diff options
Diffstat (limited to 'net')
174 files changed, 3366 insertions, 935 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 5ff8059837b4..990b9fde28c6 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -586,7 +586,8 @@ 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/ax25/af_ax25.c b/net/ax25/af_ax25.c index 324306d6fde0..ff57ea89c27e 100644 --- a/net/ax25/af_ax25.c +++ b/net/ax25/af_ax25.c @@ -808,7 +808,7 @@ static int ax25_create(struct net *net, struct socket *sock, int protocol, struct sock *sk; ax25_cb *ax25; - if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + if (protocol < 0 || protocol > U8_MAX) return -EINVAL; if (!net_eq(net, &init_net)) diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index d5028af750d5..c762758a4649 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich @@ -100,7 +100,6 @@ config BATMAN_ADV_DEBUG config BATMAN_ADV_SYSFS bool "batman-adv sysfs entries" depends on BATMAN_ADV - default y help Say Y here if you want to enable batman-adv device configuration and status interface through sysfs attributes. It is replaced by the diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index fd63e116d9ff..daa49af7ff40 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich diff --git a/net/batman-adv/bat_algo.c b/net/batman-adv/bat_algo.c index fa39eaaab9d7..382fbe51fd34 100644 --- a/net/batman-adv/bat_algo.c +++ b/net/batman-adv/bat_algo.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_algo.h b/net/batman-adv/bat_algo.h index 37898da8ad48..686a60bc9492 100644 --- a/net/batman-adv/bat_algo.h +++ b/net/batman-adv/bat_algo.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_iv_ogm.c b/net/batman-adv/bat_iv_ogm.c index 5b0b20e6da95..f0209505e41a 100644 --- a/net/batman-adv/bat_iv_ogm.c +++ b/net/batman-adv/bat_iv_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_iv_ogm.h b/net/batman-adv/bat_iv_ogm.h index c7a9ba305bfc..0c57c1000c64 100644 --- a/net/batman-adv/bat_iv_ogm.h +++ b/net/batman-adv/bat_iv_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/bat_v.c b/net/batman-adv/bat_v.c index 4ff6cf1ecae7..0ecaf1bb0068 100644 --- a/net/batman-adv/bat_v.c +++ b/net/batman-adv/bat_v.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v.h b/net/batman-adv/bat_v.h index 37833db098e6..5e0be10bc84e 100644 --- a/net/batman-adv/bat_v.h +++ b/net/batman-adv/bat_v.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Linus Lüssing */ diff --git a/net/batman-adv/bat_v_elp.c b/net/batman-adv/bat_v_elp.c index 2614a9caee00..1e3172db7492 100644 --- a/net/batman-adv/bat_v_elp.c +++ b/net/batman-adv/bat_v_elp.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ @@ -107,10 +107,17 @@ static u32 batadv_v_elp_get_throughput(struct batadv_hardif_neigh_node *neigh) } if (ret) goto default_throughput; - if (!(sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT))) - goto default_throughput; - return sinfo.expected_throughput / 100; + if (sinfo.filled & BIT(NL80211_STA_INFO_EXPECTED_THROUGHPUT)) + return sinfo.expected_throughput / 100; + + /* try to estimate the expected throughput based on reported tx + * rates + */ + if (sinfo.filled & BIT(NL80211_STA_INFO_TX_BITRATE)) + return cfg80211_calculate_bitrate(&sinfo.txrate) / 3; + + goto default_throughput; } /* if not a wifi interface, check if this device provides data via diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index 1a29505f4f66..4358d436be2a 100644 --- a/net/batman-adv/bat_v_elp.h +++ b/net/batman-adv/bat_v_elp.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner */ diff --git a/net/batman-adv/bat_v_ogm.c b/net/batman-adv/bat_v_ogm.c index 714ce56cfcc8..969466218999 100644 --- a/net/batman-adv/bat_v_ogm.c +++ b/net/batman-adv/bat_v_ogm.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bat_v_ogm.h b/net/batman-adv/bat_v_ogm.h index bf16d040461d..0ae2575f70bb 100644 --- a/net/batman-adv/bat_v_ogm.h +++ b/net/batman-adv/bat_v_ogm.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index 7f04a6acf14e..4bc695cda397 100644 --- a/net/batman-adv/bitarray.c +++ b/net/batman-adv/bitarray.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bitarray.h b/net/batman-adv/bitarray.h index 84ad2d2b6ac9..533c6d44cb58 100644 --- a/net/batman-adv/bitarray.h +++ b/net/batman-adv/bitarray.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/bridge_loop_avoidance.c b/net/batman-adv/bridge_loop_avoidance.c index 663a53b6d36e..41cc87f06b14 100644 --- a/net/batman-adv/bridge_loop_avoidance.c +++ b/net/batman-adv/bridge_loop_avoidance.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich */ @@ -844,7 +844,7 @@ static bool batadv_handle_announce(struct batadv_priv *bat_priv, u8 *an_addr, /* handle as ANNOUNCE frame */ backbone_gw->lasttime = jiffies; - crc = ntohs(*((__be16 *)(&an_addr[4]))); + crc = ntohs(*((__force __be16 *)(&an_addr[4]))); batadv_dbg(BATADV_DBG_BLA, bat_priv, "%s(): ANNOUNCE vid %d (sent by %pM)... CRC = %#.4x\n", diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 02b24a861a85..41edb2c4a327 100644 --- a/net/batman-adv/bridge_loop_avoidance.h +++ b/net/batman-adv/bridge_loop_avoidance.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich */ diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index 38c4d8e51155..452856c27d20 100644 --- a/net/batman-adv/debugfs.c +++ b/net/batman-adv/debugfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 1c5afd301ce9..7e2e8f586f42 100644 --- a/net/batman-adv/debugfs.h +++ b/net/batman-adv/debugfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/distributed-arp-table.c b/net/batman-adv/distributed-arp-table.c index b0af3a11d406..3d21dd83f8cc 100644 --- a/net/batman-adv/distributed-arp-table.c +++ b/net/batman-adv/distributed-arp-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ @@ -246,7 +246,7 @@ static u8 *batadv_arp_hw_src(struct sk_buff *skb, int hdr_size) */ static __be32 batadv_arp_ip_src(struct sk_buff *skb, int hdr_size) { - return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN); + return *(__force __be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN); } /** @@ -270,7 +270,9 @@ static u8 *batadv_arp_hw_dst(struct sk_buff *skb, int hdr_size) */ static __be32 batadv_arp_ip_dst(struct sk_buff *skb, int hdr_size) { - return *(__be32 *)(batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4); + u8 *dst = batadv_arp_hw_src(skb, hdr_size) + ETH_ALEN * 2 + 4; + + return *(__force __be32 *)dst; } /** @@ -285,16 +287,18 @@ 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; + key = (__force const unsigned char *)&dat->ip; for (i = 0; i < sizeof(dat->ip); i++) { hash += key[i]; hash += (hash << 10); 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/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index 67c7729add55..2bff2f4a325c 100644 --- a/net/batman-adv/distributed-arp-table.h +++ b/net/batman-adv/distributed-arp-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2020 B.A.T.M.A.N. contributors: * * Antonio Quartulli */ diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 385fccdcf69d..7cad97644d05 100644 --- a/net/batman-adv/fragmentation.c +++ b/net/batman-adv/fragmentation.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> */ diff --git a/net/batman-adv/fragmentation.h b/net/batman-adv/fragmentation.h index abfe8c6556de..881ef328b6cd 100644 --- a/net/batman-adv/fragmentation.h +++ b/net/batman-adv/fragmentation.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll <martin@hundeboll.net> */ diff --git a/net/batman-adv/gateway_client.c b/net/batman-adv/gateway_client.c index 47df4c678988..e22e49289677 100644 --- a/net/batman-adv/gateway_client.c +++ b/net/batman-adv/gateway_client.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index 0be8e7178ec7..88b5dba84354 100644 --- a/net/batman-adv/gateway_client.h +++ b/net/batman-adv/gateway_client.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.c b/net/batman-adv/gateway_common.c index fc55750542e4..16cd9450ceb1 100644 --- a/net/batman-adv/gateway_common.c +++ b/net/batman-adv/gateway_common.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 211b14b37db8..c3a0c5a7f7e9 100644 --- a/net/batman-adv/gateway_common.h +++ b/net/batman-adv/gateway_common.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index afb52282d5bd..c7e98a40dd33 100644 --- a/net/batman-adv/hard-interface.c +++ b/net/batman-adv/hard-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hard-interface.h b/net/batman-adv/hard-interface.h index bbb8a6f18d6b..bad2e50135e8 100644 --- a/net/batman-adv/hard-interface.h +++ b/net/batman-adv/hard-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/hash.c b/net/batman-adv/hash.c index a9d4e176f4de..68638e0450a6 100644 --- a/net/batman-adv/hash.c +++ b/net/batman-adv/hash.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/hash.h b/net/batman-adv/hash.h index 57877f0b78e0..91ae9f32b580 100644 --- a/net/batman-adv/hash.h +++ b/net/batman-adv/hash.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2006-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2020 B.A.T.M.A.N. contributors: * * Simon Wunderlich, Marek Lindner */ diff --git a/net/batman-adv/icmp_socket.c b/net/batman-adv/icmp_socket.c index 0a70b66e8770..ccb535c77e5d 100644 --- a/net/batman-adv/icmp_socket.c +++ b/net/batman-adv/icmp_socket.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/icmp_socket.h b/net/batman-adv/icmp_socket.h index 27fafff586df..6abd0f4742ef 100644 --- a/net/batman-adv/icmp_socket.h +++ b/net/batman-adv/icmp_socket.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 11941cf1adcc..a67b2b091447 100644 --- a/net/batman-adv/log.c +++ b/net/batman-adv/log.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 741cfa3719ff..f9884dc56cf3 100644 --- a/net/batman-adv/log.h +++ b/net/batman-adv/log.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -74,7 +74,7 @@ __printf(2, 3); * @bat_priv: the bat priv with all the soft interface information * @ratelimited: whether output should be rate limited * @fmt: format string - * @arg...: variable arguments + * @arg: variable arguments */ #define _batadv_dbg(type, bat_priv, ratelimited, fmt, arg...) \ do { \ @@ -98,7 +98,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_dbg() - Store debug output without ratelimiting * @type: type of debug message * @bat_priv: the bat priv with all the soft interface information - * @arg...: format string and variable arguments + * @arg: format string and variable arguments */ #define batadv_dbg(type, bat_priv, arg...) \ _batadv_dbg(type, bat_priv, 0, ## arg) @@ -107,7 +107,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_dbg_ratelimited() - Store debug output with ratelimiting * @type: type of debug message * @bat_priv: the bat priv with all the soft interface information - * @arg...: format string and variable arguments + * @arg: format string and variable arguments */ #define batadv_dbg_ratelimited(type, bat_priv, arg...) \ _batadv_dbg(type, bat_priv, 1, ## arg) @@ -116,7 +116,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_info() - Store message in debug buffer and print it to kmsg buffer * @net_dev: the soft interface net device * @fmt: format string - * @arg...: variable arguments + * @arg: variable arguments */ #define batadv_info(net_dev, fmt, arg...) \ do { \ @@ -130,7 +130,7 @@ static inline void _batadv_dbg(int type __always_unused, * batadv_err() - Store error in debug buffer and print it to kmsg buffer * @net_dev: the soft interface net device * @fmt: format string - * @arg...: variable arguments + * @arg: variable arguments */ #define batadv_err(net_dev, fmt, arg...) \ do { \ diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index 4811ec65bc43..d8a255c85e77 100644 --- a/net/batman-adv/main.c +++ b/net/batman-adv/main.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/main.h b/net/batman-adv/main.h index c7b340ddd0e7..692306df7b6f 100644 --- a/net/batman-adv/main.h +++ b/net/batman-adv/main.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -13,7 +13,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.5" +#define BATADV_SOURCE_VERSION "2020.0" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index f9ec8e7507b6..9ebdc1e864b9 100644 --- a/net/batman-adv/multicast.c +++ b/net/batman-adv/multicast.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 5d9e2bb29c97..ebf825991ecd 100644 --- a/net/batman-adv/multicast.h +++ b/net/batman-adv/multicast.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2020 B.A.T.M.A.N. contributors: * * Linus Lüssing */ diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 7e052d6f759b..02ed073f95a9 100644 --- a/net/batman-adv/netlink.c +++ b/net/batman-adv/netlink.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index ddc674e47dbb..7ee48f916997 100644 --- a/net/batman-adv/netlink.h +++ b/net/batman-adv/netlink.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2020 B.A.T.M.A.N. contributors: * * Matthias Schiffer */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 580609389f0f..8f0717c3f7b5 100644 --- a/net/batman-adv/network-coding.c +++ b/net/batman-adv/network-coding.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/network-coding.h b/net/batman-adv/network-coding.h index 753fa49723cf..334289084127 100644 --- a/net/batman-adv/network-coding.h +++ b/net/batman-adv/network-coding.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Martin Hundebøll, Jeppe Ledet-Pedersen */ diff --git a/net/batman-adv/originator.c b/net/batman-adv/originator.c index 38613487fb1b..5b0c2fffc214 100644 --- a/net/batman-adv/originator.c +++ b/net/batman-adv/originator.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/originator.h b/net/batman-adv/originator.h index 512a1f99dd75..7bc01c138b3a 100644 --- a/net/batman-adv/originator.h +++ b/net/batman-adv/originator.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.c b/net/batman-adv/routing.c index f0f864820dea..3632bd976c56 100644 --- a/net/batman-adv/routing.c +++ b/net/batman-adv/routing.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index c20feac95107..2ed49db6eff5 100644 --- a/net/batman-adv/routing.h +++ b/net/batman-adv/routing.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.c b/net/batman-adv/send.c index 3ce5f7bad369..7f8ade04e08e 100644 --- a/net/batman-adv/send.c +++ b/net/batman-adv/send.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/send.h b/net/batman-adv/send.h index 5fc0fd1e5d08..0d36e15589f6 100644 --- a/net/batman-adv/send.h +++ b/net/batman-adv/send.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.c b/net/batman-adv/soft-interface.c index 832e156c519e..5f05a728f347 100644 --- a/net/batman-adv/soft-interface.c +++ b/net/batman-adv/soft-interface.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index 29139ad769fe..534e08d6ad91 100644 --- a/net/batman-adv/soft-interface.h +++ b/net/batman-adv/soft-interface.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index e5bbc28ed12c..c45962d8527b 100644 --- a/net/batman-adv/sysfs.c +++ b/net/batman-adv/sysfs.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index 5e466093dfa5..d987f8b30a98 100644 --- a/net/batman-adv/sysfs.h +++ b/net/batman-adv/sysfs.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Marek Lindner */ diff --git a/net/batman-adv/tp_meter.c b/net/batman-adv/tp_meter.c index dd6a9a40dbb9..bd2ac570c42c 100644 --- a/net/batman-adv/tp_meter.c +++ b/net/batman-adv/tp_meter.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/tp_meter.h b/net/batman-adv/tp_meter.h index 78d310da0ad3..140105215aa2 100644 --- a/net/batman-adv/tp_meter.h +++ b/net/batman-adv/tp_meter.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2012-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2020 B.A.T.M.A.N. contributors: * * Edo Monticelli, Antonio Quartulli */ diff --git a/net/batman-adv/trace.c b/net/batman-adv/trace.c index 3cedd2c36528..3444d9e4e90d 100644 --- a/net/batman-adv/trace.c +++ b/net/batman-adv/trace.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index d8f764521c0b..f631b1e01b89 100644 --- a/net/batman-adv/trace.h +++ b/net/batman-adv/trace.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2020 B.A.T.M.A.N. contributors: * * Sven Eckelmann */ diff --git a/net/batman-adv/translation-table.c b/net/batman-adv/translation-table.c index 8a482c5ec67b..852932838ddc 100644 --- a/net/batman-adv/translation-table.c +++ b/net/batman-adv/translation-table.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/translation-table.h b/net/batman-adv/translation-table.h index 4a98860d7f0e..b24d35b9226a 100644 --- a/net/batman-adv/translation-table.h +++ b/net/batman-adv/translation-table.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich, Antonio Quartulli */ diff --git a/net/batman-adv/tvlv.c b/net/batman-adv/tvlv.c index aae63f0d21eb..0963a43ad996 100644 --- a/net/batman-adv/tvlv.c +++ b/net/batman-adv/tvlv.c @@ -1,5 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/tvlv.h b/net/batman-adv/tvlv.h index 36985000a0a8..d509d00c7a23 100644 --- a/net/batman-adv/tvlv.h +++ b/net/batman-adv/tvlv.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ diff --git a/net/batman-adv/types.h b/net/batman-adv/types.h index 47718a82eaf2..4a17a66cc572 100644 --- a/net/batman-adv/types.h +++ b/net/batman-adv/types.h @@ -1,5 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2020 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich */ @@ -457,7 +457,7 @@ struct batadv_orig_node { /** * @tt_lock: prevents from updating the table while reading it. Table * update is made up by two operations (data structure update and - * metdata -CRC/TTVN-recalculation) and they have to be executed + * metadata -CRC/TTVN-recalculation) and they have to be executed * atomically in order to avoid another thread to read the * table/metadata between those. */ @@ -1011,7 +1011,7 @@ struct batadv_priv_tt { /** * @commit_lock: prevents from executing a local TT commit while reading * the local table. The local TT commit is made up by two operations - * (data structure update and metdata -CRC/TTVN- recalculation) and + * (data structure update and metadata -CRC/TTVN- recalculation) and * they have to be executed atomically in order to avoid another thread * to read the table/metadata between those. */ diff --git a/net/bridge/br_netlink.c b/net/bridge/br_netlink.c index 60136575aea4..43dab4066f91 100644 --- a/net/bridge/br_netlink.c +++ b/net/bridge/br_netlink.c @@ -561,52 +561,73 @@ static int br_vlan_info(struct net_bridge *br, struct net_bridge_port *p, return err; } -static int br_process_vlan_info(struct net_bridge *br, - struct net_bridge_port *p, int cmd, - struct bridge_vlan_info *vinfo_curr, - struct bridge_vlan_info **vinfo_last, - bool *changed, - struct netlink_ext_ack *extack) +int br_process_vlan_info(struct net_bridge *br, + struct net_bridge_port *p, int cmd, + struct bridge_vlan_info *vinfo_curr, + struct bridge_vlan_info **vinfo_last, + bool *changed, + struct netlink_ext_ack *extack) { - if (!vinfo_curr->vid || vinfo_curr->vid >= VLAN_VID_MASK) + int err, rtm_cmd; + + if (!br_vlan_valid_id(vinfo_curr->vid, extack)) return -EINVAL; + /* needed for vlan-only NEWVLAN/DELVLAN notifications */ + rtm_cmd = br_afspec_cmd_to_rtm(cmd); + if (vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { - /* check if we are already processing a range */ - if (*vinfo_last) + if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; *vinfo_last = vinfo_curr; - /* don't allow range of pvids */ - if ((*vinfo_last)->flags & BRIDGE_VLAN_INFO_PVID) - return -EINVAL; return 0; } if (*vinfo_last) { struct bridge_vlan_info tmp_vinfo; - int v, err; - - if (!(vinfo_curr->flags & BRIDGE_VLAN_INFO_RANGE_END)) - return -EINVAL; + int v, v_change_start = 0; - if (vinfo_curr->vid <= (*vinfo_last)->vid) + if (!br_vlan_valid_range(vinfo_curr, *vinfo_last, extack)) return -EINVAL; memcpy(&tmp_vinfo, *vinfo_last, sizeof(struct bridge_vlan_info)); for (v = (*vinfo_last)->vid; v <= vinfo_curr->vid; v++) { + bool curr_change = false; + tmp_vinfo.vid = v; - err = br_vlan_info(br, p, cmd, &tmp_vinfo, changed, + err = br_vlan_info(br, p, cmd, &tmp_vinfo, &curr_change, extack); if (err) break; + if (curr_change) { + *changed = curr_change; + if (!v_change_start) + v_change_start = v; + } else { + /* nothing to notify yet */ + if (!v_change_start) + continue; + br_vlan_notify(br, p, v_change_start, + v - 1, rtm_cmd); + v_change_start = 0; + } } + /* v_change_start is set only if the last/whole range changed */ + if (v_change_start) + br_vlan_notify(br, p, v_change_start, + v - 1, rtm_cmd); + *vinfo_last = NULL; return err; } - return br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); + err = br_vlan_info(br, p, cmd, vinfo_curr, changed, extack); + if (*changed) + br_vlan_notify(br, p, vinfo_curr->vid, 0, rtm_cmd); + + return err; } static int br_afspec(struct net_bridge *br, @@ -1664,6 +1685,7 @@ int __init br_netlink_init(void) int err; br_mdb_init(); + br_vlan_rtnl_init(); rtnl_af_register(&br_af_ops); err = rtnl_link_register(&br_link_ops); @@ -1681,6 +1703,7 @@ out_af: void br_netlink_fini(void) { br_mdb_uninit(); + br_vlan_rtnl_uninit(); rtnl_af_unregister(&br_af_ops); rtnl_link_unregister(&br_link_ops); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index f540f3bdf294..a6226ff2f0cc 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -507,6 +507,65 @@ static inline bool nbp_state_should_learn(const struct net_bridge_port *p) return p->state == BR_STATE_LEARNING || p->state == BR_STATE_FORWARDING; } +static inline bool br_vlan_valid_id(u16 vid, struct netlink_ext_ack *extack) +{ + bool ret = vid > 0 && vid < VLAN_VID_MASK; + + if (!ret) + NL_SET_ERR_MSG_MOD(extack, "Vlan id is invalid"); + + return ret; +} + +static inline bool br_vlan_valid_range(const struct bridge_vlan_info *cur, + const struct bridge_vlan_info *last, + struct netlink_ext_ack *extack) +{ + /* pvid flag is not allowed in ranges */ + if (cur->flags & BRIDGE_VLAN_INFO_PVID) { + NL_SET_ERR_MSG_MOD(extack, "Pvid isn't allowed in a range"); + return false; + } + + /* when cur is the range end, check if: + * - it has range start flag + * - range ids are invalid (end is equal to or before start) + */ + if (last) { + if (cur->flags & BRIDGE_VLAN_INFO_RANGE_BEGIN) { + NL_SET_ERR_MSG_MOD(extack, "Found a new vlan range start while processing one"); + return false; + } else if (!(cur->flags & BRIDGE_VLAN_INFO_RANGE_END)) { + NL_SET_ERR_MSG_MOD(extack, "Vlan range end flag is missing"); + return false; + } else if (cur->vid <= last->vid) { + NL_SET_ERR_MSG_MOD(extack, "End vlan id is less than or equal to start vlan id"); + return false; + } + } + + /* check for required range flags */ + if (!