabc5..b2e4c4b192e6 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -384,7 +384,7 @@ static void __packet_set_status(struct packet_sock *po, void *frame, int status) smp_wmb(); } -static int __packet_get_status(struct packet_sock *po, void *frame) +static int __packet_get_status(const struct packet_sock *po, void *frame) { union tpacket_uhdr h; @@ -460,10 +460,10 @@ static __u32 __packet_set_timestamp(struct packet_sock *po, void *frame, return ts_status; } -static void *packet_lookup_frame(struct packet_sock *po, - struct packet_ring_buffer *rb, - unsigned int position, - int status) +static void *packet_lookup_frame(const struct packet_sock *po, + const struct packet_ring_buffer *rb, + unsigned int position, + int status) { unsigned int pg_vec_pos, frame_offset; union tpacket_uhdr h; @@ -544,7 +544,8 @@ static int prb_calc_retire_blk_tmo(struct packet_sock *po, msec = 1; div = ecmd.base.speed / 1000; } - } + } else + return DEFAULT_PRB_RETIRE_TOV; mbits = (blk_size_in_bytes * 8) / (1024 * 1024); @@ -758,7 +759,7 @@ static void prb_close_block(struct tpacket_kbdq_core *pkc1, struct tpacket_hdr_v1 *h1 = &pbd1->hdr.bh1; struct sock *sk = &po->sk; - if (po->stats.stats3.tp_drops) + if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; last_pkt = (struct tpacket3_hdr *)pkc1->prev; @@ -1083,10 +1084,10 @@ static void *packet_current_rx_frame(struct packet_sock *po, } } -static void *prb_lookup_block(struct packet_sock *po, - struct packet_ring_buffer *rb, - unsigned int idx, - int status) +static void *prb_lookup_block(const struct packet_sock *po, + const struct packet_ring_buffer *rb, + unsigned int idx, + int status) { struct tpacket_kbdq_core *pkc = GET_PBDQC_FROM_RB(rb); struct tpacket_block_desc *pbd = GET_PBLOCK_DESC(pkc, idx); @@ -1199,12 +1200,12 @@ static void packet_free_pending(struct packet_sock *po) #define ROOM_LOW 0x1 #define ROOM_NORMAL 0x2 -static bool __tpacket_has_room(struct packet_sock *po, int pow_off) +static bool __tpacket_has_room(const struct packet_sock *po, int pow_off) { int idx, len; - len = po->rx_ring.frame_max + 1; - idx = po->rx_ring.head; + len = READ_ONCE(po->rx_ring.frame_max) + 1; + idx = READ_ONCE(po->rx_ring.head); if (pow_off) idx += len >> pow_off; if (idx >= len) @@ -1212,12 +1213,12 @@ static bool __tpacket_has_room(struct packet_sock *po, int pow_off) return packet_lookup_frame(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } -static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off) +static bool __tpacket_v3_has_room(const struct packet_sock *po, int pow_off) { int idx, len; - len = po->rx_ring.prb_bdqc.knum_blocks; - idx = po->rx_ring.prb_bdqc.kactive_blk_num; + len = READ_ONCE(po->rx_ring.prb_bdqc.knum_blocks); + idx = READ_ONCE(po->rx_ring.prb_bdqc.kactive_blk_num); if (pow_off) idx += len >> pow_off; if (idx >= len) @@ -1225,15 +1226,18 @@ static bool __tpacket_v3_has_room(struct packet_sock *po, int pow_off) return prb_lookup_block(po, &po->rx_ring, idx, TP_STATUS_KERNEL); } -static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) +static int __packet_rcv_has_room(const struct packet_sock *po, + const struct sk_buff *skb) { - struct sock *sk = &po->sk; + const struct sock *sk = &po->sk; int ret = ROOM_NONE; if (po->prot_hook.func != tpacket_rcv) { - int avail = sk->sk_rcvbuf - atomic_read(&sk->sk_rmem_alloc) - - (skb ? skb->truesize : 0); - if (avail > (sk->sk_rcvbuf >> ROOM_POW_OFF)) + int rcvbuf = READ_ONCE(sk->sk_rcvbuf); + int avail = rcvbuf - atomic_read(&sk->sk_rmem_alloc) + - (skb ? skb->truesize : 0); + + if (avail > (rcvbuf >> ROOM_POW_OFF)) return ROOM_NORMAL; else if (avail > 0) return ROOM_LOW; @@ -1258,19 +1262,24 @@ static int __packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) static int packet_rcv_has_room(struct packet_sock *po, struct sk_buff *skb) { - int ret; - bool has_room; + int pressure, ret; - spin_lock_bh(&po->sk.sk_receive_queue.lock); ret = __packet_rcv_has_room(po, skb); - has_room = ret == ROOM_NORMAL; - if (po->pressure == has_room) - po->pressure = !has_room; - spin_unlock_bh(&po->sk.sk_receive_queue.lock); + pressure = ret != ROOM_NORMAL; + + if (READ_ONCE(po->pressure) != pressure) + WRITE_ONCE(po->pressure, pressure); return ret; } +static void packet_rcv_try_clear_pressure(struct packet_sock *po) +{ + if (READ_ONCE(po->pressure) && + __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) + WRITE_ONCE(po->pressure, 0); +} + static void packet_sock_destruct(struct sock *sk) { skb_queue_purge(&sk->sk_error_queue); @@ -1288,15 +1297,21 @@ static void packet_sock_destruct(struct sock *sk) static bool fanout_flow_is_huge(struct packet_sock *po, struct sk_buff *skb) { - u32 rxhash; + u32 *history = po->rollover->history; + u32 victim, rxhash; int i, count = 0; rxhash = skb_get_hash(skb); for (i = 0; i < ROLLOVER_HLEN; i++) - if (po->rollover->history[i] == rxhash) + if (READ_ONCE(history[i]) == rxhash) count++; - po->rollover->history[prandom_u32() % ROLLOVER_HLEN] = rxhash; + victim = prandom_u32() % ROLLOVER_HLEN; + + /* Avoid dirtying the cache line if possible */ + if (READ_ONCE(history[victim]) != rxhash) + WRITE_ONCE(history[victim], rxhash); + return count > (ROLLOVER_HLEN >> 1); } @@ -1351,7 +1366,7 @@ static unsigned int fanout_demux_rollover(struct packet_fanout *f, i = j = min_t(int, po->rollover->sock, num - 1); do { po_next = pkt_sk(f->arr[i]); - if (po_next != po_skip && !po_next->pressure && + if (po_next != po_skip && !READ_ONCE(po_next->pressure) && packet_rcv_has_room(po_next, skb) == ROOM_NORMAL) { if (i != j) po->rollover->sock = i; @@ -2126,10 +2141,8 @@ static int packet_rcv(struct sk_buff *skb, struct net_device *dev, drop_n_acct: is_drop_n_account = true; - spin_lock(&sk->sk_receive_queue.lock); - po->stats.stats1.tp_drops++; + atomic_inc(&po->tp_drops); atomic_inc(&sk->sk_drops); - spin_unlock(&sk->sk_receive_queue.lock); drop_n_restore: if (skb_head != skb->data && skb_shared(skb)) { @@ -2155,11 +2168,13 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, int skb_len = skb->len; unsigned int snaplen, res; unsigned long status = TP_STATUS_USER; - unsigned short macoff, netoff, hdrlen; + unsigned short macoff, hdrlen; + unsigned int netoff; struct sk_buff *copy_skb = NULL; struct timespec ts; __u32 ts_status; bool is_drop_n_account = false; + unsigned int slot_id = 0; bool do_vnet = false; /* struct tpacket{2,3}_hdr is aligned to a multiple of TPACKET_ALIGNMENT. @@ -2193,6 +2208,12 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, if (!res) goto drop_n_restore; + /* If we are flooded, just give up */ + if (__packet_rcv_has_room(po, skb) == ROOM_NONE) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } + if (skb->ip_summed == CHECKSUM_PARTIAL) status |= TP_STATUS_CSUMNOTREADY; else if (skb->pkt_type != PACKET_OUTGOING && @@ -2217,6 +2238,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, } macoff = netoff - maclen; } + if (netoff > USHRT_MAX) { + atomic_inc(&po->tp_drops); + goto drop_n_restore; + } if (po->tp_version <= TPACKET_V2) { if (macoff + snaplen > po->rx_ring.frame_size) { if (po->copy_thresh && @@ -2255,6 +2280,20 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, TP_STATUS_KERNEL, (macoff+snaplen)); if (!h.raw) goto drop_n_account; + + if (po->tp_version <= TPACKET_V2) { + slot_id = po->rx_ring.head; + if (test_bit(slot_id, po->rx_ring.rx_owner_map)) + goto drop_n_account; + __set_bit(slot_id, po->rx_ring.rx_owner_map); + } + + if (do_vnet && + virtio_net_hdr_from_skb(skb, h.raw + macoff - + sizeof(struct virtio_net_hdr), + vio_le(), true, 0)) + goto drop_n_account; + if (po->tp_version <= TPACKET_V2) { packet_increment_rx_head(po, &po->rx_ring); /* @@ -2263,16 +2302,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, * Anyways, moving it for V1/V2 only as V3 doesn't need this * at packet level. */ - if (po->stats.stats1.tp_drops) + if (atomic_read(&po->tp_drops)) status |= TP_STATUS_LOSING; } - if (do_vnet && - virtio_net_hdr_from_skb(skb, h.raw + macoff - - sizeof(struct virtio_net_hdr), - vio_le(), true, 0)) - goto drop_n_account; - po->stats.stats1.tp_packets++; if (copy_skb) { status |= TP_STATUS_COPY; @@ -2360,7 +2393,10 @@ static int tpacket_rcv(struct sk_buff *skb, struct net_device *dev, #endif if (po->tp_version <= TPACKET_V2) { + spin_lock(&sk->sk_receive_queue.lock); __packet_set_status(po, h.raw, status); + __clear_bit(slot_id, po->rx_ring.rx_owner_map); + spin_unlock(&sk->sk_receive_queue.lock); sk->sk_data_ready(sk); } else { prb_clear_blk_fill_status(&po->rx_ring); @@ -2379,9 +2415,9 @@ drop: return 0; drop_n_account: - is_drop_n_account = true; - po->stats.stats1.tp_drops++; spin_unlock(&sk->sk_receive_queue.lock); + atomic_inc(&po->tp_drops); + is_drop_n_account = true; sk->sk_data_ready(sk); kfree_skb(copy_skb); @@ -3325,8 +3361,7 @@ static int packet_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, if (skb == NULL) goto out; - if (pkt_sk(sk)->pressure) - packet_rcv_has_room(pkt_sk(sk), NULL); + packet_rcv_try_clear_pressure(pkt_sk(sk)); if (pkt_sk(sk)->has_vnet_hdr) { err = packet_rcv_vnet(msg, skb, &len); @@ -3898,6 +3933,7 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, void *data = &val; union tpacket_stats_u st; struct tpacket_rollover_stats rstats; + int drops; if (level != SOL_PACKET) return -ENOPROTOOPT; @@ -3914,14 +3950,17 @@ static int packet_getsockopt(struct socket *sock, int level, int optname, memcpy(&st, &po->stats, sizeof(st)); memset(&po->stats, 0, sizeof(po->stats)); spin_unlock_bh(&sk->sk_receive_queue.lock); + drops = atomic_xchg(&po->tp_drops, 0); if (po->tp_version == TPACKET_V3) { lv = sizeof(struct tpacket_stats_v3); - st.stats3.tp_packets += st.stats3.tp_drops; + st.stats3.tp_drops = drops; + st.stats3.tp_packets += drops; data = &st.stats3; } else { lv = sizeof(struct tpacket_stats); - st.stats1.tp_packets += st.stats1.tp_drops; + st.stats1.tp_drops = drops; + st.stats1.tp_packets += drops; data = &st.stats1; } @@ -4140,8 +4179,7 @@ static __poll_t packet_poll(struct file *file, struct socket *sock, TP_STATUS_KERNEL)) mask |= EPOLLIN | EPOLLRDNORM; } - if (po->pressure && __packet_rcv_has_room(po, NULL) == ROOM_NORMAL) - po->pressure = 0; + packet_rcv_try_clear_pressure(po); spin_unlock_bh(&sk->sk_receive_queue.lock); spin_lock_bh(&sk->sk_write_queue.lock); if (po->tx_ring.pg_vec) { @@ -4255,6 +4293,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, { struct pgv *pg_vec = NULL; struct packet_sock *po = pkt_sk(sk); + unsigned long *rx_owner_map = NULL; int was_running, order = 0; struct packet_ring_buffer *rb; struct sk_buff_head *rb_queue; @@ -4340,6 +4379,12 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } break; default: + if (!tx_ring) { + rx_owner_map = bitmap_alloc(req->tp_frame_nr, + GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO); + if (!rx_owner_map) + goto out_free_pg_vec; + } break; } } @@ -4369,6 +4414,8 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, err = 0; spin_lock_bh(&rb_queue->lock); swap(rb->pg_vec, pg_vec); + if (po->tp_version <= TPACKET_V2) + swap(rb->rx_owner_map, rx_owner_map); rb->frame_max = (req->tp_frame_nr - 1); rb->head = 0; rb->frame_size = req->tp_frame_size; @@ -4400,6 +4447,7 @@ static int packet_set_ring(struct sock *sk, union tpacket_req_u *req_u, } out_free_pg_vec: + bitmap_free(rx_owner_map); if (pg_vec) free_pg_vec(pg_vec, order, req->tp_block_nr); out: diff --git a/net/packet/internal.h b/net/packet/internal.h index c70a2794456f..907f4cd2a718 100644 --- a/net/packet/internal.h +++ b/net/packet/internal.h @@ -70,7 +70,10 @@ struct packet_ring_buffer { unsigned int __percpu *pending_refcnt; - struct tpacket_kbdq_core prb_bdqc; + union { + unsigned long *rx_owner_map; + struct tpacket_kbdq_core prb_bdqc; + }; }; extern struct mutex fanout_mutex; @@ -132,6 +135,7 @@ struct packet_sock { struct net_device __rcu *cached_dev; int (*xmit)(struct sk_buff *skb); struct packet_type prot_hook ____cacheline_aligned_in_smp; + atomic_t tp_drops ____cacheline_aligned_in_smp; }; static struct packet_sock *pkt_sk(struct sock *sk) diff --git a/net/phonet/socket.c b/net/phonet/socket.c index 96ea9f254ae9..76d499f6af9a 100644 --- a/net/phonet/socket.c +++ b/net/phonet/socket.c @@ -338,9 +338,9 @@ static __poll_t pn_socket_poll(struct file *file, struct socket *sock, if (sk->sk_state == TCP_CLOSE) return EPOLLERR; - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; - if (!skb_queue_empty(&pn->ctrlreq_queue)) + if (!skb_queue_empty_lockless(&pn->ctrlreq_queue)) mask |= EPOLLPRI; if (!mask && sk->sk_state == TCP_CLOSE_WAIT) return EPOLLHUP; diff --git a/net/psample/psample.c b/net/psample/psample.c index 66e4b61a350d..a3f7e35dccac 100644 --- a/net/psample/psample.c +++ b/net/psample/psample.c @@ -221,7 +221,7 @@ void psample_sample_packet(struct psample_group *group, struct sk_buff *skb, data_len = PSAMPLE_MAX_PACKET_SIZE - meta_len - NLA_HDRLEN - NLA_ALIGNTO; - nl_skb = genlmsg_new(meta_len + data_len, GFP_ATOMIC); + nl_skb = genlmsg_new(meta_len + nla_total_size(data_len), GFP_ATOMIC); if (unlikely(!nl_skb)) return; diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 88f98f27ad88..1ce1e710d025 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -196,7 +196,7 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, hdr->size = cpu_to_le32(len); hdr->confirm_rx = 0; - skb_put_padto(skb, ALIGN(len, 4)); + skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); mutex_lock(&node->ep_lock); if (node->ep) @@ -259,7 +259,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) unsigned int ver; size_t hdrlen; - if (len & 3) + if (len == 0 || len & 3) return -EINVAL; skb = netdev_alloc_skb(NULL, len); @@ -273,6 +273,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) switch (ver) { case QRTR_PROTO_VER_1: + if (len < sizeof(*v1)) + goto err; v1 = data; hdrlen = sizeof(*v1); @@ -286,6 +288,8 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) size = le32_to_cpu(v1->size); break; case QRTR_PROTO_VER_2: + if (len < sizeof(*v2)) + goto err; v2 = data; hdrlen = sizeof(*v2) + v2->optlen; @@ -711,7 +715,7 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, } mutex_unlock(&qrtr_node_lock); - qrtr_local_enqueue(node, skb, type, from, to); + qrtr_local_enqueue(NULL, skb, type, from, to); return 0; } @@ -763,20 +767,21 @@ static int qrtr_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) node = NULL; if (addr->sq_node == QRTR_NODE_BCAST) { - enqueue_fn = qrtr_bcast_enqueue; - if (addr->sq_port != QRTR_PORT_CTRL) { + if (addr->sq_port != QRTR_PORT_CTRL && + qrtr_local_nid != QRTR_NODE_BCAST) { release_sock(sk); return -ENOTCONN; } + enqueue_fn = qrtr_bcast_enqueue; } else if (addr->sq_node == ipc->us.sq_node) { enqueue_fn = qrtr_local_enqueue; } else { - enqueue_fn = qrtr_node_enqueue; node = qrtr_node_lookup(addr->sq_node); if (!node) { release_sock(sk); return -ECONNRESET; } + enqueue_fn = qrtr_node_enqueue; } plen = (len + 3) & ~3; @@ -999,6 +1004,7 @@ static int qrtr_release(struct socket *sock) sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); + sock_orphan(sk); sock->sk = NULL; if (!sock_flag(sk, SOCK_ZAPPED)) diff --git a/net/rds/message.c b/net/rds/message.c index 50f13f1d4ae0..2d43e13d6dd5 100644 --- a/net/rds/message.c +++ b/net/rds/message.c @@ -308,26 +308,20 @@ out: /* * RDS ops use this to grab SG entries from the rm's sg pool. */ -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret) +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents) { struct scatterlist *sg_first = (struct scatterlist *) &rm[1]; struct scatterlist *sg_ret; - if (WARN_ON(!ret)) - return NULL; - if (nents <= 0) { pr_warn("rds: alloc sgs failed! nents <= 0\n"); - *ret = -EINVAL; - return NULL; + return ERR_PTR(-EINVAL); } if (rm->m_used_sgs + nents > rm->m_total_sgs) { pr_warn("rds: alloc sgs failed! total %d used %d nents %d\n", rm->m_total_sgs, rm->m_used_sgs, nents); - *ret = -ENOMEM; - return NULL; + return ERR_PTR(-ENOMEM); } sg_ret = &sg_first[rm->m_used_sgs]; @@ -343,7 +337,6 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in unsigned int i; int num_sgs = DIV_ROUND_UP(total_len, PAGE_SIZE); int extra_bytes = num_sgs * sizeof(struct scatterlist); - int ret; rm = rds_message_alloc(extra_bytes, GFP_NOWAIT); if (!rm) @@ -352,10 +345,10 @@ struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned in set_bit(RDS_MSG_PAGEVEC, &rm->m_flags); rm->m_inc.i_hdr.h_len = cpu_to_be32(total_len); rm->data.op_nents = DIV_ROUND_UP(total_len, PAGE_SIZE); - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) { + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { rds_message_put(rm); - return ERR_PTR(ret); + return ERR_CAST(rm->data.op_sg); } for (i = 0; i < rm->data.op_nents; ++i) { diff --git a/net/rds/rdma.c b/net/rds/rdma.c index b340ed4fc43a..ca64d1c3231c 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -624,9 +624,11 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_active = 1; op->op_recverr = rs->rs_recverr; WARN_ON(!nr_pages); - op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); - if (!op->op_sg) + op->op_sg = rds_message_alloc_sgs(rm, nr_pages); + if (IS_ERR(op->op_sg)) { + ret = PTR_ERR(op->op_sg); goto out_pages; + } if (op->op_notify || op->op_recverr) { /* We allocate an uninitialized notifier here, because @@ -838,9 +840,11 @@ int rds_cmsg_atomic(struct rds_sock *rs, struct rds_message *rm, rm->atomic.op_silent = !!(args->flags & RDS_RDMA_SILENT); rm->atomic.op_active = 1; rm->atomic.op_recverr = rs->rs_recverr; - rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1, &ret); - if (!rm->atomic.op_sg) + rm->atomic.op_sg = rds_message_alloc_sgs(rm, 1); + if (IS_ERR(rm->atomic.op_sg)) { + ret = PTR_ERR(rm->atomic.op_sg); goto err; + } /* verify 8 byte-aligned */ if (args->local_addr & 0x7) { diff --git a/net/rds/rds.h b/net/rds/rds.h index 0d8f67cadd74..952fc5e68d75 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -845,8 +845,7 @@ rds_conn_connecting(struct rds_connection *conn) /* message.c */ struct rds_message *rds_message_alloc(unsigned int nents, gfp_t gfp); -struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents, - int *ret); +struct scatterlist *rds_message_alloc_sgs(struct rds_message *rm, int nents); int rds_message_copy_from_user(struct rds_message *rm, struct iov_iter *from, bool zcopy); struct rds_message *rds_message_map_pages(unsigned long *page_addrs, unsigned int total_len); diff --git a/net/rds/recv.c b/net/rds/recv.c index a42ba7fa06d5..dd15f93d2ef1 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -450,12 +450,13 @@ static int rds_still_queued(struct rds_sock *rs, struct rds_incoming *inc, int rds_notify_queue_get(struct rds_sock *rs, struct msghdr *msghdr) { struct rds_notifier *notifier; - struct rds_rdma_notify cmsg = { 0 }; /* fill holes with zero */ + struct rds_rdma_notify cmsg; unsigned int count = 0, max_messages = ~0U; unsigned long flags; LIST_HEAD(copy); int err = 0; + memset(&cmsg, 0, sizeof(cmsg)); /* fill holes with zero */ /* put_cmsg copies to user space and thus may sleep. We can't do this * with rs_lock held, so first grab as many notifications as we can stuff diff --git a/net/rds/send.c b/net/rds/send.c index 166dd578c1cc..c46b5fb0da89 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1264,9 +1264,11 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* Attach data to the rm */ if (payload_len) { - rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs, &ret); - if (!rm->data.op_sg) + rm->data.op_sg = rds_message_alloc_sgs(rm, num_sgs); + if (IS_ERR(rm->data.op_sg)) { + ret = PTR_ERR(rm->data.op_sg); goto out; + } ret = rds_message_copy_from_user(rm, &msg->msg_iter, zcopy); if (ret) goto out; diff --git a/net/rfkill/core.c b/net/rfkill/core.c index f9b08a6d8dbe..d1a955c79219 100644 --- a/net/rfkill/core.c +++ b/net/rfkill/core.c @@ -1002,10 +1002,13 @@ static void rfkill_sync_work(struct work_struct *work) int __must_check rfkill_register(struct rfkill *rfkill) { static unsigned long rfkill_no; - struct device *dev = &rfkill->dev; + struct device *dev; int error; - BUG_ON(!rfkill); + if (!rfkill) + return -EINVAL; + + dev = &rfkill->dev; mutex_lock(&rfkill_global_mutex); diff --git a/net/rxrpc/Makefile b/net/rxrpc/Makefile index 6ffb7e9887ce..ddd0f95713a9 100644 --- a/net/rxrpc/Makefile +++ b/net/rxrpc/Makefile @@ -25,6 +25,7 @@ rxrpc-y := \ peer_event.o \ peer_object.o \ recvmsg.o \ + rtt.o \ security.o \ sendmsg.o \ skbuff.o \ diff --git a/net/rxrpc/af_rxrpc.c b/net/rxrpc/af_rxrpc.c index 8c9bd3ae9edf..102c5715106f 100644 --- a/net/rxrpc/af_rxrpc.c +++ b/net/rxrpc/af_rxrpc.c @@ -194,6 +194,7 @@ static int rxrpc_bind(struct socket *sock, struct sockaddr *saddr, int len) service_in_use: write_unlock(&local->services_lock); rxrpc_unuse_local(local); + rxrpc_put_local(local); ret = -EADDRINUSE; error_unlock: release_sock(&rx->sk); @@ -284,7 +285,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, gfp_t gfp, rxrpc_notify_rx_t notify_rx, bool upgrade, - bool intr, + enum rxrpc_interruptibility interruptibility, unsigned int debug_id) { struct rxrpc_conn_parameters cp; @@ -309,7 +310,7 @@ struct rxrpc_call *rxrpc_kernel_begin_call(struct socket *sock, memset(&p, 0, sizeof(p)); p.user_call_ID = user_call_ID; p.tx_total_len = tx_total_len; - p.intr = intr; + p.interruptibility = interruptibility; memset(&cp, 0, sizeof(cp)); cp.local = rx->local; @@ -370,45 +371,18 @@ EXPORT_SYMBOL(rxrpc_kernel_end_call); * rxrpc_kernel_check_life - Check to see whether a call is still alive * @sock: The socket the call is on * @call: The call to check - * @_life: Where to store the life value * - * Allow a kernel service to find out whether a call is still alive - ie. we're - * getting ACKs from the server. Passes back in *_life a number representing - * the life state which can be compared to that returned by a previous call and - * return true if the call is still alive. - * - * If the life state stalls, rxrpc_kernel_probe_life() should be called and - * then 2RTT waited. + * Allow a kernel service to find out whether a call is still alive - + * ie. whether it has completed. */ bool rxrpc_kernel_check_life(const struct socket *sock, - const struct rxrpc_call *call, - u32 *_life) + const struct rxrpc_call *call) { - *_life = call->acks_latest; return call->state != RXRPC_CALL_COMPLETE; } EXPORT_SYMBOL(rxrpc_kernel_check_life); /** - * rxrpc_kernel_probe_life - Poke the peer to see if it's still alive - * @sock: The socket the call is on - * @call: The call to check - * - * In conjunction with rxrpc_kernel_check_life(), allow a kernel service to - * find out whether a call is still alive by pinging it. This should cause the - * life state to be bumped in about 2*RTT. - * - * The must be called in TASK_RUNNING state on pain of might_sleep() objecting. - */ -void rxrpc_kernel_probe_life(struct socket *sock, struct rxrpc_call *call) -{ - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, - rxrpc_propose_ack_ping_for_check_life); - rxrpc_send_ack_packet(call, true, NULL); -} -EXPORT_SYMBOL(rxrpc_kernel_probe_life); - -/** * rxrpc_kernel_get_epoch - Retrieve the epoch value from a call. * @sock: The socket the call is on * @call: The call to query @@ -902,6 +876,7 @@ static int rxrpc_release_sock(struct sock *sk) rxrpc_queue_work(&rxnet->client_conn_reaper); rxrpc_unuse_local(rx->local); + rxrpc_put_local(rx->local); rx->local = NULL; key_put(rx->key); rx->key = NULL; diff --git a/net/rxrpc/ar-internal.h b/net/rxrpc/ar-internal.h index 9796c45d2f6a..872f54c41a1d 100644 --- a/net/rxrpc/ar-internal.h +++ b/net/rxrpc/ar-internal.h @@ -7,6 +7,7 @@ #include <linux/atomic.h> #include <linux/seqlock.h> +#include <linux/win_minmax.h> #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/sock.h> @@ -203,6 +204,7 @@ struct rxrpc_skb_priv { struct rxrpc_security { const char *name; /* name of this service */ u8 security_index; /* security type provided */ + u32 no_key_abort; /* Abort code indicating no key */ /* Initialise a security service */ int (*init)(void); @@ -301,11 +303,14 @@ struct rxrpc_peer { #define RXRPC_RTT_CACHE_SIZE 32 spinlock_t rtt_input_lock; /* RTT lock for input routine */ ktime_t rtt_last_req; /* Time of last RTT request */ - u64 rtt; /* Current RTT estimate (in nS) */ - u64 rtt_sum; /* Sum of cache contents */ - u64 rtt_cache[RXRPC_RTT_CACHE_SIZE]; /* Determined RTT cache */ - u8 rtt_cursor; /* next entry at which to insert */ - u8 rtt_usage; /* amount of cache actually used */ + unsigned int rtt_count; /* Number of samples we've got */ + + u32 srtt_us; /* smoothed round trip time << 3 in usecs */ + u32 mdev_us; /* medium deviation */ + u32 mdev_max_us; /* maximal mdev for the last rtt period */ + u32 rttvar_us; /* smoothed mdev_max */ + u32 rto_j; /* Retransmission timeout in jiffies */ + u8 backoff; /* Backoff timeout */ u8 cong_cwnd; /* Congestion window size */ }; @@ -479,7 +484,7 @@ enum rxrpc_call_flag { RXRPC_CALL_BEGAN_RX_TIMER, /* We began the expect_rx_by timer */ RXRPC_CALL_RX_HEARD, /* The peer responded at least once to this call */ RXRPC_CALL_RX_UNDERRUN, /* Got data underrun */ - RXRPC_CALL_IS_INTR, /* The call is interruptible */ + RXRPC_CALL_DISCONNECTED, /* The call has been disconnected */ }; /* @@ -585,6 +590,7 @@ struct rxrpc_call { atomic_t usage; u16 service_id; /* service ID */ u8 security_ix; /* Security type */ + enum rxrpc_interruptibility interruptibility; /* At what point call may be interrupted */ u32 call_id; /* call ID on connection */ u32 cid; /* connection ID plus channel index */ int debug_id; /* debug ID for printks */ @@ -650,7 +656,6 @@ struct rxrpc_call { /* receive-phase ACK management */ u8 ackr_reason; /* reason to ACK */ - u16 ackr_skew; /* skew on packet being ACK'd */ rxrpc_serial_t ackr_serial; /* serial of packet being ACK'd */ rxrpc_serial_t ackr_first_seq; /* first sequence number received */ rxrpc_seq_t ackr_prev_seq; /* previous sequence number received */ @@ -663,7 +668,6 @@ struct rxrpc_call { /* transmission-phase ACK management */ ktime_t acks_latest_ts; /* Timestamp of latest ACK received */ - rxrpc_serial_t acks_latest; /* serial number of latest ACK received */ rxrpc_seq_t acks_lowest_nak; /* Lowest NACK in the buffer (or ==tx_hard_ack) */ rxrpc_seq_t acks_lost_top; /* tx_top at the time lost-ack ping sent */ rxrpc_serial_t acks_lost_ping; /* Serial number of probe ACK */ @@ -709,7 +713,7 @@ struct rxrpc_call_params { u32 normal; /* Max time since last call packet (msec) */ } timeouts; u8 nr_timeouts; /* Number of timeouts specified */ - bool intr; /* The call is interruptible */ + enum rxrpc_interruptibility interruptibility; /* How is interruptible is the call? */ }; struct rxrpc_send_params { @@ -744,7 +748,7 @@ int rxrpc_reject_call(struct rxrpc_sock *); /* * call_event.c */ -void rxrpc_propose_ACK(struct rxrpc_call *, u8, u16, u32, bool, bool, +void rxrpc_propose_ACK(struct rxrpc_call *, u8, u32, bool, bool, enum rxrpc_propose_ack_trace); void rxrpc_process_call(struct work_struct *); @@ -966,8 +970,9 @@ static inline void rxrpc_reduce_conn_timer(struct rxrpc_connection *conn, struct rxrpc_connection *rxrpc_find_service_conn_rcu(struct rxrpc_peer *, struct sk_buff *); struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *, gfp_t); -void rxrpc_new_incoming_connection(struct rxrpc_sock *, - struct rxrpc_connection *, struct sk_buff *); +void rxrpc_new_incoming_connection(struct rxrpc_sock *, struct rxrpc_connection *, + const struct rxrpc_security *, struct key *, + struct sk_buff *); void rxrpc_unpublish_service_conn(struct rxrpc_connection *); /* @@ -1008,6 +1013,16 @@ void rxrpc_unuse_local(struct rxrpc_local *); void rxrpc_queue_local(struct rxrpc_local *); void rxrpc_destroy_all_locals(struct rxrpc_net *); +static inline bool __rxrpc_unuse_local(struct rxrpc_local *local) +{ + return atomic_dec_return(&local->active_users) == 0; +} + +static inline bool __rxrpc_use_local(struct rxrpc_local *local) +{ + return atomic_fetch_add_unless(&local->active_users, 1, 0) != 0; +} + /* * misc.c */ @@ -1018,7 +1033,6 @@ extern unsigned long rxrpc_idle_ack_delay; extern unsigned int rxrpc_rx_window_size; extern unsigned int rxrpc_rx_mtu; extern unsigned int rxrpc_rx_jumbo_max; -extern unsigned long rxrpc_resend_timeout; extern const s8 rxrpc_ack_priority[]; @@ -1046,8 +1060,6 @@ void rxrpc_send_keepalive(struct rxrpc_peer *); * peer_event.c */ void rxrpc_error_report(struct sock *); -void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, - rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); void rxrpc_peer_keepalive_worker(struct work_struct *); /* @@ -1080,6 +1092,14 @@ void rxrpc_notify_socket(struct rxrpc_call *); int rxrpc_recvmsg(struct socket *, struct msghdr *, size_t, int); /* + * rtt.c + */ +void rxrpc_peer_add_rtt(struct rxrpc_call *, enum rxrpc_rtt_rx_trace, + rxrpc_serial_t, rxrpc_serial_t, ktime_t, ktime_t); +unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *, bool); +void rxrpc_peer_init_rtt(struct rxrpc_peer *); + +/* * rxkad.c */ #ifdef CONFIG_RXKAD @@ -1092,7 +1112,9 @@ extern const struct rxrpc_security rxkad; int __init rxrpc_init_security(void); void rxrpc_exit_security(void); int rxrpc_init_client_conn_security(struct rxrpc_connection *); -int rxrpc_init_server_conn_security(struct rxrpc_connection *); +bool rxrpc_look_up_server_security(struct rxrpc_local *, struct rxrpc_sock *, + const struct rxrpc_security **, struct key **, + struct sk_buff *); /* * sendmsg.c diff --git a/net/rxrpc/call_accept.c b/net/rxrpc/call_accept.c index 00c095d74145..7d8574f6b2da 100644 --- a/net/rxrpc/call_accept.c +++ b/net/rxrpc/call_accept.c @@ -97,7 +97,7 @@ static int rxrpc_service_prealloc_one(struct rxrpc_sock *rx, call->flags |= (1 << RXRPC_CALL_IS_SERVICE); call->state = RXRPC_CALL_SERVER_PREALLOC; - trace_rxrpc_call(call, rxrpc_call_new_service, + trace_rxrpc_call(call->debug_id, rxrpc_call_new_service, atomic_read(&call->usage), here, (const void *)user_call_ID); @@ -240,6 +240,22 @@ void rxrpc_discard_prealloc(struct rxrpc_sock *rx) } /* + * Ping the other end to fill our RTT cache and to retrieve the rwind + * and MTU parameters. + */ +static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb) +{ + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + ktime_t now = skb->tstamp; + + if (call->peer->rtt_count < 3 || + ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, + true, true, + rxrpc_propose_ack_ping_for_params); +} + +/* * Allocate a new incoming call from the prealloc pool, along with a connection * and a peer as necessary. */ @@ -247,6 +263,8 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, struct rxrpc_local *local, struct rxrpc_peer *peer, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_backlog *b = rx->backlog; @@ -294,7 +312,7 @@ static struct rxrpc_call *rxrpc_alloc_incoming_call(struct rxrpc_sock *rx, conn->params.local = rxrpc_get_local(local); conn->params.peer = peer; rxrpc_see_connection(conn); - rxrpc_new_incoming_connection(rx, conn, skb); + rxrpc_new_incoming_connection(rx, conn, sec, key, skb); } else { rxrpc_get_connection(conn); } @@ -332,9 +350,11 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + const struct rxrpc_security *sec = NULL; struct rxrpc_connection *conn; struct rxrpc_peer *peer = NULL; - struct rxrpc_call *call; + struct rxrpc_call *call = NULL; + struct key *key = NULL; _enter(""); @@ -345,9 +365,7 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, sp->hdr.seq, RX_INVALID_OPERATION, ESHUTDOWN); skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; skb->priority = RX_INVALID_OPERATION; - _leave(" = NULL [close]"); - call = NULL; - goto out; + goto no_call; } /* The peer, connection and call may all have sprung into existence due @@ -357,29 +375,19 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, */ conn = rxrpc_find_connection_rcu(local, skb, &peer); - call = rxrpc_alloc_incoming_call(rx, local, peer, conn, skb); + if (!conn && !rxrpc_look_up_server_security(local, rx, &sec, &key, skb)) + goto no_call; + + call = rxrpc_alloc_incoming_call(rx, local, peer, conn, sec, key, skb); + key_put(key); if (!call) { skb->mark = RXRPC_SKB_MARK_REJECT_BUSY; - _leave(" = NULL [busy]"); - call = NULL; - goto out; + goto no_call; } trace_rxrpc_receive(call, rxrpc_receive_incoming, sp->hdr.serial, sp->hdr.seq); - /* Lock the call to prevent rxrpc_kernel_send/recv_data() and - * sendmsg()/recvmsg() inconveniently stealing the mutex once the - * notification is generated. - * - * The BUG should never happen because the kernel should be well - * behaved enough not to access the call before the first notification - * event and userspace is prevented from doing so until the state is - * appropriate. - */ - if (!mutex_trylock(&call->user_mutex)) - BUG(); - /* Make the call live. */ rxrpc_incoming_call(rx, call, skb); conn = call->conn; @@ -420,6 +428,9 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, BUG(); } spin_unlock(&conn->state_lock); + spin_unlock(&rx->incoming_lock); + + rxrpc_send_ping(call, skb); if (call->state == RXRPC_CALL_SERVER_ACCEPTING) rxrpc_notify_socket(call); @@ -432,9 +443,12 @@ struct rxrpc_call *rxrpc_new_incoming_call(struct rxrpc_local *local, rxrpc_put_call(call, rxrpc_call_put); _leave(" = %p{%d}", call, call->debug_id); -out: - spin_unlock(&rx->incoming_lock); return call; + +no_call: + spin_unlock(&rx->incoming_lock); + _leave(" = NULL [%u]", skb->mark); + return NULL; } /* diff --git a/net/rxrpc/call_event.c b/net/rxrpc/call_event.c index bc2adeb3acb9..97ddf2f72a56 100644 --- a/net/rxrpc/call_event.c +++ b/net/rxrpc/call_event.c @@ -43,8 +43,7 @@ static void rxrpc_propose_ping(struct rxrpc_call *call, * propose an ACK be sent */ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate, - bool background, + u32 serial, bool immediate, bool background, enum rxrpc_propose_ack_trace why) { enum rxrpc_propose_ack_outcome outcome = rxrpc_propose_ack_use; @@ -69,14 +68,12 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, if (RXRPC_ACK_UPDATEABLE & (1 << ack_reason)) { outcome = rxrpc_propose_ack_update; call->ackr_serial = serial; - call->ackr_skew = skew; } if (!immediate) goto trace; } else if (prior > rxrpc_ack_priority[call->ackr_reason]) { call->ackr_reason = ack_reason; call->ackr_serial = serial; - call->ackr_skew = skew; } else { outcome = rxrpc_propose_ack_subsume; } @@ -114,8 +111,8 @@ static void __rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, } else { unsigned long now = jiffies, ack_at; - if (call->peer->rtt_usage > 0) - ack_at = nsecs_to_jiffies(call->peer->rtt); + if (call->peer->srtt_us != 0) + ack_at = usecs_to_jiffies(call->peer->srtt_us >> 3); else ack_at = expiry; @@ -137,11 +134,11 @@ trace: * propose an ACK be sent, locking the call structure */ void rxrpc_propose_ACK(struct rxrpc_call *call, u8 ack_reason, - u16 skew, u32 serial, bool immediate, bool background, + u32 serial, bool immediate, bool background, enum rxrpc_propose_ack_trace why) { spin_lock_bh(&call->lock); - __rxrpc_propose_ACK(call, ack_reason, skew, serial, + __rxrpc_propose_ACK(call, ack_reason, serial, immediate, background, why); spin_unlock_bh(&call->lock); } @@ -160,24 +157,18 @@ static void rxrpc_congestion_timeout(struct rxrpc_call *call) static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) { struct sk_buff *skb; - unsigned long resend_at; + unsigned long resend_at, rto_j; rxrpc_seq_t cursor, seq, top; - ktime_t now, max_age, oldest, ack_ts, timeout, min_timeo; + ktime_t now, max_age, oldest, ack_ts; int ix; u8 annotation, anno_type, retrans = 0, unacked = 0; _enter("{%d,%d}", call->tx_hard_ack, call->tx_top); - if (call->peer->rtt_usage > 1) - timeout = ns_to_ktime(call->peer->rtt * 3 / 2); - else - timeout = ms_to_ktime(rxrpc_resend_timeout); - min_timeo = ns_to_ktime((1000000000 / HZ) * 4); - if (ktime_before(timeout, min_timeo)) - timeout = min_timeo; + rto_j = call->peer->rto_j; now = ktime_get_real(); - max_age = ktime_sub(now, timeout); + max_age = ktime_sub(now, jiffies_to_usecs(rto_j)); spin_lock_bh(&call->lock); @@ -222,7 +213,7 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) } resend_at = nsecs_to_jiffies(ktime_to_ns(ktime_sub(now, oldest))); - resend_at += jiffies + rxrpc_resend_timeout; + resend_at += jiffies + rto_j; WRITE_ONCE(call->resend_at, resend_at); if (unacked) @@ -237,9 +228,9 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) rxrpc_timer_set_for_resend); spin_unlock_bh(&call->lock); ack_ts = ktime_sub(now, call->acks_latest_ts); - if (ktime_to_ns(ack_ts) < call->peer->rtt) + if (ktime_to_us(ack_ts) < (call->peer->srtt_us >> 3)) goto out; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); rxrpc_send_ack_packet(call, true, NULL); goto out; @@ -257,7 +248,18 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) if (anno_type != RXRPC_TX_ANNO_RETRANS) continue; + /* We need to reset the retransmission state, but we need to do + * so before we drop the lock as a new ACK/NAK may come in and + * confuse things + */ + annotation &= ~RXRPC_TX_ANNO_MASK; + annotation |= RXRPC_TX_ANNO_UNACK | RXRPC_TX_ANNO_RESENT; + call->rxtx_annotations[ix] = annotation; + skb = call->rxtx_buffer[ix]; + if (!skb) + continue; + rxrpc_get_skb(skb, rxrpc_skb_tx_got); spin_unlock_bh(&call->lock); @@ -271,24 +273,6 @@ static void rxrpc_resend(struct rxrpc_call *call, unsigned long now_j) rxrpc_free_skb(skb, rxrpc_skb_tx_freed); spin_lock_bh(&call->lock); - - /* We need to clear the retransmit state, but there are two - * things we need to be aware of: A new ACK/NAK might have been - * received and the packet might have been hard-ACK'd (in which - * case it will no longer be in the buffer). - */ - if (after(seq, call->tx_hard_ack)) { - annotation = call->rxtx_annotations[ix]; - anno_type = annotation & RXRPC_TX_ANNO_MASK; - if (anno_type == RXRPC_TX_ANNO_RETRANS || - anno_type == RXRPC_TX_ANNO_NAK) { - annotation &= ~RXRPC_TX_ANNO_MASK; - annotation |= RXRPC_TX_ANNO_UNACK; - } - annotation |= RXRPC_TX_ANNO_RESENT; - call->rxtx_annotations[ix] = annotation; - } - if (after(call->tx_hard_ack, seq)) seq = call->tx_hard_ack; } @@ -372,7 +356,7 @@ recheck_state: if (time_after_eq(now, t)) { trace_rxrpc_timer(call, rxrpc_timer_exp_keepalive, now); cmpxchg(&call->keepalive_at, t, now + MAX_JIFFY_OFFSET); - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, true, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, true, rxrpc_propose_ack_ping_for_keepalive); set_bit(RXRPC_CALL_EV_PING, &call->events); } @@ -407,7 +391,7 @@ recheck_state: send_ack = NULL; if (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events)) { call->acks_lost_top = call->tx_top; - rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, 0, true, false, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, 0, true, false, rxrpc_propose_ack_ping_for_lost_ack); send_ack = &call->acks_lost_ping; } diff --git a/net/rxrpc/call_object.c b/net/rxrpc/call_object.c index 217b12be9e08..d7f5db7b74fb 100644 --- a/net/rxrpc/call_object.c +++ b/net/rxrpc/call_object.c @@ -237,10 +237,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, return call; } - if (p->intr) - __set_bit(RXRPC_CALL_IS_INTR, &call->flags); + call->interruptibility = p->interruptibility; call->tx_total_len = p->tx_total_len; - trace_rxrpc_call(call, rxrpc_call_new_client, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_new_client, + atomic_read(&call->usage), here, (const void *)p->user_call_ID); /* We need to protect a partially set up call against the user as we @@ -288,10 +288,10 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, */ ret = rxrpc_connect_call(rx, call, cp, srx, gfp); if (ret < 0) - goto error; + goto error_attached_to_socket; - trace_rxrpc_call(call, rxrpc_call_connected, atomic_read(&call->usage), - here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_connected, + atomic_read(&call->usage), here, NULL); rxrpc_start_call_timer(call); @@ -308,18 +308,29 @@ struct rxrpc_call *rxrpc_new_client_call(struct rxrpc_sock *rx, error_dup_user_ID: write_unlock(&rx->call_lock); release_sock(&rx->sk); - ret = -EEXIST; - -error: __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, - RX_CALL_DEAD, ret); - trace_rxrpc_call(call, rxrpc_call_error, atomic_read(&call->usage), - here, ERR_PTR(ret)); + RX_CALL_DEAD, -EEXIST); + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(-EEXIST)); rxrpc_release_call(rx, call); mutex_unlock(&call->user_mutex); rxrpc_put_call(call, rxrpc_call_put); - _leave(" = %d", ret); - return ERR_PTR(ret); + _leave(" = -EEXIST"); + return ERR_PTR(-EEXIST); + + /* We got an error, but the call is attached to the socket and is in + * need of release. However, we might now race with recvmsg() when + * completing the call queues it. Return 0 from sys_sendmsg() and + * leave the error to recvmsg() to deal with. + */ +error_attached_to_socket: + trace_rxrpc_call(call->debug_id, rxrpc_call_error, + atomic_read(&call->usage), here, ERR_PTR(ret)); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); + __rxrpc_set_call_completion(call, RXRPC_CALL_LOCAL_ERROR, + RX_CALL_DEAD, ret); + _leave(" = c=%08x [err]", call->debug_id); + return call; } /* @@ -376,7 +387,8 @@ bool rxrpc_queue_call(struct rxrpc_call *call) if (n == 0) return false; if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued, n + 1, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued, n + 1, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -391,7 +403,8 @@ bool __rxrpc_queue_call(struct rxrpc_call *call) int n = atomic_read(&call->usage); ASSERTCMP(n, >=, 1); if (rxrpc_queue_work(&call->processor)) - trace_rxrpc_call(call, rxrpc_call_queued_ref, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_queued_ref, n, + here, NULL); else rxrpc_put_call(call, rxrpc_call_put_noqueue); return true; @@ -406,7 +419,8 @@ void rxrpc_see_call(struct rxrpc_call *call) if (call) { int n = atomic_read(&call->usage); - trace_rxrpc_call(call, rxrpc_call_seen, n, here, NULL); + trace_rxrpc_call(call->debug_id, rxrpc_call_seen, n, + here, NULL); } } @@ -418,7 +432,7 @@ void rxrpc_get_call(struct rxrpc_call *call, enum rxrpc_call_trace op) const void *here = __builtin_return_address(0); int n = atomic_inc_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(call->debug_id, op, n, here, NULL); } /* @@ -433,7 +447,8 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _enter("{%d,%d}", call->debug_id, atomic_read(&call->usage)); - trace_rxrpc_call(call, rxrpc_call_release, atomic_read(&call->usage), + trace_rxrpc_call(call->debug_id, rxrpc_call_release, + atomic_read(&call->usage), here, (const void *)call->flags); ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); @@ -476,7 +491,7 @@ void rxrpc_release_call(struct rxrpc_sock *rx, struct rxrpc_call *call) _debug("RELEASE CALL %p (%d CONN %p)", call, call->debug_id, conn); - if (conn) + if (conn && !test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) rxrpc_disconnect_call(call); for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) { @@ -526,12 +541,13 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) { struct rxrpc_net *rxnet = call->rxnet; const void *here = __builtin_return_address(0); + unsigned int debug_id = call->debug_id; int n; ASSERT(call != NULL); n = atomic_dec_return(&call->usage); - trace_rxrpc_call(call, op, n, here, NULL); + trace_rxrpc_call(debug_id, op, n, here, NULL); ASSERTCMP(n, >=, 0); if (n == 0) { _debug("call %d dead", call->debug_id); @@ -548,13 +564,14 @@ void rxrpc_put_call(struct rxrpc_call *call, enum rxrpc_call_trace op) } /* - * Final call destruction under RCU. + * Final call destruction - but must be done in process context. */ -static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +static void rxrpc_destroy_call(struct work_struct *work) { - struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + struct rxrpc_call *call = container_of(work, struct rxrpc_call, processor); struct rxrpc_net *rxnet = call->rxnet; + rxrpc_put_connection(call->conn); rxrpc_put_peer(call->peer); kfree(call->rxtx_buffer); kfree(call->rxtx_annotations); @@ -564,6 +581,22 @@ static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) } /* + * Final call destruction under RCU. + */ +static void rxrpc_rcu_destroy_call(struct rcu_head *rcu) +{ + struct rxrpc_call *call = container_of(rcu, struct rxrpc_call, rcu); + + if (in_softirq()) { + INIT_WORK(&call->processor, rxrpc_destroy_call); + if (!rxrpc_queue_work(&call->processor)) + BUG(); + } else { + rxrpc_destroy_call(&call->processor); + } +} + +/* * clean up a call */ void rxrpc_cleanup_call(struct rxrpc_call *call) @@ -578,7 +611,6 @@ void rxrpc_cleanup_call(struct rxrpc_call *call) ASSERTCMP(call->state, ==, RXRPC_CALL_COMPLETE); ASSERT(test_bit(RXRPC_CALL_RELEASED, &call->flags)); - ASSERTCMP(call->conn, ==, NULL); /* Clean up the Rx/Tx buffer */ for (i = 0; i < RXRPC_RXTX_BUFF_SIZE; i++) diff --git a/net/rxrpc/conn_client.c b/net/rxrpc/conn_client.c index aea82f909c60..90a51c0ee46d 100644 --- a/net/rxrpc/conn_client.c +++ b/net/rxrpc/conn_client.c @@ -651,13 +651,20 @@ static int rxrpc_wait_for_channel(struct rxrpc_call *call, gfp_t gfp) add_wait_queue_exclusive(&call->waitq, &myself); for (;;) { - if (test_bit(RXRPC_CALL_IS_INTR, &call->flags)) + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + case RXRPC_PREINTERRUPTIBLE: set_current_state(TASK_INTERRUPTIBLE); - else + break; + case RXRPC_UNINTERRUPTIBLE: + default: set_current_state(TASK_UNINTERRUPTIBLE); + break; + } if (call->call_id) break; - if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) && + if ((call->interruptibility == RXRPC_INTERRUPTIBLE || + call->interruptibility == RXRPC_PREINTERRUPTIBLE) && signal_pending(current)) { ret = -ERESTARTSYS; break; @@ -781,6 +788,7 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) u32 cid; spin_lock(&conn->channel_lock); + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); cid = call->cid; if (cid) { @@ -788,7 +796,6 @@ void rxrpc_disconnect_client_call(struct rxrpc_call *call) chan = &conn->channels[channel]; } trace_rxrpc_client(conn, channel, rxrpc_client_chan_disconnect); - call->conn = NULL; /* Calls that have never actually been assigned a channel can simply be * discarded. If the conn didn't get used either, it will follow @@ -904,7 +911,6 @@ out: spin_unlock(&rxnet->client_conn_cache_lock); out_2: spin_unlock(&conn->channel_lock); - rxrpc_put_connection(conn); _leave(""); return; diff --git a/net/rxrpc/conn_event.c b/net/rxrpc/conn_event.c index df6624c140be..488cb118fa3f 100644 --- a/net/rxrpc/conn_event.c +++ b/net/rxrpc/conn_event.c @@ -376,21 +376,7 @@ static void rxrpc_secure_connection(struct rxrpc_connection *conn) _enter("{%d}", conn->debug_id); ASSERT(conn->security_ix != 0); - - if (!conn->params.key) { - _debug("set up security"); - ret = rxrpc_init_server_conn_security(conn); - switch (ret) { - case 0: - break; - case -ENOENT: - abort_code = RX_CALL_DEAD; - goto abort; - default: - abort_code = RXKADNOAUTH; - goto abort; - } - } + ASSERT(conn->server_key); if (conn->security->issue_challenge(conn) < 0) { abort_code = RX_CALL_DEAD; @@ -452,16 +438,12 @@ again: /* * connection-level event processor */ -void rxrpc_process_connection(struct work_struct *work) +static void rxrpc_do_process_connection(struct rxrpc_connection *conn) { - struct rxrpc_connection *conn = - container_of(work, struct rxrpc_connection, processor); struct sk_buff *skb; u32 abort_code = RX_PROTOCOL_ERROR; int ret; - rxrpc_see_connection(conn); - if (test_and_clear_bit(RXRPC_CONN_EV_CHALLENGE, &conn->events)) rxrpc_secure_connection(conn); @@ -489,18 +471,32 @@ void rxrpc_process_connection(struct work_struct *work) } } -out: - rxrpc_put_connection(conn); - _leave(""); return; requeue_and_leave: skb_queue_head(&conn->rx_queue, skb); - goto out; + return; protocol_error: if (rxrpc_abort_connection(conn, ret, abort_code) < 0) goto requeue_and_leave; rxrpc_free_skb(skb, rxrpc_skb_rx_freed); - goto out; + return; +} + +void rxrpc_process_connection(struct work_struct *work) +{ + struct rxrpc_connection *conn = + container_of(work, struct rxrpc_connection, processor); + + rxrpc_see_connection(conn); + + if (__rxrpc_use_local(conn->params.local)) { + rxrpc_do_process_connection(conn); + rxrpc_unuse_local(conn->params.local); + } + + rxrpc_put_connection(conn); + _leave(""); + return; } diff --git a/net/rxrpc/conn_object.c b/net/rxrpc/conn_object.c index 434ef392212b..d76868acfa1a 100644 --- a/net/rxrpc/conn_object.c +++ b/net/rxrpc/conn_object.c @@ -212,9 +212,11 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) call->peer->cong_cwnd = call->cong_cwnd; - spin_lock_bh(&conn->params.peer->lock); - hlist_del_rcu(&call->error_link); - spin_unlock_bh(&conn->params.peer->lock); + if (!hlist_unhashed(&call->error_link)) { + spin_lock_bh(&call->peer->lock); + hlist_del_rcu(&call->error_link); + spin_unlock_bh(&call->peer->lock); + } if (rxrpc_is_client_call(call)) return rxrpc_disconnect_client_call(call); @@ -223,9 +225,8 @@ void rxrpc_disconnect_call(struct rxrpc_call *call) __rxrpc_disconnect_call(conn, call); spin_unlock(&conn->channel_lock); - call->conn = NULL; + set_bit(RXRPC_CALL_DISCONNECTED, &call->flags); conn->idle_timestamp = jiffies; - rxrpc_put_connection(conn); } /* diff --git a/net/rxrpc/conn_service.c b/net/rxrpc/conn_service.c index b30e13f6d95f..cd9440576f2d 100644 --- a/net/rxrpc/conn_service.c +++ b/net/rxrpc/conn_service.c @@ -148,6 +148,8 @@ struct rxrpc_connection *rxrpc_prealloc_service_connection(struct rxrpc_net *rxn */ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, struct rxrpc_connection *conn, + const struct rxrpc_security *sec, + struct key *key, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -160,6 +162,8 @@ void rxrpc_new_incoming_connection(struct rxrpc_sock *rx, conn->service_id = sp->hdr.serviceId; conn->security_ix = sp->hdr.securityIndex; conn->out_clientflag = 0; + conn->security = sec; + conn->server_key = key_get(key); if (conn->security_ix) conn->state = RXRPC_CONN_SERVICE_UNSECURED; else diff --git a/net/rxrpc/input.c b/net/rxrpc/input.c index ee95d1cd1cdf..5df738d527c9 100644 --- a/net/rxrpc/input.c +++ b/net/rxrpc/input.c @@ -91,11 +91,11 @@ static void rxrpc_congestion_management(struct rxrpc_call *call, /* We analyse the number of packets that get ACK'd per RTT * period and increase the window if we managed to fill it. */ - if (call->peer->rtt_usage == 0) + if (call->peer->rtt_count == 0) goto out; if (ktime_before(skb->tstamp, - ktime_add_ns(call->cong_tstamp, - call->peer->rtt))) + ktime_add_us(call->cong_tstamp, + call->peer->srtt_us >> 3))) goto out_no_clear_ca; change = rxrpc_cong_rtt_window_end; call->cong_tstamp = skb->tstamp; @@ -193,23 +193,6 @@ send_extra_data: } /* - * Ping the other end to fill our RTT cache and to retrieve the rwind - * and MTU parameters. - */ -static void rxrpc_send_ping(struct rxrpc_call *call, struct sk_buff *skb, - int skew) -{ - struct rxrpc_skb_priv *sp = rxrpc_skb(skb); - ktime_t now = skb->tstamp; - - if (call->peer->rtt_usage < 3 || - ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), now)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, - true, true, - rxrpc_propose_ack_ping_for_params); -} - -/* * Apply a hard ACK by advancing the Tx window. */ static bool rxrpc_rotate_tx_window(struct rxrpc_call *call, rxrpc_seq_t to, @@ -419,8 +402,7 @@ static void rxrpc_input_dup_data(struct rxrpc_call *call, rxrpc_seq_t seq, /* * Process a DATA packet, adding the packet to the Rx ring. */ -static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb, - u16 skew) +static void rxrpc_input_data(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); enum rxrpc_call_state state; @@ -600,18 +582,16 @@ skip: ack: if (ack) - rxrpc_propose_ACK(call, ack, skew, ack_serial, + rxrpc_propose_ACK(call, ack, ack_serial, immediate_ack, true, rxrpc_propose_ack_input_data); else - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, skew, serial, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, rxrpc_propose_ack_input_data); - if (sp->hdr.seq == READ_ONCE(call->rx_hard_ack) + 1) { - trace_rxrpc_notify_socket(call->debug_id, serial); - rxrpc_notify_socket(call); - } + trace_rxrpc_notify_socket(call->debug_id, serial); + rxrpc_notify_socket(call); unlock: spin_unlock(&call->input_lock); @@ -733,13 +713,12 @@ static void rxrpc_input_ackinfo(struct rxrpc_call *call, struct sk_buff *skb, ntohl(ackinfo->rxMTU), ntohl(ackinfo->maxMTU), rwind, ntohl(ackinfo->jumbo_max)); + if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) + rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (call->tx_winsize != rwind) { - if (rwind > RXRPC_RXTX_BUFF_SIZE - 1) - rwind = RXRPC_RXTX_BUFF_SIZE - 1; if (rwind > call->tx_winsize) wake = true; - trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, - ntohl(ackinfo->rwind), wake); + trace_rxrpc_rx_rwind_change(call, sp->hdr.serial, rwind, wake); call->tx_winsize = rwind; } @@ -813,6 +792,30 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, } /* + * Return true if the ACK is valid - ie. it doesn't appear to have regressed + * with respect to the ack state conveyed by preceding ACKs. + */ +static bool rxrpc_is_ack_valid(struct rxrpc_call *call, + rxrpc_seq_t first_pkt, rxrpc_seq_t prev_pkt) +{ + rxrpc_seq_t base = READ_ONCE(call->ackr_first_seq); + + if (after(first_pkt, base)) + return true; /* The window advanced */ + + if (before(first_pkt, base)) + return false; /* firstPacket regressed */ + + if (after_eq(prev_pkt, call->ackr_prev_seq)) + return true; /* previousPacket hasn't regressed. */ + + /* Some rx implementations put a serial number in previousPacket. */ + if (after_eq(prev_pkt, base + call->tx_winsize)) + return false; + return true; +} + +/* * Process an ACK packet. * * ack.firstPacket is the sequence number of the first soft-ACK'd/NAK'd packet @@ -822,8 +825,7 @@ static void rxrpc_input_soft_acks(struct rxrpc_call *call, u8 *acks, * soft-ACK means that the packet may be discarded and retransmission * requested. A phase is complete when all packets are hard-ACK'd. */ -static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, - u16 skew) +static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb) { struct rxrpc_ack_summary summary = { 0 }; struct rxrpc_skb_priv *sp = rxrpc_skb(skb); @@ -867,18 +869,21 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, if (buf.ack.reason == RXRPC_ACK_PING) { _proto("Rx ACK %%%u PING Request", sp->hdr.serial); rxrpc_propose_ACK(call, RXRPC_ACK_PING_RESPONSE, - skew, sp->hdr.serial, true, true, + sp->hdr.serial, true, true, rxrpc_propose_ack_respond_to_ping); } else if (sp->hdr.flags & RXRPC_REQUEST_ACK) { rxrpc_propose_ACK(call, RXRPC_ACK_REQUESTED, - skew, sp->hdr.serial, true, true, + sp->hdr.serial, true, true, rxrpc_propose_ack_respond_to_ack); } /* Discard any out-of-order or duplicate ACKs (outside lock). */ - if (before(first_soft_ack, call->ackr_first_seq) || - before(prev_pkt, call->ackr_prev_seq)) + if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { + trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + first_soft_ack, call->ackr_first_seq, + prev_pkt, call->ackr_prev_seq); return; + } buf.info.rxMTU = 0; ioffset = offset + nr_acks + 3; @@ -889,11 +894,13 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, spin_lock(&call->input_lock); /* Discard any out-of-order or duplicate ACKs (inside lock). */ - if (before(first_soft_ack, call->ackr_first_seq) || - before(prev_pkt, call->ackr_prev_seq)) + if (!rxrpc_is_ack_valid(call, first_soft_ack, prev_pkt)) { + trace_rxrpc_rx_discard_ack(call->debug_id, sp->hdr.serial, + first_soft_ack, call->ackr_first_seq, + prev_pkt, call->ackr_prev_seq); goto out; + } call->acks_latest_ts = skb->tstamp; - call->acks_latest = sp->hdr.serial; call->ackr_first_seq = first_soft_ack; call->ackr_prev_seq = prev_pkt; @@ -948,7 +955,7 @@ static void rxrpc_input_ack(struct rxrpc_call *call, struct sk_buff *skb, RXRPC_TX_ANNO_LAST && summary.nr_acks == call->tx_top - hard_ack && rxrpc_is_client_call(call)) - rxrpc_propose_ACK(call, RXRPC_ACK_PING, skew, sp->hdr.serial, + rxrpc_propose_ACK(call, RXRPC_ACK_PING, sp->hdr.serial, false, true, rxrpc_propose_ack_ping_for_lost_reply); @@ -1004,7 +1011,7 @@ static void rxrpc_input_abort(struct rxrpc_call *call, struct sk_buff *skb) * Process an incoming call packet. */ static void rxrpc_input_call_packet(struct rxrpc_call *call, - struct sk_buff *skb, u16 skew) + struct sk_buff *skb) { struct rxrpc_skb_priv *sp = rxrpc_skb(skb); unsigned long timo; @@ -1023,11 +1030,11 @@ static void rxrpc_input_call_packet(struct rxrpc_call *call, switch (sp->hdr.type) { case RXRPC_PACKET_TYPE_DATA: - rxrpc_input_data(call, skb, skew); + rxrpc_input_data(call, skb); break; case RXRPC_PACKET_TYPE_ACK: - rxrpc_input_ack(call, skb, skew); + rxrpc_input_ack(call, skb); break; case RXRPC_PACKET_TYPE_BUSY: @@ -1181,7 +1188,6 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) struct rxrpc_peer *peer = NULL; struct rxrpc_sock *rx = NULL; unsigned int channel; - int skew = 0; _enter("%p", udp_sk); @@ -1309,15 +1315,8 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) goto out; } - /* Note the serial number skew here */ - skew = (int)sp->hdr.serial - (int)conn->hi_serial; - if (skew >= 0) { - if (skew > 0) - conn->hi_serial = sp->hdr.serial; - } else { - skew = -skew; - skew = min(skew, 65535); - } + if ((int)sp->hdr.serial - (int)conn->hi_serial > 0) + conn->hi_serial = sp->hdr.serial; /* Call-bound packets are routed by connection channel. */ channel = sp->hdr.cid & RXRPC_CHANNELMASK; @@ -1380,11 +1379,9 @@ int rxrpc_input_packet(struct sock *udp_sk, struct sk_buff *skb) call = rxrpc_new_incoming_call(local, rx, skb); if (!call) goto reject_packet; - rxrpc_send_ping(call, skb, skew); - mutex_unlock(&call->user_mutex); } - rxrpc_input_call_packet(call, skb, skew); + rxrpc_input_call_packet(call, skb); goto discard; discard: diff --git a/net/rxrpc/key.c b/net/rxrpc/key.c index 83e3357a65a6..7369d023b8b0 100644 --- a/net/rxrpc/key.c +++ b/net/rxrpc/key.c @@ -31,7 +31,7 @@ static void rxrpc_free_preparse_s(struct key_preparsed_payload *); static void rxrpc_destroy(struct key *); static void rxrpc_destroy_s(struct key *); static void rxrpc_describe(const struct key *, struct seq_file *); -static long rxrpc_read(const struct key *, char __user *, size_t); +static long rxrpc_read(const struct key *, char *, size_t); /* * rxrpc defined keys take an arbitrary string as the description and an @@ -1040,12 +1040,12 @@ EXPORT_SYMBOL(rxrpc_get_null_key); * - this returns the result in XDR form */ static long rxrpc_read(const struct key *key, - char __user *buffer, size_t buflen) + char *buffer, size_t buflen) { const struct rxrpc_key_token *token; const struct krb5_principal *princ; size_t size; - __be32 __user *xdr, *oldxdr; + __be32 *xdr, *oldxdr; u32 cnlen, toksize, ntoks, tok, zero; u16 toksizes[AFSTOKEN_MAX]; int loop; @@ -1122,30 +1122,25 @@ static long rxrpc_read(const struct key *key, if (!buffer || buflen < size) return size; - xdr = (__be32 __user *) buffer; + xdr = (__be32 *)buffer; zero = 0; #define ENCODE(x) \ do { \ - __be32 y = htonl(x); \ - if (put_user(y, xdr++) < 0) \ - goto fault; \ + *xdr++ = htonl(x); \ } while(0) #define ENCODE_DATA(l, s) \ do { \ u32 _l = (l); \ ENCODE(l); \ - if (copy_to_user(xdr, (s), _l) != 0) \ - goto fault; \ - if (_l & 3 && \ - copy_to_user((u8 __user *)xdr + _l, &zero, 4 - (_l & 3)) != 0) \ - goto fault; \ + memcpy(xdr, (s), _l); \ + if (_l & 3) \ + memcpy((u8 *)xdr + _l, &zero, 4 - (_l & 3)); \ xdr += (_l + 3) >> 2; \ } while(0) #define ENCODE64(x) \ do { \ __be64 y = cpu_to_be64(x); \ - if (copy_to_user(xdr, &y, 8) != 0) \ - goto fault; \ + memcpy(xdr, &y, 8); \ xdr += 8 >> 2; \ } while(0) #define ENCODE_STR(s) \ @@ -1236,8 +1231,4 @@ static long rxrpc_read(const struct key *key, ASSERTCMP((char __user *) xdr - buffer, ==, size); _leave(" = %zu", size); return size; - -fault: - _leave(" = -EFAULT"); - return -EFAULT; } diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 72a6e12a9304..ce65db43f36b 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -165,15 +165,6 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) goto error; } - /* we want to set the don't fragment bit */ - opt = IPV6_PMTUDISC_DO; - ret = kernel_setsockopt(local->socket, SOL_IPV6, IPV6_MTU_DISCOVER, - (char *) &opt, sizeof(opt)); - if (ret < 0) { - _debug("setsockopt failed"); - goto error; - } - /* Fall through and set IPv4 options too otherwise we don't get * errors from IPv4 packets sent through the IPv6 socket. */ @@ -364,11 +355,14 @@ void rxrpc_queue_local(struct rxrpc_local *local) void rxrpc_put_local(struct rxrpc_local *local) { const void *here = __builtin_return_address(0); + unsigned int debug_id; int n; if (local) { + debug_id = local->debug_id; + n = atomic_dec_return(&local->usage); - trace_rxrpc_local(local->debug_id, rxrpc_local_put, n, here); + trace_rxrpc_local(debug_id, rxrpc_local_put, n, here); if (n == 0) call_rcu(&local->rcu, rxrpc_local_rcu); @@ -380,14 +374,11 @@ void rxrpc_put_local(struct rxrpc_local *local) */ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) { - unsigned int au; - local = rxrpc_get_local_maybe(local); if (!local) return NULL; - au = atomic_fetch_add_unless(&local->active_users, 1, 0); - if (au == 0) { + if (!__rxrpc_use_local(local)) { rxrpc_put_local(local); return NULL; } @@ -401,14 +392,11 @@ struct rxrpc_local *rxrpc_use_local(struct rxrpc_local *local) */ void rxrpc_unuse_local(struct rxrpc_local *local) { - unsigned int au; - if (local) { - au = atomic_dec_return(&local->active_users); - if (au == 0) + if (__rxrpc_unuse_local(local)) { + rxrpc_get_local(local); rxrpc_queue_local(local); - else - rxrpc_put_local(local); + } } } @@ -462,7 +450,7 @@ static void rxrpc_local_processor(struct work_struct *work) do { again = false; - if (atomic_read(&local->active_users) == 0) { + if (!__rxrpc_use_local(local)) { rxrpc_local_destroyer(local); break; } @@ -476,6 +464,8 @@ static void rxrpc_local_processor(struct work_struct *work) rxrpc_process_local_events(local); again = true; } + + __rxrpc_unuse_local(local); } while (again); rxrpc_put_local(local); diff --git a/net/rxrpc/misc.c b/net/rxrpc/misc.c index 214405f75346..d4144fd86f84 100644 --- a/net/rxrpc/misc.c +++ b/net/rxrpc/misc.c @@ -63,11 +63,6 @@ unsigned int rxrpc_rx_mtu = 5692; */ unsigned int rxrpc_rx_jumbo_max = 4; -/* - * Time till packet resend (in milliseconds). - */ -unsigned long rxrpc_resend_timeout = 4 * HZ; - const s8 rxrpc_ack_priority[] = { [0] = 0, [RXRPC_ACK_DELAY] = 1, diff --git a/net/rxrpc/output.c b/net/rxrpc/output.c index a0b6abfbd277..905484a50357 100644 --- a/net/rxrpc/output.c +++ b/net/rxrpc/output.c @@ -87,7 +87,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, *_top = top; pkt->ack.bufferSpace = htons(8); - pkt->ack.maxSkew = htons(call->ackr_skew); + pkt->ack.maxSkew = htons(0); pkt->ack.firstPacket = htonl(hard_ack + 1); pkt->ack.previousPacket = htonl(call->ackr_prev_seq); pkt->ack.serial = htonl(serial); @@ -129,7 +129,7 @@ static size_t rxrpc_fill_out_ack(struct rxrpc_connection *conn, int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, rxrpc_serial_t *_serial) { - struct rxrpc_connection *conn = NULL; + struct rxrpc_connection *conn; struct rxrpc_ack_buffer *pkt; struct msghdr msg; struct kvec iov[2]; @@ -139,18 +139,14 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, int ret; u8 reason; - spin_lock_bh(&call->lock); - if (call->conn) - conn = rxrpc_get_connection_maybe(call->conn); - spin_unlock_bh(&call->lock); - if (!conn) + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; pkt = kzalloc(sizeof(*pkt), GFP_KERNEL); - if (!pkt) { - rxrpc_put_connection(conn); + if (!pkt) return -ENOMEM; - } + + conn = call->conn; msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; @@ -228,7 +224,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, if (ping) clear_bit(RXRPC_CALL_PINGING, &call->flags); rxrpc_propose_ACK(call, pkt->ack.reason, - ntohs(pkt->ack.maxSkew), ntohl(pkt->ack.serial), false, true, rxrpc_propose_ack_retry_tx); @@ -245,7 +240,6 @@ int rxrpc_send_ack_packet(struct rxrpc_call *call, bool ping, } out: - rxrpc_put_connection(conn); kfree(pkt); return ret; } @@ -255,7 +249,7 @@ out: */ int rxrpc_send_abort_packet(struct rxrpc_call *call) { - struct rxrpc_connection *conn = NULL; + struct rxrpc_connection *conn; struct rxrpc_abort_buffer pkt; struct msghdr msg; struct kvec iov[1]; @@ -272,13 +266,11 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) test_bit(RXRPC_CALL_TX_LAST, &call->flags)) return 0; - spin_lock_bh(&call->lock); - if (call->conn) - conn = rxrpc_get_connection_maybe(call->conn); - spin_unlock_bh(&call->lock); - if (!conn) + if (test_bit(RXRPC_CALL_DISCONNECTED, &call->flags)) return -ECONNRESET; + conn = call->conn; + msg.msg_name = &call->peer->srx.transport; msg.msg_namelen = call->peer->srx.transport_len; msg.msg_control = NULL; @@ -313,8 +305,6 @@ int rxrpc_send_abort_packet(struct rxrpc_call *call) trace_rxrpc_tx_packet(call->debug_id, &pkt.whdr, rxrpc_tx_point_call_abort); rxrpc_tx_backoff(call, ret); - - rxrpc_put_connection(conn); return ret; } @@ -379,7 +369,7 @@ int rxrpc_send_data_packet(struct rxrpc_call *call, struct sk_buff *skb, (test_and_clear_bit(RXRPC_CALL_EV_ACK_LOST, &call->events) || retrans || call->cong_mode == RXRPC_CALL_SLOW_START || - (call->peer->rtt_usage < 3 && sp->hdr.seq & 1) || + (call->peer->rtt_count < 3 && sp->hdr.seq & 1) || ktime_before(ktime_add_ms(call->peer->rtt_last_req, 1000), ktime_get_real()))) whdr.flags |= RXRPC_REQUEST_ACK; @@ -433,13 +423,10 @@ done: if (whdr.flags & RXRPC_REQUEST_ACK) { call->peer->rtt_last_req = skb->tstamp; trace_rxrpc_rtt_tx(call, rxrpc_rtt_tx_data, serial); - if (call->peer->rtt_usage > 1) { + if (call->peer->rtt_count > 1) { unsigned long nowj = jiffies, ack_lost_at; - ack_lost_at = nsecs_to_jiffies(2 * call->peer->rtt); - if (ack_lost_at < 1) - ack_lost_at = 1; - + ack_lost_at = rxrpc_get_rto_backoff(call->peer, retrans); ack_lost_at += nowj; WRITE_ONCE(call->ack_lost_at, ack_lost_at); rxrpc_reduce_call_timer(call, ack_lost_at, nowj, @@ -484,41 +471,21 @@ send_fragmentable: skb->tstamp = ktime_get_real(); switch (conn->params.local->srx.transport.family) { + case AF_INET6: case AF_INET: opt = IP_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IP, IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IP_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, SOL_IP, - IP_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } - break; - -#ifdef CONFIG_AF_RXRPC_IPV6 - case AF_INET6: - opt = IPV6_PMTUDISC_DONT; - ret = kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - if (ret == 0) { - ret = kernel_sendmsg(conn->params.local->socket, &msg, - iov, 2, len); - conn->params.peer->last_tx_at = ktime_get_seconds(); - - opt = IPV6_PMTUDISC_DO; - kernel_setsockopt(conn->params.local->socket, - SOL_IPV6, IPV6_MTU_DISCOVER, - (char *)&opt, sizeof(opt)); - } + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); + ret = kernel_sendmsg(conn->params.local->socket, &msg, + iov, 2, len); + conn->params.peer->last_tx_at = ktime_get_seconds(); + + opt = IP_PMTUDISC_DO; + kernel_setsockopt(conn->params.local->socket, + SOL_IP, IP_MTU_DISCOVER, + (char *)&opt, sizeof(opt)); break; -#endif } if (ret < 0) diff --git a/net/rxrpc/peer_event.c b/net/rxrpc/peer_event.c index e92e0526e0dc..02ffe730163b 100644 --- a/net/rxrpc/peer_event.c +++ b/net/rxrpc/peer_event.c @@ -296,52 +296,6 @@ static void rxrpc_distribute_error(struct rxrpc_peer *peer, int error, } /* - * Add RTT information to cache. This is called in softirq mode and has - * exclusive access to the peer RTT data. - */ -void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, - rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, - ktime_t send_time, ktime_t resp_time) -{ - struct rxrpc_peer *peer = call->peer; - s64 rtt; - u64 sum = peer->rtt_sum, avg; - u8 cursor = peer->rtt_cursor, usage = peer->rtt_usage; - - rtt = ktime_to_ns(ktime_sub(resp_time, send_time)); - if (rtt < 0) - return; - - spin_lock(&peer->rtt_input_lock); - - /* Replace the oldest datum in the RTT buffer */ - sum -= peer->rtt_cache[cursor]; - sum += rtt; - peer->rtt_cache[cursor] = rtt; - peer->rtt_cursor = (cursor + 1) & (RXRPC_RTT_CACHE_SIZE - 1); - peer->rtt_sum = sum; - if (usage < RXRPC_RTT_CACHE_SIZE) { - usage++; - peer->rtt_usage = usage; - } - - spin_unlock(&peer->rtt_input_lock); - - /* Now recalculate the average */ - if (usage == RXRPC_RTT_CACHE_SIZE) { - avg = sum / RXRPC_RTT_CACHE_SIZE; - } else { - avg = sum; - do_div(avg, usage); - } - - /* Don't need to update this under lock */ - peer->rtt = avg; - trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, rtt, - usage, avg); -} - -/* * Perform keep-alive pings. */ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, @@ -364,27 +318,31 @@ static void rxrpc_peer_keepalive_dispatch(struct rxrpc_net *rxnet, if (!rxrpc_get_peer_maybe(peer)) continue; - spin_unlock_bh(&rxnet->peer_hash_lock); + if (__rxrpc_use_local(peer->local)) { + spin_unlock_bh(&rxnet->peer_hash_lock); - keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; - slot = keepalive_at - base; - _debug("%02x peer %u t=%d {%pISp}", - cursor, peer->debug_id, slot, &peer->srx.transport); + keepalive_at = peer->last_tx_at + RXRPC_KEEPALIVE_TIME; + slot = keepalive_at - base; + _debug("%02x peer %u t=%d {%pISp}", + cursor, peer->debug_id, slot, &peer->srx.transport); - if (keepalive_at <= base || - keepalive_at > base + RXRPC_KEEPALIVE_TIME) { - rxrpc_send_keepalive(peer); - slot = RXRPC_KEEPALIVE_TIME; - } + if (keepalive_at <= base || + keepalive_at > base + RXRPC_KEEPALIVE_TIME) { + rxrpc_send_keepalive(peer); + slot = RXRPC_KEEPALIVE_TIME; + } - /* A transmission to this peer occurred since last we examined - * it so put it into the appropriate future bucket. - */ - slot += cursor; - slot &= mask; - spin_lock_bh(&rxnet->peer_hash_lock); - list_add_tail(&peer->keepalive_link, - &rxnet->peer_keepalive[slot & mask]); + /* A transmission to this peer occurred since last we + * examined it so put it into the appropriate future + * bucket. + */ + slot += cursor; + slot &= mask; + spin_lock_bh(&rxnet->peer_hash_lock); + list_add_tail(&peer->keepalive_link, + &rxnet->peer_keepalive[slot & mask]); + rxrpc_unuse_local(peer->local); + } rxrpc_put_peer_locked(peer); } diff --git a/net/rxrpc/peer_object.c b/net/rxrpc/peer_object.c index 9c3ac96f71cb..e011594adcd1 100644 --- a/net/rxrpc/peer_object.c +++ b/net/rxrpc/peer_object.c @@ -216,7 +216,7 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) peer = kzalloc(sizeof(struct rxrpc_peer), gfp); if (peer) { atomic_set(&peer->usage, 1); - peer->local = local; + peer->local = rxrpc_get_local(local); INIT_HLIST_HEAD(&peer->error_targets); peer->service_conns = RB_ROOT; seqlock_init(&peer->service_conn_lock); @@ -224,6 +224,8 @@ struct rxrpc_peer *rxrpc_alloc_peer(struct rxrpc_local *local, gfp_t gfp) spin_lock_init(&peer->rtt_input_lock); peer->debug_id = atomic_inc_return(&rxrpc_debug_id); + rxrpc_peer_init_rtt(peer); + if (RXRPC_TX_SMSS > 2190) peer->cong_cwnd = 2; else if (RXRPC_TX_SMSS > 1095) @@ -307,7 +309,6 @@ void rxrpc_new_incoming_peer(struct rxrpc_sock *rx, struct rxrpc_local *local, unsigned long hash_key; hash_key = rxrpc_peer_hash_key(local, &peer->srx); - peer->local = local; rxrpc_init_peer(rx, peer, hash_key); spin_lock(&rxnet->peer_hash_lock); @@ -382,7 +383,7 @@ struct rxrpc_peer *rxrpc_get_peer(struct rxrpc_peer *peer) int n; n = atomic_inc_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_got, n, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n, here); return peer; } @@ -396,7 +397,7 @@ struct rxrpc_peer *rxrpc_get_peer_maybe(struct rxrpc_peer *peer) if (peer) { int n = atomic_fetch_add_unless(&peer->usage, 1, 0); if (n > 0) - trace_rxrpc_peer(peer, rxrpc_peer_got, n + 1, here); + trace_rxrpc_peer(peer->debug_id, rxrpc_peer_got, n + 1, here); else peer = NULL; } @@ -417,6 +418,7 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) list_del_init(&peer->keepalive_link); spin_unlock_bh(&rxnet->peer_hash_lock); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } @@ -426,11 +428,13 @@ static void __rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id; int n; if (peer) { + debug_id = peer->debug_id; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) __rxrpc_put_peer(peer); } @@ -443,13 +447,15 @@ void rxrpc_put_peer(struct rxrpc_peer *peer) void rxrpc_put_peer_locked(struct rxrpc_peer *peer) { const void *here = __builtin_return_address(0); + unsigned int debug_id = peer->debug_id; int n; n = atomic_dec_return(&peer->usage); - trace_rxrpc_peer(peer, rxrpc_peer_put, n, here); + trace_rxrpc_peer(debug_id, rxrpc_peer_put, n, here); if (n == 0) { hash_del_rcu(&peer->hash_link); list_del_init(&peer->keepalive_link); + rxrpc_put_local(peer->local); kfree_rcu(peer, rcu); } } @@ -491,14 +497,24 @@ void rxrpc_kernel_get_peer(struct socket *sock, struct rxrpc_call *call, EXPORT_SYMBOL(rxrpc_kernel_get_peer); /** - * rxrpc_kernel_get_rtt - Get a call's peer RTT + * rxrpc_kernel_get_srtt - Get a call's peer smoothed RTT * @sock: The socket on which the call is in progress. * @call: The call to query + * @_srtt: Where to store the SRTT value. * - * Get the call's peer RTT. + * Get the call's peer smoothed RTT in uS. */ -u64 rxrpc_kernel_get_rtt(struct socket *sock, struct rxrpc_call *call) +bool rxrpc_kernel_get_srtt(struct socket *sock, struct rxrpc_call *call, + u32 *_srtt) { - return call->peer->rtt; + struct rxrpc_peer *peer = call->peer; + + if (peer->rtt_count == 0) { + *_srtt = 1000000; /* 1S */ + return false; + } + + *_srtt = call->peer->srtt_us >> 3; + return true; } -EXPORT_SYMBOL(rxrpc_kernel_get_rtt); +EXPORT_SYMBOL(rxrpc_kernel_get_srtt); diff --git a/net/rxrpc/proc.c b/net/rxrpc/proc.c index b9d053e42821..543afd9bd664 100644 --- a/net/rxrpc/proc.c +++ b/net/rxrpc/proc.c @@ -68,7 +68,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) "Proto Local " " Remote " " SvID ConnID CallID End Use State Abort " - " UserID TxSeq TW RxSeq RW RxSerial RxTimo\n"); + " DebugId TxSeq TW RxSeq RW RxSerial RxTimo\n"); return 0; } @@ -100,7 +100,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) rx_hard_ack = READ_ONCE(call->rx_hard_ack); seq_printf(seq, "UDP %-47.47s %-47.47s %4x %08x %08x %s %3u" - " %-8.8s %08x %lx %08x %02x %08x %02x %08x %06lx\n", + " %-8.8s %08x %08x %08x %02x %08x %02x %08x %06lx\n", lbuff, rbuff, call->service_id, @@ -110,7 +110,7 @@ static int rxrpc_call_seq_show(struct seq_file *seq, void *v) atomic_read(&call->usage), rxrpc_call_states[call->state], call->abort_code, - call->user_call_ID, + call->debug_id, tx_hard_ack, READ_ONCE(call->tx_top) - tx_hard_ack, rx_hard_ack, READ_ONCE(call->rx_top) - rx_hard_ack, call->rx_serial, @@ -222,7 +222,7 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) seq_puts(seq, "Proto Local " " Remote " - " Use CW MTU LastUse RTT Rc\n" + " Use CW MTU LastUse RTT RTO\n" ); return 0; } @@ -236,15 +236,15 @@ static int rxrpc_peer_seq_show(struct seq_file *seq, void *v) now = ktime_get_seconds(); seq_printf(seq, "UDP %-47.47s %-47.47s %3u" - " %3u %5u %6llus %12llu %2u\n", + " %3u %5u %6llus %8u %8u\n", lbuff, rbuff, atomic_read(&peer->usage), peer->cong_cwnd, peer->mtu, now - peer->last_tx_at, - peer->rtt, - peer->rtt_cursor); + peer->srtt_us >> 3, + jiffies_to_usecs(peer->rto_j)); return 0; } diff --git a/net/rxrpc/recvmsg.c b/net/rxrpc/recvmsg.c index 5abf46cf9e6c..ba5d9c2885b0 100644 --- a/net/rxrpc/recvmsg.c +++ b/net/rxrpc/recvmsg.c @@ -141,7 +141,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) ASSERTCMP(call->rx_hard_ack, ==, call->rx_top); if (call->state == RXRPC_CALL_CLIENT_RECV_REPLY) { - rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, 0, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_IDLE, serial, false, true, rxrpc_propose_ack_terminal_ack); //rxrpc_send_ack_packet(call, false, NULL); } @@ -159,7 +159,7 @@ static void rxrpc_end_rx_phase(struct rxrpc_call *call, rxrpc_serial_t serial) call->state = RXRPC_CALL_SERVER_ACK_REQUEST; call->expect_req_by = jiffies + MAX_JIFFY_OFFSET; write_unlock_bh(&call->state_lock); - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, false, true, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, false, true, rxrpc_propose_ack_processing_op); break; default: @@ -212,7 +212,7 @@ static void rxrpc_rotate_rx_window(struct rxrpc_call *call) if (after_eq(hard_ack, call->ackr_consumed + 2) || after_eq(top, call->ackr_seen + 2) || (hard_ack == top && after(hard_ack, call->ackr_consumed))) - rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, 0, serial, + rxrpc_propose_ACK(call, RXRPC_ACK_DELAY, serial, true, true, rxrpc_propose_ack_rotate_rx); if (call->ackr_reason && call->ackr_reason != RXRPC_ACK_DELAY) @@ -449,7 +449,7 @@ try_again: list_empty(&rx->recvmsg_q) && rx->sk.sk_state != RXRPC_SERVER_LISTENING) { release_sock(&rx->sk); - return -ENODATA; + return -EAGAIN; } if (list_empty(&rx->recvmsg_q)) { @@ -526,7 +526,7 @@ try_again: goto error_unlock_call; } - if (msg->msg_name) { + if (msg->msg_name && call->peer) { struct sockaddr_rxrpc *srx = msg->msg_name; size_t len = sizeof(call->peer->srx); diff --git a/net/rxrpc/rtt.c b/net/rxrpc/rtt.c new file mode 100644 index 000000000000..928d8b34a3ee --- /dev/null +++ b/net/rxrpc/rtt.c @@ -0,0 +1,195 @@ +// SPDX-License-Identifier: GPL-2.0 +/* RTT/RTO calculation. + * + * Adapted from TCP for AF_RXRPC by David Howells (dhowells@redhat.com) + * + * https://tools.ietf.org/html/rfc6298 + * https://tools.ietf.org/html/rfc1122#section-4.2.3.1 + * http://ccr.sigcomm.org/archive/1995/jan95/ccr-9501-partridge87.pdf + */ + +#include <linux/net.h> +#include "ar-internal.h" + +#define RXRPC_RTO_MAX ((unsigned)(120 * HZ)) +#define RXRPC_TIMEOUT_INIT ((unsigned)(1*HZ)) /* RFC6298 2.1 initial RTO value */ +#define rxrpc_jiffies32 ((u32)jiffies) /* As rxrpc_jiffies32 */ +#define rxrpc_min_rtt_wlen 300 /* As sysctl_tcp_min_rtt_wlen */ + +static u32 rxrpc_rto_min_us(struct rxrpc_peer *peer) +{ + return 200; +} + +static u32 __rxrpc_set_rto(const struct rxrpc_peer *peer) +{ + return _usecs_to_jiffies((peer->srtt_us >> 3) + peer->rttvar_us); +} + +static u32 rxrpc_bound_rto(u32 rto) +{ + return min(rto, RXRPC_RTO_MAX); +} + +/* + * Called to compute a smoothed rtt estimate. The data fed to this + * routine either comes from timestamps, or from segments that were + * known _not_ to have been retransmitted [see Karn/Partridge + * Proceedings SIGCOMM 87]. The algorithm is from the SIGCOMM 88 + * piece by Van Jacobson. + * NOTE: the next three routines used to be one big routine. + * To save cycles in the RFC 1323 implementation it was better to break + * it up into three procedures. -- erics + */ +static void rxrpc_rtt_estimator(struct rxrpc_peer *peer, long sample_rtt_us) +{ + long m = sample_rtt_us; /* RTT */ + u32 srtt = peer->srtt_us; + + /* The following amusing code comes from Jacobson's + * article in SIGCOMM '88. Note that rtt and mdev + * are scaled versions of rtt and mean deviation. + * This is designed to be as fast as possible + * m stands for "measurement". + * + * On a 1990 paper the rto value is changed to: + * RTO = rtt + 4 * mdev + * + * Funny. This algorithm seems to be very broken. + * These formulae increase RTO, when it should be decreased, increase + * too slowly, when it should be increased quickly, decrease too quickly + * etc. I guess in BSD RTO takes ONE value, so that it is absolutely + * does not matter how to _calculate_ it. Seems, it was trap + * that VJ failed to avoid. 