diff options
Diffstat (limited to 'net')
270 files changed, 10263 insertions, 4392 deletions
diff --git a/net/batman-adv/Kconfig b/net/batman-adv/Kconfig index c386e6981416..a31db5e9ac8e 100644 --- a/net/batman-adv/Kconfig +++ b/net/batman-adv/Kconfig @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: # # Marek Lindner, Simon Wunderlich # diff --git a/net/batman-adv/Makefile b/net/batman-adv/Makefile index 9b58160fe485..a887ecc3efa1 100644 --- a/net/batman-adv/Makefile +++ b/net/batman-adv/Makefile @@ -1,5 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -# Copyright (C) 2007-2018 B.A.T.M.A.N. contributors: +# Copyright (C) 2007-2019 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 ea309ad06175..7b7e15641fef 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 534b790c3753..25e7bb51928c 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 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 f97e566f0402..de61091af666 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 3dc6a7a43eb7..785f6666273c 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 90e33f84d37a..445594ed58af 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) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 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 ec4a2a569750..465a4fc23354 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 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 ef0dec20c7d8..a9b7919c9de5 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing, Marek Lindner * diff --git a/net/batman-adv/bat_v_elp.h b/net/batman-adv/bat_v_elp.h index e8c7b7fd290d..75f189ee4a1c 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) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 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 2948b41b06d4..c9698ad41854 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) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 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 e5be14c908c6..f67cf7ee06b2 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) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * diff --git a/net/batman-adv/bitarray.c b/net/batman-adv/bitarray.c index a296a4d851f5..63e134e763e3 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) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 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 48f683289531..f3a05ad9afad 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) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 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 5fdde2947802..ef39aabdb694 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/bridge_loop_avoidance.h b/net/batman-adv/bridge_loop_avoidance.h index 71f95a3e4d3f..31771c751efb 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Simon Wunderlich * diff --git a/net/batman-adv/debugfs.c b/net/batman-adv/debugfs.c index d4a7702e48d8..3b9d1ad2f467 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/debugfs.h b/net/batman-adv/debugfs.h index 8de018e5c577..c0b8694041ec 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 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 b9ffe1826527..310a4f353008 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -19,6 +19,7 @@ #include "distributed-arp-table.h" #include "main.h" +#include <asm/unaligned.h> #include <linux/atomic.h> #include <linux/bitops.h> #include <linux/byteorder/generic.h> @@ -29,6 +30,7 @@ #include <linux/if_ether.h> #include <linux/if_vlan.h> #include <linux/in.h> +#include <linux/ip.h> #include <linux/jiffies.h> #include <linux/kernel.h> #include <linux/kref.h> @@ -42,6 +44,7 @@ #include <linux/spinlock.h> #include <linux/stddef.h> #include <linux/string.h> +#include <linux/udp.h> #include <linux/workqueue.h> #include <net/arp.h> #include <net/genetlink.h> @@ -60,6 +63,49 @@ #include "translation-table.h" #include "tvlv.h" +enum batadv_bootpop { + BATADV_BOOTREPLY = 2, +}; + +enum batadv_boothtype { + BATADV_HTYPE_ETHERNET = 1, +}; + +enum batadv_dhcpoptioncode { + BATADV_DHCP_OPT_PAD = 0, + BATADV_DHCP_OPT_MSG_TYPE = 53, + BATADV_DHCP_OPT_END = 255, +}; + +enum batadv_dhcptype { + BATADV_DHCPACK = 5, +}; + +/* { 99, 130, 83, 99 } */ +#define BATADV_DHCP_MAGIC 1669485411 + +struct batadv_dhcp_packet { + __u8 op; + __u8 htype; + __u8 hlen; + __u8 hops; + __be32 xid; + __be16 secs; + __be16 flags; + __be32 ciaddr; + __be32 yiaddr; + __be32 siaddr; + __be32 giaddr; + __u8 chaddr[16]; + __u8 sname[64]; + __u8 file[128]; + __be32 magic; + __u8 options[0]; +}; + +#define BATADV_DHCP_YIADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->yiaddr) +#define BATADV_DHCP_CHADDR_LEN sizeof(((struct batadv_dhcp_packet *)0)->chaddr) + static void batadv_dat_purge(struct work_struct *work); /** @@ -1440,6 +1486,361 @@ out: } /** + * batadv_dat_check_dhcp_ipudp() - check skb for IP+UDP headers valid for DHCP + * @skb: the packet to check + * @ip_src: a buffer to store the IPv4 source address in + * + * Checks whether the given skb has an IP and UDP header valid for a DHCP + * message from a DHCP server. And if so, stores the IPv4 source address in + * the provided buffer. + * + * Return: True if valid, false otherwise. + */ +static bool +batadv_dat_check_dhcp_ipudp(struct sk_buff *skb, __be32 *ip_src) +{ + unsigned int offset = skb_network_offset(skb); + struct udphdr *udphdr, _udphdr; + struct iphdr *iphdr, _iphdr; + + iphdr = skb_header_pointer(skb, offset, sizeof(_iphdr), &_iphdr); + if (!iphdr || iphdr->version != 4 || iphdr->ihl * 4 < sizeof(_iphdr)) + return false; + + if (iphdr->protocol != IPPROTO_UDP) + return false; + + offset += iphdr->ihl * 4; + skb_set_transport_header(skb, offset); + + udphdr = skb_header_pointer(skb, offset, sizeof(_udphdr), &_udphdr); + if (!udphdr || udphdr->source != htons(67)) + return false; + + *ip_src = get_unaligned(&iphdr->saddr); + + return true; +} + +/** + * batadv_dat_check_dhcp() - examine packet for valid DHCP message + * @skb: the packet to check + * @proto: ethernet protocol hint (behind a potential vlan) + * @ip_src: a buffer to store the IPv4 source address in + * + * Checks whether the given skb is a valid DHCP packet. And if so, stores the + * IPv4 source address in the provided buffer. + * + * Caller needs to ensure that the skb network header is set correctly. + * + * Return: If skb is a valid DHCP packet, then returns its op code + * (e.g. BOOTREPLY vs. BOOTREQUEST). Otherwise returns -EINVAL. + */ +static int +batadv_dat_check_dhcp(struct sk_buff *skb, __be16 proto, __be32 *ip_src) +{ + __be32 *magic, _magic; + unsigned int offset; + struct { + __u8 op; + __u8 htype; + __u8 hlen; + __u8 hops; + } *dhcp_h, _dhcp_h; + + if (proto != htons(ETH_P_IP)) + return -EINVAL; + + if (!batadv_dat_check_dhcp_ipudp(skb, ip_src)) + return -EINVAL; + + offset = skb_transport_offset(skb) + sizeof(struct udphdr); + if (skb->len < offset + sizeof(struct batadv_dhcp_packet)) + return -EINVAL; + + dhcp_h = skb_header_pointer(skb, offset, sizeof(_dhcp_h), &_dhcp_h); + if (!dhcp_h || dhcp_h->htype != BATADV_HTYPE_ETHERNET || + dhcp_h->hlen != ETH_ALEN) + return -EINVAL; + + offset += offsetof(struct batadv_dhcp_packet, magic); + + magic = skb_header_pointer(skb, offset, sizeof(_magic), &_magic); + if (!magic || get_unaligned(magic) != htonl(BATADV_DHCP_MAGIC)) + return -EINVAL; + + return dhcp_h->op; +} + +/** + * batadv_dat_get_dhcp_message_type() - get message type of a DHCP packet + * @skb: the DHCP packet to parse + * + * Iterates over the DHCP options of the given DHCP packet to find a + * DHCP Message Type option and parse it. + * + * Caller needs to ensure that the given skb is a valid DHCP packet and + * that the skb transport header is set correctly. + * + * Return: The found DHCP message type value, if found. -EINVAL otherwise. + */ +static int batadv_dat_get_dhcp_message_type(struct sk_buff *skb) +{ + unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); + u8 *type, _type; + struct { + u8 type; + u8 len; + } *tl, _tl; + + offset += sizeof(struct batadv_dhcp_packet); + + while ((tl = skb_header_pointer(skb, offset, sizeof(_tl), &_tl))) { + if (tl->type == BATADV_DHCP_OPT_MSG_TYPE) + break; + + if (tl->type == BATADV_DHCP_OPT_END) + break; + + if (tl->type == BATADV_DHCP_OPT_PAD) + offset++; + else + offset += tl->len + sizeof(_tl); + } + + /* Option Overload Code not supported */ + if (!tl || tl->type != BATADV_DHCP_OPT_MSG_TYPE || + tl->len != sizeof(_type)) + return -EINVAL; + + offset += sizeof(_tl); + + type = skb_header_pointer(skb, offset, sizeof(_type), &_type); + if (!type) + return -EINVAL; + + return *type; +} + +/** + * batadv_dat_get_dhcp_yiaddr() - get yiaddr from a DHCP packet + * @skb: the DHCP packet to parse + * @buf: a buffer to store the yiaddr in + * + * Caller needs to ensure that the given skb is a valid DHCP packet and + * that the skb transport header is set correctly. + * + * Return: True on success, false otherwise. + */ +static bool batadv_dat_dhcp_get_yiaddr(struct sk_buff *skb, __be32 *buf) +{ + unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); + __be32 *yiaddr; + + offset += offsetof(struct batadv_dhcp_packet, yiaddr); + yiaddr = skb_header_pointer(skb, offset, BATADV_DHCP_YIADDR_LEN, buf); + + if (!yiaddr) + return false; + + if (yiaddr != buf) + *buf = get_unaligned(yiaddr); + + return true; +} + +/** + * batadv_dat_get_dhcp_chaddr() - get chaddr from a DHCP packet + * @skb: the DHCP packet to parse + * @buf: a buffer to store the chaddr in + * + * Caller needs to ensure that the given skb is a valid DHCP packet and + * that the skb transport header is set correctly. + * + * Return: True on success, false otherwise + */ +static bool batadv_dat_get_dhcp_chaddr(struct sk_buff *skb, u8 *buf) +{ + unsigned int offset = skb_transport_offset(skb) + sizeof(struct udphdr); + u8 *chaddr; + + offset += offsetof(struct batadv_dhcp_packet, chaddr); + chaddr = skb_header_pointer(skb, offset, BATADV_DHCP_CHADDR_LEN, buf); + + if (!chaddr) + return false; + + if (chaddr != buf) + memcpy(buf, chaddr, BATADV_DHCP_CHADDR_LEN); + + return true; +} + +/** + * batadv_dat_put_dhcp() - puts addresses from a DHCP packet into the DHT and + * DAT cache + * @bat_priv: the bat priv with all the soft interface information + * @chaddr: the DHCP client MAC address + * @yiaddr: the DHCP client IP address + * @hw_dst: the DHCP server MAC address + * @ip_dst: the DHCP server IP address + * @vid: VLAN identifier + * + * Adds given MAC/IP pairs to the local DAT cache and propagates them further + * into the DHT. + * + * For the DHT propagation, client MAC + IP will appear as the ARP Reply + * transmitter (and hw_dst/ip_dst as the target). + */ +static void batadv_dat_put_dhcp(struct batadv_priv *bat_priv, u8 *chaddr, + __be32 yiaddr, u8 *hw_dst, __be32 ip_dst, + unsigned short vid) +{ + struct sk_buff *skb; + + skb = batadv_dat_arp_create_reply(bat_priv, yiaddr, ip_dst, chaddr, + hw_dst, vid); + if (!skb) + return; + + skb_set_network_header(skb, ETH_HLEN); + + batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid); + batadv_dat_entry_add(bat_priv, ip_dst, hw_dst, vid); + + batadv_dat_send_data(bat_priv, skb, yiaddr, vid, BATADV_P_DAT_DHT_PUT); + batadv_dat_send_data(bat_priv, skb, ip_dst, vid, BATADV_P_DAT_DHT_PUT); + + consume_skb(skb); + + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from outgoing DHCPACK (server address): %pI4, %pM (vid: %i)\n", + &ip_dst, hw_dst, batadv_print_vid(vid)); + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from outgoing DHCPACK (client address): %pI4, %pM (vid: %i)\n", + &yiaddr, chaddr, batadv_print_vid(vid)); +} + +/** + * batadv_dat_check_dhcp_ack() - examine packet for valid DHCP message + * @skb: the packet to check + * @proto: ethernet protocol hint (behind a potential vlan) + * @ip_src: a buffer to store the IPv4 source address in + * @chaddr: a buffer to store the DHCP Client Hardware Address in + * @yiaddr: a buffer to store the DHCP Your IP Address in + * + * Checks whether the given skb is a valid DHCPACK. And if so, stores the + * IPv4 server source address (ip_src), client MAC address (chaddr) and client + * IPv4 address (yiaddr) in the provided buffers. + * + * Caller needs to ensure that the skb network header is set correctly. + * + * Return: True if the skb is a valid DHCPACK. False otherwise. + */ +static bool +batadv_dat_check_dhcp_ack(struct sk_buff *skb, __be16 proto, __be32 *ip_src, + u8 *chaddr, __be32 *yiaddr) +{ + int type; + + type = batadv_dat_check_dhcp(skb, proto, ip_src); + if (type != BATADV_BOOTREPLY) + return false; + + type = batadv_dat_get_dhcp_message_type(skb); + if (type != BATADV_DHCPACK) + return false; + + if (!batadv_dat_dhcp_get_yiaddr(skb, yiaddr)) + return false; + + if (!batadv_dat_get_dhcp_chaddr(skb, chaddr)) + return false; + + return true; +} + +/** + * batadv_dat_snoop_outgoing_dhcp_ack() - snoop DHCPACK and fill DAT with it + * @bat_priv: the bat priv with all the soft interface information + * @skb: the packet to snoop + * @proto: ethernet protocol hint (behind a potential vlan) + * @vid: VLAN identifier + * + * This function first checks whether the given skb is a valid DHCPACK. If + * so then its source MAC and IP as well as its DHCP Client Hardware Address + * field and DHCP Your IP Address field are added to the local DAT cache and + * propagated into the DHT. + * + * Caller needs to ensure that the skb mac and network headers are set + * correctly. + */ +void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, + __be16 proto, + unsigned short vid) +{ + u8 chaddr[BATADV_DHCP_CHADDR_LEN]; + __be32 ip_src, yiaddr; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + return; + + if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr)) + return; + + batadv_dat_put_dhcp(bat_priv, chaddr, yiaddr, eth_hdr(skb)->h_source, + ip_src, vid); +} + +/** + * batadv_dat_snoop_incoming_dhcp_ack() - snoop DHCPACK and fill DAT cache + * @bat_priv: the bat priv with all the soft interface information + * @skb: the packet to snoop + * @hdr_size: header size, up to the tail of the batman-adv header + * + * This function first checks whether the given skb is a valid DHCPACK. If + * so then its source MAC and IP as well as its DHCP Client Hardware Address + * field and DHCP Your IP Address field are added to the local DAT cache. + */ +void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ + u8 chaddr[BATADV_DHCP_CHADDR_LEN]; + struct ethhdr *ethhdr; + __be32 ip_src, yiaddr; + unsigned short vid; + __be16 proto; + u8 *hw_src; + + if (!atomic_read(&bat_priv->distributed_arp_table)) + return; + + if (unlikely(!pskb_may_pull(skb, hdr_size + ETH_HLEN))) + return; + + ethhdr = (struct ethhdr *)(skb->data + hdr_size); + skb_set_network_header(skb, hdr_size + ETH_HLEN); + proto = ethhdr->h_proto; + + if (!batadv_dat_check_dhcp_ack(skb, proto, &ip_src, chaddr, &yiaddr)) + return; + + hw_src = ethhdr->h_source; + vid = batadv_dat_get_vid(skb, &hdr_size); + + batadv_dat_entry_add(bat_priv, yiaddr, chaddr, vid); + batadv_dat_entry_add(bat_priv, ip_src, hw_src, vid); + + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from incoming DHCPACK (server address): %pI4, %pM (vid: %i)\n", + &ip_src, hw_src, batadv_print_vid(vid)); + batadv_dbg(BATADV_DBG_DAT, bat_priv, + "Snooped from incoming DHCPACK (client address): %pI4, %pM (vid: %i)\n", + &yiaddr, chaddr, batadv_print_vid(vid)); +} + +/** * batadv_dat_drop_broadcast_packet() - check if an ARP request has to be * dropped (because the node has already obtained the reply via DAT) or not * @bat_priv: the bat priv with all the soft interface information diff --git a/net/batman-adv/distributed-arp-table.h b/net/batman-adv/distributed-arp-table.h index a04596028337..68c0ff321acd 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) 2011-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2011-2019 B.A.T.M.A.N. contributors: * * Antonio Quartulli * @@ -46,6 +46,12 @@ void batadv_dat_snoop_outgoing_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb); bool batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, struct sk_buff *skb, int hdr_size); +void batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, + __be16 proto, + unsigned short vid); +void batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size); bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet); @@ -140,6 +146,19 @@ batadv_dat_snoop_incoming_arp_reply(struct batadv_priv *bat_priv, return false; } +static inline void +batadv_dat_snoop_outgoing_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, __be16 proto, + unsigned short vid) +{ +} + +static inline void +batadv_dat_snoop_incoming_dhcp_ack(struct batadv_priv *bat_priv, + struct sk_buff *skb, int hdr_size) +{ +} + static inline bool batadv_dat_drop_broadcast_packet(struct batadv_priv *bat_priv, struct batadv_forw_packet *forw_packet) diff --git a/net/batman-adv/fragmentation.c b/net/batman-adv/fragmentation.c index 5b71a289d04f..b506d15b8230 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) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 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 944512e07782..abdac26579bf 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) 2013-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2013-2019 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 9d8e5eda2314..f5811f61aa92 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) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -47,7 +47,6 @@ #include <uapi/linux/batadv_packet.h> #include <uapi/linux/batman_adv.h> -#include "gateway_common.h" #include "hard-interface.h" #include "log.h" #include "netlink.h" diff --git a/net/batman-adv/gateway_client.h b/net/batman-adv/gateway_client.h index f0b86fcb2493..b5732c8be81a 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) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 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 936c107f3199..e064de45e22c 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) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -28,6 +28,7 @@ #include <linux/stddef.h> #include <linux/string.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "gateway_client.h" #include "log.h" diff --git a/net/batman-adv/gateway_common.h b/net/batman-adv/gateway_common.h index 80afb2793687..128467a0fb89 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) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -25,12 +25,6 @@ struct net_device; -enum batadv_gw_modes { - BATADV_GW_MODE_OFF, - BATADV_GW_MODE_CLIENT, - BATADV_GW_MODE_SERVER, -}; - /** * enum batadv_bandwidth_units - bandwidth unit types */ diff --git a/net/batman-adv/hard-interface.c b/net/batman-adv/hard-interface.c index 415d494cbe22..96ef7c70b4d9 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 d1c0f6189301..48de28c83401 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 9194f4d891b1..56a08ce193d5 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) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 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 0e36fa1c7c3e..37507b6d4006 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) 2006-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2006-2019 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 6d5859714f52..9859ababb82e 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 958be22beda9..5f8926522ff0 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c index 75f602e1ce94..3e610df8debf 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/log.h b/net/batman-adv/log.h index 35f4f397ed57..660e9bcc85a2 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/batman-adv/main.c b/net/batman-adv/main.c index d1ed839fd32b..75750870cf04 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 b572066325e4..3ed669d7dc6b 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -25,7 +25,7 @@ #define BATADV_DRIVER_DEVICE "batman-adv" #ifndef BATADV_SOURCE_VERSION -#define BATADV_SOURCE_VERSION "2019.0" +#define BATADV_SOURCE_VERSION "2019.1" #endif /* B.A.T.M.A.N. parameters */ diff --git a/net/batman-adv/multicast.c b/net/batman-adv/multicast.c index 69244e4598f5..f91b1b6265cf 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) 2014-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing * @@ -674,7 +674,7 @@ static void batadv_mcast_mla_update(struct work_struct *work) */ static bool batadv_mcast_is_report_ipv4(struct sk_buff *skb) { - if (ip_mc_check_igmp(skb, NULL) < 0) + if (ip_mc_check_igmp(skb) < 0) return false; switch (igmp_hdr(skb)->type) { @@ -741,7 +741,7 @@ static int batadv_mcast_forw_mode_check_ipv4(struct batadv_priv *bat_priv, */ static bool batadv_mcast_is_report_ipv6(struct sk_buff *skb) { - if (ipv6_mc_check_mld(skb, NULL) < 0) + if (ipv6_mc_check_mld(skb) < 0) return false; switch (icmp6_hdr(skb)->icmp6_type) { diff --git a/net/batman-adv/multicast.h b/net/batman-adv/multicast.h index 3b04ab13f0eb..466013fe88af 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) 2014-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2014-2019 B.A.T.M.A.N. contributors: * * Linus Lüssing * diff --git a/net/batman-adv/netlink.c b/net/batman-adv/netlink.c index 2dc3304cee54..67a58da2e6a0 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) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * @@ -20,13 +20,17 @@ #include "main.h" #include <linux/atomic.h> +#include <linux/bitops.h> +#include <linux/bug.h> #include <linux/byteorder/generic.h> #include <linux/cache.h> +#include <linux/err.h> #include <linux/errno.h> #include <linux/export.h> #include <linux/genetlink.h> #include <linux/gfp.h> #include <linux/if_ether.