diff options
Diffstat (limited to 'net')
-rw-r--r-- | net/bluetooth/hci_conn.c | 49 | ||||
-rw-r--r-- | net/bluetooth/hci_event.c | 67 | ||||
-rw-r--r-- | net/bluetooth/hci_sync.c | 30 | ||||
-rw-r--r-- | net/bluetooth/hci_sysfs.c | 14 | ||||
-rw-r--r-- | net/bluetooth/iso.c | 4 | ||||
-rw-r--r-- | net/bluetooth/l2cap_core.c | 5 | ||||
-rw-r--r-- | net/bluetooth/l2cap_sock.c | 2 | ||||
-rw-r--r-- | net/bridge/br_if.c | 5 | ||||
-rw-r--r-- | net/dsa/tag_sja1105.c | 90 | ||||
-rw-r--r-- | net/ipv4/tcp_input.c | 12 | ||||
-rw-r--r-- | net/mac80211/led.c | 2 | ||||
-rw-r--r-- | net/mac80211/led.h | 8 | ||||
-rw-r--r-- | net/mptcp/protocol.c | 7 | ||||
-rw-r--r-- | net/netfilter/xt_LED.c | 3 | ||||
-rw-r--r-- | net/sched/act_ipt.c | 70 | ||||
-rw-r--r-- | net/sched/act_pedit.c | 1 | ||||
-rw-r--r-- | net/sctp/socket.c | 4 | ||||
-rw-r--r-- | net/sunrpc/Makefile | 2 | ||||
-rw-r--r-- | net/sunrpc/auth.c | 2 | ||||
-rw-r--r-- | net/sunrpc/auth_tls.c | 175 | ||||
-rw-r--r-- | net/sunrpc/clnt.c | 22 | ||||
-rw-r--r-- | net/sunrpc/rpcb_clnt.c | 39 | ||||
-rw-r--r-- | net/sunrpc/sysfs.c | 1 | ||||
-rw-r--r-- | net/sunrpc/sysfs.h | 7 | ||||
-rw-r--r-- | net/sunrpc/xprtsock.c | 434 | ||||
-rw-r--r-- | net/xdp/xsk.c | 5 |
26 files changed, 892 insertions, 168 deletions
diff --git a/net/bluetooth/hci_conn.c b/net/bluetooth/hci_conn.c index 1ef952bda97d..056f9516e46d 100644 --- a/net/bluetooth/hci_conn.c +++ b/net/bluetooth/hci_conn.c @@ -775,6 +775,11 @@ static void le_conn_timeout(struct work_struct *work) hci_abort_conn(conn, HCI_ERROR_REMOTE_USER_TERM); } +struct iso_cig_params { + struct hci_cp_le_set_cig_params cp; + struct hci_cis_params cis[0x1f]; +}; + struct iso_list_data { union { u8 cig; @@ -786,10 +791,7 @@ struct iso_list_data { u16 sync_handle; }; int count; - struct { - struct hci_cp_le_set_cig_params cp; - struct hci_cis_params cis[0x11]; - } pdu; + struct iso_cig_params pdu; }; static void bis_list(struct hci_conn *conn, void *data) @@ -1764,10 +1766,33 @@ static int hci_le_create_big(struct hci_conn *conn, struct bt_iso_qos *qos) return hci_send_cmd(hdev, HCI_OP_LE_CREATE_BIG, sizeof(cp), &cp); } +static void set_cig_params_complete(struct hci_dev *hdev, void *data, int err) +{ + struct iso_cig_params *pdu = data; + + bt_dev_dbg(hdev, ""); + + if (err) + bt_dev_err(hdev, "Unable to set CIG parameters: %d", err); + + kfree(pdu); +} + +static int set_cig_params_sync(struct hci_dev *hdev, void *data) +{ + struct iso_cig_params *pdu = data; + u32 plen; + + plen = sizeof(pdu->cp) + pdu->cp.num_cis * sizeof(pdu->cis[0]); + return __hci_cmd_sync_status(hdev, HCI_OP_LE_SET_CIG_PARAMS, plen, pdu, + HCI_CMD_TIMEOUT); +} + static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) { struct hci_dev *hdev = conn->hdev; struct iso_list_data data; + struct iso_cig_params *pdu; memset(&data, 0, sizeof(data)); @@ -1837,11 +1862,15 @@ static bool hci_le_set_cig_params(struct hci_conn *conn, struct bt_iso_qos *qos) if (qos->ucast.cis == BT_ISO_QOS_CIS_UNSET || !data.pdu.cp.num_cis) return false; - if (hci_send_cmd(hdev, HCI_OP_LE_SET_CIG_PARAMS, - sizeof(data.pdu.cp) + - (data.pdu.cp.num_cis * sizeof(*data.pdu.cis)), - &data.pdu) < 0) + pdu = kmemdup(&data.pdu, sizeof(*pdu), GFP_KERNEL); + if (!pdu) + return false; + + if (hci_cmd_sync_queue(hdev, set_cig_params_sync, pdu, + set_cig_params_complete) < 0) { + kfree(pdu); return false; + } return true; } @@ -2044,10 +2073,10 @@ static int create_big_sync(struct hci_dev *hdev, void *data) flags |= MGMT_ADV_FLAG_SEC_2M; /* Align intervals */ - interval = qos->bcast.out.interval / 1250; + interval = (qos->bcast.out.interval / 1250) * qos->bcast.sync_factor; if (qos->bcast.bis) - sync_interval = qos->bcast.sync_interval * 1600; + sync_interval = interval * 4; err = hci_start_per_adv_sync(hdev, qos->bcast.bis, conn->le_per_adv_data_len, conn->le_per_adv_data, flags, interval, diff --git a/net/bluetooth/hci_event.c b/net/bluetooth/hci_event.c index 09ba6d8987ee..95816a938cea 100644 --- a/net/bluetooth/hci_event.c +++ b/net/bluetooth/hci_event.c @@ -3812,7 +3812,8 @@ static u8 hci_cc_le_set_cig_params(struct hci_dev *hdev, void *data, bt_dev_dbg(hdev, "status 0x%2.2x", rp->status); cp = hci_sent_cmd_data(hdev, HCI_OP_LE_SET_CIG_PARAMS); - if (!cp || rp->num_handles != cp->num_cis || rp->cig_id != cp->cig_id) { + if (!rp->status && (!cp || rp->num_handles != cp->num_cis || + rp->cig_id != cp->cig_id)) { bt_dev_err(hdev, "unexpected Set CIG Parameters response data"); status = HCI_ERROR_UNSPECIFIED; } @@ -6316,23 +6317,18 @@ static void process_adv_report(struct hci_dev *hdev, u8 type, bdaddr_t *bdaddr, return; } - /* When receiving non-connectable or scannable undirected - * advertising reports, this means that the remote device is - * not connectable and then clearly indicate this in the - * device found event. - * - * When receiving a scan response, then there is no way to + /* When receiving a scan response, then there is no way to * know if the remote device is connectable or not. However * since scan responses are merged with a previously seen * advertising report, the flags field from that report * will be used. * - * In the really unlikely case that a controller get confused - * and just sends a scan response event, then it is marked as - * not connectable as well. + * In the unlikely case that a controller just sends a scan + * response event that doesn't match the pending report, then + * it is marked as a standalone SCAN_RSP. */ if (type == LE_ADV_SCAN_RSP) - flags = MGMT_DEV_FOUND_NOT_CONNECTABLE; + flags = MGMT_DEV_FOUND_SCAN_RSP; /* If there's nothing pending either store the data from this * event or send an immediate device found event if the data @@ -6790,6 +6786,7 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, { struct hci_evt_le_cis_established *ev = data; struct hci_conn *conn; + struct bt_iso_qos *qos; u16 handle = __le16_to_cpu(ev->handle); bt_dev_dbg(hdev, "status 0x%2.2x", ev->status); @@ -6811,21 +6808,39 @@ static void hci_le_cis_estabilished_evt(struct hci_dev *hdev, void *data, goto unlock; } - if (conn->role == HCI_ROLE_SLAVE) { - __le32 interval; - - memset(&interval, 0, sizeof(interval)); - - memcpy(&interval, ev->c_latency, sizeof(ev->c_latency)); - conn->iso_qos.ucast.in.interval = le32_to_cpu(interval); - memcpy(&interval, ev->p_latency, sizeof(ev->p_latency)); - conn->iso_qos.ucast.out.interval = le32_to_cpu(interval); - conn->iso_qos.ucast.in.latency = le16_to_cpu(ev->interval); - conn->iso_qos.ucast.out.latency = le16_to_cpu(ev->interval); - conn->iso_qos.ucast.in.sdu = le16_to_cpu(ev->c_mtu); - conn->iso_qos.ucast.out.sdu = le16_to_cpu(ev->p_mtu); - conn->iso_qos.ucast.in.phy = ev->c_phy; - conn->iso_qos.ucast.out.phy = ev->p_phy; + qos = &conn->iso_qos; + + /* Convert ISO Interval (1.25 ms slots) to SDU Interval (us) */ + qos->ucast.in.interval = le16_to_cpu(ev->interval) * 1250; + qos->ucast.out.interval = qos->ucast.in.interval; + + switch (conn->role) { + case HCI_ROLE_SLAVE: + /* Convert Transport Latency (us) to Latency (msec) */ + qos->ucast.in.