8) + */ + if (srtt != 0) { + m -= (srtt >> 3); /* m is now error in rtt est */ + srtt += m; /* rtt = 7/8 rtt + 1/8 new */ + if (m < 0) { + m = -m; /* m is now abs(error) */ + m -= (peer->mdev_us >> 2); /* similar update on mdev */ + /* This is similar to one of Eifel findings. + * Eifel blocks mdev updates when rtt decreases. + * This solution is a bit different: we use finer gain + * for mdev in this case (alpha*beta). + * Like Eifel it also prevents growth of rto, + * but also it limits too fast rto decreases, + * happening in pure Eifel. + */ + if (m > 0) + m >>= 3; + } else { + m -= (peer->mdev_us >> 2); /* similar update on mdev */ + } + + peer->mdev_us += m; /* mdev = 3/4 mdev + 1/4 new */ + if (peer->mdev_us > peer->mdev_max_us) { + peer->mdev_max_us = peer->mdev_us; + if (peer->mdev_max_us > peer->rttvar_us) + peer->rttvar_us = peer->mdev_max_us; + } + } else { + /* no previous measure. */ + srtt = m << 3; /* take the measured time to be rtt */ + peer->mdev_us = m << 1; /* make sure rto = 3*rtt */ + peer->rttvar_us = max(peer->mdev_us, rxrpc_rto_min_us(peer)); + peer->mdev_max_us = peer->rttvar_us; + } + + peer->srtt_us = max(1U, srtt); +} + +/* + * Calculate rto without backoff. This is the second half of Van Jacobson's + * routine referred to above. + */ +static void rxrpc_set_rto(struct rxrpc_peer *peer) +{ + u32 rto; + + /* 1. If rtt variance happened to be less 50msec, it is hallucination. + * It cannot be less due to utterly erratic ACK generation made + * at least by solaris and freebsd. "Erratic ACKs" has _nothing_ + * to do with delayed acks, because at cwnd>2 true delack timeout + * is invisible. Actually, Linux-2.4 also generates erratic + * ACKs in some circumstances. + */ + rto = __rxrpc_set_rto(peer); + + /* 2. Fixups made earlier cannot be right. + * If we do not estimate RTO correctly without them, + * all the algo is pure shit and should be replaced + * with correct one. It is exactly, which we pretend to do. + */ + + /* NOTE: clamping at RXRPC_RTO_MIN is not required, current algo + * guarantees that rto is higher. + */ + peer->rto_j = rxrpc_bound_rto(rto); +} + +static void rxrpc_ack_update_rtt(struct rxrpc_peer *peer, long rtt_us) +{ + if (rtt_us < 0) + return; + + //rxrpc_update_rtt_min(peer, rtt_us); + rxrpc_rtt_estimator(peer, rtt_us); + rxrpc_set_rto(peer); + + /* RFC6298: only reset backoff on valid RTT measurement. */ + peer->backoff = 0; +} + +/* + * Add RTT information to cache. This is called in softirq mode and has + * exclusive access to the peer RTT data. + */ +void rxrpc_peer_add_rtt(struct rxrpc_call *call, enum rxrpc_rtt_rx_trace why, + rxrpc_serial_t send_serial, rxrpc_serial_t resp_serial, + ktime_t send_time, ktime_t resp_time) +{ + struct rxrpc_peer *peer = call->peer; + s64 rtt_us; + + rtt_us = ktime_to_us(ktime_sub(resp_time, send_time)); + if (rtt_us < 0) + return; + + spin_lock(&peer->rtt_input_lock); + rxrpc_ack_update_rtt(peer, rtt_us); + if (peer->rtt_count < 3) + peer->rtt_count++; + spin_unlock(&peer->rtt_input_lock); + + trace_rxrpc_rtt_rx(call, why, send_serial, resp_serial, + peer->srtt_us >> 3, peer->rto_j); +} + +/* + * Get the retransmission timeout to set in jiffies, backing it off each time + * we retransmit. + */ +unsigned long rxrpc_get_rto_backoff(struct rxrpc_peer *peer, bool retrans) +{ + u64 timo_j; + u8 backoff = READ_ONCE(peer->backoff); + + timo_j = peer->rto_j; + timo_j <<= backoff; + if (retrans && timo_j * 2 <= RXRPC_RTO_MAX) + WRITE_ONCE(peer->backoff, backoff + 1); + + if (timo_j < 1) + timo_j = 1; + + return timo_j; +} + +void rxrpc_peer_init_rtt(struct rxrpc_peer *peer) +{ + peer->rto_j = RXRPC_TIMEOUT_INIT; + peer->mdev_us = jiffies_to_usecs(RXRPC_TIMEOUT_INIT); + peer->backoff = 0; + //minmax_reset(&peer->rtt_min, rxrpc_jiffies32, ~0U); +} diff --git a/net/rxrpc/rxkad.c b/net/rxrpc/rxkad.c index ae8cd8926456..49e0b0fde24c 100644 --- a/net/rxrpc/rxkad.c +++ b/net/rxrpc/rxkad.c @@ -618,9 +618,9 @@ static int rxkad_issue_challenge(struct rxrpc_connection *conn) u32 serial; int ret; - _enter("{%d,%x}", conn->debug_id, key_serial(conn->params.key)); + _enter("{%d,%x}", conn->debug_id, key_serial(conn->server_key)); - ret = key_validate(conn->params.key); + ret = key_validate(conn->server_key); if (ret < 0) return ret; @@ -1114,7 +1114,7 @@ static int rxkad_verify_response(struct rxrpc_connection *conn, ret = rxkad_decrypt_ticket(conn, skb, ticket, ticket_len, &session_key, &expiry, _abort_code); if (ret < 0) - goto temporary_error_free_resp; + goto temporary_error_free_ticket; /* use the session key from inside the ticket to decrypt the * response */ @@ -1196,7 +1196,6 @@ protocol_error: temporary_error_free_ticket: kfree(ticket); -temporary_error_free_resp: kfree(response); temporary_error: /* Ignore the response packet if we got a temporary error such as @@ -1243,6 +1242,7 @@ static void rxkad_exit(void) const struct rxrpc_security rxkad = { .name = "rxkad", .security_index = RXRPC_SECURITY_RXKAD, + .no_key_abort = RXKADUNKNOWNKEY, .init = rxkad_init, .exit = rxkad_exit, .init_connection_security = rxkad_init_connection_security, diff --git a/net/rxrpc/security.c b/net/rxrpc/security.c index 2e78f0cc7ef1..fe79f514f47a 100644 --- a/net/rxrpc/security.c +++ b/net/rxrpc/security.c @@ -101,62 +101,58 @@ int rxrpc_init_client_conn_security(struct rxrpc_connection *conn) } /* - * initialise the security on a server connection + * Find the security key for a server connection. */ -int rxrpc_init_server_conn_security(struct rxrpc_connection *conn) +bool rxrpc_look_up_server_security(struct rxrpc_local *local, struct rxrpc_sock *rx, + const struct rxrpc_security **_sec, + struct key **_key, + struct sk_buff *skb) { const struct rxrpc_security *sec; - struct rxrpc_local *local = conn->params.local; - struct rxrpc_sock *rx; - struct key *key; - key_ref_t kref; + struct rxrpc_skb_priv *sp = rxrpc_skb(skb); + key_ref_t kref = NULL; char kdesc[5 + 1 + 3 + 1]; _enter(""); - sprintf(kdesc, "%u:%u", conn->service_id, conn->security_ix); + sprintf(kdesc, "%u:%u", sp->hdr.serviceId, sp->hdr.securityIndex); - sec = rxrpc_security_lookup(conn->security_ix); + sec = rxrpc_security_lookup(sp->hdr.securityIndex); if (!sec) { - _leave(" = -ENOKEY [lookup]"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVS", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } - /* find the service */ - read_lock(&local->services_lock); - rx = rcu_dereference_protected(local->service, - lockdep_is_held(&local->services_lock)); - if (rx && (rx->srx.srx_service == conn->service_id || - rx->second_service == conn->service_id)) - goto found_service; + if (sp->hdr.securityIndex == RXRPC_SECURITY_NONE) + goto out; - /* the service appears to have died */ - read_unlock(&local->services_lock); - _leave(" = -ENOENT"); - return -ENOENT; - -found_service: if (!rx->securities) { - read_unlock(&local->services_lock); - _leave(" = -ENOKEY"); - return -ENOKEY; + trace_rxrpc_abort(0, "SVR", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + RX_INVALID_OPERATION, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = RX_INVALID_OPERATION; + return false; } /* look through the service's keyring */ kref = keyring_search(make_key_ref(rx->securities, 1UL), &key_type_rxrpc_s, kdesc); if (IS_ERR(kref)) { - read_unlock(&local->services_lock); - _leave(" = %ld [search]", PTR_ERR(kref)); - return PTR_ERR(kref); + trace_rxrpc_abort(0, "SVK", + sp->hdr.cid, sp->hdr.callNumber, sp->hdr.seq, + sec->no_key_abort, EKEYREJECTED); + skb->mark = RXRPC_SKB_MARK_REJECT_ABORT; + skb->priority = sec->no_key_abort; + return false; } - key = key_ref_to_ptr(kref); - read_unlock(&local->services_lock); - - conn->server_key = key; - conn->security = sec; - - _leave(" = 0"); - return 0; +out: + *_sec = sec; + *_key = key_ref_to_ptr(kref); + return true; } diff --git a/net/rxrpc/sendmsg.c b/net/rxrpc/sendmsg.c index bae14438f869..732c7ae56afd 100644 --- a/net/rxrpc/sendmsg.c +++ b/net/rxrpc/sendmsg.c @@ -18,6 +18,21 @@ #include "ar-internal.h" /* + * Return true if there's sufficient Tx queue space. + */ +static bool rxrpc_check_tx_space(struct rxrpc_call *call, rxrpc_seq_t *_tx_win) +{ + unsigned int win_size = + min_t(unsigned int, call->tx_winsize, + call->cong_cwnd + call->cong_extra); + rxrpc_seq_t tx_win = READ_ONCE(call->tx_hard_ack); + + if (_tx_win) + *_tx_win = tx_win; + return call->tx_top - tx_win < win_size; +} + +/* * Wait for space to appear in the Tx queue or a signal to occur. */ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, @@ -26,9 +41,7 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, { for (;;) { set_current_state(TASK_INTERRUPTIBLE); - if (call->tx_top - call->tx_hard_ack < - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) + if (rxrpc_check_tx_space(call, NULL)) return 0; if (call->state >= RXRPC_CALL_COMPLETE) @@ -49,40 +62,36 @@ static int rxrpc_wait_for_tx_window_intr(struct rxrpc_sock *rx, * Wait for space to appear in the Tx queue uninterruptibly, but with * a timeout of 2*RTT if no progress was made and a signal occurred. */ -static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, +static int rxrpc_wait_for_tx_window_waitall(struct rxrpc_sock *rx, struct rxrpc_call *call) { rxrpc_seq_t tx_start, tx_win; - signed long rtt2, timeout; - u64 rtt; + signed long rtt, timeout; - rtt = READ_ONCE(call->peer->rtt); - rtt2 = nsecs_to_jiffies64(rtt) * 2; - if (rtt2 < 1) - rtt2 = 1; + rtt = READ_ONCE(call->peer->srtt_us) >> 3; + rtt = usecs_to_jiffies(rtt) * 2; + if (rtt < 2) + rtt = 2; - timeout = rtt2; + timeout = rtt; tx_start = READ_ONCE(call->tx_hard_ack); for (;;) { set_current_state(TASK_UNINTERRUPTIBLE); tx_win = READ_ONCE(call->tx_hard_ack); - if (call->tx_top - tx_win < - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) + if (rxrpc_check_tx_space(call, &tx_win)) return 0; if (call->state >= RXRPC_CALL_COMPLETE) return call->error; - if (test_bit(RXRPC_CALL_IS_INTR, &call->flags) && - timeout == 0 && + if (timeout == 0 && tx_win == tx_start && signal_pending(current)) return -EINTR; if (tx_win != tx_start) { - timeout = rtt2; + timeout = rtt; tx_start = tx_win; } @@ -92,6 +101,26 @@ static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, } /* + * Wait for space to appear in the Tx queue uninterruptibly. + */ +static int rxrpc_wait_for_tx_window_nonintr(struct rxrpc_sock *rx, + struct rxrpc_call *call, + long *timeo) +{ + for (;;) { + set_current_state(TASK_UNINTERRUPTIBLE); + if (rxrpc_check_tx_space(call, NULL)) + return 0; + + if (call->state >= RXRPC_CALL_COMPLETE) + return call->error; + + trace_rxrpc_transmit(call, rxrpc_transmit_wait); + *timeo = schedule_timeout(*timeo); + } +} + +/* * wait for space to appear in the transmit/ACK window * - caller holds the socket locked */ @@ -108,10 +137,19 @@ static int rxrpc_wait_for_tx_window(struct rxrpc_sock *rx, add_wait_queue(&call->waitq, &myself); - if (waitall) - ret = rxrpc_wait_for_tx_window_nonintr(rx, call); - else - ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); + switch (call->interruptibility) { + case RXRPC_INTERRUPTIBLE: + if (waitall) + ret = rxrpc_wait_for_tx_window_waitall(rx, call); + else + ret = rxrpc_wait_for_tx_window_intr(rx, call, timeo); + break; + case RXRPC_PREINTERRUPTIBLE: + case RXRPC_UNINTERRUPTIBLE: + default: + ret = rxrpc_wait_for_tx_window_nonintr(rx, call, timeo); + break; + } remove_wait_queue(&call->waitq, &myself); set_current_state(TASK_RUNNING); @@ -232,16 +270,9 @@ static int rxrpc_queue_packet(struct rxrpc_sock *rx, struct rxrpc_call *call, _debug("need instant resend %d", ret); rxrpc_instant_resend(call, ix); } else { - unsigned long now = jiffies, resend_at; + unsigned long now = jiffies; + unsigned long resend_at = now + call->peer->rto_j; - if (call->peer->rtt_usage > 1) - resend_at = nsecs_to_jiffies(call->peer->rtt * 3 / 2); - else - resend_at = rxrpc_resend_timeout; - if (resend_at < 1) - resend_at = 1; - - resend_at += now; WRITE_ONCE(call->resend_at, resend_at); rxrpc_reduce_call_timer(call, resend_at, now, rxrpc_timer_set_for_send); @@ -275,7 +306,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, /* this should be in poll */ sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) + if (sk->sk_shutdown & SEND_SHUTDOWN) return -EPIPE; more = msg->msg_flags & MSG_MORE; @@ -302,9 +333,7 @@ static int rxrpc_send_data(struct rxrpc_sock *rx, _debug("alloc"); - if (call->tx_top - call->tx_hard_ack >= - min_t(unsigned int, call->tx_winsize, - call->cong_cwnd + call->cong_extra)) { + if (!rxrpc_check_tx_space(call, NULL)) { ret = -EAGAIN; if (msg->msg_flags & MSG_DONTWAIT) goto maybe_error; @@ -618,7 +647,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) .call.tx_total_len = -1, .call.user_call_ID = 0, .call.nr_timeouts = 0, - .call.intr = true, + .call.interruptibility = RXRPC_INTERRUPTIBLE, .abort_code = 0, .command = RXRPC_CMD_SEND_DATA, .exclusive = false, @@ -653,6 +682,9 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) if (IS_ERR(call)) return PTR_ERR(call); /* ... and we have the call lock. */ + ret = 0; + if (READ_ONCE(call->state) == RXRPC_CALL_COMPLETE) + goto out_put_unlock; } else { switch (READ_ONCE(call->state)) { case RXRPC_CALL_UNINITIALISED: @@ -660,6 +692,7 @@ int rxrpc_do_sendmsg(struct rxrpc_sock *rx, struct msghdr *msg, size_t len) case RXRPC_CALL_SERVER_PREALLOC: case RXRPC_CALL_SERVER_SECURING: case RXRPC_CALL_SERVER_ACCEPTING: + rxrpc_put_call(call, rxrpc_call_put); ret = -EBUSY; goto error_release_sock; default: diff --git a/net/rxrpc/sysctl.c b/net/rxrpc/sysctl.c index 1e3fa67d91aa..265a38bc5ce1 100644 --- a/net/rxrpc/sysctl.c +++ b/net/rxrpc/sysctl.c @@ -72,15 +72,6 @@ static struct ctl_table rxrpc_sysctl_table[] = { .extra1 = (void *)&one_jiffy, .extra2 = (void *)&max_jiffies, }, - { - .procname = "resend_timeout", - .data = &rxrpc_resend_timeout, - .maxlen = sizeof(unsigned long), - .mode = 0644, - .proc_handler = proc_doulongvec_ms_jiffies_minmax, - .extra1 = (void *)&one_jiffy, - .extra2 = (void *)&max_jiffies, - }, /* Non-time values */ { diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 2b43cacf82af..1a8f2f85ea1a 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -43,17 +43,20 @@ static int tcf_connmark_act(struct sk_buff *skb, const struct tc_action *a, tcf_lastuse_update(&ca->tcf_tm); bstats_update(&ca->tcf_bstats, skb); - if (skb->protocol == htons(ETH_P_IP)) { + switch (skb_protocol(skb, true)) { + case htons(ETH_P_IP): if (skb->len < sizeof(struct iphdr)) goto out; proto = NFPROTO_IPV4; - } else if (skb->protocol == htons(ETH_P_IPV6)) { + break; + case htons(ETH_P_IPV6): if (skb->len < sizeof(struct ipv6hdr)) goto out; proto = NFPROTO_IPV6; - } else { + break; + default: goto out; } diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index d3cfad88dc3a..428b1ae00123 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -587,7 +587,7 @@ static int tcf_csum_act(struct sk_buff *skb, const struct tc_action *a, goto drop; update_flags = params->update_flags; - protocol = tc_skb_protocol(skb); + protocol = skb_protocol(skb, false); again: switch (protocol) { case cpu_to_be16(ETH_P_IP): diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 3a31e241c647..a0cfb4793c93 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -536,6 +536,9 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, } ife = to_ife(*a); + if (ret == ACT_P_CREATED) + INIT_LIST_HEAD(&ife->metalist); + err = tcf_action_check_ctrlact(parm->action, tp, &goto_ch, extack); if (err < 0) goto release_idr; @@ -565,10 +568,6 @@ static int tcf_ife_init(struct net *net, struct nlattr *nla, p->eth_type = ife_type; } - - if (ret == ACT_P_CREATED) - INIT_LIST_HEAD(&ife->metalist); - if (tb[TCA_IFE_METALST]) { err = nla_parse_nested_deprecated(tb2, IFE_META_MAX, tb[TCA_IFE_METALST], NULL, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index bd3178a95cb9..a82400f219f3 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -215,8 +215,10 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, bool use_reinsert; bool want_ingress; bool is_redirect; + bool expects_nh; int m_eaction; int mac_len; + bool at_nh; tcf_lastuse_update(&m->tcf_tm); bstats_cpu_update(this_cpu_ptr(m->common.cpu_bstats), skb); @@ -249,19 +251,19 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, goto out; } - /* If action's target direction differs than filter's direction, - * and devices expect a mac header on xmit, then mac push/pull is - * needed. - */ want_ingress = tcf_mirred_act_wants_ingress(m_eaction); - if (skb_at_tc_ingress(skb) != want_ingress && m_mac_header_xmit) { - if (!skb_at_tc_ingress(skb)) { - /* caught at egress, act ingress: pull mac */ - mac_len = skb_network_header(skb) - skb_mac_header(skb); + + expects_nh = want_ingress || !m_mac_header_xmit; + at_nh = skb->data == skb_network_header(skb); + if (at_nh != expects_nh) { + mac_len = skb_at_tc_ingress(skb) ? skb->mac_len : + skb_network_header(skb) - skb_mac_header(skb); + if (expects_nh) { + /* target device/action expect data at nh */ skb_pull_rcsum(skb2, mac_len); } else { - /* caught at ingress, act egress: push mac */ - skb_push_rcsum(skb2, skb->mac_len); + /* target device/action expect data at mac */ + skb_push_rcsum(skb2, mac_len); } } @@ -270,10 +272,8 @@ static int tcf_mirred_act(struct sk_buff *skb, const struct tc_action *a, /* mirror is always swallowed */ if (is_redirect) { - skb2->tc_redirected = 1; - skb2->tc_from_ingress = skb2->tc_at_ingress; - if (skb2->tc_from_ingress) - skb2->tstamp = 0; + skb_set_redirected(skb2, skb2->tc_at_ingress); + /* let's the caller reinsert the packet, if possible */ if (use_reinsert) { res->ingress = want_ingress; diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index cdfaa79382a2..b5bc631b96b7 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -43,7 +43,7 @@ static struct tcf_pedit_key_ex *tcf_pedit_keys_ex_parse(struct nlattr *nla, int err = -EINVAL; int rem; - if (!nla || !n) + if (!nla) return NULL; keys_ex = kcalloc(n, sizeof(*k), GFP_KERNEL); @@ -170,6 +170,10 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, } parm = nla_data(pattr); + if (!parm->nkeys) { + NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); + return -EINVAL; + } ksize = parm->nkeys * sizeof(struct tc_pedit_key); if (nla_len(pattr) < sizeof(*parm) + ksize) { NL_SET_ERR_MSG_ATTR(extack, pattr, "Length of TCA_PEDIT_PARMS or TCA_PEDIT_PARMS_EX pedit attribute is invalid"); @@ -183,12 +187,6 @@ static int tcf_pedit_init(struct net *net, struct nlattr *nla, index = parm->index; err = tcf_idr_check_alloc(tn, &index, a, bind); if (!err) { - if (!parm->nkeys) { - tcf_idr_cleanup(tn, index); - NL_SET_ERR_MSG_MOD(extack, "Pedit requires keys to be passed"); - ret = -EINVAL; - goto out_free; - } ret = tcf_idr_create(tn, index, est, a, &act_pedit_ops, bind, false); if (ret) { diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 6a8d3337c577..f98b2791ecec 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -41,7 +41,7 @@ static int tcf_skbedit_act(struct sk_buff *skb, const struct tc_action *a, if (params->flags & SKBEDIT_F_INHERITDSFIELD) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen)) diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 2f83a79f76aa..d55669e14741 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -135,6 +135,10 @@ static int tunnel_key_copy_opts(const struct nlattr *nla, u8 *dst, if (opt_len < 0) return opt_len; opts_len += opt_len; + if (opts_len > IP_TUNNEL_OPTS_MAX) { + NL_SET_ERR_MSG(extack, "Tunnel options exceeds max size"); + return -EINVAL; + } if (dst) { dst_len -= opt_len; dst += opt_len; diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index ffc6aa6d0f64..2b94d6f02dbb 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -21,6 +21,7 @@ #include <linux/slab.h> #include <linux/idr.h> #include <linux/rhashtable.h> +#include <linux/jhash.h> #include <net/net_namespace.h> #include <net/sock.h> #include <net/netlink.h> @@ -44,6 +45,62 @@ static LIST_HEAD(tcf_proto_base); /* Protects list of registered TC modules. It is pure SMP lock. */ static DEFINE_RWLOCK(cls_mod_lock); +static u32 destroy_obj_hashfn(const struct tcf_proto *tp) +{ + return jhash_3words(tp->chain->index, tp->prio, + (__force __u32)tp->protocol, 0); +} + +static void tcf_proto_signal_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + hash_add_rcu(block->proto_destroy_ht, &tp->destroy_ht_node, + destroy_obj_hashfn(tp)); + mutex_unlock(&block->proto_destroy_lock); +} + +static bool tcf_proto_cmp(const struct tcf_proto *tp1, + const struct tcf_proto *tp2) +{ + return tp1->chain->index == tp2->chain->index && + tp1->prio == tp2->prio && + tp1->protocol == tp2->protocol; +} + +static bool tcf_proto_exists_destroying(struct tcf_chain *chain, + struct tcf_proto *tp) +{ + u32 hash = destroy_obj_hashfn(tp); + struct tcf_proto *iter; + bool found = false; + + rcu_read_lock(); + hash_for_each_possible_rcu(chain->block->proto_destroy_ht, iter, + destroy_ht_node, hash) { + if (tcf_proto_cmp(tp, iter)) { + found = true; + break; + } + } + rcu_read_unlock(); + + return found; +} + +static void +tcf_proto_signal_destroyed(struct tcf_chain *chain, struct tcf_proto *tp) +{ + struct tcf_block *block = chain->block; + + mutex_lock(&block->proto_destroy_lock); + if (hash_hashed(&tp->destroy_ht_node)) + hash_del_rcu(&tp->destroy_ht_node); + mutex_unlock(&block->proto_destroy_lock); +} + /* Find classifier type by string name */ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) @@ -231,9 +288,11 @@ static void tcf_proto_get(struct tcf_proto *tp) static void tcf_chain_put(struct tcf_chain *chain); static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, - struct netlink_ext_ack *extack) + bool sig_destroy, struct netlink_ext_ack *extack) { tp->ops->destroy(tp, rtnl_held, extack); + if (sig_destroy) + tcf_proto_signal_destroyed(tp->chain, tp); tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); @@ -243,7 +302,7 @@ static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { if (refcount_dec_and_test(&tp->refcnt)) - tcf_proto_destroy(tp, rtnl_held, extack); + tcf_proto_destroy(tp, rtnl_held, true, extack); } static int walker_check_empty(struct tcf_proto *tp, void *fh, @@ -367,6 +426,7 @@ static bool tcf_chain_detach(struct tcf_chain *chain) static void tcf_block_destroy(struct tcf_block *block) { mutex_destroy(&block->lock); + mutex_destroy(&block->proto_destroy_lock); kfree_rcu(block, rcu); } @@ -542,6 +602,12 @@ static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_dereference(chain->filter_chain, chain); + while (tp) { + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_signal_destroying(chain, tp); + tp = tp_next; + } + tp = tcf_chain_dereference(chain->filter_chain, chain); RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); chain->flushing = true; @@ -979,6 +1045,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, return ERR_PTR(-ENOMEM); } mutex_init(&block->lock); + mutex_init(&block->proto_destroy_lock); INIT_LIST_HEAD(&block->chain_list); INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); @@ -1660,7 +1727,7 @@ int tcf_classify(struct sk_buff *skb, const struct tcf_proto *tp, reclassify: #endif for (; tp; tp = rcu_dereference_bh(tp->next)) { - __be16 protocol = tc_skb_protocol(skb); + __be16 protocol = skb_protocol(skb, false); int err; if (tp->protocol != protocol && @@ -1758,6 +1825,12 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_lock(&chain->filter_chain_lock); + if (tcf_proto_exists_destroying(chain, tp_new)) { + mutex_unlock(&chain->filter_chain_lock); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); + return ERR_PTR(-EAGAIN); + } + tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp) @@ -1765,10 +1838,10 @@ static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, mutex_unlock(&chain->filter_chain_lock); if (tp) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = tp; } else if (err) { - tcf_proto_destroy(tp_new, rtnl_held, NULL); + tcf_proto_destroy(tp_new, rtnl_held, false, NULL); tp_new = ERR_PTR(err); } @@ -1806,6 +1879,7 @@ static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, return; } + tcf_proto_signal_destroying(chain, tp); next = tcf_chain_dereference(chain_info.next, chain); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); @@ -2075,6 +2149,7 @@ replay: err = PTR_ERR(block); goto errout; } + block->classid = parent; chain_index = tca[TCA_CHAIN] ? nla_get_u32(tca[TCA_CHAIN]) : 0; if (chain_index > TC_ACT_EXT_VAL_MASK) { @@ -2125,9 +2200,8 @@ replay: &chain_info)); mutex_unlock(&chain->filter_chain_lock); - tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, rtnl_held, - extack); + tp_new = tcf_proto_create(name, protocol, prio, chain, + rtnl_held, extack); if (IS_ERR(tp_new)) { err = PTR_ERR(tp_new); goto errout_tp; @@ -2325,6 +2399,7 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -EINVAL; goto errout_locked; } else if (t->tcm_handle == 0) { + tcf_proto_signal_destroying(chain, tp); tcf_chain_tp_remove(chain, &chain_info, tp); mutex_unlock(&chain->filter_chain_lock); @@ -2617,12 +2692,10 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) return skb->len; parent = tcm->tcm_parent; - if (!parent) { + if (!parent) q = dev->qdisc; - parent = q->handle; - } else { + else q = qdisc_lookup(dev, TC_H_MAJ(tcm->tcm_parent)); - } if (!q) goto out; cops = q->ops->cl_ops; @@ -2638,6 +2711,7 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) block = cops->tcf_block(q, cl, NULL); if (!block) goto out; + parent = block->classid; if (tcf_block_shared(block)) q = NULL; } @@ -2783,13 +2857,19 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; + char name[IFNAMSIZ]; void *tmplt_priv; /* If kind is not set, user did not specify template. */ if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack); + if (tcf_proto_check_kind(tca[TCA_KIND], name)) { + NL_SET_ERR_MSG(extack, "Specified TC chain template name too long"); + return -EINVAL; + } + + ops = tcf_proto_lookup_ops(name, true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 4aafbe3d435c..f256a7c69093 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -263,12 +263,17 @@ skip: } } -static void basic_bind_class(void *fh, u32 classid, unsigned long cl) +static void basic_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct basic_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index 691f71830134..64d8a219bf3c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -625,12 +625,17 @@ nla_put_failure: return -1; } -static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl) +static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) { struct cls_bpf_prog *prog = fh; - if (prog && prog->res.classid == classid) - prog->res.class = cl; + if (prog && prog->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &prog->res, base); + else + __tcf_unbind_filter(q, &prog->res); + } } static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg, diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 80ae7b9fa90a..ab53a93b2f2b 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -80,7 +80,7 @@ static u32 flow_get_dst(const struct sk_buff *skb, const struct flow_keys *flow) if (dst) return ntohl(dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_proto(const struct sk_buff *skb, @@ -104,7 +104,7 @@ static u32 flow_get_proto_dst(const struct sk_buff *skb, if (flow->ports.ports) return ntohs(flow->ports.dst); - return addr_fold(skb_dst(skb)) ^ (__force u16) tc_skb_protocol(skb); + return addr_fold(skb_dst(skb)) ^ (__force u16)skb_protocol(skb, true); } static u32 flow_get_iif(const struct sk_buff *skb) @@ -151,7 +151,7 @@ static u32 flow_get_nfct(const struct sk_buff *skb) static u32 flow_get_nfct_src(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, src.u3.ip)); case htons(ETH_P_IPV6): @@ -164,7 +164,7 @@ fallback: static u32 flow_get_nfct_dst(const struct sk_buff *skb, const struct flow_keys *flow) { - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): return ntohl(CTTUPLE(skb, dst.u3.ip)); case htons(ETH_P_IPV6): diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index eedd5786c084..5e112f9e6078 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -282,13 +282,14 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct fl_flow_key skb_mkey; list_for_each_entry_rcu(mask, &head->masks, list) { + flow_dissector_init_keys(&skb_key.control, &skb_key.basic); fl_clear_masked_range(&skb_key, mask); skb_key.indev_ifindex = skb->skb_iif; /* skb_flow_dissect() does not set n_proto in case an unknown * protocol, so do it rather here. */ - skb_key.basic.n_proto = skb->protocol; + skb_key.basic.n_proto = skb_protocol(skb, false); skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); @@ -704,6 +705,7 @@ static const struct nla_policy fl_policy[TCA_FLOWER_MAX + 1] = { [TCA_FLOWER_KEY_ENC_IP_TTL_MASK] = { .type = NLA_U8 }, [TCA_FLOWER_KEY_ENC_OPTS] = { .type = NLA_NESTED }, [TCA_FLOWER_KEY_ENC_OPTS_MASK] = { .type = NLA_NESTED }, + [TCA_FLOWER_FLAGS] = { .type = NLA_U32 }, }; static const struct nla_policy @@ -2402,12 +2404,17 @@ nla_put_failure: return -EMSGSIZE; } -static void fl_bind_class(void *fh, u32 classid, unsigned long cl) +static void fl_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct cls_fl_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_fl_ops __read_mostly = { diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 4dab833f66cb..b6c36d60ffae 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -432,12 +432,17 @@ nla_put_failure: return -1; } -static void fw_bind_class(void *fh, u32 classid, unsigned long cl) +static void fw_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct fw_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_fw_ops __read_mostly = { diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 38c0a9f0f296..2a72a061c41b 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -157,6 +157,7 @@ static void *mall_get(struct tcf_proto *tp, u32 handle) static const struct nla_policy mall_policy[TCA_MATCHALL_MAX + 1] = { [TCA_MATCHALL_UNSPEC] = { .type = NLA_UNSPEC }, [TCA_MATCHALL_CLASSID] = { .type = NLA_U32 }, + [TCA_MATCHALL_FLAGS] = { .type = NLA_U32 }, }; static int mall_set_parms(struct net *net, struct tcf_proto *tp, @@ -391,12 +392,17 @@ nla_put_failure: return -1; } -static void mall_bind_class(void *fh, u32 classid, unsigned long cl) +static void mall_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct cls_mall_head *head = fh; - if (head && head->res.classid == classid) - head->res.class = cl; + if (head && head->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &head->res, base); + else + __tcf_unbind_filter(q, &head->res); + } } static struct tcf_proto_ops cls_mall_ops __read_mostly = { diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 2d9e0b4484ea..5efa3e7ace15 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -534,8 +534,8 @@ static int route4_change(struct net *net, struct sk_buff *in_skb, fp = &b->ht[h]; for (pfp = rtnl_dereference(*fp); pfp; fp = &pfp->next, pfp = rtnl_dereference(*fp)) { - if (pfp == f) { - *fp = f->next; + if (pfp == fold) { + rcu_assign_pointer(*fp, fold->next); break; } } @@ -641,12 +641,17 @@ nla_put_failure: return -1; } -static void route4_bind_class(void *fh, u32 classid, unsigned long cl) +static void route4_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct route4_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops cls_route4_ops __read_mostly = { diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 2f3c03b25d5d..d36949d9382c 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -463,10 +463,8 @@ static u32 gen_tunnel(struct rsvp_head *data) static const struct nla_policy rsvp_policy[TCA_RSVP_MAX + 1] = { [TCA_RSVP_CLASSID] = { .type = NLA_U32 }, - [TCA_RSVP_DST] = { .type = NLA_BINARY, - .len = RSVP_DST_LEN * sizeof(u32) }, - [TCA_RSVP_SRC] = { .type = NLA_BINARY, - .len = RSVP_DST_LEN * sizeof(u32) }, + [TCA_RSVP_DST] = { .len = RSVP_DST_LEN * sizeof(u32) }, + [TCA_RSVP_SRC] = { .len = RSVP_DST_LEN * sizeof(u32) }, [TCA_RSVP_PINFO] = { .len = sizeof(struct tc_rsvp_pinfo) }, }; @@ -738,12 +736,17 @@ nla_put_failure: return -1; } -static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl) +static void rsvp_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct rsvp_filter *f = fh; - if (f && f->res.classid == classid) - f->res.class = cl; + if (f && f->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &f->res, base); + else + __tcf_unbind_filter(q, &f->res); + } } static struct tcf_proto_ops RSVP_OPS __read_mostly = { diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index e573e5a5c794..61e95029c18f 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -11,6 +11,7 @@ #include <linux/skbuff.h> #include <linux/errno.h> #include <linux/slab.h> +#include <linux/refcount.h> #include <net/act_api.h> #include <net/netlink.h> #include <net/pkt_cls.h> @@ -26,9 +27,12 @@ #define DEFAULT_HASH_SIZE 64 /* optimized for diffserv */ +struct tcindex_data; + struct tcindex_filter_result { struct tcf_exts exts; struct tcf_result res; + struct tcindex_data *p; struct rcu_work rwork; }; @@ -49,6 +53,7 @@ struct tcindex_data { u32 hash; /* hash table size; 0 if undefined */ u32 alloc_hash; /* allocated size */ u32 fall_through; /* 0: only classify if explicit match */ + refcount_t refcnt; /* a temporary refcnt for perfect hash */ struct rcu_work rwork; }; @@ -57,6 +62,20 @@ static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) return tcf_exts_has_actions(&r->exts) || r->res.classid; } +static void tcindex_data_get(struct tcindex_data *p) +{ + refcount_inc(&p->refcnt); +} + +static void tcindex_data_put(struct tcindex_data *p) +{ + if (refcount_dec_and_test(&p->refcnt)) { + kfree(p->perfect); + kfree(p->h); + kfree(p); + } +} + static struct tcindex_filter_result *tcindex_lookup(struct tcindex_data *p, u16 key) { @@ -132,6 +151,7 @@ static int tcindex_init(struct tcf_proto *tp) p->mask = 0xffff; p->hash = DEFAULT_HASH_SIZE; p->fall_through = 1; + refcount_set(&p->refcnt, 1); /* Paired with tcindex_destroy_work() */ rcu_assign_pointer(tp->root, p); return 0; @@ -141,6 +161,7 @@ static void __tcindex_destroy_rexts(struct tcindex_filter_result *r) { tcf_exts_destroy(&r->exts); tcf_exts_put_net(&r->exts); + tcindex_data_put(r->p); } static void tcindex_destroy_rexts_work(struct work_struct *work) @@ -212,6 +233,8 @@ found: else __tcindex_destroy_fexts(f); } else { + tcindex_data_get(p); + if (tcf_exts_get_net(&r->exts)) tcf_queue_work(&r->rwork, tcindex_destroy_rexts_work); else @@ -228,9 +251,7 @@ static void tcindex_destroy_work(struct work_struct *work) struct tcindex_data, rwork); - kfree(p->perfect); - kfree(p->h); - kfree(p); + tcindex_data_put(p); } static inline int @@ -248,9 +269,11 @@ static const struct nla_policy tcindex_policy[TCA_TCINDEX_MAX + 1] = { }; static int tcindex_filter_result_init(struct tcindex_filter_result *r, + struct tcindex_data *p, struct net *net) { memset(r, 0, sizeof(*r)); + r->p = p; return tcf_exts_init(&r->exts, net, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } @@ -261,8 +284,10 @@ static void tcindex_partial_destroy_work(struct work_struct *work) struct tcindex_data, rwork); + rtnl_lock(); kfree(p->perfect); kfree(p); + rtnl_unlock(); } static void tcindex_free_perfect_hash(struct tcindex_data *cp) @@ -288,6 +313,7 @@ static int tcindex_alloc_perfect_hash(struct net *net, struct tcindex_data *cp) TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) goto errout; + cp->perfect[i].p = cp; } return 0; @@ -332,33 +358,45 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, cp->alloc_hash = p->alloc_hash; cp->fall_through = p->fall_through; cp->tp = tp; + refcount_set(&cp->refcnt, 1); /* Paired with tcindex_destroy_work() */ + + if (tb[TCA_TCINDEX_HASH]) + cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); + + if (tb[TCA_TCINDEX_MASK]) + cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); + + if (tb[TCA_TCINDEX_SHIFT]) + cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); + + if (!cp->hash) { + /* Hash not specified, use perfect hash if the upper limit + * of the hashing index is below the threshold. + */ + if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) + cp->hash = (cp->mask >> cp->shift) + 1; + else + cp->hash = DEFAULT_HASH_SIZE; + } if (p->perfect) { int i; if (tcindex_alloc_perfect_hash(net, cp) < 0) goto errout; - for (i = 0; i < cp->hash; i++) + cp->alloc_hash = cp->hash; + for (i = 0; i < min(cp->hash, p->hash); i++) cp->perfect[i].res = p->perfect[i].res; balloc = 1; } cp->h = p->h; - err = tcindex_filter_result_init(&new_filter_result, net); + err = tcindex_filter_result_init(&new_filter_result, cp, net); if (err < 0) - goto errout1; + goto errout_alloc; if (old_r) cr = r->res; - if (tb[TCA_TCINDEX_HASH]) - cp->hash = nla_get_u32(tb[TCA_TCINDEX_HASH]); - - if (tb[TCA_TCINDEX_MASK]) - cp->mask = nla_get_u16(tb[TCA_TCINDEX_MASK]); - - if (tb[TCA_TCINDEX_SHIFT]) - cp->shift = nla_get_u32(tb[TCA_TCINDEX_SHIFT]); - err = -EBUSY; /* Hash already allocated, make sure that we still meet the @@ -376,16 +414,6 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, if (tb[TCA_TCINDEX_FALL_THROUGH]) cp->fall_through = nla_get_u32(tb[TCA_TCINDEX_FALL_THROUGH]); - if (!cp->hash) { - /* Hash not specified, use perfect hash if the upper limit - * of the hashing index is below the threshold. - */ - if ((cp->mask >> cp->shift) < PERFECT_HASH_THRESHOLD) - cp->hash = (cp->mask >> cp->shift) + 1; - else - cp->hash = DEFAULT_HASH_SIZE; - } - if (!cp->perfect && !cp->h) cp->alloc_hash = cp->hash; @@ -431,7 +459,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, goto errout_alloc; f->key = handle; f->next = NULL; - err = tcindex_filter_result_init(&f->result, net); + err = tcindex_filter_result_init(&f->result, cp, net); if (err < 0) { kfree(f); goto errout_alloc; @@ -444,7 +472,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (old_r && old_r != r) { - err = tcindex_filter_result_init(old_r, net); + err = tcindex_filter_result_init(old_r, cp, net); if (err < 0) { kfree(f); goto errout_alloc; @@ -484,7 +512,6 @@ errout_alloc: tcindex_free_perfect_hash(cp); else if (balloc == 2) kfree(cp->h); -errout1: tcf_exts_destroy(&new_filter_result.exts); errout: kfree(cp); @@ -569,6 +596,14 @@ static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held, for (i = 0; i < p->hash; i++) { struct tcindex_filter_result *r = p->perfect + i; + /* tcf_queue_work() does not guarantee the ordering we + * want, so we have to take this refcnt temporarily to + * ensure 'p' is freed after all tcindex_filter_result + * here. Imperfect hash does not need this, because it + * uses linked lists rather than an array. + */ + tcindex_data_get(p); + tcf_unbind_filter(tp, &r->res); if (tcf_exts_get_net(&r->exts)) tcf_queue_work(&r->rwork, @@ -654,12 +689,17 @@ nla_put_failure: return -1; } -static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl) +static void tcindex_bind_class(void *fh, u32 classid, unsigned long cl, + void *q, unsigned long base) { struct tcindex_filter_result *r = fh; - if (r && r->res.classid == classid) - r->res.class = cl; + if (r && r->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &r->res, base); + else + __tcf_unbind_filter(q, &r->res); + } } static struct tcf_proto_ops cls_tcindex_ops __read_mostly = { diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index c7727de5e073..0443ac3ecf1e 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -1271,12 +1271,17 @@ static int u32_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, return 0; } -static void u32_bind_class(void *fh, u32 classid, unsigned long cl) +static void u32_bind_class(void *fh, u32 classid, unsigned long cl, void *q, + unsigned long base) { struct tc_u_knode *n = fh; - if (n && n->res.classid == classid) - n->res.class = cl; + if (n && n->res.classid == classid) { + if (cl) + __tcf_bind_filter(q, &n->res, base); + else + __tcf_unbind_filter(q, &n->res); + } } static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, diff --git a/net/sched/em_ipset.c b/net/sched/em_ipset.c index df00566d327d..c95cf86fb431 100644 --- a/net/sched/em_ipset.c +++ b/net/sched/em_ipset.c @@ -59,7 +59,7 @@ static int em_ipset_match(struct sk_buff *skb, struct tcf_ematch *em, }; int ret, network_offset; - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): state.pf = NFPROTO_IPV4; if (!pskb_network_may_pull(skb, sizeof(struct iphdr))) diff --git a/net/sched/em_meta.c b/net/sched/em_meta.c index 82bd14e7ac93..8de4968177bd 100644 --- a/net/sched/em_meta.c +++ b/net/sched/em_meta.c @@ -195,7 +195,7 @@ META_COLLECTOR(int_priority) META_COLLECTOR(int_protocol) { /* Let userspace take care of the byte ordering */ - dst->value = tc_skb_protocol(skb); + dst->value = skb_protocol(skb, false); } META_COLLECTOR(int_pkttype) @@ -446,7 +446,7 @@ META_COLLECTOR(int_sk_wmem_queued) *err = -1; return; } - dst->value = sk->sk_wmem_queued; + dst->value = READ_ONCE(sk->sk_wmem_queued); } META_COLLECTOR(int_sk_fwd_alloc) diff --git a/net/sched/ematch.c b/net/sched/ematch.c index 8f2ad706784d..dd3b8c11a2e0 100644 --- a/net/sched/ematch.c +++ b/net/sched/ematch.c @@ -238,6 +238,9 @@ static int tcf_em_validate(struct tcf_proto *tp, goto errout; if (em->ops->change) { + err = -EINVAL; + if (em_hdr->flags & TCF_EM_SIMPLE) + goto errout; err = em->ops->change(net, data, data_len, em); if (err < 0) goto errout; @@ -263,12 +266,12 @@ static int tcf_em_validate(struct tcf_proto *tp, } em->data = (unsigned long) v; } + em->datalen = data_len; } } em->matchid = em_hdr->matchid; em->flags = em_hdr->flags; - em->datalen = data_len; em->net = net; err = 0; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 1047825d9f48..50794125bf02 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -1891,8 +1891,9 @@ static int tclass_del_notify(struct net *net, struct tcf_bind_args { struct tcf_walker w; - u32 classid; + unsigned long base; unsigned long cl; + u32 classid; }; static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) @@ -1903,28 +1904,30 @@ static int tcf_node_bind(struct tcf_proto *tp, void *n, struct tcf_walker *arg) struct Qdisc *q = tcf_block_q(tp->chain->block); sch_tree_lock(q); - tp->ops->bind_class(n, a->classid, a->cl); + tp->ops->bind_class(n, a->classid, a->cl, q, a->base); sch_tree_unlock(q); } return 0; } -static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, - unsigned long new_cl) +struct tc_bind_class_args { + struct qdisc_walker w; + unsigned long new_cl; + u32 portid; + u32 clid; +}; + +static int tc_bind_class_walker(struct Qdisc *q, unsigned long cl, + struct qdisc_walker *w) { + struct tc_bind_class_args *a = (struct tc_bind_class_args *)w; const struct Qdisc_class_ops *cops = q->ops->cl_ops; struct tcf_block *block; struct tcf_chain *chain; - unsigned long cl; - cl = cops->find(q, portid); - if (!cl) - return; - if (!cops->tcf_block) - return; block = cops->tcf_block(q, cl, NULL); if (!block) - return; + return 0; for (chain = tcf_get_next_chain(block, NULL); chain; chain = tcf_get_next_chain(block, chain)) { @@ -1935,11 +1938,29 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; - arg.classid = clid; - arg.cl = new_cl; + arg.classid = a->clid; + arg.base = cl; + arg.cl = a->new_cl; tp->ops->walk(tp, &arg.w, true); } } + + return 0; +} + +static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, + unsigned long new_cl) +{ + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + struct tc_bind_class_args args = {}; + + if (!cops->tcf_block) + return; + args.portid = portid; + args.clid = clid; + args.new_cl = new_cl; + args.w.fn = tc_bind_class_walker; + q->ops->cl_ops->walk(q, &args.w); } #else diff --git a/net/sched/sch_atm.c b/net/sched/sch_atm.c index f4f9b8cdbffb..6385995dc700 100644 --- a/net/sched/sch_atm.c +++ b/net/sched/sch_atm.c @@ -553,16 +553,16 @@ static int atm_tc_init(struct Qdisc *sch, struct nlattr *opt, 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; - p->link.vcc = NULL; - p->link.sock = NULL; - p->link.common.classid = sch->handle; - p->link.ref = 1; tasklet_init(&p->task, sch_atm_dequeue, (unsigned long)sch); return 0; } diff --git a/net/sched/sch_cake.c b/net/sched/sch_cake.c index 53a80bc6b13a..896c0562cb42 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -592,7 +592,7 @@ static void cake_update_flowkeys(struct flow_keys *keys, struct nf_conntrack_tuple tuple = {}; bool rev = !skb->_nfct; - if (tc_skb_protocol(skb) != htons(ETH_P_IP)) + if (skb_protocol(skb, true) != htons(ETH_P_IP)) return; if (!nf_ct_get_tuple_skb(&tuple, skb)) @@ -1515,32 +1515,51 @@ static unsigned int cake_drop(struct Qdisc *sch, struct sk_buff **to_free) return idx + (tin << 16); } -static u8 cake_handle_diffserv(struct sk_buff *skb, u16 wash) +static u8 cake_handle_diffserv(struct sk_buff *skb, bool wash) { - int wlen = skb_network_offset(skb); + const int offset = skb_network_offset(skb); + u16 *buf, buf_; u8 dscp; - switch (tc_skb_protocol(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)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv4_get_dsfield(ip_hdr(skb)) >> 2; - if (wash && dscp) + /* ToS is in the second byte of iphdr */ + dscp = ipv4_get_dsfield((struct iphdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct iphdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv4_change_dsfield(ip_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_IPV6): - wlen += sizeof(struct ipv6hdr); - if (!pskb_may_pull(skb, wlen) || - skb_try_make_writable(skb, wlen)) + buf = skb_header_pointer(skb, offset, sizeof(buf_), &buf_); + if (unlikely(!buf)) return 0; - dscp = ipv6_get_dsfield(ipv6_hdr(skb)) >> 2; - if (wash && dscp) + /* Traffic class is in the first and second bytes of ipv6hdr */ + dscp = ipv6_get_dsfield((struct ipv6hdr *)buf) >> 2; + + if (wash && dscp) { + const int wlen = offset + sizeof(struct ipv6hdr); + + if (!pskb_may_pull(skb, wlen) || + skb_try_make_writable(skb, wlen)) + return 0; + ipv6_change_dsfield(ipv6_hdr(skb), INET_ECN_MASK, 0); + } + return dscp; case htons(ETH_P_ARP): @@ -1557,14 +1576,17 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, { struct cake_sched_data *q = qdisc_priv(sch); u32 tin, mark; + bool wash; u8 dscp; /* Tin selection: Default to diffserv-based selection, allow overriding - * using firewall marks or skb->priority. + * using firewall marks or skb->priority. Call DSCP parsing early if + * wash is enabled, otherwise defer to below to skip unneeded parsing. */ - dscp = cake_handle_diffserv(skb, - q->rate_flags & CAKE_FLAG_WASH); mark = (skb->mark & q->fwmark_mask) >> q->fwmark_shft; + wash = !!(q->rate_flags & CAKE_FLAG_WASH); + if (wash) + dscp = cake_handle_diffserv(skb, wash); if (q->tin_mode == CAKE_DIFFSERV_BESTEFFORT) tin = 0; @@ -1578,6 +1600,8 @@ static struct cake_tin_data *cake_select_tin(struct Qdisc *sch, tin = q->tin_order[TC_H_MIN(skb->priority) - 1]; else { + if (!wash) + dscp = cake_handle_diffserv(skb, wash); tin = q->tin_index[dscp]; if (unlikely(tin >= q->tin_cnt)) @@ -1769,7 +1793,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, q->avg_window_begin)); u64 b = q->avg_window_bytes * (u64)NSEC_PER_SEC; - do_div(b, window_interval); + b = div64_u64(b, window_interval); q->avg_peak_bandwidth = cake_ewma(q->avg_peak_bandwidth, b, b > q->avg_peak_bandwidth ? 2 : 8); @@ -2184,6 +2208,7 @@ static const struct nla_policy cake_policy[TCA_CAKE_MAX + 1] = { [TCA_CAKE_MPU] = { .type = NLA_U32 }, [TCA_CAKE_INGRESS] = { .type = NLA_U32 }, [TCA_CAKE_ACK_FILTER] = { .type = NLA_U32 }, + [TCA_CAKE_SPLIT_GSO] = { .type = NLA_U32 }, [TCA_CAKE_FWMARK] = { .type = NLA_U32 }, }; @@ -2678,7 +2703,7 @@ static int cake_init(struct Qdisc *sch, struct nlattr *opt, qdisc_watchdog_init(&q->watchdog, sch); if (opt) { - int err = cake_change(sch, opt, extack); + err = cake_change(sch, opt, extack); if (err) return err; @@ -2995,7 +3020,7 @@ static int cake_dump_class_stats(struct Qdisc *sch, unsigned long cl, PUT_STAT_S32(BLUE_TIMER_US, ktime_to_us( ktime_sub(now, - flow->cvars.blue_timer))); + flow->cvars.blue_timer))); } if (flow->cvars.dropping) { PUT_STAT_S32(DROP_NEXT_US, diff --git a/net/sched/sch_cbs.c b/net/sched/sch_cbs.c index 284ab2dcf47f..35a860764dfa 100644 --- a/net/sched/sch_cbs.c +++ b/net/sched/sch_cbs.c @@ -181,6 +181,11 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) s64 credits; int len; + /* The previous packet is still being sent */ + if (now < q->last) { + qdisc_watchdog_schedule_ns(&q->watchdog, q->last); + return NULL; + } if (q->credits < 0) { credits = timediff_to_credits(now - q->last, q->idleslope); @@ -212,7 +217,12 @@ static struct sk_buff *cbs_dequeue_soft(struct Qdisc *sch) credits += q->credits; q->credits = max_t(s64, credits, q->locredit); - q->last = now; + /* Estimate of the transmission of the last byte of the packet in ns */ + if (unlikely(atomic64_read(&q->port_rate) == 0)) + q->last = now; + else + q->last = now + div64_s64(len * NSEC_PER_SEC, + atomic64_read(&q->port_rate)); return skb; } diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index dba70377bbd9..4021f726b58f 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -323,7 +323,8 @@ static void choke_reset(struct Qdisc *sch) sch->q.qlen = 0; sch->qstats.backlog = 0; - memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); + if (q->tab) + memset(q->tab, 0, (q->tab_mask + 1) * sizeof(struct sk_buff *)); q->head = q->tail = 0; red_restart(&q->vars); } diff --git a/net/sched/sch_dsmark.c b/net/sched/sch_dsmark.c index 05605b30bef3..2b88710994d7 100644 --- a/net/sched/sch_dsmark.c +++ b/net/sched/sch_dsmark.c @@ -210,7 +210,7 @@ static int dsmark_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (p->set_tc_index) { int wlen = skb_network_offset(skb); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): wlen += sizeof(struct iphdr); if (!pskb_may_pull(skb, wlen) || @@ -303,7 +303,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) index = skb->tc_index & (p->indices - 1); pr_debug("index %d->%d\n", skb->tc_index, index); - switch (tc_skb_protocol(skb)) { + switch (skb_protocol(skb, true)) { case htons(ETH_P_IP): ipv4_change_dsfield(ip_hdr(skb), p->mv[index].mask, p->mv[index].value); @@ -320,7 +320,7 @@ static struct sk_buff *dsmark_dequeue(struct Qdisc *sch) */ if (p->mv[index].mask != 0xff || p->mv[index].value) pr_warn("%s: unsupported protocol %d\n", - __func__, ntohs(tc_skb_protocol(skb))); + __func__, ntohs(skb_protocol(skb, true))); break; } diff --git a/net/sched/sch_etf.c b/net/sched/sch_etf.c index b244881d2b9a..e7e20a05fc13 100644 --- a/net/sched/sch_etf.c +++ b/net/sched/sch_etf.c @@ -77,7 +77,7 @@ static bool is_packet_valid(struct Qdisc *sch, struct sk_buff *nskb) struct sock *sk = nskb->sk; ktime_t now; - if (!sk) + if (!sk || !sk_fullsock(sk)) return false; if (!sock_flag(sk, SOCK_TXTIME)) @@ -131,8 +131,9 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) struct sock_exterr_skb *serr; struct sk_buff *clone; ktime_t txtime = skb->tstamp; + struct sock *sk = skb->sk; - if (!skb->sk || !(skb->sk->sk_txtime_report_errors)) + if (!sk || !sk_fullsock(sk) || !(sk->sk_txtime_report_errors)) return; clone = skb_clone(skb, GFP_ATOMIC); @@ -148,7 +149,7 @@ static void report_sock_error(struct sk_buff *skb, u32 err, u8 code) serr->ee.ee_data = (txtime >> 32); /* high part of tstamp */ serr->ee.ee_info = txtime; /* low part of tstamp */ - if (sock_queue_err_skb(skb->sk, clone)) + if (sock_queue_err_skb(sk, clone)) kfree_skb(clone); } diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index 98dd87ce1510..f757ea90aba6 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -301,6 +301,9 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) f->socket_hash != sk->sk_hash)) { f->credit = q->initial_quantum; f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); if (fq_flow_is_throttled(f)) fq_flow_unset_throttled(q, f); f->time_next_packet = 0ULL; @@ -322,8 +325,12 @@ static struct fq_flow *fq_classify(struct sk_buff *skb, struct fq_sched_data *q) fq_flow_set_detached(f); f->sk = sk; - if (skb->sk == sk) + if (skb->sk == sk) { f->socket_hash = sk->sk_hash; + if (q->rate_enable) + smp_store_release(&sk->sk_pacing_status, + SK_PACING_FQ); + } f->credit = q->initial_quantum; rb_link_node(&f->fq_node, parent, p); @@ -428,17 +435,9 @@ static int fq_enqueue(struct sk_buff *skb, struct Qdisc *sch, f->qlen++; qdisc_qstats_backlog_inc(sch, skb); if (fq_flow_is_detached(f)) { - struct sock *sk = skb->sk; - fq_flow_add_tail(&q->new_flows, f); if (time_after(jiffies, f->age + q->flow_refill_delay)) f->credit = max_t(u32, f->credit, q->quantum); - if (sk && q->rate_enable) { - if (unlikely(smp_load_acquire(&sk->sk_pacing_status) != - SK_PACING_FQ)) - smp_store_release(&sk->sk_pacing_status, - SK_PACING_FQ); - } q->inactive_flows--; } @@ -746,6 +745,7 @@ static const struct nla_policy fq_policy[TCA_FQ_MAX + 1] = { [TCA_FQ_FLOW_MAX_RATE] = { .type = NLA_U32 }, [TCA_FQ_BUCKETS_LOG] = { .type = NLA_U32 }, [TCA_FQ_FLOW_REFILL_DELAY] = { .type = NLA_U32 }, + [TCA_FQ_ORPHAN_MASK] = { .type = NLA_U32 }, [TCA_FQ_LOW_RATE_THRESHOLD] = { .type = NLA_U32 }, [TCA_FQ_CE_THRESHOLD] = { .type = NLA_U32 }, }; @@ -788,10 +788,12 @@ static int fq_change(struct Qdisc *sch, struct nlattr *opt, if (tb[TCA_FQ_QUANTUM]) { u32 quantum = nla_get_u32(tb[TCA_FQ_QUANTUM]); - if (quantum > 0) + if (quantum > 0 && quantum <= (1 << 20)) { q->quantum = quantum; - else + } else { + NL_SET_ERR_MSG_MOD(extack, "invalid quantum"); err = -EINVAL; + } } if (tb[TCA_FQ_INITIAL_QUANTUM]) diff --git a/net/sched/sch_fq_codel.c b/net/sched/sch_fq_codel.c index d59fbcc745d1..23dabff624cb 100644 --- a/net/sched/sch_fq_codel.c +++ b/net/sched/sch_fq_codel.c @@ -425,7 +425,7 @@ static int fq_codel_change(struct Qdisc *sch, struct nlattr *opt, q->quantum = max(256U, nla_get_u32(tb[TCA_FQ_CODEL_QUANTUM])); if (tb[TCA_FQ_CODEL_DROP_BATCH_SIZE]) - q->drop_batch_size = min(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); + q->drop_batch_size = max(1U, nla_get_u32(tb[TCA_FQ_CODEL_DROP_BATCH_SIZE])); if (tb[TCA_FQ_CODEL_MEMORY_LIMIT]) q->memory_limit = min(1U << 31, nla_get_u32(tb[TCA_FQ_CODEL_MEMORY_LIMIT])); diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 17bd8f539bc7..71c836757952 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -469,6 +469,7 @@ void __netdev_watchdog_up(struct net_device *dev) dev_hold(dev); } } +EXPORT_SYMBOL_GPL(__netdev_watchdog_up); static void dev_watchdog_up(struct net_device *dev) { @@ -657,7 +658,7 @@ static struct sk_buff *pfifo_fast_dequeue(struct Qdisc *qdisc) if (likely(skb)) { qdisc_update_stats_at_dequeue(qdisc, skb); } else { - qdisc->empty = true; + WRITE_ONCE(qdisc->empty, true); } return skb; diff --git a/net/sched/sch_hhf.c b/net/sched/sch_hhf.c index 23cd1c873a2c..be35f03b657b 100644 --- a/net/sched/sch_hhf.c +++ b/net/sched/sch_hhf.c @@ -5,11 +5,11 @@ * Copyright (C) 2013 Nandita Dukkipati <nanditad@google.com> */ -#include <linux/jhash.h> #include <linux/jiffies.h> #include <linux/module.h> #include <linux/skbuff.h> #include <linux/vmalloc.h> +#include <linux/siphash.h> #include <net/pkt_sched.h> #include <net/sock.h> @@ -126,7 +126,7 @@ struct wdrr_bucket { struct hhf_sched_data { struct wdrr_bucket buckets[WDRR_BUCKET_CNT]; - u32 perturbation; /* hash perturbation */ + siphash_key_t perturbation; /* hash perturbation */ u32 quantum; /* psched_mtu(qdisc_dev(sch)); */ u32 drop_overlimit; /* number of times max qdisc packet * limit was hit @@ -264,7 +264,7 @@ static enum wdrr_bucket_idx hhf_classify(struct sk_buff *skb, struct Qdisc *sch) } /* Get hashed flow-id of the skb. */ - hash = skb_get_hash_perturb(skb, q->perturbation); + hash = skb_get_hash_perturb(skb, &q->perturbation); /* Check if this packet belongs to an already established HH flow. */ flow_pos = hash & HHF_BIT_MASK; @@ -582,7 +582,7 @@ static int hhf_init(struct Qdisc *sch, struct nlattr *opt, sch->limit = 1000; q->quantum = psched_mtu(qdisc_dev(sch)); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); INIT_LIST_HEAD(&q->new_buckets); INIT_LIST_HEAD(&q->old_buckets); diff --git a/net/sched/sch_mq.c b/net/sched/sch_mq.c index 0d578333e967..e79f1afe0cfd 100644 --- a/net/sched/sch_mq.c +++ b/net/sched/sch_mq.c @@ -153,6 +153,7 @@ static int mq_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -245,7 +246,8 @@ static int mq_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mq_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(&sch->running, d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(&sch->running, d, sch->cpu_bstats, + &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; return 0; diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c index 46980b8d66c5..8766ab5b8788 100644 --- a/net/sched/sch_mqprio.c +++ b/net/sched/sch_mqprio.c @@ -411,6 +411,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) __gnet_stats_copy_queue(&sch->qstats, qdisc->cpu_qstats, &qdisc->qstats, qlen); + sch->q.qlen += qlen; } else { sch->q.qlen += qdisc->q.qlen; sch->bstats.bytes += qdisc->bstats.bytes; @@ -433,7 +434,7 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb) opt.offset[tc] = dev->tc_to_txq[tc].offset; } - if (nla_put(skb, TCA_OPTIONS, NLA_ALIGN(sizeof(opt)), &opt)) + if (nla_put(skb, TCA_OPTIONS, sizeof(opt), &opt)) goto nla_put_failure; if ((priv->flags & TC_MQPRIO_F_MODE) && @@ -557,8 +558,8 @@ static int mqprio_dump_class_stats(struct Qdisc *sch, unsigned long cl, struct netdev_queue *dev_queue = mqprio_queue_get(sch, cl); sch = dev_queue->qdisc_sleeping; - if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &sch->bstats) < 0 || + if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), d, + sch->cpu_bstats, &sch->bstats) < 0 || qdisc_qstats_copy(d, sch) < 0) return -1; } diff --git a/net/sched/sch_multiq.c b/net/sched/sch_multiq.c index e1087746f6a2..5cdf3b6abae6 100644 --- a/net/sched/sch_multiq.c +++ b/net/sched/sch_multiq.c @@ -330,7 +330,7 @@ static int multiq_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_netem.c b/net/sched/sch_netem.c index f5cb35e550f8..42e557d48e4e 100644 --- a/net/sched/sch_netem.c +++ b/net/sched/sch_netem.c @@ -476,7 +476,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, * skb will be queued. */ if (count > 1 && (skb2 = skb_clone(skb, GFP_ATOMIC)) != NULL) { - struct Qdisc *rootq = qdisc_root(sch); + struct Qdisc *rootq = qdisc_root_bh(sch); u32 dupsave = q->duplicate; /* prevent duplicating a dup... */ q->duplicate = 0; @@ -509,6 +509,7 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (skb->ip_summed == CHECKSUM_PARTIAL && skb_checksum_help(skb)) { qdisc_drop(skb, sch, to_free); + skb = NULL; goto finish_segs; } @@ -593,9 +594,10 @@ static int netem_enqueue(struct sk_buff *skb, struct Qdisc *sch, finish_segs: if (segs) { unsigned int len, last_len; - int nb = 0; + int nb; - len = skb->len; + len = skb ? skb->len : 0; + nb = skb ? 1 : 0; while (segs) { skb2 = segs->next; @@ -612,7 +614,10 @@ finish_segs: } segs = skb2; } - qdisc_tree_reduce_backlog(sch, -nb, prev_len - len); + /* Parent qdiscs accounted for 1 skb of size @prev_len */ + qdisc_tree_reduce_backlog(sch, -(nb - 1), -(len - prev_len)); + } else if (!skb) { + return NET_XMIT_DROP; } return NET_XMIT_SUCCESS; } diff --git a/net/sched/sch_prio.c b/net/sched/sch_prio.c index 0f8fedb8809a..647941702f9f 100644 --- a/net/sched/sch_prio.c +++ b/net/sched/sch_prio.c @@ -292,8 +292,14 @@ static int prio_graft(struct Qdisc *sch, unsigned long arg, struct Qdisc *new, struct tc_prio_qopt_offload graft_offload; unsigned long band = arg - 1; - if (new == NULL) - new = &noop_qdisc; + if (!new) { + new = qdisc_create_dflt(sch->dev_queue, &pfifo_qdisc_ops, + TC_H_MAKE(sch->handle, arg), extack); + if (!new) + new = &noop_qdisc; + else + qdisc_hash_add(new, true); + } *old = qdisc_replace(sch, new, &q->queues[band]); @@ -356,7 +362,7 @@ static int prio_dump_class_stats(struct Qdisc *sch, unsigned long cl, cl_q = q->queues[cl - 1]; if (gnet_stats_copy_basic(qdisc_root_sleeping_running(sch), - d, NULL, &cl_q->bstats) < 0 || + d, cl_q->cpu_bstats, &cl_q->bstats) < 0 || qdisc_qstats_copy(d, cl_q) < 0) return -1; diff --git a/net/sched/sch_sfb.c b/net/sched/sch_sfb.c index 1dff8506a715..4074c50ac3d7 100644 --- a/net/sched/sch_sfb.c +++ b/net/sched/sch_sfb.c @@ -18,7 +18,7 @@ #include <linux/errno.h> #include <linux/skbuff.h> #include <linux/random.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <net/ip.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> @@ -45,7 +45,7 @@ struct sfb_bucket { * (Section 4.4 of SFB reference : moving hash functions) */ struct sfb_bins { - u32 perturbation; /* jhash perturbation */ + siphash_key_t perturbation; /* siphash key */ struct sfb_bucket bins[SFB_LEVELS][SFB_NUMBUCKETS]; }; @@ -217,7 +217,8 @@ static u32 sfb_compute_qlen(u32 *prob_r, u32 *avgpm_r, const struct sfb_sched_da static void sfb_init_perturbation(u32 slot, struct sfb_sched_data *q) { - q->bins[slot].perturbation = prandom_u32(); + get_random_bytes(&q->bins[slot].perturbation, + sizeof(q->bins[slot].perturbation)); } static void sfb_swap_slot(struct sfb_sched_data *q) @@ -314,9 +315,9 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* If using external classifiers, get result and record it. */ if (!sfb_classify(skb, fl, &ret, &salt)) goto other_drop; - sfbhash = jhash_1word(salt, q->bins[slot].perturbation); + sfbhash = siphash_1u32(salt, &q->bins[slot].perturbation); } else { - sfbhash = skb_get_hash_perturb(skb, q->bins[slot].perturbation); + sfbhash = skb_get_hash_perturb(skb, &q->bins[slot].perturbation); } @@ -352,7 +353,7 @@ static int sfb_enqueue(struct sk_buff *skb, struct Qdisc *sch, /* Inelastic flow */ if (q->double_buffering) { sfbhash = skb_get_hash_perturb(skb, - q->bins[slot].perturbation); + &q->bins[slot].perturbation); if (!sfbhash) sfbhash = 1; sfb_skb_cb(skb)->hashes[slot] = sfbhash; @@ -488,7 +489,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { struct sfb_sched_data *q = qdisc_priv(sch); - struct Qdisc *child; + struct Qdisc *child, *old; struct nlattr *tb[TCA_SFB_MAX + 1]; const struct tc_sfb_qopt *ctl = &sfb_default_ops; u32 limit; @@ -518,8 +519,8 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, qdisc_hash_add(child, true); sch_tree_lock(sch); - qdisc_tree_flush_backlog(q->qdisc); - qdisc_put(q->qdisc); + qdisc_purge_queue(q->qdisc); + old = q->qdisc; q->qdisc = child; q->rehash_interval = msecs_to_jiffies(ctl->rehash_interval); @@ -542,6 +543,7 @@ static int sfb_change(struct Qdisc *sch, struct nlattr *opt, sfb_init_perturbation(1, q); sch_tree_unlock(sch); + qdisc_put(old); return 0; } diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index 68404a9d2ce4..5a6def5e4e6d 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -14,7 +14,7 @@ #include <linux/errno.h> #include <linux/init.h> #include <linux/skbuff.h> -#include <linux/jhash.h> +#include <linux/siphash.h> #include <linux/slab.h> #include <linux/vmalloc.h> #include <net/netlink.h> @@ -117,7 +117,7 @@ struct sfq_sched_data { u8 headdrop; u8 maxdepth; /* limit of packets per flow */ - u32 perturbation; + siphash_key_t perturbation; u8 cur_depth; /* depth of longest slot */ u8 flags; unsigned short scaled_quantum; /* SFQ_ALLOT_SIZE(quantum) */ @@ -157,7 +157,7 @@ static inline struct sfq_head *sfq_dep_head(struct sfq_sched_data *q, sfq_index static unsigned int sfq_hash(const struct sfq_sched_data *q, const struct sk_buff *skb) { - return skb_get_hash_perturb(skb, q->perturbation) & (q->divisor - 1); + return skb_get_hash_perturb(skb, &q->perturbation) & (q->divisor - 1); } static unsigned int sfq_classify(struct sk_buff *skb, struct Qdisc *sch, @@ -607,9 +607,11 @@ static void sfq_perturbation(struct timer_list *t) struct sfq_sched_data *q = from_timer(q, t, perturb_timer); struct Qdisc *sch = q->sch; spinlock_t *root_lock = qdisc_lock(qdisc_root_sleeping(sch)); + siphash_key_t nkey; + get_random_bytes(&nkey, sizeof(nkey)); spin_lock(root_lock); - q->perturbation = prandom_u32(); + q->perturbation = nkey; if (!q->filter_list && q->tail) sfq_rehash(sch); spin_unlock(root_lock); @@ -635,6 +637,15 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) if (ctl->divisor && (!is_power_of_2(ctl->divisor) || ctl->divisor > 65536)) return -EINVAL; + + /* slot->allot is a short, make sure quantum is not too big. */ + if (ctl->quantum) { + unsigned int scaled = SFQ_ALLOT_SIZE(ctl->quantum); + + if (scaled <= 0 || scaled > SHRT_MAX) + return -EINVAL; + } + if (ctl_v1 && !red_check_params(ctl_v1->qth_min, ctl_v1->qth_max, ctl_v1->Wlog)) return -EINVAL; @@ -688,7 +699,7 @@ static int sfq_change(struct Qdisc *sch, struct nlattr *opt) del_timer(&q->perturb_timer); if (q->perturb_period) { mod_timer(&q->perturb_timer, jiffies + q->perturb_period); - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); } sch_tree_unlock(sch); kfree(p); @@ -745,7 +756,7 @@ static int sfq_init(struct Qdisc *sch, struct nlattr *opt, q->quantum = psched_mtu(qdisc_dev(sch)); q->scaled_quantum = SFQ_ALLOT_SIZE(q->quantum); q->perturb_period = 0; - q->perturbation = prandom_u32(); + get_random_bytes(&q->perturbation, sizeof(q->perturbation)); if (opt) { int err = sfq_change(sch, opt); diff --git a/net/sched/sch_skbprio.c b/net/sched/sch_skbprio.c index 0fb10abf7579..7a5e4c454715 100644 --- a/net/sched/sch_skbprio.c +++ b/net/sched/sch_skbprio.c @@ -169,6 +169,9 @@ static int skbprio_change(struct Qdisc *sch, struct nlattr *opt, { struct tc_skbprio_qopt *ctl = nla_data(opt); + if (opt->nla_len != nla_attr_size(sizeof(*ctl))) + return -EINVAL; + sch->limit = ctl->limit; return 0; } diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c index 2f2967dcf15a..bc18daa3ba51 100644 --- a/net/sched/sch_taprio.c +++ b/net/sched/sch_taprio.c @@ -234,8 +234,10 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) prio = skb->priority; tc = netdev_get_prio_tc_map(dev, prio); - if (!(gate_mask & BIT(tc))) + if (!(gate_mask & BIT(tc))) { + skb = NULL; continue; + } len = qdisc_pkt_len(skb); guard = ktime_add_ns(q->get_time(), @@ -245,13 +247,17 @@ static struct sk_buff *taprio_dequeue(struct Qdisc *sch) * guard band ... */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && - ktime_after(guard, entry->close_time)) + ktime_after(guard, entry->close_time)) { + skb = NULL; continue; + } /* ... and no budget. */ if (gate_mask != TAPRIO_ALL_GATES_OPEN && - atomic_sub_return(len, &entry->budget) < 0) + atomic_sub_return(len, &entry->budget) < 0) { + skb = NULL; continue; + } skb = child->ops->dequeue(child); if (unlikely(!skb)) @@ -552,7 +558,7 @@ static int taprio_parse_mqprio_opt(struct net_device *dev, } /* Verify priority mapping uses valid tcs */ - for (i = 0; i < TC_BITMASK + 1; i++) { + for (i = 0; i <= TC_BITMASK; i++) { if (qopt->prio_tc_map[i] >= qopt->num_tc) { NL_SET_ERR_MSG(extack, "Invalid traffic class in priority to traffic class mapping"); return -EINVAL; @@ -709,6 +715,26 @@ static int taprio_dev_notifier(struct notifier_block *nb, unsigned long event, return NOTIFY_DONE; } +static int taprio_mqprio_cmp(const struct net_device *dev, + const struct tc_mqprio_qopt *mqprio) +{ + int i; + + if (!mqprio || mqprio->num_tc != dev->num_tc) + return -1; + + for (i = 0; i < mqprio->num_tc; i++) + if (dev->tc_to_txq[i].count != mqprio->count[i] || + dev->tc_to_txq[i].offset != mqprio->offset[i]) + return -1; + + for (i = 0; i <= TC_BITMASK; i++) + if (dev->prio_tc_map[i] != mqprio->prio_tc_map[i]) + return -1; + + return 0; +} + static int taprio_change(struct Qdisc *sch, struct nlattr *opt, struct netlink_ext_ack *extack) { @@ -745,6 +771,10 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, admin = rcu_dereference(q->admin_sched); rcu_read_unlock(); + /* no changes - no new mqprio settings */ + if (!taprio_mqprio_cmp(dev, mqprio)) + mqprio = NULL; + if (mqprio && (oper || admin)) { NL_SET_ERR_MSG(extack, "Changing the traffic mapping of a running schedule is not supported"); err = -ENOTSUPP; @@ -801,7 +831,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt, mqprio->offset[i]); /* Always use supplied priority mappings */ - for (i = 0; i < TC_BITMASK + 1; i++) + for (i = 0; i <= TC_BITMASK; i++) netdev_set_prio_tc_map(dev, i, mqprio->prio_tc_map[i]); } @@ -877,7 +907,7 @@ static void taprio_destroy(struct Qdisc *sch) } q->qdiscs = NULL; - netdev_set_num_tc(dev, 0); + netdev_reset_tc(dev); if (q->oper_sched) call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb); diff --git a/net/sched/sch_teql.c b/net/sched/sch_teql.c index 689ef6f3ded8..2f1f0a378408 100644 --- a/net/sched/sch_teql.c +++ b/net/sched/sch_teql.c @@ -239,7 +239,7 @@ __teql_resolve(struct sk_buff *skb, struct sk_buff *skb_res, char haddr[MAX_ADDR_LEN]; neigh_ha_snapshot(haddr, n, dev); - err = dev_hard_header(skb, dev, ntohs(tc_skb_protocol(skb)), + err = dev_hard_header(skb, dev, ntohs(skb_protocol(skb, false)), haddr, NULL, skb->len); if (err < 0) diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 1999237ce481..50bbdd385eaa 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -65,6 +65,7 @@ static struct sctp_association *sctp_association_init( /* Discarding const is appropriate here. */ asoc->ep = (struct sctp_endpoint *)ep; asoc->base.sk = (struct sock *)sk; + asoc->base.net = sock_net(sk); sctp_endpoint_hold(asoc->ep); sock_hold(asoc->base.sk); @@ -1579,12 +1580,15 @@ void sctp_assoc_rwnd_decrease(struct sctp_association *asoc, unsigned int len) int sctp_assoc_set_bind_addr_from_ep(struct sctp_association *asoc, enum sctp_scope scope, gfp_t gfp) { + struct sock *sk = asoc->base.sk; int flags; /* Use scoping rules to determine the subset of addresses from * the endpoint. */ - flags = (PF_INET6 == asoc->base.sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + flags = (PF_INET6 == sk->sk_family) ? SCTP_ADDR6_ALLOWED : 0; + if (!inet_v6_ipv6only(sk)) + flags |= SCTP_ADDR4_ALLOWED; if (asoc->peer.ipv4_address) flags |= SCTP_ADDR4_PEERSUPP; if (asoc->peer.ipv6_address) diff --git a/net/sctp/bind_addr.c b/net/sctp/bind_addr.c index f54333cbbe0f..e86a05d3878d 100644 --- a/net/sctp/bind_addr.c +++ b/net/sctp/bind_addr.c @@ -466,6 +466,7 @@ static int sctp_copy_one_addr(struct net *net, struct sctp_bind_addr *dest, * well as the remote peer. */ if ((((AF_INET == addr->sa.sa_family) && + (flags & SCTP_ADDR4_ALLOWED) && (flags & SCTP_ADDR4_PEERSUPP))) || (((AF_INET6 == addr->sa.sa_family) && (flags & SCTP_ADDR6_ALLOWED) && diff --git a/net/sctp/diag.c b/net/sctp/diag.c index fc9a4c6629ce..ba9f64fdfd23 100644 --- a/net/sctp/diag.c +++ b/net/sctp/diag.c @@ -175,7 +175,7 @@ static int inet_sctp_diag_fill(struct sock *sk, struct sctp_association *asoc, mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc; mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued; mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc); - mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len; + mem[SK_MEMINFO_BACKLOG] = READ_ONCE(sk->sk_backlog.len); mem[SK_MEMINFO_DROPS] = atomic_read(&sk->sk_drops); if (nla_put(skb, INET_DIAG_SKMEMINFO, sizeof(mem), &mem) < 0) @@ -237,15 +237,11 @@ static size_t inet_assoc_attr_size(struct sctp_association *asoc) addrcnt++; return nla_total_size(sizeof(struct sctp_info)) - + nla_total_size(1) /* INET_DIAG_SHUTDOWN */ - + nla_total_size(1) /* INET_DIAG_TOS */ - + nla_total_size(1) /* INET_DIAG_TCLASS */ - + nla_total_size(4) /* INET_DIAG_MARK */ - + nla_total_size(4) /* INET_DIAG_CLASS_ID */ + nla_total_size(addrlen * asoc->peer.transport_count) + nla_total_size(addrlen * addrcnt) - + nla_total_size(sizeof(struct inet_diag_meminfo)) + nla_total_size(sizeof(struct inet_diag_msg)) + + inet_diag_msg_attrs_size() + + nla_total_size(sizeof(struct inet_diag_meminfo)) + 64; } diff --git a/net/sctp/endpointola.c b/net/sctp/endpointola.c index 69cebb2c998b..046da0bdc539 100644 --- a/net/sctp/endpointola.c +++ b/net/sctp/endpointola.c @@ -152,6 +152,7 @@ static struct sctp_endpoint *sctp_endpoint_init(struct sctp_endpoint *ep, /* Remember who we are attached to. */ ep->base.sk = sk; + ep->base.net = sock_net(sk); sock_hold(ep->base.sk); return ep; diff --git a/net/sctp/input.c b/net/sctp/input.c index 1008cdc44dd6..2b43b5ed3241 100644 --- a/net/sctp/input.c +++ b/net/sctp/input.c @@ -876,7 +876,7 @@ static inline int sctp_hash_cmp(struct rhashtable_compare_arg *arg, if (!sctp_transport_hold(t)) return err; - if (!net_eq(sock_net(t->asoc->base.sk), x->net)) + if (!net_eq(t->asoc->base.net, x->net)) goto out; if (x->lport != htons(t->asoc->base.bind_addr.port)) goto out; @@ -891,7 +891,7 @@ static inline __u32 sctp_hash_obj(const void *data, u32 len, u32 seed) { const struct sctp_transport *t = data; - return sctp_hashfn(sock_net(t->asoc->base.sk), + return sctp_hashfn(t->asoc->base.net, htons(t->asoc->base.bind_addr.port), &t->ipaddr, seed); } diff --git a/net/sctp/ipv6.c b/net/sctp/ipv6.c index 64e0a594a651..579908a2d2d7 100644 --- a/net/sctp/ipv6.c +++ b/net/sctp/ipv6.c @@ -228,7 +228,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, { struct sctp_association *asoc = t->asoc; struct dst_entry *dst = NULL; - struct flowi6 *fl6 = &fl->u.ip6; + struct flowi _fl; + struct flowi6 *fl6 = &_fl.u.ip6; struct sctp_bind_addr *bp; struct ipv6_pinfo *np = inet6_sk(sk); struct sctp_sockaddr_entry *laddr; @@ -238,7 +239,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, enum sctp_scope scope; __u8 matchlen = 0; - memset(fl6, 0, sizeof(struct flowi6)); + memset(&_fl, 0, sizeof(_fl)); fl6->daddr = daddr->v6.sin6_addr; fl6->fl6_dport = daddr->v6.sin6_port; fl6->flowi6_proto = IPPROTO_SCTP; @@ -275,9 +276,12 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); rcu_read_unlock(); - dst = ip6_dst_lookup_flow(sk, fl6, final_p); - if (!asoc || saddr) + dst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); + if (!asoc || saddr) { + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); goto out; + } bp = &asoc->base.bind_addr; scope = sctp_scope(daddr); @@ -300,6 +304,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if ((laddr->a.sa.sa_family == AF_INET6) && (sctp_v6_cmp_addr(&dst_saddr, &laddr->a))) { rcu_read_unlock(); + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); goto out; } } @@ -328,7 +334,7 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, fl6->saddr = laddr->a.v6.sin6_addr; fl6->fl6_sport = laddr->a.v6.sin6_port; final_p = fl6_update_dst(fl6, rcu_dereference(np->opt), &final); - bdst = ip6_dst_lookup_flow(sk, fl6, final_p); + bdst = ip6_dst_lookup_flow(sock_net(sk), sk, fl6, final_p); if (IS_ERR(bdst)) continue; @@ -338,6 +344,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (!IS_ERR_OR_NULL(dst)) dst_release(dst); dst = bdst; + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); break; } @@ -351,6 +359,8 @@ static void sctp_v6_get_dst(struct sctp_transport *t, union sctp_addr *saddr, dst_release(dst); dst = bdst; matchlen = bmatchlen; + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); } rcu_read_unlock(); @@ -359,14 +369,12 @@ out: struct rt6_info *rt; rt = (struct rt6_info *)dst; - t->dst = dst; t->dst_cookie = rt6_get_cookie(rt); pr_debug("rt6_dst:%pI6/%d rt6_src:%pI6\n", &rt->rt6i_dst.addr, rt->rt6i_dst.plen, - &fl6->saddr); + &fl->u.ip6.saddr); } else { t->dst = NULL; - pr_debug("no route\n"); } } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index e2b4a440416b..5968dbe8ca80 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -148,7 +148,8 @@ int sctp_copy_local_addr_list(struct net *net, struct sctp_bind_addr *bp, * sock as well as the remote peer. */ if (addr->a.sa.sa_family == AF_INET && - !