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/kernel.h> #include <linux/list.h> @@ -47,21 +51,54 @@ #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" #include "gateway_client.h" +#include "gateway_common.h" #include "hard-interface.h" +#include "log.h" #include "multicast.h" +#include "network-coding.h" #include "originator.h" #include "soft-interface.h" #include "tp_meter.h" #include "translation-table.h" +struct net; + struct genl_family batadv_netlink_family; /* multicast groups */ enum batadv_netlink_multicast_groups { + BATADV_NL_MCGRP_CONFIG, BATADV_NL_MCGRP_TPMETER, }; +/** + * enum batadv_genl_ops_flags - flags for genl_ops's internal_flags + */ +enum batadv_genl_ops_flags { + /** + * @BATADV_FLAG_NEED_MESH: request requires valid soft interface in + * attribute BATADV_ATTR_MESH_IFINDEX and expects a pointer to it to be + * saved in info->user_ptr[0] + */ + BATADV_FLAG_NEED_MESH = BIT(0), + + /** + * @BATADV_FLAG_NEED_HARDIF: request requires valid hard interface in + * attribute BATADV_ATTR_HARD_IFINDEX and expects a pointer to it to be + * saved in info->user_ptr[1] + */ + BATADV_FLAG_NEED_HARDIF = BIT(1), + + /** + * @BATADV_FLAG_NEED_VLAN: request requires valid vlan in + * attribute BATADV_ATTR_VLANID and expects a pointer to it to be + * saved in info->user_ptr[1] + */ + BATADV_FLAG_NEED_VLAN = BIT(2), +}; + static const struct genl_multicast_group batadv_netlink_mcgrps[] = { + [BATADV_NL_MCGRP_CONFIG] = { .name = BATADV_NL_MCAST_GROUP_CONFIG }, [BATADV_NL_MCGRP_TPMETER] = { .name = BATADV_NL_MCAST_GROUP_TPMETER }, }; @@ -104,6 +141,26 @@ static const struct nla_policy batadv_netlink_policy[NUM_BATADV_ATTR] = { [BATADV_ATTR_DAT_CACHE_VID] = { .type = NLA_U16 }, [BATADV_ATTR_MCAST_FLAGS] = { .type = NLA_U32 }, [BATADV_ATTR_MCAST_FLAGS_PRIV] = { .type = NLA_U32 }, + [BATADV_ATTR_VLANID] = { .type = NLA_U16 }, + [BATADV_ATTR_AGGREGATED_OGMS_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_AP_ISOLATION_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_ISOLATION_MARK] = { .type = NLA_U32 }, + [BATADV_ATTR_ISOLATION_MASK] = { .type = NLA_U32 }, + [BATADV_ATTR_BONDING_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_FRAGMENTATION_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_GW_BANDWIDTH_DOWN] = { .type = NLA_U32 }, + [BATADV_ATTR_GW_BANDWIDTH_UP] = { .type = NLA_U32 }, + [BATADV_ATTR_GW_MODE] = { .type = NLA_U8 }, + [BATADV_ATTR_GW_SEL_CLASS] = { .type = NLA_U32 }, + [BATADV_ATTR_HOP_PENALTY] = { .type = NLA_U8 }, + [BATADV_ATTR_LOG_LEVEL] = { .type = NLA_U32 }, + [BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_NETWORK_CODING_ENABLED] = { .type = NLA_U8 }, + [BATADV_ATTR_ORIG_INTERVAL] = { .type = NLA_U32 }, + [BATADV_ATTR_ELP_INTERVAL] = { .type = NLA_U32 }, + [BATADV_ATTR_THROUGHPUT_OVERRIDE] = { .type = NLA_U32 }, }; /** @@ -122,20 +179,75 @@ batadv_netlink_get_ifindex(const struct nlmsghdr *nlh, int attrtype) } /** - * batadv_netlink_mesh_info_put() - fill in generic information about mesh - * interface - * @msg: netlink message to be sent back - * @soft_iface: interface for which the data should be taken + * batadv_netlink_mesh_fill_ap_isolation() - Add ap_isolation softif attribute + * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information * - * Return: 0 on success, < 0 on error + * Return: 0 on success or negative error number in case of failure */ -static int -batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) +static int batadv_netlink_mesh_fill_ap_isolation(struct sk_buff *msg, + struct batadv_priv *bat_priv) +{ + struct batadv_softif_vlan *vlan; + u8 ap_isolation; + + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (!vlan) + return 0; + + ap_isolation = atomic_read(&vlan->ap_isolation); + batadv_softif_vlan_put(vlan); + + return nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, + !!ap_isolation); +} + +/** + * batadv_option_set_ap_isolation() - Set ap_isolation from genl msg + * @attr: parsed BATADV_ATTR_AP_ISOLATION_ENABLED attribute + * @bat_priv: the bat priv with all the soft interface information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_mesh_ap_isolation(struct nlattr *attr, + struct batadv_priv *bat_priv) +{ + struct batadv_softif_vlan *vlan; + + vlan = batadv_softif_vlan_get(bat_priv, BATADV_NO_FLAGS); + if (!vlan) + return -ENOENT; + + atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); + batadv_softif_vlan_put(vlan); + + return 0; +} + +/** + * batadv_netlink_mesh_fill() - Fill message with mesh attributes + * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information + * @cmd: type of message to generate + * @portid: Port making netlink request + * @seq: sequence number for message + * @flags: Additional flags for message + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_mesh_fill(struct sk_buff *msg, + struct batadv_priv *bat_priv, + enum batadv_nl_commands cmd, + u32 portid, u32 seq, int flags) { - struct batadv_priv *bat_priv = netdev_priv(soft_iface); + struct net_device *soft_iface = bat_priv->soft_iface; struct batadv_hard_iface *primary_if = NULL; struct net_device *hard_iface; - int ret = -ENOBUFS; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); + if (!hdr) + return -ENOBUFS; if (nla_put_string(msg, BATADV_ATTR_VERSION, BATADV_SOURCE_VERSION) || nla_put_string(msg, BATADV_ATTR_ALGO_NAME, @@ -146,16 +258,16 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) soft_iface->dev_addr) || nla_put_u8(msg, BATADV_ATTR_TT_TTVN, (u8)atomic_read(&bat_priv->tt.vn))) - goto out; + goto nla_put_failure; #ifdef CONFIG_BATMAN_ADV_BLA if (nla_put_u16(msg, BATADV_ATTR_BLA_CRC, ntohs(bat_priv->bla.claim_dest.group))) - goto out; + goto nla_put_failure; #endif if (batadv_mcast_mesh_info_put(msg, bat_priv)) - goto out; + goto nla_put_failure; primary_if = batadv_primary_if_get_selected(bat_priv); if (primary_if && primary_if->if_status == BATADV_IF_ACTIVE) { @@ -167,77 +279,345 @@ batadv_netlink_mesh_info_put(struct sk_buff *msg, struct net_device *soft_iface) hard_iface->name) || nla_put(msg, BATADV_ATTR_HARD_ADDRESS, ETH_ALEN, hard_iface->dev_addr)) - goto out; + goto nla_put_failure; } - ret = 0; + if (nla_put_u8(msg, BATADV_ATTR_AGGREGATED_OGMS_ENABLED, + !!atomic_read(&bat_priv->aggregated_ogms))) + goto nla_put_failure; + + if (batadv_netlink_mesh_fill_ap_isolation(msg, bat_priv)) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MARK, + bat_priv->isolation_mark)) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_ISOLATION_MASK, + bat_priv->isolation_mark_mask)) + goto nla_put_failure; + + if (nla_put_u8(msg, BATADV_ATTR_BONDING_ENABLED, + !!atomic_read(&bat_priv->bonding))) + goto nla_put_failure; + +#ifdef CONFIG_BATMAN_ADV_BLA + if (nla_put_u8(msg, BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED, + !!atomic_read(&bat_priv->bridge_loop_avoidance))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_BLA */ + +#ifdef CONFIG_BATMAN_ADV_DAT + if (nla_put_u8(msg, BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED, + !!atomic_read(&bat_priv->distributed_arp_table))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_DAT */ + + if (nla_put_u8(msg, BATADV_ATTR_FRAGMENTATION_ENABLED, + !!atomic_read(&bat_priv->fragmentation))) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_DOWN, + atomic_read(&bat_priv->gw.bandwidth_down))) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_GW_BANDWIDTH_UP, + atomic_read(&bat_priv->gw.bandwidth_up))) + goto nla_put_failure; + + if (nla_put_u8(msg, BATADV_ATTR_GW_MODE, + atomic_read(&bat_priv->gw.mode))) + goto nla_put_failure; + + if (bat_priv->algo_ops->gw.get_best_gw_node && + bat_priv->algo_ops->gw.is_eligible) { + /* GW selection class is not available if the routing algorithm + * in use does not implement the GW API + */ + if (nla_put_u32(msg, BATADV_ATTR_GW_SEL_CLASS, + atomic_read(&bat_priv->gw.sel_class))) + goto nla_put_failure; + } + + if (nla_put_u8(msg, BATADV_ATTR_HOP_PENALTY, + atomic_read(&bat_priv->hop_penalty))) + goto nla_put_failure; + +#ifdef CONFIG_BATMAN_ADV_DEBUG + if (nla_put_u32(msg, BATADV_ATTR_LOG_LEVEL, + atomic_read(&bat_priv->log_level))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_DEBUG */ + +#ifdef CONFIG_BATMAN_ADV_MCAST + if (nla_put_u8(msg, BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED, + !atomic_read(&bat_priv->multicast_mode))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_MCAST */ + +#ifdef CONFIG_BATMAN_ADV_NC + if (nla_put_u8(msg, BATADV_ATTR_NETWORK_CODING_ENABLED, + !!atomic_read(&bat_priv->network_coding))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_NC */ + + if (nla_put_u32(msg, BATADV_ATTR_ORIG_INTERVAL, + atomic_read(&bat_priv->orig_interval))) + goto nla_put_failure; - out: if (primary_if) batadv_hardif_put(primary_if); - return ret; + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + if (primary_if) + batadv_hardif_put(primary_if); + + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; } /** - * batadv_netlink_get_mesh_info() - handle incoming BATADV_CMD_GET_MESH_INFO - * netlink request - * @skb: received netlink message - * @info: receiver information + * batadv_netlink_notify_mesh() - send softif attributes to listener + * @bat_priv: the bat priv with all the soft interface information * * Return: 0 on success, < 0 on error */ -static int -batadv_netlink_get_mesh_info(struct sk_buff *skb, struct genl_info *info) +int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv) { - struct net *net = genl_info_net(info); - struct net_device *soft_iface; - struct sk_buff *msg = NULL; - void *msg_head; - int ifindex; + struct sk_buff *msg; int ret; - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return -EINVAL; - - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); - if (!ifindex) - return -EINVAL; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; + ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_SET_MESH, + 0, 0, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; } + genlmsg_multicast_netns(&batadv_netlink_family, + dev_net(bat_priv->soft_iface), msg, 0, + BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); + + return 0; +} + +/** + * batadv_netlink_get_mesh() - Get softif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_get_mesh(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct sk_buff *msg; + int ret; + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); - if (!msg) { - ret = -ENOMEM; - goto out; + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_mesh_fill(msg, bat_priv, BATADV_CMD_GET_MESH, + info->snd_portid, info->snd_seq, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; } - msg_head = genlmsg_put(msg, info->snd_portid, info->snd_seq, - &batadv_netlink_family, 0, - BATADV_CMD_GET_MESH_INFO); - if (!msg_head) { - ret = -ENOBUFS; - goto out; + ret = genlmsg_reply(msg, info); + + return ret; +} + +/** + * batadv_netlink_set_mesh() - Set softif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_mesh(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct nlattr *attr; + + if (info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]) { + attr = info->attrs[BATADV_ATTR_AGGREGATED_OGMS_ENABLED]; + + atomic_set(&bat_priv->aggregated_ogms, !!nla_get_u8(attr)); } - ret = batadv_netlink_mesh_info_put(msg, soft_iface); + if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { + attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; - out: - if (soft_iface) - dev_put(soft_iface); + batadv_netlink_set_mesh_ap_isolation(attr, bat_priv); + } - if (ret) { - if (msg) - nlmsg_free(msg); - return ret; + if (info->attrs[BATADV_ATTR_ISOLATION_MARK]) { + attr = info->attrs[BATADV_ATTR_ISOLATION_MARK]; + + bat_priv->isolation_mark = nla_get_u32(attr); } - genlmsg_end(msg, msg_head); - return genlmsg_reply(msg, info); + if (info->attrs[BATADV_ATTR_ISOLATION_MASK]) { + attr = info->attrs[BATADV_ATTR_ISOLATION_MASK]; + + bat_priv->isolation_mark_mask = nla_get_u32(attr); + } + + if (info->attrs[BATADV_ATTR_BONDING_ENABLED]) { + attr = info->attrs[BATADV_ATTR_BONDING_ENABLED]; + + atomic_set(&bat_priv->bonding, !!nla_get_u8(attr)); + } + +#ifdef CONFIG_BATMAN_ADV_BLA + if (info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]) { + attr = info->attrs[BATADV_ATTR_BRIDGE_LOOP_AVOIDANCE_ENABLED]; + + atomic_set(&bat_priv->bridge_loop_avoidance, + !!nla_get_u8(attr)); + batadv_bla_status_update(bat_priv->soft_iface); + } +#endif /* CONFIG_BATMAN_ADV_BLA */ + +#ifdef CONFIG_BATMAN_ADV_DAT + if (info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]) { + attr = info->attrs[BATADV_ATTR_DISTRIBUTED_ARP_TABLE_ENABLED]; + + atomic_set(&bat_priv->distributed_arp_table, + !!nla_get_u8(attr)); + batadv_dat_status_update(bat_priv->soft_iface); + } +#endif /* CONFIG_BATMAN_ADV_DAT */ + + if (info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]) { + attr = info->attrs[BATADV_ATTR_FRAGMENTATION_ENABLED]; + + atomic_set(&bat_priv->fragmentation, !!nla_get_u8(attr)); + batadv_update_min_mtu(bat_priv->soft_iface); + } + + if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]) { + attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_DOWN]; + + atomic_set(&bat_priv->gw.bandwidth_down, nla_get_u32(attr)); + batadv_gw_tvlv_container_update(bat_priv); + } + + if (info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]) { + attr = info->attrs[BATADV_ATTR_GW_BANDWIDTH_UP]; + + atomic_set(&bat_priv->gw.bandwidth_up, nla_get_u32(attr)); + batadv_gw_tvlv_container_update(bat_priv); + } + + if (info->attrs[BATADV_ATTR_GW_MODE]) { + u8 gw_mode; + + attr = info->attrs[BATADV_ATTR_GW_MODE]; + gw_mode = nla_get_u8(attr); + + if (gw_mode <= BATADV_GW_MODE_SERVER) { + /* Invoking batadv_gw_reselect() is not enough to really + * de-select the current GW. It will only instruct the + * gateway client code to perform a re-election the next + * time that this is needed. + * + * When gw client mode is being switched off the current + * GW must be de-selected explicitly otherwise no GW_ADD + * uevent is thrown on client mode re-activation. This + * is operation is performed in + * batadv_gw_check_client_stop(). + */ + batadv_gw_reselect(bat_priv); + + /* always call batadv_gw_check_client_stop() before + * changing the gateway state + */ + batadv_gw_check_client_stop(bat_priv); + atomic_set(&bat_priv->gw.mode, gw_mode); + batadv_gw_tvlv_container_update(bat_priv); + } + } + + if (info->attrs[BATADV_ATTR_GW_SEL_CLASS] && + bat_priv->algo_ops->gw.get_best_gw_node && + bat_priv->algo_ops->gw.is_eligible) { + /* setting the GW selection class is allowed only if the routing + * algorithm in use implements the GW API + */ + + u32 sel_class_max = 0xffffffffu; + u32 sel_class; + + attr = info->attrs[BATADV_ATTR_GW_SEL_CLASS]; + sel_class = nla_get_u32(attr); + + if (!bat_priv->algo_ops->gw.store_sel_class) + sel_class_max = BATADV_TQ_MAX_VALUE; + + if (sel_class >= 1 && sel_class <= sel_class_max) { + atomic_set(&bat_priv->gw.sel_class, sel_class); + batadv_gw_reselect(bat_priv); + } + } + + if (info->attrs[BATADV_ATTR_HOP_PENALTY]) { + attr = info->attrs[BATADV_ATTR_HOP_PENALTY]; + + atomic_set(&bat_priv->hop_penalty, nla_get_u8(attr)); + } + +#ifdef CONFIG_BATMAN_ADV_DEBUG + if (info->attrs[BATADV_ATTR_LOG_LEVEL]) { + attr = info->attrs[BATADV_ATTR_LOG_LEVEL]; + + atomic_set(&bat_priv->log_level, + nla_get_u32(attr) & BATADV_DBG_ALL); + } +#endif /* CONFIG_BATMAN_ADV_DEBUG */ + +#ifdef CONFIG_BATMAN_ADV_MCAST + if (info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]) { + attr = info->attrs[BATADV_ATTR_MULTICAST_FORCEFLOOD_ENABLED]; + + atomic_set(&bat_priv->multicast_mode, !nla_get_u8(attr)); + } +#endif /* CONFIG_BATMAN_ADV_MCAST */ + +#ifdef CONFIG_BATMAN_ADV_NC + if (info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]) { + attr = info->attrs[BATADV_ATTR_NETWORK_CODING_ENABLED]; + + atomic_set(&bat_priv->network_coding, !!nla_get_u8(attr)); + batadv_nc_status_update(bat_priv->soft_iface); + } +#endif /* CONFIG_BATMAN_ADV_NC */ + + if (info->attrs[BATADV_ATTR_ORIG_INTERVAL]) { + u32 orig_interval; + + attr = info->attrs[BATADV_ATTR_ORIG_INTERVAL]; + orig_interval = nla_get_u32(attr); + + orig_interval = min_t(u32, orig_interval, INT_MAX); + orig_interval = max_t(u32, orig_interval, 2 * BATADV_JITTER); + + atomic_set(&bat_priv->orig_interval, orig_interval); + } + + batadv_netlink_notify_mesh(bat_priv); + + return 0; } /** @@ -329,40 +709,24 @@ err_genlmsg: static int batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) { - struct net *net = genl_info_net(info); - struct net_device *soft_iface; - struct batadv_priv *bat_priv; + struct batadv_priv *bat_priv = info->user_ptr[0]; struct sk_buff *msg = NULL; u32 test_length; void *msg_head; - int ifindex; u32 cookie; u8 *dst; int ret; - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return -EINVAL; - if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; if (!info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]) return -EINVAL; - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); - if (!ifindex) - return -EINVAL; - dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); test_length = nla_get_u32(info->attrs[BATADV_ATTR_TPMETER_TEST_TIME]); - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } - msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) { ret = -ENOMEM; @@ -377,15 +741,11 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) goto out; } - bat_priv = netdev_priv(soft_iface); batadv_tp_start(bat_priv, dst, test_length, &cookie); ret = batadv_netlink_tp_meter_put(msg, cookie); out: - if (soft_iface) - dev_put(soft_iface); - if (ret) { if (msg) nlmsg_free(msg); @@ -406,65 +766,53 @@ batadv_netlink_tp_meter_start(struct sk_buff *skb, struct genl_info *info) static int batadv_netlink_tp_meter_cancel(struct sk_buff *skb, struct genl_info *info) { - struct net *net = genl_info_net(info); - struct net_device *soft_iface; - struct batadv_priv *bat_priv; - int ifindex; + struct batadv_priv *bat_priv = info->user_ptr[0]; u8 *dst; int ret = 0; - if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) - return -EINVAL; - if (!info->attrs[BATADV_ATTR_ORIG_ADDRESS]) return -EINVAL; - ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); - if (!ifindex) - return -EINVAL; - dst = nla_data(info->attrs[BATADV_ATTR_ORIG_ADDRESS]); - soft_iface = dev_get_by_index(net, ifindex); - if (!soft_iface || !batadv_softif_is_valid(soft_iface)) { - ret = -ENODEV; - goto out; - } - - bat_priv = netdev_priv(soft_iface); batadv_tp_stop(bat_priv, dst, BATADV_TP_REASON_CANCEL); -out: - if (soft_iface) - dev_put(soft_iface); - return ret; } /** - * batadv_netlink_dump_hardif_entry() - Dump one hard interface into a message + * batadv_netlink_hardif_fill() - Fill message with hardif attributes * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information + * @hard_iface: hard interface which was modified + * @cmd: type of message to generate * @portid: Port making netlink request + * @seq: sequence number for