(cur->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | + BRIDGE_VLAN_INFO_RANGE_END))) { + NL_SET_ERR_MSG_MOD(extack, "Both vlan range flags are missing"); + return false; + } + + return true; +} + +static inline int br_afspec_cmd_to_rtm(int cmd) +{ + switch (cmd) { + case RTM_SETLINK: + return RTM_NEWVLAN; + case RTM_DELLINK: + return RTM_DELVLAN; + } + + return 0; +} + static inline int br_opt_get(const struct net_bridge *br, enum net_bridge_opts opt) { @@ -911,6 +970,12 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, void br_vlan_port_event(struct net_bridge_port *p, unsigned long event); int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr); +void br_vlan_rtnl_init(void); +void br_vlan_rtnl_uninit(void); +void br_vlan_notify(const struct net_bridge *br, + const struct net_bridge_port *p, + u16 vid, u16 vid_range, + int cmd); static inline struct net_bridge_vlan_group *br_vlan_group( const struct net_bridge *br) @@ -962,6 +1027,10 @@ static inline u16 br_get_pvid(const struct net_bridge_vlan_group *vg) return vg->pvid; } +static inline u16 br_vlan_flags(const struct net_bridge_vlan *v, u16 pvid) +{ + return v->vid == pvid ? v->flags | BRIDGE_VLAN_INFO_PVID : v->flags; +} #else static inline bool br_allowed_ingress(const struct net_bridge *br, struct net_bridge_vlan_group *vg, @@ -1105,6 +1174,21 @@ static inline int br_vlan_bridge_event(struct net_device *dev, { return 0; } + +static inline void br_vlan_rtnl_init(void) +{ +} + +static inline void br_vlan_rtnl_uninit(void) +{ +} + +static inline void br_vlan_notify(const struct net_bridge *br, + const struct net_bridge_port *p, + u16 vid, u16 vid_range, + int cmd) +{ +} #endif struct nf_br_ops { @@ -1176,6 +1260,12 @@ int br_setlink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags, int br_dellink(struct net_device *dev, struct nlmsghdr *nlmsg, u16 flags); int br_getlink(struct sk_buff *skb, u32 pid, u32 seq, struct net_device *dev, u32 filter_mask, int nlflags); +int br_process_vlan_info(struct net_bridge *br, + struct net_bridge_port *p, int cmd, + struct bridge_vlan_info *vinfo_curr, + struct bridge_vlan_info **vinfo_last, + bool *changed, + struct netlink_ext_ack *extack); #ifdef CONFIG_SYSFS /* br_sysfs_if.c */ diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index bb98984cd27d..e4f7dd10c3f8 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -257,6 +257,10 @@ static int __vlan_add(struct net_bridge_vlan *v, u16 flags, &changed, extack); if (err) goto out_filt; + + if (changed) + br_vlan_notify(br, NULL, v->vid, 0, + RTM_NEWVLAN); } masterv = br_vlan_get_master(br, v->vid, extack); @@ -380,13 +384,31 @@ static void __vlan_group_free(struct net_bridge_vlan_group *vg) kfree(vg); } -static void __vlan_flush(struct net_bridge_vlan_group *vg) +static void __vlan_flush(const struct net_bridge *br, + const struct net_bridge_port *p, + struct net_bridge_vlan_group *vg) { struct net_bridge_vlan *vlan, *tmp; + u16 v_start = 0, v_end = 0; __vlan_delete_pvid(vg, vg->pvid); - list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) + list_for_each_entry_safe(vlan, tmp, &vg->vlan_list, vlist) { + /* take care of disjoint ranges */ + if (!v_start) { + v_start = vlan->vid; + } else if (vlan->vid - v_end != 1) { + /* found range end, notify and start next one */ + br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); + v_start = vlan->vid; + } + v_end = vlan->vid; + __vlan_del(vlan); + } + + /* notify about the last/whole vlan range */ + if (v_start) + br_vlan_notify(br, p, v_start, v_end, RTM_DELVLAN); } struct sk_buff *br_handle_vlan(struct net_bridge *br, @@ -716,7 +738,7 @@ void br_vlan_flush(struct net_bridge *br) ASSERT_RTNL(); vg = br_vlan_group(br); - __vlan_flush(vg); + __vlan_flush(br, NULL, vg); RCU_INIT_POINTER(br->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); @@ -925,12 +947,15 @@ static void br_vlan_disable_default_pvid(struct net_bridge *br) /* Disable default_pvid on all ports where it is still * configured. */ - if (vlan_default_pvid(br_vlan_group(br), pvid)) - br_vlan_delete(br, pvid); + if (vlan_default_pvid(br_vlan_group(br), pvid)) { + if (!br_vlan_delete(br, pvid)) + br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); + } list_for_each_entry(p, &br->port_list, list) { - if (vlan_default_pvid(nbp_vlan_group(p), pvid)) - nbp_vlan_delete(p, pvid); + if (vlan_default_pvid(nbp_vlan_group(p), pvid) && + !nbp_vlan_delete(p, pvid)) + br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } br->default_pvid = 0; @@ -972,7 +997,10 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, &vlchange, extack); if (err) goto out; - br_vlan_delete(br, old_pvid); + + if (br_vlan_delete(br, old_pvid)) + br_vlan_notify(br, NULL, old_pvid, 0, RTM_DELVLAN); + br_vlan_notify(br, NULL, pvid, 0, RTM_NEWVLAN); set_bit(0, changed); } @@ -992,7 +1020,9 @@ int __br_vlan_set_default_pvid(struct net_bridge *br, u16 pvid, &vlchange, extack); if (err) goto err_port; - nbp_vlan_delete(p, old_pvid); + if (nbp_vlan_delete(p, old_pvid)) + br_vlan_notify(br, p, old_pvid, 0, RTM_DELVLAN); + br_vlan_notify(p->br, p, pvid, 0, RTM_NEWVLAN); set_bit(p->port_no, changed); } @@ -1007,22 +1037,28 @@ err_port: if (!test_bit(p->port_no, changed)) continue; - if (old_pvid) + if (old_pvid) { nbp_vlan_add(p, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED, &vlchange, NULL); + br_vlan_notify(p->br, p, old_pvid, 0, RTM_NEWVLAN); + } nbp_vlan_delete(p, pvid); + br_vlan_notify(br, p, pvid, 0, RTM_DELVLAN); } if (test_bit(0, changed)) { - if (old_pvid) + if (old_pvid) { br_vlan_add(br, old_pvid, BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &vlchange, NULL); + br_vlan_notify(br, NULL, old_pvid, 0, RTM_NEWVLAN); + } br_vlan_delete(br, pvid); + br_vlan_notify(br, NULL, pvid, 0, RTM_DELVLAN); } goto out; } @@ -1115,6 +1151,7 @@ int nbp_vlan_init(struct net_bridge_port *p, struct netlink_ext_ack *extack) &changed, extack); if (ret) goto err_vlan_add; + br_vlan_notify(p->br, p, p->br->default_pvid, 0, RTM_NEWVLAN); } out: return ret; @@ -1196,7 +1233,7 @@ void nbp_vlan_flush(struct net_bridge_port *port) ASSERT_RTNL(); vg = nbp_vlan_group(port); - __vlan_flush(vg); + __vlan_flush(port->br, port, vg); RCU_INIT_POINTER(port->vlgrp, NULL); synchronize_rcu(); __vlan_group_free(vg); @@ -1462,8 +1499,8 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) { struct netdev_notifier_changeupper_info *info; struct net_bridge *br = netdev_priv(dev); - bool changed; - int ret = 0; + int vlcmd = 0, ret = 0; + bool changed = false; switch (event) { case NETDEV_REGISTER: @@ -1471,9 +1508,11 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) BRIDGE_VLAN_INFO_PVID | BRIDGE_VLAN_INFO_UNTAGGED | BRIDGE_VLAN_INFO_BRENTRY, &changed, NULL); + vlcmd = RTM_NEWVLAN; break; case NETDEV_UNREGISTER: - br_vlan_delete(br, br->default_pvid); + changed = !br_vlan_delete(br, br->default_pvid); + vlcmd = RTM_DELVLAN; break; case NETDEV_CHANGEUPPER: info = ptr; @@ -1487,6 +1526,8 @@ int br_vlan_bridge_event(struct net_device *dev, unsigned long event, void *ptr) br_vlan_link_state_change(dev, br); break; } + if (changed) + br_vlan_notify(br, NULL, br->default_pvid, 0, vlcmd); return ret; } @@ -1505,3 +1546,405 @@ void br_vlan_port_event(struct net_bridge_port *p, unsigned long event) break; } } + +static bool br_vlan_fill_vids(struct sk_buff *skb, u16 vid, u16 vid_range, + u16 flags) +{ + struct bridge_vlan_info info; + struct nlattr *nest; + + nest = nla_nest_start(skb, BRIDGE_VLANDB_ENTRY); + if (!nest) + return false; + + memset(&info, 0, sizeof(info)); + info.vid = vid; + if (flags & BRIDGE_VLAN_INFO_UNTAGGED) + info.flags |= BRIDGE_VLAN_INFO_UNTAGGED; + if (flags & BRIDGE_VLAN_INFO_PVID) + info.flags |= BRIDGE_VLAN_INFO_PVID; + + if (nla_put(skb, BRIDGE_VLANDB_ENTRY_INFO, sizeof(info), &info)) + goto out_err; + + if (vid_range && vid < vid_range && + !(flags & BRIDGE_VLAN_INFO_PVID) && + nla_put_u16(skb, BRIDGE_VLANDB_ENTRY_RANGE, vid_range)) + goto out_err; + + nla_nest_end(skb, nest); + + return true; + +out_err: + nla_nest_cancel(skb, nest); + return false; +} + +static size_t rtnl_vlan_nlmsg_size(void) +{ + return NLMSG_ALIGN(sizeof(struct br_vlan_msg)) + + nla_total_size(0) /* BRIDGE_VLANDB_ENTRY */ + + nla_total_size(sizeof(u16)) /* BRIDGE_VLANDB_ENTRY_RANGE */ + + nla_total_size(sizeof(struct bridge_vlan_info)); /* BRIDGE_VLANDB_ENTRY_INFO */ +} + +void br_vlan_notify(const struct net_bridge *br, + const struct net_bridge_port *p, + u16 vid, u16 vid_range, + int cmd) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct br_vlan_msg *bvm; + struct nlmsghdr *nlh; + struct sk_buff *skb; + int err = -ENOBUFS; + struct net *net; + u16 flags = 0; + int ifindex; + + /* right now notifications are done only with rtnl held */ + ASSERT_RTNL(); + + if (p) { + ifindex = p->dev->ifindex; + vg = nbp_vlan_group(p); + net = dev_net(p->dev); + } else { + ifindex = br->dev->ifindex; + vg = br_vlan_group(br); + net = dev_net(br->dev); + } + + skb = nlmsg_new(rtnl_vlan_nlmsg_size(), GFP_KERNEL); + if (!skb) + goto out_err; + + err = -EMSGSIZE; + nlh = nlmsg_put(skb, 0, 0, cmd, sizeof(*bvm), 0); + if (!nlh) + goto out_err; + bvm = nlmsg_data(nlh); + memset(bvm, 0, sizeof(*bvm)); + bvm->family = AF_BRIDGE; + bvm->ifindex = ifindex; + + switch (cmd) { + case RTM_NEWVLAN: + /* need to find the vlan due to flags/options */ + v = br_vlan_find(vg, vid); + if (!v || !br_vlan_should_use(v)) + goto out_kfree; + + flags = v->flags; + if (br_get_pvid(vg) == v->vid) + flags |= BRIDGE_VLAN_INFO_PVID; + break; + case RTM_DELVLAN: + break; + default: + goto out_kfree; + } + + if (!br_vlan_fill_vids(skb, vid, vid_range, flags)) + goto out_err; + + nlmsg_end(skb, nlh); + rtnl_notify(skb, net, 0, RTNLGRP_BRVLAN, NULL, GFP_KERNEL); + return; + +out_err: + rtnl_set_sk_err(net, RTNLGRP_BRVLAN, err); +out_kfree: + kfree_skb(skb); +} + +/* check if v_curr can enter a range ending in range_end */ +static bool br_vlan_can_enter_range(const struct net_bridge_vlan *v_curr, + const struct net_bridge_vlan *range_end) +{ + return v_curr->vid - range_end->vid == 1 && + range_end->flags == v_curr->flags; +} + +static int br_vlan_dump_dev(const struct net_device *dev, + struct sk_buff *skb, + struct netlink_callback *cb) +{ + struct net_bridge_vlan *v, *range_start = NULL, *range_end = NULL; + struct net_bridge_vlan_group *vg; + int idx = 0, s_idx = cb->args[1]; + struct nlmsghdr *nlh = NULL; + struct net_bridge_port *p; + struct br_vlan_msg *bvm; + struct net_bridge *br; + int err = 0; + u16 pvid; + + if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) + return -EINVAL; + + if (netif_is_bridge_master(dev)) { + br = netdev_priv(dev); + vg = br_vlan_group_rcu(br); + p = NULL; + } else { + p = br_port_get_rcu(dev); + if (WARN_ON(!p)) + return -EINVAL; + vg = nbp_vlan_group_rcu(p); + br = p->br; + } + + if (!vg) + return 0; + + nlh = nlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, + RTM_NEWVLAN, sizeof(*bvm), NLM_F_MULTI); + if (!nlh) + return -EMSGSIZE; + bvm = nlmsg_data(nlh); + memset(bvm, 0, sizeof(*bvm)); + bvm->family = PF_BRIDGE; + bvm->ifindex = dev->ifindex; + pvid = br_get_pvid(vg); + + /* idx must stay at range's beginning until it is filled in */ + list_for_each_entry_rcu(v, &vg->vlan_list, vlist) { + if (!br_vlan_should_use(v)) + continue; + if (idx < s_idx) { + idx++; + continue; + } + + if (!range_start) { + range_start = v; + range_end = v; + continue; + } + + if (v->vid == pvid || !br_vlan_can_enter_range(v, range_end)) { + u16 flags = br_vlan_flags(range_start, pvid); + + if (!br_vlan_fill_vids(skb, range_start->vid, + range_end->vid, flags)) { + err = -EMSGSIZE; + break; + } + /* advance number of filled vlans */ + idx += range_end->vid - range_start->vid + 1; + + range_start = v; + } + range_end = v; + } + + /* err will be 0 and range_start will be set in 3 cases here: + * - first vlan (range_start == range_end) + * - last vlan (range_start == range_end, not in range) + * - last vlan range (range_start != range_end, in range) + */ + if (!err && range_start && + !br_vlan_fill_vids(skb, range_start->vid, range_end->vid, + br_vlan_flags(range_start, pvid))) + err = -EMSGSIZE; + + cb->args[1] = err ? idx : 0; + + nlmsg_end(skb, nlh); + + return err; +} + +static int br_vlan_rtm_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int idx = 0, err = 0, s_idx = cb->args[0]; + struct net *net = sock_net(skb->sk); + struct br_vlan_msg *bvm; + struct net_device *dev; + + err = nlmsg_parse(cb->nlh, sizeof(*bvm), NULL, 0, NULL, cb->extack); + if (err < 0) + return err; + + bvm = nlmsg_data(cb->nlh); + + rcu_read_lock(); + if (bvm->ifindex) { + dev = dev_get_by_index_rcu(net, bvm->ifindex); + if (!dev) { + err = -ENODEV; + goto out_err; + } + err = br_vlan_dump_dev(dev, skb, cb); + if (err && err != -EMSGSIZE) + goto out_err; + } else { + for_each_netdev_rcu(net, dev) { + if (idx < s_idx) + goto skip; + + err = br_vlan_dump_dev(dev, skb, cb); + if (err == -EMSGSIZE) + break; +skip: + idx++; + } + } + cb->args[0] = idx; + rcu_read_unlock(); + + return skb->len; + +out_err: + rcu_read_unlock(); + + return err; +} + +static const struct nla_policy br_vlan_db_policy[BRIDGE_VLANDB_ENTRY_MAX + 1] = { + [BRIDGE_VLANDB_ENTRY_INFO] = { .type = NLA_EXACT_LEN, + .len = sizeof(struct bridge_vlan_info) }, + [BRIDGE_VLANDB_ENTRY_RANGE] = { .type = NLA_U16 }, +}; + +static int br_vlan_rtm_process_one(struct net_device *dev, + const struct nlattr *attr, + int cmd, struct netlink_ext_ack *extack) +{ + struct bridge_vlan_info *vinfo, vrange_end, *vinfo_last = NULL; + struct nlattr *tb[BRIDGE_VLANDB_ENTRY_MAX + 1]; + struct net_bridge_vlan_group *vg; + struct net_bridge_port *p = NULL; + int err = 0, cmdmap = 0; + struct net_bridge *br; + bool changed = false; + + if (netif_is_bridge_master(dev)) { + br = netdev_priv(dev); + vg = br_vlan_group(br); + } else { + p = br_port_get_rtnl(dev); + if (WARN_ON(!p)) + return -ENODEV; + br = p->br; + vg = nbp_vlan_group(p); + } + + if (WARN_ON(!vg)) + return -ENODEV; + + err = nla_parse_nested(tb, BRIDGE_VLANDB_ENTRY_MAX, attr, + br_vlan_db_policy, extack); + if (err) + return err; + + if (!tb[BRIDGE_VLANDB_ENTRY_INFO]) { + NL_SET_ERR_MSG_MOD(extack, "Missing vlan entry info"); + return -EINVAL; + } + memset(&vrange_end, 0, sizeof(vrange_end)); + + vinfo = nla_data(tb[BRIDGE_VLANDB_ENTRY_INFO]); + if (vinfo->flags & (BRIDGE_VLAN_INFO_RANGE_BEGIN | + BRIDGE_VLAN_INFO_RANGE_END)) { + NL_SET_ERR_MSG_MOD(extack, "Old-style vlan ranges are not allowed when using RTM vlan calls"); + return -EINVAL; + } + if (!br_vlan_valid_id(vinfo->vid, extack)) + return -EINVAL; + + if (tb[BRIDGE_VLANDB_ENTRY_RANGE]) { + vrange_end.vid = nla_get_u16(tb[BRIDGE_VLANDB_ENTRY_RANGE]); + /* validate user-provided flags without RANGE_BEGIN */ + vrange_end.flags = BRIDGE_VLAN_INFO_RANGE_END | vinfo->flags; + vinfo->flags |= BRIDGE_VLAN_INFO_RANGE_BEGIN; + + /* vinfo_last is the range start, vinfo the range end */ + vinfo_last = vinfo; + vinfo = &vrange_end; + + if (!br_vlan_valid_id(vinfo->vid, extack) || + !br_vlan_valid_range(vinfo, vinfo_last, extack)) + return -EINVAL; + } + + switch (cmd) { + case RTM_NEWVLAN: + cmdmap = RTM_SETLINK; + break; + case RTM_DELVLAN: + cmdmap = RTM_DELLINK; + break; + } + + err = br_process_vlan_info(br, p, cmdmap, vinfo, &vinfo_last, &changed, + extack); + if (changed) + br_ifinfo_notify(cmdmap, br, p); + + return err; +} + +static int br_vlan_rtm_process(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct br_vlan_msg *bvm; + struct net_device *dev; + struct nlattr *attr; + int err, vlans = 0; + int rem; + + /* this should validate the header and check for remaining bytes */ + err = nlmsg_parse(nlh, sizeof(*bvm), NULL, BRIDGE_VLANDB_MAX, NULL, + extack); + if (err < 0) + return err; + + bvm = nlmsg_data(nlh); + dev = __dev_get_by_index(net, bvm->ifindex); + if (!dev) + return -ENODEV; + + if (!netif_is_bridge_master(dev) && !netif_is_bridge_port(dev)) { + NL_SET_ERR_MSG_MOD(extack, "The device is not a valid bridge or bridge port"); + return -EINVAL; + } + + nlmsg_for_each_attr(attr, nlh, sizeof(*bvm), rem) { + if (nla_type(attr) != BRIDGE_VLANDB_ENTRY) + continue; + + vlans++; + err = br_vlan_rtm_process_one(dev, attr, nlh->nlmsg_type, + extack); + if (err) + break; + } + if (!vlans) { + NL_SET_ERR_MSG_MOD(extack, "No vlans found to process"); + err = -EINVAL; + } + + return err; +} + +void br_vlan_rtnl_init(void) +{ + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_GETVLAN, NULL, + br_vlan_rtm_dump, 0); + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_NEWVLAN, + br_vlan_rtm_process, NULL, 0); + rtnl_register_module(THIS_MODULE, PF_BRIDGE, RTM_DELVLAN, + br_vlan_rtm_process, NULL, 0); +} + +void br_vlan_rtnl_uninit(void) +{ + rtnl_unregister(PF_BRIDGE, RTM_GETVLAN); + rtnl_unregister(PF_BRIDGE, RTM_NEWVLAN); + rtnl_unregister(PF_BRIDGE, RTM_DELVLAN); +} diff --git a/net/core/datagram.c b/net/core/datagram.c index da3c24ed129c..a78e7f864c1e 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -84,7 +84,8 @@ static int receiver_wake_function(wait_queue_entry_t *wait, unsigned int mode, i /* * Wait for the last received packet to be different from skb */ -int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, +int __skb_wait_for_more_packets(struct sock *sk, struct sk_buff_head *queue, + int *err, long *timeo_p, const struct sk_buff *skb) { int error; @@ -97,7 +98,7 @@ int __skb_wait_for_more_packets(struct sock *sk, int *err, long *timeo_p, if (error) goto out_err; - if (READ_ONCE(sk->sk_receive_queue.prev) != skb) + if (READ_ONCE(queue->prev) != skb) goto out; /* Socket shut down? */ @@ -209,6 +210,7 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, /** * __skb_try_recv_datagram - Receive a datagram skbuff * @sk: socket + * @queue: socket queue from which to receive * @flags: MSG\_ flags * @destructor: invoked under the receive lock on successful dequeue * @off: an offset in bytes to peek skb from. Returns an offset @@ -241,13 +243,14 @@ struct sk_buff *__skb_try_recv_from_queue(struct sock *sk, * quite explicitly by POSIX 1003.1g, don't change them without having * the standard around please. */ -struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, +struct sk_buff *__skb_try_recv_datagram(struct sock *sk, + struct sk_buff_head *queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err, struct sk_buff **last) { - struct sk_buff_head *queue = &sk->sk_receive_queue; struct sk_buff *skb; unsigned long cpu_flags; /* @@ -278,7 +281,7 @@ struct sk_buff *__skb_try_recv_datagram(struct sock *sk, unsigned int flags, break; sk_busy_loop(sk, flags & MSG_DONTWAIT); - } while (READ_ONCE(sk->sk_receive_queue.prev) != *last); + } while (READ_ONCE(queue->prev) != *last); error = -EAGAIN; @@ -288,7 +291,9 @@ no_packet: } EXPORT_SYMBOL(__skb_try_recv_datagram); -struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, +struct sk_buff *__skb_recv_datagram(struct sock *sk, + struct sk_buff_head *sk_queue, + unsigned int flags, void (*destructor)(struct sock *sk, struct sk_buff *skb), int *off, int *err) @@ -299,15 +304,16 @@ struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { - skb = __skb_try_recv_datagram(sk, flags, destructor, off, err, - &last); + skb = __skb_try_recv_datagram(sk, sk_queue, flags, destructor, + off, err, &last); if (skb) return skb; if (*err != -EAGAIN) break; } while (timeo && - !__skb_wait_for_more_packets(sk, err, &timeo, last)); + !__skb_wait_for_more_packets(sk, sk_queue, err, + &timeo, last)); return NULL; } @@ -318,7 +324,8 @@ struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags, { int off = 0; - return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), + return __skb_recv_datagram(sk, &sk->sk_receive_queue, + flags | (noblock ? MSG_DONTWAIT : 0), NULL, &off, err); } EXPORT_SYMBOL(skb_recv_datagram); diff --git a/net/core/dev.c b/net/core/dev.c index e7802a41ae7f..4dcc1b390667 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -9192,22 +9192,10 @@ static void netdev_unregister_lockdep_key(struct net_device *dev) void netdev_update_lockdep_key(struct net_device *dev) { - struct netdev_queue *queue; - int i; - - lockdep_unregister_key(&dev->qdisc_xmit_lock_key); lockdep_unregister_key(&dev->addr_list_lock_key); - - lockdep_register_key(&dev->qdisc_xmit_lock_key); lockdep_register_key(&dev->addr_list_lock_key); lockdep_set_class(&dev->addr_list_lock, &dev->addr_list_lock_key); - for (i = 0; i < dev->num_tx_queues; i++) { - queue = netdev_get_tx_queue(dev, i); - - lockdep_set_class(&queue->_xmit_lock, - &dev->qdisc_xmit_lock_key); - } } EXPORT_SYMBOL(netdev_update_lockdep_key); diff --git a/net/core/devlink.c b/net/core/devlink.c index 4c63c9a4c09e..64367eeb21e6 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -4844,21 +4844,12 @@ devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); void -devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, - enum devlink_health_reporter_state state) +devlink_health_reporter_recovery_done(struct devlink_health_reporter *reporter) { - if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && - state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) - return; - - if (reporter->health_state == state) - return; - - reporter->health_state = state; - trace_devlink_health_reporter_state_update(reporter->devlink, - reporter->ops->name, state); + reporter->recovery_count++; + reporter->last_recovery_ts = jiffies; } -EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); +EXPORT_SYMBOL_GPL(devlink_health_reporter_recovery_done); static int devlink_health_reporter_recover(struct devlink_health_reporter *reporter, @@ -4876,9 +4867,8 @@ devlink_health_reporter_recover(struct devlink_health_reporter *reporter, if (err) return err; - reporter->recovery_count++; + devlink_health_reporter_recovery_done(reporter); reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; - reporter->last_recovery_ts = jiffies; return 0; } @@ -5090,6 +5080,48 @@ genlmsg_cancel: return -EMSGSIZE; } +static void devlink_recover_notify(struct devlink_health_reporter *reporter, + enum devlink_command cmd) +{ + struct sk_buff *msg; + int err; + + WARN_ON(cmd != DEVLINK_CMD_HEALTH_REPORTER_RECOVER); + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + err = devlink_nl_health_reporter_fill(msg, reporter->devlink, + reporter, cmd, 0, 0, 0); + if (err) { + nlmsg_free(msg); + return; + } + + genlmsg_multicast_netns(&devlink_nl_family, + devlink_net(reporter->devlink), + msg, 0, DEVLINK_MCGRP_CONFIG, GFP_KERNEL); +} + +void +devlink_health_reporter_state_update(struct devlink_health_reporter *reporter, + enum devlink_health_reporter_state state) +{ + if (WARN_ON(state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY && + state != DEVLINK_HEALTH_REPORTER_STATE_ERROR)) + return; + + if (reporter->health_state == state) + return; + + reporter->health_state = state; + trace_devlink_health_reporter_state_update(reporter->devlink, + reporter->ops->name, state); + devlink_recover_notify(reporter, DEVLINK_CMD_HEALTH_REPORTER_RECOVER); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_state_update); + static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, struct genl_info *info) { @@ -6406,7 +6438,7 @@ static bool devlink_port_type_should_warn(struct devlink_port *devlink_port) devlink_port->attrs.flavour != DEVLINK_PORT_FLAVOUR_DSA; } -#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 30) +#define DEVLINK_PORT_TYPE_WARN_TIMEOUT (HZ * 3600) static void devlink_port_type_warn_schedule(struct devlink_port *devlink_port) { @@ -7563,7 +7595,7 @@ void devlink_region_destroy(struct devlink_region *region) EXPORT_SYMBOL_GPL(devlink_region_destroy); /** - * devlink_region_shapshot_id_get - get snapshot ID + * devlink_region_snapshot_id_get - get snapshot ID * * This callback should be called when adding a new snapshot, * Driver should use the same id for multiple snapshots taken @@ -7571,7 +7603,7 @@ EXPORT_SYMBOL_GPL(devlink_region_destroy); * * @devlink: devlink */ -u32 devlink_region_shapshot_id_get(struct devlink *devlink) +u32 devlink_region_snapshot_id_get(struct devlink *devlink) { u32 id; @@ -7581,7 +7613,7 @@ u32 devlink_region_shapshot_id_get(struct devlink *devlink) return id; } -EXPORT_SYMBOL_GPL(devlink_region_shapshot_id_get); +EXPORT_SYMBOL_GPL(devlink_region_snapshot_id_get); /** * devlink_region_snapshot_create - create a new snapshot @@ -7674,6 +7706,9 @@ static const struct devlink_trap devlink_trap_generic[] = { DEVLINK_TRAP(REJECT_ROUTE, EXCEPTION), DEVLINK_TRAP(IPV4_LPM_UNICAST_MISS, EXCEPTION), DEVLINK_TRAP(IPV6_LPM_UNICAST_MISS, EXCEPTION), + DEVLINK_TRAP(NON_ROUTABLE, DROP), + DEVLINK_TRAP(DECAP_ERROR, EXCEPTION), + DEVLINK_TRAP(OVERLAY_SMAC_MC, DROP), }; #define DEVLINK_TRAP_GROUP(_id) \ @@ -7686,6 +7721,7 @@ static const struct devlink_trap_group devlink_trap_group_generic[] = { DEVLINK_TRAP_GROUP(L2_DROPS), DEVLINK_TRAP_GROUP(L3_DROPS), DEVLINK_TRAP_GROUP(BUFFER_DROPS), + DEVLINK_TRAP_GROUP(TUNNEL_DROPS), }; static int devlink_trap_generic_verify(const struct devlink_trap *trap) diff --git a/net/core/filter.c b/net/core/filter.c index 4bf3e4aa8a7a..792e3744b915 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -2231,10 +2231,10 @@ 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); @@ -2346,7 +2346,7 @@ 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; @@ -2356,11 +2356,11 @@ 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); @@ -2415,6 +2415,7 @@ 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); } @@ -2506,7 +2507,7 @@ 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; @@ -2516,11 +2517,11 @@ 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); @@ -5225,8 +5226,7 @@ __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; } } @@ -5263,8 +5263,7 @@ 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; } } @@ -5331,7 +5330,8 @@ 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; } @@ -7557,21 +7557,21 @@ u32 bpf_sock_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock, type): - BUILD_BUG_ON(HWEIGHT32(SK_FL_TYPE_MASK) != BITS_PER_BYTE * 2); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sock, __sk_flags_offset)); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT); - *target_size = 2; + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock, sk_type), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock, sk_type, + sizeof_field(struct sock, sk_type), + target_size)); break; case offsetof(struct bpf_sock, protocol): - BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); - *insn++ = BPF_LDX_MEM(BPF_W, si->dst_reg, si->src_reg, - offsetof(struct sock, __sk_flags_offset)); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_PROTO_SHIFT); - *target_size = 1; + *insn++ = BPF_LDX_MEM( + BPF_FIELD_SIZEOF(struct sock, sk_protocol), + si->dst_reg, si->src_reg, + bpf_target_off(struct sock, sk_protocol, + sizeof_field(struct sock, sk_protocol), + target_size)); break; case offsetof(struct bpf_sock, src_ip4): @@ -7853,20 +7853,13 @@ static u32 sock_addr_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct bpf_sock_addr, type): - SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( - struct bpf_sock_addr_kern, struct sock, sk, - __sk_flags_offset, BPF_W, 0); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_TYPE_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, SK_FL_TYPE_SHIFT); + SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, + struct sock, sk, sk_type); break; case offsetof(struct bpf_sock_addr, protocol): - SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF( - struct bpf_sock_addr_kern, struct sock, sk, - __sk_flags_offset, BPF_W, 0); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, - SK_FL_PROTO_SHIFT); + SOCK_ADDR_LOAD_NESTED_FIELD(struct bpf_sock_addr_kern, + struct sock, sk, sk_protocol); break; case offsetof(struct bpf_sock_addr, msg_src_ip4): @@ -8785,11 +8778,11 @@ sk_reuseport_is_valid_access(int off, int size, skb, \ SKB_FIELD) -#define SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(SK_FIELD, BPF_SIZE, EXTRA_OFF) \ - SOCK_ADDR_LOAD_NESTED_FIELD_SIZE_OFF(struct sk_reuseport_kern, \ - struct sock, \ - sk, \ - SK_FIELD, BPF_SIZE, EXTRA_OFF) +#define SK_REUSEPORT_LOAD_SK_FIELD(SK_FIELD) \ + SOCK_ADDR_LOAD_NESTED_FIELD(struct sk_reuseport_kern, \ + struct sock, \ + sk, \ + SK_FIELD) static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, const struct bpf_insn *si, @@ -8813,16 +8806,7 @@ static u32 sk_reuseport_convert_ctx_access(enum bpf_access_type type, break; case offsetof(struct sk_reuseport_md, ip_protocol): - BUILD_BUG_ON(HWEIGHT32(SK_FL_PROTO_MASK) != BITS_PER_BYTE); - SK_REUSEPORT_LOAD_SK_FIELD_SIZE_OFF(__sk_flags_offset, - BPF_W, 0); - *insn++ = BPF_ALU32_IMM(BPF_AND, si->dst_reg, SK_FL_PROTO_MASK); - *insn++ = BPF_ALU32_IMM(BPF_RSH, si->dst_reg, - SK_FL_PROTO_SHIFT); - /* SK_FL_PROTO_MASK and SK_FL_PROTO_SHIFT are endian - * aware. No further narrowing or masking is needed. - */ - *target_size = 1; + SK_REUSEPORT_LOAD_SK_FIELD(sk_protocol); break; case offsetof(struct sk_reuseport_md, data_end): diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 2dbbb030fbed..f560b4902060 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -233,7 +233,7 @@ static bool