(copy_flags & SCTP_ADDR4_PEERSUPP)) + (!(copy_flags & SCTP_ADDR4_ALLOWED) || + !(copy_flags & SCTP_ADDR4_PEERSUPP))) continue; if (addr->a.sa.sa_family == AF_INET6 && (!(copy_flags & SCTP_ADDR6_ALLOWED) || @@ -227,6 +228,7 @@ static void sctp_v4_from_skb(union sctp_addr *addr, struct sk_buff *skb, sa->sin_port = sh->dest; sa->sin_addr.s_addr = ip_hdr(skb)->daddr; } + memset(sa->sin_zero, 0, sizeof(sa->sin_zero)); } /* Initialize an sctp_addr from a socket. */ @@ -235,6 +237,7 @@ static void sctp_v4_from_sk(union sctp_addr *addr, struct sock *sk) addr->v4.sin_family = AF_INET; addr->v4.sin_port = 0; addr->v4.sin_addr.s_addr = inet_sk(sk)->inet_rcv_saddr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize sk->sk_rcv_saddr from sctp_addr. */ @@ -257,6 +260,7 @@ static void sctp_v4_from_addr_param(union sctp_addr *addr, addr->v4.sin_family = AF_INET; addr->v4.sin_port = port; addr->v4.sin_addr.s_addr = param->v4.addr.s_addr; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Initialize an address parameter from a sctp_addr and return the length @@ -281,6 +285,7 @@ static void sctp_v4_dst_saddr(union sctp_addr *saddr, struct flowi4 *fl4, saddr->v4.sin_family = AF_INET; saddr->v4.sin_port = port; saddr->v4.sin_addr.s_addr = fl4->saddr; + memset(saddr->v4.sin_zero, 0, sizeof(saddr->v4.sin_zero)); } /* Compare two addresses exactly. */ @@ -303,6 +308,7 @@ static void sctp_v4_inaddr_any(union sctp_addr *addr, __be16 port) addr->v4.sin_family = AF_INET; addr->v4.sin_addr.s_addr = htonl(INADDR_ANY); addr->v4.sin_port = port; + memset(addr->v4.sin_zero, 0, sizeof(addr->v4.sin_zero)); } /* Is this a wildcard address? */ @@ -404,7 +410,8 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, { struct sctp_association *asoc = t->asoc; struct rtable *rt; - struct flowi4 *fl4 = &fl->u.ip4; + struct flowi _fl; + struct flowi4 *fl4 = &_fl.u.ip4; struct sctp_bind_addr *bp; struct sctp_sockaddr_entry *laddr; struct dst_entry *dst = NULL; @@ -414,7 +421,7 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, if (t->dscp & SCTP_DSCP_SET_MASK) tos = t->dscp & SCTP_DSCP_VAL_MASK; - memset(fl4, 0x0, sizeof(struct flowi4)); + memset(&_fl, 0x0, sizeof(_fl)); fl4->daddr = daddr->v4.sin_addr.s_addr; fl4->fl4_dport = daddr->v4.sin_port; fl4->flowi4_proto = IPPROTO_SCTP; @@ -433,8 +440,11 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, &fl4->saddr); rt = ip_route_output_key(sock_net(sk), fl4); - if (!IS_ERR(rt)) + if (!IS_ERR(rt)) { dst = &rt->dst; + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); + } /* If there is no association or if a source address is passed, no * more validation is required. @@ -497,27 +507,33 @@ static void sctp_v4_get_dst(struct sctp_transport *t, union sctp_addr *saddr, odev = __ip_dev_find(sock_net(sk), laddr->a.v4.sin_addr.s_addr, false); if (!odev || odev->ifindex != fl4->flowi4_oif) { - if (!dst) + if (!dst) { dst = &rt->dst; - else + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); + } else { dst_release(&rt->dst); + } continue; } dst_release(dst); dst = &rt->dst; + t->dst = dst; + memcpy(fl, &_fl, sizeof(_fl)); break; } out_unlock: rcu_read_unlock(); out: - t->dst = dst; - if (dst) + if (dst) { pr_debug("rt_dst:%pI4, rt_src:%pI4\n", - &fl4->daddr, &fl4->saddr); - else + &fl->u.ip4.daddr, &fl->u.ip4.saddr); + } else { + t->dst = NULL; pr_debug("no route\n"); + } } /* For v4, the source address is cached in the route entry(dst). So no need diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index 9b0e5b0d701a..8f179abec5ed 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -856,7 +856,11 @@ struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, struct sctp_chunk *retval; __u32 ctsn; - ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); + if (chunk && chunk->asoc) + ctsn = sctp_tsnmap_get_ctsn(&chunk->asoc->peer.tsn_map); + else + ctsn = sctp_tsnmap_get_ctsn(&asoc->peer.tsn_map); + shut.cum_tsn_ack = htonl(ctsn); retval = sctp_make_control(asoc, SCTP_CID_SHUTDOWN, 0, diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index e52b2128e43b..6927b658dad3 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1358,8 +1358,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, /* Generate an INIT ACK chunk. */ new_obj = sctp_make_init_ack(asoc, chunk, GFP_ATOMIC, 0); - if (!new_obj) - goto nomem; + if (!new_obj) { + error = -ENOMEM; + break; + } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); @@ -1381,7 +1383,8 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, if (!new_obj) { if (cmd->obj.chunk) sctp_chunk_free(cmd->obj.chunk); - goto nomem; + error = -ENOMEM; + break; } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); @@ -1428,8 +1431,10 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, /* Generate a SHUTDOWN chunk. */ new_obj = sctp_make_shutdown(asoc, chunk); - if (!new_obj) - goto nomem; + if (!new_obj) { + error = -ENOMEM; + break; + } sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(new_obj)); break; @@ -1517,9 +1522,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, timeout = asoc->timeouts[cmd->obj.to]; BUG_ON(!timeout); - timer->expires = jiffies + timeout; - sctp_association_hold(asoc); - add_timer(timer); + /* + * SCTP has a hard time with timer starts. Because we process + * timer starts as side effects, it can be hard to tell if we + * have already started a timer or not, which leads to BUG + * halts when we call add_timer. So here, instead of just starting + * a timer, if the timer is already started, and just mod + * the timer with the shorter of the two expiration times + */ + if (!timer_pending(timer)) + sctp_association_hold(asoc); + timer_reduce(timer, jiffies + timeout); break; case SCTP_CMD_TIMER_RESTART: @@ -1765,11 +1778,17 @@ static int sctp_cmd_interpreter(enum sctp_event_type event_type, break; } - if (error) + if (error) { + cmd = sctp_next_cmd(commands); + while (cmd) { + if (cmd->verb == SCTP_CMD_REPLY) + sctp_chunk_free(cmd->obj.chunk); + cmd = sctp_next_cmd(commands); + } break; + } } -out: /* If this is in response to a received chunk, wait until * we are done with the packet to open the queue so that we don't * send multiple packets in response to a single request. @@ -1784,7 +1803,4 @@ out: sp->data_ready_signalled = 0; return error; -nomem: - error = -ENOMEM; - goto out; } diff --git a/net/sctp/sm_statefuns.c b/net/sctp/sm_statefuns.c index 2c244b29a199..6b2886dc3120 100644 --- a/net/sctp/sm_statefuns.c +++ b/net/sctp/sm_statefuns.c @@ -170,6 +170,16 @@ static inline bool sctp_chunk_length_valid(struct sctp_chunk *chunk, return true; } +/* Check for format error in an ABORT chunk */ +static inline bool sctp_err_chunk_valid(struct sctp_chunk *chunk) +{ + struct sctp_errhdr *err; + + sctp_walk_errors(err, chunk->chunk_hdr); + + return (void *)err == (void *)chunk->chunk_end; +} + /********************************************************** * These are the state functions for handling chunk events. **********************************************************/ @@ -1846,16 +1856,17 @@ static enum sctp_disposition sctp_sf_do_dupcook_a( /* Update the content of current association. */ sctp_add_cmd_sf(commands, SCTP_CMD_UPDATE_ASSOC, SCTP_ASOC(new_asoc)); sctp_add_cmd_sf(commands, SCTP_CMD_EVENT_ULP, SCTP_ULPEVENT(ev)); - if (sctp_state(asoc, SHUTDOWN_PENDING) && + if ((sctp_state(asoc, SHUTDOWN_PENDING) || + sctp_state(asoc, SHUTDOWN_SENT)) && (sctp_sstate(asoc->base.sk, CLOSING) || sock_flag(asoc->base.sk, SOCK_DEAD))) { - /* if were currently in SHUTDOWN_PENDING, but the socket - * has been closed by user, don't transition to ESTABLISHED. - * Instead trigger SHUTDOWN bundled with COOKIE_ACK. + /* If the socket has been closed by user, don't + * transition to ESTABLISHED. Instead trigger SHUTDOWN + * bundled with COOKIE_ACK. */ sctp_add_cmd_sf(commands, SCTP_CMD_REPLY, SCTP_CHUNK(repl)); return sctp_sf_do_9_2_start_shutdown(net, ep, asoc, - SCTP_ST_CHUNK(0), NULL, + SCTP_ST_CHUNK(0), repl, commands); } else { sctp_add_cmd_sf(commands, SCTP_CMD_NEW_STATE, @@ -2160,8 +2171,10 @@ enum sctp_disposition sctp_sf_do_5_2_4_dupcook( /* Update socket peer label if first association. */ if (security_sctp_assoc_request((struct sctp_endpoint *)ep, - chunk->skb)) + chunk->skb)) { + sctp_association_free(new_asoc); return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + } /* Set temp so that it won't be added into hashtable */ new_asoc->temp = 1; @@ -2253,6 +2266,9 @@ enum sctp_disposition sctp_sf_shutdown_pending_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2296,6 +2312,9 @@ enum sctp_disposition sctp_sf_shutdown_sent_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + /* Stop the T2-shutdown timer. */ sctp_add_cmd_sf(commands, SCTP_CMD_TIMER_STOP, SCTP_TO(SCTP_EVENT_TIMEOUT_T2_SHUTDOWN)); @@ -2563,6 +2582,9 @@ enum sctp_disposition sctp_sf_do_9_1_abort( sctp_bind_addr_state(&asoc->base.bind_addr, &chunk->dest)) return sctp_sf_discard_chunk(net, ep, asoc, type, arg, commands); + if (!sctp_err_chunk_valid(chunk)) + return sctp_sf_pdiscard(net, ep, asoc, type, arg, commands); + return __sctp_sf_do_9_1_abort(net, ep, asoc, type, arg, commands); } @@ -2580,16 +2602,8 @@ static enum sctp_disposition __sctp_sf_do_9_1_abort( /* See if we have an error cause code in the chunk. */ len = ntohs(chunk->chunk_hdr->length); - if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) { - struct sctp_errhdr *err; - - sctp_walk_errors(err, chunk->chunk_hdr); - if ((void *)err != (void *)chunk->chunk_end) - return sctp_sf_pdiscard(net, ep, asoc, type, arg, - commands); - + if (len >= sizeof(struct sctp_chunkhdr) + sizeof(struct sctp_errhdr)) error = ((struct sctp_errhdr *)chunk->skb->data)->cause; - } sctp_add_cmd_sf(commands, SCTP_CMD_SET_SK_ERR, SCTP_ERROR(ECONNRESET)); /* ASSOC_FAILED will DELETE_TCB. */ @@ -5455,7 +5469,7 @@ enum sctp_disposition sctp_sf_do_9_2_start_shutdown( * in the Cumulative TSN Ack field the last sequential TSN it * has received from the peer. */ - reply = sctp_make_shutdown(asoc, NULL); + reply = sctp_make_shutdown(asoc, arg); if (!reply) goto nomem; @@ -6053,7 +6067,7 @@ enum sctp_disposition sctp_sf_autoclose_timer_expire( disposition = SCTP_DISPOSITION_CONSUME; if (sctp_outq_is_empty(&asoc->outqueue)) { disposition = sctp_sf_do_9_2_start_shutdown(net, ep, asoc, type, - arg, commands); + NULL, commands); } return disposition; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 34ad7445db13..ed0682f33c8b 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -147,29 +147,44 @@ static void sctp_clear_owner_w(struct sctp_chunk *chunk) skb_orphan(chunk->skb); } +#define traverse_and_process() \ +do { \ + msg = chunk->msg; \ + if (msg == prev_msg) \ + continue; \ + list_for_each_entry(c, &msg->chunks, frag_list) { \ + if ((clear && asoc->base.sk == c->skb->sk) || \ + (!clear && asoc->base.sk != c->skb->sk)) \ + cb(c); \ + } \ + prev_msg = msg; \ +} while (0) + static void sctp_for_each_tx_datachunk(struct sctp_association *asoc, + bool clear, void (*cb)(struct sctp_chunk *)) { + struct sctp_datamsg *msg, *prev_msg = NULL; struct sctp_outq *q = &asoc->outqueue; + struct sctp_chunk *chunk, *c; struct sctp_transport *t; - struct sctp_chunk *chunk; list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) list_for_each_entry(chunk, &t->transmitted, transmitted_list) - cb(chunk); + traverse_and_process(); list_for_each_entry(chunk, &q->retransmit, transmitted_list) - cb(chunk); + traverse_and_process(); list_for_each_entry(chunk, &q->sacked, transmitted_list) - cb(chunk); + traverse_and_process(); list_for_each_entry(chunk, &q->abandoned, transmitted_list) - cb(chunk); + traverse_and_process(); list_for_each_entry(chunk, &q->out_chunk_list, list) - cb(chunk); + traverse_and_process(); } static void sctp_for_each_rx_skb(struct sctp_association *asoc, struct sock *sk, @@ -8331,7 +8346,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) mask = 0; /* Is there any exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); if (sk->sk_shutdown & RCV_SHUTDOWN) @@ -8340,7 +8355,7 @@ __poll_t sctp_poll(struct file *file, struct socket *sock, poll_table *wait) mask |= EPOLLHUP; /* Is it readable? Reconsider this code with TCP-style support. */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* The association is either gone or not ready. */ @@ -8726,7 +8741,7 @@ struct sk_buff *sctp_skb_recv_datagram(struct sock *sk, int flags, if (sk_can_busy_loop(sk)) { sk_busy_loop(sk, noblock); - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) continue; } @@ -9161,7 +9176,7 @@ void sctp_copy_sock(struct sock *newsk, struct sock *sk, newinet->inet_rcv_saddr = inet->inet_rcv_saddr; newinet->inet_dport = htons(asoc->peer.port); newinet->pmtudisc = inet->pmtudisc; - newinet->inet_id = asoc->next_tsn ^ jiffies; + newinet->inet_id = prandom_u32(); newinet->uc_ttl = inet->uc_ttl; newinet->mc_loop = 1; @@ -9316,9 +9331,9 @@ static int sctp_sock_migrate(struct sock *oldsk, struct sock *newsk, * paths won't try to lock it and then oldsk. */ lock_sock_nested(newsk, SINGLE_DEPTH_NESTING); - sctp_for_each_tx_datachunk(assoc, sctp_clear_owner_w); + sctp_for_each_tx_datachunk(assoc, true, sctp_clear_owner_w); sctp_assoc_migrate(assoc, newsk); - sctp_for_each_tx_datachunk(assoc, sctp_set_owner_w); + sctp_for_each_tx_datachunk(assoc, false, sctp_set_owner_w); /* If the association on the newsk is already closed before accept() * is called, set RCV_SHUTDOWN flag. diff --git a/net/sctp/stream.c b/net/sctp/stream.c index e83cdaa2ab76..e13cbd5c0193 100644 --- a/net/sctp/stream.c +++ b/net/sctp/stream.c @@ -22,17 +22,11 @@ #include <net/sctp/sm.h> #include <net/sctp/stream_sched.h> -/* Migrates chunks from stream queues to new stream queues if needed, - * but not across associations. Also, removes those chunks to streams - * higher than the new max. - */ -static void sctp_stream_outq_migrate(struct sctp_stream *stream, - struct sctp_stream *new, __u16 outcnt) +static void sctp_stream_shrink_out(struct sctp_stream *stream, __u16 outcnt) { struct sctp_association *asoc; struct sctp_chunk *ch, *temp; struct sctp_outq *outq; - int i; asoc = container_of(stream, struct sctp_association, stream); outq = &asoc->outqueue; @@ -56,6 +50,19 @@ static void sctp_stream_outq_migrate(struct sctp_stream *stream, sctp_chunk_free(ch); } +} + +/* Migrates chunks from stream queues to new stream queues if needed, + * but not across associations. Also, removes those chunks to streams + * higher than the new max. + */ +static void sctp_stream_outq_migrate(struct sctp_stream *stream, + struct sctp_stream *new, __u16 outcnt) +{ + int i; + + if (stream->outcnt > outcnt) + sctp_stream_shrink_out(stream, outcnt); if (new) { /* Here we actually move the old ext stuff into the new @@ -119,7 +126,7 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, * a new one with new outcnt to save memory if needed. */ if (outcnt == stream->outcnt) - goto in; + goto handle_in; /* Filter out chunks queued on streams that won't exist anymore */ sched->unsched_all(stream); @@ -128,24 +135,28 @@ int sctp_stream_init(struct sctp_stream *stream, __u16 outcnt, __u16 incnt, ret = sctp_stream_alloc_out(stream, outcnt, gfp); if (ret) - goto out; + goto out_err; for (i = 0; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; -in: +handle_in: sctp_stream_interleave_init(stream); if (!incnt) goto out; ret = sctp_stream_alloc_in(stream, incnt, gfp); - if (ret) { - sched->free(stream); - genradix_free(&stream->out); - stream->outcnt = 0; - goto out; - } + if (ret) + goto in_err; + + goto out; +in_err: + sched->free(stream); + genradix_free(&stream->in); +out_err: + genradix_free(&stream->out); + stream->outcnt = 0; out: return ret; } @@ -1034,11 +1045,13 @@ struct sctp_chunk *sctp_process_strreset_resp( nums = ntohs(addstrm->number_of_streams); number = stream->outcnt - nums; - if (result == SCTP_STRRESET_PERFORMED) + if (result == SCTP_STRRESET_PERFORMED) { for (i = number; i < stream->outcnt; i++) SCTP_SO(stream, i)->state = SCTP_STREAM_OPEN; - else + } else { + sctp_stream_shrink_out(stream, number); stream->outcnt = number; + } *evp = sctp_ulpevent_make_stream_change_event(asoc, flags, 0, nums, GFP_ATOMIC); diff --git a/net/sctp/transport.c b/net/sctp/transport.c index e2f8e369cd08..515cef5e0dce 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -263,7 +263,7 @@ bool sctp_transport_update_pmtu(struct sctp_transport *t, u32 pmtu) pf->af->from_sk(&addr, sk); pf->to_sk_daddr(&t->ipaddr, sk); - dst->ops->update_pmtu(dst, sk, NULL, pmtu); + dst->ops->update_pmtu(dst, sk, NULL, pmtu, true); pf->to_sk_daddr(&addr, sk); dst = sctp_transport_dst_check(t); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index a3cc879d2589..1070e6edeca2 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -123,6 +123,14 @@ struct proto smc_proto6 = { }; EXPORT_SYMBOL_GPL(smc_proto6); +static void smc_restore_fallback_changes(struct smc_sock *smc) +{ + if (smc->clcsock->file) { /* non-accepted sockets have no file yet */ + smc->clcsock->file->private_data = smc->sk.sk_socket; + smc->clcsock->file = NULL; + } +} + static int smc_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -160,6 +168,7 @@ static int smc_release(struct socket *sock) } sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); + smc_restore_fallback_changes(smc); } sk->sk_prot->unhash(sk); @@ -690,8 +699,6 @@ static int __smc_connect(struct smc_sock *smc) int smc_type; int rc = 0; - sock_hold(&smc->sk); /* sock put in passive closing */ - if (smc->use_fallback) return smc_connect_fallback(smc, smc->fallback_rsn); @@ -781,6 +788,7 @@ static void smc_connect_work(struct work_struct *work) smc->sk.sk_err = EPIPE; else if (signal_pending(current)) smc->sk.sk_err = -sock_intr_errno(timeo); + sock_put(&smc->sk); /* passive closing */ goto out; } @@ -836,6 +844,10 @@ static int smc_connect(struct socket *sock, struct sockaddr *addr, rc = kernel_connect(smc->clcsock, addr, alen, flags); if (rc && rc != -EINPROGRESS) goto out; + + sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out; if (flags & O_NONBLOCK) { if (schedule_work(&smc->connect_work)) smc->connect_nonblock = 1; @@ -1300,8 +1312,8 @@ static void smc_listen_work(struct work_struct *work) /* check if RDMA is available */ if (!ism_supported) { /* SMC_TYPE_R or SMC_TYPE_B */ /* prepare RDMA check */ - memset(&ini, 0, sizeof(ini)); ini.is_smcd = false; + ini.ism_dev = NULL; ini.ib_lcl = &pclc->lcl; rc = smc_find_rdma_device(new_smc, &ini); if (rc) { @@ -1717,8 +1729,6 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, sk->sk_err = smc->clcsock->sk->sk_err; sk->sk_error_report(sk); } - if (rc) - return rc; if (optlen < sizeof(int)) return -EINVAL; @@ -1726,6 +1736,8 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, return -EFAULT; lock_sock(sk); + if (rc || smc->use_fallback) + goto out; switch (optname) { case TCP_ULP: case TCP_FASTOPEN: @@ -1733,19 +1745,18 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, case TCP_FASTOPEN_KEY: case TCP_FASTOPEN_NO_COOKIE: /* option not supported by SMC */ - if (sk->sk_state == SMC_INIT) { + if (sk->sk_state == SMC_INIT && !smc->connect_nonblock) { smc_switch_to_fallback(smc); smc->fallback_rsn = SMC_CLC_DECL_OPTUNSUPP; } else { - if (!smc->use_fallback) - rc = -EINVAL; + rc = -EINVAL; } break; case TCP_NODELAY: if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (val && !smc->use_fallback) + if (val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1754,7 +1765,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_CLOSED) { - if (!val && !smc->use_fallback) + if (!val) mod_delayed_work(system_wq, &smc->conn.tx_work, 0); } @@ -1765,6 +1776,7 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, default: break; } +out: release_sock(sk); return rc; diff --git a/net/smc/smc_clc.c b/net/smc/smc_clc.c index 745afd82f281..bd0aed55ca20 100644 --- a/net/smc/smc_clc.c +++ b/net/smc/smc_clc.c @@ -369,7 +369,9 @@ int smc_clc_send_decline(struct smc_sock *smc, u32 peer_diag_info) dclc.hdr.length = htons(sizeof(struct smc_clc_msg_decline)); dclc.hdr.version = SMC_CLC_V1; dclc.hdr.flag = (peer_diag_info == SMC_CLC_DECL_SYNCERR) ? 1 : 0; - memcpy(dclc.id_for_peer, local_systemid, sizeof(local_systemid)); + if (smc->conn.lgr && !smc->conn.lgr->is_smcd) + memcpy(dclc.id_for_peer, local_systemid, + sizeof(local_systemid)); dclc.peer_diagnosis = htonl(peer_diag_info); memcpy(dclc.trl.eyecatcher, SMC_EYECATCHER, sizeof(SMC_EYECATCHER)); diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index 4ca50ddf8d16..7bc230928411 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -231,10 +231,12 @@ static int smc_lgr_create(struct smc_sock *smc, struct smc_init_info *ini) lgr->conns_all = RB_ROOT; if (ini->is_smcd) { /* SMC-D specific settings */ + get_device(&ini->ism_dev->dev); lgr->peer_gid = ini->ism_gid; lgr->smcd = ini->ism_dev; } else { /* SMC-R specific settings */ + get_device(&ini->ib_dev->ibdev->dev); lgr->role = smc->listen_smc ? SMC_SERV : SMC_CLNT; memcpy(lgr->peer_systemid, ini->ib_lcl->id_for_peer, SMC_SYSTEMID_LEN); @@ -430,10 +432,13 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr) static void smc_lgr_free(struct smc_link_group *lgr) { smc_lgr_free_bufs(lgr); - if (lgr->is_smcd) + if (lgr->is_smcd) { smc_ism_put_vlan(lgr->smcd, lgr->vlan_id); - else + put_device(&lgr->smcd->dev); + } else { smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); + put_device(&lgr->lnk[SMC_SINGLE_LINK].smcibdev->ibdev->dev); + } kfree(lgr); } diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index f38727ecf8b2..e1f64f4ba236 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -39,16 +39,15 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); + memset(r, 0, sizeof(*r)); r->diag_family = sk->sk_family; + sock_diag_save_cookie(sk, r->id.idiag_cookie); if (!smc->clcsock) return; r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); r->id.idiag_dport = smc->clcsock->sk->sk_dport; r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; - sock_diag_save_cookie(sk, r->id.idiag_cookie); if (sk->sk_protocol == SMCPROTO_SMC) { - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; #if IS_ENABLED(CONFIG_IPV6) diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index d14ca4af6f94..d74a71dff5b8 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -560,12 +560,15 @@ static void smc_ib_remove_dev(struct ib_device *ibdev, void *client_data) struct smc_ib_device *smcibdev; smcibdev = ib_get_client_data(ibdev, &smc_ib_client); + if (!smcibdev || smcibdev->ibdev != ibdev) + return; ib_set_client_data(ibdev, &smc_ib_client, NULL); spin_lock(&smc_ib_devices.lock); list_del_init(&smcibdev->list); /* remove from smc_ib_devices */ spin_unlock(&smc_ib_devices.lock); smc_ib_cleanup_per_ibdev(smcibdev); ib_unregister_event_handler(&smcibdev->event_handler); + cancel_work_sync(&smcibdev->port_event_work); kfree(smcibdev); } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index bab2da8cf17a..a20594056fef 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -376,8 +376,6 @@ static int smc_pnet_fill_entry(struct net *net, return 0; error: - if (pnetelem->ndev) - dev_put(pnetelem->ndev); return rc; } diff --git a/net/socket.c b/net/socket.c index 38eec1583f6d..81ee3118dfa1 100644 --- a/net/socket.c +++ b/net/socket.c @@ -496,7 +496,7 @@ static struct socket *sockfd_lookup_light(int fd, int *err, int *fput_needed) if (f.file) { sock = sock_from_file(f.file, err); if (likely(sock)) { - *fput_needed = f.flags; + *fput_needed = f.flags & FDPUT_FPUT; return sock; } fdput(f); @@ -960,7 +960,7 @@ static ssize_t sock_read_iter(struct kiocb *iocb, struct iov_iter *to) .msg_iocb = iocb}; ssize_t res; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (iocb->ki_pos != 0) @@ -985,7 +985,7 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) if (iocb->ki_pos != 0) return -ESPIPE; - if (file->f_flags & O_NONBLOCK) + if (file->f_flags & O_NONBLOCK || (iocb->ki_flags & IOCB_NOWAIT)) msg.msg_flags = MSG_DONTWAIT; if (sock->type == SOCK_SEQPACKET) @@ -3412,6 +3412,7 @@ static int compat_sock_ioctl_trans(struct file *file, struct socket *sock, case SIOCSARP: case SIOCGARP: case SIOCDARP: + case SIOCOUTQNSD: case SIOCATMARK: return sock_do_ioctl(net, sock, cmd, arg); } diff --git a/net/sunrpc/addr.c b/net/sunrpc/addr.c index d024af4be85e..105d17af4abc 100644 --- a/net/sunrpc/addr.c +++ b/net/sunrpc/addr.c @@ -82,11 +82,11 @@ static size_t rpc_ntop6(const struct sockaddr *sap, rc = snprintf(scopebuf, sizeof(scopebuf), "%c%u", IPV6_SCOPE_DELIMITER, sin6->sin6_scope_id); - if (unlikely((size_t)rc > sizeof(scopebuf))) + if (unlikely((size_t)rc >= sizeof(scopebuf))) return 0; len += rc; - if (unlikely(len > buflen)) + if (unlikely(len >= buflen)) return 0; strcat(buf, scopebuf); diff --git a/net/sunrpc/auth_gss/auth_gss.c b/net/sunrpc/auth_gss/auth_gss.c index 4ce42c62458e..5fc6c028f89c 100644 --- a/net/sunrpc/auth_gss/auth_gss.c +++ b/net/sunrpc/auth_gss/auth_gss.c @@ -20,6 +20,7 @@ #include <linux/sunrpc/clnt.h> #include <linux/sunrpc/auth.h> #include <linux/sunrpc/auth_gss.h> +#include <linux/sunrpc/gss_krb5.h> #include <linux/sunrpc/svcauth_gss.h> #include <linux/sunrpc/gss_err.h> #include <linux/workqueue.h> @@ -1050,7 +1051,7 @@ gss_create_new(const struct rpc_auth_create_args *args, struct rpc_clnt *clnt) goto err_put_mech; auth = &gss_auth->rpc_auth; auth->au_cslack = GSS_CRED_SLACK >> 2; - auth->au_rslack = GSS_VERF_SLACK >> 2; + auth->au_rslack = GSS_KRB5_MAX_SLACK_NEEDED >> 2; auth->au_verfsize = GSS_VERF_SLACK >> 2; auth->au_ralign = GSS_VERF_SLACK >> 2; auth->au_flags = 0; @@ -1934,35 +1935,69 @@ gss_unwrap_resp_auth(struct rpc_cred *cred) return 0; } +/* + * RFC 2203, Section 5.3.2.2 + * + * struct rpc_gss_integ_data { + * opaque databody_integ<>; + * opaque checksum<>; + * }; + * + * struct rpc_gss_data_t { + * unsigned int seq_num; + * proc_req_arg_t arg; + * }; + */ static int gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred, struct gss_cl_ctx *ctx, struct rpc_rqst *rqstp, struct xdr_stream *xdr) { - struct xdr_buf integ_buf, *rcv_buf = &rqstp->rq_rcv_buf; - u32 data_offset, mic_offset, integ_len, maj_stat; + struct xdr_buf gss_data, *rcv_buf = &rqstp->rq_rcv_buf; struct rpc_auth *auth = cred->cr_auth; + u32 len, offset, seqno, maj_stat; struct xdr_netobj mic; - __be32 *p; + int ret; - p = xdr_inline_decode(xdr, 2 * sizeof(*p)); - if (unlikely(!p)) + ret = -EIO; + mic.data = NULL; + + /* opaque databody_integ<>; */ + if (xdr_stream_decode_u32(xdr, &len)) goto unwrap_failed; - integ_len = be32_to_cpup(p++); - if (integ_len & 3) + if (len & 3) goto unwrap_failed; - data_offset = (u8 *)(p) - (u8 *)rcv_buf->head[0].iov_base; - mic_offset = integ_len + data_offset; - if (mic_offset > rcv_buf->len) + offset = rcv_buf->len - xdr_stream_remaining(xdr); + if (xdr_stream_decode_u32(xdr, &seqno)) goto unwrap_failed; - if (be32_to_cpup(p) != rqstp->rq_seqno) + if (seqno != rqstp->rq_seqno) goto bad_seqno; + if (xdr_buf_subsegment(rcv_buf, &gss_data, offset, len)) + goto unwrap_failed; - if (xdr_buf_subsegment(rcv_buf, &integ_buf, data_offset, integ_len)) + /* + * The xdr_stream now points to the beginning of the + * upper layer payload, to be passed below to + * rpcauth_unwrap_resp_decode(). The checksum, which + * follows the upper layer payload in @rcv_buf, is + * located and parsed without updating the xdr_stream. + */ + + /* opaque checksum<>; */ + offset += len; + if (xdr_decode_word(rcv_buf, offset, &len)) + goto unwrap_failed; + offset += sizeof(__be32); + if (offset + len > rcv_buf->len) goto unwrap_failed; - if (xdr_buf_read_netobj(rcv_buf, &mic, mic_offset)) + mic.len = len; + mic.data = kmalloc(len, GFP_NOFS); + if (!mic.data) goto unwrap_failed; - maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &integ_buf, &mic); + if (read_bytes_from_xdr_buf(rcv_buf, offset, mic.data, mic.len)) + goto unwrap_failed; + + maj_stat = gss_verify_mic(ctx->gc_gss_ctx, &gss_data, &mic); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); if (maj_stat != GSS_S_COMPLETE) @@ -1970,16 +2005,21 @@ gss_unwrap_resp_integ(struct rpc_task *task, struct rpc_cred *cred, auth->au_rslack = auth->au_verfsize + 2 + 1 + XDR_QUADLEN(mic.len); auth->au_ralign = auth->au_verfsize + 2; - return 0; + ret = 0; + +out: + kfree(mic.data); + return ret; + unwrap_failed: trace_rpcgss_unwrap_failed(task); - return -EIO; + goto out; bad_seqno: - trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, be32_to_cpup(p)); - return -EIO; + trace_rpcgss_bad_seqno(task, rqstp->rq_seqno, seqno); + goto out; bad_mic: trace_rpcgss_verify_mic(task, maj_stat); - return -EIO; + goto out; } static int @@ -1990,7 +2030,6 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, struct xdr_buf *rcv_buf = &rqstp->rq_rcv_buf; struct kvec *head = rqstp->rq_rcv_buf.head; struct rpc_auth *auth = cred->cr_auth; - unsigned int savedlen = rcv_buf->len; u32 offset, opaque_len, maj_stat; __be32 *p; @@ -2001,9 +2040,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, offset = (u8 *)(p) - (u8 *)head->iov_base; if (offset + opaque_len > rcv_buf->len) goto unwrap_failed; - rcv_buf->len = offset + opaque_len; - maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, rcv_buf); + maj_stat = gss_unwrap(ctx->gc_gss_ctx, offset, + offset + opaque_len, rcv_buf); if (maj_stat == GSS_S_CONTEXT_EXPIRED) clear_bit(RPCAUTH_CRED_UPTODATE, &cred->cr_flags); if (maj_stat != GSS_S_COMPLETE) @@ -2017,10 +2056,9 @@ gss_unwrap_resp_priv(struct rpc_task *task, struct rpc_cred *cred, */ xdr_init_decode(xdr, rcv_buf, p, rqstp); - auth->au_rslack = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); - auth->au_ralign = auth->au_verfsize + 2 + - XDR_QUADLEN(savedlen - rcv_buf->len); + auth->au_rslack = auth->au_verfsize + 2 + ctx->gc_gss_ctx->slack; + auth->au_ralign = auth->au_verfsize + 2 + ctx->gc_gss_ctx->align; + return 0; unwrap_failed: trace_rpcgss_unwrap_failed(task); diff --git a/net/sunrpc/auth_gss/gss_krb5_crypto.c b/net/sunrpc/auth_gss/gss_krb5_crypto.c index 6f2d30d7b766..e7180da1fc6a 100644 --- a/net/sunrpc/auth_gss/gss_krb5_crypto.c +++ b/net/sunrpc/auth_gss/gss_krb5_crypto.c @@ -851,8 +851,8 @@ out_err: } u32 -gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, - u32 *headskip, u32 *tailskip) +gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, u32 len, + struct xdr_buf *buf, u32 *headskip, u32 *tailskip) { struct xdr_buf subbuf; u32 ret = 0; @@ -881,7 +881,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, /* create a segment skipping the header and leaving out the checksum */ xdr_buf_subsegment(buf, &subbuf, offset + GSS_KRB5_TOK_HDR_LEN, - (buf->len - offset - GSS_KRB5_TOK_HDR_LEN - + (len - offset - GSS_KRB5_TOK_HDR_LEN - kctx->gk5e->cksumlength)); nblocks = (subbuf.len + blocksize - 1) / blocksize; @@ -926,7 +926,7 @@ gss_krb5_aes_decrypt(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, goto out_err; /* Get the packet's hmac value */ - ret = read_bytes_from_xdr_buf(buf, buf->len - kctx->gk5e->cksumlength, + ret = read_bytes_from_xdr_buf(buf, len - kctx->gk5e->cksumlength, pkt_hmac, kctx->gk5e->cksumlength); if (ret) goto out_err; diff --git a/net/sunrpc/auth_gss/gss_krb5_mech.c b/net/sunrpc/auth_gss/gss_krb5_mech.c index 6e5d6d240215..75b3c2e9e8f8 100644 --- a/net/sunrpc/auth_gss/gss_krb5_mech.c +++ b/net/sunrpc/auth_gss/gss_krb5_mech.c @@ -253,6 +253,7 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) { u32 seq_send; int tmp; + u32 time32; p = simple_get_bytes(p, end, &ctx->initiate, sizeof(ctx->initiate)); if (IS_ERR(p)) @@ -290,9 +291,11 @@ gss_import_v1_context(const void *p, const void *end, struct krb5_ctx *ctx) p = ERR_PTR(-ENOSYS); goto out_err; } - p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime)); + p = simple_get_bytes(p, end, &time32, sizeof(time32)); if (IS_ERR(p)) goto out_err; + /* unsigned 32-bit time overflows in year 2106 */ + ctx->endtime = (time64_t)time32; p = simple_get_bytes(p, end, &seq_send, sizeof(seq_send)); if (IS_ERR(p)) goto out_err; @@ -587,15 +590,18 @@ gss_import_v2_context(const void *p, const void *end, struct krb5_ctx *ctx, { u64 seq_send64; int keylen; + u32 time32; p = simple_get_bytes(p, end, &ctx->flags, sizeof(ctx->flags)); if (IS_ERR(p)) goto out_err; ctx->initiate = ctx->flags & KRB5_CTX_FLAG_INITIATOR; - p = simple_get_bytes(p, end, &ctx->endtime, sizeof(ctx->endtime)); + p = simple_get_bytes(p, end, &time32, sizeof(time32)); if (IS_ERR(p)) goto out_err; + /* unsigned 32-bit time overflows in year 2106 */ + ctx->endtime = (time64_t)time32; p = simple_get_bytes(p, end, &seq_send64, sizeof(seq_send64)); if (IS_ERR(p)) goto out_err; @@ -659,7 +665,7 @@ out_err: static int gss_import_sec_context_kerberos(const void *p, size_t len, struct gss_ctx *ctx_id, - time_t *endtime, + time64_t *endtime, gfp_t gfp_mask) { const void *end = (const void *)((const char *)p + len); diff --git a/net/sunrpc/auth_gss/gss_krb5_seal.c b/net/sunrpc/auth_gss/gss_krb5_seal.c index 48fe4a591b54..f1d280accf43 100644 --- a/net/sunrpc/auth_gss/gss_krb5_seal.c +++ b/net/sunrpc/auth_gss/gss_krb5_seal.c @@ -131,14 +131,14 @@ gss_get_mic_v1(struct krb5_ctx *ctx, struct xdr_buf *text, struct xdr_netobj md5cksum = {.len = sizeof(cksumdata), .data = cksumdata}; void *ptr; - s32 now; + time64_t now; u32 seq_send; u8 *cksumkey; dprintk("RPC: %s\n", __func__); BUG_ON(ctx == NULL); - now = get_seconds(); + now = ktime_get_real_seconds(); ptr = setup_token(ctx, token); @@ -170,7 +170,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, struct xdr_netobj cksumobj = { .len = sizeof(cksumdata), .data = cksumdata}; void *krb5_hdr; - s32 now; + time64_t now; u8 *cksumkey; unsigned int cksum_usage; __be64 seq_send_be64; @@ -198,7 +198,7 @@ gss_get_mic_v2(struct krb5_ctx *ctx, struct xdr_buf *text, memcpy(krb5_hdr + GSS_KRB5_TOK_HDR_LEN, cksumobj.data, cksumobj.len); - now = get_seconds(); + now = ktime_get_real_seconds(); return (ctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } diff --git a/net/sunrpc/auth_gss/gss_krb5_unseal.c b/net/sunrpc/auth_gss/gss_krb5_unseal.c index ef2b25b86d2f..aaab91cf24c8 100644 --- a/net/sunrpc/auth_gss/gss_krb5_unseal.c +++ b/net/sunrpc/auth_gss/gss_krb5_unseal.c @@ -124,7 +124,7 @@ gss_verify_mic_v1(struct krb5_ctx *ctx, /* it got through unscathed. Make sure the context is unexpired */ - now = get_seconds(); + now = ktime_get_real_seconds(); if (now > ctx->endtime) return