message + * @flags: Additional flags for message * @cb: Control block containing additional options - * @hard_iface: Hard interface to dump * - * Return: error code, or 0 on success + * Return: 0 on success or negative error number in case of failure */ -static int -batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, - struct netlink_callback *cb, - struct batadv_hard_iface *hard_iface) +static int batadv_netlink_hardif_fill(struct sk_buff *msg, + struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface, + enum batadv_nl_commands cmd, + u32 portid, u32 seq, int flags, + struct netlink_callback *cb) { struct net_device *net_dev = hard_iface->net_dev; void *hdr; - hdr = genlmsg_put(msg, portid, cb->nlh->nlmsg_seq, - &batadv_netlink_family, NLM_F_MULTI, - BATADV_CMD_GET_HARDIFS); + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); if (!hdr) - return -EMSGSIZE; + return -ENOBUFS; + + if (cb) + genl_dump_check_consistent(cb, hdr); - genl_dump_check_consistent(cb, hdr); + if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, + bat_priv->soft_iface->ifindex)) + goto nla_put_failure; if (nla_put_u32(msg, BATADV_ATTR_HARD_IFINDEX, net_dev->ifindex) || @@ -479,27 +827,137 @@ batadv_netlink_dump_hardif_entry(struct sk_buff *msg, u32 portid, goto nla_put_failure; } +#ifdef CONFIG_BATMAN_ADV_BATMAN_V + if (nla_put_u32(msg, BATADV_ATTR_ELP_INTERVAL, + atomic_read(&hard_iface->bat_v.elp_interval))) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_THROUGHPUT_OVERRIDE, + atomic_read(&hard_iface->bat_v.throughput_override))) + goto nla_put_failure; +#endif /* CONFIG_BATMAN_ADV_BATMAN_V */ + genlmsg_end(msg, hdr); return 0; - nla_put_failure: +nla_put_failure: genlmsg_cancel(msg, hdr); return -EMSGSIZE; } /** - * batadv_netlink_dump_hardifs() - Dump all hard interface into a messages + * batadv_netlink_notify_hardif() - send hardif attributes to listener + * @bat_priv: the bat priv with all the soft interface information + * @hard_iface: hard interface which was modified + * + * Return: 0 on success, < 0 on error + */ +int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface) +{ + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, + BATADV_CMD_SET_HARDIF, 0, 0, 0, NULL); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + genlmsg_multicast_netns(&batadv_netlink_family, + dev_net(bat_priv->soft_iface), msg, 0, + BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); + + return 0; +} + +/** + * batadv_netlink_get_hardif() - Get hardif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_get_hardif(struct sk_buff *skb, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, + BATADV_CMD_GET_HARDIF, + info->snd_portid, info->snd_seq, 0, + NULL); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + ret = genlmsg_reply(msg, info); + + return ret; +} + +/** + * batadv_netlink_set_hardif() - Set hardif attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_hardif(struct sk_buff *skb, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + +#ifdef CONFIG_BATMAN_ADV_BATMAN_V + struct nlattr *attr; + + if (info->attrs[BATADV_ATTR_ELP_INTERVAL]) { + attr = info->attrs[BATADV_ATTR_ELP_INTERVAL]; + + atomic_set(&hard_iface->bat_v.elp_interval, nla_get_u32(attr)); + } + + if (info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]) { + attr = info->attrs[BATADV_ATTR_THROUGHPUT_OVERRIDE]; + + atomic_set(&hard_iface->bat_v.throughput_override, + nla_get_u32(attr)); + } +#endif /* CONFIG_BATMAN_ADV_BATMAN_V */ + + batadv_netlink_notify_hardif(bat_priv, hard_iface); + + return 0; +} + +/** + * batadv_netlink_dump_hardif() - Dump all hard interface into a messages * @msg: Netlink message to dump into * @cb: Parameters from query * * Return: error code, or length of reply message on success */ static int -batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) +batadv_netlink_dump_hardif(struct sk_buff *msg, struct netlink_callback *cb) { struct net *net = sock_net(cb->skb->sk); struct net_device *soft_iface; struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv; int ifindex; int portid = NETLINK_CB(cb->skb).portid; int skip = cb->args[0]; @@ -519,6 +977,8 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) return -ENODEV; } + bat_priv = netdev_priv(soft_iface); + rtnl_lock(); cb->seq = batadv_hardif_generation << 1 | 1; @@ -529,8 +989,10 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) if (i++ < skip) continue; - if (batadv_netlink_dump_hardif_entry(msg, portid, cb, - hard_iface)) { + if (batadv_netlink_hardif_fill(msg, bat_priv, hard_iface, + BATADV_CMD_GET_HARDIF, + portid, cb->nlh->nlmsg_seq, + NLM_F_MULTI, cb)) { i--; break; } @@ -545,24 +1007,361 @@ batadv_netlink_dump_hardifs(struct sk_buff *msg, struct netlink_callback *cb) return msg->len; } +/** + * batadv_netlink_vlan_fill() - Fill message with vlan attributes + * @msg: Netlink message to dump into + * @bat_priv: the bat priv with all the soft interface information + * @vlan: vlan which was modified + * @cmd: type of message to generate + * @portid: Port making netlink request + * @seq: sequence number for message + * @flags: Additional flags for message + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_vlan_fill(struct sk_buff *msg, + struct batadv_priv *bat_priv, + struct batadv_softif_vlan *vlan, + enum batadv_nl_commands cmd, + u32 portid, u32 seq, int flags) +{ + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &batadv_netlink_family, flags, cmd); + if (!hdr) + return -ENOBUFS; + + if (nla_put_u32(msg, BATADV_ATTR_MESH_IFINDEX, + bat_priv->soft_iface->ifindex)) + goto nla_put_failure; + + if (nla_put_u32(msg, BATADV_ATTR_VLANID, vlan->vid & VLAN_VID_MASK)) + goto nla_put_failure; + + if (nla_put_u8(msg, BATADV_ATTR_AP_ISOLATION_ENABLED, + !!atomic_read(&vlan->ap_isolation))) + goto nla_put_failure; + + genlmsg_end(msg, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +/** + * batadv_netlink_notify_vlan() - send vlan attributes to listener + * @bat_priv: the bat priv with all the soft interface information + * @vlan: vlan which was modified + * + * Return: 0 on success, < 0 on error + */ +int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, + struct batadv_softif_vlan *vlan) +{ + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, + BATADV_CMD_SET_VLAN, 0, 0, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + genlmsg_multicast_netns(&batadv_netlink_family, + dev_net(bat_priv->soft_iface), msg, 0, + BATADV_NL_MCGRP_CONFIG, GFP_KERNEL); + + return 0; +} + +/** + * batadv_netlink_get_vlan() - Get vlan attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_get_vlan(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_softif_vlan *vlan = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct sk_buff *msg; + int ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + ret = batadv_netlink_vlan_fill(msg, bat_priv, vlan, BATADV_CMD_GET_VLAN, + info->snd_portid, info->snd_seq, 0); + if (ret < 0) { + nlmsg_free(msg); + return ret; + } + + ret = genlmsg_reply(msg, info); + + return ret; +} + +/** + * batadv_netlink_set_vlan() - Get vlan attributes + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_netlink_set_vlan(struct sk_buff *skb, struct genl_info *info) +{ + struct batadv_softif_vlan *vlan = info->user_ptr[1]; + struct batadv_priv *bat_priv = info->user_ptr[0]; + struct nlattr *attr; + + if (info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]) { + attr = info->attrs[BATADV_ATTR_AP_ISOLATION_ENABLED]; + + atomic_set(&vlan->ap_isolation, !!nla_get_u8(attr)); + } + + batadv_netlink_notify_vlan(bat_priv, vlan); + + return 0; +} + +/** + * batadv_get_softif_from_info() - Retrieve soft interface from genl attributes + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to soft interface (with increased refcnt) on success, error + * pointer on error + */ +static struct net_device * +batadv_get_softif_from_info(struct net *net, struct genl_info *info) +{ + struct net_device *soft_iface; + int ifindex; + + if (!info->attrs[BATADV_ATTR_MESH_IFINDEX]) + return ERR_PTR(-EINVAL); + + ifindex = nla_get_u32(info->attrs[BATADV_ATTR_MESH_IFINDEX]); + + soft_iface = dev_get_by_index(net, ifindex); + if (!soft_iface) + return ERR_PTR(-ENODEV); + + if (!batadv_softif_is_valid(soft_iface)) + goto err_put_softif; + + return soft_iface; + +err_put_softif: + dev_put(soft_iface); + + return ERR_PTR(-EINVAL); +} + +/** + * batadv_get_hardif_from_info() - Retrieve hardif from genl attributes + * @bat_priv: the bat priv with all the soft interface information + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to hard interface (with increased refcnt) on success, error + * pointer on error + */ +static struct batadv_hard_iface * +batadv_get_hardif_from_info(struct batadv_priv *bat_priv, struct net *net, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface; + struct net_device *hard_dev; + unsigned int hardif_index; + + if (!info->attrs[BATADV_ATTR_HARD_IFINDEX]) + return ERR_PTR(-EINVAL); + + hardif_index = nla_get_u32(info->attrs[BATADV_ATTR_HARD_IFINDEX]); + + hard_dev = dev_get_by_index(net, hardif_index); + if (!hard_dev) + return ERR_PTR(-ENODEV); + + hard_iface = batadv_hardif_get_by_netdev(hard_dev); + if (!hard_iface) + goto err_put_harddev; + + if (hard_iface->soft_iface != bat_priv->soft_iface) + goto err_put_hardif; + + /* hard_dev is referenced by hard_iface and not needed here */ + dev_put(hard_dev); + + return hard_iface; + +err_put_hardif: + batadv_hardif_put(hard_iface); +err_put_harddev: + dev_put(hard_dev); + + return ERR_PTR(-EINVAL); +} + +/** + * batadv_get_vlan_from_info() - Retrieve vlan from genl attributes + * @bat_priv: the bat priv with all the soft interface information + * @net: the applicable net namespace + * @info: receiver information + * + * Return: Pointer to vlan on success (with increased refcnt), error pointer + * on error + */ +static struct batadv_softif_vlan * +batadv_get_vlan_from_info(struct batadv_priv *bat_priv, struct net *net, + struct genl_info *info) +{ + struct batadv_softif_vlan *vlan; + u16 vid; + + if (!info->attrs[BATADV_ATTR_VLANID]) + return ERR_PTR(-EINVAL); + + vid = nla_get_u16(info->attrs[BATADV_ATTR_VLANID]); + + vlan = batadv_softif_vlan_get(bat_priv, vid | BATADV_VLAN_HAS_TAG); + if (!vlan) + return ERR_PTR(-ENOENT); + + return vlan; +} + +/** + * batadv_pre_doit() - Prepare batman-adv genl doit request + * @ops: requested netlink operation + * @skb: Netlink message with request data + * @info: receiver information + * + * Return: 0 on success or negative error number in case of failure + */ +static int batadv_pre_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct batadv_hard_iface *hard_iface; + struct batadv_priv *bat_priv = NULL; + struct batadv_softif_vlan *vlan; + struct net_device *soft_iface; + u8 user_ptr1_flags; + u8 mesh_dep_flags; + int ret; + + user_ptr1_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; + if (WARN_ON(hweight8(ops->internal_flags & user_ptr1_flags) > 1)) + return -EINVAL; + + mesh_dep_flags = BATADV_FLAG_NEED_HARDIF | BATADV_FLAG_NEED_VLAN; + if (WARN_ON((ops->internal_flags & mesh_dep_flags) && + (~ops->internal_flags & BATADV_FLAG_NEED_MESH))) + return -EINVAL; + + if (ops->internal_flags & BATADV_FLAG_NEED_MESH) { + soft_iface = batadv_get_softif_from_info(net, info); + if (IS_ERR(soft_iface)) + return PTR_ERR(soft_iface); + + bat_priv = netdev_priv(soft_iface); + info->user_ptr[0] = bat_priv; + } + + if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF) { + hard_iface = batadv_get_hardif_from_info(bat_priv, net, info); + if (IS_ERR(hard_iface)) { + ret = PTR_ERR(hard_iface); + goto err_put_softif; + } + + info->user_ptr[1] = hard_iface; + } + + if (ops->internal_flags & BATADV_FLAG_NEED_VLAN) { + vlan = batadv_get_vlan_from_info(bat_priv, net, info); + if (IS_ERR(vlan)) { + ret = PTR_ERR(vlan); + goto err_put_softif; + } + + info->user_ptr[1] = vlan; + } + + return 0; + +err_put_softif: + if (bat_priv) + dev_put(bat_priv->soft_iface); + + return ret; +} + +/** + * batadv_post_doit() - End batman-adv genl doit request + * @ops: requested netlink operation + * @skb: Netlink message with request data + * @info: receiver information + */ +static void batadv_post_doit(const struct genl_ops *ops, struct sk_buff *skb, + struct genl_info *info) +{ + struct batadv_hard_iface *hard_iface; + struct batadv_softif_vlan *vlan; + struct batadv_priv *bat_priv; + + if (ops->internal_flags & BATADV_FLAG_NEED_HARDIF && + info->user_ptr[1]) { + hard_iface = info->user_ptr[1]; + + batadv_hardif_put(hard_iface); + } + + if (ops->internal_flags & BATADV_FLAG_NEED_VLAN && info->user_ptr[1]) { + vlan = info->user_ptr[1]; + batadv_softif_vlan_put(vlan); + } + + if (ops->internal_flags & BATADV_FLAG_NEED_MESH && info->user_ptr[0]) { + bat_priv = info->user_ptr[0]; + dev_put(bat_priv->soft_iface); + } +} + static const struct genl_ops batadv_netlink_ops[] = { { - .cmd = BATADV_CMD_GET_MESH_INFO, - .flags = GENL_ADMIN_PERM, + .cmd = BATADV_CMD_GET_MESH, + /* can be retrieved by unprivileged users */ .policy = batadv_netlink_policy, - .doit = batadv_netlink_get_mesh_info, + .doit = batadv_netlink_get_mesh, + .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER, .flags = GENL_ADMIN_PERM, .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_start, + .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_TP_METER_CANCEL, .flags = GENL_ADMIN_PERM, .policy = batadv_netlink_policy, .doit = batadv_netlink_tp_meter_cancel, + .internal_flags = BATADV_FLAG_NEED_MESH, }, { .cmd = BATADV_CMD_GET_ROUTING_ALGOS, @@ -571,10 +1370,13 @@ static const struct genl_ops batadv_netlink_ops[] = { .dumpit = batadv_algo_dump, }, { - .cmd = BATADV_CMD_GET_HARDIFS, - .flags = GENL_ADMIN_PERM, + .cmd = BATADV_CMD_GET_HARDIF, + /* can be retrieved by unprivileged users */ .policy = batadv_netlink_policy, - .dumpit = batadv_netlink_dump_hardifs, + .dumpit = batadv_netlink_dump_hardif, + .doit = batadv_netlink_get_hardif, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_HARDIF, }, { .cmd = BATADV_CMD_GET_TRANSTABLE_LOCAL, @@ -630,7 +1432,37 @@ static const struct genl_ops batadv_netlink_ops[] = { .policy = batadv_netlink_policy, .dumpit = batadv_mcast_flags_dump, }, - + { + .cmd = BATADV_CMD_SET_MESH, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .doit = batadv_netlink_set_mesh, + .internal_flags = BATADV_FLAG_NEED_MESH, + }, + { + .cmd = BATADV_CMD_SET_HARDIF, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .doit = batadv_netlink_set_hardif, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_HARDIF, + }, + { + .cmd = BATADV_CMD_GET_VLAN, + /* can be retrieved by unprivileged users */ + .policy = batadv_netlink_policy, + .doit = batadv_netlink_get_vlan, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_VLAN, + }, + { + .cmd = BATADV_CMD_SET_VLAN, + .flags = GENL_ADMIN_PERM, + .policy = batadv_netlink_policy, + .doit = batadv_netlink_set_vlan, + .internal_flags = BATADV_FLAG_NEED_MESH | + BATADV_FLAG_NEED_VLAN, + }, }; struct genl_family batadv_netlink_family __ro_after_init = { @@ -639,6 +1471,8 @@ struct genl_family batadv_netlink_family __ro_after_init = { .version = 1, .maxattr = BATADV_ATTR_MAX, .netnsok = true, + .pre_doit = batadv_pre_doit, + .post_doit = batadv_post_doit, .module = THIS_MODULE, .ops = batadv_netlink_ops, .n_ops = ARRAY_SIZE(batadv_netlink_ops), diff --git a/net/batman-adv/netlink.h b/net/batman-adv/netlink.h index 571d9a5ae7aa..7273368544fc 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) 2016-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2016-2019 B.A.T.M.A.N. contributors: * * Matthias Schiffer * @@ -34,6 +34,12 @@ int batadv_netlink_tpmeter_notify(struct batadv_priv *bat_priv, const u8 *dst, u8 result, u32 test_time, u64 total_bytes, u32 cookie); +int batadv_netlink_notify_mesh(struct batadv_priv *bat_priv); +int batadv_netlink_notify_hardif(struct batadv_priv *bat_priv, + struct batadv_hard_iface *hard_iface); +int batadv_netlink_notify_vlan(struct batadv_priv *bat_priv, + struct batadv_softif_vlan *vlan); + extern struct genl_family batadv_netlink_family; #endif /* _NET_BATMAN_ADV_NETLINK_H_ */ diff --git a/net/batman-adv/network-coding.c b/net/batman-adv/network-coding.c index 34caf129a9bf..278762bd94c6 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) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 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 65c346812bc1..96ef0a511fc7 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) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 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 56a981af5c92..e5cdf89ef63c 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) 2009-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2009-2019 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 a8b4c7b667ec..dca1e4a34ec6 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 cc3ed93a6d51..cae0e5dd0768 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -1043,6 +1043,8 @@ int batadv_recv_unicast_packet(struct sk_buff *skb, hdr_size)) goto rx_success; + batadv_dat_snoop_incoming_dhcp_ack(bat_priv, skb, hdr_size); + batadv_interface_rx(recv_if->soft_iface, skb, hdr_size, orig_node); @@ -1278,6 +1280,8 @@ int batadv_recv_bcast_packet(struct sk_buff *skb, if (batadv_dat_snoop_incoming_arp_reply(bat_priv, skb, hdr_size)) goto rx_success; + batadv_dat_snoop_incoming_dhcp_ack(bat_priv, skb, hdr_size); + /* broadcast for me */ batadv_interface_rx(recv_if->soft_iface, skb, hdr_size, orig_node); diff --git a/net/batman-adv/routing.h b/net/batman-adv/routing.h index db54c2d9b8bf..0102d69d345c 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 4a35f5c2f52b..66a8b3e44501 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 64cce07b8fe6..1f6132922e60 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 ffc83bebfe40..2e367230376b 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * @@ -50,13 +50,13 @@ #include <linux/string.h> #include <linux/types.