icmp_has_id(u8 type) * @skb: sk_buff to extract from * @key_icmp: struct flow_dissector_key_icmp to fill * @data: raw buffer pointer to the packet - * @toff: offset to extract at + * @thoff: offset to extract at * @hlen: packet header length */ void skb_flow_get_icmp_tci(const struct sk_buff *skb, diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index 39402840025e..757cc1d084e7 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -211,16 +211,10 @@ static int net_eq_idr(int id, void *net, void *peer) return 0; } -/* Should be called with nsid_lock held. If a new id is assigned, the bool alloc - * is set to true, thus the caller knows that the new id must be notified via - * rtnl. - */ -static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) +/* Must be called from RCU-critical section or with nsid_lock held */ +static int __peernet2id(const struct net *net, struct net *peer) { int id = idr_for_each(&net->netns_ids, net_eq_idr, peer); - bool alloc_it = *alloc; - - *alloc = false; /* Magic value for id 0. */ if (id == NET_ID_ZERO) @@ -228,23 +222,9 @@ static int __peernet2id_alloc(struct net *net, struct net *peer, bool *alloc) if (id > 0) return id; - if (alloc_it) { - id = alloc_netid(net, peer, -1); - *alloc = true; - return id >= 0 ? id : NETNSA_NSID_NOT_ASSIGNED; - } - return NETNSA_NSID_NOT_ASSIGNED; } -/* should be called with nsid_lock held */ -static int __peernet2id(struct net *net, struct net *peer) -{ - bool no = false; - - return __peernet2id_alloc(net, peer, &no); -} - static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, struct nlmsghdr *nlh, gfp_t gfp); /* This function returns the id of a peer netns. If no id is assigned, one will @@ -252,38 +232,50 @@ static void rtnl_net_notifyid(struct net *net, int cmd, int id, u32 portid, */ int peernet2id_alloc(struct net *net, struct net *peer, gfp_t gfp) { - bool alloc = false, alive = false; int id; if (refcount_read(&net->count) == 0) return NETNSA_NSID_NOT_ASSIGNED; - spin_lock_bh(&net->nsid_lock); - /* - * When peer is obtained from RCU lists, we may race with + + spin_lock(&net->nsid_lock); + id = __peernet2id(net, peer); + if (id >= 0) { + spin_unlock(&net->nsid_lock); + return id; + } + + /* When peer is obtained from RCU lists, we may race with * its cleanup. Check whether it's alive, and this guarantees * we never hash a peer back to net->netns_ids, after it has * just been idr_remove()'d from there in cleanup_net(). */ - if (maybe_get_net(peer)) - alive = alloc = true; - id = __peernet2id_alloc(net, peer, &alloc); - spin_unlock_bh(&net->nsid_lock); - if (alloc && id >= 0) - rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); - if (alive) - put_net(peer); + if (!maybe_get_net(peer)) { + spin_unlock(&net->nsid_lock); + return NETNSA_NSID_NOT_ASSIGNED; + } + + id = alloc_netid(net, peer, -1); + spin_unlock(&net->nsid_lock); + + put_net(peer); + if (id < 0) + return NETNSA_NSID_NOT_ASSIGNED; + + rtnl_net_notifyid(net, RTM_NEWNSID, id, 0, NULL, gfp); + return id; } EXPORT_SYMBOL_GPL(peernet2id_alloc); /* This function returns, if assigned, the id of a peer netns. */ -int peernet2id(struct net *net, struct net *peer) +int peernet2id(const struct net *net, struct net *peer) { int id; - spin_lock_bh(&net->nsid_lock); + rcu_read_lock(); id = __peernet2id(net, peer); - spin_unlock_bh(&net->nsid_lock); + rcu_read_unlock(); + return id; } EXPORT_SYMBOL(peernet2id); @@ -291,12 +283,12 @@ EXPORT_SYMBOL(peernet2id); /* This function returns true is the peer netns has an id assigned into the * current netns. */ -bool peernet_has_id(struct net *net, struct net *peer) +bool peernet_has_id(const struct net *net, struct net *peer) { return peernet2id(net, peer) >= 0; } -struct net *get_net_ns_by_id(struct net *net, int id) +struct net *get_net_ns_by_id(const struct net *net, int id) { struct net *peer; @@ -528,20 +520,20 @@ static void unhash_nsid(struct net *net, struct net *last) for_each_net(tmp) { int id; - spin_lock_bh(&tmp->nsid_lock); + spin_lock(&tmp->nsid_lock); id = __peernet2id(tmp, net); if (id >= 0) idr_remove(&tmp->netns_ids, id); - spin_unlock_bh(&tmp->nsid_lock); + spin_unlock(&tmp->nsid_lock); if (id >= 0) rtnl_net_notifyid(tmp, RTM_DELNSID, id, 0, NULL, GFP_KERNEL); if (tmp == last) break; } - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); idr_destroy(&net->netns_ids); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); } static LLIST_HEAD(cleanup_list); @@ -754,9 +746,9 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, return PTR_ERR(peer); } - spin_lock_bh(&net->nsid_lock); + spin_lock(&net->nsid_lock); if (__peernet2id(net, peer) >= 0) { - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); err = -EEXIST; NL_SET_BAD_ATTR(extack, nla); NL_SET_ERR_MSG(extack, @@ -765,7 +757,7 @@ static int rtnl_net_newid(struct sk_buff *skb, struct nlmsghdr *nlh, } err = alloc_netid(net, peer, nsid); - spin_unlock_bh(&net->nsid_lock); + spin_unlock(&net->nsid_lock); if (err >= 0) { rtnl_net_notifyid(net, RTM_NEWNSID, err, NETLINK_CB(skb).portid, nlh, GFP_KERNEL); @@ -950,6 +942,7 @@ struct rtnl_net_dump_cb { int s_idx; }; +/* Runs in RCU-critical section. */ static int rtnl_net_dumpid_one(int id, void *peer, void *data) { struct rtnl_net_dump_cb *net_cb = (struct rtnl_net_dump_cb *)data; @@ -1034,19 +1027,9 @@ static int rtnl_net_dumpid(struct sk_buff *skb, struct netlink_callback *cb) goto end; } - spin_lock_bh(&net_cb.tgt_net->nsid_lock); - if (net_cb.fillargs.add_ref && - !net_eq(net_cb.ref_net, net_cb.tgt_net) && - !spin_trylock_bh(&net_cb.ref_net->nsid_lock)) { - spin_unlock_bh(&net_cb.tgt_net->nsid_lock); - err = -EAGAIN; - goto end; - } + rcu_read_lock(); idr_for_each(&net_cb.tgt_net->netns_ids, rtnl_net_dumpid_one, &net_cb); - if (net_cb.fillargs.add_ref && - !net_eq(net_cb.ref_net, net_cb.tgt_net)) - spin_unlock_bh(&net_cb.ref_net->nsid_lock); - spin_unlock_bh(&net_cb.tgt_net->nsid_lock); + rcu_read_unlock(); cb->args[0] = net_cb.idx; end: diff --git a/net/core/pktgen.c b/net/core/pktgen.c index 294bfcf0ce0e..890be1b4877e 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -323,6 +323,10 @@ struct pktgen_dev { struct in6_addr max_in6_daddr; struct in6_addr min_in6_saddr; struct in6_addr max_in6_saddr; + u64 max_in6_h; + u64 max_in6_l; + u64 min_in6_h; + u64 min_in6_l; /* If we're doing ranges, random or incremental, then this * defines the min/max for those ranges. @@ -1355,6 +1359,59 @@ static ssize_t pktgen_if_write(struct file *file, sprintf(pg_result, "OK: dst6_max=%s", buf); return count; } + if (!strcmp(name, "src6_min")) { + len = strn_len(&user_buffer[i], sizeof(buf) - 1); + if (len < 0) + return len; + + pkt_dev->flags |= F_IPV6; + + if (copy_from_user(buf, &user_buffer[i], len)) + return -EFAULT; + buf[len] = 0; + + in6_pton(buf, -1, pkt_dev->min_in6_saddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->min_in6_saddr); + + memcpy(&pkt_dev->min_in6_h, pkt_dev->min_in6_saddr.s6_addr, 8); + memcpy(&pkt_dev->min_in6_l, pkt_dev->min_in6_saddr.s6_addr + 8, 8); + pkt_dev->min_in6_h = be64_to_cpu(pkt_dev->min_in6_h); + pkt_dev->min_in6_l = be64_to_cpu(pkt_dev->min_in6_l); + + pkt_dev->cur_in6_saddr = pkt_dev->min_in6_saddr; + if (debug) + pr_debug("src6_min set to: %s\n", buf); + + i += len; + sprintf(pg_result, "OK: src6_min=%s", buf); + return count; + } + if (!strcmp(name, "src6_max")) { + len = strn_len(&user_buffer[i], sizeof(buf) - 1); + if (len < 0) + return len; + + pkt_dev->flags |= F_IPV6; + + if (copy_from_user(buf, &user_buffer[i], len)) + return -EFAULT; + buf[len] = 0; + + in6_pton(buf, -1, pkt_dev->max_in6_saddr.s6_addr, -1, NULL); + snprintf(buf, sizeof(buf), "%pI6c", &pkt_dev->max_in6_saddr); + + memcpy(&pkt_dev->max_in6_h, pkt_dev->max_in6_saddr.s6_addr, 8); + memcpy(&pkt_dev->max_in6_l, pkt_dev->max_in6_saddr.s6_addr + 8, 8); + pkt_dev->max_in6_h = be64_to_cpu(pkt_dev->max_in6_h); + pkt_dev->max_in6_l = be64_to_cpu(pkt_dev->max_in6_l); + + if (debug) + pr_debug("src6_max set to: %s\n", buf); + + i += len; + sprintf(pg_result, "OK: src6_max=%s", buf); + return count; + } if (!strcmp(name, "src6")) { len = strn_len(&user_buffer[i], sizeof(buf) - 1); if (len < 0) @@ -2286,6 +2343,45 @@ static void set_cur_queue_map(struct pktgen_dev *pkt_dev) pkt_dev->cur_queue_map = pkt_dev->cur_queue_map % pkt_dev->odev->real_num_tx_queues; } +/* generate ipv6 source addr */ +static void set_src_in6_addr(struct pktgen_dev *pkt_dev) +{ + u64 min6, max6, rand, i; + struct in6_addr addr6; + __be64 addr_l, *t; + + min6 = pkt_dev->min_in6_l; + max6 = pkt_dev->max_in6_l; + + /* only generate source address in least significant 64 bits range + * most significant 64 bits must be equal + */ + if (pkt_dev->max_in6_h != pkt_dev->min_in6_h || min6 >= max6) + return; + + addr6 = pkt_dev->min_in6_saddr; + t = (__be64 *)addr6.s6_addr + 1; + + if (pkt_dev->flags & F_IPSRC_RND) { + do { + prandom_bytes(&rand, sizeof(rand)); + rand = rand % (max6 - min6) + min6; + addr_l = cpu_to_be64(rand); + memcpy(t, &addr_l, 8); + } while (ipv6_addr_loopback(&addr6) || + ipv6_addr_v4mapped(&addr6) || + ipv6_addr_is_multicast(&addr6)); + } else { + addr6 = pkt_dev->cur_in6_saddr; + i = be64_to_cpu(*t); + if (++i > max6) + i = min6; + addr_l = cpu_to_be64(i); + memcpy(t, &addr_l, 8); + } + pkt_dev->cur_in6_saddr = addr6; +} + /* Increment/randomize headers according to flags and current values * for IP src/dest, UDP src/dst port, MAC-Addr src/dst */ @@ -2454,6 +2550,8 @@ static void mod_cur_headers(struct pktgen_dev *pkt_dev) } } else { /* IPV6 * */ + set_src_in6_addr(pkt_dev); + if (!ipv6_addr_any(&pkt_dev->min_in6_daddr)) { int i; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 44b0894d8ae1..48a7029529c9 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -68,6 +68,7 @@ #include <net/ip6_checksum.h> #include <net/xfrm.h> #include <net/mpls.h> +#include <net/mptcp.h> #include <linux/uaccess.h> #include <trace/events/skb.h> @@ -4109,6 +4110,9 @@ static const u8 skb_ext_type_len[] = { #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) [TC_SKB_EXT] = SKB_EXT_CHUNKSIZEOF(struct tc_skb_ext), #endif +#if IS_ENABLED(CONFIG_MPTCP) + [SKB_EXT_MPTCP] = SKB_EXT_CHUNKSIZEOF(struct mptcp_ext), +#endif }; static __always_inline unsigned int skb_ext_total_length(void) @@ -4123,6 +4127,9 @@ static __always_inline unsigned int skb_ext_total_length(void) #if IS_ENABLED(CONFIG_NET_TC_SKB_EXT) skb_ext_type_len[TC_SKB_EXT] + #endif +#if IS_ENABLED(CONFIG_MPTCP) + skb_ext_type_len[SKB_EXT_MPTCP] + +#endif 0; } @@ -5980,7 +5987,14 @@ static void *skb_ext_get_ptr(struct skb_ext *ext, enum skb_ext_id id) return (void *)ext + (ext->offset[id] * SKB_EXT_ALIGN_VALUE); } -static struct skb_ext *skb_ext_alloc(void) +/** + * __skb_ext_alloc - allocate a new skb extensions storage + * + * Returns the newly allocated pointer. The pointer can later attached to a + * skb via __skb_ext_set(). + * Note: caller must handle the skb_ext as an opaque data. + */ +struct skb_ext *__skb_ext_alloc(void) { struct skb_ext *new = kmem_cache_alloc(skbuff_ext_cache, GFP_ATOMIC); @@ -6021,6 +6035,30 @@ static struct skb_ext *skb_ext_maybe_cow(struct skb_ext *old, } /** + * __skb_ext_set - attach the specified extension storage to this skb + * @skb: buffer + * @id: extension id + * @ext: extension storage previously allocated via __skb_ext_alloc() + * + * Existing extensions, if any, are cleared. + * + * Returns the pointer to the extension. + */ +void *__skb_ext_set(struct sk_buff *skb, enum skb_ext_id id, + struct skb_ext *ext) +{ + unsigned int newlen, newoff = SKB_EXT_CHUNKSIZEOF(*ext); + + skb_ext_put(skb); + newlen = newoff + skb_ext_type_len[id]; + ext->chunks = newlen; + ext->offset[id] = newoff; + skb->extensions = ext; + skb->active_extensions = 1 << id; + return skb_ext_get_ptr(ext, id); +} + +/** * skb_ext_add - allocate space for given extension, COW if needed * @skb: buffer * @id: extension to allocate space for @@ -6053,7 +6091,7 @@ void *skb_ext_add(struct sk_buff *skb, enum skb_ext_id id) } else { newoff = SKB_EXT_CHUNKSIZEOF(*new); - new = skb_ext_alloc(); + new = __skb_ext_alloc(); if (!new) return NULL; } diff --git a/net/core/skmsg.c b/net/core/skmsg.c index ded2d5227678..3866d7e20c07 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -594,6 +594,8 @@ EXPORT_SYMBOL_GPL(sk_psock_destroy); void sk_psock_drop(struct sock *sk, struct sk_psock *psock) { + sock_owned_by_me(sk); + sk_psock_cork_free(psock); sk_psock_zap_ingress(psock); diff --git a/net/core/sock_map.c b/net/core/sock_map.c index eb114ee419b6..8998e356f423 100644 --- a/net/core/sock_map.c +++ b/net/core/sock_map.c @@ -241,8 +241,11 @@ static void sock_map_free(struct bpf_map *map) struct sock *sk; sk = xchg(psk, NULL); - if (sk) + if (sk) { + lock_sock(sk); sock_map_unref(sk, psk); + release_sock(sk); + } } raw_spin_unlock_bh(&stab->lock); rcu_read_unlock(); @@ -862,7 +865,9 @@ static void sock_hash_free(struct bpf_map *map) raw_spin_lock_bh(&bucket->lock); hlist_for_each_entry_safe(elem, node, &bucket->head, node) { hlist_del_rcu(&elem->node); + lock_sock(elem->sk); sock_map_unref(elem->sk, elem); + release_sock(elem->sk); } raw_spin_unlock_bh(&bucket->lock); } diff --git a/net/decnet/af_decnet.c b/net/decnet/af_decnet.c index e19a92a62e14..0a46ea3bddd5 100644 --- a/net/decnet/af_decnet.c +++ b/net/decnet/af_decnet.c @@ -670,7 +670,7 @@ static int dn_create(struct net *net, struct socket *sock, int protocol, { struct sock *sk; - if (protocol < 0 || protocol > SK_PROTOCOL_MAX) + if (protocol < 0 || protocol > U8_MAX) return -EINVAL; if (!net_eq(net, &init_net)) diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index c66abbed4daf..c6d81f2baf4e 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -614,6 +614,32 @@ static int dsa_port_parse_dsa(struct dsa_port *dp) return 0; } +static enum dsa_tag_protocol dsa_get_tag_protocol(struct dsa_port *dp, + struct net_device *master) +{ + enum dsa_tag_protocol tag_protocol = DSA_TAG_PROTO_NONE; + struct dsa_switch *mds, *ds = dp->ds; + unsigned int mdp_upstream; + struct dsa_port *mdp; + + /* It is possible to stack DSA switches onto one another when that + * happens the switch driver may want to know if its tagging protocol + * is going to work in such a configuration. + */ + if (dsa_slave_dev_check(master)) { + mdp = dsa_slave_to_port(master); + mds = mdp->ds; + mdp_upstream = dsa_upstream_port(mds, mdp->index); + tag_protocol = mds->ops->get_tag_protocol(mds, mdp_upstream, + DSA_TAG_PROTO_NONE); + } + + /* If the master device is not itself a DSA slave in a disjoint DSA + * tree, then return immediately. + */ + return ds->ops->get_tag_protocol(ds, dp->index, tag_protocol); +} + static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) { struct dsa_switch *ds = dp->ds; @@ -621,20 +647,21 @@ static int dsa_port_parse_cpu(struct dsa_port *dp, struct net_device *master) const struct dsa_device_ops *tag_ops; enum dsa_tag_protocol tag_protocol; - tag_protocol = ds->ops->get_tag_protocol(ds, dp->index); + tag_protocol = dsa_get_tag_protocol(dp, master); tag_ops = dsa_tag_driver_get(tag_protocol); if (IS_ERR(tag_ops)) { if (PTR_ERR(tag_ops) == -ENOPROTOOPT) return -EPROBE_DEFER; dev_warn(ds->dev, "No tagger for this switch\n"); + dp->master = NULL; return PTR_ERR(tag_ops); } + dp->master = master; dp->type = DSA_PORT_TYPE_CPU; dp->filter = tag_ops->filter; dp->rcv = tag_ops->rcv; dp->tag_ops = tag_ops; - dp->master = master; dp->dst = dst; return 0; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 8a162605b861..a7662e7a691d 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -157,6 +157,7 @@ extern const struct dsa_device_ops notag_netdev_ops; void dsa_slave_mii_bus_init(struct dsa_switch *ds); int dsa_slave_create(struct dsa_port *dp); void dsa_slave_destroy(struct net_device *slave_dev); +bool dsa_slave_dev_check(const struct net_device *dev); int dsa_slave_suspend(struct net_device *slave_dev); int dsa_slave_resume(struct net_device *slave_dev); int dsa_slave_register_notifier(void); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index c1828bdc79dc..088c886e609e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -22,8 +22,6 @@ #include "dsa_priv.h" -static bool dsa_slave_dev_check(const struct net_device *dev); - /* slave mii_bus handling ***************************************************/ static int dsa_slave_phy_read(struct mii_bus *bus, int addr, int reg) { @@ -1473,7 +1471,7 @@ void dsa_slave_destroy(struct net_device *slave_dev) free_netdev(slave_dev); } -static bool dsa_slave_dev_check(const struct net_device *dev) +bool dsa_slave_dev_check(const struct net_device *dev) { return dev->netdev_ops == &dsa_slave_netdev_ops; } 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_qca.c b/net/dsa/tag_qca.c index c95885215525..c8a128c9e5e0 100644 --- a/net/dsa/tag_qca.c +++ b/net/dsa/tag_qca.c @@ -33,9 +33,6 @@ 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) return NULL; diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c index 4ca96c7b86b3..86b79f9bc08d 100644 --- a/net/ethtool/netlink.c +++ b/net/ethtool/netlink.c @@ -319,9 +319,10 @@ static int ethnl_default_doit(struct sk_buff *skb, struct genl_info *info) rtnl_unlock(); if (ret < 0) goto err_cleanup; - reply_len = ops->reply_size(req_info, reply_data); + ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; + reply_len = ret; ret = -ENOMEM; rskb = ethnl_reply_init(reply_len, req_info->dev, ops->reply_cmd, ops->hdr_attr, info, &reply_payload); @@ -472,8 +473,8 @@ static int ethnl_default_start(struct netlink_callback *cb) return -ENOMEM; reply_data = kmalloc(ops->reply_data_size, GFP_KERNEL); if (!reply_data) { - kfree(req_info); - return -ENOMEM; + ret = -ENOMEM; + goto free_req_info; } ret = ethnl_default_parse(req_info, cb->nlh, sock_net(cb->skb->sk), ops, @@ -487,7 +488,7 @@ static int ethnl_default_start(struct netlink_callback *cb) req_info->dev = NULL; } if (ret < 0) - return ret; + goto free_reply_data; ctx->ops = ops; ctx->req_info = req_info; @@ -496,6 +497,13 @@ static int ethnl_default_start(struct netlink_callback *cb) ctx->pos_idx = 0; return 0; + +free_reply_data: + kfree(reply_data); +free_req_info: + kfree(req_info); + + return ret; } /* default ->done() handler for GET requests */ @@ -548,9 +556,10 @@ static void ethnl_default_notify(struct net_device *dev, unsigned int cmd, ret = ops->prepare_data(req_info, reply_data, NULL); if (ret < 0) goto err_cleanup; - reply_len = ops->reply_size(req_info, reply_data); + ret = ops->reply_size(req_info, reply_data); if (ret < 0) goto err_cleanup; + reply_len = ret; ret = -ENOMEM; skb = genlmsg_new(reply_len, GFP_KERNEL); if (!skb) diff --git a/net/ethtool/strset.c b/net/ethtool/strset.c index 9f2243329015..82a059c13c1c 100644 --- a/net/ethtool/strset.c +++ b/net/ethtool/strset.c @@ -239,6 +239,7 @@ static int strset_prepare_data(const struct ethnl_req_info *req_base, return -EINVAL; } } + return 0; } ret = ethnl_ops_begin(dev); diff --git a/net/hsr/hsr_framereg.c b/net/hsr/hsr_framereg.c index 27dc65d7de67..364ea2cc028e 100644 --- a/net/hsr/hsr_framereg.c +++ b/net/hsr/hsr_framereg.c @@ -35,7 +35,6 @@ static bool seq_nr_after(u16 a, u16 b) } #define seq_nr_before(a, b) seq_nr_after((b), (a)) -#define seq_nr_after_or_eq(a, b) (!seq_nr_before((a), (b))) #define seq_nr_before_or_eq(a, b) (!seq_nr_after((a), (b))) bool hsr_addr_is_self(struct hsr_priv *hsr, unsigned char *addr) diff --git a/net/hsr/hsr_main.h b/net/hsr/hsr_main.h index d40de84a637f..754d84b217f0 100644 --- a/net/hsr/hsr_main.h +++ b/net/hsr/hsr_main.h @@ -191,7 +191,7 @@ void hsr_debugfs_term(struct hsr_priv *priv); void hsr_debugfs_create_root(void); void hsr_debugfs_remove_root(void); #else -static inline void void hsr_debugfs_rename(struct net_device *dev) +static inline void hsr_debugfs_rename(struct net_device *dev) { } static inline void hsr_debugfs_init(struct hsr_priv *priv, diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index fc816b187170..f96bd489b362 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -378,6 +378,17 @@ config INET_ESP_OFFLOAD If unsure, say N. +config INET_ESPINTCP + bool "IP: ESP in TCP encapsulation (RFC 8229)" + depends on XFRM && INET_ESP + select STREAM_PARSER + select NET_SOCK_MSG + help + Support for RFC 8229 encapsulation of ESP and IKE over + TCP/IPv4 sockets. + + If unsure, say N. + config INET_IPCOMP tristate "IP: IPComp transformation" select INET_XFRM_TUNNEL diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 5c967764041f..103c7d599a3c 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -18,6 +18,8 @@ #include <net/icmp.h> #include <net/protocol.h> #include <net/udp.h> +#include <net/tcp.h> +#include <net/espintcp.h> #include <linux/highmem.h> @@ -117,6 +119,132 @@ static void esp_ssg_unref(struct xfrm_state *x, void *tmp) put_page(sg_page(sg)); } +#ifdef CONFIG_INET_ESPINTCP +struct esp_tcp_sk { + struct sock *sk; + struct rcu_head rcu; +}; + +static void esp_free_tcp_sk(struct rcu_head *head) +{ + struct esp_tcp_sk *esk = container_of(head, struct esp_tcp_sk, rcu); + + sock_put(esk->sk); + kfree(esk); +} + +static struct sock *esp_find_tcp_sk(struct xfrm_state *x) +{ + struct xfrm_encap_tmpl *encap = x->encap; + struct esp_tcp_sk *esk; + __be16 sport, dport; + struct sock *nsk; + struct sock *sk; + + sk = rcu_dereference(x->encap_sk); + if (sk && sk->sk_state == TCP_ESTABLISHED) + return sk; + + spin_lock_bh(&x->lock); + sport = encap->encap_sport; + dport = encap->encap_dport; + nsk = rcu_dereference_protected(x->encap_sk, + lockdep_is_held(&x->lock)); + if (sk && sk == nsk) { + esk = kmalloc(sizeof(*esk), GFP_ATOMIC); + if (!esk) { + spin_unlock_bh(&x->lock); + return ERR_PTR(-ENOMEM); + } + RCU_INIT_POINTER(x->encap_sk, NULL); + esk->sk = sk; + call_rcu(&esk->rcu, esp_free_tcp_sk); + } + spin_unlock_bh(&x->lock); + + sk = inet_lookup_established(xs_net(x), &tcp_hashinfo, x->id.daddr.a4, + dport, x->props.saddr.a4, sport, 0); + if (!sk) + return ERR_PTR(-ENOENT); + + if (!tcp_is_ulp_esp(sk)) { + sock_put(sk); + return ERR_PTR(-EINVAL); + } + + spin_lock_bh(&x->lock); + nsk = rcu_dereference_protected(x->encap_sk, + lockdep_is_held(&x->lock)); + if (encap->encap_sport != sport || + encap->encap_dport != dport) { + sock_put(sk); + sk = nsk ?: ERR_PTR(-EREMCHG); + } else if (sk == nsk) { + sock_put(sk); + } else { + rcu_assign_pointer(x->encap_sk, sk); + } + spin_unlock_bh(&x->lock); + + return sk; +} + +static int esp_output_tcp_finish(struct xfrm_state *x, struct sk_buff *skb) +{ + struct sock *sk; + int err; + + rcu_read_lock(); + + sk = esp_find_tcp_sk(x); + err = PTR_ERR_OR_ZERO(sk); + if (err) + goto out; + + bh_lock_sock(sk); + if (sock_owned_by_user(sk)) + err = espintcp_queue_out(sk, skb); + else + err = espintcp_push_skb(sk, skb); + bh_unlock_sock(sk); + +out: + rcu_read_unlock(); + return err; +} + +static int esp_output_tcp_encap_cb(struct net *net, struct sock *sk, + struct sk_buff *skb) +{ + struct dst_entry *dst = skb_dst(skb); + struct xfrm_state *x = dst->xfrm; + + return esp_output_tcp_finish(x, skb); +} + +static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) +{ + int err; + + local_bh_disable(); + err = xfrm_trans_queue_net(xs_net(x), skb, esp_output_tcp_encap_cb); + local_bh_enable(); + + /* EINPROGRESS just happens to do the right thing. It + * actually means that the skb has been consumed and + * isn't coming back. + */ + return err ?: -EINPROGRESS; +} +#else +static int esp_output_tail_tcp(struct xfrm_state *x, struct sk_buff *skb) +{ + kfree_skb(skb); + + return -EOPNOTSUPP; +} +#endif + static void esp_output_done(struct crypto_async_request *base, int err) { struct sk_buff *skb = base->data; @@ -147,7 +275,11 @@ static void esp_output_done(struct crypto_async_request *base, int err) secpath_reset(skb); xfrm_dev_resume(skb); } else { - xfrm_output_resume(skb, err); + if (!err && + x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) + esp_output_tail_tcp(x, skb); + else + xfrm_output_resume(skb, err); } } @@ -225,45 +357,100 @@ static void esp_output_fill_trailer(u8 *tail, int tfclen, int plen, __u8 proto) tail[plen - 1] = proto; } -static int esp_output_udp_encap(struct xfrm_state *x, struct sk_buff *skb, struct esp_info *esp) +static struct ip_esp_hdr *esp_output_udp_encap(struct sk_buff *skb, + int encap_type, + struct esp_info *esp, + __be16 sport, + __be16 dport) { - int encap_type; struct udphdr *uh; __be32 *udpdata32; - __be16 sport, dport; - struct xfrm_encap_tmpl *encap = x->encap; - struct ip_esp_hdr *esph = esp->esph; unsigned int len; - spin_lock_bh(&x->lock); - sport = encap->encap_sport; - dport = encap->encap_dport; - encap_type = encap->encap_type; - spin_unlock_bh(&x->lock); - len = skb->len + esp->tailen - skb_transport_offset(skb); - if (len + sizeof(struct iphdr) >= IP_MAX_MTU) - return -EMSGSIZE; + if (len + sizeof(struct iphdr) > IP_MAX_MTU) + return ERR_PTR(-EMSGSIZE); - uh = (struct udphdr *)esph; + uh = (struct udphdr *)esp->esph; uh->source = sport; uh->dest = dport; uh->len = htons(len); uh->check = 0; + *skb_mac_header(skb) = IPPROTO_UDP; + + if (encap_type == UDP_ENCAP_ESPINUDP_NON_IKE) { + udpdata32 = (__be32 *)(uh + 1); + udpdata32[0] = udpdata32[1] = 0; + return (struct ip_esp_hdr *)(udpdata32 + 2); + } + + return (struct ip_esp_hdr *)(uh + 1); +} + +#ifdef CONFIG_INET_ESPINTCP +static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, + struct sk_buff *skb, + struct esp_info *esp) +{ + __be16 *lenp = (void *)esp->esph; + struct ip_esp_hdr *esph; + unsigned int len; + struct sock *sk; + + len = skb->len + esp->tailen - skb_transport_offset(skb); + if (len > IP_MAX_MTU) + return ERR_PTR(-EMSGSIZE); + + rcu_read_lock(); + sk = esp_find_tcp_sk(x); + rcu_read_unlock(); + + if (IS_ERR(sk)) + return ERR_CAST(sk); + + *lenp = htons(len); + esph = (struct ip_esp_hdr *)(lenp + 1); + + return esph; +} +#else +static struct ip_esp_hdr *esp_output_tcp_encap(struct xfrm_state *x, + struct sk_buff *skb, + struct