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), + 1000); + qos->ucast.out.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), + 1000); + qos->ucast.in.sdu = le16_to_cpu(ev->c_mtu); + qos->ucast.out.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.in.phy = ev->c_phy; + qos->ucast.out.phy = ev->p_phy; + break; + case HCI_ROLE_MASTER: + /* Convert Transport Latency (us) to Latency (msec) */ + qos->ucast.out.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->c_latency), + 1000); + qos->ucast.in.latency = + DIV_ROUND_CLOSEST(get_unaligned_le24(ev->p_latency), + 1000); + qos->ucast.out.sdu = le16_to_cpu(ev->c_mtu); + qos->ucast.in.sdu = le16_to_cpu(ev->p_mtu); + qos->ucast.out.phy = ev->c_phy; + qos->ucast.in.phy = ev->p_phy; + break; } if (!ev->status) { diff --git a/net/bluetooth/hci_sync.c b/net/bluetooth/hci_sync.c index 804cde43b4e0..8561616abbe5 100644 --- a/net/bluetooth/hci_sync.c +++ b/net/bluetooth/hci_sync.c @@ -4623,26 +4623,18 @@ static int hci_dev_setup_sync(struct hci_dev *hdev) * BD_ADDR invalid before creating the HCI device or in * its setup callback. */ - invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks); - + invalid_bdaddr = test_bit(HCI_QUIRK_INVALID_BDADDR, &hdev->quirks) || + test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks); if (!ret) { - if (test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks)) { - if (!bacmp(&hdev->public_addr, BDADDR_ANY)) - hci_dev_get_bd_addr_from_property(hdev); - - if (bacmp(&hdev->public_addr, BDADDR_ANY) && - 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; - } + if (test_bit(HCI_QUIRK_USE_BDADDR_PROPERTY, &hdev->quirks) && + !bacmp(&hdev->public_addr, BDADDR_ANY)) + hci_dev_get_bd_addr_from_property(hdev); + + if (invalid_bdaddr && bacmp(&hdev->public_addr, BDADDR_ANY) && + hdev->set_bdaddr) { + ret = hdev->set_bdaddr(hdev, &hdev->public_addr); + if (!ret) + invalid_bdaddr = false; } } diff --git a/net/bluetooth/hci_sysfs.c b/net/bluetooth/hci_sysfs.c index 2934d7f4d564..15b33579007c 100644 --- a/net/bluetooth/hci_sysfs.c +++ b/net/bluetooth/hci_sysfs.c @@ -6,7 +6,9 @@ #include <net/bluetooth/bluetooth.h> #include <net/bluetooth/hci_core.h> -static struct class *bt_class; +static const struct class bt_class = { + .name = "bluetooth", +}; static void bt_link_release(struct device *dev) { @@ -36,7 +38,7 @@ void hci_conn_init_sysfs(struct hci_conn *conn) BT_DBG("conn %p", conn); conn->dev.type = &bt_link; - conn->dev.class = bt_class; + conn->dev.class = &bt_class; conn->dev.parent = &hdev->dev; device_initialize(&conn->dev); @@ -104,7 +106,7 @@ void hci_init_sysfs(struct hci_dev *hdev) struct device *dev = &hdev->dev; dev->type = &bt_host; - dev->class = bt_class; + dev->class = &bt_class; __module_get(THIS_MODULE); device_initialize(dev); @@ -112,12 +114,10 @@ void hci_init_sysfs(struct hci_dev *hdev) int __init bt_sysfs_init(void) { - bt_class = class_create("bluetooth"); - - return PTR_ERR_OR_ZERO(bt_class); + return class_register(&bt_class); } void bt_sysfs_cleanup(void) { - class_destroy(bt_class); + class_unregister(&bt_class); } diff --git a/net/bluetooth/iso.c b/net/bluetooth/iso.c index 34d55a85d8f6..0e6cc57b3911 100644 --- a/net/bluetooth/iso.c +++ b/net/bluetooth/iso.c @@ -704,7 +704,7 @@ static struct bt_iso_qos default_qos = { .bcast = { .big = BT_ISO_QOS_BIG_UNSET, .bis = BT_ISO_QOS_BIS_UNSET, - .sync_interval = 0x00, + .sync_factor = 0x01, .packing = 0x00, .framing = 0x00, .in = DEFAULT_IO_QOS, @@ -1213,7 +1213,7 @@ static bool check_ucast_qos(struct bt_iso_qos *qos) static bool check_bcast_qos(struct bt_iso_qos *qos) { - if (qos->bcast.sync_interval > 0x07) + if (qos->bcast.sync_factor == 0x00) return false; if (qos->bcast.packing > 0x01) diff --git a/net/bluetooth/l2cap_core.c b/net/bluetooth/l2cap_core.c index c5e8798e297c..17ca13e8c044 100644 --- a/net/bluetooth/l2cap_core.c +++ b/net/bluetooth/l2cap_core.c @@ -6374,9 +6374,14 @@ static inline int l2cap_le_command_rej(struct l2cap_conn *conn, if (!chan) goto done; + chan = l2cap_chan_hold_unless_zero(chan); + if (!chan) + goto done; + l2cap_chan_lock(chan); l2cap_chan_del(chan, ECONNREFUSED); l2cap_chan_unlock(chan); + l2cap_chan_put(chan); done: mutex_unlock(&conn->chan_lock); diff --git a/net/bluetooth/l2cap_sock.c b/net/bluetooth/l2cap_sock.c index eebe256104bc..947ca580bb9a 100644 --- a/net/bluetooth/l2cap_sock.c +++ b/net/bluetooth/l2cap_sock.c @@ -46,6 +46,7 @@ static const struct proto_ops l2cap_sock_ops; static void l2cap_sock_init(struct sock *sk, struct sock *parent); static struct sock *l2cap_sock_alloc(struct net *net, struct socket *sock, int proto, gfp_t prio, int kern); +static void l2cap_sock_cleanup_listen(struct sock *parent); bool l2cap_is_socket(struct socket *sock) { @@ -1415,6 +1416,7 @@ static int l2cap_sock_release(struct socket *sock) if (!sk) return 0; + l2cap_sock_cleanup_listen(sk); bt_sock_unlink(&l2cap_sk_list, sk); err = l2cap_sock_shutdown(sock, SHUT_RDWR); diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 3f04b40f6056..2450690f98cf 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -166,8 +166,9 @@ void br_manage_promisc(struct net_bridge *br) * This lets us disable promiscuous mode and write * this config to hw. */ - if (br->auto_cnt == 0 || - (br->auto_cnt == 1 && br_auto_port(p))) + if ((p->dev->priv_flags & IFF_UNICAST_FLT) && + (br->auto_cnt == 0 || + (br->auto_cnt == 1 && br_auto_port(p)))) br_port_clear_promisc(p); else br_port_set_promisc(p); diff --git a/net/dsa/tag_sja1105.c b/net/dsa/tag_sja1105.c index a5f3b73da417..ade3eeb2f3e6 100644 --- a/net/dsa/tag_sja1105.c +++ b/net/dsa/tag_sja1105.c @@ -58,11 +58,8 @@ #define SJA1110_TX_TRAILER_LEN 4 #define SJA1110_MAX_PADDING_LEN 15 -#define SJA1105_HWTS_RX_EN 0 - struct sja1105_tagger_private { struct sja1105_tagger_data data; /* Must be first */ - unsigned long state; /* Protects concurrent access to the meta state machine * from taggers running on multiple ports on SMP systems */ @@ -118,8 +115,8 @@ static void sja1105_meta_unpack(const struct sk_buff *skb, * a unified unpacking command for both device series. */ packing(buf, &meta->tstamp, 31, 0, 4, UNPACK, 0); - packing(buf + 4, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); - packing(buf + 5, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 4, &meta->dmac_byte_3, 7, 0, 1, UNPACK, 0); + packing(buf + 5, &meta->dmac_byte_4, 7, 0, 1, UNPACK, 0); packing(buf + 6, &meta->source_port, 7, 0, 1, UNPACK, 