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "bat_algo.h" #include "bridge_loop_avoidance.h" #include "debugfs.h" #include "distributed-arp-table.h" #include "gateway_client.h" -#include "gateway_common.h" #include "hard-interface.h" #include "multicast.h" #include "network-coding.h" @@ -212,6 +212,7 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, enum batadv_forw_mode forw_mode; struct batadv_orig_node *mcast_single_orig = NULL; int network_offset = ETH_HLEN; + __be16 proto; if (atomic_read(&bat_priv->mesh_state) != BATADV_MESH_ACTIVE) goto dropped; @@ -225,14 +226,17 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, skb_reset_mac_header(skb); ethhdr = eth_hdr(skb); - switch (ntohs(ethhdr->h_proto)) { + proto = ethhdr->h_proto; + + switch (ntohs(proto)) { case ETH_P_8021Q: if (!pskb_may_pull(skb, sizeof(*vhdr))) goto dropped; vhdr = vlan_eth_hdr(skb); + proto = vhdr->h_vlan_encapsulated_proto; /* drop batman-in-batman packets to prevent loops */ - if (vhdr->h_vlan_encapsulated_proto != htons(ETH_P_BATMAN)) { + if (proto != htons(ETH_P_BATMAN)) { network_offset += VLAN_HLEN; break; } @@ -260,6 +264,9 @@ static netdev_tx_t batadv_interface_tx(struct sk_buff *skb, goto dropped; } + /* Snoop address candidates from DHCPACKs for early DAT filling */ + batadv_dat_snoop_outgoing_dhcp_ack(bat_priv, skb, proto, vid); + /* don't accept stp packets. STP does not help in meshes. * better use the bridge loop avoidance ... * diff --git a/net/batman-adv/soft-interface.h b/net/batman-adv/soft-interface.h index daf87f07fadd..538bb661878c 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * diff --git a/net/batman-adv/sysfs.c b/net/batman-adv/sysfs.c index 09427fc6494a..0b4b3fb778a6 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Marek Lindner * @@ -40,6 +40,7 @@ #include <linux/stringify.h> #include <linux/workqueue.h> #include <uapi/linux/batadv_packet.h> +#include <uapi/linux/batman_adv.h> #include "bridge_loop_avoidance.h" #include "distributed-arp-table.h" @@ -47,6 +48,7 @@ #include "gateway_common.h" #include "hard-interface.h" #include "log.h" +#include "netlink.h" #include "network-coding.h" #include "soft-interface.h" @@ -153,9 +155,14 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + ssize_t length; \ + \ + length = __batadv_store_bool_attr(buff, count, _post_func, attr,\ + &bat_priv->_name, net_dev); \ \ - return __batadv_store_bool_attr(buff, count, _post_func, attr, \ - &bat_priv->_name, net_dev); \ + batadv_netlink_notify_mesh(bat_priv); \ + \ + return length; \ } #define BATADV_ATTR_SIF_SHOW_BOOL(_name) \ @@ -185,11 +192,16 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_priv *bat_priv = netdev_priv(net_dev); \ + ssize_t length; \ \ - return __batadv_store_uint_attr(buff, count, _min, _max, \ - _post_func, attr, \ - &bat_priv->_var, net_dev, \ - NULL); \ + length = __batadv_store_uint_attr(buff, count, _min, _max, \ + _post_func, attr, \ + &bat_priv->_var, net_dev, \ + NULL); \ + \ + batadv_netlink_notify_mesh(bat_priv); \ + \ + return length; \ } #define BATADV_ATTR_SIF_SHOW_UINT(_name, _var) \ @@ -222,6 +234,11 @@ ssize_t batadv_store_vlan_##_name(struct kobject *kobj, \ attr, &vlan->_name, \ bat_priv->soft_iface); \ \ + if (vlan->vid) \ + batadv_netlink_notify_vlan(bat_priv, vlan); \ + else \ + batadv_netlink_notify_mesh(bat_priv); \ + \ batadv_softif_vlan_put(vlan); \ return res; \ } @@ -255,6 +272,7 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ { \ struct net_device *net_dev = batadv_kobj_to_netdev(kobj); \ struct batadv_hard_iface *hard_iface; \ + struct batadv_priv *bat_priv; \ ssize_t length; \ \ hard_iface = batadv_hardif_get_by_netdev(net_dev); \ @@ -267,6 +285,11 @@ ssize_t batadv_store_##_name(struct kobject *kobj, \ hard_iface->soft_iface, \ net_dev); \ \ + if (hard_iface->soft_iface) { \ + bat_priv = netdev_priv(hard_iface->soft_iface); \ + batadv_netlink_notify_hardif(bat_priv, hard_iface); \ + } \ + \ batadv_hardif_put(hard_iface); \ return length; \ } @@ -536,6 +559,9 @@ static ssize_t batadv_store_gw_mode(struct kobject *kobj, batadv_gw_check_client_stop(bat_priv); atomic_set(&bat_priv->gw.mode, (unsigned int)gw_mode_tmp); batadv_gw_tvlv_container_update(bat_priv); + + batadv_netlink_notify_mesh(bat_priv); + return count; } @@ -562,6 +588,7 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, size_t count) { struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); + ssize_t length; /* setting the GW selection class is allowed only if the routing * algorithm in use implements the GW API @@ -577,10 +604,14 @@ static ssize_t batadv_store_gw_sel_class(struct kobject *kobj, return bat_priv->algo_ops->gw.store_sel_class(bat_priv, buff, count); - return __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, - batadv_post_gw_reselect, attr, - &bat_priv->gw.sel_class, - bat_priv->soft_iface, NULL); + length = __batadv_store_uint_attr(buff, count, 1, BATADV_TQ_MAX_VALUE, + batadv_post_gw_reselect, attr, + &bat_priv->gw.sel_class, + bat_priv->soft_iface, NULL); + + batadv_netlink_notify_mesh(bat_priv); + + return length; } static ssize_t batadv_show_gw_bwidth(struct kobject *kobj, @@ -600,12 +631,18 @@ static ssize_t batadv_store_gw_bwidth(struct kobject *kobj, struct attribute *attr, char *buff, size_t count) { + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); struct net_device *net_dev = batadv_kobj_to_netdev(kobj); + ssize_t length; if (buff[count - 1] == '\n') buff[count - 1] = '\0'; - return batadv_gw_bandwidth_set(net_dev, buff, count); + length = batadv_gw_bandwidth_set(net_dev, buff, count); + + batadv_netlink_notify_mesh(bat_priv); + + return length; } /** @@ -673,6 +710,8 @@ static ssize_t batadv_store_isolation_mark(struct kobject *kobj, "New skb mark for extended isolation: %#.8x/%#.8x\n", bat_priv->isolation_mark, bat_priv->isolation_mark_mask); + batadv_netlink_notify_mesh(bat_priv); + return count; } @@ -1077,6 +1116,7 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, struct attribute *attr, char *buff, size_t count) { + struct batadv_priv *bat_priv = batadv_kobj_to_batpriv(kobj); struct net_device *net_dev = batadv_kobj_to_netdev(kobj); struct batadv_hard_iface *hard_iface; u32 tp_override; @@ -1107,6 +1147,8 @@ static ssize_t batadv_store_throughput_override(struct kobject *kobj, atomic_set(&hard_iface->bat_v.throughput_override, tp_override); + batadv_netlink_notify_hardif(bat_priv, hard_iface); + out: batadv_hardif_put(hard_iface); return count; diff --git a/net/batman-adv/sysfs.h b/net/batman-adv/sysfs.h index c1e3fb69952d..705ffbe763f4 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 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 11520de96ccb..500109bbd551 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) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 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 68e600974759..6b4d0f733896 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) 2012-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2012-2019 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 8e1024217cff..f77c917ed20d 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 B.A.T.M.A.N. contributors: * * Sven Eckelmann * diff --git a/net/batman-adv/trace.h b/net/batman-adv/trace.h index 104784be94d7..5e5579051400 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) 2010-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2010-2019 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 8dcd4968cde7..f73d79139ae7 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 01b6c8eafaf9..61bca75e5911 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 40e69c9346d2..7e947b01919d 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 ef5867f49824..c0f033b1acb8 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 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 cbe17da36fcb..a21b34ed6548 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) 2007-2018 B.A.T.M.A.N. contributors: +/* Copyright (C) 2007-2019 B.A.T.M.A.N. contributors: * * Marek Lindner, Simon Wunderlich * diff --git a/net/bluetooth/hci_sock.c b/net/bluetooth/hci_sock.c index 1506e1632394..65228bfa4487 100644 --- a/net/bluetooth/hci_sock.c +++ b/net/bluetooth/hci_sock.c @@ -1383,9 +1383,9 @@ static void hci_sock_cmsg(struct sock *sk, struct msghdr *msg, if (mask & HCI_CMSG_TSTAMP) { #ifdef CONFIG_COMPAT - struct compat_timeval ctv; + struct old_timeval32 ctv; #endif - struct timeval tv; + struct __kernel_old_timeval tv; void *data; int len; diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index fa2644d276ef..2c5172b33209 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -240,3 +240,85 @@ out: kfree(data); return ret; } + +int bpf_prog_test_run_flow_dissector(struct bpf_prog *prog, + const union bpf_attr *kattr, + union bpf_attr __user *uattr) +{ + u32 size = kattr->test.data_size_in; + u32 repeat = kattr->test.repeat; + struct bpf_flow_keys flow_keys; + u64 time_start, time_spent = 0; + struct bpf_skb_data_end *cb; + u32 retval, duration; + struct sk_buff *skb; + struct sock *sk; + void *data; + int ret; + u32 i; + + if (prog->type != BPF_PROG_TYPE_FLOW_DISSECTOR) + return -EINVAL; + + data = bpf_test_init(kattr, size, NET_SKB_PAD + NET_IP_ALIGN, + SKB_DATA_ALIGN(sizeof(struct skb_shared_info))); + if (IS_ERR(data)) + return PTR_ERR(data); + + sk = kzalloc(sizeof(*sk), GFP_USER); + if (!sk) { + kfree(data); + return -ENOMEM; + } + sock_net_set(sk, current->nsproxy->net_ns); + sock_init_data(NULL, sk); + + skb = build_skb(data, 0); + if (!skb) { + kfree(data); + kfree(sk); + return -ENOMEM; + } + skb->sk = sk; + + skb_reserve(skb, NET_SKB_PAD + NET_IP_ALIGN); + __skb_put(skb, size); + skb->protocol = eth_type_trans(skb, + current->nsproxy->net_ns->loopback_dev); + skb_reset_network_header(skb); + + cb = (struct bpf_skb_data_end *)skb->cb; + cb->qdisc_cb.flow_keys = &flow_keys; + + if (!repeat) + repeat = 1; + + time_start = ktime_get_ns(); + for (i = 0; i < repeat; i++) { + preempt_disable(); + rcu_read_lock(); + retval = __skb_flow_bpf_dissect(prog, skb, + &flow_keys_dissector, + &flow_keys); + rcu_read_unlock(); + preempt_enable(); + + if (need_resched()) { + if (signal_pending(current)) + break; + time_spent += ktime_get_ns() - time_start; + cond_resched(); + time_start = ktime_get_ns(); + } + } + time_spent += ktime_get_ns() - time_start; + do_div(time_spent, repeat); + duration = time_spent > U32_MAX ? U32_MAX : (u32)time_spent; + + ret = bpf_test_finish(kattr, uattr, &flow_keys, sizeof(flow_keys), + retval, duration); + + kfree_skb(skb); + kfree(sk); + return ret; +} diff --git a/net/bpfilter/Makefile b/net/bpfilter/Makefile index 0947ee7f70d5..5d6c7760142d 100644 --- a/net/bpfilter/Makefile +++ b/net/bpfilter/Makefile @@ -5,7 +5,6 @@ hostprogs-y := bpfilter_umh bpfilter_umh-objs := main.o -KBUILD_HOSTCFLAGS += -I. -Itools/include/ -Itools/include/uapi HOSTCC := $(CC) ifeq ($(CONFIG_BPFILTER_UMH), y) diff --git a/net/bpfilter/main.c b/net/bpfilter/main.c index 1317f108df8a..61ce8454a88e 100644 --- a/net/bpfilter/main.c +++ b/net/bpfilter/main.c @@ -6,7 +6,7 @@ #include <sys/socket.h> #include <fcntl.h> #include <unistd.h> -#include "include/uapi/linux/bpf.h" +#include "../../include/uapi/linux/bpf.h" #include <asm/unistd.h> #include "msgfmt.h" diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 9e14767500ea..00573cc46c98 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -915,7 +915,8 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, /* Add new permanent fdb entry with RTM_NEWNEIGH */ int br_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 vid, u16 nlh_flags) + const unsigned char *addr, u16 vid, u16 nlh_flags, + struct netlink_ext_ack *extack) { struct net_bridge_vlan_group *vg; struct net_bridge_port *p = NULL; diff --git a/net/bridge/br_multicast.c b/net/bridge/br_multicast.c index 3aeff0895669..4a048fd1cbea 100644 --- a/net/bridge/br_multicast.c +++ b/net/bridge/br_multicast.c @@ -14,6 +14,7 @@ #include <linux/export.h> #include <linux/if_ether.h> #include <linux/igmp.h> +#include <linux/in.h> #include <linux/jhash.h> #include <linux/kernel.h> #include <linux/log2.h> @@ -29,6 +30,7 @@ #include <net/ip.h> #include <net/switchdev.h> #if IS_ENABLED(CONFIG_IPV6) +#include <linux/icmpv6.h> #include <net/ipv6.h> #include <net/mld.h> #include <net/ip6_checksum.h> @@ -938,7 +940,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, for (i = 0; i < num; i++) { len += sizeof(*grec); - if (!pskb_may_pull(skb, len)) + if (!ip_mc_may_pull(skb, len)) return -EINVAL; grec = (void *)(skb->data + len - sizeof(*grec)); @@ -946,7 +948,7 @@ static int br_ip4_multicast_igmp3_report(struct net_bridge *br, type = grec->grec_type; len += ntohs(grec->grec_nsrcs) * 4; - if (!pskb_may_pull(skb, len)) + if (!ip_mc_may_pull(skb, len)) return -EINVAL; /* We treat this as an IGMPv2 report for now. */ @@ -985,15 +987,17 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + unsigned int nsrcs_offset; const unsigned char *src; struct icmp6hdr *icmp6h; struct mld2_grec *grec; + unsigned int grec_len; int i; int len; int num; int err = 0; - if (!pskb_may_pull(skb, sizeof(*icmp6h))) + if (!ipv6_mc_may_pull(skb, sizeof(*icmp6h))) return -EINVAL; icmp6h = icmp6_hdr(skb); @@ -1003,21 +1007,24 @@ static int br_ip6_multicast_mld2_report(struct net_bridge *br, for (i = 0; i < num; i++) { __be16 *nsrcs, _nsrcs; - nsrcs = skb_header_pointer(skb, - len + offsetof(struct mld2_grec, - grec_nsrcs), + nsrcs_offset = len + offsetof(struct mld2_grec, grec_nsrcs); + + if (skb_transport_offset(skb) + ipv6_transport_len(skb) < + nsrcs_offset + sizeof(_nsrcs)) + return -EINVAL; + + nsrcs = skb_header_pointer(skb, nsrcs_offset, sizeof(_nsrcs), &_nsrcs); if (!nsrcs) return -EINVAL; - if (!pskb_may_pull(skb, - len + sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs))) + grec_len = struct_size(grec, grec_src, ntohs(*nsrcs)); + + if (!ipv6_mc_may_pull(skb, len + grec_len)) return -EINVAL; grec = (struct mld2_grec *)(skb->data + len); - len += sizeof(*grec) + - sizeof(struct in6_addr) * ntohs(*nsrcs); + len += grec_len; /* We treat these as MLDv1 reports for now. */ switch (grec->grec_type) { @@ -1219,6 +1226,7 @@ static void br_ip4_multicast_query(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + unsigned int transport_len = ip_transport_len(skb); const struct iphdr *iph = ip_hdr(skb); struct igmphdr *ih = igmp_hdr(skb); struct net_bridge_mdb_entry *mp; @@ -1228,7 +1236,6 @@ static void br_ip4_multicast_query(struct net_bridge *br, struct br_ip saddr; unsigned long max_delay; unsigned long now = jiffies; - unsigned int offset = skb_transport_offset(skb); __be32 group; spin_lock(&br->multicast_lock); @@ -1238,14 +1245,14 @@ static void br_ip4_multicast_query(struct net_bridge *br, group = ih->group; - if (skb->len == offset + sizeof(*ih)) { + if (transport_len == sizeof(*ih)) { max_delay = ih->code * (HZ / IGMP_TIMER_SCALE); if (!max_delay) { max_delay = 10 * HZ; group = 0; } - } else if (skb->len >= offset + sizeof(*ih3)) { + } else if (transport_len >= sizeof(*ih3)) { ih3 = igmpv3_query_hdr(skb); if (ih3->nsrcs) goto out; @@ -1296,6 +1303,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, struct sk_buff *skb, u16 vid) { + unsigned int transport_len = ipv6_transport_len(skb); const struct ipv6hdr *ip6h = ipv6_hdr(skb); struct mld_msg *mld; struct net_bridge_mdb_entry *mp; @@ -1315,7 +1323,7 @@ static int br_ip6_multicast_query(struct net_bridge *br, (port && port->state == BR_STATE_DISABLED)) goto out; - if (skb->len == offset + sizeof(*mld)) { + if (transport_len == sizeof(*mld)) { if (!pskb_may_pull(skb, offset + sizeof(*mld))) { err = -EINVAL; goto out; @@ -1576,17 +1584,29 @@ static void br_multicast_pim(struct net_bridge *br, br_multicast_mark_router(br, port); } +static int br_ip4_multicast_mrd_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + if (ip_hdr(skb)->protocol != IPPROTO_IGMP || + igmp_hdr(skb)->type != IGMP_MRDISC_ADV) + return -ENOMSG; + + br_multicast_mark_router(br, port); + + return 0; +} + static int br_multicast_ipv4_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb_trimmed = NULL; const unsigned char *src; struct igmphdr *ih; int err; - err = ip_mc_check_igmp(skb, &skb_trimmed); + err = ip_mc_check_igmp(skb); if (err == -ENOMSG) { if (!ipv4_is_local_multicast(ip_hdr(skb)->daddr)) { @@ -1594,7 +1614,15 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, } else if (pim_ipv4_all_pim_routers(ip_hdr(skb)->daddr)) { if (ip_hdr(skb)->protocol == IPPROTO_PIM) br_multicast_pim(br, port, skb); + } else if (ipv4_is_all_snoopers(ip_hdr(skb)->daddr)) { + err = br_ip4_multicast_mrd_rcv(br, port, skb); + + if (err < 0 && err != -ENOMSG) { + br_multicast_err_count(br, port, skb->protocol); + return err; + } } + return 0; } else if (err < 0) { br_multicast_err_count(br, port, skb->protocol); @@ -1612,19 +1640,16 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, err = br_ip4_multicast_add_group(br, port, ih->group, vid, src); break; case IGMPV3_HOST_MEMBERSHIP_REPORT: - err = br_ip4_multicast_igmp3_report(br, port, skb_trimmed, vid); + err = br_ip4_multicast_igmp3_report(br, port, skb, vid); break; case IGMP_HOST_MEMBERSHIP_QUERY: - br_ip4_multicast_query(br, port, skb_trimmed, vid); + br_ip4_multicast_query(br, port, skb, vid); break; case IGMP_HOST_LEAVE_MESSAGE: br_ip4_multicast_leave_group(br, port, ih->group, vid, src); break; } - if (skb_trimmed && skb_trimmed != skb) - kfree_skb(skb_trimmed); - br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); @@ -1632,21 +1657,51 @@ static int br_multicast_ipv4_rcv(struct net_bridge *br, } #if IS_ENABLED(CONFIG_IPV6) +static int br_ip6_multicast_mrd_rcv(struct net_bridge *br, + struct net_bridge_port *port, + struct sk_buff *skb) +{ + int ret; + + if (ipv6_hdr(skb)->nexthdr != IPPROTO_ICMPV6) + return -ENOMSG; + + ret = ipv6_mc_check_icmpv6(skb); + if (ret < 0) + return ret; + + if (icmp6_hdr(skb)->icmp6_type != ICMPV6_MRDISC_ADV) + return -ENOMSG; + + br_multicast_mark_router(br, port); + + return 0; +} + static int br_multicast_ipv6_rcv(struct net_bridge *br, struct net_bridge_port *port, struct sk_buff *skb, u16 vid) { - struct sk_buff *skb_trimmed = NULL; const unsigned char *src; struct mld_msg *mld; int err; - err = ipv6_mc_check_mld(skb, &skb_trimmed); + err = ipv6_mc_check_mld(skb); if (err == -ENOMSG) { if (!ipv6_addr_is_ll_all_nodes(&ipv6_hdr(skb)->daddr)) BR_INPUT_SKB_CB(skb)->mrouters_only = 1; + + if (ipv6_addr_is_all_snoopers(&ipv6_hdr(skb)->daddr)) { + err = br_ip6_multicast_mrd_rcv(br, port, skb); + + if (err < 0 && err != -ENOMSG) { + br_multicast_err_count(br, port, skb->protocol); + return err; + } + } + return 0; } else if (err < 0) { br_multicast_err_count(br, port, skb->protocol); @@ -1664,10 +1719,10 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, src); break; case ICMPV6_MLD2_REPORT: - err = br_ip6_multicast_mld2_report(br, port, skb_trimmed, vid); + err = br_ip6_multicast_mld2_report(br, port, skb, vid); break; case ICMPV6_MGM_QUERY: - err = br_ip6_multicast_query(br, port, skb_trimmed, vid); + err = br_ip6_multicast_query(br, port, skb, vid); break; case ICMPV6_MGM_REDUCTION: src = eth_hdr(skb)->h_source; @@ -1675,9 +1730,6 @@ static int br_multicast_ipv6_rcv(struct net_bridge *br, break; } - if (skb_trimmed && skb_trimmed != skb) - kfree_skb(skb_trimmed); - br_multicast_count(br, port, skb, BR_INPUT_SKB_CB(skb)->igmp, BR_MCAST_DIR_RX); @@ -1781,6 +1833,68 @@ void br_multicast_init(struct net_bridge *br) INIT_HLIST_HEAD(&br->mdb_list); } +static void br_ip4_multicast_join_snoopers(struct net_bridge *br) +{ + struct in_device *in_dev = in_dev_get(br->dev); + + if (!in_dev) + return; + + __ip_mc_inc_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); + in_dev_put(in_dev); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_join_snoopers(struct net_bridge *br) +{ + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); + ipv6_dev_mc_inc(br->dev, &addr); +} +#else +static inline void br_ip6_multicast_join_snoopers(struct net_bridge *br) +{ +} +#endif + +static void br_multicast_join_snoopers(struct net_bridge *br) +{ + br_ip4_multicast_join_snoopers(br); + br_ip6_multicast_join_snoopers(br); +} + +static void br_ip4_multicast_leave_snoopers(struct net_bridge *br) +{ + struct in_device *in_dev = in_dev_get(br->dev); + + if (WARN_ON(!in_dev)) + return; + + __ip_mc_dec_group(in_dev, htonl(INADDR_ALLSNOOPERS_GROUP), GFP_ATOMIC); + in_dev_put(in_dev); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void br_ip6_multicast_leave_snoopers(struct net_bridge *br) +{ + struct in6_addr addr; + + ipv6_addr_set(&addr, htonl(0xff020000), 0, 0, htonl(0x6a)); + ipv6_dev_mc_dec(br->dev, &addr); +} +#else +static inline void br_ip6_multicast_leave_snoopers(struct net_bridge *br) +{ +} +#endif + +static void br_multicast_leave_snoopers(struct net_bridge *br) +{ + br_ip4_multicast_leave_snoopers(br); + br_ip6_multicast_leave_snoopers(br); +} + static void __br_multicast_open(struct net_bridge *br, struct bridge_mcast_own_query *query) { @@ -1794,6 +1908,9 @@ static void __br_multicast_open(struct net_bridge *br, void br_multicast_open(struct net_bridge *br) { + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_join_snoopers(br); + __br_multicast_open(br, &br->ip4_own_query); #if IS_ENABLED(CONFIG_IPV6) __br_multicast_open(br, &br->ip6_own_query); @@ -1809,6 +1926,9 @@ void br_multicast_stop(struct net_bridge *br) del_timer_sync(&br->ip6_other_query.timer); del_timer_sync(&br->ip6_own_query.timer); #endif + + if (br_opt_get(br, BROPT_MULTICAST_ENABLED)) + br_multicast_leave_snoopers(br); } void br_multicast_dev_del(struct net_bridge *br) @@ -1944,8 +2064,10 @@ int br_multicast_toggle(struct net_bridge *br, unsigned long val) br_mc_disabled_update(br->dev, val); br_opt_toggle(br, BROPT_MULTICAST_ENABLED, !!val); - if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) + if (!br_opt_get(br, BROPT_MULTICAST_ENABLED)) { + br_multicast_leave_snoopers(br); goto unlock; + } if (!netif_running(br->dev)) goto unlock; diff --git a/net/bridge/br_netfilter_hooks.c b/net/bridge/br_netfilter_hooks.c index c93c35bb73dd..40d058378b52 100644 --- a/net/bridge/br_netfilter_hooks.c +++ b/net/bridge/br_netfilter_hooks.c @@ -881,11 +881,6 @@ static const struct nf_br_ops br_ops = { .br_dev_xmit_hook = br_nf_dev_xmit, }; -void br_netfilter_enable(void) -{ -} -EXPORT_SYMBOL_GPL(br_netfilter_enable); - /* For br_nf_post_routing, we need (prio = NF_BR_PRI_LAST), because * br_dev_queue_push_xmit is called afterwards */ static const struct nf_hook_ops br_nf_ops[] = { diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index eabf8bf28a3f..00deef7fc1f3 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -573,7 +573,8 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, int br_fdb_delete(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); int br_fdb_add(struct ndmsg *nlh, struct nlattr *tb[], struct net_device *dev, - const unsigned char *addr, u16 vid, u16 nlh_flags); + const unsigned char *addr, u16 vid, u16 nlh_flags, + struct netlink_ext_ack *extack); int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, struct net_device *dev, struct net_device *fdev, int *idx); int br_fdb_get(struct sk_buff *skb, struct nlattr *tb[], struct net_device *dev, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index 035ff59d9cbd..db9e8ab96d48 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -14,7 +14,7 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) /* dev is yet to be added to the port list. */ list_for_each_entry(p, &br->port_list, list) { - if (switchdev_port_same_parent_id(dev, p->dev)) + if (netdev_port_same_parent_id(dev, p->dev)) return p->offload_fwd_mark; } @@ -23,15 +23,12 @@ static int br_switchdev_mark_get(struct net_bridge *br, struct net_device *dev) int nbp_switchdev_mark_set(struct net_bridge_port *p) { - struct switchdev_attr attr = { - .orig_dev = p->dev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; + struct netdev_phys_item_id ppid = { }; int err; ASSERT_RTNL(); - err = switchdev_port_attr_get(p->dev, &attr); + err = dev_get_port_parent_id(p->dev, &ppid, true); if (err) { if (err == -EOPNOTSUPP) return 0; @@ -113,7 +110,7 @@ br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, info.added_by_user = added_by_user; info.offloaded = offloaded; notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE; - call_switchdev_notifiers(notifier_type, dev, &info.info); + call_switchdev_notifiers(notifier_type, dev, &info.info, NULL); } void diff --git a/net/compat.c b/net/compat.c index 959d1c51826d..9629f053d4fa 100644 --- a/net/compat.c +++ b/net/compat.c @@ -209,8 +209,8 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat { struct compat_cmsghdr __user *cm = (struct compat_cmsghdr __user *) kmsg->msg_control; struct compat_cmsghdr cmhdr; - struct compat_timeval ctv; - struct compat_timespec cts[3]; + struct old_timeval32 ctv; + struct old_timespec32 cts[3]; int cmlen; if (cm == NULL || kmsg->msg_controllen < sizeof(*cm)) { @@ -219,16 +219,16 @@ int put_cmsg_compat(struct msghdr *kmsg, int level, int type, int len, void *dat } if (!COMPAT_USE_64BIT_TIME) { - if (level == SOL_SOCKET && type == SCM_TIMESTAMP) { - struct timeval *tv = (struct timeval *)data; + if (level == SOL_SOCKET && type == SO_TIMESTAMP_OLD) { + struct __kernel_old_timeval *tv = (struct __kernel_old_timeval *)data; ctv.tv_sec = tv->tv_sec; ctv.tv_usec = tv->tv_usec; data = &ctv; len = sizeof(ctv); } if (level == SOL_SOCKET && - (type == SCM_TIMESTAMPNS || type == SCM_TIMESTAMPING)) { - int count = type == SCM_TIMESTAMPNS ? 