esp_info *esp) +{ + return ERR_PTR(-EOPNOTSUPP); +} +#endif + +static int esp_output_encap(struct xfrm_state *x, struct sk_buff *skb, + struct esp_info *esp) +{ + struct xfrm_encap_tmpl *encap = x->encap; + struct ip_esp_hdr *esph; + __be16 sport, dport; + int encap_type; + + spin_lock_bh(&x->lock); + sport = encap->encap_sport; + dport = encap->encap_dport; + encap_type = encap->encap_type; + spin_unlock_bh(&x->lock); + switch (encap_type) { default: case UDP_ENCAP_ESPINUDP: - esph = (struct ip_esp_hdr *)(uh + 1); - break; case UDP_ENCAP_ESPINUDP_NON_IKE: - udpdata32 = (__be32 *)(uh + 1); - udpdata32[0] = udpdata32[1] = 0; - esph = (struct ip_esp_hdr *)(udpdata32 + 2); + esph = esp_output_udp_encap(skb, encap_type, esp, sport, dport); + break; + case TCP_ENCAP_ESPINTCP: + esph = esp_output_tcp_encap(x, skb, esp); break; } - *skb_mac_header(skb) = IPPROTO_UDP; + if (IS_ERR(esph)) + return PTR_ERR(esph); + esp->esph = esph; return 0; @@ -279,9 +466,9 @@ int esp_output_head(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * struct sk_buff *trailer; int tailen = esp->tailen; - /* this is non-NULL only with UDP Encapsulation */ + /* this is non-NULL only with TCP/UDP Encapsulation */ if (x->encap) { - int err = esp_output_udp_encap(x, skb, esp); + int err = esp_output_encap(x, skb, esp); if (err < 0) return err; @@ -474,6 +661,9 @@ int esp_output_tail(struct xfrm_state *x, struct sk_buff *skb, struct esp_info * if (sg != dsg) esp_ssg_unref(x, tmp); + if (!err && x->encap && x->encap->encap_type == TCP_ENCAP_ESPINTCP) + err = esp_output_tail_tcp(x, skb); + error_free: kfree(tmp); error: @@ -600,7 +790,23 @@ int esp_input_done2(struct sk_buff *skb, int err) if (x->encap) { struct xfrm_encap_tmpl *encap = x->encap; + struct tcphdr *th = (void *)(skb_network_header(skb) + ihl); struct udphdr *uh = (void *)(skb_network_header(skb) + ihl); + __be16 source; + + switch (x->encap->encap_type) { + case TCP_ENCAP_ESPINTCP: + source = th->source; + break; + case UDP_ENCAP_ESPINUDP: + case UDP_ENCAP_ESPINUDP_NON_IKE: + source = uh->source; + break; + default: + WARN_ON_ONCE(1); + err = -EINVAL; + goto out; + } /* * 1) if the NAT-T peer's IP or port changed then @@ -609,11 +815,11 @@ int esp_input_done2(struct sk_buff *skb, int err) * SRC ports. */ if (iph->saddr != x->props.saddr.a4 || - uh->source != encap->encap_sport) { + source != encap->encap_sport) { xfrm_address_t ipaddr; ipaddr.a4 = iph->saddr; - km_new_mapping(x, &ipaddr, uh->source); + km_new_mapping(x, &ipaddr, source); /* XXX: perhaps add an extra * policy check here, to see @@ -988,6 +1194,14 @@ static int esp_init_state(struct xfrm_state *x) case UDP_ENCAP_ESPINUDP_NON_IKE: x->props.header_len += sizeof(struct udphdr) + 2 * sizeof(u32); break; +#ifdef CONFIG_INET_ESPINTCP + case TCP_ENCAP_ESPINTCP: + /* only the length field, TCP encap is done by + * the socket + */ + x->props.header_len += 2; + break; +#endif } } diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index a68b5e21ec51..c092e9a55790 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -16,6 +16,9 @@ struct fib_alias { u8 fa_slen; u32 tb_id; s16 fa_default; + u8 offload:1, + trap:1, + unused:6; struct rcu_head rcu; }; @@ -35,9 +38,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg, int fib_nh_match(struct fib_config *cfg, struct fib_info *fi, struct netlink_ext_ack *extack); bool fib_metrics_match(struct fib_config *cfg, struct fib_info *fi); -int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, u32 tb_id, - u8 type, __be32 dst, int dst_len, u8 tos, struct fib_info *fi, - unsigned int); +int fib_dump_info(struct sk_buff *skb, u32 pid, u32 seq, int event, + struct fib_rt_info *fri, unsigned int flags); void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index f1888c683426..a803cdd9400a 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -504,6 +504,7 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, int dst_len, u32 tb_id, const struct nl_info *info, unsigned int nlm_flags) { + struct fib_rt_info fri; struct sk_buff *skb; u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; int err = -ENOBUFS; @@ -512,9 +513,15 @@ void rtmsg_fib(int event, __be32 key, struct fib_alias *fa, if (!skb) goto errout; - err = fib_dump_info(skb, info->portid, seq, event, tb_id, - fa->fa_type, key, dst_len, - fa->fa_tos, fa->fa_info, nlm_flags); + fri.fi = fa->fa_info; + fri.tb_id = tb_id; + fri.dst = key; + fri.dst_len = dst_len; + fri.tos = fa->fa_tos; + fri.type = fa->fa_type; + fri.offload = fa->offload; + fri.trap = fa->trap; + err = fib_dump_info(skb, info->portid, seq, event, &fri, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in fib_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -1725,10 +1732,11 @@ static int fib_add_multipath(struct sk_buff *skb, struct fib_info *fi) #endif int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, - u32 tb_id, u8 type, __be32 dst, int dst_len, u8 tos, - struct fib_info *fi, unsigned int flags) + struct fib_rt_info *fri, unsigned int flags) { - unsigned int nhs = fib_info_num_path(fi); + unsigned int nhs = fib_info_num_path(fri->fi); + struct fib_info *fi = fri->fi; + u32 tb_id = fri->tb_id; struct nlmsghdr *nlh; struct rtmsg *rtm; @@ -1738,22 +1746,22 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET; - rtm->rtm_dst_len = dst_len; + rtm->rtm_dst_len = fri->dst_len; rtm->rtm_src_len = 0; - rtm->rtm_tos = tos; + rtm->rtm_tos = fri->tos; if (tb_id < 256) rtm->rtm_table = tb_id; else rtm->rtm_table = RT_TABLE_COMPAT; if (nla_put_u32(skb, RTA_TABLE, tb_id)) goto nla_put_failure; - rtm->rtm_type = type; + rtm->rtm_type = fri->type; rtm->rtm_flags = fi->fib_flags; rtm->rtm_scope = fi->fib_scope; rtm->rtm_protocol = fi->fib_protocol; if (rtm->rtm_dst_len && - nla_put_in_addr(skb, RTA_DST, dst)) + nla_put_in_addr(skb, RTA_DST, fri->dst)) goto nla_put_failure; if (fi->fib_priority && nla_put_u32(skb, RTA_PRIORITY, fi->fib_priority)) @@ -1795,6 +1803,11 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, goto nla_put_failure; } + if (fri->offload) + rtm->rtm_flags |= RTM_F_OFFLOAD; + if (fri->trap) + rtm->rtm_flags |= RTM_F_TRAP; + nlmsg_end(skb, nlh); return 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b92a42433a7d..ff0c24371e33 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1012,6 +1012,52 @@ static struct fib_alias *fib_find_alias(struct hlist_head *fah, u8 slen, return NULL; } +static struct fib_alias * +fib_find_matching_alias(struct net *net, const struct fib_rt_info *fri) +{ + u8 slen = KEYLENGTH - fri->dst_len; + struct key_vector *l, *tp; + struct fib_table *tb; + struct fib_alias *fa; + struct trie *t; + + tb = fib_get_table(net, fri->tb_id); + if (!tb) + return NULL; + + t = (struct trie *)tb->tb_data; + l = fib_find_node(t, &tp, be32_to_cpu(fri->dst)); + if (!l) + return NULL; + + hlist_for_each_entry_rcu(fa, &l->leaf, fa_list) { + if (fa->fa_slen == slen && fa->tb_id == fri->tb_id && + fa->fa_tos == fri->tos && fa->fa_info == fri->fi && + fa->fa_type == fri->type) + return fa; + } + + return NULL; +} + +void fib_alias_hw_flags_set(struct net *net, const struct fib_rt_info *fri) +{ + struct fib_alias *fa_match; + + rcu_read_lock(); + + fa_match = fib_find_matching_alias(net, fri); + if (!fa_match) + goto out; + + fa_match->offload = fri->offload; + fa_match->trap = fri->trap; + +out: + rcu_read_unlock(); +} +EXPORT_SYMBOL_GPL(fib_alias_hw_flags_set); + static void trie_rebalance(struct trie *t, struct key_vector *tn) { while (!IS_TRIE(tn)) @@ -1220,24 +1266,29 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_slen = fa->fa_slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; + new_fa->offload = 0; + new_fa->trap = 0; + + hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); if (fib_find_alias(&l->leaf, fa->fa_slen, 0, 0, - tb->tb_id, true) == fa) { + tb->tb_id, true) == new_fa) { enum fib_event_type fib_event; fib_event = FIB_EVENT_ENTRY_REPLACE; err = call_fib_entry_notifiers(net, fib_event, key, plen, new_fa, extack); - if (err) + if (err) { + hlist_replace_rcu(&new_fa->fa_list, + &fa->fa_list); goto out_free_new_fa; + } } rtmsg_fib(RTM_NEWROUTE, htonl(key), new_fa, plen, tb->tb_id, &cfg->fc_nlinfo, nlflags); - hlist_replace_rcu(&fa->fa_list, &new_fa->fa_list); - alias_free_mem_rcu(fa); fib_release_info(fi_drop); @@ -1275,6 +1326,8 @@ int fib_table_insert(struct net *net, struct fib_table *tb, new_fa->fa_slen = slen; new_fa->tb_id = tb->tb_id; new_fa->fa_default = -1; + new_fa->offload = 0; + new_fa->trap = 0; /* Insert new entry to the list. */ err = fib_insert_alias(t, tp, l, new_fa, fa, key); @@ -2191,14 +2244,20 @@ static int fn_trie_dump_leaf(struct key_vector *l, struct fib_table *tb, if (filter->dump_routes) { if (!s_fa) { + struct fib_rt_info fri; + + fri.fi = fi; + fri.tb_id = tb->tb_id; + fri.dst = xkey; + fri.dst_len = KEYLENGTH - fa->fa_slen; + fri.tos = fa->fa_tos; + fri.type = fa->fa_type; + fri.offload = fa->offload; + fri.trap = fa->trap; err = fib_dump_info(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, - RTM_NEWROUTE, - tb->tb_id, fa->fa_type, - xkey, - KEYLENGTH - fa->fa_slen, - fa->fa_tos, fi, flags); + RTM_NEWROUTE, &fri, flags); if (err < 0) goto stop; } @@ -2238,6 +2297,12 @@ 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; diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 18c0d5bffe12..a4db79b1b643 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -610,12 +610,6 @@ no_route: } EXPORT_SYMBOL_GPL(inet_csk_route_child_sock); -#if IS_ENABLED(CONFIG_IPV6) -#define AF_INET_FAMILY(fam) ((fam) == AF_INET) -#else -#define AF_INET_FAMILY(fam) true -#endif - /* Decide when to expire the request and when to resend SYN-ACK */ static inline void syn_ack_recalc(struct request_sock *req, const int thresh, const int max_retries, @@ -770,6 +764,18 @@ void inet_csk_reqsk_queue_hash_add(struct sock *sk, struct request_sock *req, } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_hash_add); +static void inet_clone_ulp(const struct request_sock *req, struct sock *newsk, + const gfp_t priority) +{ + struct inet_connection_sock *icsk = inet_csk(newsk); + + if (!icsk->icsk_ulp_ops) + return; + + if (icsk->icsk_ulp_ops->clone) + icsk->icsk_ulp_ops->clone(req, newsk, priority); +} + /** * inet_csk_clone_lock - clone an inet socket, and lock its clone * @sk: the socket to clone @@ -810,6 +816,8 @@ struct sock *inet_csk_clone_lock(const struct sock *sk, /* Deinitialize accept_queue to trap illegal accesses. */ memset(&newicsk->icsk_accept_queue, 0, sizeof(newicsk->icsk_accept_queue)); + inet_clone_ulp(req, newsk, priority); + security_inet_csk_clone(newsk, req); } return newsk; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 14db1e0b8a6e..d84819893db9 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -240,8 +240,8 @@ static int ip_finish_output2(struct net *net, struct sock *sk, struct sk_buff *s static int ip_finish_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb, unsigned int mtu) { + struct sk_buff *segs, *nskb; netdev_features_t features; - struct sk_buff *segs; int ret = 0; /* common case: seglen is <= mtu @@ -272,8 +272,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, consume_skb(skb); - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); @@ -281,8 +280,7 @@ static int ip_finish_output_gso(struct net *net, struct sock *sk, if (err && ret == 0) ret = err; - segs = nskb; - } while (segs); + } return ret; } 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/route.c b/net/ipv4/route.c index 87e979f2b74a..2010888e68ca 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -3223,16 +3223,41 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, skb_reset_mac_header(skb); if (rtm->rtm_flags & RTM_F_FIB_MATCH) { + struct fib_rt_info fri; + if (!res.fi) { err = fib_props[res.type].error; if (!err) err = -EHOSTUNREACH; goto errout_rcu; } + fri.fi = res.fi; + fri.tb_id = table_id; + fri.dst = res.prefix; + fri.dst_len = res.prefixlen; + fri.tos = fl4.flowi4_tos; + fri.type = rt->rt_type; + fri.offload = 0; + fri.trap = 0; + if (res.fa_head) { + struct fib_alias *fa; + + hlist_for_each_entry_rcu(fa, res.fa_head, fa_list) { + u8 slen = 32 - fri.dst_len; + + if (fa->fa_slen == slen && + fa->tb_id == fri.tb_id && + fa->fa_tos == fri.tos && + fa->fa_info == res.fi && + fa->fa_type == fri.type) { + fri.offload = fa->offload; + fri.trap = fa->trap; + break; + } + } + } err = fib_dump_info(skb, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, RTM_NEWROUTE, table_id, - rt->rt_type, res.prefix, res.prefixlen, - fl4.flowi4_tos, res.fi, 0); + nlh->nlmsg_seq, RTM_NEWROUTE, &fri, 0); } else { err = rt_fill_info(net, dst, src, rt, table_id, &fl4, skb, NETLINK_CB(in_skb).portid, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index f09fbc85b108..6711a97de3ce 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -690,8 +690,8 @@ static bool tcp_should_autocork(struct sock *sk, struct sk_buff *skb, refcount_read(&sk->sk_wmem_alloc) > skb->truesize; } -static void tcp_push(struct sock *sk, int flags, int mss_now, - int nonagle, int size_goal) +void tcp_push(struct sock *sk, int flags, int mss_now, + int nonagle, int size_goal) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -925,7 +925,7 @@ static unsigned int tcp_xmit_size_goal(struct sock *sk, u32 mss_now, return max(size_goal, mss_now); } -static int tcp_send_mss(struct sock *sk, int *size_goal, int flags) +int tcp_send_mss(struct sock *sk, int *size_goal, int flags) { int mss_now; diff --git a/net/ipv4/tcp_bpf.c b/net/ipv4/tcp_bpf.c index e38705165ac9..8a01428f80c1 100644 --- a/net/ipv4/tcp_bpf.c +++ b/net/ipv4/tcp_bpf.c @@ -121,14 +121,14 @@ int tcp_bpf_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, struct sk_psock *psock; int copied, ret; - 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 (unlikely(flags & MSG_ERRQUEUE)) + return inet_recv_error(sk, msg, len, addr_len); + if (!skb_queue_empty(&sk->sk_receive_queue) && + sk_psock_queue_empty(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 +139,7 @@ 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); @@ -315,10 +315,7 @@ 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_input.c b/net/ipv4/tcp_input.c index 1d1e3493965f..358365598216 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -915,9 +915,10 @@ 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; } @@ -1422,7 +1423,7 @@ static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) goto fallback; - if (!tcp_skb_can_collapse_to(prev)) + if (!tcp_skb_can_collapse(prev, skb)) goto fallback; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && @@ -1727,8 +1728,11 @@ 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++; } @@ -4420,6 +4424,9 @@ static bool tcp_try_coalesce(struct sock *sk, if (TCP_SKB_CB(from)->seq != TCP_SKB_CB(to)->end_seq) return false; + if (!mptcp_skb_can_collapse(to, from)) + return false; + #ifdef CONFIG_TLS_DEVICE if (from->decrypted != to->decrypted) return false; @@ -4929,7 +4936,7 @@ restart: /* The first skb to collapse is: * - not SYN/FIN and * - bloated or contains data before "start" or - * overlaps to the next one. + * overlaps to the next one and mptcp allow collapsing. */ if (!(TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN)) && (tcp_win_from_space(sk, skb->truesize) > skb->len || @@ -4938,7 +4945,7 @@ restart: break; } - if (n && n != tail && + if (n && n != tail && mptcp_skb_can_collapse(skb, n) && TCP_SKB_CB(skb)->end_seq != TCP_SKB_CB(n)->seq) { end_of_skbs = false; break; @@ -4971,6 +4978,7 @@ restart: else __skb_queue_tail(&tmp, nskb); /* defer rbtree insertion */ skb_set_owner_r(nskb, sk); + mptcp_skb_ext_move(nskb, skb); /* Copy data, releasing collapsed skbs. */ while (copy > 0) { @@ -4990,6 +4998,7 @@ restart: skb = tcp_collapse_one(sk, skb, list, root); if (!skb || skb == tail || + !mptcp_skb_can_collapse(nskb, skb) || (TCP_SKB_CB(skb)->tcp_flags & (TCPHDR_SYN | TCPHDR_FIN))) goto end; #ifdef CONFIG_TLS_DEVICE diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 317ccca548a2..df1166b76126 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1426,7 +1426,7 @@ struct request_sock_ops tcp_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { .mss_clamp = TCP_MSS_DEFAULT, #ifdef CONFIG_TCP_MD5SIG .req_md5_lookup = tcp_v4_md5_lookup, diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 377cfab422df..786978cb2db7 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -754,13 +754,17 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb eff_sacks = tp->rx_opt.num_sacks + tp->rx_opt.dsack; if (unlikely(eff_sacks)) { const unsigned int remaining = MAX_TCP_OPTION_SPACE - size; + if (unlikely(remaining < TCPOLEN_SACK_BASE_ALIGNED + + TCPOLEN_SACK_PERBLOCK)) + return size; + opts->num_sack_blocks = min_t(unsigned int, eff_sacks, (remaining - TCPOLEN_SACK_BASE_ALIGNED) / TCPOLEN_SACK_PERBLOCK); - if (likely(opts->num_sack_blocks)) - size += TCPOLEN_SACK_BASE_ALIGNED + - opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; + + size += TCPOLEN_SACK_BASE_ALIGNED + + opts->num_sack_blocks * TCPOLEN_SACK_PERBLOCK; } return size; @@ -2865,7 +2869,7 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, if (!tcp_can_collapse(sk, skb)) break; - if (!tcp_skb_can_collapse_to(to)) + if (!tcp_skb_can_collapse(to, skb)) break; space -= skb->len; diff --git a/net/ipv4/tcp_ulp.c b/net/ipv4/tcp_ulp.c index 12ab5db2b71c..38d3ad141161 100644 --- a/net/ipv4/tcp_ulp.c +++ b/net/ipv4/tcp_ulp.c @@ -99,17 +99,19 @@ void tcp_get_available_ulp(char *buf, size_t maxlen) rcu_read_unlock(); } -void tcp_update_ulp(struct sock *sk, struct proto *proto) +void tcp_update_ulp(struct sock *sk, struct proto *proto, + void (*write_space)(struct sock *sk)) { struct inet_connection_sock *icsk = inet_csk(sk); if (!icsk->icsk_ulp_ops) { + sk->sk_write_space = write_space; sk->sk_prot = proto; return; } if (icsk->icsk_ulp_ops->update) - icsk->icsk_ulp_ops->update(sk, proto); + icsk->icsk_ulp_ops->update(sk, proto, write_space); } void tcp_cleanup_ulp(struct sock *sk) diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 93a355b6b092..e4fd4408b775 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1708,7 +1708,8 @@ busy_check: /* sk_queue is empty, reader_queue may contain peeked packets */ } while (timeo && - !__skb_wait_for_more_packets(sk, &error, &timeo, + !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, + &error, &timeo, (struct sk_buff *)sk_queue)); *err = error; @@ -2104,8 +2105,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET); __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, true); - for (skb = segs; skb; skb = next) { - next = skb->next; + skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); ret = udp_queue_rcv_one_skb(sk, skb); if (ret > 0) diff --git a/net/ipv4/xfrm4_protocol.c b/net/ipv4/xfrm4_protocol.c index 8a4285712808..ea595c8549c7 100644 --- a/net/ipv4/xfrm4_protocol.c +++ b/net/ipv4/xfrm4_protocol.c @@ -72,6 +72,14 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, if (!head) goto out; + if (!skb_dst(skb)) { + const struct iphdr *iph = ip_hdr(skb); + + if (ip_route_input_noref(skb, iph->daddr, iph->saddr, + iph->tos, skb->dev)) + goto drop; + } + for_each_protocol_rcu(*head, handler) if ((ret = handler->input_handler(skb, nexthdr, spi, encap_type)) != -EINVAL) return ret; @@ -79,6 +87,7 @@ int xfrm4_rcv_encap(struct sk_buff *skb, int nexthdr, __be32 spi, out: icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +drop: kfree_skb(skb); return 0; } diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 0253b702afb7..4fbdc60b4e07 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -5576,6 +5576,13 @@ static int rt6_fill_node(struct net *net, struct sk_buff *skb, expires -= jiffies; } + if (!dst) { + if (rt->offload) + rtm->rtm_flags |= RTM_F_OFFLOAD; + if (rt->trap) + rtm->rtm_flags |= RTM_F_TRAP; + } + if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 95e4e1e95db2..5b5260103b65 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -75,7 +75,7 @@ static void tcp_v6_reqsk_send_ack(const struct sock *sk, struct sk_buff *skb, static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb); static const struct inet_connection_sock_af_ops ipv6_mapped; -static const struct inet_connection_sock_af_ops ipv6_specific; +const struct inet_connection_sock_af_ops ipv6_specific; #ifdef CONFIG_TCP_MD5SIG static const struct tcp_sock_af_ops tcp_sock_ipv6_specific; static const struct tcp_sock_af_ops tcp_sock_ipv6_mapped_specific; @@ -819,7 +819,7 @@ struct request_sock_ops tcp6_request_sock_ops __read_mostly = { .syn_ack_timeout = tcp_syn_ack_timeout, }; -static const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { +const struct tcp_request_sock_ops tcp_request_sock_ipv6_ops = { .mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr), #ifdef CONFIG_TCP_MD5SIG @@ -1794,7 +1794,7 @@ static struct timewait_sock_ops tcp6_timewait_sock_ops = { .twsk_destructor = tcp_twsk_destructor, }; -static const struct inet_connection_sock_af_ops ipv6_specific = { +const struct inet_connection_sock_af_ops ipv6_specific = { .queue_xmit = inet6_csk_xmit, .send_check = tcp_v6_send_check, .rebuild_header = inet6_sk_rebuild_header, diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9fec580c968e..5dc439a391fe 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -690,8 +690,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) __skb_push(skb, -skb_mac_offset(skb)); segs = udp_rcv_segment(sk, skb, false); - for (skb = segs; skb; skb = next) { - next = skb->next; + skb_list_walk_safe(segs, skb, next) { __skb_pull(skb, skb_transport_offset(skb)); ret = udpv6_queue_rcv_one_skb(sk, skb); diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 4fb7f1f12109..000c742d0527 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -2954,6 +2954,28 @@ 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 +4045,7 @@ 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/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 68af62306385..d69983370381 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 diff --git a/net/mac80211/tkip.c b/net/mac80211/tkip.c index 727dc9f3f3b3..e7f57bb18f6e 100644 --- a/net/mac80211/tkip.c +++ b/net/mac80211/tkip.c @@ -263,9 +263,21 @@ int ieee80211_tkip_decrypt_data(struct arc4_ctx *ctx, 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) { diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index a8a7306a1f56..4bd1faf4f779 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -3949,18 +3949,15 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, } } - next = skb; - while (next) { - skb = next; - next = skb->next; - - skb->prev = NULL; - skb->next = NULL; + skb_list_walk_safe(skb, skb, next) { + skb_mark_not_on_list(skb); skb = ieee80211_build_hdr(sdata, skb, info_flags, sta, ctrl_flags); - if (IS_ERR(skb)) + if (IS_ERR(skb)) { + kfree_skb_list(next); goto out; + } ieee80211_tx_stats(dev, skb->len); diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index ad3fd7f1da75..e37102546be6 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -64,6 +64,17 @@ enum { NCSI_MODE_MAX }; +/* Supported media status bits for Mellanox Mac affinity command. + * Bit (0-2) for different protocol support; Bit 1 for RBT support, + * bit 1 for SMBUS support and bit 2 for PCIE support. Bit (3-5) + * for different protocol availability. Bit 4 for RBT, bit 4 for + * SMBUS and bit 5 for PCIE. + */ +enum { + MLX_MC_RBT_SUPPORT = 0x01, /* MC supports RBT */ + MLX_MC_RBT_AVL = 0x08, /* RBT medium is available */ +}; + /* OEM Vendor Manufacture ID */ #define NCSI_OEM_MFR_MLX_ID 0x8119 #define NCSI_OEM_MFR_BCM_ID 0x113d @@ -72,9 +83,15 @@ enum { /* Mellanox specific OEM Command */ #define NCSI_OEM_MLX_CMD_GMA 0x00 /* CMD ID for Get MAC */ #define NCSI_OEM_MLX_CMD_GMA_PARAM 0x1b /* Parameter for GMA */ +#define NCSI_OEM_MLX_CMD_SMAF 0x01 /* CMD ID for Set MC Affinity */ +#define NCSI_OEM_MLX_CMD_SMAF_PARAM 0x07 /* Parameter for SMAF */ /* OEM Command payload lengths*/ #define NCSI_OEM_BCM_CMD_GMA_LEN 12 #define NCSI_OEM_MLX_CMD_GMA_LEN 8 +#define NCSI_OEM_MLX_CMD_SMAF_LEN 60 +/* Offset in OEM request */ +#define MLX_SMAF_MAC_ADDR_OFFSET 8 /* Offset for MAC in SMAF */ +#define MLX_SMAF_MED_SUPPORT_OFFSET 14 /* Offset for medium in SMAF */ /* Mac address offset in OEM response */ #define BCM_MAC_ADDR_OFFSET 28 #define MLX_MAC_ADDR_OFFSET 8 @@ -251,6 +268,8 @@ enum { ncsi_dev_state_probe_deselect = 0x0201, ncsi_dev_state_probe_package, ncsi_dev_state_probe_channel, + ncsi_dev_state_probe_mlx_gma, + ncsi_dev_state_probe_mlx_smaf, ncsi_dev_state_probe_cis, ncsi_dev_state_probe_gvi, ncsi_dev_state_probe_gc, @@ -311,6 +330,7 @@ struct ncsi_dev_priv { struct list_head vlan_vids; /* List of active VLAN IDs */ bool multi_package; /* Enable multiple packages */ + bool mlx_multi_host; /* Enable multi host Mellanox */ u32 package_whitelist; /* Packages to configure */ }; diff --git a/net/ncsi/ncsi-cmd.c b/net/ncsi/ncsi-cmd.c index 0187e65176c0..ba9ae482141b 100644 --- a/net/ncsi/ncsi-cmd.c +++ b/net/ncsi/ncsi-cmd.c @@ -369,7 +369,15 @@ int ncsi_xmit_cmd(struct ncsi_cmd_arg *nca) eh = skb_push(nr->cmd, sizeof(*eh)); eh->h_proto = htons(ETH_P_NCSI); eth_broadcast_addr(eh->h_dest); - eth_broadcast_addr(eh->h_source); + + /* If mac address received from device then use it for + * source address as unicast address else use broadcast + * address as source address + */ + if (nca->ndp->gma_flag == 1) + memcpy(eh->h_source, nca->ndp->ndev.dev->dev_addr, ETH_ALEN); + else + eth_broadcast_addr(eh->h_source); /* Start the timer for the request that might not have * corresponding response. Given NCSI is an internal diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index e20b81514029..1f387be7827b 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -8,6 +8,8 @@ #include <linux/init.h> #include <linux/netdevice.h> #include <linux/skbuff.h> +#include <linux/of.h> +#include <linux/platform_device.h> #include <net/ncsi.h> #include <net/net_namespace.h> @@ -730,6 +732,34 @@ static int ncsi_oem_gma_handler_mlx(struct ncsi_cmd_arg *nca) return ret; } +static int ncsi_oem_smaf_mlx(struct ncsi_cmd_arg *nca) +{ + union { + u8 data_u8[NCSI_OEM_MLX_CMD_SMAF_LEN]; + u32 data_u32[NCSI_OEM_MLX_CMD_SMAF_LEN / sizeof(u32)]; + } u; + int ret = 0; + + memset(&u, 0, sizeof(u)); + u.data_u32[0] = ntohl(NCSI_OEM_MFR_MLX_ID); + u.data_u8[5] = NCSI_OEM_MLX_CMD_SMAF; + u.data_u8[6] = NCSI_OEM_MLX_CMD_SMAF_PARAM; + memcpy(&u.data_u8[MLX_SMAF_MAC_ADDR_OFFSET], + nca->ndp->ndev.dev->dev_addr, ETH_ALEN); + u.data_u8[MLX_SMAF_MED_SUPPORT_OFFSET] = + (MLX_MC_RBT_AVL | MLX_MC_RBT_SUPPORT); + + nca->payload = NCSI_OEM_MLX_CMD_SMAF_LEN; + nca->data = u.data_u8; + + ret = ncsi_xmit_cmd(nca); + if (ret) + netdev_err(nca->ndp->ndev.dev, + "NCSI: Failed to transmit cmd 0x%x during probe\n", + nca->type); + return ret; +} + /* OEM Command handlers initialization */ static struct ncsi_oem_gma_handler { unsigned int mfr_id; @@ -1310,8 +1340,38 @@ static void ncsi_probe_channel(struct ncsi_dev_priv *ndp) break; } nd->state = ncsi_dev_state_probe_cis; + if (IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) && + ndp->mlx_multi_host) + nd->state = ncsi_dev_state_probe_mlx_gma; + schedule_work(&ndp->work); break; +#if IS_ENABLED(CONFIG_NCSI_OEM_CMD_GET_MAC) + case ncsi_dev_state_probe_mlx_gma: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_gma_handler_mlx(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_mlx_smaf; + break; + case ncsi_dev_state_probe_mlx_smaf: + ndp->pending_req_num = 1; + + nca.type = NCSI_PKT_CMD_OEM; + nca.package = ndp->active_package->id; + nca.channel = 0; + ret = ncsi_oem_smaf_mlx(&nca); + if (ret) + goto error; + + nd->state = ncsi_dev_state_probe_cis; + break; +#endif /* CONFIG_NCSI_OEM_CMD_GET_MAC */ case ncsi_dev_state_probe_cis: ndp->pending_req_num = NCSI_RESERVED_CHANNEL; @@ -1621,6 +1681,8 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, { struct ncsi_dev_priv *ndp; struct ncsi_dev *nd; + struct platform_device *pdev; + struct device_node *np; unsigned long flags; int i; @@ -1667,6 +1729,13 @@ struct ncsi_dev *ncsi_register_dev(struct net_device *dev, /* Set up generic netlink interface */ ncsi_init_netlink(dev); + pdev = to_platform_device(dev->dev.parent); + if (pdev) { + np = pdev->dev.of_node; + if (np && of_get_property(np, "mlx,multi-host", NULL)) + ndp->mlx_multi_host = true; + } + return nd; } EXPORT_SYMBOL_GPL(ncsi_register_dev); diff --git a/net/netfilter/ipset/ip_set_bitmap_gen.h b/net/netfilter/ipset/ip_set_bitmap_gen.h index 1abd6f0dc227..077a2cb65fcb 100644 --- a/net/netfilter/ipset/ip_set_bitmap_gen.h +++ b/net/netfilter/ipset/ip_set_bitmap_gen.h @@ -60,9 +60,9 @@ 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; diff --git a/net/netfilter/ipset/ip_set_core.c b/net/netfilter/ipset/ip_set_core.c index 169e0a04f814..cf895bc80871 100644 --- a/net/netfilter/ipset/ip_set_core.c +++ b/net/netfilter/ipset/ip_set_core.c @@ -1848,6 +1848,7 @@ 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] || @@ -1864,7 +1865,7 @@ static int ip_set_utest(struct net *net, struct sock *ctnl, struct sk_buff *skb, 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) 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 fce3d93f1541..0399ae8f1188 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -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_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index 9889d52eda82..7e91989a1b55 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -61,9 +61,9 @@ struct flow_offload *flow_offload_alloc(struct nf_conn *ct) flow_offload_fill_dir(flow, FLOW_OFFLOAD_DIR_REPLY); if (ct->status & IPS_SRC_NAT) - flow->flags |= FLOW_OFFLOAD_SNAT; + __set_bit(NF_FLOW_SNAT, &flow->flags); if (ct->status & IPS_DST_NAT) - flow->flags |= FLOW_OFFLOAD_DNAT; + __set_bit(NF_FLOW_DNAT, &flow->flags); return flow; @@ -134,11 +134,6 @@ static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) #define NF_FLOWTABLE_TCP_PICKUP_TIMEOUT (120 * HZ) #define NF_FLOWTABLE_UDP_PICKUP_TIMEOUT (30 * HZ) -static inline __s32 nf_flow_timeout_delta(unsigned int timeout) -{ - return (__s32)(timeout - (u32)jiffies); -} - static void flow_offload_fixup_ct_timeout(struct nf_conn *ct) { const struct nf_conntrack_l4proto *l4proto; @@ -187,8 +182,6 @@ void flow_offload_free(struct flow_offload *flow) default: break; } - if (flow->flags & FLOW_OFFLOAD_DYING) - nf_ct_delete(flow->ct, 0, 0); nf_ct_put(flow->ct); kfree_rcu(flow, rcu_head); } @@ -232,7 +225,7 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { int err; - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; err = rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[0].node, @@ -250,8 +243,10 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) return err; } - if (flow_table->flags & NF_FLOWTABLE_HW_OFFLOAD) + if (nf_flowtable_hw_offload(flow_table)) { + __set_bit(NF_FLOW_HW, &flow->flags); nf_flow_offload_add(flow_table, flow); + } return 0; } @@ -276,7 +271,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, if (nf_flow_has_expired(flow)) flow_offload_fixup_ct(flow->ct); - else if (flow->flags & FLOW_OFFLOAD_TEARDOWN) + else if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) flow_offload_fixup_ct_timeout(flow->ct); flow_offload_free(flow); @@ -284,7 +279,7 @@ static void flow_offload_del(struct nf_flowtable *flow_table, void flow_offload_teardown(struct flow_offload *flow) { - flow->flags |= FLOW_OFFLOAD_TEARDOWN; + set_bit(NF_FLOW_TEARDOWN, &flow->flags); flow_offload_fixup_ct_state(flow->ct); } @@ -305,7 +300,7 @@ flow_offload_lookup(struct nf_flowtable *flow_table, dir = tuplehash->tuple.dir; flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)) + if (test_bit(NF_FLOW_TEARDOWN, &flow->flags)) return NULL; if (unlikely(nf_ct_is_dying(flow->ct))) @@ -353,19 +348,18 @@ static void nf_flow_offload_gc_step(struct flow_offload *flow, void *data) { struct nf_flowtable *flow_table = data; - if (flow->flags & FLOW_OFFLOAD_HW) - nf_flow_offload_stats(flow_table, flow); - if (nf_flow_has_expired(flow) || nf_ct_is_dying(flow->ct) || - (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN))) { - if (flow->flags & FLOW_OFFLOAD_HW) { - if (!(flow->flags & FLOW_OFFLOAD_HW_DYING)) + test_bit(NF_FLOW_TEARDOWN, &flow->flags)) { + if (test_bit(NF_FLOW_HW, &flow->flags)) { + if (!test_bit(NF_FLOW_HW_DYING, &flow->flags)) nf_flow_offload_del(flow_table, flow); - else if (flow->flags & FLOW_OFFLOAD_HW_DEAD) + else if (test_bit(NF_FLOW_HW_DEAD, &flow->flags)) flow_offload_del(flow_table, flow); } else { flow_offload_del(flow_table, flow); } + } else if (test_bit(NF_FLOW_HW, &flow->flags)) { + nf_flow_offload_stats(flow_table, flow); } } @@ -529,7 +523,7 @@ static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) if (net_eq(nf_ct_net(flow->ct), dev_net(dev)) && (flow->tuplehash[0].tuple.iifidx == dev->ifindex || flow->tuplehash[1].tuple.iifidx == dev->ifindex)) - flow_offload_dead(flow); + flow_offload_teardown(flow); } static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c index b9e7dd6e60ce..9e563fd3da0f 100644 --- a/net/netfilter/nf_flow_table_ip.c +++ b/net/netfilter/nf_flow_table_ip.c @@ -144,11 +144,11 @@ static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, { struct iphdr *iph = ip_hdr(skb); - if (flow->flags & FLOW_OFFLOAD_SNAT && + if (test_bit(NF_FLOW_SNAT, &flow->flags) && (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && + if (test_bit(NF_FLOW_DNAT, &flow->flags) && (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) return -1; @@ -232,6 +232,13 @@ static unsigned int nf_flow_xmit_xfrm(struct sk_buff *skb, return NF_STOLEN; } +static bool nf_flow_offload_refresh(struct nf_flowtable *flow_table, + struct flow_offload *flow) +{ + return nf_flowtable_hw_offload(flow_table) && + test_and_clear_bit(NF_FLOW_HW_REFRESH, &flow->flags); +} + unsigned int nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) @@ -272,6 +279,9 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) return NF_ACCEPT; + if (unlikely(nf_flow_offload_refresh(flow_table, flow))) + nf_flow_offload_add(flow_table, flow); + if (nf_flow_offload_dst_check(&rt->dst)) { flow_offload_teardown(flow); return NF_ACCEPT; @@ -280,7 +290,7 @@ nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, if (nf_flow_nat_ip(flow, skb, thoff, dir) < 0) return NF_DROP; - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; iph = ip_hdr(skb); ip_decrease_ttl(iph); skb->tstamp = 0; @@ -414,11 +424,11 @@ static int nf_flow_nat_ipv6(const struct flow_offload *flow, struct ipv6hdr *ip6h = ipv6_hdr(skb); unsigned int thoff = sizeof(*ip6h); - if (flow->flags & FLOW_OFFLOAD_SNAT && + if (test_bit(NF_FLOW_SNAT, &flow->flags) && (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && + if (test_bit(NF_FLOW_DNAT, &flow->flags) && (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) return -1; @@ -498,6 +508,9 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, sizeof(*ip6h))) return NF_ACCEPT; + if (unlikely(nf_flow_offload_refresh(flow_table, flow))) + nf_flow_offload_add(flow_table, flow); + if (nf_flow_offload_dst_check(&rt->dst)) { flow_offload_teardown(flow); return NF_ACCEPT; @@ -509,7 +522,7 @@ nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, if (nf_flow_nat_ipv6(flow, skb, dir) < 0) return NF_DROP; - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + flow->timeout = nf_flowtable_time_stamp + NF_FLOW_TIMEOUT; ip6h = ipv6_hdr(skb); ip6h->hop_limit--; skb->tstamp = 0; diff --git a/net/netfilter/nf_flow_table_offload.c b/net/netfilter/nf_flow_table_offload.c index 0d72e5ccb47b..c8b70ffeef0c 100644 --- a/net/netfilter/nf_flow_table_offload.c +++ b/net/netfilter/nf_flow_table_offload.c @@ -24,6 +24,7 @@ struct flow_offload_work { }; struct nf_flow_key { + struct flow_dissector_key_meta meta; struct flow_dissector_key_control control; struct flow_dissector_key_basic basic; union { @@ -55,6 +56,7 @@ static int nf_flow_rule_match(struct nf_flow_match *match, struct nf_flow_key *mask = &match->mask; struct nf_flow_key *key = &match->key; + NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_META, meta); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_CONTROL, control); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_BASIC, basic); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_IPV4_ADDRS, ipv4); @@ -62,6 +64,9 @@ static int nf_flow_rule_match(struct nf_flow_match *match, NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_TCP, tcp); NF_FLOW_DISSECTOR(match, FLOW_DISSECTOR_KEY_PORTS, tp); + key->meta.ingress_ifindex = tuple->iifidx; + mask->meta.ingress_ifindex = 0xffffffff; + switch (tuple->l3proto) { case AF_INET: key->control.addr_type = FLOW_DISSECTOR_KEY_IPV4_ADDRS; @@ -105,7 +110,8 @@ static int nf_flow_rule_match(struct nf_flow_match *match, key->tp.dst = tuple->dst_port; mask->tp.dst = 0xffff; - match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_CONTROL) | + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_META) | + BIT(FLOW_DISSECTOR_KEY_CONTROL) | BIT(FLOW_DISSECTOR_KEY_BASIC) | BIT(FLOW_DISSECTOR_KEY_PORTS); return 0; @@ -166,24 +172,38 @@ static int flow_offload_eth_dst(struct net *net, enum flow_offload_tuple_dir dir, struct nf_flow_rule *flow_rule) { - const struct flow_offload_tuple *tuple = &flow->tuplehash[dir].tuple; struct flow_action_entry *entry0 = flow_action_entry_next(flow_rule); struct flow_action_entry *entry1 = flow_action_entry_next(flow_rule); + const void *daddr = &flow->tuplehash[!dir].tuple.src_v4; + const struct dst_entry *dst_cache; + unsigned char ha[ETH_ALEN]; struct neighbour *n; u32 mask, val; + u8 nud_state; u16 val16; - n = dst_neigh_lookup(tuple->dst_cache, &tuple->dst_v4); + dst_cache = flow->tuplehash[dir].tuple.dst_cache; + n = dst_neigh_lookup(dst_cache, daddr); if (!n) return -ENOENT; + read_lock_bh(&n->lock); + nud_state = n->nud_state; + ether_addr_copy(ha, n->ha); + read_unlock_bh(&n->lock); + + if (!(nud_state & NUD_VALID)) { + neigh_release(n); + return -ENOENT; + } + mask = ~0xffffffff; - memcpy(&val, n->ha, 4); + memcpy(&val, ha, 4); flow_offload_mangle(entry0, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 0, &val, &mask); mask = ~0x0000ffff; - memcpy(&val16, n->ha + 4, 2); + memcpy(&val16, ha + 4, 2); val = val16; flow_offload_mangle(entry1, FLOW_ACT_MANGLE_HDR_TYPE_ETH, 4, &val, &mask); @@ -335,22 +355,26 @@ static void flow_offload_port_snat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff0000), port; + u32 mask, port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); offset = 0; /* offsetof(struct tcphdr, source); */ + port = htonl(port << 16); + mask = ~htonl(0xffff0000); break; case FLOW_OFFLOAD_DIR_REPLY: port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); offset = 0; /* offsetof(struct tcphdr, dest); */ + port = htonl(port); + mask = ~htonl(0xffff); break; default: return; } - port = htonl(port << 16); + flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, &port, &mask); } @@ -361,22 +385,26 @@ static void flow_offload_port_dnat(struct net *net, struct nf_flow_rule *flow_rule) { struct flow_action_entry *entry = flow_action_entry_next(flow_rule); - u32 mask = ~htonl(0xffff), port; + u32 mask, port; u32 offset; switch (dir) { case FLOW_OFFLOAD_DIR_ORIGINAL: - port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port); - offset = 0; /* offsetof(struct tcphdr, source); */ + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port); + offset = 0; /* offsetof(struct tcphdr, dest); */ + port = htonl(port); + mask = ~htonl(0xffff); break; case FLOW_OFFLOAD_DIR_REPLY: - port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port); - offset = 0; /* offsetof(struct tcphdr, dest); */ + port = ntohs(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port); + offset = 0; /* offsetof(struct tcphdr, source); */ + port = htonl(port << 16); + mask = ~htonl(0xffff0000); break; default: return; } - port = htonl(port); + flow_offload_mangle(entry, flow_offload_l4proto(flow), offset, &port, &mask); } @@ -422,16 +450,16 @@ int nf_flow_rule_route_ipv4(struct net *net, const struct flow_offload *flow, flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) return -1; - if (flow->flags & FLOW_OFFLOAD_SNAT) { + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { flow_offload_ipv4_snat(net, flow, dir, flow_rule); flow_offload_port_snat(net, flow, dir, flow_rule); } - if (flow->flags & FLOW_OFFLOAD_DNAT) { + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { flow_offload_ipv4_dnat(net, flow, dir, flow_rule); flow_offload_port_dnat(net, flow, dir, flow_rule); } - if (flow->flags & FLOW_OFFLOAD_SNAT || - flow->flags & FLOW_OFFLOAD_DNAT) + if (test_bit(NF_FLOW_SNAT, &flow->flags) || + test_bit(NF_FLOW_DNAT, &flow->flags)) flow_offload_ipv4_checksum(net, flow, flow_rule); flow_offload_redirect(flow, dir, flow_rule); @@ -448,11 +476,11 @@ int nf_flow_rule_route_ipv6(struct net *net, const struct flow_offload *flow, flow_offload_eth_dst(net, flow, dir, flow_rule) < 0) return -1; - if (flow->flags & FLOW_OFFLOAD_SNAT) { + if (test_bit(NF_FLOW_SNAT, &flow->flags)) { flow_offload_ipv6_snat(net, flow, dir, flow_rule); flow_offload_port_snat(net, flow, dir, flow_rule); } - if (flow->flags & FLOW_OFFLOAD_DNAT) { + if (test_bit(NF_FLOW_DNAT, &flow->flags)) { flow_offload_ipv6_dnat(net, flow, dir, flow_rule); flow_offload_port_dnat(net, flow, dir, flow_rule); } @@ -564,23 +592,25 @@ static void nf_flow_offload_init(struct flow_cls_offload *cls_flow, cls_flow->cookie = (unsigned long)tuple; } -static int flow_offload_tuple_add(struct flow_offload_work *offload, - struct nf_flow_rule *flow_rule, - enum flow_offload_tuple_dir dir) +static int nf_flow_offload_tuple(struct nf_flowtable *flowtable, + struct flow_offload *flow, + struct nf_flow_rule *flow_rule, + enum flow_offload_tuple_dir dir, + int priority, int cmd, + struct list_head *block_cb_list) { - struct nf_flowtable *flowtable = offload->flowtable; struct flow_cls_offload cls_flow = {}; struct flow_block_cb *block_cb; struct netlink_ext_ack extack; __be16 proto = ETH_P_ALL; int err, i = 0; - nf_flow_offload_init(&cls_flow, proto, offload->priority, - FLOW_CLS_REPLACE, - &offload->flow->tuplehash[dir].tuple, &extack); - cls_flow.rule = flow_rule->rule; + nf_flow_offload_init(&cls_flow, proto, priority, cmd, + &flow->tuplehash[dir].tuple, &extack); + if (cmd == FLOW_CLS_REPLACE) + cls_flow.rule = flow_rule->rule; - list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) { + list_for_each_entry(block_cb, block_cb_list, list) { err = block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); if (err < 0) @@ -592,23 +622,22 @@ static int flow_offload_tuple_add(struct flow_offload_work *offload, return i; } +static int flow_offload_tuple_add(struct flow_offload_work *offload, + struct nf_flow_rule *flow_rule, + enum flow_offload_tuple_dir dir) +{ + return nf_flow_offload_tuple(offload->flowtable, offload->flow, + flow_rule, dir, offload->priority, + FLOW_CLS_REPLACE, + &offload->flowtable->flow_block.cb_list); +} + static void flow_offload_tuple_del(struct flow_offload_work *offload, enum flow_offload_tuple_dir dir) { - struct nf_flowtable *flowtable = offload->flowtable; - struct flow_cls_offload cls_flow = {}; - struct flow_block_cb *block_cb; - struct netlink_ext_ack extack; - __be16 proto = ETH_P_ALL; - - nf_flow_offload_init(&cls_flow, proto, offload->priority, - FLOW_CLS_DESTROY, - &offload->flow->tuplehash[dir].tuple, &extack); - - list_for_each_entry(block_cb, &flowtable->flow_block.cb_list, list) - block_cb->cb(TC_SETUP_CLSFLOWER, &cls_flow, block_cb->cb_priv); - - offload->flow->flags |= FLOW_OFFLOAD_HW_DEAD; + nf_flow_offload_tuple(offload->flowtable, offload->flow, NULL, dir, + offload->priority, FLOW_CLS_DESTROY, + &offload->flowtable->flow_block.cb_list); } static int flow_offload_rule_add(struct flow_offload_work *offload, @@ -626,20 +655,20 @@ static int flow_offload_rule_add(struct flow_offload_work *offload, return 0; } -static int flow_offload_work_add(struct flow_offload_work *offload) +static void flow_offload_work_add(struct flow_offload_work *offload) { struct nf_flow_rule *flow_rule[FLOW_OFFLOAD_DIR_MAX]; int err; err = nf_flow_offload_alloc(offload, flow_rule); if (err < 0) - return -ENOMEM; + return; err = flow_offload_rule_add(offload, flow_rule); + if (err < 0) + set_bit(NF_FLOW_HW_REFRESH, &offload->flow->flags); nf_flow_offload_destroy(flow_rule); - - return err; } static void flow_offload_work_del(struct flow_offload_work *offload) @@ -684,7 +713,6 @@ static void flow_offload_work_handler(struct work_struct *work) { struct flow_offload_work *offload, *next; LIST_HEAD(offload_pending_list); - int ret; spin_lock_bh(&flow_offload_pending_list_lock); list_replace_init(&flow_offload_pending_list, &offload_pending_list); @@ -693,9 +721,7 @@ static void flow_offload_work_handler(struct work_struct *work) list_for_each_entry_safe(offload, next, &offload_pending_list, list) { switch (offload->cmd) { case FLOW_CLS_REPLACE: - ret = flow_offload_work_add(offload); - if (ret < 0) - offload->flow->flags &= ~FLOW_OFFLOAD_HW; + flow_offload_work_add(offload); break; case FLOW_CLS_DESTROY: flow_offload_work_del(offload); @@ -720,20 +746,33 @@ static void flow_offload_queue_work(struct flow_offload_work *offload) schedule_work(&nf_flow_offload_work); } -void nf_flow_offload_add(struct nf_flowtable *flowtable, - struct flow_offload *flow) +static struct flow_offload_work * +nf_flow_offload_work_alloc(struct nf_flowtable *flowtable, + struct flow_offload *flow, unsigned int cmd) { struct flow_offload_work *offload; offload = kmalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); if (!offload) - return; + return NULL; - offload->cmd = FLOW_CLS_REPLACE; + offload->cmd = cmd; offload->flow = flow; offload->priority = flowtable->priority; offload->flowtable = flowtable; - flow->flags |= FLOW_OFFLOAD_HW; + + return offload; +} + + +void nf_flow_offload_add(struct nf_flowtable *flowtable, + struct flow_offload *flow) +{ + struct flow_offload_work *offload; + + offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_REPLACE); + if (!offload) + return; flow_offload_queue_work(offload); } @@ -743,15 +782,11 @@ void nf_flow_offload_del(struct nf_flowtable *flowtable, { struct flow_offload_work *offload; - offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_DESTROY); if (!offload) return; - offload->cmd = FLOW_CLS_DESTROY; - offload->flow = flow; - offload->flow->flags |= FLOW_OFFLOAD_HW_DYING; - offload->flowtable = flowtable; - + set_bit(NF_FLOW_HW_DYING, &flow->flags); flow_offload_queue_work(offload); } @@ -759,27 +794,22 @@ void nf_flow_offload_stats(struct nf_flowtable *flowtable, struct flow_offload *flow) { struct flow_offload_work *offload; - s64 delta; + __s32 delta; - delta = flow->timeout - jiffies; - if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10) || - flow->flags & FLOW_OFFLOAD_HW_DYING) + delta = nf_flow_timeout_delta(flow->timeout); + if ((delta >= (9 * NF_FLOW_TIMEOUT) / 10)) return; - offload = kzalloc(sizeof(struct flow_offload_work), GFP_ATOMIC); + offload = nf_flow_offload_work_alloc(flowtable, flow, FLOW_CLS_STATS); if (!offload) return; - offload->cmd = FLOW_CLS_STATS; - offload->flow = flow; - offload->flowtable = flowtable; - flow_offload_queue_work(offload); } void nf_flow_table_offload_flush(struct nf_flowtable *flowtable) { - if (flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD) + if (nf_flowtable_hw_offload(flowtable)) flush_work(&nf_flow_offload_work); } @@ -808,28 +838,44 @@ static int nf_flow_table_block_setup(struct nf_flowtable *flowtable, return err; } -int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, - struct net_device *dev, - enum flow_block_command cmd) +static int nf_flow_table_offload_cmd(struct flow_block_offload *bo, + struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd, + struct netlink_ext_ack *extack) { - struct netlink_ext_ack extack = {}; - struct flow_block_offload bo = {}; int err; - if (!(flowtable->flags & NF_FLOWTABLE_HW_OFFLOAD)) + if (!nf_flowtable_hw_offload(flowtable)) return 0; if (!dev->netdev_ops->ndo_setup_tc) return -EOPNOTSUPP; - bo.net = dev_net(dev); - bo.block = &flowtable->flow_block; - bo.command = cmd; - bo.binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; - bo.extack = &extack; - INIT_LIST_HEAD(&bo.cb_list); + memset(bo, 0, sizeof(*bo)); + bo->net = dev_net(dev); + bo->block = &flowtable->flow_block; + bo->command = cmd; + bo->binder_type = FLOW_BLOCK_BINDER_TYPE_CLSACT_INGRESS; + bo->extack = extack; + INIT_LIST_HEAD(&bo->cb_list); + + err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, bo); + if (err < 0) + return err; + + return 0; +} + +int nf_flow_table_offload_setup(struct nf_flowtable *flowtable, + struct net_device *dev, + enum flow_block_command cmd) +{ + struct netlink_ext_ack extack = {}; + struct flow_block_offload bo; + int err; - err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_FT, &bo); + err = nf_flow_table_offload_cmd(&bo, flowtable, dev, cmd, &extack); if (err < 0) return err; diff --git a/net/netfilter/nf_nat_proto.c b/net/netfilter/nf_nat_proto.c index 0a59c14b5177..64eedc17037a 100644 --- a/net/netfilter/nf_nat_proto.c +++ b/net/netfilter/nf_nat_proto.c @@ -233,6 +233,19 @@ 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; diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 273f3838318b..65f51a2e9c2a 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -22,6 +22,8 @@ #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); @@ -564,33 +566,34 @@ __nf_tables_chain_type_lookup(const struct nlattr *nla, u8 family) } /* - * 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. + * Loading a module requires dropping mutex that guards the transaction. + * A different client might race to start a new transaction meanwhile. Zap the + * list of pending transaction and then restore it once the mutex is grabbed + * again. Users of this function return EAGAIN which implicitly triggers the + * transaction abort path to clean up the list of pending transactions. */ #ifdef CONFIG_MODULES -static int __nf_tables_abort(struct net *net); - static void nft_request_module(struct net *net, const char *fmt, ...) { char module_name[MODULE_NAME_LEN]; + LIST_HEAD(commit_list); va_list args; int ret; - __nf_tables_abort(net); + list_splice_init(&net->nft.commit_list, &commit_list); 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)) + if (ret >= MODULE_NAME_LEN) return; mutex_unlock(&net->nft.commit_mutex); request_module("%s", module_name); mutex_lock(&net->nft.commit_mutex); + + WARN_ON_ONCE(!list_empty(&net->nft.commit_list)); + list_splice(&commit_list, &net->nft.commit_list); } #endif @@ -1045,12 +1048,18 @@ 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; @@ -1241,7 +1250,8 @@ 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 }, [NFTA_CHAIN_FLAGS] = { .type = NLA_U32 }, }; @@ -1676,6 +1686,7 @@ static int nf_tables_parse_netdev_hooks(struct net *net, goto err_hook; } if (nft_hook_list_find(hook_list, hook)) { + kfree(hook); err = -EEXIST; goto err_hook; } @@ -2355,7 +2366,8 @@ 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 }, }; @@ -4198,7 +4210,8 @@ 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] = { @@ -5984,6 +5997,7 @@ nft_flowtable_type_get(struct net *net, u8 family) return ERR_PTR(-ENOENT); } +/* Only called from error and netdev event paths. */ static void nft_unregister_flowtable_hook(struct net *net, struct nft_flowtable *flowtable, struct nft_hook *hook) @@ -5999,7 +6013,7 @@ static void nft_unregister_flowtable_net_hooks(struct net *net, struct nft_hook *hook; list_for_each_entry(hook, &flowtable->hook_list, list) - nft_unregister_flowtable_hook(net, flowtable, hook); + nf_unregister_net_hook(net, &hook->ops); } static int nft_register_flowtable_net_hooks(struct net *net, @@ -6448,12 +6462,14 @@ static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { struct nft_hook *hook, *next; + flowtable->data.type->free(&flowtable->data); list_for_each_entry_safe(hook, next, &flowtable->hook_list, list) { + flowtable->data.type->setup(&flowtable->data, hook->ops.dev, + FLOW_BLOCK_UNBIND); list_del_rcu(&hook->list); kfree(hook); } kfree(flowtable->name); - flowtable->data.type->free(&flowtable->data); module_put(flowtable->data.type->owner); kfree(flowtable); } @@ -6497,6 +6513,7 @@ static void nft_flowtable_event(unsigned long event, struct net_device *dev, if (hook->ops.dev != dev) continue; + /* flow_offload_netdev_event() cleans up entries for us. */ nft_unregister_flowtable_hook(dev_net(dev), flowtable, hook); list_del_rcu(&hook->list); kfree_rcu(hook, rcu); diff --git a/net/netfilter/nfnetlink_queue.c b/net/netfilter/nfnetlink_queue.c index feabdfb22920..76535fd9278c 100644 --- a/net/netfilter/nfnetlink_queue.c +++ b/net/netfilter/nfnetlink_queue.c @@ -778,7 +778,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) { unsigned int queued; struct nfqnl_instance *queue; - struct sk_buff *skb, *segs; + struct sk_buff *skb, *segs, *nskb; int err = -ENOBUFS; struct net *net = entry->state.net; struct nfnl_queue_net *q = nfnl_queue_pernet(net); @@ -815,8 +815,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) goto out_err; queued = 0; err = 0; - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { if (err == 0) err = __nfqnl_enqueue_packet_gso(net, queue, segs, entry); @@ -824,8 +823,7 @@ nfqnl_enqueue_packet(struct nf_queue_entry *entry, unsigned int queuenum) queued++; else kfree_skb(segs); - segs = nskb; - } while (segs); + } if (queued) { if (err) /* some segments are already queued */ diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index 10e9d50e4e19..0ed2281f03be 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -18,21 +18,66 @@ struct nft_bitwise { enum nft_registers sreg:8; enum nft_registers dreg:8; + enum nft_bitwise_ops op:8; u8 len; struct nft_data mask; struct nft_data xor; + struct nft_data data; }; +static void nft_bitwise_eval_bool(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) +{ + unsigned int i; + + for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) + dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i]; +} + +static void nft_bitwise_eval_lshift(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) +{ + u32 shift = priv->data.data[0]; + unsigned int i; + u32 carry = 0; + + for (i = DIV_ROUND_UP(priv->len, sizeof(u32)); i > 0; i--) { + dst[i - 1] = (src[i - 1] << shift) | carry; + carry = src[i - 1] >> (BITS_PER_TYPE(u32) - shift); + } +} + +static void nft_bitwise_eval_rshift(u32 *dst, const u32 *src, + const struct nft_bitwise *priv) +{ + u32 shift = priv->data.data[0]; + unsigned int i; + u32 carry = 0; + + for (i = 0; i < DIV_ROUND_UP(priv->len, sizeof(u32)); i++) { + dst[i] = carry | (src[i] >> shift); + carry = src[i] << (BITS_PER_TYPE(u32) - shift); + } +} + void nft_bitwise_eval(const struct nft_expr *expr, struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_bitwise *priv = nft_expr_priv(expr); const u32 *src = ®s->data[priv->sreg]; u32 *dst = ®s->data[priv->dreg]; - unsigned int i; - for (i = 0; i < DIV_ROUND_UP(priv->len, 4); i++) - dst[i] = (src[i] & priv->mask.data[i]) ^ priv->xor.data[i]; + switch (priv->op) { + case NFT_BITWISE_BOOL: + nft_bitwise_eval_bool(dst, src, priv); + break; + case NFT_BITWISE_LSHIFT: + nft_bitwise_eval_lshift(dst, src, priv); + break; + case NFT_BITWISE_RSHIFT: + nft_bitwise_eval_rshift(dst, src, priv); + break; + } } static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { @@ -41,40 +86,22 @@ static const struct nla_policy nft_bitwise_policy[NFTA_BITWISE_MAX + 1] = { [NFTA_BITWISE_LEN] = { .type = NLA_U32 }, [NFTA_BITWISE_MASK] = { .type = NLA_NESTED }, [NFTA_BITWISE_XOR] = { .type = NLA_NESTED }, + [NFTA_BITWISE_OP] = { .type = NLA_U32 }, + [NFTA_BITWISE_DATA] = { .type = NLA_NESTED }, }; -static int nft_bitwise_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_bitwise_init_bool(struct nft_bitwise *priv, + const struct nlattr *const tb[]) { - struct nft_bitwise *priv = nft_expr_priv(expr); struct nft_data_desc d1, d2; - u32 len; int err; - if (tb[NFTA_BITWISE_SREG] == NULL || - tb[NFTA_BITWISE_DREG] == NULL || - tb[NFTA_BITWISE_LEN] == NULL || - tb[NFTA_BITWISE_MASK] == NULL || - tb[NFTA_BITWISE_XOR] == NULL) + if (tb[NFTA_BITWISE_DATA]) return -EINVAL; - err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); - if (err < 0) - return err; - - priv->len = len; - - priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); - err = nft_validate_register_load(priv->sreg, priv->len); - if (err < 0) - return err; - - priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); - err = nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, priv->len); - if (err < 0) - return err; + if (!tb[NFTA_BITWISE_MASK] || + !tb[NFTA_BITWISE_XOR]) + return -EINVAL; err = nft_data_init(NULL, &priv->mask, sizeof(priv->mask), &d1, tb[NFTA_BITWISE_MASK]); @@ -102,40 +129,151 @@ err1: return err; } -static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) +static int nft_bitwise_init_shift(struct nft_bitwise *priv, + const struct nlattr *const tb[]) { - const struct nft_bitwise *priv = nft_expr_priv(expr); + struct nft_data_desc d; + int err; - if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg)) - goto nla_put_failure; - if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg)) - goto nla_put_failure; - if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len))) - goto nla_put_failure; + if (tb[NFTA_BITWISE_MASK] || + tb[NFTA_BITWISE_XOR]) + return -EINVAL; + + if (!tb[NFTA_BITWISE_DATA]) + return -EINVAL; + err = nft_data_init(NULL, &priv->data, sizeof(priv->data), &d, + tb[NFTA_BITWISE_DATA]); + if (err < 0) + return err; + if (d.type != NFT_DATA_VALUE || d.len != sizeof(u32) || + priv->data.data[0] >= BITS_PER_TYPE(u32)) { + nft_data_release(&priv->data, d.type); + return -EINVAL; + } + + return 0; +} + +static int nft_bitwise_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_bitwise *priv = nft_expr_priv(expr); + u32 len; + int err; + + if (!tb[NFTA_BITWISE_SREG] || + !tb[NFTA_BITWISE_DREG] || + !tb[NFTA_BITWISE_LEN]) + return -EINVAL; + + err = nft_parse_u32_check(tb[NFTA_BITWISE_LEN], U8_MAX, &len); + if (err < 0) + return err; + + priv->len = len; + + priv->sreg = nft_parse_register(tb[NFTA_BITWISE_SREG]); + err = nft_validate_register_load(priv->sreg, priv->len); + if (err < 0) + return err; + + priv->dreg = nft_parse_register(tb[NFTA_BITWISE_DREG]); + err = nft_validate_register_store(ctx, priv->dreg, NULL, + NFT_DATA_VALUE, priv->len); + if (err < 0) + return err; + + if (tb[NFTA_BITWISE_OP]) { + priv->op = ntohl(nla_get_be32(tb[NFTA_BITWISE_OP])); + switch (priv->op) { + case NFT_BITWISE_BOOL: + case NFT_BITWISE_LSHIFT: + case NFT_BITWISE_RSHIFT: + break; + default: + return -EOPNOTSUPP; + } + } else { + priv->op = NFT_BITWISE_BOOL; + } + + switch(priv->op) { + case NFT_BITWISE_BOOL: + err = nft_bitwise_init_bool(priv, tb); + break; + case NFT_BITWISE_LSHIFT: + case NFT_BITWISE_RSHIFT: + err = nft_bitwise_init_shift(priv, tb); + break; + } + + return err; +} + +static int nft_bitwise_dump_bool(struct sk_buff *skb, + const struct nft_bitwise *priv) +{ if (nft_data_dump(skb, NFTA_BITWISE_MASK, &priv->mask, NFT_DATA_VALUE, priv->len) < 0) - goto nla_put_failure; + return -1; if (nft_data_dump(skb, NFTA_BITWISE_XOR, &priv->xor, NFT_DATA_VALUE, priv->len) < 0) - goto nla_put_failure; + return -1; return 0; +} + +static int nft_bitwise_dump_shift(struct sk_buff *skb, + const struct nft_bitwise *priv) +{ + if (nft_data_dump(skb, NFTA_BITWISE_DATA, &priv->data, + NFT_DATA_VALUE, sizeof(u32)) < 0) + return -1; + return 0; +} + +static int nft_bitwise_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + const struct nft_bitwise *priv = nft_expr_priv(expr); + int err = 0; + + if (nft_dump_register(skb, NFTA_BITWISE_SREG, priv->sreg)) + return -1; + if (nft_dump_register(skb, NFTA_BITWISE_DREG, priv->dreg)) + return -1; + if (nla_put_be32(skb, NFTA_BITWISE_LEN, htonl(priv->len))) + return -1; + if (nla_put_be32(skb, NFTA_BITWISE_OP, htonl(priv->op))) + return -1; + + switch (priv->op) { + case NFT_BITWISE_BOOL: + err = nft_bitwise_dump_bool(skb, priv); + break; + case NFT_BITWISE_LSHIFT: + case NFT_BITWISE_RSHIFT: + err = nft_bitwise_dump_shift(skb, priv); + break; + } -nla_put_failure: - return -1; + return err; } static struct nft_data zero; static int nft_bitwise_offload(struct nft_offload_ctx *ctx, - struct nft_flow_rule *flow, - const struct nft_expr *expr) + struct nft_flow_rule *flow, + const struct nft_expr *expr) { const struct nft_bitwise *priv = nft_expr_priv(expr); struct nft_offload_reg *reg = &ctx->regs[priv->dreg]; + if (priv->op != NFT_BITWISE_BOOL) + return -EOPNOTSUPP; + if (memcmp(&priv->xor, &zero, sizeof(priv->xor)) || priv->sreg != priv->dreg || priv->len != reg->len) return -EOPNOTSUPP; diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index dd82ff2ee19f..b70b48996801 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -200,9 +200,6 @@ static void nft_flow_offload_activate(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_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 087a056e34d1..87e8d9ba0c9b 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -259,8 +259,8 @@ static u64 nft_bitmap_privsize(const struct nlattr * const nla[], } static int nft_bitmap_init(const struct nft_set *set, - const struct nft_set_desc *desc, - const struct nlattr * const nla[]) + const struct nft_set_desc *desc, + const struct nlattr * const nla[]) { struct nft_bitmap *priv = nft_set_priv(set); diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index b331a3c9a3a8..d350a7cd3af0 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -645,7 +645,7 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, } static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features, - struct nft_set_estimate *est) + struct nft_set_estimate *est) { if (!desc->size) return false; diff --git a/net/netfilter/nft_tunnel.c b/net/netfilter/nft_tunnel.c index 23cd163689d5..4c3f2e24c7cb 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; @@ -267,6 +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: diff --git a/net/netfilter/xt_hashlimit.c b/net/netfilter/xt_hashlimit.c index ced3fc8fad7c..bccd47cd7190 100644 --- a/net/netfilter/xt_hashlimit.c +++ b/net/netfilter/xt_hashlimit.c @@ -357,21 +357,7 @@ 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; @@ -381,7 +367,7 @@ 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); @@ -395,7 +381,7 @@ 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)); @@ -419,7 +405,7 @@ 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); + htable_selective_cleanup(hinfo, true); kfree(hinfo->name); vfree(hinfo); } diff --git a/net/openvswitch/datapath.c b/net/openvswitch/datapath.c index e3a37d22539c..659c2a790fe7 100644 --- a/net/openvswitch/datapath.c +++ b/net/openvswitch/datapath.c @@ -321,8 +321,7 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, } /* Queue all of the segments. */ - skb = segs; - do { + skb_list_walk_safe(segs, skb, nskb) { if (gso_type & SKB_GSO_UDP && skb != segs) key = &later_key; @@ -330,17 +329,15 @@ static int queue_gso_packets(struct datapath *dp, struct sk_buff *skb, if (err) break; - } while ((skb = skb->next)); + } /* Free all of the segments. */ - skb = segs; - do { - nskb = skb->next; + skb_list_walk_safe(segs, skb, nskb) { if (err) kfree_skb(skb); else consume_skb(skb); - } while ((skb = nskb)); + } return err; } diff --git a/net/qrtr/qrtr.c b/net/qrtr/qrtr.c index 88f98f27ad88..5a8e42ad1504 100644 --- a/net/qrtr/qrtr.c +++ b/net/qrtr/qrtr.c @@ -8,6 +8,8 @@ #include <linux/qrtr.h> #include <linux/termios.h> /* For TIOCINQ/OUTQ */ #include <linux/numa.h> +#include <linux/spinlock.h> +#include <linux/wait.h> #include <net/sock.h> @@ -97,10 +99,11 @@ static inline struct qrtr_sock *qrtr_sk(struct sock *sk) static unsigned int qrtr_local_nid = NUMA_NO_NODE; /* for node ids */ -static RADIX_TREE(qrtr_nodes, GFP_KERNEL); +static RADIX_TREE(qrtr_nodes, GFP_ATOMIC); +static DEFINE_SPINLOCK(qrtr_nodes_lock); /* broadcast list */ static LIST_HEAD(qrtr_all_nodes); -/* lock for qrtr_nodes, qrtr_all_nodes and node reference */ +/* lock for qrtr_all_nodes and node reference */ static DEFINE_MUTEX(qrtr_node_lock); /* local port allocation management */ @@ -113,8 +116,9 @@ static DEFINE_MUTEX(qrtr_port_lock); * @ep: endpoint * @ref: reference count for node * @nid: node id + * @qrtr_tx_flow: tree of qrtr_tx_flow, keyed by node << 32 | port + * @qrtr_tx_lock: lock for qrtr_tx_flow inserts * @rx_queue: receive queue - * @work: scheduled work struct for recv work * @item: list item for broadcast list */ struct qrtr_node { @@ -123,17 +127,36 @@ struct qrtr_node { struct kref ref; unsigned int nid; + struct radix_tree_root qrtr_tx_flow; + struct mutex qrtr_tx_lock; /* for qrtr_tx_flow */ + struct sk_buff_head rx_queue; - struct work_struct work; struct list_head item; }; +/** + * struct qrtr_tx_flow - tx flow control + * @resume_tx: waiters for a resume tx from the remote + * @pending: number of waiting senders + * @tx_failed: indicates that a message with confirm_rx flag was lost + */ +struct qrtr_tx_flow { + struct wait_queue_head resume_tx; + int pending; + int tx_failed; +}; + +#define QRTR_TX_FLOW_HIGH 10 +#define QRTR_TX_FLOW_LOW 5 + static int qrtr_local_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, struct sockaddr_qrtr *to); static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, struct sockaddr_qrtr *to); +static struct qrtr_sock *qrtr_port_lookup(int port); +static void qrtr_port_put(struct qrtr_sock *ipc); /* Release node resources and free the node. * @@ -143,15 +166,25 @@ static int qrtr_bcast_enqueue(struct qrtr_node *node, struct sk_buff *skb, static void __qrtr_node_release(struct kref *kref) { struct qrtr_node *node = container_of(kref, struct qrtr_node, ref); + struct radix_tree_iter iter; + unsigned long flags; + void __rcu **slot; + spin_lock_irqsave(&qrtr_nodes_lock, flags); if (node->nid != QRTR_EP_NID_AUTO) radix_tree_delete(&qrtr_nodes, node->nid); + spin_unlock_irqrestore(&qrtr_nodes_lock, flags); list_del(&node->item); mutex_unlock(&qrtr_node_lock); - cancel_work_sync(&node->work); skb_queue_purge(&node->rx_queue); + + /* Free tx flow counters */ + radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + radix_tree_iter_delete(&node->qrtr_tx_flow, &iter, slot); + kfree(*slot); + } kfree(node); } @@ -171,6 +204,126 @@ static void qrtr_node_release(struct qrtr_node *node) kref_put_mutex(&node->ref, __qrtr_node_release, &qrtr_node_lock); } +/** + * qrtr_tx_resume() - reset flow control counter + * @node: qrtr_node that the QRTR_TYPE_RESUME_TX packet arrived on + * @skb: resume_tx packet + */ +static void qrtr_tx_resume(struct qrtr_node *node, struct sk_buff *skb) +{ + struct qrtr_ctrl_pkt *pkt = (struct qrtr_ctrl_pkt *)skb->data; + u64 remote_node = le32_to_cpu(pkt->client.node); + u32 remote_port = le32_to_cpu(pkt->client.port); + struct qrtr_tx_flow *flow; + unsigned long key; + + key = remote_node << 32 | remote_port; + + rcu_read_lock(); + flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + rcu_read_unlock(); + if (flow) { + spin_lock(&flow->resume_tx.lock); + flow->pending = 0; + spin_unlock(&flow->resume_tx.lock); + wake_up_interruptible_all(&flow->resume_tx); + } + + consume_skb(skb); +} + +/** + * qrtr_tx_wait() - flow control for outgoing packets + * @node: qrtr_node that the packet is to be send to + * @dest_node: node id of the destination + * @dest_port: port number of the destination + * @type: type of message + * + * The flow control scheme is based around the low and high "watermarks". When + * the low watermark is passed the confirm_rx flag is set on the outgoing + * message, which will trigger the remote to send a control message of the type + * QRTR_TYPE_RESUME_TX to reset the counter. If the high watermark is hit + * further transmision should be paused. + * + * Return: 1 if confirm_rx should be set, 0 otherwise or errno failure + */ +static int qrtr_tx_wait(struct qrtr_node *node, int dest_node, int dest_port, + int type) +{ + unsigned long key = (u64)dest_node << 32 | dest_port; + struct qrtr_tx_flow *flow; + int confirm_rx = 0; + int ret; + + /* Never set confirm_rx on non-data packets */ + if (type != QRTR_TYPE_DATA) + return 0; + + mutex_lock(&node->qrtr_tx_lock); + flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + if (!flow) { + flow = kzalloc(sizeof(*flow), GFP_KERNEL); + if (flow) { + init_waitqueue_head(&flow->resume_tx); + radix_tree_insert(&node->qrtr_tx_flow, key, flow); + } + } + mutex_unlock(&node->qrtr_tx_lock); + + /* Set confirm_rx if we where unable to find and allocate a flow */ + if (!flow) + return 1; + + spin_lock_irq(&flow->resume_tx.lock); + ret = wait_event_interruptible_locked_irq(flow->resume_tx, + flow->pending < QRTR_TX_FLOW_HIGH || + flow->tx_failed || + !node->ep); + if (ret < 0) { + confirm_rx = ret; + } else if (!node->ep) { + confirm_rx = -EPIPE; + } else if (flow->tx_failed) { + flow->tx_failed = 0; + confirm_rx = 1; + } else { + flow->pending++; + confirm_rx = flow->pending == QRTR_TX_FLOW_LOW; + } + spin_unlock_irq(&flow->resume_tx.lock); + + return confirm_rx; +} + +/** + * qrtr_tx_flow_failed() - flag that tx of confirm_rx flagged messages failed + * @node: qrtr_node that the packet is to be send to + * @dest_node: node id of the destination + * @dest_port: port number of the destination + * + * Signal that the transmission of a message with confirm_rx flag failed. The + * flow's "pending" counter will keep incrementing towards QRTR_TX_FLOW_HIGH, + * at which point transmission would stall forever waiting for the resume TX + * message associated with the dropped confirm_rx message. + * Work around this by marking the flow as having a failed transmission and + * cause the next transmission attempt to be sent with the confirm_rx. + */ +static void qrtr_tx_flow_failed(struct qrtr_node *node, int dest_node, + int dest_port) +{ + unsigned long key = (u64)dest_node << 32 | dest_port; + struct qrtr_tx_flow *flow; + + rcu_read_lock(); + flow = radix_tree_lookup(&node->qrtr_tx_flow, key); + rcu_read_unlock(); + if (flow) { + spin_lock_irq(&flow->resume_tx.lock); + flow->tx_failed = 1; + spin_unlock_irq(&flow->resume_tx.lock); + } +} + /* Pass an outgoing packet socket buffer to the endpoint driver. */ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, int type, struct sockaddr_qrtr *from, @@ -179,6 +332,13 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, struct qrtr_hdr_v1 *hdr; size_t len = skb->len; int rc = -ENODEV; + int confirm_rx; + + confirm_rx = qrtr_tx_wait(node, to->sq_node, to->sq_port, type); + if (confirm_rx < 0) { + kfree_skb(skb); + return confirm_rx; + } hdr = skb_push(skb, sizeof(*hdr)); hdr->version = cpu_to_le32(QRTR_PROTO_VER_1); @@ -194,9 +354,9 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, } hdr->size = cpu_to_le32(len); - hdr->confirm_rx = 0; + hdr->confirm_rx = !!confirm_rx; - skb_put_padto(skb, ALIGN(len, 4)); + skb_put_padto(skb, ALIGN(len, 4) + sizeof(*hdr)); mutex_lock(&node->ep_lock); if (node->ep) @@ -205,6 +365,11 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, kfree_skb(skb); mutex_unlock(&node->ep_lock); + /* Need to ensure that a subsequent message carries the otherwise lost + * confirm_rx flag if we dropped this one */ + if (rc && confirm_rx) + qrtr_tx_flow_failed(node, to->sq_node, to->sq_port); + return rc; } @@ -215,11 +380,12 @@ static int qrtr_node_enqueue(struct qrtr_node *node, struct sk_buff *skb, static struct qrtr_node *qrtr_node_lookup(unsigned int nid) { struct qrtr_node *node; + unsigned long flags; - mutex_lock(&qrtr_node_lock); + spin_lock_irqsave(&qrtr_nodes_lock, flags); node = radix_tree_lookup(&qrtr_nodes, nid); node = qrtr_node_acquire(node); - mutex_unlock(&qrtr_node_lock); + spin_unlock_irqrestore(&qrtr_nodes_lock, flags); return node; } @@ -231,13 +397,15 @@ static struct qrtr_node *qrtr_node_lookup(unsigned int nid) */ static void qrtr_node_assign(struct qrtr_node *node, unsigned int nid) { + unsigned long flags; + if (node->nid != QRTR_EP_NID_AUTO || nid == QRTR_EP_NID_AUTO) return; - mutex_lock(&qrtr_node_lock); + spin_lock_irqsave(&qrtr_nodes_lock, flags); radix_tree_insert(&qrtr_nodes, nid, node); node->nid = nid; - mutex_unlock(&qrtr_node_lock); + spin_unlock_irqrestore(&qrtr_nodes_lock, flags); } /** @@ -253,6 +421,7 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) struct qrtr_node *node = ep->node; const struct qrtr_hdr_v1 *v1; const struct qrtr_hdr_v2 *v2; + struct qrtr_sock *ipc; struct sk_buff *skb; struct qrtr_cb *cb; unsigned int size; @@ -311,13 +480,26 @@ int qrtr_endpoint_post(struct qrtr_endpoint *ep, const void *data, size_t len) if (len != ALIGN(size, 4) + hdrlen) goto err; - if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA) + if (cb->dst_port != QRTR_PORT_CTRL && cb->type != QRTR_TYPE_DATA && + cb->type != QRTR_TYPE_RESUME_TX) goto err; skb_put_data(skb, data + hdrlen, size); - skb_queue_tail(&node->rx_queue, skb); - schedule_work(&node->work); + qrtr_node_assign(node, cb->src_node); + + if (cb->type == QRTR_TYPE_RESUME_TX) { + qrtr_tx_resume(node, skb); + } else { + ipc = qrtr_port_lookup(cb->dst_port); + if (!ipc) + goto err; + + if (sock_queue_rcv_skb(&ipc->sk, skb)) + goto err; + + qrtr_port_put(ipc); + } return 0; @@ -352,61 +534,6 @@ static struct sk_buff *qrtr_alloc_ctrl_packet(struct qrtr_ctrl_pkt **pkt) return skb; } -static struct qrtr_sock *qrtr_port_lookup(int port); -static void qrtr_port_put(struct qrtr_sock *ipc); - -/* Handle and route a received packet. - * - * This will auto-reply with resume-tx packet as necessary. - */ -static void qrtr_node_rx_work(struct work_struct *work) -{ - struct qrtr_node *node = container_of(work, struct qrtr_node, work); - struct qrtr_ctrl_pkt *pkt; - struct sockaddr_qrtr dst; - struct sockaddr_qrtr src; - struct sk_buff *skb; - - while ((skb = skb_dequeue(&node->rx_queue)) != NULL) { - struct qrtr_sock *ipc; - struct qrtr_cb *cb; - int confirm; - - cb = (struct qrtr_cb *)skb->cb; - src.sq_node = cb->src_node; - src.sq_port = cb->src_port; - dst.sq_node = cb->dst_node; - dst.sq_port = cb->dst_port; - confirm = !!cb->confirm_rx; - - qrtr_node_assign(node, cb->src_node); - - ipc = qrtr_port_lookup(cb->dst_port); - if (!ipc) { - kfree_skb(skb); - } else { - if (sock_queue_rcv_skb(&ipc->sk, skb)) - kfree_skb(skb); - - qrtr_port_put(ipc); - } - - if (confirm) { - skb = qrtr_alloc_ctrl_packet(&pkt); - if (!skb) - break; - - pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); - pkt->client.node = cpu_to_le32(dst.sq_node); - pkt->client.port = cpu_to_le32(dst.sq_port); - - if (qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, - &dst, &src)) - break; - } - } -} - /** * qrtr_endpoint_register() - register a new endpoint * @ep: endpoint to register @@ -426,13 +553,15 @@ int qrtr_endpoint_register(struct qrtr_endpoint *ep, unsigned int nid) if (!node) return -ENOMEM; - INIT_WORK(&node->work, qrtr_node_rx_work); kref_init(&node->ref); mutex_init(&node->ep_lock); skb_queue_head_init(&node->rx_queue); node->nid = QRTR_EP_NID_AUTO; node->ep = ep; + INIT_RADIX_TREE(&node->qrtr_tx_flow, GFP_KERNEL); + mutex_init(&node->qrtr_tx_lock); + qrtr_node_assign(node, nid); mutex_lock(&qrtr_node_lock); @@ -453,8 +582,11 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) struct qrtr_node *node = ep->node; struct sockaddr_qrtr src = {AF_QIPCRTR, node->nid, QRTR_PORT_CTRL}; struct sockaddr_qrtr dst = {AF_QIPCRTR, qrtr_local_nid, QRTR_PORT_CTRL}; + struct radix_tree_iter iter; struct qrtr_ctrl_pkt *pkt; + struct qrtr_tx_flow *flow; struct sk_buff *skb; + void __rcu **slot; mutex_lock(&node->ep_lock); node->ep = NULL; @@ -467,6 +599,14 @@ void qrtr_endpoint_unregister(struct qrtr_endpoint *ep) qrtr_local_enqueue(NULL, skb, QRTR_TYPE_BYE, &src, &dst); } + /* Wake up any transmitters waiting for resume-tx from the node */ + mutex_lock(&node->qrtr_tx_lock); + radix_tree_for_each_slot(slot, &node->qrtr_tx_flow, &iter, 0) { + flow = *slot; + wake_up_interruptible_all(&flow->resume_tx); + } + mutex_unlock(&node->qrtr_tx_lock); + qrtr_node_release(node); ep->node = NULL; } @@ -483,11 +623,11 @@ static struct qrtr_sock *qrtr_port_lookup(int port) if (port == QRTR_PORT_CTRL) port = 0; - mutex_lock(&qrtr_port_lock); + rcu_read_lock(); ipc = idr_find(&qrtr_ports, port); if (ipc) sock_hold(&ipc->sk); - mutex_unlock(&qrtr_port_lock); + rcu_read_unlock(); return ipc; } @@ -529,6 +669,10 @@ static void qrtr_port_remove(struct qrtr_sock *ipc) mutex_lock(&qrtr_port_lock); idr_remove(&qrtr_ports, port); mutex_unlock(&qrtr_port_lock); + + /* Ensure that if qrtr_port_lookup() did enter the RCU read section we + * wait for it to up increment the refcount */ + synchronize_rcu(); } /* Assign port number to socket. @@ -816,6 +960,34 @@ out_node: return rc; } +static int qrtr_send_resume_tx(struct qrtr_cb *cb) +{ + struct sockaddr_qrtr remote = { AF_QIPCRTR, cb->src_node, cb->src_port }; + struct sockaddr_qrtr local = { AF_QIPCRTR, cb->dst_node, cb->dst_port }; + struct qrtr_ctrl_pkt *pkt; + struct qrtr_node *node; + struct sk_buff *skb; + int ret; + + node = qrtr_node_lookup(remote.sq_node); + if (!node) + return -EINVAL; + + skb = qrtr_alloc_ctrl_packet(&pkt); + if (!skb) + return -ENOMEM; + + pkt->cmd = cpu_to_le32(QRTR_TYPE_RESUME_TX); + pkt->client.node = cpu_to_le32(cb->dst_node); + pkt->client.port = cpu_to_le32(cb->dst_port); + + ret = qrtr_node_enqueue(node, skb, QRTR_TYPE_RESUME_TX, &local, &remote); + + qrtr_node_release(node); + + return ret; +} + static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, size_t size, int flags) { @@ -838,6 +1010,7 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, release_sock(sk); return rc; } + cb = (struct qrtr_cb *)skb->cb; copied = skb->len; if (copied > size) { @@ -851,7 +1024,6 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, rc = copied; if (addr) { - cb = (struct qrtr_cb *)skb->cb; addr->sq_family = AF_QIPCRTR; addr->sq_node = cb->src_node; addr->sq_port = cb->src_port; @@ -859,6 +1031,9 @@ static int qrtr_recvmsg(struct socket *sock, struct msghdr *msg, } out: + if (cb->confirm_rx) + qrtr_send_resume_tx(cb); + skb_free_datagram(sk, skb); release_sock(sk); diff --git a/net/rds/ib.c b/net/rds/ib.c index 3fd5f40189bd..a792d8a3872a 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -156,6 +156,13 @@ static void rds_ib_add_one(struct ib_device *device) has_fmr = (device->ops.alloc_fmr && device->ops.dealloc_fmr && device->ops.map_phys_fmr && device->ops.unmap_fmr); rds_ibdev->use_fastreg = (has_fr && !has_fmr); + rds_ibdev->odp_capable = + !!