0); packing(buf + 7, &meta->switch_id, 7, 0, 1, UNPACK, 0); } @@ -392,10 +389,6 @@ static struct sk_buff priv = sja1105_tagger_private(ds); - if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) - /* Do normal processing. */ - return skb; - spin_lock(&priv->meta_lock); /* Was this a link-local frame instead of the meta * that we were expecting? @@ -431,12 +424,6 @@ static struct sk_buff priv = sja1105_tagger_private(ds); - /* Drop the meta frame if we're not in the right state - * to process it. - */ - if (!test_bit(SJA1105_HWTS_RX_EN, &priv->state)) - return NULL; - spin_lock(&priv->meta_lock); stampable_skb = priv->stampable_skb; @@ -472,30 +459,6 @@ static struct sk_buff return skb; } -static bool sja1105_rxtstamp_get_state(struct dsa_switch *ds) -{ - struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); - - return test_bit(SJA1105_HWTS_RX_EN, &priv->state); -} - -static void sja1105_rxtstamp_set_state(struct dsa_switch *ds, bool on) -{ - struct sja1105_tagger_private *priv = sja1105_tagger_private(ds); - - if (on) - set_bit(SJA1105_HWTS_RX_EN, &priv->state); - else - clear_bit(SJA1105_HWTS_RX_EN, &priv->state); - - /* Initialize the meta state machine to a known state */ - if (!priv->stampable_skb) - return; - - kfree_skb(priv->stampable_skb); - priv->stampable_skb = NULL; -} - static bool sja1105_skb_has_tag_8021q(const struct sk_buff *skb) { u16 tpid = ntohs(eth_hdr(skb)->h_proto); @@ -545,33 +508,53 @@ static struct sk_buff *sja1105_rcv(struct sk_buff *skb, is_link_local = sja1105_is_link_local(skb); is_meta = sja1105_is_meta_frame(skb); - if (sja1105_skb_has_tag_8021q(skb)) { - /* Normal traffic path. */ - sja1105_vlan_rcv(skb, &source_port, &switch_id, &vbid, &vid); - } else if (is_link_local) { + if (is_link_local) { /* Management traffic path. Switch embeds the switch ID and * port ID into bytes of the destination MAC, courtesy of * the incl_srcpt options. */ source_port = hdr->h_dest[3]; switch_id = hdr->h_dest[4]; - /* Clear the DMAC bytes that were mangled by the switch */ - hdr->h_dest[3] = 0; - hdr->h_dest[4] = 0; } else if (is_meta) { sja1105_meta_unpack(skb, &meta); source_port = meta.source_port; switch_id = meta.switch_id; - } else { + } + + /* Normal data plane traffic and link-local frames are tagged with + * a tag_8021q VLAN which we have to strip + */ + if (sja1105_skb_has_tag_8021q(skb)) { + int tmp_source_port = -1, tmp_switch_id = -1; + + sja1105_vlan_rcv(skb, &tmp_source_port, &tmp_switch_id, &vbid, + &vid); + /* Preserve the source information from the INCL_SRCPT option, + * if available. This allows us to not overwrite a valid source + * port and switch ID with zeroes when receiving link-local + * frames from a VLAN-unaware bridged port (non-zero vbid) or a + * VLAN-aware bridged port (non-zero vid). Furthermore, the + * tag_8021q source port information is only of trust when the + * vbid is 0 (precise port). Otherwise, tmp_source_port and + * tmp_switch_id will be zeroes. + */ + if (vbid == 0 && source_port == -1) + source_port = tmp_source_port; + if (vbid == 0 && switch_id == -1) + switch_id = tmp_switch_id; + } else if (source_port == -1 && switch_id == -1) { + /* Packets with no source information have no chance of + * getting accepted, drop them straight away. + */ return NULL; } - if (vbid >= 1) + if (source_port != -1 && switch_id != -1) + skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + else if (vbid >= 1) skb->dev = dsa_tag_8021q_find_port_by_vbid(netdev, vbid); - else if (source_port == -1 || switch_id == -1) - skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); else - skb->dev = dsa_master_find_slave(netdev, switch_id, source_port); + skb->dev = dsa_find_designated_bridge_port_by_vid(netdev, vid); if (!skb->dev) { netdev_warn(netdev, "Couldn't decode source port\n"); return NULL; @@ -762,7 +745,6 @@ static void sja1105_disconnect(struct dsa_switch *ds) static int sja1105_connect(struct dsa_switch *ds) { - struct sja1105_tagger_data *tagger_data; struct sja1105_tagger_private *priv; struct kthread_worker *xmit_worker; int err; @@ -782,10 +764,6 @@ static int sja1105_connect(struct dsa_switch *ds) } priv->xmit_worker = xmit_worker; - /* Export functions for switch driver use */ - tagger_data = &priv->data; - tagger_data->rxtstamp_get_state = sja1105_rxtstamp_get_state; - tagger_data->rxtstamp_set_state = sja1105_rxtstamp_set_state; ds->tagger_data = priv; return 0; diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 6f072095211e..57c8af1859c1 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3590,8 +3590,11 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, u32 *last_oow_ack_time) { - if (*last_oow_ack_time) { - s32 elapsed = (s32)(tcp_jiffies32 - *last_oow_ack_time); + /* Paired with the WRITE_ONCE() in this function. */ + u32 val = READ_ONCE(*last_oow_ack_time); + + if (val) { + s32 elapsed = (s32)(tcp_jiffies32 - val); if (0 <= elapsed && elapsed < READ_ONCE(net->ipv4.sysctl_tcp_invalid_ratelimit)) { @@ -3600,7 +3603,10 @@ static bool __tcp_oow_rate_limited(struct net *net, int mib_idx, } } - *last_oow_ack_time = tcp_jiffies32; + /* Paired with the prior READ_ONCE() and with itself, + * as we might be lockless. + */ + WRITE_ONCE(*last_oow_ack_time, tcp_jiffies32); return false; /* not rate-limited: go ahead, send dupack now! */ } diff --git a/net/mac80211/led.c b/net/mac80211/led.c index 6de8d0ad5497..2dc732147e85 100644 --- a/net/mac80211/led.c +++ b/net/mac80211/led.c @@ -282,7 +282,7 @@ static void tpt_trig_timer(struct timer_list *t) } } - led_trigger_blink(&local->tpt_led, &on, &off); + led_trigger_blink(&local->tpt_led, on, off); } const char * diff --git a/net/mac80211/led.h b/net/mac80211/led.h index b71a1428d883..d25f13346b82 100644 --- a/net/mac80211/led.h +++ b/net/mac80211/led.h @@ -13,22 +13,18 @@ static inline void ieee80211_led_rx(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_LEDS - unsigned long led_delay = MAC80211_BLINK_DELAY; - if (!atomic_read(&local->rx_led_active)) return; - led_trigger_blink_oneshot(&local->rx_led, &led_delay, &led_delay, 0); + led_trigger_blink_oneshot(&local->rx_led, MAC80211_BLINK_DELAY, MAC80211_BLINK_DELAY, 0); #endif } static inline void ieee80211_led_tx(struct ieee80211_local *local) { #ifdef CONFIG_MAC80211_LEDS - unsigned long led_delay = MAC80211_BLINK_DELAY; - if (!atomic_read(&local->tx_led_active)) return; - led_trigger_blink_oneshot(&local->tx_led, &led_delay, &led_delay, 0); + led_trigger_blink_oneshot(&local->tx_led, MAC80211_BLINK_DELAY, MAC80211_BLINK_DELAY, 0); #endif } diff --git a/net/mptcp/protocol.c b/net/mptcp/protocol.c index e892673deb73..3613489eb6e3 100644 --- a/net/mptcp/protocol.c +++ b/net/mptcp/protocol.c @@ -2909,10 +2909,10 @@ static void mptcp_check_listen_stop(struct