GSS_S_CONTEXT_EXPIRED; @@ -149,7 +149,7 @@ gss_verify_mic_v2(struct krb5_ctx *ctx, char cksumdata[GSS_KRB5_MAX_CKSUM_LEN]; struct xdr_netobj cksumobj = {.len = sizeof(cksumdata), .data = cksumdata}; - s32 now; + time64_t now; u8 *ptr = read_token->data; u8 *cksumkey; u8 flags; @@ -194,7 +194,7 @@ gss_verify_mic_v2(struct krb5_ctx *ctx, return GSS_S_BAD_SIG; /* it got through unscathed. Make sure the context is unexpired */ - now = get_seconds(); + now = ktime_get_real_seconds(); if (now > ctx->endtime) return GSS_S_CONTEXT_EXPIRED; diff --git a/net/sunrpc/auth_gss/gss_krb5_wrap.c b/net/sunrpc/auth_gss/gss_krb5_wrap.c index 14a0aff0cd84..90b8329fef82 100644 --- a/net/sunrpc/auth_gss/gss_krb5_wrap.c +++ b/net/sunrpc/auth_gss/gss_krb5_wrap.c @@ -163,7 +163,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, .data = cksumdata}; int blocksize = 0, plainlen; unsigned char *ptr, *msg_start; - s32 now; + time64_t now; int headlen; struct page **tmp_pages; u32 seq_send; @@ -172,7 +172,7 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, dprintk("RPC: %s\n", __func__); - now = get_seconds(); + now = ktime_get_real_seconds(); blocksize = crypto_sync_skcipher_blocksize(kctx->enc); gss_krb5_add_padding(buf, offset, blocksize); @@ -261,14 +261,16 @@ gss_wrap_kerberos_v1(struct krb5_ctx *kctx, int offset, } static u32 -gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { int signalg; int sealalg; char cksumdata[GSS_KRB5_MAX_CKSUM_LEN]; struct xdr_netobj md5cksum = {.len = sizeof(cksumdata), .data = cksumdata}; - s32 now; + time64_t now; int direction; s32 seqnum; unsigned char *ptr; @@ -279,12 +281,13 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) u32 conflen = kctx->gk5e->conflen; int crypt_offset; u8 *cksumkey; + unsigned int saved_len = buf->len; dprintk("RPC: gss_unwrap_kerberos\n"); ptr = (u8 *)buf->head[0].iov_base + offset; if (g_verify_token_header(&kctx->mech_used, &bodysize, &ptr, - buf->len - offset)) + len - offset)) return GSS_S_DEFECTIVE_TOKEN; if ((ptr[0] != ((KG_TOK_WRAP_MSG >> 8) & 0xff)) || @@ -324,6 +327,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) (!kctx->initiate && direction != 0)) return GSS_S_BAD_SIG; + buf->len = len; if (kctx->enctype == ENCTYPE_ARCFOUR_HMAC) { struct crypto_sync_skcipher *cipher; int err; @@ -359,7 +363,7 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) /* it got through unscathed. Make sure the context is unexpired */ - now = get_seconds(); + now = ktime_get_real_seconds(); if (now > kctx->endtime) return GSS_S_CONTEXT_EXPIRED; @@ -376,11 +380,15 @@ gss_unwrap_kerberos_v1(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) data_len = (buf->head[0].iov_base + buf->head[0].iov_len) - data_start; memmove(orig_start, data_start, data_len); buf->head[0].iov_len -= (data_start - orig_start); - buf->len -= (data_start - orig_start); + buf->len = len - (data_start - orig_start); if (gss_krb5_remove_padding(buf, blocksize)) return GSS_S_DEFECTIVE_TOKEN; + /* slack must include room for krb5 padding */ + *slack = XDR_QUADLEN(saved_len - buf->len); + /* The GSS blob always precedes the RPC message payload */ + *align = *slack; return GSS_S_COMPLETE; } @@ -439,7 +447,7 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, struct xdr_buf *buf, struct page **pages) { u8 *ptr, *plainhdr; - s32 now; + time64_t now; u8 flags = 0x00; __be16 *be16ptr; __be64 *be64ptr; @@ -481,14 +489,16 @@ gss_wrap_kerberos_v2(struct krb5_ctx *kctx, u32 offset, if (err) return err; - now = get_seconds(); + now = ktime_get_real_seconds(); return (kctx->endtime < now) ? GSS_S_CONTEXT_EXPIRED : GSS_S_COMPLETE; } static u32 -gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, int len, + struct xdr_buf *buf, unsigned int *slack, + unsigned int *align) { - s32 now; + time64_t now; u8 *ptr; u8 flags = 0x00; u16 ec, rrc; @@ -532,7 +542,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) if (rrc != 0) rotate_left(offset + 16, buf, rrc); - err = (*kctx->gk5e->decrypt_v2)(kctx, offset, buf, + err = (*kctx->gk5e->decrypt_v2)(kctx, offset, len, buf, &headskip, &tailskip); if (err) return GSS_S_FAILURE; @@ -542,7 +552,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * it against the original */ err = read_bytes_from_xdr_buf(buf, - buf->len - GSS_KRB5_TOK_HDR_LEN - tailskip, + len - GSS_KRB5_TOK_HDR_LEN - tailskip, decrypted_hdr, GSS_KRB5_TOK_HDR_LEN); if (err) { dprintk("%s: error %u getting decrypted_hdr\n", __func__, err); @@ -557,7 +567,7 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) /* do sequencing checks */ /* it got through unscathed. Make sure the context is unexpired */ - now = get_seconds(); + now = ktime_get_real_seconds(); if (now > kctx->endtime) return GSS_S_CONTEXT_EXPIRED; @@ -568,18 +578,19 @@ gss_unwrap_kerberos_v2(struct krb5_ctx *kctx, int offset, struct xdr_buf *buf) * Note that buf->head[0].iov_len may indicate the available * head buffer space rather than that actually occupied. */ - movelen = min_t(unsigned int, buf->head[0].iov_len, buf->len); + movelen = min_t(unsigned int, buf->head[0].iov_len, len); movelen -= offset + GSS_KRB5_TOK_HDR_LEN + headskip; - if (offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > - buf->head[0].iov_len) - return GSS_S_FAILURE; + BUG_ON(offset + GSS_KRB5_TOK_HDR_LEN + headskip + movelen > + buf->head[0].iov_len); memmove(ptr, ptr + GSS_KRB5_TOK_HDR_LEN + headskip, movelen); buf->head[0].iov_len -= GSS_KRB5_TOK_HDR_LEN + headskip; - buf->len -= GSS_KRB5_TOK_HDR_LEN + headskip; + buf->len = len - (GSS_KRB5_TOK_HDR_LEN + headskip); /* Trim off the trailing "extra count" and checksum blob */ - buf->len -= ec + GSS_KRB5_TOK_HDR_LEN + tailskip; + xdr_buf_trim(buf, ec + GSS_KRB5_TOK_HDR_LEN + tailskip); + *align = XDR_QUADLEN(GSS_KRB5_TOK_HDR_LEN + headskip); + *slack = *align + XDR_QUADLEN(ec + GSS_KRB5_TOK_HDR_LEN + tailskip); return GSS_S_COMPLETE; } @@ -603,7 +614,8 @@ gss_wrap_kerberos(struct gss_ctx *gctx, int offset, } u32 -gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) +gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, + int len, struct xdr_buf *buf) { struct krb5_ctx *kctx = gctx->internal_ctx_id; @@ -613,9 +625,11 @@ gss_unwrap_kerberos(struct gss_ctx *gctx, int offset, struct xdr_buf *buf) case ENCTYPE_DES_CBC_RAW: case ENCTYPE_DES3_CBC_RAW: case ENCTYPE_ARCFOUR_HMAC: - return gss_unwrap_kerberos_v1(kctx, offset, buf); + return gss_unwrap_kerberos_v1(kctx, offset, len, buf, + &gctx->slack, &gctx->align); case ENCTYPE_AES128_CTS_HMAC_SHA1_96: case ENCTYPE_AES256_CTS_HMAC_SHA1_96: - return gss_unwrap_kerberos_v2(kctx, offset, buf); + return gss_unwrap_kerberos_v2(kctx, offset, len, buf, + &gctx->slack, &gctx->align); } } diff --git a/net/sunrpc/auth_gss/gss_mech_switch.c b/net/sunrpc/auth_gss/gss_mech_switch.c index 82060099a429..95cebc912f63 100644 --- a/net/sunrpc/auth_gss/gss_mech_switch.c +++ b/net/sunrpc/auth_gss/gss_mech_switch.c @@ -36,6 +36,8 @@ gss_mech_free(struct gss_api_mech *gm) for (i = 0; i < gm->gm_pf_num; i++) { pf = &gm->gm_pfs[i]; + if (pf->domain) + auth_domain_put(pf->domain); kfree(pf->auth_domain_name); pf->auth_domain_name = NULL; } @@ -58,6 +60,7 @@ make_auth_domain_name(char *name) static int gss_mech_svc_setup(struct gss_api_mech *gm) { + struct auth_domain *dom; struct pf_desc *pf; int i, status; @@ -67,10 +70,13 @@ gss_mech_svc_setup(struct gss_api_mech *gm) status = -ENOMEM; if (pf->auth_domain_name == NULL) goto out; - status = svcauth_gss_register_pseudoflavor(pf->pseudoflavor, - pf->auth_domain_name); - if (status) + dom = svcauth_gss_register_pseudoflavor( + pf->pseudoflavor, pf->auth_domain_name); + if (IS_ERR(dom)) { + status = PTR_ERR(dom); goto out; + } + pf->domain = dom; } return 0; out: @@ -374,7 +380,7 @@ int gss_import_sec_context(const void *input_token, size_t bufsize, struct gss_api_mech *mech, struct gss_ctx **ctx_id, - time_t *endtime, + time64_t *endtime, gfp_t gfp_mask) { if (!(*ctx_id = kzalloc(sizeof(**ctx_id), gfp_mask))) @@ -438,10 +444,11 @@ gss_wrap(struct gss_ctx *ctx_id, u32 gss_unwrap(struct gss_ctx *ctx_id, int offset, + int len, struct xdr_buf *buf) { return ctx_id->mech_type->gm_ops - ->gss_unwrap(ctx_id, offset, buf); + ->gss_unwrap(ctx_id, offset, len, buf); } diff --git a/net/sunrpc/auth_gss/svcauth_gss.c b/net/sunrpc/auth_gss/svcauth_gss.c index 8be2f209982b..0bd2df7f2503 100644 --- a/net/sunrpc/auth_gss/svcauth_gss.c +++ b/net/sunrpc/auth_gss/svcauth_gss.c @@ -433,7 +433,7 @@ static int rsc_parse(struct cache_detail *cd, int id; int len, rv; struct rsc rsci, *rscp = NULL; - time_t expiry; + time64_t expiry; int status = -EINVAL; struct gss_api_mech *gm = NULL; @@ -800,7 +800,7 @@ u32 svcauth_gss_flavor(struct auth_domain *dom) EXPORT_SYMBOL_GPL(svcauth_gss_flavor); -int +struct auth_domain * svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name) { struct gss_domain *new; @@ -817,21 +817,23 @@ svcauth_gss_register_pseudoflavor(u32 pseudoflavor, char * name) new->h.flavour = &svcauthops_gss; new->pseudoflavor = pseudoflavor; - stat = 0; test = auth_domain_lookup(name, &new->h); - if (test != &new->h) { /* Duplicate registration */ + if (test != &new->h) { + pr_warn("svc: duplicate registration of gss pseudo flavour %s.\n", + name); + stat = -EADDRINUSE; auth_domain_put(test); - kfree(new->h.name); - goto out_free_dom; + goto out_free_name; } - return 0; + return test; +out_free_name: + kfree(new->h.name); out_free_dom: kfree(new); out: - return stat; + return ERR_PTR(stat); } - EXPORT_SYMBOL_GPL(svcauth_gss_register_pseudoflavor); static inline int @@ -897,7 +899,7 @@ unwrap_integ_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct g if (svc_getnl(&buf->head[0]) != seq) goto out; /* trim off the mic and padding at the end before returning */ - buf->len -= 4 + round_up_to_quad(mic.len); + xdr_buf_trim(buf, round_up_to_quad(mic.len) + 4); stat = 0; out: kfree(mic.data); @@ -925,7 +927,7 @@ static int unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gss_ctx *ctx) { u32 priv_len, maj_stat; - int pad, saved_len, remaining_len, offset; + int pad, remaining_len, offset; clear_bit(RQ_SPLICE_OK, &rqstp->rq_flags); @@ -945,13 +947,8 @@ unwrap_priv_data(struct svc_rqst *rqstp, struct xdr_buf *buf, u32 seq, struct gs buf->len -= pad; fix_priv_head(buf, pad); - /* Maybe it would be better to give gss_unwrap a length parameter: */ - saved_len = buf->len; - buf->len = priv_len; - maj_stat = gss_unwrap(ctx, 0, buf); + maj_stat = gss_unwrap(ctx, 0, priv_len, buf); pad = priv_len - buf->len; - buf->len = saved_len; - buf->len -= pad; /* The upper layers assume the buffer is aligned on 4-byte boundaries. * In the krb5p case, at least, the data ends up offset, so we need to * move it around. */ @@ -1075,24 +1072,32 @@ gss_read_verf(struct rpc_gss_wire_cred *gc, return 0; } -/* Ok this is really heavily depending on a set of semantics in - * how rqstp is set up by svc_recv and pages laid down by the - * server when reading a request. We are basically guaranteed that - * the token lays all down linearly across a set of pages, starting - * at iov_base in rq_arg.head[0] which happens to be the first of a - * set of pages stored in rq_pages[]. - * rq_arg.head[0].iov_base will provide us the page_base to pass - * to the upcall. - */ -static inline int -gss_read_proxy_verf(struct svc_rqst *rqstp, - struct rpc_gss_wire_cred *gc, __be32 *authp, - struct xdr_netobj *in_handle, - struct gssp_in_token *in_token) +static void gss_free_in_token_pages(struct gssp_in_token *in_token) { - struct kvec *argv = &rqstp->rq_arg.head[0]; u32 inlen; - int res; + int i; + + i = 0; + inlen = in_token->page_len; + while (inlen) { + if (in_token->pages[i]) + put_page(in_token->pages[i]); + inlen -= inlen > PAGE_SIZE ? PAGE_SIZE : inlen; + } + + kfree(in_token->pages); + in_token->pages = NULL; +} + +static int gss_read_proxy_verf(struct svc_rqst *rqstp, + struct rpc_gss_wire_cred *gc, __be32 *authp, + struct xdr_netobj *in_handle, + struct gssp_in_token *in_token) +{ + struct kvec *argv = &rqstp->rq_arg.head[0]; + unsigned int page_base, length; + int pages, i, res; + size_t inlen; res = gss_read_common_verf(gc, argv, authp, in_handle); if (res) @@ -1102,10 +1107,36 @@ gss_read_proxy_verf(struct svc_rqst *rqstp, if (inlen > (argv->iov_len + rqstp->rq_arg.page_len)) return SVC_DENIED; - in_token->pages = rqstp->rq_pages; - in_token->page_base = (ulong)argv->iov_base & ~PAGE_MASK; + pages = DIV_ROUND_UP(inlen, PAGE_SIZE); + in_token->pages = kcalloc(pages, sizeof(struct page *), GFP_KERNEL); + if (!in_token->pages) + return SVC_DENIED; + in_token->page_base = 0; in_token->page_len = inlen; + for (i = 0; i < pages; i++) { + in_token->pages[i] = alloc_page(GFP_KERNEL); + if (!in_token->pages[i]) { + gss_free_in_token_pages(in_token); + return SVC_DENIED; + } + } + length = min_t(unsigned int, inlen, argv->iov_len); + memcpy(page_address(in_token->pages[0]), argv->iov_base, length); + inlen -= length; + + i = 1; + page_base = rqstp->rq_arg.page_base; + while (inlen) { + length = min_t(unsigned int, inlen, PAGE_SIZE); + memcpy(page_address(in_token->pages[i]), + page_address(rqstp->rq_arg.pages[i]) + page_base, + length); + + inlen -= length; + page_base = 0; + i++; + } return 0; } @@ -1184,7 +1215,7 @@ static int gss_proxy_save_rsc(struct cache_detail *cd, static atomic64_t ctxhctr; long long ctxh; struct gss_api_mech *gm = NULL; - time_t expiry; + time64_t expiry; int status = -EINVAL; memset(&rsci, 0, sizeof(rsci)); @@ -1211,6 +1242,7 @@ static int gss_proxy_save_rsc(struct cache_detail *cd, dprintk("RPC: No creds found!\n"); goto out; } else { + struct timespec64 boot; /* steal creds */ rsci.cred = ud->creds; @@ -1231,6 +1263,9 @@ static int gss_proxy_save_rsc(struct cache_detail *cd, &expiry, GFP_KERNEL); if (status) goto out; + + getboottime64(&boot); + expiry -= boot.tv_sec; } rsci.h.expiry_time = expiry; @@ -1280,8 +1315,11 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, break; case GSS_S_COMPLETE: status = gss_proxy_save_rsc(sn->rsc_cache, &ud, &handle); - if (status) + if (status) { + pr_info("%s: gss_proxy_save_rsc failed (%d)\n", + __func__, status); goto out; + } cli_handle.data = (u8 *)&handle; cli_handle.len = sizeof(handle); break; @@ -1292,15 +1330,20 @@ static int svcauth_gss_proxy_init(struct svc_rqst *rqstp, /* Got an answer to the upcall; use it: */ if (gss_write_init_verf(sn->rsc_cache, rqstp, - &cli_handle, &ud.major_status)) + &cli_handle, &ud.major_status)) { + pr_info("%s: gss_write_init_verf failed\n", __func__); goto out; + } if (gss_write_resv(resv, PAGE_SIZE, &cli_handle, &ud.out_token, - ud.major_status, ud.minor_status)) + ud.major_status, ud.minor_status)) { + pr_info("%s: gss_write_resv failed\n", __func__); goto out; + } ret = SVC_COMPLETE; out: + gss_free_in_token_pages(&ud.in_token); gssp_free_upcall_data(&ud); return ret; } diff --git a/net/sunrpc/backchannel_rqst.c b/net/sunrpc/backchannel_rqst.c index c47d82622fd1..dd6caa594fbf 100644 --- a/net/sunrpc/backchannel_rqst.c +++ b/net/sunrpc/backchannel_rqst.c @@ -303,8 +303,8 @@ void xprt_free_bc_rqst(struct rpc_rqst *req) */ dprintk("RPC: Last session removed req=%p\n", req); xprt_free_allocation(req); - return; } + xprt_put(xprt); } /* @@ -335,7 +335,7 @@ found: spin_unlock(&xprt->bc_pa_lock); if (new) { if (req != new) - xprt_free_bc_rqst(new); + xprt_free_allocation(new); break; } else if (req) break; @@ -364,6 +364,7 @@ void xprt_complete_bc_request(struct rpc_rqst *req, uint32_t copied) set_bit(RPC_BC_PA_IN_USE, &req->rq_bc_pa_state); dprintk("RPC: add callback request to list\n"); + xprt_get(xprt); spin_lock(&bc_serv->sv_cb_lock); list_add(&req->rq_bc_list, &bc_serv->sv_cb_list); wake_up(&bc_serv->sv_cb_waitq); diff --git a/net/sunrpc/cache.c b/net/sunrpc/cache.c index 66fbb9d2fba7..1270d26990fb 100644 --- a/net/sunrpc/cache.c +++ b/net/sunrpc/cache.c @@ -53,9 +53,6 @@ static void cache_init(struct cache_head *h, struct cache_detail *detail) h->last_refresh = now; } -static inline int cache_is_valid(struct cache_head *h); -static void cache_fresh_locked(struct cache_head *head, time_t expiry, - struct cache_detail *detail); static void cache_fresh_unlocked(struct cache_head *head, struct cache_detail *detail); @@ -105,9 +102,6 @@ static struct cache_head *sunrpc_cache_add_entry(struct cache_detail *detail, if (cache_is_expired(detail, tmp)) { hlist_del_init_rcu(&tmp->cache_list); detail->entries --; - if (cache_is_valid(tmp) == -EAGAIN) - set_bit(CACHE_NEGATIVE, &tmp->flags); - cache_fresh_locked(tmp, 0, detail); freeme = tmp; break; } @@ -1888,7 +1882,9 @@ void sunrpc_cache_unhash(struct cache_detail *cd, struct cache_head *h) if (!hlist_unhashed(&h->cache_list)){ hlist_del_init_rcu(&h->cache_list); cd->entries--; + set_bit(CACHE_CLEANED, &h->flags); spin_unlock(&cd->hash_lock); + cache_fresh_unlocked(h, cd); cache_put(h, cd); } else spin_unlock(&cd->hash_lock); diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d504d3a895d1..62bd29c849c1 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -2341,6 +2341,11 @@ rpc_check_timeout(struct rpc_task *task) { struct rpc_clnt *clnt = task->tk_client; + if (RPC_SIGNALLED(task)) { + rpc_call_rpcerror(task, -ERESTARTSYS); + return; + } + if (xprt_adjust_timeout(task->tk_rqstp) == 0) return; diff --git a/net/sunrpc/rpc_pipe.c b/net/sunrpc/rpc_pipe.c index 126d31472a99..be04bafcdb7f 100644 --- a/net/sunrpc/rpc_pipe.c +++ b/net/sunrpc/rpc_pipe.c @@ -1312,6 +1312,7 @@ rpc_gssd_dummy_populate(struct dentry *root, struct rpc_pipe *pipe_data) q.len = strlen(gssd_dummy_clnt_dir[0].name); clnt_dentry = d_hash_and_lookup(gssd_dentry, &q); if (!clnt_dentry) { + __rpc_depopulate(gssd_dentry, gssd_dummy_clnt_dir, 0, 1); pipe_dentry = ERR_PTR(-ENOENT); goto out; } diff --git a/net/sunrpc/sunrpc.h b/net/sunrpc/sunrpc.h index c9bacb3c930f..82035fa65b8f 100644 --- a/net/sunrpc/sunrpc.h +++ b/net/sunrpc/sunrpc.h @@ -56,4 +56,5 @@ int svc_send_common(struct socket *sock, struct xdr_buf *xdr, int rpc_clients_notifier_register(void); void rpc_clients_notifier_unregister(void); +void auth_domain_cleanup(void); #endif /* _NET_SUNRPC_SUNRPC_H */ diff --git a/net/sunrpc/sunrpc_syms.c b/net/sunrpc/sunrpc_syms.c index f9edaa9174a4..236fadc4a439 100644 --- a/net/sunrpc/sunrpc_syms.c +++ b/net/sunrpc/sunrpc_syms.c @@ -23,6 +23,7 @@ #include <linux/sunrpc/rpc_pipe_fs.h> #include <linux/sunrpc/xprtsock.h> +#include "sunrpc.h" #include "netns.h" unsigned int sunrpc_net_id; @@ -131,6 +132,7 @@ cleanup_sunrpc(void) unregister_rpc_pipefs(); rpc_destroy_mempool(); unregister_pernet_subsys(&sunrpc_net_ops); + auth_domain_cleanup(); #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) rpc_unregister_sysctl(); #endif diff --git a/net/sunrpc/svc.c b/net/sunrpc/svc.c index e15cb704453e..f843d27452c9 100644 --- a/net/sunrpc/svc.c +++ b/net/sunrpc/svc.c @@ -1635,6 +1635,22 @@ u32 svc_max_payload(const struct svc_rqst *rqstp) EXPORT_SYMBOL_GPL(svc_max_payload); /** + * svc_encode_read_payload - mark a range of bytes as a READ payload + * @rqstp: svc_rqst to operate on + * @offset: payload's byte offset in rqstp->rq_res + * @length: size of payload, in bytes + * + * Returns zero on success, or a negative errno if a permanent + * error occurred. + */ +int svc_encode_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + return rqstp->rq_xprt->xpt_ops->xpo_read_payload(rqstp, offset, length); +} +EXPORT_SYMBOL_GPL(svc_encode_read_payload); + +/** * svc_fill_write_vector - Construct data argument for VFS write call * @rqstp: svc_rqst to operate on * @pages: list of pages containing data payload diff --git a/net/sunrpc/svc_xprt.c b/net/sunrpc/svc_xprt.c index 869ce7737997..26384a36237e 100644 --- a/net/sunrpc/svc_xprt.c +++ b/net/sunrpc/svc_xprt.c @@ -897,9 +897,6 @@ int svc_send(struct svc_rqst *rqstp) if (!xprt) goto out; - /* release the receive skb before sending the reply */ - xprt->xpt_ops->xpo_release_rqst(rqstp); - /* calculate over-all length */ xb = &rqstp->rq_res; xb->len = xb->head[0].iov_len + @@ -1028,6 +1025,8 @@ static void svc_delete_xprt(struct svc_xprt *xprt) dprintk("svc: svc_delete_xprt(%p)\n", xprt); xprt->xpt_ops->xpo_detach(xprt); + if (xprt->xpt_bc_xprt) + xprt->xpt_bc_xprt->ops->close(xprt->xpt_bc_xprt); spin_lock_bh(&serv->sv_lock); list_del_init(&xprt->xpt_list); diff --git a/net/sunrpc/svcauth.c b/net/sunrpc/svcauth.c index 550b214cb001..998b196b6176 100644 --- a/net/sunrpc/svcauth.c +++ b/net/sunrpc/svcauth.c @@ -19,6 +19,10 @@ #include <linux/err.h> #include <linux/hash.h> +#include <trace/events/sunrpc.h> + +#include "sunrpc.h" + #define RPCDBG_FACILITY RPCDBG_AUTH @@ -203,3 +207,26 @@ struct auth_domain *auth_domain_find(char *name) return NULL; } EXPORT_SYMBOL_GPL(auth_domain_find); + +/** + * auth_domain_cleanup - check that the auth_domain table is empty + * + * On module unload the auth_domain_table must be empty. To make it + * easier to catch bugs which don't clean up domains properly, we + * warn if anything remains in the table at cleanup time. + * + * Note that we cannot proactively remove the domains at this stage. + * The ->release() function might be in a module that has already been + * unloaded. + */ + +void auth_domain_cleanup(void) +{ + int h; + struct auth_domain *hp; + + for (h = 0; h < DN_HASHMAX; h++) + hlist_for_each_entry(hp, &auth_domain_table[h], hash) + pr_warn("svc: domain %s still present at module unload.\n", + hp->name); +} diff --git a/net/sunrpc/svcsock.c b/net/sunrpc/svcsock.c index 2934dd711715..d52abde51f1b 100644 --- a/net/sunrpc/svcsock.c +++ b/net/sunrpc/svcsock.c @@ -279,6 +279,12 @@ out: return len; } +static int svc_sock_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + return 0; +} + /* * Report socket names for nfsdfs */ @@ -605,6 +611,8 @@ svc_udp_sendto(struct svc_rqst *rqstp) { int error; + svc_release_udp_skb(rqstp); + error = svc_sendto(rqstp, &rqstp->rq_res); if (error == -ECONNREFUSED) /* ICMP error on earlier request. */ @@ -653,6 +661,7 @@ static const struct svc_xprt_ops svc_udp_ops = { .xpo_create = svc_udp_create, .xpo_recvfrom = svc_udp_recvfrom, .xpo_sendto = svc_udp_sendto, + .xpo_read_payload = svc_sock_read_payload, .xpo_release_rqst = svc_release_udp_skb, .xpo_detach = svc_sock_detach, .xpo_free = svc_sock_free, @@ -1137,6 +1146,8 @@ static int svc_tcp_sendto(struct svc_rqst *rqstp) int sent; __be32 reclen; + svc_release_skb(rqstp); + /* Set up the first element of the reply kvec. * Any other kvecs that may be in use have been taken * care of by the server implementation itself. @@ -1171,6 +1182,7 @@ static const struct svc_xprt_ops svc_tcp_ops = { .xpo_create = svc_tcp_create, .xpo_recvfrom = svc_tcp_recvfrom, .xpo_sendto = svc_tcp_sendto, + .xpo_read_payload = svc_sock_read_payload, .xpo_release_rqst = svc_release_skb, .xpo_detach = svc_tcp_sock_detach, .xpo_free = svc_sock_free, diff --git a/net/sunrpc/xdr.c b/net/sunrpc/xdr.c index b256806d69cd..683f058b9061 100644 --- a/net/sunrpc/xdr.c +++ b/net/sunrpc/xdr.c @@ -436,13 +436,12 @@ xdr_shrink_bufhead(struct xdr_buf *buf, size_t len) } /** - * xdr_shrink_pagelen + * xdr_shrink_pagelen - shrinks buf->pages by up to @len bytes * @buf: xdr_buf * @len: bytes to remove from buf->pages * - * Shrinks XDR buffer's page array buf->pages by - * 'len' bytes. The extra data is not lost, but is instead - * moved into the tail. + * The extra data is not lost, but is instead moved into buf->tail. + * Returns the actual number of bytes moved. */ static unsigned int xdr_shrink_pagelen(struct xdr_buf *buf, size_t len) @@ -455,8 +454,8 @@ xdr_shrink_pagelen(struct xdr_buf *buf, size_t len) result = 0; tail = buf->tail; - BUG_ON (len > pglen); - + if (len > buf->page_len) + len = buf-> page_len; tailbuf_len = buf->buflen - buf->head->iov_len - buf->page_len; /* Shift the tail first */ @@ -1119,6 +1118,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->head[0].iov_len; + subbuf->head[0].iov_base = buf->head[0].iov_base; subbuf->head[0].iov_len = 0; } @@ -1131,6 +1131,8 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->page_len; + subbuf->pages = buf->pages; + subbuf->page_base = 0; subbuf->page_len = 0; } @@ -1142,6 +1144,7 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, base = 0; } else { base -= buf->tail[0].iov_len; + subbuf->tail[0].iov_base = buf->tail[0].iov_base; subbuf->tail[0].iov_len = 0; } @@ -1151,6 +1154,47 @@ xdr_buf_subsegment(struct xdr_buf *buf, struct xdr_buf *subbuf, } EXPORT_SYMBOL_GPL(xdr_buf_subsegment); +/** + * xdr_buf_trim - lop at most "len" bytes off the end of "buf" + * @buf: buf to be trimmed + * @len: number of bytes to reduce "buf" by + * + * Trim an xdr_buf by the given number of bytes by fixing up the lengths. Note + * that it's possible that we'll trim less than that amount if the xdr_buf is + * too small, or if (for instance) it's all in the head and the parser has + * already read too far into it. + */ +void xdr_buf_trim(struct xdr_buf *buf, unsigned int len) +{ + size_t cur; + unsigned int trim = len; + + if (buf->tail[0].iov_len) { + cur = min_t(size_t, buf->tail[0].iov_len, trim); + buf->tail[0].iov_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->page_len) { + cur = min_t(unsigned int, buf->page_len, trim); + buf->page_len -= cur; + trim -= cur; + if (!trim) + goto fix_len; + } + + if (buf->head[0].iov_len) { + cur = min_t(size_t, buf->head[0].iov_len, trim); + buf->head[0].iov_len -= cur; + trim -= cur; + } +fix_len: + buf->len -= (len - trim); +} +EXPORT_SYMBOL_GPL(xdr_buf_trim); + static void __read_bytes_from_xdr_buf(struct xdr_buf *subbuf, void *obj, unsigned int len) { unsigned int this_len; @@ -1236,52 +1280,60 @@ xdr_encode_word(struct xdr_buf *buf, unsigned int base, u32 obj) } EXPORT_SYMBOL_GPL(xdr_encode_word); -/* If the netobj starting offset bytes from the start of xdr_buf is contained - * entirely in the head, pages, or tail, set object to point to it; otherwise - * shift the buffer until it is contained entirely within the pages or tail. +/** + * xdr_buf_read_mic() - obtain the address of the GSS mic from xdr buf + * @buf: pointer to buffer containing a mic + * @mic: on success, returns the address of the mic + * @offset: the offset in buf where mic may be found + * + * This function may modify the xdr buf if the mic is found to be straddling + * a boundary between head, pages, and tail. On success the mic can be read + * from the address returned. There is no need to free the mic. + * + * Return: Success returns 0, otherwise an integer error. */ -int xdr_buf_read_netobj(struct xdr_buf *buf, struct xdr_netobj *obj, unsigned int offset) +int xdr_buf_read_mic(struct xdr_buf *buf, struct xdr_netobj *mic, unsigned int offset) { struct xdr_buf subbuf; unsigned int boundary; - if (xdr_decode_word(buf, offset, &obj->len)) + if (xdr_decode_word(buf, offset, &mic->len)) return -EFAULT; offset += 4; - /* Is the obj partially in the head? */ + /* Is the mic partially in the head? */ boundary = buf->head[0].iov_len; - if (offset < boundary && (offset + obj->len) > boundary) + if (offset < boundary && (offset + mic->len) > boundary) xdr_shift_buf(buf, boundary - offset); - /* Is the obj partially in the pages? */ + /* Is the mic partially in the pages? */ boundary += buf->page_len; - if (offset < boundary && (offset + obj->len) > boundary) + if (offset < boundary && (offset + mic->len) > boundary) xdr_shrink_pagelen(buf, boundary - offset); - if (xdr_buf_subsegment(buf, &subbuf, offset, obj->len)) + if (xdr_buf_subsegment(buf, &subbuf, offset, mic->len)) return -EFAULT; - /* Is the obj contained entirely in the head? */ - obj->data = subbuf.head[0].iov_base; - if (subbuf.head[0].iov_len == obj->len) + /* Is the mic contained entirely in the head? */ + mic->data = subbuf.head[0].iov_base; + if (subbuf.head[0].iov_len == mic->len) return 0; - /* ..or is the obj contained entirely in the tail? */ - obj->data = subbuf.tail[0].iov_base; - if (subbuf.tail[0].iov_len == obj->len) + /* ..or is the mic contained entirely in the tail? */ + mic->data = subbuf.tail[0].iov_base; + if (subbuf.tail[0].iov_len == mic->len) return 0; - /* Find a contiguous area in @buf to hold all of @obj */ - if (obj->len > buf->buflen - buf->len) + /* Find a contiguous area in @buf to hold all of @mic */ + if (mic->len > buf->buflen - buf->len) return -ENOMEM; if (buf->tail[0].iov_len != 0) - obj->data = buf->tail[0].iov_base + buf->tail[0].iov_len; + mic->data = buf->tail[0].iov_base + buf->tail[0].iov_len; else - obj->data = buf->head[0].iov_base + buf->head[0].iov_len; - __read_bytes_from_xdr_buf(&subbuf, obj->data, obj->len); + mic->data = buf->head[0].iov_base + buf->head[0].iov_len; + __read_bytes_from_xdr_buf(&subbuf, mic->data, mic->len); return 0; } -EXPORT_SYMBOL_GPL(xdr_buf_read_netobj); +EXPORT_SYMBOL_GPL(xdr_buf_read_mic); /* Returns 0 on success, or else a negative error code. */ static int diff --git a/net/sunrpc/xprtrdma/backchannel.c b/net/sunrpc/xprtrdma/backchannel.c index ce986591f213..63b000824654 100644 --- a/net/sunrpc/xprtrdma/backchannel.c +++ b/net/sunrpc/xprtrdma/backchannel.c @@ -158,6 +158,7 @@ void xprt_rdma_bc_free_rqst(struct rpc_rqst *rqst) spin_lock(&xprt->bc_pa_lock); list_add_tail(&rqst->rq_bc_pa_list, &xprt->bc_pa_list); spin_unlock(&xprt->bc_pa_lock); + xprt_put(xprt); } static struct rpc_rqst *rpcrdma_bc_rqst_get(struct rpcrdma_xprt *r_xprt) @@ -254,6 +255,7 @@ void rpcrdma_bc_receive_call(struct rpcrdma_xprt *r_xprt, /* Queue rqst for ULP's callback service */ bc_serv = xprt->bc_serv; + xprt_get(xprt); spin_lock(&bc_serv->sv_cb_lock); list_add(&rqst->rq_bc_list, &bc_serv->sv_cb_list); spin_unlock(&bc_serv->sv_cb_lock); diff --git a/net/sunrpc/xprtrdma/frwr_ops.c b/net/sunrpc/xprtrdma/frwr_ops.c index 794ba4ca0994..7b1694c0a77e 100644 --- a/net/sunrpc/xprtrdma/frwr_ops.c +++ b/net/sunrpc/xprtrdma/frwr_ops.c @@ -381,8 +381,8 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, struct rpcrdma_frwr *frwr; struct rpcrdma_mr *mr; struct ib_mr *ibmr; + int i, n, dma_nents; struct ib_reg_wr *reg_wr; - int i, n; u8 key; mr = NULL; @@ -417,15 +417,16 @@ struct rpcrdma_mr_seg *frwr_map(struct rpcrdma_xprt *r_xprt, break; } mr->mr_dir = rpcrdma_data_dir(writing); + mr->mr_nents = i; - mr->mr_nents = - ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, i, mr->mr_dir); - if (!mr->mr_nents) + dma_nents = ib_dma_map_sg(ia->ri_id->device, mr->mr_sg, mr->mr_nents, + mr->mr_dir); + if (!dma_nents) goto out_dmamap_err; ibmr = frwr->fr_mr; - n = ib_map_mr_sg(ibmr, mr->mr_sg, mr->mr_nents, NULL, PAGE_SIZE); - if (unlikely(n != mr->mr_nents)) + n = ib_map_mr_sg(ibmr, mr->mr_sg, dma_nents, NULL, PAGE_SIZE); + if (n != dma_nents) goto out_mapmr_err; ibmr->iova &= 0x00000000ffffffff; diff --git a/net/sunrpc/xprtrdma/rpc_rdma.c b/net/sunrpc/xprtrdma/rpc_rdma.c index 85115a2e2639..77a911d14015 100644 --- a/net/sunrpc/xprtrdma/rpc_rdma.c +++ b/net/sunrpc/xprtrdma/rpc_rdma.c @@ -71,7 +71,7 @@ static unsigned int rpcrdma_max_call_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Read list size */ - size = maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); + size += maxsegs * rpcrdma_readchunk_maxsz * sizeof(__be32); /* Minimal Read chunk size */ size += sizeof(__be32); /* segment count */ @@ -96,7 +96,7 @@ static unsigned int rpcrdma_max_reply_header_size(unsigned int maxsegs) size = RPCRDMA_HDRLEN_MIN; /* Maximum Write list size */ - size = sizeof(__be32); /* segment count */ + size += sizeof(__be32); /* segment count */ size += maxsegs * rpcrdma_segment_maxsz * sizeof(__be32); size += sizeof(__be32); /* list discriminator */ @@ -1219,8 +1219,7 @@ rpcrdma_decode_error(struct rpcrdma_xprt *r_xprt, struct rpcrdma_rep *rep, be32_to_cpup(p), be32_to_cpu(rep->rr_xid)); } - r_xprt->rx_stats.bad_reply_count++; - return -EREMOTEIO; + return -EIO; } /* Perform XID lookup, reconstruction of the RPC reply, and @@ -1259,13 +1258,11 @@ out: spin_unlock(&xprt->queue_lock); return; -/* If the incoming reply terminated a pending RPC, the next - * RPC call will post a replacement receive buffer as it is - * being marshaled. - */ out_badheader: trace_xprtrdma_reply_hdr(rep); r_xprt->rx_stats.bad_reply_count++; + rqst->rq_task->tk_status = status; + status = 0; goto out; } @@ -1365,6 +1362,7 @@ void rpcrdma_reply_handler(struct rpcrdma_rep *rep) xprt->cwnd = credits << RPC_CWNDSHIFT; spin_unlock_bh(&xprt->transport_lock); } + rpcrdma_post_recvs(r_xprt, false); req = rpcr_to_rdmar(rqst); if (req->rl_reply) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c index bed57d8b5c19..6436b65f11fb 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_backchannel.c +++ b/net/sunrpc/xprtrdma/svc_rdma_backchannel.c @@ -195,6 +195,7 @@ rpcrdma_bc_send_request(struct svcxprt_rdma *rdma, struct rpc_rqst *rqst) pr_info("%s: %*ph\n", __func__, 64, rqst->rq_buffer); #endif + rqst->rq_xtime = ktime_get(); rc = svc_rdma_bc_sendto(rdma, rqst, ctxt); if (rc) { svc_rdma_send_ctxt_put(rdma, ctxt); @@ -241,6 +242,8 @@ static void xprt_rdma_bc_close(struct rpc_xprt *xprt) { dprintk("svcrdma: %s: xprt %p\n", __func__, xprt); + + xprt_disconnect_done(xprt); xprt->cwnd = RPC_CWNDSHIFT; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c index 65e2fb9aac65..6566620912d6 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c +++ b/net/sunrpc/xprtrdma/svc_rdma_recvfrom.c @@ -193,6 +193,7 @@ svc_rdma_recv_ctxt_get(struct svcxprt_rdma *rdma) out: ctxt->rc_page_count = 0; + ctxt->rc_read_payload_length = 0; return ctxt; out_empty: @@ -226,6 +227,26 @@ void svc_rdma_recv_ctxt_put(struct svcxprt_rdma *rdma, svc_rdma_recv_ctxt_destroy(rdma, ctxt); } +/** + * svc_rdma_release_rqst - Release transport-specific per-rqst resources + * @rqstp: svc_rqst being released + * + * Ensure that the recv_ctxt is released whether or not a Reply + * was sent. For example, the client could close the connection, + * or svc_process could drop an RPC, before the Reply is sent. + */ +void svc_rdma_release_rqst(struct svc_rqst *rqstp) +{ + struct svc_rdma_recv_ctxt *ctxt = rqstp->rq_xprt_ctxt; + struct svc_xprt *xprt = rqstp->rq_xprt; + struct svcxprt_rdma *rdma = + container_of(xprt, struct svcxprt_rdma, sc_xprt); + + rqstp->rq_xprt_ctxt = NULL; + if (ctxt) + svc_rdma_recv_ctxt_put(rdma, ctxt); +} + static int __svc_rdma_post_recv(struct svcxprt_rdma *rdma, struct svc_rdma_recv_ctxt *ctxt) { @@ -760,6 +781,8 @@ int svc_rdma_recvfrom(struct svc_rqst *rqstp) __be32 *p; int ret; + rqstp->rq_xprt_ctxt = NULL; + spin_lock(&rdma_xprt->sc_rq_dto_lock); ctxt = svc_rdma_next_recv_ctxt(&rdma_xprt->sc_read_complete_q); if (ctxt) { diff --git a/net/sunrpc/xprtrdma/svc_rdma_rw.c b/net/sunrpc/xprtrdma/svc_rdma_rw.c index 2121c9b4d275..04ec2a83af69 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_rw.c +++ b/net/sunrpc/xprtrdma/svc_rdma_rw.c @@ -322,8 +322,6 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) if (atomic_sub_return(cc->cc_sqecount, &rdma->sc_sq_avail) > 0) { ret = ib_post_send(rdma->sc_qp, first_wr, &bad_wr); - trace_svcrdma_post_rw(&cc->cc_cqe, - cc->cc_sqecount, ret); if (ret) break; return 0; @@ -336,6 +334,7 @@ static int svc_rdma_post_chunk_ctxt(struct svc_rdma_chunk_ctxt *cc) trace_svcrdma_sq_retry(rdma); } while (1); + trace_svcrdma_sq_post_err(rdma, ret); set_bit(XPT_CLOSE, &xprt->xpt_flags); /* If even one was posted, there will be a completion. */ @@ -481,18 +480,19 @@ static int svc_rdma_send_xdr_kvec(struct svc_rdma_write_info *info, vec->iov_len); } -/* Send an xdr_buf's page list by itself. A Write chunk is - * just the page list. a Reply chunk is the head, page list, - * and tail. This function is shared between the two types - * of chunk. +/* Send an xdr_buf's page list by itself. A Write chunk is just + * the page list. A Reply chunk is @xdr's head, page list, and + * tail. This function is shared between the two types of chunk. */ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, - struct xdr_buf *xdr) + struct xdr_buf *xdr, + unsigned int offset, + unsigned long length) { info->wi_xdr = xdr; - info->wi_next_off = 0; + info->wi_next_off = offset - xdr->head[0].iov_len; return svc_rdma_build_writes(info, svc_rdma_pagelist_to_sg, - xdr->page_len); + length); } /** @@ -500,6 +500,8 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * @rdma: controlling RDMA transport * @wr_ch: Write chunk provided by client * @xdr: xdr_buf containing the data payload + * @offset: payload's byte offset in @xdr + * @length: size of payload, in bytes * * Returns a non-negative number of bytes the chunk consumed, or * %-E2BIG if the payload was larger than the Write chunk, @@ -509,19 +511,20 @@ static int svc_rdma_send_xdr_pagelist(struct svc_rdma_write_info *info, * %-EIO if rdma_rw initialization failed (DMA mapping, etc). */ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, - struct xdr_buf *xdr) + struct xdr_buf *xdr, + unsigned int offset, unsigned long length) { struct svc_rdma_write_info *info; int ret; - if (!xdr->page_len) + if (!length) return 0; info = svc_rdma_write_info_alloc(rdma, wr_ch); if (!info) return -ENOMEM; - ret = svc_rdma_send_xdr_pagelist(info, xdr); + ret = svc_rdma_send_xdr_pagelist(info, xdr, offset, length); if (ret < 0) goto out_err; @@ -530,7 +533,7 @@ int svc_rdma_send_write_chunk(struct svcxprt_rdma *rdma, __be32 *wr_ch, goto out_err; trace_svcrdma_encode_write(xdr->page_len); - return xdr->page_len; + return length; out_err: svc_rdma_write_info_free(info); @@ -570,7 +573,9 @@ int svc_rdma_send_reply_chunk(struct svcxprt_rdma *rdma, __be32 *rp_ch, * client did not provide Write chunks. */ if (!writelist && xdr->page_len) { - ret = svc_rdma_send_xdr_pagelist(info, xdr); + ret = svc_rdma_send_xdr_pagelist(info, xdr, + xdr->head[0].iov_len, + xdr->page_len); if (ret < 0) goto out_err; consumed += xdr->page_len; @@ -671,7 +676,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, struct svc_rdma_read_info *info, __be32 *p) { - unsigned int i; int ret; ret = -EINVAL; @@ -694,12 +698,6 @@ static int svc_rdma_build_read_chunk(struct svc_rqst *rqstp, info->ri_chunklen += rs_length; } - /* Pages under I/O have been copied to head->rc_pages. - * Prevent their premature release by svc_xprt_release() . - */ - for (i = 0; i < info->ri_readctxt->rc_page_count; i++) - rqstp->rq_pages[i] = NULL; - return ret; } @@ -794,6 +792,26 @@ out: return ret; } +/* Pages under I/O have been copied to head->rc_pages. Ensure they + * are not released by svc_xprt_release() until the I/O is complete. + * + * This has to be done after all Read WRs are constructed to properly + * handle a page that is part of I/O on behalf of two different RDMA + * segments. + * + * Do this only if I/O has been posted. Otherwise, we do indeed want + * svc_xprt_release() to clean things up properly. + */ +static void svc_rdma_save_io_pages(struct svc_rqst *rqstp, + const unsigned int start, + const unsigned int num_pages) +{ + unsigned int i; + + for (i = start; i < num_pages + start; i++) + rqstp->rq_pages[i] = NULL; +} + /** * svc_rdma_recv_read_chunk - Pull a Read chunk from the client * @rdma: controlling RDMA transport @@ -847,6 +865,7 @@ int svc_rdma_recv_read_chunk(struct svcxprt_rdma *rdma, struct svc_rqst *rqstp, ret = svc_rdma_post_chunk_ctxt(&info->ri_cc); if (ret < 0) goto out_err; + svc_rdma_save_io_pages(rqstp, 0, head->rc_page_count); return 0; out_err: diff --git a/net/sunrpc/xprtrdma/svc_rdma_sendto.c b/net/sunrpc/xprtrdma/svc_rdma_sendto.c index 6fdba72f89f4..217106c66a13 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_sendto.c +++ b/net/sunrpc/xprtrdma/svc_rdma_sendto.c @@ -306,15 +306,17 @@ int svc_rdma_send(struct svcxprt_rdma *rdma, struct ib_send_wr *wr) } svc_xprt_get(&rdma->sc_xprt); + trace_svcrdma_post_send(wr); ret = ib_post_send(rdma->sc_qp, wr, NULL); - trace_svcrdma_post_send(wr, ret); - if (ret) { - set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); - svc_xprt_put(&rdma->sc_xprt); - wake_up(&rdma->sc_send_wait); - } - break; + if (ret) + break; + return 0; } + + trace_svcrdma_sq_post_err(rdma, ret); + set_bit(XPT_CLOSE, &rdma->sc_xprt.xpt_flags); + svc_xprt_put(&rdma->sc_xprt); + wake_up(&rdma->sc_send_wait); return ret; } @@ -854,7 +856,18 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) if (wr_lst) { /* XXX: Presume the client sent only one Write chunk */ - ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr); + unsigned long offset; + unsigned int length; + + if (rctxt->rc_read_payload_length) { + offset = rctxt->rc_read_payload_offset; + length = rctxt->rc_read_payload_length; + } else { + offset = xdr->head[0].iov_len; + length = xdr->page_len; + } + ret = svc_rdma_send_write_chunk(rdma, wr_lst, xdr, offset, + length); if (ret < 0) goto err2; svc_rdma_xdr_encode_write_list(rdma_resp, wr_lst, ret); @@ -871,12 +884,7 @@ int svc_rdma_sendto(struct svc_rqst *rqstp) wr_lst, rp_ch); if (ret < 0) goto err1; - ret = 0; - -out: - rqstp->rq_xprt_ctxt = NULL; - svc_rdma_recv_ctxt_put(rdma, rctxt); - return ret; + return 0; err2: if (ret != -E2BIG && ret != -EINVAL) @@ -885,14 +893,39 @@ out: ret = svc_rdma_send_error_msg(rdma, sctxt, rqstp); if (ret < 0) goto err1; - ret = 0; - goto out; + return 0; err1: svc_rdma_send_ctxt_put(rdma, sctxt); err0: trace_svcrdma_send_failed(rqstp, ret); set_bit(XPT_CLOSE, &xprt->xpt_flags); - ret = -ENOTCONN; - goto out; + return -ENOTCONN; +} + +/** + * svc_rdma_read_payload - special processing for a READ payload + * @rqstp: svc_rqst to operate on + * @offset: payload's byte offset in @xdr + * @length: size of payload, in bytes + * + * Returns zero on success. + * + * For the moment, just record the xdr_buf location of the READ + * payload. svc_rdma_sendto will use that location later when + * we actually send the payload. + */ +int svc_rdma_read_payload(struct svc_rqst *rqstp, unsigned int offset, + unsigned int length) +{ + struct svc_rdma_recv_ctxt *rctxt = rqstp->rq_xprt_ctxt; + + /* XXX: Just one READ payload slot for now, since our + * transport implementation currently supports only one + * Write chunk. + */ + rctxt->rc_read_payload_offset = offset; + rctxt->rc_read_payload_length = length; + + return 0; } diff --git a/net/sunrpc/xprtrdma/svc_rdma_transport.c b/net/sunrpc/xprtrdma/svc_rdma_transport.c index 0004535c0188..acb7c558e4fd 100644 --- a/net/sunrpc/xprtrdma/svc_rdma_transport.c +++ b/net/sunrpc/xprtrdma/svc_rdma_transport.c @@ -71,7 +71,6 @@ static struct svc_xprt *svc_rdma_create(struct svc_serv *serv, struct sockaddr *sa, int salen, int flags); static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt); -static void svc_rdma_release_rqst(struct svc_rqst *); static void svc_rdma_detach(struct svc_xprt *xprt); static void svc_rdma_free(struct svc_xprt *xprt); static int svc_rdma_has_wspace(struct svc_xprt *xprt); @@ -82,6 +81,7 @@ static const struct svc_xprt_ops svc_rdma_ops = { .xpo_create = svc_rdma_create, .xpo_recvfrom = svc_rdma_recvfrom, .xpo_sendto = svc_rdma_sendto, + .xpo_read_payload = svc_rdma_read_payload, .xpo_release_rqst = svc_rdma_release_rqst, .xpo_detach = svc_rdma_detach, .xpo_free = svc_rdma_free, @@ -559,10 +559,6 @@ static struct svc_xprt *svc_rdma_accept(struct svc_xprt *xprt) return NULL; } -static void svc_rdma_release_rqst(struct svc_rqst *rqstp) -{ -} - /* * When connected, an svc_xprt has at least two references: * diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 3f67c395845d..638285d6602d 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -81,7 +81,6 @@ rpcrdma_regbuf_alloc(size_t size, enum dma_data_direction direction, gfp_t flags); static void rpcrdma_regbuf_dma_unmap(struct rpcrdma_regbuf *rb); static void rpcrdma_regbuf_free(struct rpcrdma_regbuf *rb); -static void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* Wait for outstanding transport work to finish. ib_drain_qp * handles the drains in the wrong order for us, so open code @@ -169,7 +168,6 @@ rpcrdma_wc_receive(struct ib_cq *cq, struct ib_wc *wc) rdmab_addr(rep->rr_rdmabuf), wc->byte_len, DMA_FROM_DEVICE); - rpcrdma_post_recvs(r_xprt, false); rpcrdma_reply_handler(rep); return; @@ -246,6 +244,7 @@ rpcrdma_cm_event_handler(struct rdma_cm_id *id, struct rdma_cm_event *event) ia->ri_id->device->name, rpcrdma_addrstr(r_xprt), rpcrdma_portstr(r_xprt)); #endif + init_completion(&ia->ri_remove_done); set_bit(RPCRDMA_IAF_REMOVING, &ia->ri_flags); ep->rep_connected = -ENODEV; xprt_force_disconnect(xprt); @@ -300,7 +299,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) trace_xprtrdma_conn_start(xprt); init_completion(&ia->ri_done); - init_completion(&ia->ri_remove_done); id = rdma_create_id(xprt->rx_xprt.xprt_net, rpcrdma_cm_event_handler, xprt, RDMA_PS_TCP, IB_QPT_RC); @@ -611,6 +609,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, struct ib_qp_init_attr *qp_init_attr) { struct rpcrdma_ia *ia = &r_xprt->rx_ia; + struct rpcrdma_ep *ep = &r_xprt->rx_ep; int rc, err; trace_xprtrdma_reinsert(r_xprt); @@ -625,6 +624,7 @@ static int rpcrdma_ep_recreate_xprt(struct rpcrdma_xprt *r_xprt, pr_err("rpcrdma: rpcrdma_ep_create returned %d\n", err); goto out2; } + memcpy(qp_init_attr, &ep->rep_attr, sizeof(*qp_init_attr)); rc = -ENETUNREACH; err = rdma_create_qp(ia->ri_id, ia->ri_pd, qp_init_attr); @@ -1502,8 +1502,13 @@ rpcrdma_ep_post(struct rpcrdma_ia *ia, return 0; } -static void -rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) +/** + * rpcrdma_post_recvs - Refill the Receive Queue + * @r_xprt: controlling transport instance + * @temp: mark Receive buffers to be deleted after use + * + */ +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) { struct rpcrdma_buffer *buf = &r_xprt->rx_buf; struct rpcrdma_ep *ep = &r_xprt->rx_ep; diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index d1e0749bcbc4..6554f89ebaa1 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -496,6 +496,7 @@ void rpcrdma_ep_disconnect(struct rpcrdma_ep *, struct rpcrdma_ia *); int rpcrdma_ep_post(struct rpcrdma_ia *, struct rpcrdma_ep *, struct rpcrdma_req *); +void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp); /* * Buffer calls - xprtrdma/verbs.c diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 85166c552542..676bc9c30477 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -2611,6 +2611,8 @@ static int bc_sendto(struct rpc_rqst *req) .iov_len = sizeof(marker), }; + req->rq_xtime = ktime_get(); + len = kernel_sendmsg(transport->sock, &msg, &iov, 1, iov.iov_len); if (len != iov.iov_len) return -EAGAIN; @@ -2636,7 +2638,6 @@ static int bc_send_request(struct rpc_rqst *req) struct svc_xprt *xprt; int len; - dprintk("sending request with xid: %08x\n", ntohl(req->rq_xid)); /* * Get the server socket associated with this callback xprt */ @@ -2665,6 +2666,7 @@ static int bc_send_request(struct rpc_rqst *req) static void bc_close(struct rpc_xprt *xprt) { + xprt_disconnect_done(xprt); } /* diff --git a/net/tipc/bcast.c b/net/tipc/bcast.c index 6c997d4a6218..f04a105d8768 100644 --- a/net/tipc/bcast.c +++ b/net/tipc/bcast.c @@ -305,17 +305,17 @@ static int tipc_rcast_xmit(struct net *net, struct sk_buff_head *pkts, * @skb: socket buffer to copy * @method: send method to be used * @dests: destination nodes for message. - * @cong_link_cnt: returns number of encountered congested destination links * Returns 0 if success, otherwise errno */ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, struct tipc_mc_method *method, - struct tipc_nlist *dests, - u16 *cong_link_cnt) + struct tipc_nlist *dests) { struct tipc_msg *hdr, *_hdr; struct sk_buff_head tmpq; struct sk_buff *_skb; + u16 cong_link_cnt; + int rc = 0; /* Is a cluster supporting with new capabilities ? */ if (!(tipc_net(net)->capabilities & TIPC_MCAST_RBCTL)) @@ -343,18 +343,19 @@ static int tipc_mcast_send_sync(struct net *net, struct sk_buff *skb, _hdr = buf_msg(_skb); msg_set_size(_hdr, MCAST_H_SIZE); msg_set_is_rcast(_hdr, !msg_is_rcast(hdr)); + msg_set_errcode(_hdr, TIPC_ERR_NO_PORT); skb_queue_head_init(&tmpq); __skb_queue_tail(&tmpq, _skb); if (method->rcast) - tipc_bcast_xmit(net, &tmpq, cong_link_cnt); + rc = tipc_bcast_xmit(net, &tmpq, &cong_link_cnt); else - tipc_rcast_xmit(net, &tmpq, dests, cong_link_cnt); + rc = tipc_rcast_xmit(net, &tmpq, dests, &cong_link_cnt); /* This queue should normally be empty by now */ __skb_queue_purge(&tmpq); - return 0; + return rc; } /* tipc_mcast_xmit - deliver message to indicated destination nodes @@ -396,9 +397,14 @@ int tipc_mcast_xmit(struct net *net, struct sk_buff_head *pkts, msg_set_is_rcast(hdr, method->rcast); /* Switch method ? */ - if (rcast != method->rcast) - tipc_mcast_send_sync(net, skb, method, - dests, cong_link_cnt); + if (rcast != method->rcast) { + rc = tipc_mcast_send_sync(net, skb, method, dests); + if (unlikely(rc)) { + pr_err("Unable to send SYN: method %d, rc %d\n", + rcast, rc); + goto exit; + } + } if (method->rcast) rc = tipc_rcast_xmit(net, pkts, dests, cong_link_cnt); diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index 2bed6589f41e..17ed11af2a13 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -138,10 +138,7 @@ static int bearer_name_validate(const char *name, u32 if_len; /* copy bearer name & ensure length is OK */ - name_copy[TIPC_MAX_BEARER_NAME - 1] = 0; - /* need above in case non-Posix strncpy() doesn't pad with nulls */ - strncpy(name_copy, name, TIPC_MAX_BEARER_NAME); - if (name_copy[TIPC_MAX_BEARER_NAME - 1] != 0) + if (strscpy(name_copy, name, TIPC_MAX_BEARER_NAME) < 0) return 0; /* ensure all component parts of bearer name are present */ diff --git a/net/tipc/core.c b/net/tipc/core.c index c8370722f0bb..10d5b888a9c1 100644 --- a/net/tipc/core.c +++ b/net/tipc/core.c @@ -122,14 +122,6 @@ static int __init tipc_init(void) sysctl_tipc_rmem[1] = RCVBUF_DEF; sysctl_tipc_rmem[2] = RCVBUF_MAX; - err = tipc_netlink_start(); - if (err) - goto out_netlink; - - err = tipc_netlink_compat_start(); - if (err) - goto out_netlink_compat; - err = tipc_register_sysctl(); if (err) goto out_sysctl; @@ -150,8 +142,21 @@ static int __init tipc_init(void) if (err) goto out_bearer; + err = tipc_netlink_start(); + if (err) + goto out_netlink; + + err = tipc_netlink_compat_start(); + if (err) + goto out_netlink_compat; + pr_info("Started in single node mode\n"); return 0; + +out_netlink_compat: + tipc_netlink_stop(); +out_netlink: + tipc_bearer_cleanup(); out_bearer: unregister_pernet_device(&tipc_topsrv_net_ops); out_pernet_topsrv: @@ -161,22 +166,18 @@ out_socket: out_pernet: tipc_unregister_sysctl(); out_sysctl: - tipc_netlink_compat_stop(); -out_netlink_compat: - tipc_netlink_stop(); -out_netlink: pr_err("Unable to start in single node mode\n"); return err; } static void __exit tipc_exit(void) { + tipc_netlink_compat_stop(); + tipc_netlink_stop(); tipc_bearer_cleanup(); unregister_pernet_device(&tipc_topsrv_net_ops); tipc_socket_stop(); unregister_pernet_device(&tipc_net_ops); - tipc_netlink_stop(); - tipc_netlink_compat_stop(); tipc_unregister_sysctl(); pr_info("Deactivated\n"); diff --git a/net/tipc/monitor.c b/net/tipc/monitor.c index 6a6eae88442f..58708b4c7719 100644 --- a/net/tipc/monitor.c +++ b/net/tipc/monitor.c @@ -665,6 +665,21 @@ void tipc_mon_delete(struct net *net, int bearer_id) kfree(mon); } +void tipc_mon_reinit_self(struct net *net) +{ + struct tipc_monitor *mon; + int bearer_id; + + for (bearer_id = 0; bearer_id < MAX_BEARERS; bearer_id++) { + mon = tipc_monitor(net, bearer_id); + if (!mon) + continue; + write_lock_bh(&mon->lock); + mon->self->addr = tipc_own_addr(net); + write_unlock_bh(&mon->lock); + } +} + int tipc_nl_monitor_set_threshold(struct net *net, u32 cluster_size) { struct tipc_net *tn = tipc_net(net); diff --git a/net/tipc/monitor.h b/net/tipc/monitor.h index 2a21b93e0d04..ed63d2e650b0 100644 --- a/net/tipc/monitor.h +++ b/net/tipc/monitor.h @@ -77,6 +77,7 @@ int __tipc_nl_add_monitor(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id); int tipc_nl_add_monitor_peer(struct net *net, struct tipc_nl_msg *msg, u32 bearer_id, u32 *prev_node); +void tipc_mon_reinit_self(struct net *net); extern const int tipc_max_domain_size; #endif diff --git a/net/tipc/net.c b/net/tipc/net.c index 85707c185360..2de3cec9929d 100644 --- a/net/tipc/net.c +++ b/net/tipc/net.c @@ -42,6 +42,7 @@ #include "node.h" #include "bcast.h" #include "netlink.h" +#include "monitor.h" /* * The TIPC locking policy is designed to ensure a very fine locking @@ -136,6 +137,7 @@ static void tipc_net_finalize(struct net *net, u32 addr) tipc_set_node_addr(net, addr); tipc_named_reinit(net); tipc_sk_reinit(net); + tipc_mon_reinit_self(net); tipc_nametbl_publish(net, TIPC_CFG_SRV, addr, addr, TIPC_CLUSTER_SCOPE, 0, addr); } diff --git a/net/tipc/netlink.c b/net/tipc/netlink.c index 99bd166bccec..e9bbf4a00881 100644 --- a/net/tipc/netlink.c +++ b/net/tipc/netlink.c @@ -111,6 +111,7 @@ const struct nla_policy tipc_nl_prop_policy[TIPC_NLA_PROP_MAX + 1] = { [TIPC_NLA_PROP_PRIO] = { .type = NLA_U32 }, [TIPC_NLA_PROP_TOL] = { .type = NLA_U32 }, [TIPC_NLA_PROP_WIN] = { .type = NLA_U32 }, + [TIPC_NLA_PROP_MTU] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST] = { .type = NLA_U32 }, [TIPC_NLA_PROP_BROADCAST_RATIO] = { .type = NLA_U32 } }; @@ -261,7 +262,7 @@ struct genl_family tipc_genl_family __ro_after_init = { .version = TIPC_GENL_V2_VERSION, .hdrsize = 0, .maxattr = TIPC_NLA_MAX, - .policy = tipc_nl_policy, + .policy = tipc_nl_policy, .netnsok = true, .module = THIS_MODULE, .ops = tipc_genl_v2_ops, diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index acd8a72169c1..f0ffe4407d79 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -550,7 +550,7 @@ static int tipc_nl_compat_link_stat_dump(struct tipc_nl_compat_msg *msg, if (len <= 0) return -EINVAL; - len = min_t(int, len, TIPC_MAX_BEARER_NAME); + len = min_t(int, len, TIPC_MAX_LINK_NAME); if (!string_is_valid(name, len)) return -EINVAL; @@ -832,7 +832,7 @@ static int tipc_nl_compat_link_reset_stats(struct tipc_nl_compat_cmd_doit *cmd, if (len <= 0) return -EINVAL; - len = min_t(int, len, TIPC_MAX_BEARER_NAME); + len = min_t(int, len, TIPC_MAX_LINK_NAME); if (!string_is_valid(name, len)) return -EINVAL; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 83ae41d7e554..648d15045855 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -504,7 +504,7 @@ static void __tipc_shutdown(struct socket *sock, int error) struct sock *sk = sock->sk; struct tipc_sock *tsk = tipc_sk(sk); struct net *net = sock_net(sk); - long timeout = CONN_TIMEOUT_DEFAULT; + long timeout = msecs_to_jiffies(CONN_TIMEOUT_DEFAULT); u32 dnode = tsk_peer_node(tsk); struct sk_buff *skb; @@ -740,7 +740,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, /* fall through */ case TIPC_LISTEN: case TIPC_CONNECTING: - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) revents |= EPOLLIN | EPOLLRDNORM; break; case TIPC_OPEN: @@ -748,7 +748,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, revents |= EPOLLOUT; if (!tipc_sk_type_connectionless(sk)) break; - if (skb_queue_empty(&sk->sk_receive_queue)) + if (skb_queue_empty_lockless(&sk->sk_receive_queue)) break; revents |= EPOLLIN | EPOLLRDNORM; break; @@ -1306,8 +1306,8 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) struct tipc_msg *hdr = &tsk->phdr; struct tipc_name_seq *seq; struct sk_buff_head pkts; - u32 dport, dnode = 0; - u32 type, inst; + u32 dport = 0, dnode = 0; + u32 type = 0, inst = 0; int mtu, rc; if (unlikely(dlen > TIPC_MAX_USER_MSG_SIZE)) @@ -1360,23 +1360,11 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) type = dest->addr.name.name.type; inst = dest->addr.name.name.instance; dnode = dest->addr.name.domain; - msg_set_type(hdr, TIPC_NAMED_MSG); - msg_set_hdr_sz(hdr, NAMED_H_SIZE); - msg_set_nametype(hdr, type); - msg_set_nameinst(hdr, inst); - msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); dport = tipc_nametbl_translate(net, type, inst, &dnode); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dport); if (unlikely(!dport && !dnode)) return -EHOSTUNREACH; } else if (dest->addrtype == TIPC_ADDR_ID) { dnode = dest->addr.id.node; - msg_set_type(hdr, TIPC_DIRECT_MSG); - msg_set_lookup_scope(hdr, 0); - msg_set_destnode(hdr, dnode); - msg_set_destport(hdr, dest->addr.id.ref); - msg_set_hdr_sz(hdr, BASIC_H_SIZE); } else { return -EINVAL; } @@ -1387,13 +1375,31 @@ static int __tipc_sendmsg(struct socket *sock, struct msghdr *m, size_t dlen) if (unlikely(rc)) return rc; + if (dest->addrtype == TIPC_ADDR_NAME) { + msg_set_type(hdr, TIPC_NAMED_MSG); + msg_set_hdr_sz(hdr, NAMED_H_SIZE); + msg_set_nametype(hdr, type); + msg_set_nameinst(hdr, inst); + msg_set_lookup_scope(hdr, tipc_node2scope(dnode)); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dport); + } else { /* TIPC_ADDR_ID */ + msg_set_type(hdr, TIPC_DIRECT_MSG); + msg_set_lookup_scope(hdr, 0); + msg_set_destnode(hdr, dnode); + msg_set_destport(hdr, dest->addr.id.ref); + msg_set_hdr_sz(hdr, BASIC_H_SIZE); + } + skb_queue_head_init(&pkts); mtu = tipc_node_get_mtu(net, dnode, tsk->portid); rc = tipc_msg_build(hdr, m, 0, dlen, mtu, &pkts); if (unlikely(rc != dlen)) return rc; - if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue))) + if (unlikely(syn && !tipc_msg_skb_clone(&pkts, &sk->sk_write_queue))) { + __skb_queue_purge(&pkts); return -ENOMEM; + } trace_tipc_sk_sendmsg(sk, skb_peek(&pkts), TIPC_DUMP_SK_SNDQ, " "); rc = tipc_node_xmit(net, &pkts, dnode, tsk->portid); @@ -2681,6 +2687,7 @@ static void tipc_sk_timeout(struct timer_list *t) if (sock_owned_by_user(sk)) { sk_reset_timer(sk, &sk->sk_timer, jiffies + HZ / 20); bh_unlock_sock(sk); + sock_put(sk); return; } @@ -3790,7 +3797,7 @@ int tipc_sk_dump(struct sock *sk, u16 dqueues, char *buf) i += scnprintf(buf + i, sz - i, " %d", sk->sk_sndbuf); i += scnprintf(buf + i, sz - i, " | %d", sk_rmem_alloc_get(sk)); i += scnprintf(buf + i, sz - i, " %d", sk->sk_rcvbuf); - i += scnprintf(buf + i, sz - i, " | %d\n", sk->sk_backlog.len); + i += scnprintf(buf + i, sz - i, " | %d\n", READ_ONCE(sk->sk_backlog.len)); if (dqueues & TIPC_DUMP_SK_SNDQ) { i += scnprintf(buf + i, sz - i, "sk_write_queue: "); diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index f345662890a6..c58b5782a3a6 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -401,10 +401,11 @@ static int tipc_conn_rcv_from_sock(struct tipc_conn *con) read_lock_bh(&sk->sk_callback_lock); ret = tipc_conn_rcv_sub(srv, con, &s); read_unlock_bh(&sk->sk_callback_lock); + if (!ret) + return 0; } - if (ret < 0) - tipc_conn_close(con); + tipc_conn_close(con); return ret; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index 1405ccc9101c..c879bb1ca01a 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -189,10 +189,12 @@ static int tipc_udp_xmit(struct net *net, struct sk_buff *skb, .saddr = src->ipv6, .flowi6_proto = IPPROTO_UDP }; - err = ipv6_stub->ipv6_dst_lookup(net, ub->ubsock->sk, &ndst, - &fl6); - if (err) + ndst = ipv6_stub->ipv6_dst_lookup_flow(net, ub->ubsock->sk, + &fl6, NULL); + if (IS_ERR(ndst)) { + err = PTR_ERR(ndst); goto tx_error; + } ttl = ip6_dst_hoplimit(ndst); err = udp_tunnel6_xmit_skb(ndst, ub->ubsock->sk, skb, NULL, &src->ipv6, &dst->ipv6, 0, ttl, 0, diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index 4cfcce211c2f..3b0c363e7f83 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -354,7 +354,7 @@ static int tls_push_data(struct sock *sk, if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) - return -ENOTSUPP; + return -EOPNOTSUPP; if (sk->sk_err) return -sk->sk_err; @@ -451,8 +451,10 @@ last_record: int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { unsigned char record_type = TLS_RECORD_TYPE_DATA; + struct tls_context *tls_ctx = tls_get_ctx(sk); int rc; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (unlikely(msg->msg_controllen)) { @@ -466,27 +468,31 @@ int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } int tls_device_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); struct iov_iter msg_iter; - char *kaddr = kmap(page); + char *kaddr; struct kvec iov; int rc; if (flags & MSG_SENDPAGE_NOTLAST) flags |= MSG_MORE; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); if (flags & MSG_OOB) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto out; } + kaddr = kmap(page); iov.iov_base = kaddr + offset; iov.iov_len = size; iov_iter_kvec(&msg_iter, WRITE, &iov, 1, size); @@ -496,6 +502,7 @@ int tls_device_sendpage(struct sock *sk, struct page *page, out: release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return rc; } @@ -503,7 +510,7 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, u32 seq, u64 *p_record_sn) { u64 record_sn = context->hint_record_sn; - struct tls_record_info *info; + struct tls_record_info *info, *last; info = context->retransmit_hint; if (!info || @@ -513,6 +520,24 @@ struct tls_record_info *tls_get_record(struct tls_offload_context_tx *context, */ info = list_first_entry(&context->records_list, struct tls_record_info, list); + /* send the start_marker record if seq number is before the + * tls offload start marker sequence number. This record is + * required to handle TCP packets which are before TLS offload + * started. + * And if it's not start marker, look if this seq number + * belongs to the list. + */ + if (likely(!tls_record_is_start_marker(info))) { + /* we have the first record, get the last record to see + * if this seq number belongs to the list. + */ + last = list_last_entry(&context->records_list, + struct tls_record_info, list); + + if (!between(seq, tls_record_start_seq(info), + last->end_seq)) + return NULL; + } record_sn = context->unacked_record_sn; } @@ -544,9 +569,11 @@ static int tls_device_push_pending_record(struct sock *sk, int flags) void tls_device_write_space(struct sock *sk, struct tls_context *ctx) { - if (!sk->sk_write_pending && tls_is_partially_sent_record(ctx)) { + if (tls_is_partially_sent_record(ctx)) { gfp_t sk_allocation = sk->sk_allocation; + WARN_ON_ONCE(sk->sk_write_pending); + sk->sk_allocation = GFP_ATOMIC; tls_push_partial_record(sk, ctx, MSG_DONTWAIT | MSG_NOSIGNAL | @@ -830,7 +857,7 @@ int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) } if (!(netdev->features & NETIF_F_HW_TLS_TX)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto release_netdev; } @@ -903,7 +930,7 @@ int tls_set_device_offload_rx(struct sock *sk, struct tls_context *ctx) } if (!(netdev->features & NETIF_F_HW_TLS_RX)) { - rc = -ENOTSUPP; + rc = -EOPNOTSUPP; goto release_netdev; } diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 4674e57e66b0..be043c8f5a53 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -208,24 +208,15 @@ int tls_push_partial_record(struct sock *sk, struct tls_context *ctx, return tls_push_sg(sk, ctx, sg, offset, flags); } -bool tls_free_partial_record(struct sock *sk, struct tls_context *ctx) +void tls_free_partial_record(struct sock *sk, struct tls_context *ctx) { struct scatterlist *sg; - sg = ctx->partially_sent_record; - if (!sg) - return false; - - while (1) { + for (sg = ctx->partially_sent_record; sg; sg = sg_next(sg)) { put_page(sg_page(sg)); sk_mem_uncharge(sk, sg->length); - - if (sg_is_last(sg)) - break; - sg++; } ctx->partially_sent_record = NULL; - return true; } static void tls_write_space(struct sock *sk) @@ -258,6 +249,7 @@ void tls_ctx_free(struct tls_context *ctx) memzero_explicit(&ctx->crypto_send, sizeof(ctx->crypto_send)); memzero_explicit(&ctx->crypto_recv, sizeof(ctx->crypto_recv)); + mutex_destroy(&ctx->tx_lock); kfree(ctx); } @@ -476,7 +468,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, /* check version */ if (crypto_info->version != TLS_1_2_VERSION && crypto_info->version != TLS_1_3_VERSION) { - rc = -ENOTSUPP; + rc = -EINVAL; goto err_crypto_info; } @@ -603,6 +595,7 @@ static struct tls_context *create_ctx(struct sock *sk) if (!ctx) return NULL; + mutex_init(&ctx->tx_lock); icsk->icsk_ulp_data = ctx; ctx->setsockopt = sk->sk_prot->setsockopt; ctx->getsockopt = sk->sk_prot->getsockopt; @@ -782,7 +775,7 @@ static int tls_init(struct sock *sk) * share the ulp context. */ if (sk->sk_state != TCP_ESTABLISHED) - return -ENOTSUPP; + return -ENOTCONN; /* allocate tls context */ ctx = create_ctx(sk); @@ -825,6 +818,7 @@ static int __init tls_register(void) { tls_sw_proto_ops = inet_stream_ops; tls_sw_proto_ops.splice_read = tls_sw_splice_read; + tls_sw_proto_ops.sendpage_locked = tls_sw_sendpage_locked, #ifdef CONFIG_TLS_DEVICE tls_device_init(); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index e2385183526e..eff098d15e56 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -203,10 +203,12 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) kfree(aead_req); + spin_lock_bh(&ctx->decrypt_compl_lock); pending = atomic_dec_return(&ctx->decrypt_pending); - if (!pending && READ_ONCE(ctx->async_notify)) + if (!pending && ctx->async_notify) complete(&ctx->async_wait.completion); + spin_unlock_bh(&ctx->decrypt_compl_lock); } static int tls_do_decryption(struct sock *sk, @@ -464,10 +466,12 @@ static void tls_encrypt_done(struct crypto_async_request *req, int err) ready = true; } + spin_lock_bh(&ctx->encrypt_compl_lock); pending = atomic_dec_return(&ctx->encrypt_pending); - if (!pending && READ_ONCE(ctx->async_notify)) + if (!pending && ctx->async_notify) complete(&ctx->async_wait.completion); + spin_unlock_bh(&ctx->encrypt_compl_lock); if (!ready) return; @@ -677,12 +681,32 @@ static int tls_push_record(struct sock *sk, int flags, split_point = msg_pl->apply_bytes; split = split_point && split_point < msg_pl->sg.size; + if (unlikely((!split && + msg_pl->sg.size + + prot->overhead_size > msg_en->sg.size) || + (split && + split_point + + prot->overhead_size > msg_en->sg.size))) { + split = true; + split_point = msg_en->sg.size; + } if (split) { rc = tls_split_open_record(sk, rec, &tmp, msg_pl, msg_en, split_point, prot->overhead_size, &orig_end); if (rc < 0) return rc; + /* This can happen if above tls_split_open_record allocates + * a single large encryption buffer instead of two smaller + * ones. In this case adjust pointers and continue without + * split. + */ + if (!msg_pl->sg.size) { + tls_merge_open_record(sk, rec, tmp, orig_end); + msg_pl = &rec->msg_plaintext; + msg_en = &rec->msg_encrypted; + split = false; + } sk_msg_trim(sk, msg_en, msg_pl->sg.size + prot->overhead_size); } @@ -704,9 +728,14 @@ static int tls_push_record(struct sock *sk, int flags, sg_mark_end(sk_msg_elem(msg_pl, i)); } + if (msg_pl->sg.end < msg_pl->sg.start) { + sg_chain(&msg_pl->sg.data[msg_pl->sg.start], + MAX_SKB_FRAGS - msg_pl->sg.start + 1, + msg_pl->sg.data); + } + i = msg_pl->sg.start; - sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ? - &msg_en->sg.data[i] : &msg_pl->sg.data[i]); + sg_chain(rec->sg_aead_in, 2, &msg_pl->sg.data[i]); i = msg_en->sg.end; sk_msg_iter_var_prev(i); @@ -752,7 +781,7 @@ static int tls_push_record(struct sock *sk, int flags, static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, bool full_record, u8 record_type, - size_t *copied, int flags) + ssize_t *copied, int flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); @@ -766,17 +795,23 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, policy = !(flags & MSG_SENDPAGE_NOPOLICY); psock = sk_psock_get(sk); - if (!psock || !policy) - return tls_push_record(sk, flags, record_type); + if (!psock || !policy) { + err = tls_push_record(sk, flags, record_type); + if (err && sk->sk_err == EBADMSG) { + *copied -= sk_msg_free(sk, msg); + tls_free_open_rec(sk); + err = -sk->sk_err; + } + if (psock) + sk_psock_put(sk, psock); + return err; + } more_data: enospc = sk_msg_full(msg); if (psock->eval == __SK_NONE) { delta = msg->sg.size; psock->eval = sk_psock_msg_verdict(sk, psock, msg); - if (delta < msg->sg.size) - delta -= msg->sg.size; - else - delta = 0; + delta -= msg->sg.size; } if (msg->cork_bytes && msg->cork_bytes > msg->sg.size && !enospc && !full_record) { @@ -791,9 +826,10 @@ more_data: switch (psock->eval) { case __SK_PASS: err = tls_push_record(sk, flags, record_type); - if (err < 0) { + if (err && sk->sk_err == EBADMSG) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); + err = -sk->sk_err; goto out_err; } break; @@ -883,7 +919,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) unsigned char record_type = TLS_RECORD_TYPE_DATA; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); - size_t try_to_copy, copied = 0; + size_t try_to_copy; + ssize_t copied = 0; struct sk_msg *msg_pl, *msg_en; struct tls_rec *rec; int required_size; @@ -893,19 +930,14 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) int num_zc = 0; int orig_size; int ret = 0; + int pending; if (msg->msg_flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL)) - return -ENOTSUPP; + return -EOPNOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto send_end; - } - if (unlikely(msg->msg_controllen)) { ret = tls_proccess_cmsg(sk, msg, &record_type); if (ret) { @@ -971,8 +1003,6 @@ alloc_encrypted: if (ret) goto fallback_to_reg_send; - rec->inplace_crypto = 0; - num_zc++; copied += try_to_copy; @@ -985,7 +1015,7 @@ alloc_encrypted: num_async++; else if (ret == -ENOMEM) goto wait_for_memory; - else if (ret == -ENOSPC) + else if (ctx->open_rec && ret == -ENOSPC) goto rollback_iter; else if (ret != -EAGAIN) goto send_end; @@ -1054,11 +1084,12 @@ wait_for_memory: ret = sk_stream_wait_memory(sk, &timeo); if (ret) { trim_sgl: - tls_trim_both_msgs(sk, orig_size); + if (ctx->open_rec) + tls_trim_both_msgs(sk, orig_size); goto send_end; } - if (msg_en->sg.size < required_size) + if (ctx->open_rec && msg_en->sg.size < required_size) goto alloc_encrypted; } @@ -1066,13 +1097,19 @@ trim_sgl: goto send_end; } else if (num_zc) { /* Wait for pending encryptions to get completed */ - smp_store_mb(ctx->async_notify, true); + spin_lock_bh(&ctx->encrypt_compl_lock); + ctx->async_notify = true; - if (atomic_read(&ctx->encrypt_pending)) + pending = atomic_read(&ctx->encrypt_pending); + spin_unlock_bh(&ctx->encrypt_compl_lock); + if (pending) crypto_wait_req(-EINPROGRESS, &ctx->async_wait); else reinit_completion(&ctx->async_wait.completion); + /* There can be no concurrent accesses, since we have no + * pending encrypt operations + */ WRITE_ONCE(ctx->async_notify, false); if (ctx->async_wait.err) { @@ -1091,7 +1128,8 @@ send_end: ret = sk_stream_error(sk, msg->msg_flags, ret); release_sock(sk); - return copied ? copied : ret; + mutex_unlock(&tls_ctx->tx_lock); + return copied > 0 ? copied : ret; } static int tls_sw_do_sendpage(struct sock *sk, struct page *page, @@ -1105,7 +1143,7 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, struct sk_msg *msg_pl; struct tls_rec *rec; int num_async = 0; - size_t copied = 0; + ssize_t copied = 0; bool full_record; int record_room; int ret = 0; @@ -1114,13 +1152,6 @@ static int tls_sw_do_sendpage(struct sock *sk, struct page *page, eor = !