1 : 3; + (type == SO_TIMESTAMPNS_OLD || type == SO_TIMESTAMPING_OLD)) { + int count = type == SO_TIMESTAMPNS_OLD ? 1 : 3; int i; struct timespec *ts = (struct timespec *)data; for (i = 0; i < count; i++) { @@ -348,28 +348,6 @@ static int do_set_attach_filter(struct socket *sock, int level, int optname, sizeof(struct sock_fprog)); } -static int do_set_sock_timeout(struct socket *sock, int level, - int optname, char __user *optval, unsigned int optlen) -{ - struct compat_timeval __user *up = (struct compat_timeval __user *)optval; - struct timeval ktime; - mm_segment_t old_fs; - int err; - - if (optlen < sizeof(*up)) - return -EINVAL; - if (!access_ok(up, sizeof(*up)) || - __get_user(ktime.tv_sec, &up->tv_sec) || - __get_user(ktime.tv_usec, &up->tv_usec)) - return -EFAULT; - old_fs = get_fs(); - set_fs(KERNEL_DS); - err = sock_setsockopt(sock, level, optname, (char *)&ktime, sizeof(ktime)); - set_fs(old_fs); - - return err; -} - static int compat_sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, unsigned int optlen) { @@ -377,10 +355,6 @@ static int compat_sock_setsockopt(struct socket *sock, int level, int optname, optname == SO_ATTACH_REUSEPORT_CBPF) return do_set_attach_filter(sock, level, optname, optval, optlen); - if (!COMPAT_USE_64BIT_TIME && - (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) - return do_set_sock_timeout(sock, level, optname, optval, optlen); - return sock_setsockopt(sock, level, optname, optval, optlen); } @@ -417,44 +391,6 @@ COMPAT_SYSCALL_DEFINE5(setsockopt, int, fd, int, level, int, optname, return __compat_sys_setsockopt(fd, level, optname, optval, optlen); } -static int do_get_sock_timeout(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - struct compat_timeval __user *up; - struct timeval ktime; - mm_segment_t old_fs; - int len, err; - - up = (struct compat_timeval __user *) optval; - if (get_user(len, optlen)) - return -EFAULT; - if (len < sizeof(*up)) - return -EINVAL; - len = sizeof(ktime); - old_fs = get_fs(); - set_fs(KERNEL_DS); - err = sock_getsockopt(sock, level, optname, (char *) &ktime, &len); - set_fs(old_fs); - - if (!err) { - if (put_user(sizeof(*up), optlen) || - !access_ok(up, sizeof(*up)) || - __put_user(ktime.tv_sec, &up->tv_sec) || - __put_user(ktime.tv_usec, &up->tv_usec)) - err = -EFAULT; - } - return err; -} - -static int compat_sock_getsockopt(struct socket *sock, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (!COMPAT_USE_64BIT_TIME && - (optname == SO_RCVTIMEO || optname == SO_SNDTIMEO)) - return do_get_sock_timeout(sock, level, optname, optval, optlen); - return sock_getsockopt(sock, level, optname, optval, optlen); -} - int compat_sock_get_timestamp(struct sock *sk, struct timeval __user *userstamp) { struct compat_timeval __user *ctv; @@ -527,7 +463,7 @@ static int __compat_sys_getsockopt(int fd, int level, int optname, } if (level == SOL_SOCKET) - err = compat_sock_getsockopt(sock, level, + err = sock_getsockopt(sock, level, optname, optval, optlen); else if (sock->ops->compat_getsockopt) err = sock->ops->compat_getsockopt(sock, level, diff --git a/net/core/Makefile b/net/core/Makefile index fccd31e0e7f7..f97d6254e564 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -11,7 +11,7 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ neighbour.o rtnetlink.o utils.o link_watch.o filter.o \ sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \ - fib_notifier.o xdp.o + fib_notifier.o xdp.o flow_offload.o obj-y += net-sysfs.o obj-$(CONFIG_PAGE_POOL) += page_pool.o diff --git a/net/core/dev.c b/net/core/dev.c index 8e276e0192a1..ecbe419e05ab 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -7878,6 +7878,63 @@ int dev_get_phys_port_name(struct net_device *dev, EXPORT_SYMBOL(dev_get_phys_port_name); /** + * dev_get_port_parent_id - Get the device's port parent identifier + * @dev: network device + * @ppid: pointer to a storage for the port's parent identifier + * @recurse: allow/disallow recursion to lower devices + * + * Get the devices's port parent identifier + */ +int dev_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid, + bool recurse) +{ + const struct net_device_ops *ops = dev->netdev_ops; + struct netdev_phys_item_id first = { }; + struct net_device *lower_dev; + struct list_head *iter; + int err = -EOPNOTSUPP; + + if (ops->ndo_get_port_parent_id) + return ops->ndo_get_port_parent_id(dev, ppid); + + if (!recurse) + return err; + + netdev_for_each_lower_dev(dev, lower_dev, iter) { + err = dev_get_port_parent_id(lower_dev, ppid, recurse); + if (err) + break; + if (!first.id_len) + first = *ppid; + else if (memcmp(&first, ppid, sizeof(*ppid))) + return -ENODATA; + } + + return err; +} +EXPORT_SYMBOL(dev_get_port_parent_id); + +/** + * netdev_port_same_parent_id - Indicate if two network devices have + * the same port parent identifier + * @a: first network device + * @b: second network device + */ +bool netdev_port_same_parent_id(struct net_device *a, struct net_device *b) +{ + struct netdev_phys_item_id a_id = { }; + struct netdev_phys_item_id b_id = { }; + + if (dev_get_port_parent_id(a, &a_id, true) || + dev_get_port_parent_id(b, &b_id, true)) + return false; + + return netdev_phys_item_id_same(&a_id, &b_id); +} +EXPORT_SYMBOL(netdev_port_same_parent_id); + +/** * dev_change_proto_down - update protocol port state information * @dev: device * @proto_down: new value @@ -7976,35 +8033,41 @@ int dev_change_xdp_fd(struct net_device *dev, struct netlink_ext_ack *extack, enum bpf_netdev_command query; struct bpf_prog *prog = NULL; bpf_op_t bpf_op, bpf_chk; + bool offload; int err; ASSERT_RTNL(); - query = flags & XDP_FLAGS_HW_MODE ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; + offload = flags & XDP_FLAGS_HW_MODE; + query = offload ? XDP_QUERY_PROG_HW : XDP_QUERY_PROG; bpf_op = bpf_chk = ops->ndo_bpf; - if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) + if (!bpf_op && (flags & (XDP_FLAGS_DRV_MODE | XDP_FLAGS_HW_MODE))) { + NL_SET_ERR_MSG(extack, "underlying driver does not support XDP in native mode"); return -EOPNOTSUPP; + } if (!bpf_op || (flags & XDP_FLAGS_SKB_MODE)) bpf_op = generic_xdp_install; if (bpf_op == bpf_chk) bpf_chk = generic_xdp_install; if (fd >= 0) { - if (__dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG) || - __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG_HW)) + if (!offload && __dev_xdp_query(dev, bpf_chk, XDP_QUERY_PROG)) { + NL_SET_ERR_MSG(extack, "native and generic XDP can't be active at the same time"); return -EEXIST; + } if ((flags & XDP_FLAGS_UPDATE_IF_NOEXIST) && - __dev_xdp_query(dev, bpf_op, query)) + __dev_xdp_query(dev, bpf_op, query)) { + NL_SET_ERR_MSG(extack, "XDP program already attached"); return -EBUSY; + } prog = bpf_prog_get_type_dev(fd, BPF_PROG_TYPE_XDP, bpf_op == ops->ndo_bpf); if (IS_ERR(prog)) return PTR_ERR(prog); - if (!(flags & XDP_FLAGS_HW_MODE) && - bpf_prog_is_dev_bound(prog->aux)) { + if (!offload && bpf_prog_is_dev_bound(prog->aux)) { NL_SET_ERR_MSG(extack, "using device-bound program without HW_MODE flag is not supported"); bpf_prog_put(prog); return -EINVAL; diff --git a/net/core/devlink.c b/net/core/devlink.c index abb0da9d7b4b..1d7502a5a651 100644 --- a/net/core/devlink.c +++ b/net/core/devlink.c @@ -81,6 +81,7 @@ struct devlink_dpipe_header devlink_dpipe_header_ipv6 = { EXPORT_SYMBOL(devlink_dpipe_header_ipv6); EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwmsg); +EXPORT_TRACEPOINT_SYMBOL_GPL(devlink_hwerr); static LIST_HEAD(devlink_list); @@ -115,6 +116,8 @@ static struct devlink *devlink_get_from_attrs(struct net *net, busname = nla_data(attrs[DEVLINK_ATTR_BUS_NAME]); devname = nla_data(attrs[DEVLINK_ATTR_DEV_NAME]); + lockdep_assert_held(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { if (strcmp(devlink->dev->bus->name, busname) == 0 && strcmp(dev_name(devlink->dev), devname) == 0 && @@ -932,6 +935,9 @@ static int devlink_nl_sb_pool_fill(struct sk_buff *msg, struct devlink *devlink, if (nla_put_u8(msg, DEVLINK_ATTR_SB_POOL_THRESHOLD_TYPE, pool_info.threshold_type)) goto nla_put_failure; + if (nla_put_u32(msg, DEVLINK_ATTR_SB_POOL_CELL_SIZE, + pool_info.cell_size)) + goto nla_put_failure; genlmsg_end(msg, hdr); return 0; @@ -2843,11 +2849,13 @@ nla_put_failure: } static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, + unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd, u32 portid, u32 seq, int flags) { union devlink_param_value param_value[DEVLINK_PARAM_CMODE_MAX + 1]; + bool param_value_set[DEVLINK_PARAM_CMODE_MAX + 1] = {}; const struct devlink_param *param = param_item->param; struct devlink_param_gset_ctx ctx; struct nlattr *param_values_list; @@ -2866,12 +2874,15 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, return -EOPNOTSUPP; param_value[i] = param_item->driverinit_value; } else { + if (!param_item->published) + continue; ctx.cmode = i; err = devlink_param_get(devlink, param, &ctx); if (err) return err; param_value[i] = ctx.val; } + param_value_set[i] = true; } hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); @@ -2880,6 +2891,13 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, if (devlink_nl_put_handle(msg, devlink)) goto genlmsg_cancel; + + if (cmd == DEVLINK_CMD_PORT_PARAM_GET || + cmd == DEVLINK_CMD_PORT_PARAM_NEW || + cmd == DEVLINK_CMD_PORT_PARAM_DEL) + if (nla_put_u32(msg, DEVLINK_ATTR_PORT_INDEX, port_index)) + goto genlmsg_cancel; + param_attr = nla_nest_start(msg, DEVLINK_ATTR_PARAM); if (!param_attr) goto genlmsg_cancel; @@ -2899,7 +2917,7 @@ static int devlink_nl_param_fill(struct sk_buff *msg, struct devlink *devlink, goto param_nest_cancel; for (i = 0; i <= DEVLINK_PARAM_CMODE_MAX; i++) { - if (!devlink_param_cmode_is_supported(param, i)) + if (!param_value_set[i]) continue; err = devlink_nl_param_value_fill_one(msg, param->type, i, param_value[i]); @@ -2922,18 +2940,22 @@ genlmsg_cancel: } static void devlink_param_notify(struct devlink *devlink, + unsigned int port_index, struct devlink_param_item *param_item, enum devlink_command cmd) { struct sk_buff *msg; int err; - WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL); + WARN_ON(cmd != DEVLINK_CMD_PARAM_NEW && cmd != DEVLINK_CMD_PARAM_DEL && + cmd != DEVLINK_CMD_PORT_PARAM_NEW && + cmd != DEVLINK_CMD_PORT_PARAM_DEL); msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); if (!msg) return; - err = devlink_nl_param_fill(msg, devlink, param_item, cmd, 0, 0, 0); + err = devlink_nl_param_fill(msg, devlink, port_index, param_item, cmd, + 0, 0, 0); if (err) { nlmsg_free(msg); return; @@ -2962,7 +2984,7 @@ static int devlink_nl_cmd_param_get_dumpit(struct sk_buff *msg, idx++; continue; } - err = devlink_nl_param_fill(msg, devlink, param_item, + err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, @@ -3051,7 +3073,7 @@ devlink_param_value_get_from_info(const struct devlink_param *param, } static struct devlink_param_item * -devlink_param_get_from_info(struct devlink *devlink, +devlink_param_get_from_info(struct list_head *param_list, struct genl_info *info) { char *param_name; @@ -3060,7 +3082,7 @@ devlink_param_get_from_info(struct devlink *devlink, return NULL; param_name = nla_data(info->attrs[DEVLINK_ATTR_PARAM_NAME]); - return devlink_param_find_by_name(&devlink->param_list, param_name); + return devlink_param_find_by_name(param_list, param_name); } static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, @@ -3071,7 +3093,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, struct sk_buff *msg; int err; - param_item = devlink_param_get_from_info(devlink, info); + param_item = devlink_param_get_from_info(&devlink->param_list, info); if (!param_item) return -EINVAL; @@ -3079,7 +3101,7 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, if (!msg) return -ENOMEM; - err = devlink_nl_param_fill(msg, devlink, param_item, + err = devlink_nl_param_fill(msg, devlink, 0, param_item, DEVLINK_CMD_PARAM_GET, info->snd_portid, info->snd_seq, 0); if (err) { @@ -3090,10 +3112,12 @@ static int devlink_nl_cmd_param_get_doit(struct sk_buff *skb, return genlmsg_reply(msg, info); } -static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, - struct genl_info *info) +static int __devlink_nl_cmd_param_set_doit(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + struct genl_info *info, + enum devlink_command cmd) { - struct devlink *devlink = info->user_ptr[0]; enum devlink_param_type param_type; struct devlink_param_gset_ctx ctx; enum devlink_param_cmode cmode; @@ -3102,7 +3126,7 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, union devlink_param_value value; int err = 0; - param_item = devlink_param_get_from_info(devlink, info); + param_item = devlink_param_get_from_info(param_list, info); if (!param_item) return -EINVAL; param = param_item->param; @@ -3142,17 +3166,28 @@ static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, return err; } - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } +static int devlink_nl_cmd_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink, 0, &devlink->param_list, + info, DEVLINK_CMD_PARAM_NEW); +} + static int devlink_param_register_one(struct devlink *devlink, - const struct devlink_param *param) + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *param, + enum devlink_command cmd) { struct devlink_param_item *param_item; - if (devlink_param_find_by_name(&devlink->param_list, - param->name)) + if (devlink_param_find_by_name(param_list, param->name)) return -EEXIST; if (param->supported_cmodes == BIT(DEVLINK_PARAM_CMODE_DRIVERINIT)) @@ -3165,24 +3200,111 @@ static int devlink_param_register_one(struct devlink *devlink, return -ENOMEM; param_item->param = param; - list_add_tail(¶m_item->list, &devlink->param_list); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + list_add_tail(¶m_item->list, param_list); + devlink_param_notify(devlink, port_index, param_item, cmd); return 0; } static void devlink_param_unregister_one(struct devlink *devlink, - const struct devlink_param *param) + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *param, + enum devlink_command cmd) { struct devlink_param_item *param_item; - param_item = devlink_param_find_by_name(&devlink->param_list, - param->name); + param_item = devlink_param_find_by_name(param_list, param->name); WARN_ON(!param_item); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_DEL); + devlink_param_notify(devlink, port_index, param_item, cmd); list_del(¶m_item->list); kfree(param_item); } +static int devlink_nl_cmd_port_param_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_param_item *param_item; + struct devlink_port *devlink_port; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + list_for_each_entry(param_item, + &devlink_port->param_list, list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_param_fill(msg, + devlink_port->devlink, + devlink_port->index, param_item, + DEVLINK_CMD_PORT_PARAM_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int devlink_nl_cmd_port_param_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[0]; + struct devlink_param_item *param_item; + struct sk_buff *msg; + int err; + + param_item = devlink_param_get_from_info(&devlink_port->param_list, + info); + if (!param_item) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_param_fill(msg, devlink_port->devlink, + devlink_port->index, param_item, + DEVLINK_CMD_PORT_PARAM_GET, + info->snd_portid, info->snd_seq, 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_port_param_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink_port *devlink_port = info->user_ptr[0]; + + return __devlink_nl_cmd_param_set_doit(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, info, + DEVLINK_CMD_PORT_PARAM_NEW); +} + static int devlink_nl_region_snapshot_id_put(struct sk_buff *msg, struct devlink *devlink, struct devlink_snapshot *snapshot) @@ -3504,44 +3626,56 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, struct netlink_callback *cb) { u64 ret_offset, start_offset, end_offset = 0; - struct nlattr *attrs[DEVLINK_ATTR_MAX + 1]; const struct genl_ops *ops = cb->data; struct devlink_region *region; struct nlattr *chunks_attr; const char *region_name; struct devlink *devlink; + struct nlattr **attrs; bool dump = true; void *hdr; int err; start_offset = *((u64 *)&cb->args[0]); + attrs = kmalloc_array(DEVLINK_ATTR_MAX + 1, sizeof(*attrs), GFP_KERNEL); + if (!attrs) + return -ENOMEM; + err = nlmsg_parse(cb->nlh, GENL_HDRLEN + devlink_nl_family.hdrsize, attrs, DEVLINK_ATTR_MAX, ops->policy, cb->extack); if (err) - goto out; + goto out_free; + mutex_lock(&devlink_mutex); devlink = devlink_get_from_attrs(sock_net(cb->skb->sk), attrs); - if (IS_ERR(devlink)) - goto out; + if (IS_ERR(devlink)) { + err = PTR_ERR(devlink); + goto out_dev; + } - mutex_lock(&devlink_mutex); mutex_lock(&devlink->lock); if (!attrs[DEVLINK_ATTR_REGION_NAME] || - !