sock *sk) return; lock_sock_nested(ssk, SINGLE_DEPTH_NESTING); + tcp_set_state(ssk, TCP_CLOSE); mptcp_subflow_queue_clean(sk, ssk); inet_csk_listen_stop(ssk); mptcp_event_pm_listener(ssk, MPTCP_EVENT_LISTENER_CLOSED); - tcp_set_state(ssk, TCP_CLOSE); release_sock(ssk); } @@ -3703,6 +3703,11 @@ static int mptcp_listen(struct socket *sock, int backlog) pr_debug("msk=%p", msk); lock_sock(sk); + + err = -EINVAL; + if (sock->state != SS_UNCONNECTED || sock->type != SOCK_STREAM) + goto unlock; + ssock = __mptcp_nmpc_socket(msk); if (IS_ERR(ssock)) { err = PTR_ERR(ssock); diff --git a/net/netfilter/xt_LED.c b/net/netfilter/xt_LED.c index 66b0f941d8fb..36c9720ad8d6 100644 --- a/net/netfilter/xt_LED.c +++ b/net/netfilter/xt_LED.c @@ -43,7 +43,6 @@ led_tg(struct sk_buff *skb, const struct xt_action_param *par) { const struct xt_led_info *ledinfo = par->targinfo; struct xt_led_info_internal *ledinternal = ledinfo->internal_data; - unsigned long led_delay = XT_LED_BLINK_DELAY; /* * If "always blink" is enabled, and there's still some time until the @@ -52,7 +51,7 @@ led_tg(struct sk_buff *skb, const struct xt_action_param *par) if ((ledinfo->delay > 0) && ledinfo->always_blink && timer_pending(&ledinternal->timer)) led_trigger_blink_oneshot(&ledinternal->netfilter_led_trigger, - &led_delay, &led_delay, 1); + XT_LED_BLINK_DELAY, XT_LED_BLINK_DELAY, 1); else led_trigger_event(&ledinternal->netfilter_led_trigger, LED_FULL); diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 5d96ffebd40f..598d6e299152 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -21,6 +21,7 @@ #include <linux/tc_act/tc_ipt.h> #include <net/tc_act/tc_ipt.h> #include <net/tc_wrapper.h> +#include <net/ip.h> #include <linux/netfilter_ipv4/ip_tables.h> @@ -48,7 +49,7 @@ static int ipt_init_target(struct net *net, struct xt_entry_target *t, par.entryinfo = &e; par.target = target; par.targinfo = t->data; - par.hook_mask = hook; + par.hook_mask = 1 << hook; par.family = NFPROTO_IPV4; ret = xt_check_target(&par, t->u.target_size - sizeof(*t), 0, false); @@ -85,7 +86,8 @@ static void tcf_ipt_release(struct tc_action *a) static const struct nla_policy ipt_policy[TCA_IPT_MAX + 1] = { [TCA_IPT_TABLE] = { .type = NLA_STRING, .len = IFNAMSIZ }, - [TCA_IPT_HOOK] = { .type = NLA_U32 }, + [TCA_IPT_HOOK] = NLA_POLICY_RANGE(NLA_U32, NF_INET_PRE_ROUTING, + NF_INET_NUMHOOKS), [TCA_IPT_INDEX] = { .type = NLA_U32 }, [TCA_IPT_TARG] = { .len = sizeof(struct xt_entry_target) }, }; @@ -158,15 +160,27 @@ static int __tcf_ipt_init(struct net *net, unsigned int id, struct nlattr *nla, return -EEXIST; } } + + err = -EINVAL; hook = nla_get_u32(tb[TCA_IPT_HOOK]); + switch (hook) { + case NF_INET_PRE_ROUTING: + break; + case NF_INET_POST_ROUTING: + break; + default: + goto err1; + } + + if (tb[TCA_IPT_TABLE]) { + /* mangle only for now */ + if (nla_strcmp(tb[TCA_IPT_TABLE], "mangle")) + goto err1; + } - err = -ENOMEM; - tname = kmalloc(IFNAMSIZ, GFP_KERNEL); + tname = kstrdup("mangle", GFP_KERNEL); if (unlikely(!tname)) goto err1; - if (tb[TCA_IPT_TABLE] == NULL || - nla_strscpy(tname, tb[TCA_IPT_TABLE], IFNAMSIZ) >= IFNAMSIZ) - strcpy(tname, "mangle"); t = kmemdup(td, td->u.target_size, GFP_KERNEL); if (unlikely(!t)) @@ -217,10 +231,31 @@ static int tcf_xt_init(struct net *net, struct nlattr *nla, a, &act_xt_ops, tp, flags); } +static bool tcf_ipt_act_check(struct sk_buff *skb) +{ + const struct iphdr *iph; + unsigned int nhoff, len; + + if (!pskb_may_pull(skb, sizeof(struct iphdr))) + return false; + + nhoff = skb_network_offset(skb); + iph = ip_hdr(skb); + if (iph->ihl < 5 || iph->version != 4) + return false; + + len = skb_ip_totlen(skb); + if (skb->len < nhoff + len || len < (iph->ihl * 4u)) + return false; + + return pskb_may_pull(skb, iph->ihl * 4u); +} + TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, const struct tc_action *a, struct tcf_result *res) { + char saved_cb[sizeof_field(struct sk_buff, cb)]; int ret = 0, result = 0; struct tcf_ipt *ipt = to_ipt(a); struct xt_action_param par; @@ -231,9 +266,24 @@ TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, .pf = NFPROTO_IPV4, }; + if (skb_protocol(skb, false) != htons(ETH_P_IP)) + return TC_ACT_UNSPEC; + if (skb_unclone(skb, GFP_ATOMIC)) return TC_ACT_UNSPEC; + if (!tcf_ipt_act_check(skb)) + return TC_ACT_UNSPEC; + + if (state.hook == NF_INET_POST_ROUTING) { + if (!skb_dst(skb)) + return TC_ACT_UNSPEC; + + state.out = skb->dev; + } + + memcpy(saved_cb, skb->cb, sizeof(saved_cb)); + spin_lock(&ipt->tcf_lock); tcf_lastuse_update(&ipt->tcf_tm); @@ -246,6 +296,9 @@ TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, par.state = &state; par.target = ipt->tcfi_t->u.kernel.target; par.targinfo = ipt->tcfi_t->data; + + memset(IPCB(skb), 0, sizeof(struct inet_skb_parm)); + ret = par.target->target(skb, &par); switch (ret) { @@ -266,6 +319,9 @@ TC_INDIRECT_SCOPE int tcf_ipt_act(struct sk_buff *skb, break; } spin_unlock(&ipt->tcf_lock); + + memcpy(skb->cb, saved_cb, sizeof(skb->cb)); + return result; } diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index b562fc2bb5b1..1ef8fcfa9997 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -29,6 +29,7 @@ static struct tc_action_ops act_pedit_ops; static const struct nla_policy pedit_policy[TCA_PEDIT_MAX + 1] = { [TCA_PEDIT_PARMS] = { .len = sizeof(struct tc_pedit) }, + [TCA_PEDIT_PARMS_EX] = { .len = sizeof(struct tc_pedit) }, [TCA_PEDIT_KEYS_EX] = { .type = NLA_NESTED }, }; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 6554a357fe33..9388d98aebc0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -364,9 +364,9 @@ static void sctp_auto_asconf_init(struct sctp_sock *sp) struct net *net = sock_net(&sp->inet.sk); if (net->sctp.default_auto_asconf) { - spin_lock(&net->sctp.addr_wq_lock); + spin_lock_bh(&net->sctp.addr_wq_lock); list_add_tail(&sp->auto_asconf_list, &net->sctp.auto_asconf_splist); - spin_unlock(&net->sctp.addr_wq_lock); + spin_unlock_bh(&net->sctp.addr_wq_lock); sp->do_auto_asconf = 1; } } diff --git a/net/sunrpc/Makefile b/net/sunrpc/Makefile index 1c8de397d6ad..f89c10fe7e6a 100644 --- a/net/sunrpc/Makefile +++ b/net/sunrpc/Makefile @@ -9,7 +9,7 @@ obj-$(CONFIG_SUNRPC_GSS) += auth_gss/ obj-$(CONFIG_SUNRPC_XPRT_RDMA) += xprtrdma/ sunrpc-y := clnt.o xprt.o socklib.o xprtsock.o sched.o \ - auth.o auth_null.o auth_unix.o \ + auth.o auth_null.o auth_tls.o auth_unix.o \ svc.o svcsock.o svcauth.o svcauth_unix.o \ addr.o rpcb_clnt.o timer.o xdr.o \ sunrpc_syms.o cache.o rpc_pipe.o sysfs.o \ diff --git a/net/sunrpc/auth.c b/net/sunrpc/auth.c index fb75a883503f..2f16f9d17966 100644 --- a/net/sunrpc/auth.c +++ b/net/sunrpc/auth.c @@ -32,7 +32,7 @@ static unsigned int auth_hashbits = RPC_CREDCACHE_DEFAULT_HASHBITS; static const struct rpc_authops __rcu *auth_flavors[RPC_AUTH_MAXFLAVOR] = { [RPC_AUTH_NULL] = (const struct rpc_authops __force __rcu *)&authnull_ops, [RPC_AUTH_UNIX] = (const struct rpc_authops __force __rcu *)&authunix_ops, - NULL, /* others can be loadable modules */ + [RPC_AUTH_TLS] = (const struct rpc_authops __force __rcu *)&authtls_ops, }; static LIST_HEAD(cred_unused); diff --git a/net/sunrpc/auth_tls.c b/net/sunrpc/auth_tls.c new file mode 100644 index 000000000000..de7678f8a23d --- /dev/null +++ b/net/sunrpc/auth_tls.c @@ -0,0 +1,175 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* + * Copyright (c) 2021, 2022 Oracle. All rights reserved. + * + * The AUTH_TLS credential is used only to probe a remote peer + * for RPC-over-TLS support. + */ + +#include <linux/types.h> +#include <linux/module.h> +#include <linux/sunrpc/clnt.h> + +static const char *starttls_token = "STARTTLS"; +static const size_t starttls_len = 8; + +static struct rpc_auth tls_auth; +static struct rpc_cred tls_cred; + +static void tls_encode_probe(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + const void *obj) +{ +} + +static int tls_decode_probe(struct rpc_rqst *rqstp, struct xdr_stream *xdr, + void *obj) +{ + return 0; +} + +static const struct rpc_procinfo rpcproc_tls_probe = { + .p_encode = tls_encode_probe, + .p_decode = tls_decode_probe, +}; + +static void rpc_tls_probe_call_prepare(struct rpc_task *task, void *data) +{ + task->tk_flags &= ~RPC_TASK_NO_RETRANS_TIMEOUT; + rpc_call_start(task); +} + +static void rpc_tls_probe_call_done(struct rpc_task *task, void *data) +{ +} + +static const struct rpc_call_ops rpc_tls_probe_ops = { + .rpc_call_prepare = rpc_tls_probe_call_prepare, + .rpc_call_done = rpc_tls_probe_call_done, +}; + +static int tls_probe(struct rpc_clnt *clnt) +{ + struct rpc_message msg = { + .rpc_proc = &rpcproc_tls_probe, + }; + struct rpc_task_setup task_setup_data = { + .rpc_client = clnt, + .rpc_message = &msg, + .rpc_op_cred = &tls_cred, + .callback_ops = &rpc_tls_probe_ops, + .flags = RPC_TASK_SOFT | RPC_TASK_SOFTCONN, + }; + struct rpc_task *task; + int status; + + task = rpc_run_task(&task_setup_data); + if (IS_ERR(task)) + return PTR_ERR(task); + status = task->tk_status; + rpc_put_task(task); + return status; +} + +static struct rpc_auth *tls_create(const struct rpc_auth_create_args *args, + struct rpc_clnt *clnt) +{ + refcount_inc(&tls_auth.au_count); + return &tls_auth; +} + +static void tls_destroy(struct rpc_auth *auth) +{ +} + +static struct rpc_cred *tls_lookup_cred(struct rpc_auth *auth, + struct auth_cred *acred, int flags) +{ + return get_rpccred(&tls_cred); +} + +static void tls_destroy_cred(struct rpc_cred *cred) +{ +} + +static int tls_match(struct auth_cred *acred, struct rpc_cred *cred, int taskflags) +{ + return 1; +} + +static int tls_marshal(struct rpc_task *task, struct xdr_stream *xdr) +{ + __be32 *p; + + p = xdr_reserve_space(xdr, 4 * XDR_UNIT); + if (!p) + return -EMSGSIZE; + /* Credential */ + *p++ = rpc_auth_tls; + *p++ = xdr_zero; + /* Verifier */ + *p++ = rpc_auth_null; + *p = xdr_zero; + return 0; +} + +static int tls_refresh(struct rpc_task *task) +{ + set_bit(RPCAUTH_CRED_UPTODATE, &task->tk_rqstp->rq_cred->cr_flags); + return 0; +} + +static int tls_validate(struct rpc_task *task, struct xdr_stream *xdr) +{ + __be32 *p; + void *str; + + p = xdr_inline_decode(xdr, XDR_UNIT); + if (!p) + return -EIO; + if (*p != rpc_auth_null) + return -EIO; + if (xdr_stream_decode_opaque_inline(xdr, &str, starttls_len) != starttls_len) + return -EIO; + if (memcmp(str, starttls_token, starttls_len)) + return -EIO; + return 0; +} + +const struct rpc_authops authtls_ops = { + .owner = THIS_MODULE, + .au_flavor = RPC_AUTH_TLS, + .au_name = "NULL", + .create = tls_create, + .destroy = tls_destroy, + .lookup_cred = tls_lookup_cred, + .ping = tls_probe, +}; + +static struct rpc_auth tls_auth = { + .au_cslack = NUL_CALLSLACK, + .au_rslack = NUL_REPLYSLACK, + .au_verfsize = NUL_REPLYSLACK, + .au_ralign = NUL_REPLYSLACK, + .au_ops = &authtls_ops, + .au_flavor = RPC_AUTH_TLS, + .au_count = REFCOUNT_INIT(1), +}; + +static const struct rpc_credops tls_credops = { + .cr_name = "AUTH_TLS", + .crdestroy = tls_destroy_cred, + .crmatch = tls_match, + .crmarshal = tls_marshal, + .crwrap_req = rpcauth_wrap_req_encode, + .crrefresh = tls_refresh, + .crvalidate = tls_validate, + .crunwrap_resp = rpcauth_unwrap_resp_decode, +}; + +static struct rpc_cred tls_cred = { + .cr_lru = LIST_HEAD_INIT(tls_cred.cr_lru), + .cr_auth = &tls_auth, + .cr_ops = &tls_credops, + .cr_count = REFCOUNT_INIT(2), + .cr_flags = 1UL << RPCAUTH_CRED_UPTODATE, +}; diff --git a/net/sunrpc/clnt.c b/net/sunrpc/clnt.c index d2ee56634308..d7c697af3762 100644 --- a/net/sunrpc/clnt.c +++ b/net/sunrpc/clnt.c @@ -385,6 +385,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (!clnt) goto out_err; clnt->cl_parent = parent ? : clnt; + clnt->cl_xprtsec = args->xprtsec; err = rpc_alloc_clid(clnt); if (err) @@ -434,7 +435,7 @@ static struct rpc_clnt * rpc_new_client(const struct rpc_create_args *args, if (parent) refcount_inc(&parent->cl_count); - trace_rpc_clnt_new(clnt, xprt, program->name, args->servername); + trace_rpc_clnt_new(clnt, xprt, args); return clnt; out_no_path: @@ -532,6 +533,7 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) .addrlen = args->addrsize, .servername = args->servername, .bc_xprt = args->bc_xprt, + .xprtsec = args->xprtsec, }; char servername[48]; struct rpc_clnt *clnt; @@ -565,8 +567,12 @@ struct rpc_clnt *rpc_create(struct rpc_create_args *args) servername[0] = '\0'; switch (args->address->sa_family) { case AF_LOCAL: - snprintf(servername, sizeof(servername), "%s", - sun->sun_path); + if (sun->sun_path[0]) + snprintf(servername, sizeof(servername), "%s", + sun->sun_path); + else + snprintf(servername, sizeof(servername), "@%s", + sun->sun_path+1); break; case AF_INET: snprintf(servername, sizeof(servername), "%pI4", @@ -727,6 +733,7 @@ int rpc_switch_client_transport(struct rpc_clnt *clnt, struct rpc_clnt *parent; int err; + args->xprtsec = clnt->cl_xprtsec; xprt = xprt_create_transport(args); if (IS_ERR(xprt)) return PTR_ERR(xprt); @@ -1717,6 +1724,11 @@ call_start(struct rpc_task *task) trace_rpc_request(task); + if (task->tk_client->cl_shutdown) { + rpc_call_rpcerror(task, -EIO); + return; + } + /* Increment call count (version might not be valid for ping) */ if (clnt->cl_program->version[clnt->cl_vers]) clnt->cl_program->version[clnt->cl_vers]->counts[idx]++; @@ -2826,6 +2838,9 @@ static int rpc_ping(struct rpc_clnt *clnt) struct rpc_task *task; int status; + if (clnt->cl_auth->au_ops->ping) + return clnt->cl_auth->au_ops->ping(clnt); + task = rpc_call_null_helper(clnt, NULL, NULL, 0, NULL, NULL); if (IS_ERR(task)) return PTR_ERR(task); @@ -3046,6 +3061,7 @@ int