(flags & (MSG_MORE | MSG_SENDPAGE_NOTLAST)); sk_clear_bit(SOCKWQ_ASYNC_NOSPACE, sk); - /* Wait till there is any pending write on socket */ - if (unlikely(sk->sk_write_pending)) { - ret = wait_on_pending_writer(sk, &timeo); - if (unlikely(ret)) - goto sendpage_end; - } - /* Call the sk_stream functions to manage the sndbuf mem. */ while (size > 0) { size_t copy, required_size; @@ -1176,7 +1207,6 @@ alloc_payload: tls_ctx->pending_open_record_frags = true; if (full_record || eor || sk_msg_full(msg_pl)) { - rec->inplace_crypto = 0; ret = bpf_exec_tx_verdict(msg_pl, sk, full_record, record_type, &copied, flags); if (ret) { @@ -1197,11 +1227,13 @@ wait_for_sndbuf: wait_for_memory: ret = sk_stream_wait_memory(sk, &timeo); if (ret) { - tls_trim_both_msgs(sk, msg_pl->sg.size); + if (ctx->open_rec) + tls_trim_both_msgs(sk, msg_pl->sg.size); goto sendpage_end; } - goto alloc_payload; + if (ctx->open_rec) + goto alloc_payload; } if (num_async) { @@ -1213,21 +1245,35 @@ wait_for_memory: } sendpage_end: ret = sk_stream_error(sk, flags, ret); - return copied ? copied : ret; + return copied > 0 ? copied : ret; +} + +int tls_sw_sendpage_locked(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | + MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY | + MSG_NO_SHARED_FRAGS)) + return -EOPNOTSUPP; + + return tls_sw_do_sendpage(sk, page, offset, size, flags); } int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct tls_context *tls_ctx = tls_get_ctx(sk); int ret; if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) - return -ENOTSUPP; + return -EOPNOTSUPP; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); ret = tls_sw_do_sendpage(sk, page, offset, size, flags); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); return ret; } @@ -1691,7 +1737,9 @@ int tls_sw_recvmsg(struct sock *sk, long timeo; 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; @@ -1700,6 +1748,7 @@ int tls_sw_recvmsg(struct sock *sk, psock = sk_psock_get(sk); lock_sock(sk); + bpf_strp_enabled = sk_psock_strp_enabled(psock); /* Process pending decrypted records. It must be non-zero-copy */ err = process_rx_list(ctx, msg, &control, &cmsg, 0, len, false, @@ -1753,11 +1802,12 @@ int tls_sw_recvmsg(struct sock *sk, if (to_decrypt <= len && !is_kvec && !is_peek && ctx->control == TLS_RECORD_TYPE_DATA && - prot->version != TLS_1_3_VERSION) + prot->version != TLS_1_3_VERSION && + !bpf_strp_enabled) zc = true; /* Do not use async mode if record is non-data */ - if (ctx->control == TLS_RECORD_TYPE_DATA) + if (ctx->control == TLS_RECORD_TYPE_DATA && !bpf_strp_enabled) async_capable = ctx->async_capable; else async_capable = false; @@ -1807,6 +1857,19 @@ int tls_sw_recvmsg(struct sock *sk, goto pick_next_record; if (!zc) { + if (bpf_strp_enabled) { + err = sk_psock_tls_strp_read(psock, skb); + if (err != __SK_PASS) { + rxm->offset = rxm->offset + rxm->full_len; + rxm->full_len = 0; + if (err == __SK_DROP) + consume_skb(skb); + ctx->recv_pkt = NULL; + __strp_unpause(&ctx->strp); + continue; + } + } + if (rxm->full_len > len) { retain_skb = true; chunk = len; @@ -1854,8 +1917,11 @@ pick_next_record: recv_end: if (num_async) { /* Wait for all previously submitted records to be decrypted */ - smp_store_mb(ctx->async_notify, true); - if (atomic_read(&ctx->decrypt_pending)) { + spin_lock_bh(&ctx->decrypt_compl_lock); + ctx->async_notify = true; + pending = atomic_read(&ctx->decrypt_pending); + spin_unlock_bh(&ctx->decrypt_compl_lock); + if (pending) { err = crypto_wait_req(-EINPROGRESS, &ctx->async_wait); if (err) { /* one of async decrypt failed */ @@ -1867,6 +1933,10 @@ recv_end: } else { reinit_completion(&ctx->async_wait.completion); } + + /* There can be no concurrent accesses, since we have no + * pending decrypt operations + */ WRITE_ONCE(ctx->async_notify, false); /* Drain records from the rx_list & copy if required */ @@ -1920,7 +1990,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, /* splice does not support reading control messages */ if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -ENOTSUPP; + err = -EINVAL; goto splice_read_end; } @@ -2047,8 +2117,9 @@ static void tls_data_ready(struct sock *sk) strp_data_ready(&ctx->strp); psock = sk_psock_get(sk); - if (psock && !list_empty(&psock->ingress_msg)) { - ctx->saved_data_ready(sk); + if (psock) { + if (!list_empty(&psock->ingress_msg)) + ctx->saved_data_ready(sk); sk_psock_put(sk, psock); } } @@ -2074,7 +2145,8 @@ void tls_sw_free_resources_tx(struct sock *sk) /* Free up un-sent records in tx_list. First, free * the partially sent record if any at head of tx_list. */ - if (tls_free_partial_record(sk, tls_ctx)) { + if (tls_ctx->partially_sent_record) { + tls_free_partial_record(sk, tls_ctx); rec = list_first_entry(&ctx->tx_list, struct tls_rec, list); list_del(&rec->list); @@ -2141,9 +2213,11 @@ static void tx_work_handler(struct work_struct *work) if (!test_and_clear_bit(BIT_TX_SCHEDULED, &ctx->tx_bitmask)) return; + mutex_lock(&tls_ctx->tx_lock); lock_sock(sk); tls_tx_records(sk, -1); release_sock(sk); + mutex_unlock(&tls_ctx->tx_lock); } void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) @@ -2151,12 +2225,9 @@ void tls_sw_write_space(struct sock *sk, struct tls_context *ctx) struct tls_sw_context_tx *tx_ctx = tls_sw_ctx_tx(ctx); /* Schedule the transmission if tx list is ready */ - if (is_tx_ready(tx_ctx) && !sk->sk_write_pending) { - /* Schedule the transmission */ - if (!test_and_set_bit(BIT_TX_SCHEDULED, - &tx_ctx->tx_bitmask)) - schedule_delayed_work(&tx_ctx->tx_work.work, 0); - } + if (is_tx_ready(tx_ctx) && + !test_and_set_bit(BIT_TX_SCHEDULED, &tx_ctx->tx_bitmask)) + schedule_delayed_work(&tx_ctx->tx_work.work, 0); } int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) @@ -2211,6 +2282,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (tx) { crypto_init_wait(&sw_ctx_tx->async_wait); + spin_lock_init(&sw_ctx_tx->encrypt_compl_lock); crypto_info = &ctx->crypto_send.info; cctx = &ctx->tx; aead = &sw_ctx_tx->aead_send; @@ -2219,6 +2291,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) sw_ctx_tx->tx_work.sk = sk; } else { crypto_init_wait(&sw_ctx_rx->async_wait); + spin_lock_init(&sw_ctx_rx->decrypt_compl_lock); crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; skb_queue_head_init(&sw_ctx_rx->rx_list); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 67e87db5877f..b3369d678f1a 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -646,6 +646,9 @@ static __poll_t unix_poll(struct file *, struct socket *, poll_table *); static __poll_t unix_dgram_poll(struct file *, struct socket *, poll_table *); static int unix_ioctl(struct socket *, unsigned int, unsigned long); +#ifdef CONFIG_COMPAT +static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg); +#endif static int unix_shutdown(struct socket *, int); static int unix_stream_sendmsg(struct socket *, struct msghdr *, size_t); static int unix_stream_recvmsg(struct socket *, struct msghdr *, size_t, int); @@ -687,6 +690,9 @@ static const struct proto_ops unix_stream_ops = { .getname = unix_getname, .poll = unix_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = unix_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@ -710,6 +716,9 @@ static const struct proto_ops unix_dgram_ops = { .getname = unix_getname, .poll = unix_dgram_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = sock_no_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@ -732,6 +741,9 @@ static const struct proto_ops unix_seqpacket_ops = { .getname = unix_getname, .poll = unix_dgram_poll, .ioctl = unix_ioctl, +#ifdef CONFIG_COMPAT + .compat_ioctl = unix_compat_ioctl, +#endif .listen = unix_listen, .shutdown = unix_shutdown, .setsockopt = sock_no_setsockopt, @@ -2582,6 +2594,13 @@ static int unix_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return err; } +#ifdef CONFIG_COMPAT +static int unix_compat_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) +{ + return unix_ioctl(sock, cmd, (unsigned long)compat_ptr(arg)); +} +#endif + static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wait) { struct sock *sk = sock->sk; @@ -2599,7 +2618,7 @@ static __poll_t unix_poll(struct file *file, struct socket *sock, poll_table *wa mask |= EPOLLRDHUP | EPOLLIN | EPOLLRDNORM; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ @@ -2628,7 +2647,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask = 0; /* exceptional events? */ - if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue)) + if (sk->sk_err || !skb_queue_empty_lockless(&sk->sk_error_queue)) mask |= EPOLLERR | (sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? EPOLLPRI : 0); @@ -2638,7 +2657,7 @@ static __poll_t unix_dgram_poll(struct file *file, struct socket *sock, mask |= EPOLLHUP; /* readable? */ - if (!skb_queue_empty(&sk->sk_receive_queue)) + if (!skb_queue_empty_lockless(&sk->sk_receive_queue)) mask |= EPOLLIN | EPOLLRDNORM; /* Connection-based need to check for termination and startup */ diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 2ab43b2bba31..7bd6c8199ca6 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -870,7 +870,7 @@ static __poll_t vsock_poll(struct file *file, struct socket *sock, * the queue and write as long as the socket isn't shutdown for * sending. */ - if (!skb_queue_empty(&sk->sk_receive_queue) || + if (!skb_queue_empty_lockless(&sk->sk_receive_queue) || (sk->sk_shutdown & RCV_SHUTDOWN)) { mask |= EPOLLIN | EPOLLRDNORM; } @@ -1275,7 +1275,7 @@ static int vsock_accept(struct socket *sock, struct socket *newsock, int flags, /* Wait for children sockets to appear; these are the new sockets * created upon connection establishment. */ - timeout = sock_sndtimeo(listener, flags & O_NONBLOCK); + timeout = sock_rcvtimeo(listener, flags & O_NONBLOCK); prepare_to_wait(sk_sleep(listener), &wait, TASK_INTERRUPTIBLE); while ((connected = vsock_dequeue_accept(listener)) == NULL && diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index 920f14705346..420e1cfa028f 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -135,28 +135,15 @@ struct hvsock { **************************************************************************** * The only valid Service GUIDs, from the perspectives of both the host and * * Linux VM, that can be connected by the other end, must conform to this * - * format: <port>-facb-11e6-bd58-64006a7986d3, and the "port" must be in * - * this range [0, 0x7FFFFFFF]. * + * format: <port>-facb-11e6-bd58-64006a7986d3. * **************************************************************************** * * When we write apps on the host to connect(), the GUID ServiceID is used. * When we write apps in Linux VM to connect(), we only need to specify the * port and the driver will form the GUID and use that to request the host. * - * From the perspective of Linux VM: - * 1. the local ephemeral port (i.e. the local auto-bound port when we call - * connect() without explicit bind()) is generated by __vsock_bind_stream(), - * and the range is [1024, 0xFFFFFFFF). - * 2. the remote ephemeral port (i.e. the auto-generated remote port for - * a connect request initiated by the host's connect()) is generated by - * hvs_remote_addr_init() and the range is [0x80000000, 0xFFFFFFFF). */ -#define MAX_LISTEN_PORT ((u32)0x7FFFFFFF) -#define MAX_VM_LISTEN_PORT MAX_LISTEN_PORT -#define MAX_HOST_LISTEN_PORT MAX_LISTEN_PORT -#define MIN_HOST_EPHEMERAL_PORT (MAX_HOST_LISTEN_PORT + 1) - /* 00000000-facb-11e6-bd58-64006a7986d3 */ static const uuid_le srv_id_template = UUID_LE(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58, @@ -179,33 +166,6 @@ static void hvs_addr_init(struct sockaddr_vm *addr, const uuid_le *svr_id) vsock_addr_init(addr, VMADDR_CID_ANY, port); } -static void hvs_remote_addr_init(struct sockaddr_vm *remote, - struct sockaddr_vm *local) -{ - static u32 host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT; - struct sock *sk; - - vsock_addr_init(remote, VMADDR_CID_ANY, VMADDR_PORT_ANY); - - while (1) { - /* Wrap around ? */ - if (host_ephemeral_port < MIN_HOST_EPHEMERAL_PORT || - host_ephemeral_port == VMADDR_PORT_ANY) - host_ephemeral_port = MIN_HOST_EPHEMERAL_PORT; - - remote->svm_port = host_ephemeral_port++; - - sk = vsock_find_connected_socket(remote, local); - if (!sk) { - /* Found an available ephemeral port */ - return; - } - - /* Release refcnt got in vsock_find_connected_socket */ - sock_put(sk); - } -} - static void hvs_set_channel_pending_send_size(struct vmbus_channel *chan) { set_channel_pending_send_size(chan, @@ -332,12 +292,7 @@ static void hvs_open_connection(struct vmbus_channel *chan) if_type = &chan->offermsg.offer.if_type; if_instance = &chan->offermsg.offer.if_instance; conn_from_host = chan->offermsg.offer.u.pipe.user_def[0]; - - /* The host or the VM should only listen on a port in - * [0, MAX_LISTEN_PORT] - */ - if (!is_valid_srv_id(if_type) || - get_port_by_srv_id(if_type) > MAX_LISTEN_PORT) + if (!is_valid_srv_id(if_type)) return; hvs_addr_init(&addr, conn_from_host ? if_type : if_instance); @@ -400,8 +355,11 @@ static void hvs_open_connection(struct vmbus_channel *chan) sk->sk_ack_backlog++; hvs_addr_init(&vnew->local_addr, if_type); - hvs_remote_addr_init(&vnew->remote_addr, &vnew->local_addr); + /* Remote peer is always the host */ + vsock_addr_init(&vnew->remote_addr, + VMADDR_CID_HOST, VMADDR_PORT_ANY); + vnew->remote_addr.svm_port = get_port_by_srv_id(if_instance); hvs_new->vm_srv_id = *if_type; hvs_new->host_srv_id = *if_instance; @@ -706,16 +664,6 @@ static bool hvs_stream_is_active(struct vsock_sock *vsk) static bool hvs_stream_allow(u32 cid, u32 port) { - /* The host's port range [MIN_HOST_EPHEMERAL_PORT, 0xFFFFFFFF) is - * reserved as ephemeral ports, which are used as the host's ports - * when the host initiates connections. - * - * Perform this check in the guest so an immediate error is produced - * instead of a timeout. - */ - if (port > MAX_HOST_LISTEN_PORT) - return false; - if (cid == VMADDR_CID_HOST) return true; diff --git a/net/vmw_vsock/virtio_transport_common.c b/net/vmw_vsock/virtio_transport_common.c index a7adffd062c7..279d838784e5 100644 --- a/net/vmw_vsock/virtio_transport_common.c +++ b/net/vmw_vsock/virtio_transport_common.c @@ -91,8 +91,17 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) struct virtio_vsock_pkt *pkt = opaque; struct af_vsockmon_hdr *hdr; struct sk_buff *skb; + size_t payload_len; + void *payload_buf; - skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + pkt->len, + /* A packet could be split to fit the RX buffer, so we can retrieve + * the payload length from the header and the buffer pointer taking + * care of the offset in the original packet. + */ + payload_len = le32_to_cpu(pkt->hdr.len); + payload_buf = pkt->buf + pkt->off; + + skb = alloc_skb(sizeof(*hdr) + sizeof(pkt->hdr) + payload_len, GFP_ATOMIC); if (!skb) return NULL; @@ -132,8 +141,8 @@ static struct sk_buff *virtio_transport_build_skb(void *opaque) skb_put_data(skb, &pkt->hdr, sizeof(pkt->hdr)); - if (pkt->len) { - skb_put_data(skb, pkt->buf, pkt->len); + if (payload_len) { + skb_put_data(skb, payload_buf, payload_len); } return skb; @@ -870,9 +879,11 @@ virtio_transport_recv_connected(struct sock *sk, if (le32_to_cpu(pkt->hdr.flags) & VIRTIO_VSOCK_SHUTDOWN_SEND) vsk->peer_shutdown |= SEND_SHUTDOWN; if (vsk->peer_shutdown == SHUTDOWN_MASK && - vsock_stream_has_data(vsk) <= 0) { - sock_set_flag(sk, SOCK_DONE); - sk->sk_state = TCP_CLOSING; + vsock_stream_has_data(vsk) <= 0 && + !sock_flag(sk, SOCK_DONE)) { + (void)virtio_transport_reset(vsk, NULL); + + virtio_transport_do_close(vsk, true); } if (le32_to_cpu(pkt->hdr.flags)) sk->sk_state_change(sk); diff --git a/net/wireless/core.c b/net/wireless/core.c index ed24a0b071c3..fa6353b9ca1e 100644 --- a/net/wireless/core.c +++ b/net/wireless/core.c @@ -1093,6 +1093,7 @@ static void __cfg80211_unregister_wdev(struct wireless_dev *wdev, bool sync) #ifdef CONFIG_CFG80211_WEXT kzfree(wdev->wext.keys); + wdev->wext.keys = NULL; #endif /* only initialized if we have a netdev */ if (wdev->netdev) diff --git a/net/wireless/ethtool.c b/net/wireless/ethtool.c index a9c0f368db5d..24e18405cdb4 100644 --- a/net/wireless/ethtool.c +++ b/net/wireless/ethtool.c @@ -7,9 +7,13 @@ void cfg80211_get_drvinfo(struct net_device *dev, struct ethtool_drvinfo *info) { struct wireless_dev *wdev = dev->ieee80211_ptr; + struct device *pdev = wiphy_dev(wdev->wiphy); - strlcpy(info->driver, wiphy_dev(wdev->wiphy)->driver->name, - sizeof(info->driver)); + if (pdev->driver) + strlcpy(info->driver, pdev->driver->name, + sizeof(info->driver)); + else + strlcpy(info->driver, "N/A", sizeof(info->driver)); strlcpy(info->version, init_utsname()->release, sizeof(info->version)); diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index 07c9707cdb85..f4f2d3e23a54 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -377,7 +377,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MNTR_FLAGS] = { /* NLA_NESTED can't be empty */ }, [NL80211_ATTR_MESH_ID] = { .type = NLA_BINARY, .len = IEEE80211_MAX_MESH_ID_LEN }, - [NL80211_ATTR_MPATH_NEXT_HOP] = { .type = NLA_U32 }, + [NL80211_ATTR_MPATH_NEXT_HOP] = NLA_POLICY_ETH_ADDR_COMPAT, [NL80211_ATTR_REG_ALPHA2] = { .type = NLA_STRING, .len = 2 }, [NL80211_ATTR_REG_RULES] = { .type = NLA_NESTED }, @@ -421,6 +421,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_CONTROL_PORT_NO_ENCRYPT] = { .type = NLA_FLAG }, [NL80211_ATTR_CONTROL_PORT_OVER_NL80211] = { .type = NLA_FLAG }, [NL80211_ATTR_PRIVACY] = { .type = NLA_FLAG }, + [NL80211_ATTR_STATUS_CODE] = { .type = NLA_U16 }, [NL80211_ATTR_CIPHER_SUITE_GROUP] = { .type = NLA_U32 }, [NL80211_ATTR_WPA_VERSIONS] = { .type = NLA_U32 }, [NL80211_ATTR_PID] = { .type = NLA_U32 }, @@ -452,6 +453,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_WOWLAN_TRIGGERS] = { .type = NLA_NESTED }, [NL80211_ATTR_STA_PLINK_STATE] = NLA_POLICY_MAX(NLA_U8, NUM_NL80211_PLINK_STATES - 1), + [NL80211_ATTR_MEASUREMENT_DURATION] = { .type = NLA_U16 }, + [NL80211_ATTR_MEASUREMENT_DURATION_MANDATORY] = { .type = NLA_FLAG }, [NL80211_ATTR_MESH_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_SCHED_SCAN_INTERVAL] = { .type = NLA_U32 }, @@ -513,6 +516,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_MDID] = { .type = NLA_U16 }, [NL80211_ATTR_IE_RIC] = { .type = NLA_BINARY, .len = IEEE80211_MAX_DATA_LEN }, + [NL80211_ATTR_CRIT_PROT_ID] = { .type = NLA_U16 }, + [NL80211_ATTR_MAX_CRIT_PROT_DURATION] = { .type = NLA_U16 }, [NL80211_ATTR_PEER_AID] = NLA_POLICY_RANGE(NLA_U16, 1, IEEE80211_MAX_AID), [NL80211_ATTR_CH_SWITCH_COUNT] = { .type = NLA_U32 }, @@ -543,6 +548,7 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { NLA_POLICY_MAX(NLA_U8, IEEE80211_NUM_UPS - 1), [NL80211_ATTR_ADMITTED_TIME] = { .type = NLA_U16 }, [NL80211_ATTR_SMPS_MODE] = { .type = NLA_U8 }, + [NL80211_ATTR_OPER_CLASS] = { .type = NLA_U8 }, [NL80211_ATTR_MAC_MASK] = { .type = NLA_EXACT_LEN_WARN, .len = ETH_ALEN @@ -596,10 +602,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { [NL80211_ATTR_HE_CAPABILITY] = { .type = NLA_BINARY, .len = NL80211_HE_MAX_CAPABILITY_LEN }, - [NL80211_ATTR_FTM_RESPONDER] = { - .type = NLA_NESTED, - .validation_data = nl80211_ftm_responder_policy, - }, + [NL80211_ATTR_FTM_RESPONDER] = + NLA_POLICY_NESTED(nl80211_ftm_responder_policy), [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), @@ -10669,6 +10673,7 @@ static int cfg80211_cqm_rssi_update(struct cfg80211_registered_device *rdev, if (err) return err; + cfg80211_sinfo_release_content(&sinfo); if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_BEACON_SIGNAL_AVG)) wdev->cqm_config->last_rssi_event_value = (s8) sinfo.rx_beacon_signal_avg; @@ -12755,13 +12760,13 @@ static int nl80211_vendor_cmd(struct sk_buff *skb, struct genl_info *info) if (!wdev_running(wdev)) return -ENETDOWN; } - - if (!vcmd->doit) - return -EOPNOTSUPP; } else { wdev = NULL; } + if (!vcmd->doit) + return -EOPNOTSUPP; + if (info->attrs[NL80211_ATTR_VENDOR_DATA]) { data = nla_data(info->attrs[NL80211_ATTR_VENDOR_DATA]); len = nla_len(info->attrs[NL80211_ATTR_VENDOR_DATA]); @@ -13572,6 +13577,8 @@ static int nl80211_probe_mesh_link(struct sk_buff *skb, struct genl_info *info) if (err) return err; + cfg80211_sinfo_release_content(&sinfo); + return rdev_probe_mesh_link(rdev, dev, dest, buf, len); } @@ -16167,7 +16174,7 @@ void cfg80211_sta_opmode_change_notify(struct net_device *dev, const u8 *mac, goto nla_put_failure; if ((sta_opmode->changed & STA_OPMODE_MAX_BW_CHANGED) && - nla_put_u8(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw)) + nla_put_u32(msg, NL80211_ATTR_CHANNEL_WIDTH, sta_opmode->bw)) goto nla_put_failure; if ((sta_opmode->changed & STA_OPMODE_N_SS_CHANGED) && diff --git a/net/wireless/rdev-ops.h b/net/wireless/rdev-ops.h index e853a4fe6f97..e0d34f796d0b 100644 --- a/net/wireless/rdev-ops.h +++ b/net/wireless/rdev-ops.h @@ -538,6 +538,10 @@ static inline int rdev_set_wiphy_params(struct cfg80211_registered_device *rdev, u32 changed) { int ret; + + if (!rdev->ops->set_wiphy_params) + return -EOPNOTSUPP; + trace_rdev_set_wiphy_params(&rdev->wiphy, changed); ret = rdev->ops->set_wiphy_params(&rdev->wiphy, changed); trace_rdev_return_int(&rdev->wiphy, ret); @@ -1167,6 +1171,16 @@ rdev_start_radar_detection(struct cfg80211_registered_device *rdev, return ret; } +static inline void +rdev_end_cac(struct cfg80211_registered_device *rdev, + struct net_device *dev) +{ + trace_rdev_end_cac(&rdev->wiphy, dev); + if (rdev->ops->end_cac) + rdev->ops->end_cac(&rdev->wiphy, dev); + trace_rdev_return_void(&rdev->wiphy); +} + static inline int rdev_set_mcast_rate(struct cfg80211_registered_device *rdev, struct net_device *dev, diff --git a/net/wireless/reg.c b/net/wireless/reg.c index 36eba5804efe..017340a4b818 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2261,21 +2261,22 @@ static void update_all_wiphy_regulatory(enum nl80211_reg_initiator initiator) static void handle_channel_custom(struct wiphy *wiphy, struct ieee80211_channel *chan, - const struct ieee80211_regdomain *regd) + const struct ieee80211_regdomain *regd, + u32 min_bw) { u32 bw_flags = 0; const struct ieee80211_reg_rule *reg_rule = NULL; const struct ieee80211_power_rule *power_rule = NULL; u32 bw; - for (bw = MHZ_TO_KHZ(20); bw >= MHZ_TO_KHZ(5); bw = bw / 2) { + for (bw = MHZ_TO_KHZ(20); bw >= min_bw; bw = bw / 2) { reg_rule = freq_reg_info_regd(MHZ_TO_KHZ(chan->center_freq), regd, bw); if (!IS_ERR(reg_rule)) break; } - if (IS_ERR(reg_rule)) { + if (IS_ERR_OR_NULL(reg_rule)) { pr_debug("Disabling freq %d MHz as custom regd has no rule that fits it\n", chan->center_freq); if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED) { @@ -2324,8 +2325,14 @@ static void handle_band_custom(struct wiphy *wiphy, if (!sband) return; + /* + * We currently assume that you always want at least 20 MHz, + * otherwise channel 12 might get enabled if this rule is + * compatible to US, which permits 2402 - 2472 MHz. + */ for (i = 0; i < sband->n_channels; i++) - handle_channel_custom(wiphy, &sband->channels[i], regd); + handle_channel_custom(wiphy, &sband->channels[i], regd, + MHZ_TO_KHZ(20)); } /* Used by drivers prior to wiphy registration */ @@ -3867,6 +3874,25 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy) return pre_cac_allowed; } +static void cfg80211_check_and_end_cac(struct cfg80211_registered_device *rdev) +{ + struct wireless_dev *wdev; + /* If we finished CAC or received radar, we should end any + * CAC running on the same channels. + * the check !cfg80211_chandef_dfs_usable contain 2 options: + * either all channels are available - those the CAC_FINISHED + * event has effected another wdev state, or there is a channel + * in unavailable state in wdev chandef - those the RADAR_DETECTED + * event has effected another wdev state. + * In both cases we should end the CAC on the wdev. + */ + list_for_each_entry(wdev, &rdev->wiphy.wdev_list, list) { + if (wdev->cac_started && + !cfg80211_chandef_dfs_usable(&rdev->wiphy, &wdev->chandef)) + rdev_end_cac(rdev, wdev->netdev); + } +} + void regulatory_propagate_dfs_state(struct wiphy *wiphy, struct cfg80211_chan_def *chandef, enum nl80211_dfs_state dfs_state, @@ -3893,8 +3919,10 @@ void regulatory_propagate_dfs_state(struct wiphy *wiphy, cfg80211_set_dfs_state(&rdev->wiphy, chandef, dfs_state); if (event == NL80211_RADAR_DETECTED || - event == NL80211_RADAR_CAC_FINISHED) + event == NL80211_RADAR_CAC_FINISHED) { cfg80211_sched_dfs_chan_update(rdev); + cfg80211_check_and_end_cac(rdev); + } nl80211_radar_notify(rdev, chandef, event, NULL, GFP_KERNEL); } diff --git a/net/wireless/sme.c b/net/wireless/sme.c index 7d34cb884840..9d96da127e09 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1283,14 +1283,14 @@ void cfg80211_autodisconnect_wk(struct work_struct *work) if (wdev->conn_owner_nlportid) { switch (wdev->iftype) { case NL80211_IFTYPE_ADHOC: - cfg80211_leave_ibss(rdev, wdev->netdev, false); + __cfg80211_leave_ibss(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_AP: case NL80211_IFTYPE_P2P_GO: - cfg80211_stop_ap(rdev, wdev->netdev, false); + __cfg80211_stop_ap(rdev, wdev->netdev, false); break; case NL80211_IFTYPE_MESH_POINT: - cfg80211_leave_mesh(rdev, wdev->netdev); + __cfg80211_leave_mesh(rdev, wdev->netdev); break; case NL80211_IFTYPE_STATION: case NL80211_IFTYPE_P2P_CLIENT: diff --git a/net/wireless/trace.h b/net/wireless/trace.h index 2abfff925aac..08b0ee8bb590 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -646,6 +646,11 @@ DEFINE_EVENT(wiphy_netdev_evt, rdev_flush_pmksa, TP_ARGS(wiphy, netdev) ); +DEFINE_EVENT(wiphy_netdev_evt, rdev_end_cac, + TP_PROTO(struct wiphy *wiphy, struct net_device *netdev), + TP_ARGS(wiphy, netdev) +); + DECLARE_EVENT_CLASS(station_add_change, TP_PROTO(struct wiphy *wiphy, struct net_device *netdev, u8 *mac, struct station_parameters *params), diff --git a/net/wireless/util.c b/net/wireless/util.c index f68818dbac1a..95fc3bbaa07c 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -555,7 +555,7 @@ __frame_add_frag(struct sk_buff *skb, struct page *page, struct skb_shared_info *sh = skb_shinfo(skb); int page_offset; - page_ref_inc(page); + get_page(page); page_offset = ptr - page_address(page); skb_add_rx_frag(skb, sh->nr_frags, page, page_offset, len, size); } diff --git a/net/wireless/wext-core.c b/net/wireless/wext-core.c index 5e677dac2a0c..69102fda9ebd 100644 --- a/net/wireless/wext-core.c +++ b/net/wireless/wext-core.c @@ -657,7 +657,8 @@ struct iw_statistics *get_wireless_stats(struct net_device *dev) return NULL; } -static int iw_handler_get_iwstats(struct net_device * dev, +/* noinline to avoid a bogus warning with -O3 */ +static noinline int iw_handler_get_iwstats(struct net_device * dev, struct iw_request_info * info, union iwreq_data * wrqu, char * extra) diff --git a/net/x25/af_x25.c b/net/x25/af_x25.c index 6aee9f5e8e71..256f3e97d1f3 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -760,6 +760,10 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, if (sk->sk_state == TCP_ESTABLISHED) goto out; + rc = -EALREADY; /* Do nothing if call is already in progress */ + if (sk->sk_state == TCP_SYN_SENT) + goto out; + sk->sk_state = TCP_CLOSE; sock->state = SS_UNCONNECTED; @@ -806,7 +810,7 @@ static int x25_connect(struct socket *sock, struct sockaddr *uaddr, /* Now the loop */ rc = -EINPROGRESS; if (sk->sk_state != TCP_ESTABLISHED && (flags & O_NONBLOCK)) - goto out_put_neigh; + goto out; rc = x25_wait_for_connection_establishment(sk); if (rc) diff --git a/net/x25/x25_dev.c b/net/x25/x25_dev.c index 5c111bc3c8ea..48b0f02592fe 100644 --- a/net/x25/x25_dev.c +++ b/net/x25/x25_dev.c @@ -115,8 +115,10 @@ int x25_lapb_receive_frame(struct sk_buff *skb, struct net_device *dev, goto drop; } - if (!pskb_may_pull(skb, 1)) + if (!pskb_may_pull(skb, 1)) { + x25_neigh_put(nb); return 0; + } switch (skb->data[0]) { diff --git a/net/x25/x25_subr.c b/net/x25/x25_subr.c index 8aa415a38814..0285aaa1e93c 100644 --- a/net/x25/x25_subr.c +++ b/net/x25/x25_subr.c @@ -357,6 +357,12 @@ void x25_disconnect(struct sock *sk, int reason, unsigned char cause, sk->sk_state_change(sk); sock_set_flag(sk, SOCK_DEAD); } + if (x25->neighbour) { + read_lock_bh(&x25_list_lock); + x25_neigh_put(x25->neighbour); + x25->neighbour = NULL; + read_unlock_bh(&x25_list_lock); + } } /* diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index 9bd7b96027c1..7459fc756da8 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -26,6 +26,9 @@ void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; + if (!xs->tx) + return; + spin_lock_irqsave(&umem->xsk_list_lock, flags); list_add_rcu(&xs->list, &umem->xsk_list); spin_unlock_irqrestore(&umem->xsk_list_lock, flags); @@ -35,6 +38,9 @@ void xdp_del_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; + if (!xs->tx) + return; + spin_lock_irqsave(&umem->xsk_list_lock, flags); list_del_rcu(&xs->list); spin_unlock_irqrestore(&umem->xsk_list_lock, flags); @@ -303,9 +309,9 @@ static int xdp_umem_account_pages(struct xdp_umem *umem) static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) { u32 chunk_size = mr->chunk_size, headroom = mr->headroom; + u64 npgs, addr = mr->addr, size = mr->len; unsigned int chunks, chunks_per_page; - u64 addr = mr->addr, size = mr->len; - int size_chk, err, i; + int err, i; if (chunk_size < XDP_UMEM_MIN_CHUNK_SIZE || chunk_size > PAGE_SIZE) { /* Strictly speaking we could support this, if: @@ -330,6 +336,10 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) if ((addr + size) < addr) return -EINVAL; + npgs = div_u64(size, PAGE_SIZE); + if (npgs > U32_MAX) + return -EINVAL; + chunks = (unsigned int)div_u64(size, chunk_size); if (chunks == 0) return -EINVAL; @@ -340,8 +350,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) headroom = ALIGN(headroom, 64); - size_chk = chunk_size - headroom - XDP_PACKET_HEADROOM; - if (size_chk < 0) + if (headroom >= chunk_size - XDP_PACKET_HEADROOM) return -EINVAL; umem->address = (unsigned long)addr; @@ -349,7 +358,7 @@ static int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) umem->size = size; umem->headroom = headroom; umem->chunk_size_nohr = chunk_size - headroom; - umem->npgs = size / PAGE_SIZE; + umem->npgs = (u32)npgs; umem->pgs = NULL; umem->user = NULL; INIT_LIST_HEAD(&umem->xsk_list); diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5e0637db92ea..ce6ff65b5095 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -256,10 +256,8 @@ static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, len = desc.len; skb = sock_alloc_send_skb(sk, len, 1, &err); - if (unlikely(!skb)) { - err = -EAGAIN; + if (unlikely(!skb)) goto out; - } skb_put(skb, len); addr = desc.addr; diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index ff654306d836..9d76ba7e1cc7 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -25,12 +25,10 @@ static void __xfrm_transport_prep(struct xfrm_state *x, struct sk_buff *skb, struct xfrm_offload *xo = xfrm_offload(skb); skb_reset_mac_len(skb); - pskb_pull(skb, skb->mac_len + hsize + x->props.header_len); - - if (xo->flags & XFRM_GSO_SEGMENT) { - skb_reset_transport_header(skb); + if (xo->flags & XFRM_GSO_SEGMENT) skb->transport_header -= x->props.header_len; - } + + pskb_pull(skb, skb_transport_offset(skb) + x->props.header_len); } static void __xfrm_mode_tunnel_prep(struct xfrm_state *x, struct sk_buff *skb, @@ -84,7 +82,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur struct xfrm_offload *xo = xfrm_offload(skb); struct sec_path *sp; - if (!xo) + if (!xo || (xo->flags & XFRM_XMIT)) return skb; if (!(features & NETIF_F_HW_ESP)) @@ -105,6 +103,8 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } + xo->flags |= XFRM_XMIT; + if (skb_is_gso(skb)) { struct net_device *dev = skb->dev; @@ -391,6 +391,7 @@ static int xfrm_dev_event(struct notifier_block *this, unsigned long event, void return xfrm_dev_feat_change(dev); case NETDEV_DOWN: + case NETDEV_UNREGISTER: return xfrm_dev_down(dev); } return NOTIFY_DONE; diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 314973aaa414..805b336369fa 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -479,6 +479,9 @@ int xfrm_input(struct sk_buff *skb, int nexthdr, __be32 spi, int encap_type) else XFRM_INC_STATS(net, LINUX_MIB_XFRMINSTATEINVALID); + + if (encap_type == -1) + dev_put(skb->dev); goto drop; } @@ -639,7 +642,7 @@ resume: dev_put(skb->dev); spin_lock(&x->lock); - if (nexthdr <= 0) { + if (nexthdr < 0) { if (nexthdr == -EBADMSG) { xfrm_audit_state_icvfail(x, skb, x->type->proto); diff --git a/net/xfrm/xfrm_interface.c b/net/xfrm/xfrm_interface.c index ad3a2555c517..71508b35725d 100644 --- a/net/xfrm/xfrm_interface.c +++ b/net/xfrm/xfrm_interface.c @@ -324,9 +324,6 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) int err = -1; int mtu; - if (!dst) - goto tx_err_link_failure; - dst_hold(dst); dst = xfrm_lookup_with_ifid(xi->net, dst, fl, NULL, 0, xi->p.if_id); if (IS_ERR(dst)) { @@ -353,7 +350,7 @@ xfrmi_xmit2(struct sk_buff *skb, struct net_device *dev, struct flowi *fl) mtu = dst_mtu(dst); if (!skb->ignore_df && skb->len > mtu) { - skb_dst_update_pmtu(skb, mtu); + skb_dst_update_pmtu_no_confirm(skb, mtu); if (skb->protocol == htons(ETH_P_IPV6)) { if (mtu < IPV6_MIN_MTU) @@ -399,6 +396,7 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) { struct xfrm_if *xi = netdev_priv(dev); struct net_device_stats *stats = &xi->dev->stats; + struct dst_entry *dst = skb_dst(skb); struct flowi fl; int ret; @@ -408,10 +406,33 @@ static netdev_tx_t xfrmi_xmit(struct sk_buff *skb, struct net_device *dev) case htons(ETH_P_IPV6): xfrm_decode_session(skb, &fl, AF_INET6); memset(IP6CB(skb), 0, sizeof(*IP6CB(skb))); + if (!dst) { + fl.u.ip6.flowi6_oif = dev->ifindex; + fl.u.ip6.flowi6_flags |= FLOWI_FLAG_ANYSRC; + dst = ip6_route_output(dev_net(dev), NULL, &fl.u.ip6); + if (dst->error) { + dst_release(dst); + stats->tx_carrier_errors++; + goto tx_err; + } + skb_dst_set(skb, dst); + } break; case htons(ETH_P_IP): xfrm_decode_session(skb, &fl, AF_INET); memset(IPCB(skb), 0, sizeof(*IPCB(skb))); + if (!dst) { + struct rtable *rt; + + fl.u.ip4.flowi4_oif = dev->ifindex; + fl.u.ip4.flowi4_flags |= FLOWI_FLAG_ANYSRC; + rt = __ip_route_output_key(dev_net(dev), &fl.u.ip4); + if (IS_ERR(rt)) { + stats->tx_carrier_errors++; + goto tx_err; + } + skb_dst_set(skb, &rt->dst); + } break; default: goto tx_err; @@ -619,12 +640,9 @@ static void xfrmi_dev_setup(struct net_device *dev) { dev->netdev_ops = &xfrmi_netdev_ops; dev->type = ARPHRD_NONE; - dev->hard_header_len = ETH_HLEN; - dev->min_header_len = ETH_HLEN; dev->mtu = ETH_DATA_LEN; dev->min_mtu = ETH_MIN_MTU; - dev->max_mtu = ETH_DATA_LEN; - dev->addr_len = ETH_ALEN; + dev->max_mtu = IP_MAX_MTU; dev->flags = IFF_NOARP; dev->needs_free_netdev = true; dev->priv_destructor = xfrmi_dev_free; @@ -807,9 +825,30 @@ static void __net_exit xfrmi_exit_net(struct net *net) rtnl_unlock(); } +static void __net_exit xfrmi_exit_batch_net(struct list_head *net_exit_list) +{ + struct net *net; + LIST_HEAD(list); + + rtnl_lock(); + list_for_each_entry(net, net_exit_list, exit_list) { + struct xfrmi_net *xfrmn = net_generic(net, xfrmi_net_id); + struct xfrm_if __rcu **xip; + struct xfrm_if *xi; + + for (xip = &xfrmn->xfrmi[0]; + (xi = rtnl_dereference(*xip)) != NULL; + xip = &xi->next) + unregister_netdevice_queue(xi->dev, &list); + } + unregister_netdevice_many(&list); + rtnl_unlock(); +} + static struct pernet_operations xfrmi_net_ops = { .init = xfrmi_init_net, .exit = xfrmi_exit_net, + .exit_batch = xfrmi_exit_batch_net, .id = &xfrmi_net_id, .size = sizeof(struct xfrmi_net), }; diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index 9499b35feb92..2e7288e4da7b 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -586,18 +586,20 @@ int xfrm_output(struct sock *sk, struct sk_buff *skb) xfrm_state_hold(x); if (skb_is_gso(skb)) { - skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; + if (skb->inner_protocol) + return xfrm_output_gso(net, sk, skb); - return xfrm_output2(net, sk, skb); + skb_shinfo(skb)->gso_type |= SKB_GSO_ESP; + goto out; } if (x->xso.dev && x->xso.dev->features & NETIF_F_HW_ESP_TX_CSUM) goto out; + } else { + if (skb_is_gso(skb)) + return xfrm_output_gso(net, sk, skb); } - if (skb_is_gso(skb)) - return xfrm_output_gso(net, sk, skb); - if (skb->ip_summed == CHECKSUM_PARTIAL) { err = skb_checksum_help(skb); if (err) { @@ -643,7 +645,8 @@ void xfrm_local_error(struct sk_buff *skb, int mtu) if (skb->protocol == htons(ETH_P_IP)) proto = AF_INET; - else if (skb->protocol == htons(ETH_P_IPV6)) + else if (skb->protocol == htons(ETH_P_IPV6) && + skb->sk->sk_family == AF_INET6) proto = AF_INET6; else return; diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index 7c2fa80b20bd..c7106f43db45 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -431,7 +431,9 @@ EXPORT_SYMBOL(xfrm_policy_destroy); static void xfrm_policy_kill(struct xfrm_policy *policy) { + write_lock_bh(&policy->lock); policy->walk.dead = 1; + write_unlock_bh(&policy->lock); atomic_inc(&policy->genid); @@ -1431,19 +1433,10 @@ static void xfrm_policy_requeue(struct xfrm_policy *old, spin_unlock_bh(&pq->hold_queue.lock); } -static bool xfrm_policy_mark_match(struct xfrm_policy *policy, - struct xfrm_policy *pol) +static inline bool xfrm_policy_mark_match(const struct xfrm_mark *mark, + struct xfrm_policy *pol) { - u32 mark = policy->mark.v & policy->mark.m; - - if (policy->mark.v == pol->mark.v && policy->mark.m == pol->mark.m) - return true; - - if ((mark & pol->mark.m) == pol->mark.v && - policy->priority == pol->priority) - return true; - - return false; + return mark->v == pol->mark.v && mark->m == pol->mark.m; } static u32 xfrm_pol_bin_key(const void *data, u32 len, u32 seed) @@ -1506,7 +1499,7 @@ static void xfrm_policy_insert_inexact_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { delpol = pol; @@ -1541,7 +1534,7 @@ static struct xfrm_policy *xfrm_policy_insert_list(struct hlist_head *chain, if (pol->type == policy->type && pol->if_id == policy->if_id && !selector_cmp(&pol->selector, &policy->selector) && - xfrm_policy_mark_match(policy, pol) && + xfrm_policy_mark_match(&policy->mark, pol) && xfrm_sec_ctx_match(pol->security, policy->security) && !WARN_ON(delpol)) { if (excl) @@ -1613,9 +1606,8 @@ int xfrm_policy_insert(int dir, struct xfrm_policy *policy, int excl) EXPORT_SYMBOL(xfrm_policy_insert); static struct xfrm_policy * -__xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, +__xfrm_policy_bysel_ctx(struct hlist_head *chain, const struct xfrm_mark *mark, + u32 if_id, u8 type, int dir, struct xfrm_selector *sel, struct xfrm_sec_ctx *ctx) { struct xfrm_policy *pol; @@ -1626,7 +1618,7 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, hlist_for_each_entry(pol, chain, bydst) { if (pol->type == type && pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v && + xfrm_policy_mark_match(mark, pol) && !selector_cmp(sel, &pol->selector) && xfrm_sec_ctx_match(ctx, pol->security)) return pol; @@ -1635,11 +1627,10 @@ __xfrm_policy_bysel_ctx(struct hlist_head *chain, u32 mark, u32 if_id, return NULL; } -struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, - struct xfrm_selector *sel, - struct xfrm_sec_ctx *ctx, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_bysel_ctx(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, struct xfrm_selector *sel, + struct xfrm_sec_ctx *ctx, int delete, int *err) { struct xfrm_pol_inexact_bin *bin = NULL; struct xfrm_policy *pol, *ret = NULL; @@ -1706,9 +1697,9 @@ struct xfrm_policy *xfrm_policy_bysel_ctx(struct net *net, u32 mark, u32 if_id, } EXPORT_SYMBOL(xfrm_policy_bysel_ctx); -struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, - u8 type, int dir, u32 id, int delete, - int *err) +struct xfrm_policy * +xfrm_policy_byid(struct net *net, const struct xfrm_mark *mark, u32 if_id, + u8 type, int dir, u32 id, int delete, int *err) { struct xfrm_policy *pol, *ret; struct hlist_head *chain; @@ -1723,8 +1714,7 @@ struct xfrm_policy *xfrm_policy_byid(struct net *net, u32 mark, u32 if_id, ret = NULL; hlist_for_each_entry(pol, chain, byidx) { if (pol->type == type && pol->index == id && - pol->if_id == if_id && - (mark & pol->mark.m) == pol->mark.v) { + pol->if_id == if_id && xfrm_policy_mark_match(mark, pol)) { xfrm_pol_hold(pol); if (delete) { *err = security_xfrm_policy_delete( diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 50621d982970..eac463c6bcb0 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -418,6 +418,8 @@ static void ___xfrm_state_destroy(struct xfrm_state *x) x->type->destructor(x); xfrm_put_type(x->type); } + if (x->xfrag.page) + put_page(x->xfrag.page); xfrm_dev_state_free(x); security_xfrm_state_free(x); xfrm_state_free(x); diff --git a/net/xfrm/xfrm_user.c b/net/xfrm/xfrm_user.c index b88ba45ff1ac..fbb7d9d06478 100644 --- a/net/xfrm/xfrm_user.c +++ b/net/xfrm/xfrm_user.c @@ -110,7 +110,8 @@ static inline int verify_sec_ctx_len(struct nlattr **attrs) return 0; uctx = nla_data(rt); - if (uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len)) + if (uctx->len > nla_len(rt) || + uctx->len != (sizeof(struct xfrm_user_sec_ctx) + uctx->ctx_len)) return -EINVAL; return 0; @@ -1862,7 +1863,6 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, struct km_event c; int delete; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; p = nlmsg_data(nlh); @@ -1879,8 +1879,11 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, delete, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, + p->index, delete, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -1897,8 +1900,8 @@ static int xfrm_get_policy(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, &p->sel, - ctx, delete, &err); + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, + &p->sel, ctx, delete, &err); security_xfrm_policy_free(ctx); } if (xp == NULL) @@ -2165,7 +2168,6 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, u8 type = XFRM_POLICY_TYPE_MAIN; int err = -ENOENT; struct xfrm_mark m; - u32 mark = xfrm_mark_get(attrs, &m); u32 if_id = 0; err = copy_from_user_policy_type(&type, attrs); @@ -2179,8 +2181,11 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (attrs[XFRMA_IF_ID]) if_id = nla_get_u32(attrs[XFRMA_IF_ID]); + xfrm_mark_get(attrs, &m); + if (p->index) - xp = xfrm_policy_byid(net, mark, if_id, type, p->dir, p->index, 0, &err); + xp = xfrm_policy_byid(net, &m, if_id, type, p->dir, p->index, + 0, &err); else { struct nlattr *rt = attrs[XFRMA_SEC_CTX]; struct xfrm_sec_ctx *ctx; @@ -2197,7 +2202,7 @@ static int xfrm_add_pol_expire(struct sk_buff *skb, struct nlmsghdr *nlh, if (err) return err; } - xp = xfrm_policy_bysel_ctx(net, mark, if_id, type, p->dir, + xp = xfrm_policy_bysel_ctx(net, &m, if_id, type, p->dir, &p->sel, ctx, 0, &err); security_xfrm_policy_free(ctx); } @@ -2275,6 +2280,9 @@ static int xfrm_add_acquire(struct sk_buff *skb, struct nlmsghdr *nlh, err = verify_newpolicy_info(&ua->policy); if (err) goto free_state; + err = verify_sec_ctx_len(attrs); + if (err) + goto free_state; /* build an XP */ xp = xfrm_policy_construct(net, &ua->policy, attrs, &err); |