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) + !attrs[DEVLINK_ATTR_REGION_SNAPSHOT_ID]) { + err = -EINVAL; goto out_unlock; + } region_name = nla_data(attrs[DEVLINK_ATTR_REGION_NAME]); region = devlink_region_get_by_name(devlink, region_name); - if (!region) + if (!region) { + err = -EINVAL; goto out_unlock; + } hdr = genlmsg_put(skb, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, &devlink_nl_family, NLM_F_ACK | NLM_F_MULTI, DEVLINK_CMD_REGION_READ); - if (!hdr) + if (!hdr) { + err = -EMSGSIZE; goto out_unlock; + } err = devlink_nl_put_handle(skb, devlink); if (err) @@ -3552,8 +3686,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; chunks_attr = nla_nest_start(skb, DEVLINK_ATTR_REGION_CHUNKS); - if (!chunks_attr) + if (!chunks_attr) { + err = -EMSGSIZE; goto nla_put_failure; + } if (attrs[DEVLINK_ATTR_REGION_CHUNK_ADDR] && attrs[DEVLINK_ATTR_REGION_CHUNK_LEN]) { @@ -3576,8 +3712,10 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, goto nla_put_failure; /* Check if there was any progress done to prevent infinite loop */ - if (ret_offset == start_offset) + if (ret_offset == start_offset) { + err = -EINVAL; goto nla_put_failure; + } *((u64 *)&cb->args[0]) = ret_offset; @@ -3585,6 +3723,7 @@ static int devlink_nl_cmd_region_read_dumpit(struct sk_buff *skb, genlmsg_end(skb, hdr); mutex_unlock(&devlink->lock); mutex_unlock(&devlink_mutex); + kfree(attrs); return skb->len; @@ -3592,8 +3731,1127 @@ nla_put_failure: genlmsg_cancel(skb, hdr); out_unlock: mutex_unlock(&devlink->lock); +out_dev: + mutex_unlock(&devlink_mutex); +out_free: + kfree(attrs); + return err; +} + +struct devlink_info_req { + struct sk_buff *msg; +}; + +int devlink_info_driver_name_put(struct devlink_info_req *req, const char *name) +{ + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_DRIVER_NAME, name); +} +EXPORT_SYMBOL_GPL(devlink_info_driver_name_put); + +int devlink_info_serial_number_put(struct devlink_info_req *req, const char *sn) +{ + return nla_put_string(req->msg, DEVLINK_ATTR_INFO_SERIAL_NUMBER, sn); +} +EXPORT_SYMBOL_GPL(devlink_info_serial_number_put); + +static int devlink_info_version_put(struct devlink_info_req *req, int attr, + const char *version_name, + const char *version_value) +{ + struct nlattr *nest; + int err; + + nest = nla_nest_start(req->msg, attr); + if (!nest) + return -EMSGSIZE; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_NAME, + version_name); + if (err) + goto nla_put_failure; + + err = nla_put_string(req->msg, DEVLINK_ATTR_INFO_VERSION_VALUE, + version_value); + if (err) + goto nla_put_failure; + + nla_nest_end(req->msg, nest); + + return 0; + +nla_put_failure: + nla_nest_cancel(req->msg, nest); + return err; +} + +int devlink_info_version_fixed_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_FIXED, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_fixed_put); + +int devlink_info_version_stored_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_STORED, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_stored_put); + +int devlink_info_version_running_put(struct devlink_info_req *req, + const char *version_name, + const char *version_value) +{ + return devlink_info_version_put(req, DEVLINK_ATTR_INFO_VERSION_RUNNING, + version_name, version_value); +} +EXPORT_SYMBOL_GPL(devlink_info_version_running_put); + +static int +devlink_nl_info_fill(struct sk_buff *msg, struct devlink *devlink, + enum devlink_command cmd, u32 portid, + u32 seq, int flags, struct netlink_ext_ack *extack) +{ + struct devlink_info_req req; + void *hdr; + int err; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + err = -EMSGSIZE; + if (devlink_nl_put_handle(msg, devlink)) + goto err_cancel_msg; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, extack); + if (err) + goto err_cancel_msg; + + genlmsg_end(msg, hdr); + return 0; + +err_cancel_msg: + genlmsg_cancel(msg, hdr); + return err; +} + +static int devlink_nl_cmd_info_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct sk_buff *msg; + int err; + + if (!devlink->ops || !devlink->ops->info_get) + return -EOPNOTSUPP; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + info->snd_portid, info->snd_seq, 0, + info->extack); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int devlink_nl_cmd_info_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + if (idx < start) { + idx++; + continue; + } + + mutex_lock(&devlink->lock); + err = devlink_nl_info_fill(msg, devlink, DEVLINK_CMD_INFO_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + cb->extack); + mutex_unlock(&devlink->lock); + if (err) + break; + idx++; + } mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +struct devlink_fmsg_item { + struct list_head list; + int attrtype; + u8 nla_type; + u16 len; + int value[0]; +}; + +struct devlink_fmsg { + struct list_head item_list; +}; + +static struct devlink_fmsg *devlink_fmsg_alloc(void) +{ + struct devlink_fmsg *fmsg; + + fmsg = kzalloc(sizeof(*fmsg), GFP_KERNEL); + if (!fmsg) + return NULL; + + INIT_LIST_HEAD(&fmsg->item_list); + + return fmsg; +} + +static void devlink_fmsg_free(struct devlink_fmsg *fmsg) +{ + struct devlink_fmsg_item *item, *tmp; + + list_for_each_entry_safe(item, tmp, &fmsg->item_list, list) { + list_del(&item->list); + kfree(item); + } + kfree(fmsg); +} + +static int devlink_fmsg_nest_common(struct devlink_fmsg *fmsg, + int attrtype) +{ + struct devlink_fmsg_item *item; + + item = kzalloc(sizeof(*item), GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->attrtype = attrtype; + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_obj_nest_start(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_OBJ_NEST_START); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_start); + +static int devlink_fmsg_nest_end(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_NEST_END); +} + +int devlink_fmsg_obj_nest_end(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_obj_nest_end); + +#define DEVLINK_FMSG_MAX_SIZE (GENLMSG_DEFAULT_SIZE - GENL_HDRLEN - NLA_HDRLEN) + +static int devlink_fmsg_put_name(struct devlink_fmsg *fmsg, const char *name) +{ + struct devlink_fmsg_item *item; + + if (strlen(name) + 1 > DEVLINK_FMSG_MAX_SIZE) + return -EMSGSIZE; + + item = kzalloc(sizeof(*item) + strlen(name) + 1, GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->nla_type = NLA_NUL_STRING; + item->len = strlen(name) + 1; + item->attrtype = DEVLINK_ATTR_FMSG_OBJ_NAME; + memcpy(&item->value, name, item->len); + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_pair_nest_start(struct devlink_fmsg *fmsg, const char *name) +{ + int err; + + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_PAIR_NEST_START); + if (err) + return err; + + err = devlink_fmsg_put_name(fmsg, name); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_start); + +int devlink_fmsg_pair_nest_end(struct devlink_fmsg *fmsg) +{ + return devlink_fmsg_nest_end(fmsg); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_pair_nest_end); + +int devlink_fmsg_arr_pair_nest_start(struct devlink_fmsg *fmsg, + const char *name) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_nest_common(fmsg, DEVLINK_ATTR_FMSG_ARR_NEST_START); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_start); + +int devlink_fmsg_arr_pair_nest_end(struct devlink_fmsg *fmsg) +{ + int err; + + err = devlink_fmsg_nest_end(fmsg); + if (err) + return err; + + err = devlink_fmsg_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_arr_pair_nest_end); + +static int devlink_fmsg_put_value(struct devlink_fmsg *fmsg, + const void *value, u16 value_len, + u8 value_nla_type) +{ + struct devlink_fmsg_item *item; + + if (value_len > DEVLINK_FMSG_MAX_SIZE) + return -EMSGSIZE; + + item = kzalloc(sizeof(*item) + value_len, GFP_KERNEL); + if (!item) + return -ENOMEM; + + item->nla_type = value_nla_type; + item->len = value_len; + item->attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; + memcpy(&item->value, value, item->len); + list_add_tail(&item->list, &fmsg->item_list); + + return 0; +} + +int devlink_fmsg_bool_put(struct devlink_fmsg *fmsg, bool value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_FLAG); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_bool_put); + +int devlink_fmsg_u8_put(struct devlink_fmsg *fmsg, u8 value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U8); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u8_put); + +int devlink_fmsg_u32_put(struct devlink_fmsg *fmsg, u32 value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U32); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u32_put); + +int devlink_fmsg_u64_put(struct devlink_fmsg *fmsg, u64 value) +{ + return devlink_fmsg_put_value(fmsg, &value, sizeof(value), NLA_U64); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u64_put); + +int devlink_fmsg_string_put(struct devlink_fmsg *fmsg, const char *value) +{ + return devlink_fmsg_put_value(fmsg, value, strlen(value) + 1, + NLA_NUL_STRING); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_string_put); + +int devlink_fmsg_binary_put(struct devlink_fmsg *fmsg, const void *value, + u16 value_len) +{ + return devlink_fmsg_put_value(fmsg, value, value_len, NLA_BINARY); +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_put); + +int devlink_fmsg_bool_pair_put(struct devlink_fmsg *fmsg, const char *name, + bool value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_bool_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_bool_pair_put); + +int devlink_fmsg_u8_pair_put(struct devlink_fmsg *fmsg, const char *name, + u8 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u8_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u8_pair_put); + +int devlink_fmsg_u32_pair_put(struct devlink_fmsg *fmsg, const char *name, + u32 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u32_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u32_pair_put); + +int devlink_fmsg_u64_pair_put(struct devlink_fmsg *fmsg, const char *name, + u64 value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_u64_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_u64_pair_put); + +int devlink_fmsg_string_pair_put(struct devlink_fmsg *fmsg, const char *name, + const char *value) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_string_put(fmsg, value); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_string_pair_put); + +int devlink_fmsg_binary_pair_put(struct devlink_fmsg *fmsg, const char *name, + const void *value, u16 value_len) +{ + int err; + + err = devlink_fmsg_pair_nest_start(fmsg, name); + if (err) + return err; + + err = devlink_fmsg_binary_put(fmsg, value, value_len); + if (err) + return err; + + err = devlink_fmsg_pair_nest_end(fmsg); + if (err) + return err; + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_fmsg_binary_pair_put); + +static int +devlink_fmsg_item_fill_type(struct devlink_fmsg_item *msg, struct sk_buff *skb) +{ + switch (msg->nla_type) { + case NLA_FLAG: + case NLA_U8: + case NLA_U32: + case NLA_U64: + case NLA_NUL_STRING: + case NLA_BINARY: + return nla_put_u8(skb, DEVLINK_ATTR_FMSG_OBJ_VALUE_TYPE, + msg->nla_type); + default: + return -EINVAL; + } +} + +static int +devlink_fmsg_item_fill_data(struct devlink_fmsg_item *msg, struct sk_buff *skb) +{ + int attrtype = DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA; + u8 tmp; + + switch (msg->nla_type) { + case NLA_FLAG: + /* Always provide flag data, regardless of its value */ + tmp = *(bool *) msg->value; + + return nla_put_u8(skb, attrtype, tmp); + case NLA_U8: + return nla_put_u8(skb, attrtype, *(u8 *) msg->value); + case NLA_U32: + return nla_put_u32(skb, attrtype, *(u32 *) msg->value); + case NLA_U64: + return nla_put_u64_64bit(skb, attrtype, *(u64 *) msg->value, + DEVLINK_ATTR_PAD); + case NLA_NUL_STRING: + return nla_put_string(skb, attrtype, (char *) &msg->value); + case NLA_BINARY: + return nla_put(skb, attrtype, msg->len, (void *) &msg->value); + default: + return -EINVAL; + } +} + +static int +devlink_fmsg_prepare_skb(struct devlink_fmsg *fmsg, struct sk_buff *skb, + int *start) +{ + struct devlink_fmsg_item *item; + struct nlattr *fmsg_nlattr; + int i = 0; + int err; + + fmsg_nlattr = nla_nest_start(skb, DEVLINK_ATTR_FMSG); + if (!fmsg_nlattr) + return -EMSGSIZE; + + list_for_each_entry(item, &fmsg->item_list, list) { + if (i < *start) { + i++; + continue; + } + + switch (item->attrtype) { + case DEVLINK_ATTR_FMSG_OBJ_NEST_START: + case DEVLINK_ATTR_FMSG_PAIR_NEST_START: + case DEVLINK_ATTR_FMSG_ARR_NEST_START: + case DEVLINK_ATTR_FMSG_NEST_END: + err = nla_put_flag(skb, item->attrtype); + break; + case DEVLINK_ATTR_FMSG_OBJ_VALUE_DATA: + err = devlink_fmsg_item_fill_type(item, skb); + if (err) + break; + err = devlink_fmsg_item_fill_data(item, skb); + break; + case DEVLINK_ATTR_FMSG_OBJ_NAME: + err = nla_put_string(skb, item->attrtype, + (char *) &item->value); + break; + default: + err = -EINVAL; + break; + } + if (!err) + *start = ++i; + else + break; + } + + nla_nest_end(skb, fmsg_nlattr); + return err; +} + +static int devlink_fmsg_snd(struct devlink_fmsg *fmsg, + struct genl_info *info, + enum devlink_command cmd, int flags) +{ + struct nlmsghdr *nlh; + struct sk_buff *skb; + bool last = false; + int index = 0; + void *hdr; + int err; + + while (!last) { + int tmp_index = index; + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + + hdr = genlmsg_put(skb, info->snd_portid, info->snd_seq, + &devlink_nl_family, flags | NLM_F_MULTI, cmd); + if (!hdr) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + err = devlink_fmsg_prepare_skb(fmsg, skb, &index); + if (!err) + last = true; + else if (err != -EMSGSIZE || tmp_index == index) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + err = genlmsg_reply(skb, info); + if (err) + return err; + } + + skb = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!skb) + return -ENOMEM; + nlh = nlmsg_put(skb, info->snd_portid, info->snd_seq, + NLMSG_DONE, 0, flags | NLM_F_MULTI); + if (!nlh) { + err = -EMSGSIZE; + goto nla_put_failure; + } + + return genlmsg_reply(skb, info); + +nla_put_failure: + nlmsg_free(skb); + return err; +} + +struct devlink_health_reporter { + struct list_head list; + void *priv; + const struct devlink_health_reporter_ops *ops; + struct devlink *devlink; + struct devlink_fmsg *dump_fmsg; + struct mutex dump_lock; /* lock parallel read/write from dump buffers */ + u64 graceful_period; + bool auto_recover; + u8 health_state; + u64 dump_ts; + u64 error_count; + u64 recovery_count; + u64 last_recovery_ts; +}; + +enum devlink_health_reporter_state { + DEVLINK_HEALTH_REPORTER_STATE_HEALTHY, + DEVLINK_HEALTH_REPORTER_STATE_ERROR, +}; + +void * +devlink_health_reporter_priv(struct devlink_health_reporter *reporter) +{ + return reporter->priv; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_priv); + +static struct devlink_health_reporter * +devlink_health_reporter_find_by_name(struct devlink *devlink, + const char *reporter_name) +{ + struct devlink_health_reporter *reporter; + + list_for_each_entry(reporter, &devlink->reporter_list, list) + if (!strcmp(reporter->ops->name, reporter_name)) + return reporter; + return NULL; +} + +/** + * devlink_health_reporter_create - create devlink health reporter + * + * @devlink: devlink + * @ops: ops + * @graceful_period: to avoid recovery loops, in msecs + * @auto_recover: auto recover when error occurs + * @priv: priv + */ +struct devlink_health_reporter * +devlink_health_reporter_create(struct devlink *devlink, + const struct devlink_health_reporter_ops *ops, + u64 graceful_period, bool auto_recover, + void *priv) +{ + struct devlink_health_reporter *reporter; + + mutex_lock(&devlink->lock); + if (devlink_health_reporter_find_by_name(devlink, ops->name)) { + reporter = ERR_PTR(-EEXIST); + goto unlock; + } + + if (WARN_ON(auto_recover && !ops->recover) || + WARN_ON(graceful_period && !ops->recover)) { + reporter = ERR_PTR(-EINVAL); + goto unlock; + } + + reporter = kzalloc(sizeof(*reporter), GFP_KERNEL); + if (!reporter) { + reporter = ERR_PTR(-ENOMEM); + goto unlock; + } + + reporter->priv = priv; + reporter->ops = ops; + reporter->devlink = devlink; + reporter->graceful_period = graceful_period; + reporter->auto_recover = auto_recover; + mutex_init(&reporter->dump_lock); + list_add_tail(&reporter->list, &devlink->reporter_list); +unlock: + mutex_unlock(&devlink->lock); + return reporter; +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_create); + +/** + * devlink_health_reporter_destroy - destroy devlink health reporter + * + * @reporter: devlink health reporter to destroy + */ +void +devlink_health_reporter_destroy(struct devlink_health_reporter *reporter) +{ + mutex_lock(&reporter->devlink->lock); + list_del(&reporter->list); + mutex_unlock(&reporter->devlink->lock); + if (reporter->dump_fmsg) + devlink_fmsg_free(reporter->dump_fmsg); + kfree(reporter); +} +EXPORT_SYMBOL_GPL(devlink_health_reporter_destroy); + +static int +devlink_health_reporter_recover(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->recover) + return -EOPNOTSUPP; + + err = reporter->ops->recover(reporter, priv_ctx); + if (err) + return err; + + reporter->recovery_count++; + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_HEALTHY; + reporter->last_recovery_ts = jiffies; + + return 0; +} + +static void +devlink_health_dump_clear(struct devlink_health_reporter *reporter) +{ + if (!reporter->dump_fmsg) + return; + devlink_fmsg_free(reporter->dump_fmsg); + reporter->dump_fmsg = NULL; +} + +static int devlink_health_do_dump(struct devlink_health_reporter *reporter, + void *priv_ctx) +{ + int err; + + if (!reporter->ops->dump) + return 0; + + if (reporter->dump_fmsg) + return 0; + + reporter->dump_fmsg = devlink_fmsg_alloc(); + if (!reporter->dump_fmsg) { + err = -ENOMEM; + return err; + } + + err = devlink_fmsg_obj_nest_start(reporter->dump_fmsg); + if (err) + goto dump_err; + + err = reporter->ops->dump(reporter, reporter->dump_fmsg, + priv_ctx); + if (err) + goto dump_err; + + err = devlink_fmsg_obj_nest_end(reporter->dump_fmsg); + if (err) + goto dump_err; + + reporter->dump_ts = jiffies; + + return 0; + +dump_err: + devlink_health_dump_clear(reporter); + return err; +} + +int devlink_health_report(struct devlink_health_reporter *reporter, + const char *msg, void *priv_ctx) +{ + struct devlink *devlink = reporter->devlink; + + /* write a log message of the current error */ + WARN_ON(!msg); + trace_devlink_health_report(devlink, reporter->ops->name, msg); + reporter->error_count++; + + /* abort if the previous error wasn't recovered */ + if (reporter->auto_recover && + (reporter->health_state != DEVLINK_HEALTH_REPORTER_STATE_HEALTHY || + jiffies - reporter->last_recovery_ts < + msecs_to_jiffies(reporter->graceful_period))) { + trace_devlink_health_recover_aborted(devlink, + reporter->ops->name, + reporter->health_state, + jiffies - + reporter->last_recovery_ts); + return -ECANCELED; + } + + reporter->health_state = DEVLINK_HEALTH_REPORTER_STATE_ERROR; + + mutex_lock(&reporter->dump_lock); + /* store current dump of current error, for later analysis */ + devlink_health_do_dump(reporter, priv_ctx); + mutex_unlock(&reporter->dump_lock); + + if (reporter->auto_recover) + return devlink_health_reporter_recover(reporter, priv_ctx); + + return 0; +} +EXPORT_SYMBOL_GPL(devlink_health_report); + +static struct devlink_health_reporter * +devlink_health_reporter_get_from_info(struct devlink *devlink, + struct genl_info *info) +{ + char *reporter_name; + + if (!info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]) + return NULL; + + reporter_name = + nla_data(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_NAME]); + return devlink_health_reporter_find_by_name(devlink, reporter_name); +} + +static int +devlink_nl_health_reporter_fill(struct sk_buff *msg, + struct devlink *devlink, + struct devlink_health_reporter *reporter, + enum devlink_command cmd, u32 portid, + u32 seq, int flags) +{ + struct nlattr *reporter_attr; + void *hdr; + + hdr = genlmsg_put(msg, portid, seq, &devlink_nl_family, flags, cmd); + if (!hdr) + return -EMSGSIZE; + + if (devlink_nl_put_handle(msg, devlink)) + goto genlmsg_cancel; + + reporter_attr = nla_nest_start(msg, DEVLINK_ATTR_HEALTH_REPORTER); + if (!reporter_attr) + goto genlmsg_cancel; + if (nla_put_string(msg, DEVLINK_ATTR_HEALTH_REPORTER_NAME, + reporter->ops->name)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_STATE, + reporter->health_state)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_ERR, + reporter->error_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_RECOVER, + reporter->recovery_count, DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD, + reporter->graceful_period, + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + if (nla_put_u8(msg, DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER, + reporter->auto_recover)) + goto