rpc_clnt_add_xprt(struct rpc_clnt *clnt, if (!xprtargs->ident) xprtargs->ident = ident; + xprtargs->xprtsec = clnt->cl_xprtsec; xprt = xprt_create_transport(xprtargs); if (IS_ERR(xprt)) { ret = PTR_ERR(xprt); diff --git a/net/sunrpc/rpcb_clnt.c b/net/sunrpc/rpcb_clnt.c index 5a8e6d46809a..5988a5c5ff3f 100644 --- a/net/sunrpc/rpcb_clnt.c +++ b/net/sunrpc/rpcb_clnt.c @@ -36,6 +36,7 @@ #include "netns.h" #define RPCBIND_SOCK_PATHNAME "/var/run/rpcbind.sock" +#define RPCBIND_SOCK_ABSTRACT_NAME "\0/run/rpcbind.sock" #define RPCBIND_PROGRAM (100000u) #define RPCBIND_PORT (111u) @@ -216,21 +217,22 @@ static void rpcb_set_local(struct net *net, struct rpc_clnt *clnt, sn->rpcb_users = 1; } +/* Evaluate to actual length of the `sockaddr_un' structure. */ +# define SUN_LEN(ptr) (offsetof(struct sockaddr_un, sun_path) \ + + 1 + strlen((ptr)->sun_path + 1)) + /* * Returns zero on success, otherwise a negative errno value * is returned. */ -static int rpcb_create_local_unix(struct net *net) +static int rpcb_create_af_local(struct net *net, + const struct sockaddr_un *addr) { - static const struct sockaddr_un rpcb_localaddr_rpcbind = { - .sun_family = AF_LOCAL, - .sun_path = RPCBIND_SOCK_PATHNAME, - }; struct rpc_create_args args = { .net = net, .protocol = XPRT_TRANSPORT_LOCAL, - .address = (struct sockaddr *)&rpcb_localaddr_rpcbind, - .addrsize = sizeof(rpcb_localaddr_rpcbind), + .address = (struct sockaddr *)addr, + .addrsize = SUN_LEN(addr), .servername = "localhost", .program = &rpcb_program, .version = RPCBVERS_2, @@ -269,6 +271,26 @@ out: return result; } +static int rpcb_create_local_abstract(struct net *net) +{ + static const struct sockaddr_un rpcb_localaddr_abstract = { + .sun_family = AF_LOCAL, + .sun_path = RPCBIND_SOCK_ABSTRACT_NAME, + }; + + return rpcb_create_af_local(net, &rpcb_localaddr_abstract); +} + +static int rpcb_create_local_unix(struct net *net) +{ + static const struct sockaddr_un rpcb_localaddr_unix = { + .sun_family = AF_LOCAL, + .sun_path = RPCBIND_SOCK_PATHNAME, + }; + + return rpcb_create_af_local(net, &rpcb_localaddr_unix); +} + /* * Returns zero on success, otherwise a negative errno value * is returned. @@ -332,7 +354,8 @@ int rpcb_create_local(struct net *net) if (rpcb_get_local(net)) goto out; - if (rpcb_create_local_unix(net) != 0) + if (rpcb_create_local_abstract(net) != 0 && + rpcb_create_local_unix(net) != 0) result = rpcb_create_local_net(net); out: diff --git a/net/sunrpc/sysfs.c b/net/sunrpc/sysfs.c index 0d0db4e1064e..5c8ecdaaa985 100644 --- a/net/sunrpc/sysfs.c +++ b/net/sunrpc/sysfs.c @@ -239,6 +239,7 @@ static ssize_t rpc_sysfs_xprt_dstaddr_store(struct kobject *kobj, if (!xprt) return 0; if (!(xprt->xprt_class->ident == XPRT_TRANSPORT_TCP || + xprt->xprt_class->ident == XPRT_TRANSPORT_TCP_TLS || xprt->xprt_class->ident == XPRT_TRANSPORT_RDMA)) { xprt_put(xprt); return -EOPNOTSUPP; diff --git a/net/sunrpc/sysfs.h b/net/sunrpc/sysfs.h index 6620cebd1037..d2dd77a0a0e9 100644 --- a/net/sunrpc/sysfs.h +++ b/net/sunrpc/sysfs.h @@ -5,13 +5,6 @@ #ifndef __SUNRPC_SYSFS_H #define __SUNRPC_SYSFS_H -struct rpc_sysfs_client { - struct kobject kobject; - struct net *net; - struct rpc_clnt *clnt; - struct rpc_xprt_switch *xprt_switch; -}; - struct rpc_sysfs_xprt_switch { struct kobject kobject; struct net *net; diff --git a/net/sunrpc/xprtsock.c b/net/sunrpc/xprtsock.c index 5f9030b81c9e..9f010369100a 100644 --- a/net/sunrpc/xprtsock.c +++ b/net/sunrpc/xprtsock.c @@ -47,6 +47,9 @@ #include <net/checksum.h> #include <net/udp.h> #include <net/tcp.h> +#include <net/tls.h> +#include <net/handshake.h> + #include <linux/bvec.h> #include <linux/highmem.h> #include <linux/uio.h> @@ -96,6 +99,7 @@ static struct ctl_table_header *sunrpc_table_header; static struct xprt_class xs_local_transport; static struct xprt_class xs_udp_transport; static struct xprt_class xs_tcp_transport; +static struct xprt_class xs_tcp_tls_transport; static struct xprt_class xs_bc_tcp_transport; /* @@ -187,6 +191,11 @@ static struct ctl_table xs_tunables_table[] = { */ #define XS_IDLE_DISC_TO (5U * 60 * HZ) +/* + * TLS handshake timeout. + */ +#define XS_TLS_HANDSHAKE_TO (10U * HZ) + #if IS_ENABLED(CONFIG_SUNRPC_DEBUG) # undef RPC_DEBUG_DATA # define RPCDBG_FACILITY RPCDBG_TRANS @@ -253,7 +262,12 @@ static void xs_format_common_peer_addresses(struct rpc_xprt *xprt) switch (sap->sa_family) { case AF_LOCAL: sun = xs_addr_un(xprt); - strscpy(buf, sun->sun_path, sizeof(buf)); + if (sun->sun_path[0]) { + strscpy(buf, sun->sun_path, sizeof(buf)); + } else { + buf[0] = '@'; + strscpy(buf+1, sun->sun_path+1, sizeof(buf)-1); + } xprt->address_strings[RPC_DISPLAY_ADDR] = kstrdup(buf, GFP_KERNEL); break; @@ -342,13 +356,56 @@ xs_alloc_sparse_pages(struct xdr_buf *buf, size_t want, gfp_t gfp) return want; } +static int +xs_sock_process_cmsg(struct socket *sock, struct msghdr *msg, + struct cmsghdr *cmsg, int ret) +{ + if (cmsg->cmsg_level == SOL_TLS && + cmsg->cmsg_type == TLS_GET_RECORD_TYPE) { + u8 content_type = *((u8 *)CMSG_DATA(cmsg)); + + switch (content_type) { + case TLS_RECORD_TYPE_DATA: + /* TLS sets EOR at the end of each application data + * record, even though there might be more frames + * waiting to be decrypted. + */ + msg->msg_flags &= ~MSG_EOR; + break; + case TLS_RECORD_TYPE_ALERT: + ret = -ENOTCONN; + break; + default: + ret = -EAGAIN; + } + } + return ret; +} + +static int +xs_sock_recv_cmsg(struct socket *sock, struct msghdr *msg, int flags) +{ + union { + struct cmsghdr cmsg; + u8 buf[CMSG_SPACE(sizeof(u8))]; + } u; + int ret; + + msg->msg_control = &u; + msg->msg_controllen = sizeof(u); + ret = sock_recvmsg(sock, msg, flags); + if (msg->msg_controllen != sizeof(u)) + ret = xs_sock_process_cmsg(sock, msg, &u.cmsg, ret); + return ret; +} + static ssize_t xs_sock_recvmsg(struct socket *sock, struct msghdr *msg, int flags, size_t seek) { ssize_t ret; if (seek != 0) iov_iter_advance(&msg->msg_iter, seek); - ret = sock_recvmsg(sock, msg, flags); + ret = xs_sock_recv_cmsg(sock, msg, flags); return ret > 0 ? ret + seek : ret; } @@ -374,7 +431,7 @@ xs_read_discard(struct socket *sock, struct msghdr *msg, int flags, size_t count) { iov_iter_discard(&msg->msg_iter, ITER_DEST, count); - return sock_recvmsg(sock, msg, flags); + return xs_sock_recv_cmsg(sock, msg, flags); } #if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE @@ -695,6 +752,8 @@ static void xs_poll_check_readable(struct sock_xprt *transport) { clear_bit(XPRT_SOCK_DATA_READY, &transport->sock_state); + if (test_bit(XPRT_SOCK_IGNORE_RECV, &transport->sock_state)) + return; if (!xs_poll_socket_readable(transport)) return; if (!test_and_set_bit(XPRT_SOCK_DATA_READY, &transport->sock_state)) @@ -1191,6 +1250,8 @@ static void xs_reset_transport(struct sock_xprt *transport) if (atomic_read(&transport->xprt.swapper)) sk_clear_memalloc(sk); + tls_handshake_cancel(sk); + kernel_sock_shutdown(sock, SHUT_RDWR); mutex_lock(&transport->recv_mutex); @@ -1380,6 +1441,10 @@ static void xs_data_ready(struct sock *sk) trace_xs_data_ready(xprt); transport->old_data_ready(sk); + + if (test_bit(XPRT_SOCK_IGNORE_RECV, &transport->sock_state)) + return; + /* Any data means we had a useful conversation, so * then we don't need to delay the next reconnect */ @@ -2360,6 +2425,267 @@ out_unlock: current_restore_flags(pflags, PF_MEMALLOC); } +/* + * Transfer the connected socket to @upper_transport, then mark that + * xprt CONNECTED. + */ +static int xs_tcp_tls_finish_connecting(struct rpc_xprt *lower_xprt, + struct sock_xprt *upper_transport) +{ + struct sock_xprt *lower_transport = + container_of(lower_xprt, struct sock_xprt, xprt); + struct rpc_xprt *upper_xprt = &upper_transport->xprt; + + if (!upper_transport->inet) { + struct socket *sock = lower_transport->sock; + struct sock *sk = sock->sk; + + /* Avoid temporary address, they are bad for long-lived + * connections such as NFS mounts. + * RFC4941, section 3.6 suggests that: + * Individual applications, which have specific + * knowledge about the normal duration of connections, + * MAY override this as appropriate. + */ + if (xs_addr(upper_xprt)->sa_family == PF_INET6) + ip6_sock_set_addr_preferences(sk, IPV6_PREFER_SRC_PUBLIC); + + xs_tcp_set_socket_timeouts(upper_xprt, sock); + tcp_sock_set_nodelay(sk); + + lock_sock(sk); + + /* @sk is already connected, so it now has the RPC callbacks. + * Reach into @lower_transport to save the original ones. + */ + upper_transport->old_data_ready = lower_transport->old_data_ready; + upper_transport->old_state_change = lower_transport->old_state_change; + upper_transport->old_write_space = lower_transport->old_write_space; + upper_transport->old_error_report = lower_transport->old_error_report; + sk->sk_user_data = upper_xprt; + + /* socket options */ + sock_reset_flag(sk, SOCK_LINGER); + + xprt_clear_connected(upper_xprt); + + upper_transport->sock = sock; + upper_transport->inet = sk; + upper_transport->file = lower_transport->file; + + release_sock(sk); + + /* Reset lower_transport before shutting down its clnt */ + mutex_lock(&lower_transport->recv_mutex); + lower_transport->inet = NULL; + lower_transport->sock = NULL; + lower_transport->file = NULL; + + xprt_clear_connected(lower_xprt); + xs_sock_reset_connection_flags(lower_xprt); + xs_stream_reset_connect(lower_transport); + mutex_unlock(&lower_transport->recv_mutex); + } + + if (!xprt_bound(upper_xprt)) + return -ENOTCONN; + + xs_set_memalloc(upper_xprt); + + if (!xprt_test_and_set_connected(upper_xprt)) { + upper_xprt->connect_cookie++; + clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state); + xprt_clear_connecting(upper_xprt); + + upper_xprt->stat.connect_count++; + upper_xprt->stat.connect_time += (long)jiffies - + upper_xprt->stat.connect_start; + xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING); + } + return 0; +} + +/** + * xs_tls_handshake_done - TLS handshake completion handler + * @data: address of xprt to wake + * @status: status of handshake + * @peerid: serial number of key containing the remote's identity + * + */ +static void xs_tls_handshake_done(void *data, int status, key_serial_t peerid) +{ + struct rpc_xprt *lower_xprt = data; + struct sock_xprt *lower_transport = + container_of(lower_xprt, struct sock_xprt, xprt); + + lower_transport->xprt_err = status ? -EACCES : 0; + complete(&lower_transport->handshake_done); + xprt_put(lower_xprt); +} + +static int xs_tls_handshake_sync(struct rpc_xprt *lower_xprt, struct xprtsec_parms *xprtsec) +{ + struct sock_xprt *lower_transport = + container_of(lower_xprt, struct sock_xprt, xprt); + struct tls_handshake_args args = { + .ta_sock = lower_transport->sock, + .ta_done = xs_tls_handshake_done, + .ta_data = xprt_get(lower_xprt), + .ta_peername = lower_xprt->servername, + }; + struct sock *sk = lower_transport->inet; + int rc; + + init_completion(&lower_transport->handshake_done); + set_bit(XPRT_SOCK_IGNORE_RECV, &lower_transport->sock_state); + lower_transport->xprt_err = -ETIMEDOUT; + switch (xprtsec->policy) { + case RPC_XPRTSEC_TLS_ANON: + rc = tls_client_hello_anon(&args, GFP_KERNEL); + if (rc) + goto out_put_xprt; + break; + case RPC_XPRTSEC_TLS_X509: + args.ta_my_cert = xprtsec->cert_serial; + args.ta_my_privkey = xprtsec->privkey_serial; + rc = tls_client_hello_x509(&args, GFP_KERNEL); + if (rc) + goto out_put_xprt; + break; + default: + rc = -EACCES; + goto out_put_xprt; + } + + rc = wait_for_completion_interruptible_timeout(&lower_transport->handshake_done, + XS_TLS_HANDSHAKE_TO); + if (rc <= 0) { + if (!tls_handshake_cancel(sk)) { + if (rc == 0) + rc = -ETIMEDOUT; + goto out_put_xprt; + } + } + + rc = lower_transport->xprt_err; + +out: + xs_stream_reset_connect(lower_transport); + clear_bit(XPRT_SOCK_IGNORE_RECV, &lower_transport->sock_state); + return rc; + +out_put_xprt: + xprt_put(lower_xprt); + goto out; +} + +/** + * xs_tcp_tls_setup_socket - establish a TLS session on a TCP socket + * @work: queued work item + * + * Invoked by a work queue tasklet. + * + * For RPC-with-TLS, there is a two-stage connection process. + * + * The "upper-layer xprt" is visible to the RPC consumer. Once it has + * been marked connected, the consumer knows that a TCP connection and + * a TLS session have been established. + * + * A "lower-layer xprt", created in this function, handles the mechanics + * of connecting the TCP socket, performing the RPC_AUTH_TLS probe, and + * then driving the TLS handshake. Once all that is complete, the upper + * layer xprt is marked connected. + */ +static void xs_tcp_tls_setup_socket(struct work_struct *work) +{ + struct sock_xprt *upper_transport = + container_of(work, struct sock_xprt, connect_worker.work); + struct rpc_clnt *upper_clnt = upper_transport->clnt; + struct rpc_xprt *upper_xprt = &upper_transport->xprt; + struct rpc_create_args args = { + .net = upper_xprt->xprt_net, + .protocol = upper_xprt->prot, + .address = (struct sockaddr *)&upper_xprt->addr, + .addrsize = upper_xprt->addrlen, + .timeout = upper_clnt->cl_timeout, + .servername = upper_xprt->servername, + .program = upper_clnt->cl_program, + .prognumber = upper_clnt->cl_prog, + .version = upper_clnt->cl_vers, + .authflavor = RPC_AUTH_TLS, + .cred = upper_clnt->cl_cred, + .xprtsec = { + .policy = RPC_XPRTSEC_NONE, + }, + }; + unsigned int pflags = current->flags; + struct rpc_clnt *lower_clnt; + struct rpc_xprt *lower_xprt; + int status; + + if (atomic_read(&upper_xprt->swapper)) + current->flags |= PF_MEMALLOC; + + xs_stream_start_connect(upper_transport); + + /* This implicitly sends an RPC_AUTH_TLS