(device->attrs.device_cap_flags & + IB_DEVICE_ON_DEMAND_PAGING) && + !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & + IB_ODP_SUPPORT_WRITE) && + !!(device->attrs.odp_caps.per_transport_caps.rc_odp_caps & + IB_ODP_SUPPORT_READ); rds_ibdev->fmr_max_remaps = device->attrs.max_map_per_fmr?: 32; rds_ibdev->max_1m_mrs = device->attrs.max_mr ? diff --git a/net/rds/ib.h b/net/rds/ib.h index 6e6f24753998..0296f1f7acda 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -247,7 +247,8 @@ struct rds_ib_device { struct ib_device *dev; struct ib_pd *pd; struct dma_pool *rid_hdrs_pool; /* RDS headers DMA pool */ - bool use_fastreg; + u8 use_fastreg:1; + u8 odp_capable:1; unsigned int max_mrs; struct rds_ib_mr_pool *mr_1m_pool; diff --git a/net/rds/ib_mr.h b/net/rds/ib_mr.h index 9045a8c0edff..0c8252d7fe2b 100644 --- a/net/rds/ib_mr.h +++ b/net/rds/ib_mr.h @@ -67,6 +67,7 @@ struct rds_ib_frmr { /* This is stored as mr->r_trans_private. */ struct rds_ib_mr { + struct delayed_work work; struct rds_ib_device *device; struct rds_ib_mr_pool *pool; struct rds_ib_connection *ic; @@ -81,9 +82,11 @@ struct rds_ib_mr { unsigned int sg_len; int sg_dma_len; + u8 odp:1; union { struct rds_ib_fmr fmr; struct rds_ib_frmr frmr; + struct ib_mr *mr; } u; }; @@ -122,12 +125,14 @@ void rds6_ib_get_mr_info(struct rds_ib_device *rds_ibdev, void rds_ib_destroy_mr_pool(struct rds_ib_mr_pool *); void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_sock *rs, u32 *key_ret, - struct rds_connection *conn); + struct rds_connection *conn, u64 start, u64 length, + int need_odp); void rds_ib_sync_mr(void *trans_private, int dir); void rds_ib_free_mr(void *trans_private, int invalidate); void rds_ib_flush_mrs(void); int rds_ib_mr_init(void); void rds_ib_mr_exit(void); +u32 rds_ib_get_lkey(void *trans_private); void __rds_ib_teardown_mr(struct rds_ib_mr *); void rds_ib_teardown_mr(struct rds_ib_mr *); diff --git a/net/rds/ib_rdma.c b/net/rds/ib_rdma.c index c8c1e3ae8d84..b34b24e237f8 100644 --- a/net/rds/ib_rdma.c +++ b/net/rds/ib_rdma.c @@ -37,8 +37,15 @@ #include "rds_single_path.h" #include "ib_mr.h" +#include "rds.h" struct workqueue_struct *rds_ib_mr_wq; +struct rds_ib_dereg_odp_mr { + struct work_struct work; + struct ib_mr *mr; +}; + +static void rds_ib_odp_mr_worker(struct work_struct *work); static struct rds_ib_device *rds_ib_get_device(__be32 ipaddr) { @@ -213,6 +220,9 @@ void rds_ib_sync_mr(void *trans_private, int direction) struct rds_ib_mr *ibmr = trans_private; struct rds_ib_device *rds_ibdev = ibmr->device; + if (ibmr->odp) + return; + switch (direction) { case DMA_FROM_DEVICE: ib_dma_sync_sg_for_cpu(rds_ibdev->dev, ibmr->sg, @@ -482,6 +492,16 @@ void rds_ib_free_mr(void *trans_private, int invalidate) rdsdebug("RDS/IB: free_mr nents %u\n", ibmr->sg_len); + if (ibmr->odp) { + /* A MR created and marked as use_once. We use delayed work, + * because there is a change that we are in interrupt and can't + * call to ib_dereg_mr() directly. + */ + INIT_DELAYED_WORK(&ibmr->work, rds_ib_odp_mr_worker); + queue_delayed_work(rds_ib_mr_wq, &ibmr->work, 0); + return; + } + /* Return it to the pool's free list */ if (rds_ibdev->use_fastreg) rds_ib_free_frmr_list(ibmr); @@ -526,9 +546,17 @@ void rds_ib_flush_mrs(void) up_read(&rds_ib_devices_lock); } +u32 rds_ib_get_lkey(void *trans_private) +{ + struct rds_ib_mr *ibmr = trans_private; + + return ibmr->u.mr->lkey; +} + void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, struct rds_sock *rs, u32 *key_ret, - struct rds_connection *conn) + struct rds_connection *conn, + u64 start, u64 length, int need_odp) { struct rds_ib_device *rds_ibdev; struct rds_ib_mr *ibmr = NULL; @@ -541,6 +569,51 @@ void *rds_ib_get_mr(struct scatterlist *sg, unsigned long nents, goto out; } + if (need_odp == ODP_ZEROBASED || need_odp == ODP_VIRTUAL) { + u64 virt_addr = need_odp == ODP_ZEROBASED ? 0 : start; + int access_flags = + (IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_READ | + IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_ATOMIC | + IB_ACCESS_ON_DEMAND); + struct ib_sge sge = {}; + struct ib_mr *ib_mr; + + if (!rds_ibdev->odp_capable) { + ret = -EOPNOTSUPP; + goto out; + } + + ib_mr = ib_reg_user_mr(rds_ibdev->pd, start, length, virt_addr, + access_flags); + + if (IS_ERR(ib_mr)) { + rdsdebug("rds_ib_get_user_mr returned %d\n", + IS_ERR(ib_mr)); + ret = PTR_ERR(ib_mr); + goto out; + } + if (key_ret) + *key_ret = ib_mr->rkey; + + ibmr = kzalloc(sizeof(*ibmr), GFP_KERNEL); + if (!ibmr) { + ib_dereg_mr(ib_mr); + ret = -ENOMEM; + goto out; + } + ibmr->u.mr = ib_mr; + ibmr->odp = 1; + + sge.addr = virt_addr; + sge.length = length; + sge.lkey = ib_mr->lkey; + + ib_advise_mr(rds_ibdev->pd, + IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE, + IB_UVERBS_ADVISE_MR_FLAG_FLUSH, &sge, 1); + return ibmr; + } + if (conn) ic = conn->c_transport_data; @@ -629,3 +702,12 @@ void rds_ib_mr_exit(void) { destroy_workqueue(rds_ib_mr_wq); } + +static void rds_ib_odp_mr_worker(struct work_struct *work) +{ + struct rds_ib_mr *ibmr; + + ibmr = container_of(work, struct rds_ib_mr, work.work); + ib_dereg_mr(ibmr->u.mr); + kfree(ibmr); +} diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index d1cc1d7778d8..dfe778220657 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -39,6 +39,7 @@ #include "rds_single_path.h" #include "rds.h" #include "ib.h" +#include "ib_mr.h" /* * Convert IB-specific error message to RDS error message and call core @@ -635,6 +636,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, send->s_sge[0].addr = ic->i_send_hdrs_dma[pos]; send->s_sge[0].length = sizeof(struct rds_header); + send->s_sge[0].lkey = ic->i_pd->local_dma_lkey; memcpy(ic->i_send_hdrs[pos], &rm->m_inc.i_hdr, sizeof(struct rds_header)); @@ -650,6 +652,7 @@ int rds_ib_xmit(struct rds_connection *conn, struct rds_message *rm, send->s_sge[1].addr = sg_dma_address(scat); send->s_sge[1].addr += rm->data.op_dmaoff; send->s_sge[1].length = len; + send->s_sge[1].lkey = ic->i_pd->local_dma_lkey; bytes_sent += len; rm->data.op_dmaoff += len; @@ -858,20 +861,29 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) int ret; int num_sge; int nr_sig = 0; + u64 odp_addr = op->op_odp_addr; + u32 odp_lkey = 0; /* map the op the first time we see it */ - if (!op->op_mapped) { - op->op_count = ib_dma_map_sg(ic->i_cm_id->device, - op->op_sg, op->op_nents, (op->op_write) ? - DMA_TO_DEVICE : DMA_FROM_DEVICE); - rdsdebug("ic %p mapping op %p: %d\n", ic, op, op->op_count); - if (op->op_count == 0) { - rds_ib_stats_inc(s_ib_tx_sg_mapping_failure); - ret = -ENOMEM; /* XXX ? */ - goto out; + if (!op->op_odp_mr) { + if (!op->op_mapped) { + op->op_count = + ib_dma_map_sg(ic->i_cm_id->device, op->op_sg, + op->op_nents, + (op->op_write) ? DMA_TO_DEVICE : + DMA_FROM_DEVICE); + rdsdebug("ic %p mapping op %p: %d\n", ic, op, + op->op_count); + if (op->op_count == 0) { + rds_ib_stats_inc(s_ib_tx_sg_mapping_failure); + ret = -ENOMEM; /* XXX ? */ + goto out; + } + op->op_mapped = 1; } - - op->op_mapped = 1; + } else { + op->op_count = op->op_nents; + odp_lkey = rds_ib_get_lkey(op->op_odp_mr->r_trans_private); } /* @@ -923,14 +935,20 @@ int rds_ib_xmit_rdma(struct rds_connection *conn, struct rm_rdma_op *op) for (j = 0; j < send->s_rdma_wr.wr.num_sge && scat != &op->op_sg[op->op_count]; j++) { len = sg_dma_len(scat); - send->s_sge[j].addr = sg_dma_address(scat); + if (!op->op_odp_mr) { + send->s_sge[j].addr = sg_dma_address(scat); + send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; + } else { + send->s_sge[j].addr = odp_addr; + send->s_sge[j].lkey = odp_lkey; + } send->s_sge[j].length = len; - send->s_sge[j].lkey = ic->i_pd->local_dma_lkey; sent += len; rdsdebug("ic %p sent %d remote_addr %llu\n", ic, sent, remote_addr); remote_addr += len; + odp_addr += len; scat++; } diff --git a/net/rds/rdma.c b/net/rds/rdma.c index 916f5ec373d8..3341eee87bf9 100644 --- a/net/rds/rdma.c +++ b/net/rds/rdma.c @@ -156,11 +156,13 @@ void rds_rdma_drop_keys(struct rds_sock *rs) static int rds_pin_pages(unsigned long user_addr, unsigned int nr_pages, struct page **pages, int write) { + unsigned int gup_flags = FOLL_LONGTERM; int ret; - ret = get_user_pages_fast(user_addr, nr_pages, write ? FOLL_WRITE : 0, - pages); + if (write) + gup_flags |= FOLL_WRITE; + ret = get_user_pages_fast(user_addr, nr_pages, gup_flags, pages); if (ret >= 0 && ret < nr_pages) { while (ret--) put_page(pages[ret]); @@ -175,13 +177,14 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, struct rds_conn_path *cp) { struct rds_mr *mr = NULL, *found; + struct scatterlist *sg = NULL; unsigned int nr_pages; struct page **pages = NULL; - struct scatterlist *sg; void *trans_private; unsigned long flags; rds_rdma_cookie_t cookie; - unsigned int nents; + unsigned int nents = 0; + int need_odp = 0; long i; int ret; @@ -195,6 +198,21 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, goto out; } + /* If the combination of the addr and size requested for this memory + * region causes an integer overflow, return error. + */ + if (((args->vec.addr + args->vec.bytes) < args->vec.addr) || + PAGE_ALIGN(args->vec.addr + args->vec.bytes) < + (args->vec.addr + args->vec.bytes)) { + ret = -EINVAL; + goto out; + } + + if (!can_do_mlock()) { + ret = -EPERM; + goto out; + } + nr_pages = rds_pages_in_vec(&args->vec); if (nr_pages == 0) { ret = -EINVAL; @@ -248,36 +266,44 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * the zero page. */ ret = rds_pin_pages(args->vec.addr, nr_pages, pages, 1); - if (ret < 0) - goto out; - - nents = ret; - sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); - if (!sg) { - ret = -ENOMEM; + if (ret == -EOPNOTSUPP) { + need_odp = 1; + } else if (ret <= 0) { goto out; - } - WARN_ON(!nents); - sg_init_table(sg, nents); - - /* Stick all pages into the scatterlist */ - for (i = 0 ; i < nents; i++) - sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); + } else { + nents = ret; + sg = kcalloc(nents, sizeof(*sg), GFP_KERNEL); + if (!sg) { + ret = -ENOMEM; + goto out; + } + WARN_ON(!nents); + sg_init_table(sg, nents); - rdsdebug("RDS: trans_private nents is %u\n", nents); + /* Stick all pages into the scatterlist */ + for (i = 0 ; i < nents; i++) + sg_set_page(&sg[i], pages[i], PAGE_SIZE, 0); + rdsdebug("RDS: trans_private nents is %u\n", nents); + } /* Obtain a transport specific MR. If this succeeds, the * s/g list is now owned by the MR. * Note that dma_map() implies that pending writes are * flushed to RAM, so no dma_sync is needed here. */ - trans_private = rs->rs_transport->get_mr(sg, nents, rs, - &mr->r_key, - cp ? cp->cp_conn : NULL); + trans_private = rs->rs_transport->get_mr( + sg, nents, rs, &mr->r_key, cp ? cp->cp_conn : NULL, + args->vec.addr, args->vec.bytes, + need_odp ? ODP_ZEROBASED : ODP_NOT_NEEDED); if (IS_ERR(trans_private)) { - for (i = 0 ; i < nents; i++) - put_page(sg_page(&sg[i])); - kfree(sg); + /* In ODP case, we don't GUP pages, so don't need + * to release anything. + */ + if (!need_odp) { + for (i = 0 ; i < nents; i++) + put_page(sg_page(&sg[i])); + kfree(sg); + } ret = PTR_ERR(trans_private); goto out; } @@ -291,7 +317,11 @@ static int __rds_rdma_map(struct rds_sock *rs, struct rds_get_mr_args *args, * map page aligned regions. So we keep the offset, and build * a 64bit cookie containing <R_Key, offset> and pass that * around. */ - cookie = rds_rdma_make_cookie(mr->r_key, args->vec.addr & ~PAGE_MASK); + if (need_odp) + cookie = rds_rdma_make_cookie(mr->r_key, 0); + else + cookie = rds_rdma_make_cookie(mr->r_key, + args->vec.addr & ~PAGE_MASK); if (cookie_ret) *cookie_ret = cookie; @@ -456,22 +486,26 @@ void rds_rdma_free_op(struct rm_rdma_op *ro) { unsigned int i; - for (i = 0; i < ro->op_nents; i++) { - struct page *page = sg_page(&ro->op_sg[i]); - - /* Mark page dirty if it was possibly modified, which - * is the case for a RDMA_READ which copies from remote - * to local memory */ - if (!ro->op_write) { - WARN_ON(!page->mapping && irqs_disabled()); - set_page_dirty(page); + if (ro->op_odp_mr) { + rds_mr_put(ro->op_odp_mr); + } else { + for (i = 0; i < ro->op_nents; i++) { + struct page *page = sg_page(&ro->op_sg[i]); + + /* Mark page dirty if it was possibly modified, which + * is the case for a RDMA_READ which copies from remote + * to local memory + */ + if (!ro->op_write) + set_page_dirty(page); + put_page(page); } - put_page(page); } kfree(ro->op_notifier); ro->op_notifier = NULL; ro->op_active = 0; + ro->op_odp_mr = NULL; } void rds_atomic_free_op(struct rm_atomic_op *ao) @@ -581,6 +615,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, struct rds_iovec *iovs; unsigned int i, j; int ret = 0; + bool odp_supported = true; if (cmsg->cmsg_len < CMSG_LEN(sizeof(struct rds_rdma_args)) || rm->rdma.op_active) @@ -602,6 +637,9 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, ret = -EINVAL; goto out_ret; } + /* odp-mr is not supported for multiple requests within one message */ + if (args->nr_local != 1) + odp_supported = false; iovs = vec->iov; @@ -623,6 +661,8 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, op->op_silent = !!(args->flags & RDS_RDMA_SILENT); op->op_active = 1; op->op_recverr = rs->rs_recverr; + op->op_odp_mr = NULL; + WARN_ON(!nr_pages); op->op_sg = rds_message_alloc_sgs(rm, nr_pages, &ret); if (!op->op_sg) @@ -672,10 +712,44 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, * If it's a READ operation, we need to pin the pages for writing. */ ret = rds_pin_pages(iov->addr, nr, pages, !op->op_write); - if (ret < 0) + if ((!odp_supported && ret <= 0) || + (odp_supported && ret <= 0 && ret != -EOPNOTSUPP)) goto out_pages; - else - ret = 0; + + if (ret == -EOPNOTSUPP) { + struct rds_mr *local_odp_mr; + + if (!rs->rs_transport->get_mr) { + ret = -EOPNOTSUPP; + goto out_pages; + } + local_odp_mr = + kzalloc(sizeof(*local_odp_mr), GFP_KERNEL); + if (!local_odp_mr) { + ret = -ENOMEM; + goto out_pages; + } + RB_CLEAR_NODE(&local_odp_mr->r_rb_node); + refcount_set(&local_odp_mr->r_refcount, 1); + local_odp_mr->r_trans = rs->rs_transport; + local_odp_mr->r_sock = rs; + local_odp_mr->r_trans_private = + rs->rs_transport->get_mr( + NULL, 0, rs, &local_odp_mr->r_key, NULL, + iov->addr, iov->bytes, ODP_VIRTUAL); + if (IS_ERR(local_odp_mr->r_trans_private)) { + ret = IS_ERR(local_odp_mr->r_trans_private); + rdsdebug("get_mr ret %d %p\"", ret, + local_odp_mr->r_trans_private); + kfree(local_odp_mr); + ret = -EOPNOTSUPP; + goto out_pages; + } + rdsdebug("Need odp; local_odp_mr %p trans_private %p\n", + local_odp_mr, local_odp_mr->r_trans_private); + op->op_odp_mr = local_odp_mr; + op->op_odp_addr = iov->addr; + } rdsdebug("RDS: nr_bytes %u nr %u iov->bytes %llu iov->addr %llx\n", nr_bytes, nr, iov->bytes, iov->addr); @@ -691,6 +765,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, min_t(unsigned int, iov->bytes, PAGE_SIZE - offset), offset); + sg_dma_len(sg) = sg->length; rdsdebug("RDS: sg->offset %x sg->len %x iov->addr %llx iov->bytes %llu\n", sg->offset, sg->length, iov->addr, iov->bytes); @@ -709,6 +784,7 @@ int rds_cmsg_rdma_args(struct rds_sock *rs, struct rds_message *rm, goto out_pages; } op->op_bytes = nr_bytes; + ret = 0; out_pages: kfree(pages); @@ -755,7 +831,8 @@ int rds_cmsg_rdma_dest(struct rds_sock *rs, struct rds_message *rm, spin_unlock_irqrestore(&rs->rs_rdma_lock, flags); if (mr) { - mr->r_trans->sync_mr(mr->r_trans_private, DMA_TO_DEVICE); + mr->r_trans->sync_mr(mr->r_trans_private, + DMA_TO_DEVICE); rm->rdma.op_rdma_mr = mr; } return err; diff --git a/net/rds/rds.h b/net/rds/rds.h index 53e86911773a..e4a603523083 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -40,7 +40,6 @@ #ifdef ATOMIC64_INIT #define KERNEL_HAS_ATOMIC64 #endif - #ifdef RDS_DEBUG #define rdsdebug(fmt, args...) pr_debug("%s(): " fmt, __func__ , ##args) #else @@ -478,6 +477,9 @@ struct rds_message { struct rds_notifier *op_notifier; struct rds_mr *op_rdma_mr; + + u64 op_odp_addr; + struct rds_mr *op_odp_mr; } rdma; struct rm_data_op { unsigned int op_active:1; @@ -573,7 +575,8 @@ struct rds_transport { void (*exit)(void); void *(*get_mr)(struct scatterlist *sg, unsigned long nr_sg, struct rds_sock *rs, u32 *key_ret, - struct rds_connection *conn); + struct rds_connection *conn, + u64 start, u64 length, int need_odp); void (*sync_mr)(void *trans_private, int direction); void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); @@ -956,6 +959,12 @@ static inline bool rds_destroy_pending(struct rds_connection *conn) (conn->c_trans->t_unloading && conn->c_trans->t_unloading(conn)); } +enum { + ODP_NOT_NEEDED, + ODP_ZEROBASED, + ODP_VIRTUAL +}; + /* stats.c */ DECLARE_PER_CPU_SHARED_ALIGNED(struct rds_statistics, rds_stats); #define rds_stats_inc_which(which, member) do { \ diff --git a/net/rose/rose_route.c b/net/rose/rose_route.c index c53307623236..5277631fa14c 100644 --- a/net/rose/rose_route.c +++ b/net/rose/rose_route.c @@ -696,7 +696,6 @@ struct rose_neigh *rose_get_neigh(rose_address *addr, unsigned char *cause, for (i = 0; i < node->count; i++) { if (!rose_ftimer_running(node->neighbour[i])) { res = node->neighbour[i]; - failed = 0; goto out; } failed = 1; diff --git a/net/sched/act_ctinfo.c b/net/sched/act_ctinfo.c index 40038c321b4a..19649623493b 100644 --- a/net/sched/act_ctinfo.c +++ b/net/sched/act_ctinfo.c @@ -360,6 +360,16 @@ static int tcf_ctinfo_search(struct net *net, struct tc_action **a, u32 index) return tcf_idr_search(tn, a, index); } +static void tcf_ctinfo_cleanup(struct tc_action *a) +{ + struct tcf_ctinfo *ci = to_ctinfo(a); + struct tcf_ctinfo_params *cp; + + cp = rcu_dereference_protected(ci->params, 1); + if (cp) + kfree_rcu(cp, rcu); +} + static struct tc_action_ops act_ctinfo_ops = { .kind = "ctinfo", .id = TCA_ID_CTINFO, @@ -367,6 +377,7 @@ static struct tc_action_ops act_ctinfo_ops = { .act = tcf_ctinfo_act, .dump = tcf_ctinfo_dump, .init = tcf_ctinfo_init, + .cleanup= tcf_ctinfo_cleanup, .walk = tcf_ctinfo_walker, .lookup = tcf_ctinfo_search, .size = sizeof(struct tcf_ctinfo), diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 5e6379028fc3..c1fcd85719d6 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -537,6 +537,9 @@ 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; @@ -566,10 +569,6 @@ 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/sch_cake.c b/net/sched/sch_cake.c index 6cc3ab145513..1496e87cd07b 100644 --- a/net/sched/sch_cake.c +++ b/net/sched/sch_cake.c @@ -1682,8 +1682,7 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, if (IS_ERR_OR_NULL(segs)) return qdisc_drop(skb, sch, to_free); - while (segs) { - nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; cobalt_set_enqueue_time(segs, now); @@ -1696,7 +1695,6 @@ static s32 cake_enqueue(struct sk_buff *skb, struct Qdisc *sch, slen += segs->len; q->buffer_used += segs->truesize; b->packets++; - segs = nskb; } /* stats */ @@ -1768,7 +1766,7 @@ 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); diff --git a/net/sched/sch_fq.c b/net/sched/sch_fq.c index ff4c5e9d0d77..a5a295477ecc 100644 --- a/net/sched/sch_fq.c +++ b/net/sched/sch_fq.c @@ -786,10 +786,12 @@ 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_prio.c b/net/sched/sch_prio.c index 18b884cfdfe8..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]); diff --git a/net/sched/sch_tbf.c b/net/sched/sch_tbf.c index 5f72f3f916a5..2cd94973795c 100644 --- a/net/sched/sch_tbf.c +++ b/net/sched/sch_tbf.c @@ -155,8 +155,7 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, return qdisc_drop(skb, sch, to_free); nb = 0; - while (segs) { - nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { skb_mark_not_on_list(segs); qdisc_skb_cb(segs)->pkt_len = segs->len; len += segs->len; @@ -167,7 +166,6 @@ static int tbf_segment(struct sk_buff *skb, struct Qdisc *sch, } else { nb++; } - segs = nskb; } sch->q.qlen += nb; if (nb > 1) diff --git a/net/sctp/sm_sideeffect.c b/net/sctp/sm_sideeffect.c index ce82699d0dca..2bc29463e1dc 100644 --- a/net/sctp/sm_sideeffect.c +++ b/net/sctp/sm_sideeffect.c @@ -1359,8 +1359,10 @@ 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)); @@ -1382,7 +1384,8 @@ 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)); @@ -1429,8 +1432,10 @@ 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; @@ -1766,11 +1771,17 @@ 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. @@ -1785,7 +1796,4 @@ out: sp->data_ready_signalled = 0; return error; -nomem: - error = -ENOMEM; - goto out; } diff --git a/net/smc/smc_pnet.c b/net/smc/smc_pnet.c index 82dedf052d86..2a5ed47c3e08 100644 --- a/net/smc/smc_pnet.c +++ b/net/smc/smc_pnet.c @@ -611,7 +611,7 @@ static const struct genl_ops smc_pnet_ops[] = { { .cmd = SMC_PNETID_GET, .validate = GENL_DONT_VALIDATE_STRICT | GENL_DONT_VALIDATE_DUMP, - .flags = GENL_ADMIN_PERM, + /* can be retrieved by unprivileged users */ .doit = smc_pnet_get, .dumpit = smc_pnet_dump, .start = smc_pnet_dump_start diff --git a/net/socket.c b/net/socket.c index 51bf34995bcb..b79a05de7c6e 100644 --- a/net/socket.c +++ b/net/socket.c @@ -128,7 +128,18 @@ static ssize_t sock_sendpage(struct file *file, struct page *page, static ssize_t sock_splice_read(struct file *file, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); -static void sock_show_fdinfo(struct seq_file *m, struct file *f); + +#ifdef CONFIG_PROC_FS +static void sock_show_fdinfo(struct seq_file *m, struct file *f) +{ + struct socket *sock = f->private_data; + + if (sock->ops->show_fdinfo) + sock->ops->show_fdinfo(m, sock); +} +#else +#define sock_show_fdinfo NULL +#endif /* * Socket files have a set of 'special' operations as well as the generic file ones. These don't appear @@ -151,9 +162,7 @@ static const struct file_operations socket_file_ops = { .sendpage = sock_sendpage, .splice_write = generic_splice_sendpage, .splice_read = sock_splice_read, -#ifdef CONFIG_PROC_FS .show_fdinfo = sock_show_fdinfo, -#endif }; /* @@ -997,14 +1006,6 @@ static ssize_t sock_write_iter(struct kiocb *iocb, struct iov_iter *from) return res; } -static void sock_show_fdinfo(struct seq_file *m, struct file *f) -{ - struct socket *sock = f->private_data; - - if (sock->ops->show_fdinfo) - sock->ops->show_fdinfo(m, sock); -} - /* * Atomic setting of ioctl hooks to avoid race * with module unload. diff --git a/net/sunrpc/xprtrdma/verbs.c b/net/sunrpc/xprtrdma/verbs.c index 77c7dd7f05e8..fda3889993cb 100644 --- a/net/sunrpc/xprtrdma/verbs.c +++ b/net/sunrpc/xprtrdma/verbs.c @@ -77,7 +77,7 @@ static void rpcrdma_sendctx_put_locked(struct rpcrdma_xprt *r_xprt, struct rpcrdma_sendctx *sc); static void rpcrdma_reqs_reset(struct rpcrdma_xprt *r_xprt); -static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf); +static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_create(struct rpcrdma_xprt *r_xprt); static void rpcrdma_mrs_destroy(struct rpcrdma_xprt *r_xprt); static struct rpcrdma_regbuf * @@ -244,6 +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); @@ -297,7 +298,6 @@ rpcrdma_create_id(struct rpcrdma_xprt *xprt, struct rpcrdma_ia *ia) int rc; 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); @@ -421,7 +421,7 @@ rpcrdma_ia_remove(struct rpcrdma_ia *ia) /* The ULP is responsible for ensuring all DMA * mappings and MRs are gone. */ - rpcrdma_reps_destroy(buf); + rpcrdma_reps_unmap(r_xprt); list_for_each_entry(req, &buf->rb_allreqs, rl_all) { rpcrdma_regbuf_dma_unmap(req->rl_rdmabuf); rpcrdma_regbuf_dma_unmap(req->rl_sendbuf); @@ -599,6 +599,7 @@ 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); @@ -613,6 +614,7 @@ 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); @@ -1090,6 +1092,7 @@ static struct rpcrdma_rep *rpcrdma_rep_create(struct rpcrdma_xprt *r_xprt, rep->rr_recv_wr.sg_list = &rep->rr_rdmabuf->rg_iov; rep->rr_recv_wr.num_sge = 1; rep->rr_temp = temp; + list_add(&rep->rr_all, &r_xprt->rx_buf.rb_all_reps); return rep; out_free: @@ -1100,6 +1103,7 @@ out: static void rpcrdma_rep_destroy(struct rpcrdma_rep *rep) { + list_del(&rep->rr_all); rpcrdma_regbuf_free(rep->rr_rdmabuf); kfree(rep); } @@ -1118,10 +1122,16 @@ static struct rpcrdma_rep *rpcrdma_rep_get_locked(struct rpcrdma_buffer *buf) static void rpcrdma_rep_put(struct rpcrdma_buffer *buf, struct rpcrdma_rep *rep) { - if (!rep->rr_temp) - llist_add(&rep->rr_node, &buf->rb_free_reps); - else - rpcrdma_rep_destroy(rep); + llist_add(&rep->rr_node, &buf->rb_free_reps); +} + +static void rpcrdma_reps_unmap(struct rpcrdma_xprt *r_xprt) +{ + struct rpcrdma_buffer *buf = &r_xprt->rx_buf; + struct rpcrdma_rep *rep; + + list_for_each_entry(rep, &buf->rb_all_reps, rr_all) + rpcrdma_regbuf_dma_unmap(rep->rr_rdmabuf); } static void rpcrdma_reps_destroy(struct rpcrdma_buffer *buf) @@ -1152,6 +1162,7 @@ int rpcrdma_buffer_create(struct rpcrdma_xprt *r_xprt) INIT_LIST_HEAD(&buf->rb_send_bufs); INIT_LIST_HEAD(&buf->rb_allreqs); + INIT_LIST_HEAD(&buf->rb_all_reps); rc = -ENOMEM; for (i = 0; i < buf->rb_max_requests; i++) { @@ -1504,6 +1515,10 @@ void rpcrdma_post_recvs(struct rpcrdma_xprt *r_xprt, bool temp) wr = NULL; while (needed) { rep = rpcrdma_rep_get_locked(buf); + if (rep && rep->rr_temp) { + rpcrdma_rep_destroy(rep); + continue; + } if (!rep) rep = rpcrdma_rep_create(r_xprt, temp); if (!rep) diff --git a/net/sunrpc/xprtrdma/xprt_rdma.h b/net/sunrpc/xprtrdma/xprt_rdma.h index 5d15140a0266..d796d68609ed 100644 --- a/net/sunrpc/xprtrdma/xprt_rdma.h +++ b/net/sunrpc/xprtrdma/xprt_rdma.h @@ -203,6 +203,7 @@ struct rpcrdma_rep { struct xdr_stream rr_stream; struct llist_node rr_node; struct ib_recv_wr rr_recv_wr; + struct list_head rr_all; }; /* To reduce the rate at which a transport invokes ib_post_recv @@ -368,6 +369,7 @@ struct rpcrdma_buffer { struct list_head rb_allreqs; struct list_head rb_all_mrs; + struct list_head rb_all_reps; struct llist_head rb_free_reps; diff --git a/net/tipc/Makefile b/net/tipc/Makefile index 11255e970dd4..ee49a9f1dd4f 100644 --- a/net/tipc/Makefile +++ b/net/tipc/Makefile @@ -9,7 +9,7 @@ tipc-y += addr.o bcast.o bearer.o \ core.o link.o discover.o msg.o \ name_distr.o subscr.o monitor.o name_table.o net.o \ netlink.o netlink_compat.o node.o socket.o eth_media.o \ - topsrv.o socket.o group.o trace.o + topsrv.o group.o trace.o CFLAGS_trace.o += -I$(src) @@ -20,5 +20,3 @@ tipc-$(CONFIG_TIPC_CRYPTO) += crypto.o obj-$(CONFIG_TIPC_DIAG) += diag.o - -tipc_diag-y := diag.o diff --git a/net/tipc/netlink_compat.c b/net/tipc/netlink_compat.c index 0254bb7e418b..217516357ef2 100644 --- a/net/tipc/netlink_compat.c +++ b/net/tipc/netlink_compat.c @@ -204,8 +204,8 @@ static int __tipc_nl_compat_dumpit(struct tipc_nl_compat_cmd_dump *cmd, return -ENOMEM; } - attrbuf = kmalloc_array(tipc_genl_family.maxattr + 1, - sizeof(struct nlattr *), GFP_KERNEL); + attrbuf = kcalloc(tipc_genl_family.maxattr + 1, + sizeof(struct nlattr *), GFP_KERNEL); if (!attrbuf) { err = -ENOMEM; goto err_out; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 6552f986774c..f9b4fb92c0b1 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -287,12 +287,12 @@ static void tipc_sk_respond(struct sock *sk, struct sk_buff *skb, int err) * * Caller must hold socket lock */ -static void tsk_rej_rx_queue(struct sock *sk) +static void tsk_rej_rx_queue(struct sock *sk, int error) { struct sk_buff *skb; while ((skb = __skb_dequeue(&sk->sk_receive_queue))) - tipc_sk_respond(sk, skb, TIPC_ERR_NO_PORT); + tipc_sk_respond(sk, skb, error); } static bool tipc_sk_connected(struct sock *sk) @@ -545,34 +545,45 @@ static void __tipc_shutdown(struct socket *sock, int error) /* Remove pending SYN */ __skb_queue_purge(&sk->sk_write_queue); - /* Reject all unreceived messages, except on an active connection - * (which disconnects locally & sends a 'FIN+' to peer). - */ - while ((skb = __skb_dequeue(&sk->sk_receive_queue)) != NULL) { - if (TIPC_SKB_CB(skb)->bytes_read) { - kfree_skb(skb); - continue; - } - if (!tipc_sk_type_connectionless(sk) && - sk->sk_state != TIPC_DISCONNECTING) { - tipc_set_sk_state(sk, TIPC_DISCONNECTING); - tipc_node_remove_conn(net, dnode, tsk->portid); - } - tipc_sk_respond(sk, skb, error); + /* Remove partially received buffer if any */ + skb = skb_peek(&sk->sk_receive_queue); + if (skb && TIPC_SKB_CB(skb)->bytes_read) { + __skb_unlink(skb, &sk->sk_receive_queue); + kfree_skb(skb); } - if (tipc_sk_type_connectionless(sk)) + /* Reject all unreceived messages if connectionless */ + if (tipc_sk_type_connectionless(sk)) { + tsk_rej_rx_queue(sk, error); return; + } - if (sk->sk_state != TIPC_DISCONNECTING) { + switch (sk->sk_state) { + case TIPC_CONNECTING: + case TIPC_ESTABLISHED: + tipc_set_sk_state(sk, TIPC_DISCONNECTING); + tipc_node_remove_conn(net, dnode, tsk->portid); + /* Send a FIN+/- to its peer */ + skb = __skb_dequeue(&sk->sk_receive_queue); + if (skb) { + __skb_queue_purge(&sk->sk_receive_queue); + tipc_sk_respond(sk, skb, error); + break; + } skb = tipc_msg_create(TIPC_CRITICAL_IMPORTANCE, TIPC_CONN_MSG, SHORT_H_SIZE, 0, dnode, tsk_own_node(tsk), tsk_peer_port(tsk), tsk->portid, error); if (skb) tipc_node_xmit_skb(net, skb, dnode, tsk->portid); - tipc_node_remove_conn(net, dnode, tsk->portid); - tipc_set_sk_state(sk, TIPC_DISCONNECTING); + break; + case TIPC_LISTEN: + /* Reject all SYN messages */ + tsk_rej_rx_queue(sk, error); + break; + default: + __skb_queue_purge(&sk->sk_receive_queue); + break; } } @@ -2432,8 +2443,8 @@ static int tipc_wait_for_connect(struct socket *sock, long *timeo_p) return sock_intr_errno(*timeo_p); add_wait_queue(sk_sleep(sk), &wait); - done = sk_wait_event(sk, timeo_p, - sk->sk_state != TIPC_CONNECTING, &wait); + done = sk_wait_event(sk, timeo_p, tipc_sk_connected(sk), + &wait); remove_wait_queue(sk_sleep(sk), &wait); } while (!done); return 0; @@ -2643,7 +2654,7 @@ static int tipc_accept(struct socket *sock, struct socket *new_sock, int flags, * Reject any stray messages received by new socket * before the socket lock was taken (very, very unlikely) */ - tsk_rej_rx_queue(new_sk); + tsk_rej_rx_queue(new_sk, TIPC_ERR_NO_PORT); /* Connect new socket to it's peer */ tipc_sk_finish_conn(new_tsock, msg_origport(msg), msg_orignode(msg)); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index dac24c7aa7d4..94774c0e5ff3 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -732,15 +732,19 @@ out: return rc; } -static void tls_update(struct sock *sk, struct proto *p) +static void tls_update(struct sock *sk, struct proto *p, + void (*write_space)(struct sock *sk)) { struct tls_context *ctx; ctx = tls_get_ctx(sk); - if (likely(ctx)) + if (likely(ctx)) { + ctx->sk_write_space = write_space; ctx->sk_proto = p; - else + } else { sk->sk_prot = p; + sk->sk_write_space = write_space; + } } static int tls_get_info(const struct sock *sk, struct sk_buff *skb) diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index c6803a82b769..c98e602a1a2d 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -256,8 +256,6 @@ static int tls_do_decryption(struct sock *sk, return ret; ret = crypto_wait_req(ret, &ctx->async_wait); - } else if (ret == -EBADMSG) { - TLS_INC_STATS(sock_net(sk), LINUX_MIB_TLSDECRYPTERROR); } if (async) @@ -682,12 +680,32 @@ 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); } @@ -709,6 +727,12 @@ 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, &msg_pl->sg.data[i]); @@ -772,7 +796,7 @@ static int bpf_exec_tx_verdict(struct sk_msg *msg, struct sock *sk, psock = sk_psock_get(sk); if (!psock || !policy) { err = tls_push_record(sk, flags, record_type); - if (err) { + if (err && err != -EINPROGRESS) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); } @@ -783,10 +807,7 @@ more_data: 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) { @@ -801,7 +822,7 @@ more_data: switch (psock->eval) { case __SK_PASS: err = tls_push_record(sk, flags, record_type); - if (err < 0) { + if (err && err != -EINPROGRESS) { *copied -= sk_msg_free(sk, msg); tls_free_open_rec(sk); goto out_err; @@ -1515,7 +1536,9 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, if (err == -EINPROGRESS) tls_advance_record_sn(sk, prot, &tls_ctx->rx); - + else if (err == -EBADMSG) + TLS_INC_STATS(sock_net(sk), + LINUX_MIB_TLSDECRYPTERROR); return err; } } else { diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 6756a3ccc392..321af97c7bbe 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -2100,8 +2100,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, mutex_lock(&u->iolock); skip = sk_peek_offset(sk, flags); - skb = __skb_try_recv_datagram(sk, flags, scm_stat_del, - &skip, &err, &last); + skb = __skb_try_recv_datagram(sk, &sk->sk_receive_queue, flags, + scm_stat_del, &skip, &err, &last); if (skb) break; @@ -2110,7 +2110,8 @@ static int unix_dgram_recvmsg(struct socket *sock, struct msghdr *msg, if (err != -EAGAIN) break; } while (timeo && - !__skb_wait_for_more_packets(sk, &err, &timeo, last)); + !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, + &err, &timeo, last)); if (!skb) { /* implies iolock unlocked */ unix_state_lock(sk); diff --git a/net/vmw_vsock/hyperv_transport.c b/net/vmw_vsock/hyperv_transport.c index b3bdae74c243..3492c021925f 100644 --- a/net/vmw_vsock/hyperv_transport.c +++ b/net/vmw_vsock/hyperv_transport.c @@ -138,28 +138,15 @@ 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 guid_t srv_id_template = GUID_INIT(0x00000000, 0xfacb, 0x11e6, 0xbd, 0x58, @@ -184,34 +171,6 @@ static void hvs_addr_init(struct sockaddr_vm *addr, const guid_t *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; - - /* Remote peer is always the host */ - vsock_addr_init(remote, VMADDR_CID_HOST, 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, @@ -341,12 +300,7 @@ 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); @@ -371,8 +325,11 @@ static void hvs_open_connection(struct vmbus_channel *chan) vnew = vsock_sk(new); 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); ret = vsock_assign_transport(vnew, vsock_sk(sk)); /* Transport assigned (looking at remote_addr) must be the * same where we received the request. @@ -766,16 +723,6 @@ 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/wireless/nl80211.c b/net/wireless/nl80211.c index fa3526592c51..123b8d720a59 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -10843,6 +10843,7 @@ 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; @@ -13795,6 +13796,8 @@ 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); } 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 446c76d44e65..fff9a74891fc 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2261,14 +2261,15 @@ 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)) @@ -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 */ @@ -3885,6 +3892,25 @@ bool regulatory_pre_cac_allowed(struct wiphy *wiphy) } EXPORT_SYMBOL(regulatory_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, @@ -3911,8 +3937,10 @@ 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 7a6c38ddc65a..d32a2ec4d96a 100644 --- a/net/wireless/sme.c +++ b/net/wireless/sme.c @@ -1307,14 +1307,14 @@ 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 d98ad2b3143b..8677d7ab7d69 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 5b4ed5bbc542..8481e9ac33da 100644 --- a/net/wireless/util.c +++ b/net/wireless/util.c @@ -564,7 +564,7 @@ __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 2efe44a34644..d5b09bbff375 100644 --- a/net/x25/af_x25.c +++ b/net/x25/af_x25.c @@ -766,6 +766,10 @@ 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; @@ -812,7 +816,7 @@ 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/xfrm/Makefile b/net/xfrm/Makefile index fbc4552d17b8..212a4fcb4a88 100644 --- a/net/xfrm/Makefile +++ b/net/xfrm/Makefile @@ -11,3 +11,4 @@ obj-$(CONFIG_XFRM_ALGO) += xfrm_algo.o obj-$(CONFIG_XFRM_USER) += xfrm_user.o obj-$(CONFIG_XFRM_IPCOMP) += xfrm_ipcomp.o obj-$(CONFIG_XFRM_INTERFACE) += xfrm_interface.o +obj-$(CONFIG_INET_ESPINTCP) += espintcp.o diff --git a/net/xfrm/espintcp.c b/net/xfrm/espintcp.c new file mode 100644 index 000000000000..f15d6a564b0e --- /dev/null +++ b/net/xfrm/espintcp.c @@ -0,0 +1,509 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <net/tcp.h> +#include <net/strparser.h> +#include <net/xfrm.h> +#include <net/esp.h> +#include <net/espintcp.h> +#include <linux/skmsg.h> +#include <net/inet_common.h> + +static void handle_nonesp(struct espintcp_ctx *ctx, struct sk_buff *skb, + struct sock *sk) +{ + if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf || + !sk_rmem_schedule(sk, skb, skb->truesize)) { + kfree_skb(skb); + return; + } + + skb_set_owner_r(skb, sk); + + memset(skb->cb, 0, sizeof(skb->cb)); + skb_queue_tail(&ctx->ike_queue, skb); + ctx->saved_data_ready(sk); +} + +static void handle_esp(struct sk_buff *skb, struct sock *sk) +{ + skb_reset_transport_header(skb); + memset(skb->cb, 0, sizeof(skb->cb)); + + rcu_read_lock(); + skb->dev = dev_get_by_index_rcu(sock_net(sk), skb->skb_iif); + local_bh_disable(); + xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, TCP_ENCAP_ESPINTCP); + local_bh_enable(); + rcu_read_unlock(); +} + +static void espintcp_rcv(struct strparser *strp, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = container_of(strp, struct espintcp_ctx, + strp); + struct strp_msg *rxm = strp_msg(skb); + u32 nonesp_marker; + int err; + + err = skb_copy_bits(skb, rxm->offset + 2, &nonesp_marker, + sizeof(nonesp_marker)); + if (err < 0) { + kfree_skb(skb); + return; + } + + /* remove header, leave non-ESP marker/SPI */ + if (!__pskb_pull(skb, rxm->offset + 2)) { + kfree_skb(skb); + return; + } + + if (pskb_trim(skb, rxm->full_len - 2) != 0) { + kfree_skb(skb); + return; + } + + if (nonesp_marker == 0) + handle_nonesp(ctx, skb, strp->sk); + else + handle_esp(skb, strp->sk); +} + +static int espintcp_parse(struct strparser *strp, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + __be16 blen; + u16 len; + int err; + + if (skb->len < rxm->offset + 2) + return 0; + + err = skb_copy_bits(skb, rxm->offset, &blen, sizeof(blen)); + if (err < 0) + return err; + + len = be16_to_cpu(blen); + if (len < 6) + return -EINVAL; + + return len; +} + +static int espintcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, + int nonblock, int flags, int *addr_len) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct sk_buff *skb; + int err = 0; + int copied; + int off = 0; + + flags |= nonblock ? MSG_DONTWAIT : 0; + + skb = __skb_recv_datagram(sk, &ctx->ike_queue, flags, NULL, &off, &err); + if (!skb) + return err; + + copied = len; + if (copied > skb->len) + copied = skb->len; + else if (copied < skb->len) + msg->msg_flags |= MSG_TRUNC; + + err = skb_copy_datagram_msg(skb, 0, msg, copied); + if (unlikely(err)) { + kfree_skb(skb); + return err; + } + + if (flags & MSG_TRUNC) + copied = skb->len; + kfree_skb(skb); + return copied; +} + +int espintcp_queue_out(struct sock *sk, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + if (skb_queue_len(&ctx->out_queue) >= netdev_max_backlog) + return -ENOBUFS; + + __skb_queue_tail(&ctx->out_queue, skb); + + return 0; +} +EXPORT_SYMBOL_GPL(espintcp_queue_out); + +/* espintcp length field is 2B and length includes the length field's size */ +#define MAX_ESPINTCP_MSG (((1 << 16) - 1) - 2) + +static int espintcp_sendskb_locked(struct sock *sk, struct espintcp_msg *emsg, + int flags) +{ + do { + int ret; + + ret = skb_send_sock_locked(sk, emsg->skb, + emsg->offset, emsg->len); + if (ret < 0) + return ret; + + emsg->len -= ret; + emsg->offset += ret; + } while (emsg->len > 0); + + kfree_skb(emsg->skb); + memset(emsg, 0, sizeof(*emsg)); + + return 0; +} + +static int espintcp_sendskmsg_locked(struct sock *sk, + struct espintcp_msg *emsg, int flags) +{ + struct sk_msg *skmsg = &emsg->skmsg; + struct scatterlist *sg; + int done = 0; + int ret; + + flags |= MSG_SENDPAGE_NOTLAST; + sg = &skmsg->sg.data[skmsg->sg.start]; + do { + size_t size = sg->length - emsg->offset; + int offset = sg->offset + emsg->offset; + struct page *p; + + emsg->offset = 0; + + if (sg_is_last(sg)) + flags &= ~MSG_SENDPAGE_NOTLAST; + + p = sg_page(sg); +retry: + ret = do_tcp_sendpages(sk, p, offset, size, flags); + if (ret < 0) { + emsg->offset = offset - sg->offset; + skmsg->sg.start += done; + return ret; + } + + if (ret != size) { + offset += ret; + size -= ret; + goto retry; + } + + done++; + put_page(p); + sk_mem_uncharge(sk, sg->length); + sg = sg_next(sg); + } while (sg); + + memset(emsg, 0, sizeof(*emsg)); + + return 0; +} + +static int espintcp_push_msgs(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + int err; + + if (!emsg->len) + return 0; + + if (ctx->tx_running) + return -EAGAIN; + ctx->tx_running = 1; + + if (emsg->skb) + err = espintcp_sendskb_locked(sk, emsg, 0); + else + err = espintcp_sendskmsg_locked(sk, emsg, 0); + if (err == -EAGAIN) { + ctx->tx_running = 0; + return 0; + } + if (!err) + memset(emsg, 0, sizeof(*emsg)); + + ctx->tx_running = 0; + + return err; +} + +int espintcp_push_skb(struct sock *sk, struct sk_buff *skb) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + unsigned int len; + int offset; + + if (sk->sk_state != TCP_ESTABLISHED) { + kfree_skb(skb); + return -ECONNRESET; + } + + offset = skb_transport_offset(skb); + len = skb->len - offset; + + espintcp_push_msgs(sk); + + if (emsg->len) { + kfree_skb(skb); + return -ENOBUFS; + } + + skb_set_owner_w(skb, sk); + + emsg->offset = offset; + emsg->len = len; + emsg->skb = skb; + + espintcp_push_msgs(sk); + + return 0; +} +EXPORT_SYMBOL_GPL(espintcp_push_skb); + +static int espintcp_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + struct iov_iter pfx_iter; + struct kvec pfx_iov = {}; + size_t msglen = size + 2; + char buf[2] = {0}; + int err, end; + + if (msg->msg_flags) + return -EOPNOTSUPP; + + if (size > MAX_ESPINTCP_MSG) + return -EMSGSIZE; + + if (msg->msg_controllen) + return -EOPNOTSUPP; + + lock_sock(sk); + + err = espintcp_push_msgs(sk); + if (err < 0) { + err = -ENOBUFS; + goto unlock; + } + + sk_msg_init(&emsg->skmsg); + while (1) { + /* only -ENOMEM is possible since we don't coalesce */ + err = sk_msg_alloc(sk, &emsg->skmsg, msglen, 0); + if (!err) + break; + + err = sk_stream_wait_memory(sk, &timeo); + if (err) + goto fail; + } + + *((__be16 *)buf) = cpu_to_be16(msglen); + pfx_iov.iov_base = buf; + pfx_iov.iov_len = sizeof(buf); + iov_iter_kvec(&pfx_iter, WRITE, &pfx_iov, 1, pfx_iov.iov_len); + + err = sk_msg_memcopy_from_iter(sk, &pfx_iter, &emsg->skmsg, + pfx_iov.iov_len); + if (err < 0) + goto fail; + + err = sk_msg_memcopy_from_iter(sk, &msg->msg_iter, &emsg->skmsg, size); + if (err < 0) + goto fail; + + end = emsg->skmsg.sg.end; + emsg->len = size; + sk_msg_iter_var_prev(end); + sg_mark_end(sk_msg_elem(&emsg->skmsg, end)); + + tcp_rate_check_app_limited(sk); + + err = espintcp_push_msgs(sk); + /* this message could be partially sent, keep it */ + if (err < 0) + goto unlock; + release_sock(sk); + + return size; + +fail: + sk_msg_free(sk, &emsg->skmsg); + memset(emsg, 0, sizeof(*emsg)); +unlock: + release_sock(sk); + return err; +} + +static struct proto espintcp_prot __ro_after_init; +static struct proto_ops espintcp_ops __ro_after_init; + +static void espintcp_data_ready(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + strp_data_ready(&ctx->strp); +} + +static void espintcp_tx_work(struct work_struct *work) +{ + struct espintcp_ctx *ctx = container_of(work, + struct espintcp_ctx, work); + struct sock *sk = ctx->strp.sk; + + lock_sock(sk); + if (!ctx->tx_running) + espintcp_push_msgs(sk); + release_sock(sk); +} + +static void espintcp_write_space(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + schedule_work(&ctx->work); + ctx->saved_write_space(sk); +} + +static void espintcp_destruct(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + kfree(ctx); +} + +bool tcp_is_ulp_esp(struct sock *sk) +{ + return sk->sk_prot == &espintcp_prot; +} +EXPORT_SYMBOL_GPL(tcp_is_ulp_esp); + +static int espintcp_init_sk(struct sock *sk) +{ + struct inet_connection_sock *icsk = inet_csk(sk); + struct strp_callbacks cb = { + .rcv_msg = espintcp_rcv, + .parse_msg = espintcp_parse, + }; + struct espintcp_ctx *ctx; + int err; + + /* sockmap is not compatible with espintcp */ + if (sk->sk_user_data) + return -EBUSY; + + ctx = kzalloc(sizeof(*ctx), GFP_KERNEL); + if (!ctx) + return -ENOMEM; + + err = strp_init(&ctx->strp, sk, &cb); + if (err) + goto free; + + __sk_dst_reset(sk); + + strp_check_rcv(&ctx->strp); + skb_queue_head_init(&ctx->ike_queue); + skb_queue_head_init(&ctx->out_queue); + sk->sk_prot = &espintcp_prot; + sk->sk_socket->ops = &espintcp_ops; + ctx->saved_data_ready = sk->sk_data_ready; + ctx->saved_write_space = sk->sk_write_space; + sk->sk_data_ready = espintcp_data_ready; + sk->sk_write_space = espintcp_write_space; + sk->sk_destruct = espintcp_destruct; + rcu_assign_pointer(icsk->icsk_ulp_data, ctx); + INIT_WORK(&ctx->work, espintcp_tx_work); + + /* avoid using task_frag */ + sk->sk_allocation = GFP_ATOMIC; + + return 0; + +free: + kfree(ctx); + return err; +} + +static void espintcp_release(struct sock *sk) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct sk_buff_head queue; + struct sk_buff *skb; + + __skb_queue_head_init(&queue); + skb_queue_splice_init(&ctx->out_queue, &queue); + + while ((skb = __skb_dequeue(&queue))) + espintcp_push_skb(sk, skb); + + tcp_release_cb(sk); +} + +static void espintcp_close(struct sock *sk, long timeout) +{ + struct espintcp_ctx *ctx = espintcp_getctx(sk); + struct espintcp_msg *emsg = &ctx->partial; + + strp_stop(&ctx->strp); + + sk->sk_prot = &tcp_prot; + barrier(); + + cancel_work_sync(&ctx->work); + strp_done(&ctx->strp); + + skb_queue_purge(&ctx->out_queue); + skb_queue_purge(&ctx->ike_queue); + + if (emsg->len) { + if (emsg->skb) + kfree_skb(emsg->skb); + else + sk_msg_free(sk, &emsg->skmsg); + } + + tcp_close(sk, timeout); +} + +static __poll_t espintcp_poll(struct file *file, struct socket *sock, + poll_table *wait) +{ + __poll_t mask = datagram_poll(file, sock, wait); + struct sock *sk = sock->sk; + struct espintcp_ctx *ctx = espintcp_getctx(sk); + + if (!skb_queue_empty(&ctx->ike_queue)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static struct tcp_ulp_ops espintcp_ulp __read_mostly = { + .name = "espintcp", + .owner = THIS_MODULE, + .init = espintcp_init_sk, +}; + +void __init espintcp_init(void) +{ + memcpy(&espintcp_prot, &tcp_prot, sizeof(tcp_prot)); + memcpy(&espintcp_ops, &inet_stream_ops, sizeof(inet_stream_ops)); + espintcp_prot.sendmsg = espintcp_sendmsg; + espintcp_prot.recvmsg = espintcp_recvmsg; + espintcp_prot.close = espintcp_close; + espintcp_prot.release_cb = espintcp_release; + espintcp_ops.poll = espintcp_poll; + + tcp_register_ulp(&espintcp_ulp); +} diff --git a/net/xfrm/xfrm_device.c b/net/xfrm/xfrm_device.c index 189ef15acbbc..50f567a88f45 100644 --- a/net/xfrm/xfrm_device.c +++ b/net/xfrm/xfrm_device.c @@ -78,7 +78,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur int err; unsigned long flags; struct xfrm_state *x; - struct sk_buff *skb2; + struct sk_buff *skb2, *nskb; struct softnet_data *sd; netdev_features_t esp_features = features; struct xfrm_offload *xo = xfrm_offload(skb); @@ -148,11 +148,7 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur return skb; } - skb2 = skb; - - do { - struct sk_buff *nskb = skb2->next; - + skb_list_walk_safe(skb, skb2, nskb) { esp_features |= skb->dev->gso_partial_features; skb_mark_not_on_list(skb2); @@ -176,14 +172,11 @@ struct sk_buff *validate_xmit_xfrm(struct sk_buff *skb, netdev_features_t featur if (!skb) return NULL; - goto skip_push; + continue; } skb_push(skb2, skb2->data - skb_mac_header(skb2)); - -skip_push: - skb2 = nskb; - } while (skb2); + } return skb; } diff --git a/net/xfrm/xfrm_input.c b/net/xfrm/xfrm_input.c index 2c86a2fc3915..aa35f23c4912 100644 --- a/net/xfrm/xfrm_input.c +++ b/net/xfrm/xfrm_input.c @@ -36,6 +36,7 @@ struct xfrm_trans_cb { #endif } header; int (*finish)(struct net *net, struct sock *sk, struct sk_buff *skb); + struct net *net; }; #define XFRM_TRANS_SKB_CB(__skb) ((struct xfrm_trans_cb *)&((__skb)->cb[0])) @@ -766,12 +767,13 @@ static void xfrm_trans_reinject(unsigned long data) skb_queue_splice_init(&trans->queue, &queue); while ((skb = __skb_dequeue(&queue))) - XFRM_TRANS_SKB_CB(skb)->finish(dev_net(skb->dev), NULL, skb); + XFRM_TRANS_SKB_CB(skb)->finish(XFRM_TRANS_SKB_CB(skb)->net, + NULL, skb); } -int xfrm_trans_queue(struct sk_buff *skb, - int (*finish)(struct net *, struct sock *, - struct sk_buff *)) +int xfrm_trans_queue_net(struct net *net, struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) { struct xfrm_trans_tasklet *trans; @@ -780,11 +782,22 @@ int xfrm_trans_queue(struct sk_buff *skb, if (skb_queue_len(&trans->queue) >= netdev_max_backlog) return -ENOBUFS; + BUILD_BUG_ON(sizeof(struct xfrm_trans_cb) > sizeof(skb->cb)); + XFRM_TRANS_SKB_CB(skb)->finish = finish; + XFRM_TRANS_SKB_CB(skb)->net = net; __skb_queue_tail(&trans->queue, skb); tasklet_schedule(&trans->tasklet); return 0; } +EXPORT_SYMBOL(xfrm_trans_queue_net); + +int xfrm_trans_queue(struct sk_buff *skb, + int (*finish)(struct net *, struct sock *, + struct sk_buff *)) +{ + return xfrm_trans_queue_net(dev_net(skb->dev), skb, finish); +} EXPORT_SYMBOL(xfrm_trans_queue); void __init xfrm_input_init(void) diff --git a/net/xfrm/xfrm_output.c b/net/xfrm/xfrm_output.c index b1db55b50ba1..fafc7aba705f 100644 --- a/net/xfrm/xfrm_output.c +++ b/net/xfrm/xfrm_output.c @@ -533,7 +533,7 @@ static int xfrm_output2(struct net *net, struct sock *sk, struct sk_buff *skb) static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb) { - struct sk_buff *segs; + struct sk_buff *segs, *nskb; BUILD_BUG_ON(sizeof(*IPCB(skb)) > SKB_SGO_CB_OFFSET); BUILD_BUG_ON(sizeof(*IP6CB(skb)) > SKB_SGO_CB_OFFSET); @@ -544,8 +544,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb if (segs == NULL) return -EINVAL; - do { - struct sk_buff *nskb = segs->next; + skb_list_walk_safe(segs, segs, nskb) { int err; skb_mark_not_on_list(segs); @@ -555,9 +554,7 @@ static int xfrm_output_gso(struct net *net, struct sock *sk, struct sk_buff *skb kfree_skb_list(nskb); return err; } - - segs = nskb; - } while (segs); + } return 0; } diff --git a/net/xfrm/xfrm_policy.c b/net/xfrm/xfrm_policy.c index f2d1e573ea55..297d1eb79e5c 100644 --- a/net/xfrm/xfrm_policy.c +++ b/net/xfrm/xfrm_policy.c @@ -39,6 +39,9 @@ #ifdef CONFIG_XFRM_STATISTICS #include <net/snmp.h> #endif +#ifdef CONFIG_INET_ESPINTCP +#include <net/espintcp.h> +#endif #include "xfrm_hash.h" @@ -4157,6 +4160,10 @@ void __init xfrm_init(void) seqcount_init(&xfrm_policy_hash_generation); xfrm_input_init(); +#ifdef CONFIG_INET_ESPINTCP + espintcp_init(); +#endif + RCU_INIT_POINTER(xfrm_if_cb, NULL); synchronize_rcu(); } diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index f3423562d933..170d6e7f31d3 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -670,6 +670,9 @@ int __xfrm_state_delete(struct xfrm_state *x) net->xfrm.state_num--; spin_unlock(&net->xfrm.xfrm_state_lock); + if (x->encap_sk) + sock_put(rcu_dereference_raw(x->encap_sk)); + xfrm_dev_state_delete(x); /* All xfrm_state objects are created by xfrm_state_alloc. |