reporter_nest_cancel; + if (reporter->dump_fmsg && + nla_put_u64_64bit(msg, DEVLINK_ATTR_HEALTH_REPORTER_DUMP_TS, + jiffies_to_msecs(reporter->dump_ts), + DEVLINK_ATTR_PAD)) + goto reporter_nest_cancel; + + nla_nest_end(msg, reporter_attr); + genlmsg_end(msg, hdr); + return 0; + +reporter_nest_cancel: + nla_nest_end(msg, reporter_attr); +genlmsg_cancel: + genlmsg_cancel(msg, hdr); + return -EMSGSIZE; +} + +static int devlink_nl_cmd_health_reporter_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct sk_buff *msg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + err = devlink_nl_health_reporter_fill(msg, devlink, reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + info->snd_portid, info->snd_seq, + 0); + if (err) { + nlmsg_free(msg); + return err; + } + + return genlmsg_reply(msg, info); +} + +static int +devlink_nl_cmd_health_reporter_get_dumpit(struct sk_buff *msg, + struct netlink_callback *cb) +{ + struct devlink_health_reporter *reporter; + struct devlink *devlink; + int start = cb->args[0]; + int idx = 0; + int err; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + if (!net_eq(devlink_net(devlink), sock_net(msg->sk))) + continue; + mutex_lock(&devlink->lock); + list_for_each_entry(reporter, &devlink->reporter_list, + list) { + if (idx < start) { + idx++; + continue; + } + err = devlink_nl_health_reporter_fill(msg, devlink, + reporter, + DEVLINK_CMD_HEALTH_REPORTER_GET, + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, + NLM_F_MULTI); + if (err) { + mutex_unlock(&devlink->lock); + goto out; + } + idx++; + } + mutex_unlock(&devlink->lock); + } out: + mutex_unlock(&devlink_mutex); + + cb->args[0] = idx; + return msg->len; +} + +static int +devlink_nl_cmd_health_reporter_set_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->recover && + (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] || + info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER])) + return -EOPNOTSUPP; + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]) + reporter->graceful_period = + nla_get_u64(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD]); + + if (info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]) + reporter->auto_recover = + nla_get_u8(info->attrs[DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER]); + + return 0; +} + +static int devlink_nl_cmd_health_reporter_recover_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + return devlink_health_reporter_recover(reporter, NULL); +} + +static int devlink_nl_cmd_health_reporter_diagnose_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + struct devlink_fmsg *fmsg; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->diagnose) + return -EOPNOTSUPP; + + fmsg = devlink_fmsg_alloc(); + if (!fmsg) + return -ENOMEM; + + err = devlink_fmsg_obj_nest_start(fmsg); + if (err) + goto out; + + err = reporter->ops->diagnose(reporter, fmsg); + if (err) + goto out; + + err = devlink_fmsg_obj_nest_end(fmsg); + if (err) + goto out; + + err = devlink_fmsg_snd(fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, 0); + +out: + devlink_fmsg_free(fmsg); + return err; +} + +static int devlink_nl_cmd_health_reporter_dump_get_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + int err; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) + return -EOPNOTSUPP; + + mutex_lock(&reporter->dump_lock); + err = devlink_health_do_dump(reporter, NULL); + if (err) + goto out; + + err = devlink_fmsg_snd(reporter->dump_fmsg, info, + DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, 0); + +out: + mutex_unlock(&reporter->dump_lock); + return err; +} + +static int +devlink_nl_cmd_health_reporter_dump_clear_doit(struct sk_buff *skb, + struct genl_info *info) +{ + struct devlink *devlink = info->user_ptr[0]; + struct devlink_health_reporter *reporter; + + reporter = devlink_health_reporter_get_from_info(devlink, info); + if (!reporter) + return -EINVAL; + + if (!reporter->ops->dump) + return -EOPNOTSUPP; + + mutex_lock(&reporter->dump_lock); + devlink_health_dump_clear(reporter); + mutex_unlock(&reporter->dump_lock); return 0; } @@ -3622,6 +4880,9 @@ static const struct nla_policy devlink_nl_policy[DEVLINK_ATTR_MAX + 1] = { [DEVLINK_ATTR_PARAM_VALUE_CMODE] = { .type = NLA_U8 }, [DEVLINK_ATTR_REGION_NAME] = { .type = NLA_NUL_STRING }, [DEVLINK_ATTR_REGION_SNAPSHOT_ID] = { .type = NLA_U32 }, + [DEVLINK_ATTR_HEALTH_REPORTER_NAME] = { .type = NLA_NUL_STRING }, + [DEVLINK_ATTR_HEALTH_REPORTER_GRACEFUL_PERIOD] = { .type = NLA_U64 }, + [DEVLINK_ATTR_HEALTH_REPORTER_AUTO_RECOVER] = { .type = NLA_U8 }, }; static const struct genl_ops devlink_nl_ops[] = { @@ -3821,6 +5082,21 @@ static const struct genl_ops devlink_nl_ops[] = { .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, { + .cmd = DEVLINK_CMD_PORT_PARAM_GET, + .doit = devlink_nl_cmd_port_param_get_doit, + .dumpit = devlink_nl_cmd_port_param_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_PORT_PARAM_SET, + .doit = devlink_nl_cmd_port_param_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_PORT, + }, + { .cmd = DEVLINK_CMD_REGION_GET, .doit = devlink_nl_cmd_region_get_doit, .dumpit = devlink_nl_cmd_region_get_dumpit, @@ -3842,6 +5118,59 @@ static const struct genl_ops devlink_nl_ops[] = { .flags = GENL_ADMIN_PERM, .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, }, + { + .cmd = DEVLINK_CMD_INFO_GET, + .doit = devlink_nl_cmd_info_get_doit, + .dumpit = devlink_nl_cmd_info_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_GET, + .doit = devlink_nl_cmd_health_reporter_get_doit, + .dumpit = devlink_nl_cmd_health_reporter_get_dumpit, + .policy = devlink_nl_policy, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + /* can be retrieved by unprivileged users */ + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_SET, + .doit = devlink_nl_cmd_health_reporter_set_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_RECOVER, + .doit = devlink_nl_cmd_health_reporter_recover_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DIAGNOSE, + .doit = devlink_nl_cmd_health_reporter_diagnose_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_GET, + .doit = devlink_nl_cmd_health_reporter_dump_get_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, + { + .cmd = DEVLINK_CMD_HEALTH_REPORTER_DUMP_CLEAR, + .doit = devlink_nl_cmd_health_reporter_dump_clear_doit, + .policy = devlink_nl_policy, + .flags = GENL_ADMIN_PERM, + .internal_flags = DEVLINK_NL_FLAG_NEED_DEVLINK | + DEVLINK_NL_FLAG_NO_LOCK, + }, }; static struct genl_family devlink_nl_family __ro_after_init = { @@ -3882,6 +5211,7 @@ struct devlink *devlink_alloc(const struct devlink_ops *ops, size_t priv_size) INIT_LIST_HEAD(&devlink->resource_list); INIT_LIST_HEAD(&devlink->param_list); INIT_LIST_HEAD(&devlink->region_list); + INIT_LIST_HEAD(&devlink->reporter_list); mutex_init(&devlink->lock); return devlink; } @@ -3924,6 +5254,14 @@ EXPORT_SYMBOL_GPL(devlink_unregister); */ void devlink_free(struct devlink *devlink) { + WARN_ON(!list_empty(&devlink->reporter_list)); + WARN_ON(!list_empty(&devlink->region_list)); + WARN_ON(!list_empty(&devlink->param_list)); + WARN_ON(!list_empty(&devlink->resource_list)); + WARN_ON(!list_empty(&devlink->dpipe_table_list)); + WARN_ON(!list_empty(&devlink->sb_list)); + WARN_ON(!list_empty(&devlink->port_list)); + kfree(devlink); } EXPORT_SYMBOL_GPL(devlink_free); @@ -3954,6 +5292,7 @@ int devlink_port_register(struct devlink *devlink, devlink_port->index = port_index; devlink_port->registered = true; list_add_tail(&devlink_port->list, &devlink->port_list); + INIT_LIST_HEAD(&devlink_port->param_list); mutex_unlock(&devlink->lock); devlink_port_notify(devlink_port, DEVLINK_CMD_PORT_NEW); return 0; @@ -4471,18 +5810,23 @@ out: } EXPORT_SYMBOL_GPL(devlink_resource_occ_get_unregister); -/** - * devlink_params_register - register configuration parameters - * - * @devlink: devlink - * @params: configuration parameters array - * @params_count: number of parameters provided - * - * Register the configuration parameters supported by the driver. - */ -int devlink_params_register(struct devlink *devlink, - const struct devlink_param *params, - size_t params_count) +static int devlink_param_verify(const struct devlink_param *param) +{ + if (!param || !param->name || !param->supported_cmodes) + return -EINVAL; + if (param->generic) + return devlink_param_generic_verify(param); + else + return devlink_param_driver_verify(param); +} + +static int __devlink_params_register(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *params, + size_t params_count, + enum devlink_command reg_cmd, + enum devlink_command unreg_cmd) { const struct devlink_param *param = params; int i; @@ -4490,20 +5834,12 @@ int devlink_params_register(struct devlink *devlink, mutex_lock(&devlink->lock); for (i = 0; i < params_count; i++, param++) { - if (!param || !param->name || !param->supported_cmodes) { - err = -EINVAL; + err = devlink_param_verify(param); + if (err) goto rollback; - } - if (param->generic) { - err = devlink_param_generic_verify(param); - if (err) - goto rollback; - } else { - err = devlink_param_driver_verify(param); - if (err) - goto rollback; - } - err = devlink_param_register_one(devlink, param); + + err = devlink_param_register_one(devlink, port_index, + param_list, param, reg_cmd); if (err) goto rollback; } @@ -4515,11 +5851,48 @@ rollback: if (!i) goto unlock; for (param--; i > 0; i--, param--) - devlink_param_unregister_one(devlink, param); + devlink_param_unregister_one(devlink, port_index, param_list, + param, unreg_cmd); unlock: mutex_unlock(&devlink->lock); return err; } + +static void __devlink_params_unregister(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, + const struct devlink_param *params, + size_t params_count, + enum devlink_command cmd) +{ + const struct devlink_param *param = params; + int i; + + mutex_lock(&devlink->lock); + for (i = 0; i < params_count; i++, param++) + devlink_param_unregister_one(devlink, 0, param_list, param, + cmd); + mutex_unlock(&devlink->lock); +} + +/** + * devlink_params_register - register configuration parameters + * + * @devlink: devlink + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the driver. + */ +int devlink_params_register(struct devlink *devlink, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_register(devlink, 0, &devlink->param_list, + params, params_count, + DEVLINK_CMD_PARAM_NEW, + DEVLINK_CMD_PARAM_DEL); +} EXPORT_SYMBOL_GPL(devlink_params_register); /** @@ -4532,36 +5905,103 @@ void devlink_params_unregister(struct devlink *devlink, const struct devlink_param *params, size_t params_count) { - const struct devlink_param *param = params; - int i; - - mutex_lock(&devlink->lock); - for (i = 0; i < params_count; i++, param++) - devlink_param_unregister_one(devlink, param); - mutex_unlock(&devlink->lock); + return __devlink_params_unregister(devlink, 0, &devlink->param_list, + params, params_count, + DEVLINK_CMD_PARAM_DEL); } EXPORT_SYMBOL_GPL(devlink_params_unregister); /** - * devlink_param_driverinit_value_get - get configuration parameter - * value for driver initializing + * devlink_params_publish - publish configuration parameters * * @devlink: devlink - * @param_id: parameter ID - * @init_val: value of parameter in driverinit configuration mode * - * This function should be used by the driver to get driverinit - * configuration for initialization after reload command. + * Publish previously registered configuration parameters. */ -int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, - union devlink_param_value *init_val) +void devlink_params_publish(struct devlink *devlink) { struct devlink_param_item *param_item; - if (!devlink->ops || !devlink->ops->reload) - return -EOPNOTSUPP; + list_for_each_entry(param_item, &devlink->param_list, list) { + if (param_item->published) + continue; + param_item->published = true; + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_NEW); + } +} +EXPORT_SYMBOL_GPL(devlink_params_publish); - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); +/** + * devlink_params_unpublish - unpublish configuration parameters + * + * @devlink: devlink + * + * Unpublish previously registered configuration parameters. + */ +void devlink_params_unpublish(struct devlink *devlink) +{ + struct devlink_param_item *param_item; + + list_for_each_entry(param_item, &devlink->param_list, list) { + if (!param_item->published) + continue; + param_item->published = false; + devlink_param_notify(devlink, 0, param_item, + DEVLINK_CMD_PARAM_DEL); + } +} +EXPORT_SYMBOL_GPL(devlink_params_unpublish); + +/** + * devlink_port_params_register - register port configuration parameters + * + * @devlink_port: devlink port + * @params: configuration parameters array + * @params_count: number of parameters provided + * + * Register the configuration parameters supported by the port. + */ +int devlink_port_params_register(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_register(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, params, + params_count, + DEVLINK_CMD_PORT_PARAM_NEW, + DEVLINK_CMD_PORT_PARAM_DEL); +} +EXPORT_SYMBOL_GPL(devlink_port_params_register); + +/** + * devlink_port_params_unregister - unregister port configuration + * parameters + * + * @devlink_port: devlink port + * @params: configuration parameters array + * @params_count: number of parameters provided + */ +void devlink_port_params_unregister(struct devlink_port *devlink_port, + const struct devlink_param *params, + size_t params_count) +{ + return __devlink_params_unregister(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, + params, params_count, + DEVLINK_CMD_PORT_PARAM_DEL); +} +EXPORT_SYMBOL_GPL(devlink_port_params_unregister); + +static int +__devlink_param_driverinit_value_get(struct list_head *param_list, u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(param_list, param_id); if (!param_item) return -EINVAL; @@ -4577,6 +6017,54 @@ int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, return 0; } + +static int +__devlink_param_driverinit_value_set(struct devlink *devlink, + unsigned int port_index, + struct list_head *param_list, u32 param_id, + union devlink_param_value init_val, + enum devlink_command cmd) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(param_list, param_id); + if (!param_item) + return -EINVAL; + + if (!devlink_param_cmode_is_supported(param_item->param, + DEVLINK_PARAM_CMODE_DRIVERINIT)) + return -EOPNOTSUPP; + + if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) + strcpy(param_item->driverinit_value.vstr, init_val.vstr); + else + param_item->driverinit_value = init_val; + param_item->driverinit_value_valid = true; + + devlink_param_notify(devlink, port_index, param_item, cmd); + return 0; +} + +/** + * devlink_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink: devlink + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_param_driverinit_value_get(struct devlink *devlink, u32 param_id, + union devlink_param_value *init_val) +{ + if (!devlink->ops || !devlink->ops->reload) + return -EOPNOTSUPP; + + return __devlink_param_driverinit_value_get(&devlink->param_list, + param_id, init_val); +} EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); /** @@ -4594,26 +6082,61 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_get); int devlink_param_driverinit_value_set(struct devlink *devlink, u32 param_id, union devlink_param_value init_val) { - struct devlink_param_item *param_item; + return __devlink_param_driverinit_value_set(devlink, 0, + &devlink->param_list, + param_id, init_val, + DEVLINK_CMD_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); - param_item = devlink_param_find_by_id(&devlink->param_list, param_id); - if (!param_item) - return -EINVAL; +/** + * devlink_port_param_driverinit_value_get - get configuration parameter + * value for driver initializing + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * @init_val: value of parameter in driverinit configuration mode + * + * This function should be used by the driver to get driverinit + * configuration for initialization after reload command. + */ +int devlink_port_param_driverinit_value_get(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value *init_val) +{ + struct devlink *devlink = devlink_port->devlink; - if (!devlink_param_cmode_is_supported(param_item->param, - DEVLINK_PARAM_CMODE_DRIVERINIT)) + if (!devlink->ops || !devlink->ops->reload) return -EOPNOTSUPP; - if (param_item->param->type == DEVLINK_PARAM_TYPE_STRING) - strcpy(param_item->driverinit_value.vstr, init_val.vstr); - else - param_item->driverinit_value = init_val; - param_item->driverinit_value_valid = true; + return __devlink_param_driverinit_value_get(&devlink_port->param_list, + param_id, init_val); +} +EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_get); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); - return 0; +/** + * devlink_port_param_driverinit_value_set - set value of configuration + * parameter for driverinit + * configuration mode + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * @init_val: value of parameter to set for driverinit configuration mode + * + * This function should be used by the driver to set driverinit + * configuration mode default value. + */ +int devlink_port_param_driverinit_value_set(struct devlink_port *devlink_port, + u32 param_id, + union devlink_param_value init_val) +{ + return __devlink_param_driverinit_value_set(devlink_port->devlink, + devlink_port->index, + &devlink_port->param_list, + param_id, init_val, + DEVLINK_CMD_PORT_PARAM_NEW); } -EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); +EXPORT_SYMBOL_GPL(devlink_port_param_driverinit_value_set); /** * devlink_param_value_changed - notify devlink on a parameter's value @@ -4626,7 +6149,6 @@ EXPORT_SYMBOL_GPL(devlink_param_driverinit_value_set); * This function should be used by the driver to notify devlink on value * change, excluding driverinit configuration mode. * For driverinit configuration mode driver should use the function - * devlink_param_driverinit_value_set() instead. */ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) { @@ -4635,11 +6157,38 @@ void devlink_param_value_changed(struct devlink *devlink, u32 param_id) param_item = devlink_param_find_by_id(&devlink->param_list, param_id); WARN_ON(!param_item); - devlink_param_notify(devlink, param_item, DEVLINK_CMD_PARAM_NEW); + devlink_param_notify(devlink, 0, param_item, DEVLINK_CMD_PARAM_NEW); } EXPORT_SYMBOL_GPL(devlink_param_value_changed); /** + * devlink_port_param_value_changed - notify devlink on a parameter's value + * change. Should be called by the driver + * right after the change. + * + * @devlink_port: devlink_port + * @param_id: parameter ID + * + * This function should be used by the driver to notify devlink on value + * change, excluding driverinit configuration mode. + * For driverinit configuration mode driver should use the function + * devlink_port_param_driverinit_value_set() instead. + */ +void devlink_port_param_value_changed(struct devlink_port *devlink_port, + u32 param_id) +{ + struct devlink_param_item *param_item; + + param_item = devlink_param_find_by_id(&devlink_port->param_list, + param_id); + WARN_ON(!param_item); + + devlink_param_notify(devlink_port->devlink, devlink_port->index, + param_item, DEVLINK_CMD_PORT_PARAM_NEW); +} +EXPORT_SYMBOL_GPL(devlink_port_param_value_changed); + +/** * devlink_param_value_str_fill - Safely fill-up the string preventing * from overflow of the preallocated buffer * @@ -4808,6 +6357,69 @@ unlock: } EXPORT_SYMBOL_GPL(devlink_region_snapshot_create); +static void __devlink_compat_running_version(struct devlink *devlink, + char *buf, size_t len) +{ + const struct nlattr *nlattr; + struct devlink_info_req req; + struct sk_buff *msg; + int rem, err; + + if (!devlink->ops->info_get) + return; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return; + + req.msg = msg; + err = devlink->ops->info_get(devlink, &req, NULL); + if (err) + goto free_msg; + + nla_for_each_attr(nlattr, (void *)msg->data, msg->len, rem) { + const struct nlattr *kv; + int rem_kv; + + if (nla_type(nlattr) != DEVLINK_ATTR_INFO_VERSION_RUNNING) + continue; + + nla_for_each_nested(kv, nlattr, rem_kv) { + if (nla_type(kv) != DEVLINK_ATTR_INFO_VERSION_VALUE) + continue; + + strlcat(buf, nla_data(kv), len); + strlcat(buf, " ", len); + } + } +free_msg: + nlmsg_free(msg); +} + +void devlink_compat_running_version(struct net_device *dev, + char *buf, size_t len) +{ + struct devlink_port *devlink_port; + struct devlink *devlink; + + mutex_lock(&devlink_mutex); + list_for_each_entry(devlink, &devlink_list, list) { + mutex_lock(&devlink->lock); + list_for_each_entry(devlink_port, &devlink->port_list, list) { + if (devlink_port->type == DEVLINK_PORT_TYPE_ETH && + devlink_port->type_dev == dev) { + __devlink_compat_running_version(devlink, + buf, len); + mutex_unlock(&devlink->lock); + goto out; + } + } + mutex_unlock(&devlink->lock); + } +out: + mutex_unlock(&devlink_mutex); +} + static int __init devlink_module_init(void) { return genl_register_family(&devlink_nl_family); diff --git a/net/core/dst.c b/net/core/dst.c index 81ccf20e2826..a263309df115 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -98,8 +98,12 @@ void *dst_alloc(struct dst_ops *ops, struct net_device *dev, struct dst_entry *dst; if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) { - if (ops->gc(ops)) + if (ops->gc(ops)) { + printk_ratelimited(KERN_NOTICE "Route cache is full: " + "consider increasing sysctl " + "net.ipv[4|6].route.max_size.