probe */ + lower_clnt = rpc_create(&args); + if (IS_ERR(lower_clnt)) { + trace_rpc_tls_unavailable(upper_clnt, upper_xprt); + clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state); + xprt_clear_connecting(upper_xprt); + xprt_wake_pending_tasks(upper_xprt, PTR_ERR(lower_clnt)); + xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING); + goto out_unlock; + } + + /* RPC_AUTH_TLS probe was successful. Try a TLS handshake on + * the lower xprt. + */ + rcu_read_lock(); + lower_xprt = rcu_dereference(lower_clnt->cl_xprt); + rcu_read_unlock(); + status = xs_tls_handshake_sync(lower_xprt, &upper_xprt->xprtsec); + if (status) { + trace_rpc_tls_not_started(upper_clnt, upper_xprt); + goto out_close; + } + + status = xs_tcp_tls_finish_connecting(lower_xprt, upper_transport); + if (status) + goto out_close; + + trace_rpc_socket_connect(upper_xprt, upper_transport->sock, 0); + if (!xprt_test_and_set_connected(upper_xprt)) { + upper_xprt->connect_cookie++; + clear_bit(XPRT_SOCK_CONNECTING, &upper_transport->sock_state); + xprt_clear_connecting(upper_xprt); + + upper_xprt->stat.connect_count++; + upper_xprt->stat.connect_time += (long)jiffies - + upper_xprt->stat.connect_start; + xs_run_error_worker(upper_transport, XPRT_SOCK_WAKE_PENDING); + } + rpc_shutdown_client(lower_clnt); + +out_unlock: + current_restore_flags(pflags, PF_MEMALLOC); + upper_transport->clnt = NULL; + xprt_unlock_connect(upper_xprt, upper_transport); + return; + +out_close: + rpc_shutdown_client(lower_clnt); + + /* xprt_force_disconnect() wakes tasks with a fixed tk_status code. + * Wake them first here to ensure they get our tk_status code. + */ + xprt_wake_pending_tasks(upper_xprt, status); + xs_tcp_force_close(upper_xprt); + xprt_clear_connecting(upper_xprt); + goto out_unlock; +} + /** * xs_connect - connect a socket to a remote endpoint * @xprt: pointer to transport structure @@ -2391,6 +2717,7 @@ static void xs_connect(struct rpc_xprt *xprt, struct rpc_task *task) } else dprintk("RPC: xs_connect scheduled xprt %p\n", xprt); + transport->clnt = task->tk_client; queue_delayed_work(xprtiod_workqueue, &transport->connect_worker, delay); @@ -2858,7 +3185,7 @@ static struct rpc_xprt *xs_setup_local(struct xprt_create *args) switch (sun->sun_family) { case AF_LOCAL: - if (sun->sun_path[0] != '/') { + if (sun->sun_path[0] != '/' && sun->sun_path[0] != '\0') { dprintk("RPC: bad AF_LOCAL address: %s\n", sun->sun_path); ret = ERR_PTR(-EINVAL); @@ -3045,6 +3372,94 @@ out_err: } /** + * xs_setup_tcp_tls - Set up transport to use a TCP with TLS + * @args: rpc transport creation arguments + * + */ +static struct rpc_xprt *xs_setup_tcp_tls(struct xprt_create *args) +{ + struct sockaddr *addr = args->dstaddr; + struct rpc_xprt *xprt; + struct sock_xprt *transport; + struct rpc_xprt *ret; + unsigned int max_slot_table_size = xprt_max_tcp_slot_table_entries; + + if (args->flags & XPRT_CREATE_INFINITE_SLOTS) + max_slot_table_size = RPC_MAX_SLOT_TABLE_LIMIT; + + xprt = xs_setup_xprt(args, xprt_tcp_slot_table_entries, + max_slot_table_size); + if (IS_ERR(xprt)) + return xprt; + transport = container_of(xprt, struct sock_xprt, xprt); + + xprt->prot = IPPROTO_TCP; + xprt->xprt_class = &xs_tcp_transport; + xprt->max_payload = RPC_MAX_FRAGMENT_SIZE; + + xprt->bind_timeout = XS_BIND_TO; + xprt->reestablish_timeout = XS_TCP_INIT_REEST_TO; + xprt->idle_timeout = XS_IDLE_DISC_TO; + + xprt->ops = &xs_tcp_ops; + xprt->timeout = &xs_tcp_default_timeout; + + xprt->max_reconnect_timeout = xprt->timeout->to_maxval; + xprt->connect_timeout = xprt->timeout->to_initval * + (xprt->timeout->to_retries + 1); + + INIT_WORK(&transport->recv_worker, xs_stream_data_receive_workfn); + INIT_WORK(&transport->error_worker, xs_error_handle); + + switch (args->xprtsec.policy) { + case RPC_XPRTSEC_TLS_ANON: + case RPC_XPRTSEC_TLS_X509: + xprt->xprtsec = args->xprtsec; + INIT_DELAYED_WORK(&transport->connect_worker, + xs_tcp_tls_setup_socket); + break; + default: + ret = ERR_PTR(-EACCES); + goto out_err; + } + + switch (addr->sa_family) { + case AF_INET: + if (((struct sockaddr_in *)addr)->sin_port != htons(0)) + xprt_set_bound(xprt); + + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP); + break; + case AF_INET6: + if (((struct sockaddr_in6 *)addr)->sin6_port != htons(0)) + xprt_set_bound(xprt); + + xs_format_peer_addresses(xprt, "tcp", RPCBIND_NETID_TCP6); + break; + default: + ret = ERR_PTR(-EAFNOSUPPORT); + goto out_err; + } + + if (xprt_bound(xprt)) + dprintk("RPC: set up xprt to %s (port %s) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PORT], + xprt->address_strings[RPC_DISPLAY_PROTO]); + else + dprintk("RPC: set up xprt to %s (autobind) via %s\n", + xprt->address_strings[RPC_DISPLAY_ADDR], + xprt->address_strings[RPC_DISPLAY_PROTO]); + + if (try_module_get(THIS_MODULE)) + return xprt; + ret = ERR_PTR(-EINVAL); +out_err: + xs_xprt_free(xprt); + return ret; +} + +/** * xs_setup_bc_tcp - Set up transport to use a TCP backchannel socket * @args: rpc transport creation arguments * @@ -3153,6 +3568,15 @@ static struct xprt_class xs_tcp_transport = { .netid = { "tcp", "tcp6", "" }, }; +static struct xprt_class xs_tcp_tls_transport = { + .list = LIST_HEAD_INIT(xs_tcp_tls_transport.list), + .name = "tcp-with-tls", + .owner = THIS_MODULE, + .ident = XPRT_TRANSPORT_TCP_TLS, + .setup = xs_setup_tcp_tls, + .netid = { "tcp", "tcp6", "" }, +}; + static struct xprt_class xs_bc_tcp_transport = { .list = LIST_HEAD_INIT(xs_bc_tcp_transport.list), .name = "tcp NFSv4.1 backchannel", @@ -3174,6 +3598,7 @@ int init_socket_xprt(void) xprt_register_transport(&xs_local_transport); xprt_register_transport(&xs_udp_transport); xprt_register_transport(&xs_tcp_transport); + xprt_register_transport(&xs_tcp_tls_transport); xprt_register_transport(&xs_bc_tcp_transport); return 0; @@ -3193,6 +3618,7 @@ void cleanup_socket_xprt(void) xprt_unregister_transport(&xs_local_transport); xprt_unregister_transport(&xs_udp_transport); xprt_unregister_transport(&xs_tcp_transport); + xprt_unregister_transport(&xs_tcp_tls_transport); xprt_unregister_transport(&xs_bc_tcp_transport); } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index 5a8c0dd250af..31dca4ecb2c5 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -886,6 +886,7 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) struct sock *sk = sock->sk; struct xdp_sock *xs = xdp_sk(sk); struct net_device *dev; + int bound_dev_if; u32 flags, qid; int err = 0; @@ -899,6 +900,10 @@ static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) XDP_USE_NEED_WAKEUP)) return -EINVAL; + bound_dev_if = READ_ONCE(sk->sk_bound_dev_if); + if (bound_dev_if && bound_dev_if != sxdp->sxdp_ifindex) + return -EINVAL; + rtnl_lock(); mutex_lock(&xs->mutex); if (xs->state != XSK_READY) { |