\n"); return NULL; + } } dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index 158264f7cfaf..d2c47cdf25da 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -27,7 +27,9 @@ #include <linux/rtnetlink.h> #include <linux/sched/signal.h> #include <linux/net.h> +#include <net/devlink.h> #include <net/xdp_sock.h> +#include <net/flow_offload.h> /* * Some useful ethtool_ops methods that're device independent. @@ -803,6 +805,12 @@ static noinline_for_stack int ethtool_get_drvinfo(struct net_device *dev, if (ops->get_eeprom_len) info.eedump_len = ops->get_eeprom_len(dev); + rtnl_unlock(); + if (!info.fw_version[0]) + devlink_compat_running_version(dev, info.fw_version, + sizeof(info.fw_version)); + rtnl_lock(); + if (copy_to_user(useraddr, &info, sizeof(info))) return -EFAULT; return 0; @@ -1348,12 +1356,9 @@ static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) if (regs.len > reglen) regs.len = reglen; - regbuf = NULL; - if (reglen) { - regbuf = vzalloc(reglen); - if (!regbuf) - return -ENOMEM; - } + regbuf = vzalloc(reglen); + if (!regbuf) + return -ENOMEM; ops->get_regs(dev, ®s, regbuf); @@ -2816,3 +2821,241 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) return rc; } + +struct ethtool_rx_flow_key { + struct flow_dissector_key_basic basic; + union { + struct flow_dissector_key_ipv4_addrs ipv4; + struct flow_dissector_key_ipv6_addrs ipv6; + }; + struct flow_dissector_key_ports tp; + struct flow_dissector_key_ip ip; + struct flow_dissector_key_vlan vlan; + struct flow_dissector_key_eth_addrs eth_addrs; +} __aligned(BITS_PER_LONG / 8); /* Ensure that we can do comparisons as longs. */ + +struct ethtool_rx_flow_match { + struct flow_dissector dissector; + struct ethtool_rx_flow_key key; + struct ethtool_rx_flow_key mask; +}; + +struct ethtool_rx_flow_rule * +ethtool_rx_flow_rule_create(const struct ethtool_rx_flow_spec_input *input) +{ + const struct ethtool_rx_flow_spec *fs = input->fs; + static struct in6_addr zero_addr = {}; + struct ethtool_rx_flow_match *match; + struct ethtool_rx_flow_rule *flow; + struct flow_action_entry *act; + + flow = kzalloc(sizeof(struct ethtool_rx_flow_rule) + + sizeof(struct ethtool_rx_flow_match), GFP_KERNEL); + if (!flow) + return ERR_PTR(-ENOMEM); + + /* ethtool_rx supports only one single action per rule. */ + flow->rule = flow_rule_alloc(1); + if (!flow->rule) { + kfree(flow); + return ERR_PTR(-ENOMEM); + } + + match = (struct ethtool_rx_flow_match *)flow->priv; + flow->rule->match.dissector = &match->dissector; + flow->rule->match.mask = &match->mask; + flow->rule->match.key = &match->key; + + match->mask.basic.n_proto = htons(0xffff); + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + case UDP_V4_FLOW: { + const struct ethtool_tcpip4_spec *v4_spec, *v4_m_spec; + + match->key.basic.n_proto = htons(ETH_P_IP); + + v4_spec = &fs->h_u.tcp_ip4_spec; + v4_m_spec = &fs->m_u.tcp_ip4_spec; + + if (v4_m_spec->ip4src) { + match->key.ipv4.src = v4_spec->ip4src; + match->mask.ipv4.src = v4_m_spec->ip4src; + } + if (v4_m_spec->ip4dst) { + match->key.ipv4.dst = v4_spec->ip4dst; + match->mask.ipv4.dst = v4_m_spec->ip4dst; + } + if (v4_m_spec->ip4src || + v4_m_spec->ip4dst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IPV4_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_IPV4_ADDRS] = + offsetof(struct ethtool_rx_flow_key, ipv4); + } + if (v4_m_spec->psrc) { + match->key.tp.src = v4_spec->psrc; + match->mask.tp.src = v4_m_spec->psrc; + } + if (v4_m_spec->pdst) { + match->key.tp.dst = v4_spec->pdst; + match->mask.tp.dst = v4_m_spec->pdst; + } + if (v4_m_spec->psrc || + v4_m_spec->pdst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = + offsetof(struct ethtool_rx_flow_key, tp); + } + if (v4_m_spec->tos) { + match->key.ip.tos = v4_spec->tos; + match->mask.ip.tos = v4_m_spec->tos; + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IP); + match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = + offsetof(struct ethtool_rx_flow_key, ip); + } + } + break; + case TCP_V6_FLOW: + case UDP_V6_FLOW: { + const struct ethtool_tcpip6_spec *v6_spec, *v6_m_spec; + + match->key.basic.n_proto = htons(ETH_P_IPV6); + + v6_spec = &fs->h_u.tcp_ip6_spec; + v6_m_spec = &fs->m_u.tcp_ip6_spec; + if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + memcpy(&match->key.ipv6.src, v6_spec->ip6src, + sizeof(match->key.ipv6.src)); + memcpy(&match->mask.ipv6.src, v6_m_spec->ip6src, + sizeof(match->mask.ipv6.src)); + } + if (memcmp(v6_m_spec->ip6dst, &zero_addr, sizeof(zero_addr))) { + memcpy(&match->key.ipv6.dst, v6_spec->ip6dst, + sizeof(match->key.ipv6.dst)); + memcpy(&match->mask.ipv6.dst, v6_m_spec->ip6dst, + sizeof(match->mask.ipv6.dst)); + } + if (memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr)) || + memcmp(v6_m_spec->ip6src, &zero_addr, sizeof(zero_addr))) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IPV6_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_IPV6_ADDRS] = + offsetof(struct ethtool_rx_flow_key, ipv6); + } + if (v6_m_spec->psrc) { + match->key.tp.src = v6_spec->psrc; + match->mask.tp.src = v6_m_spec->psrc; + } + if (v6_m_spec->pdst) { + match->key.tp.dst = v6_spec->pdst; + match->mask.tp.dst = v6_m_spec->pdst; + } + if (v6_m_spec->psrc || + v6_m_spec->pdst) { + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_PORTS); + match->dissector.offset[FLOW_DISSECTOR_KEY_PORTS] = + offsetof(struct ethtool_rx_flow_key, tp); + } + if (v6_m_spec->tclass) { + match->key.ip.tos = v6_spec->tclass; + match->mask.ip.tos = v6_m_spec->tclass; + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_IP); + match->dissector.offset[FLOW_DISSECTOR_KEY_IP] = + offsetof(struct ethtool_rx_flow_key, ip); + } + } + break; + default: + ethtool_rx_flow_rule_destroy(flow); + return ERR_PTR(-EINVAL); + } + + switch (fs->flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS)) { + case TCP_V4_FLOW: + case TCP_V6_FLOW: + match->key.basic.ip_proto = IPPROTO_TCP; + break; + case UDP_V4_FLOW: + case UDP_V6_FLOW: + match->key.basic.ip_proto = IPPROTO_UDP; + break; + } + match->mask.basic.ip_proto = 0xff; + + match->dissector.used_keys |= BIT(FLOW_DISSECTOR_KEY_BASIC); + match->dissector.offset[FLOW_DISSECTOR_KEY_BASIC] = + offsetof(struct ethtool_rx_flow_key, basic); + + if (fs->flow_type & FLOW_EXT) { + const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; + const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; + + if (ext_m_spec->vlan_etype && + ext_m_spec->vlan_tci) { + match->key.vlan.vlan_tpid = ext_h_spec->vlan_etype; + match->mask.vlan.vlan_tpid = ext_m_spec->vlan_etype; + + match->key.vlan.vlan_id = + ntohs(ext_h_spec->vlan_tci) & 0x0fff; + match->mask.vlan.vlan_id = + ntohs(ext_m_spec->vlan_tci) & 0x0fff; + + match->key.vlan.vlan_priority = + (ntohs(ext_h_spec->vlan_tci) & 0xe000) >> 13; + match->mask.vlan.vlan_priority = + (ntohs(ext_m_spec->vlan_tci) & 0xe000) >> 13; + + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_VLAN); + match->dissector.offset[FLOW_DISSECTOR_KEY_VLAN] = + offsetof(struct ethtool_rx_flow_key, vlan); + } + } + if (fs->flow_type & FLOW_MAC_EXT) { + const struct ethtool_flow_ext *ext_h_spec = &fs->h_ext; + const struct ethtool_flow_ext *ext_m_spec = &fs->m_ext; + + memcpy(match->key.eth_addrs.dst, ext_h_spec->h_dest, + ETH_ALEN); + memcpy(match->mask.eth_addrs.dst, ext_m_spec->h_dest, + ETH_ALEN); + + match->dissector.used_keys |= + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS); + match->dissector.offset[FLOW_DISSECTOR_KEY_ETH_ADDRS] = + offsetof(struct ethtool_rx_flow_key, eth_addrs); + } + + act = &flow->rule->action.entries[0]; + switch (fs->ring_cookie) { + case RX_CLS_FLOW_DISC: + act->id = FLOW_ACTION_DROP; + break; + case RX_CLS_FLOW_WAKE: + act->id = FLOW_ACTION_WAKE; + break; + default: + act->id = FLOW_ACTION_QUEUE; + if (fs->flow_type & FLOW_RSS) + act->queue.ctx = input->rss_ctx; + + act->queue.vf = ethtool_get_flow_spec_ring_vf(fs->ring_cookie); + act->queue.index = ethtool_get_flow_spec_ring(fs->ring_cookie); + break; + } + + return flow; +} +EXPORT_SYMBOL(ethtool_rx_flow_rule_create); + +void ethtool_rx_flow_rule_destroy(struct ethtool_rx_flow_rule *flow) +{ + kfree(flow->rule); + kfree(flow); +} +EXPORT_SYMBOL(ethtool_rx_flow_rule_destroy); diff --git a/net/core/filter.c b/net/core/filter.c index 7a54dc11ac2d..b5a002d7b263 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -5316,10 +5316,20 @@ bpf_base_func_proto(enum bpf_func_id func_id) return &bpf_tail_call_proto; case BPF_FUNC_ktime_get_ns: return &bpf_ktime_get_ns_proto; + default: + break; + } + + if (!capable(CAP_SYS_ADMIN)) + return NULL; + + switch (func_id) { + case BPF_FUNC_spin_lock: + return &bpf_spin_lock_proto; + case BPF_FUNC_spin_unlock: + return &bpf_spin_unlock_proto; case BPF_FUNC_trace_printk: - if (capable(CAP_SYS_ADMIN)) - return bpf_get_trace_printk_proto(); - /* else, fall through */ + return bpf_get_trace_printk_proto(); default: return NULL; } @@ -6710,6 +6720,27 @@ static u32 bpf_convert_ctx_access(enum bpf_access_type type, target_size)); break; + case offsetof(struct __sk_buff, gso_segs): + /* si->dst_reg = skb_shinfo(SKB); */ +#ifdef NET_SKBUFF_DATA_USES_OFFSET + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, head), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, head)); + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), + BPF_REG_AX, si->src_reg, + offsetof(struct sk_buff, end)); + *insn++ = BPF_ALU64_REG(BPF_ADD, si->dst_reg, BPF_REG_AX); +#else + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, end), + si->dst_reg, si->src_reg, + offsetof(struct sk_buff, end)); +#endif + *insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct skb_shared_info, gso_segs), + si->dst_reg, si->dst_reg, + bpf_target_off(struct skb_shared_info, + gso_segs, 2, + target_size)); + break; case offsetof(struct __sk_buff, wire_len): BUILD_BUG_ON(FIELD_SIZEOF(struct qdisc_skb_cb, pkt_len) != 4); @@ -7700,6 +7731,7 @@ const struct bpf_verifier_ops flow_dissector_verifier_ops = { }; const struct bpf_prog_ops flow_dissector_prog_ops = { + .test_run = bpf_prog_test_run_flow_dissector, }; int sk_detach_filter(struct sock *sk) diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 9f2840510e63..bb1a54747d64 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -683,6 +683,46 @@ static void __skb_flow_bpf_to_target(const struct bpf_flow_keys *flow_keys, } } +bool __skb_flow_bpf_dissect(struct bpf_prog *prog, + const struct sk_buff *skb, + struct flow_dissector *flow_dissector, + struct bpf_flow_keys *flow_keys) +{ + struct bpf_skb_data_end cb_saved; + struct bpf_skb_data_end *cb; + u32 result; + + /* Note that even though the const qualifier is discarded + * throughout the execution of the BPF program, all changes(the + * control block) are reverted after the BPF program returns. + * Therefore, __skb_flow_dissect does not alter the skb. + */ + + cb = (struct bpf_skb_data_end *)skb->cb; + + /* Save Control Block */ + memcpy(&cb_saved, cb, sizeof(cb_saved)); + memset(cb, 0, sizeof(*cb)); + + /* Pass parameters to the BPF program */ + memset(flow_keys, 0, sizeof(*flow_keys)); + cb->qdisc_cb.flow_keys = flow_keys; + flow_keys->nhoff = skb_network_offset(skb); + flow_keys->thoff = flow_keys->nhoff; + + bpf_compute_data_pointers((struct sk_buff *)skb); + result = BPF_PROG_RUN(prog, skb); + + /* Restore state */ + memcpy(cb, &cb_saved, sizeof(cb_saved)); + + flow_keys->nhoff = clamp_t(u16, flow_keys->nhoff, 0, skb->len); + flow_keys->thoff = clamp_t(u16, flow_keys->thoff, + flow_keys->nhoff, skb->len); + + return result == BPF_OK; +} + /** * __skb_flow_dissect - extract the flow_keys struct and return it * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified @@ -714,7 +754,6 @@ bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_dissector_key_vlan *key_vlan; enum flow_dissect_ret fdret; enum flow_dissector_key_id dissector_vlan = FLOW_DISSECTOR_KEY_MAX; - struct bpf_prog *attached = NULL; int num_hdrs = 0; u8 ip_proto = 0; bool ret; @@ -754,53 +793,30 @@ bool __skb_flow_dissect(const struct sk_buff *skb, FLOW_DISSECTOR_KEY_BASIC, target_container); - rcu_read_lock(); if (skb) { + struct bpf_flow_keys flow_keys; + struct bpf_prog *attached = NULL; + + rcu_read_lock(); + if (skb->dev) attached = rcu_dereference(dev_net(skb->dev)->flow_dissector_prog); else if (skb->sk) attached = rcu_dereference(sock_net(skb->sk)->flow_dissector_prog); else WARN_ON_ONCE(1); - } - if (attached) { - /* Note that even though the const qualifier is discarded - * throughout the execution of the BPF program, all changes(the - * control block) are reverted after the BPF program returns. - * Therefore, __skb_flow_dissect does not alter the skb. - */ - struct bpf_flow_keys flow_keys = {}; - struct bpf_skb_data_end cb_saved; - struct bpf_skb_data_end *cb; - u32 result; - - cb = (struct bpf_skb_data_end *)skb->cb; - - /* Save Control Block */ - memcpy(&cb_saved, cb, sizeof(cb_saved)); - memset(cb, 0, sizeof(cb_saved)); - /* Pass parameters to the BPF program */ - cb->qdisc_cb.flow_keys = &flow_keys; - flow_keys.nhoff = nhoff; - flow_keys.thoff = nhoff; - - bpf_compute_data_pointers((struct sk_buff *)skb); - result = BPF_PROG_RUN(attached, skb); - - /* Restore state */ - memcpy(cb, &cb_saved, sizeof(cb_saved)); - - flow_keys.nhoff = clamp_t(u16, flow_keys.nhoff, 0, skb->len); - flow_keys.thoff = clamp_t(u16, flow_keys.thoff, - flow_keys.nhoff, skb->len); - - __skb_flow_bpf_to_target(&flow_keys, flow_dissector, - target_container); + if (attached) { + ret = __skb_flow_bpf_dissect(attached, skb, + flow_dissector, + &flow_keys); + __skb_flow_bpf_to_target(&flow_keys, flow_dissector, + target_container); + rcu_read_unlock(); + return ret; + } rcu_read_unlock(); - return result == BPF_OK; } - rcu_read_unlock(); if (dissector_uses_key(flow_dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { diff --git a/net/core/flow_offload.c b/net/core/flow_offload.c new file mode 100644 index 000000000000..c3a00eac4804 --- /dev/null +++ b/net/core/flow_offload.c @@ -0,0 +1,153 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#include <linux/kernel.h> +#include <linux/slab.h> +#include <net/flow_offload.h> + +struct flow_rule *flow_rule_alloc(unsigned int num_actions) +{ + struct flow_rule *rule; + + rule = kzalloc(sizeof(struct flow_rule) + + sizeof(struct flow_action_entry) * num_actions, + GFP_KERNEL); + if (!rule) + return NULL; + + rule->action.num_entries = num_actions; + + return rule; +} +EXPORT_SYMBOL(flow_rule_alloc); + +#define FLOW_DISSECTOR_MATCH(__rule, __type, __out) \ + const struct flow_match *__m = &(__rule)->match; \ + struct flow_dissector *__d = (__m)->dissector; \ + \ + (__out)->key = skb_flow_dissector_target(__d, __type, (__m)->key); \ + (__out)->mask = skb_flow_dissector_target(__d, __type, (__m)->mask); \ + +void flow_rule_match_basic(const struct flow_rule *rule, + struct flow_match_basic *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_BASIC, out); +} +EXPORT_SYMBOL(flow_rule_match_basic); + +void flow_rule_match_control(const struct flow_rule *rule, + struct flow_match_control *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_CONTROL, out); +} +EXPORT_SYMBOL(flow_rule_match_control); + +void flow_rule_match_eth_addrs(const struct flow_rule *rule, + struct flow_match_eth_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ETH_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_eth_addrs); + +void flow_rule_match_vlan(const struct flow_rule *rule, + struct flow_match_vlan *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_VLAN, out); +} +EXPORT_SYMBOL(flow_rule_match_vlan); + +void flow_rule_match_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV4_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_ipv4_addrs); + +void flow_rule_match_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IPV6_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_ipv6_addrs); + +void flow_rule_match_ip(const struct flow_rule *rule, + struct flow_match_ip *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_IP, out); +} +EXPORT_SYMBOL(flow_rule_match_ip); + +void flow_rule_match_ports(const struct flow_rule *rule, + struct flow_match_ports *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_PORTS, out); +} +EXPORT_SYMBOL(flow_rule_match_ports); + +void flow_rule_match_tcp(const struct flow_rule *rule, + struct flow_match_tcp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_TCP, out); +} +EXPORT_SYMBOL(flow_rule_match_tcp); + +void flow_rule_match_icmp(const struct flow_rule *rule, + struct flow_match_icmp *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ICMP, out); +} +EXPORT_SYMBOL(flow_rule_match_icmp); + +void flow_rule_match_mpls(const struct flow_rule *rule, + struct flow_match_mpls *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_MPLS, out); +} +EXPORT_SYMBOL(flow_rule_match_mpls); + +void flow_rule_match_enc_control(const struct flow_rule *rule, + struct flow_match_control *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_CONTROL, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_control); + +void flow_rule_match_enc_ipv4_addrs(const struct flow_rule *rule, + struct flow_match_ipv4_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV4_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ipv4_addrs); + +void flow_rule_match_enc_ipv6_addrs(const struct flow_rule *rule, + struct flow_match_ipv6_addrs *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IPV6_ADDRS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ipv6_addrs); + +void flow_rule_match_enc_ip(const struct flow_rule *rule, + struct flow_match_ip *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_IP, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ip); + +void flow_rule_match_enc_ports(const struct flow_rule *rule, + struct flow_match_ports *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_PORTS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_ports); + +void flow_rule_match_enc_keyid(const struct flow_rule *rule, + struct flow_match_enc_keyid *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_KEYID, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_keyid); + +void flow_rule_match_enc_opts(const struct flow_rule *rule, + struct flow_match_enc_opts *out) +{ + FLOW_DISSECTOR_MATCH(rule, FLOW_DISSECTOR_KEY_ENC_OPTS, out); +} +EXPORT_SYMBOL(flow_rule_match_enc_opts); diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index ff9fd2bb4ce4..7c5061123ead 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -12,7 +12,6 @@ #include <linux/capability.h> #include <linux/kernel.h> #include <linux/netdevice.h> -#include <net/switchdev.h> #include <linux/if_arp.h> #include <linux/slab.h> #include <linux/sched/signal.h> @@ -501,16 +500,11 @@ static ssize_t phys_switch_id_show(struct device *dev, return restart_syscall(); if (dev_isalive(netdev)) { - struct switchdev_attr attr = { - .orig_dev = netdev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, - }; + struct netdev_phys_item_id ppid = { }; - ret = switchdev_port_attr_get(netdev, &attr); + ret = dev_get_port_parent_id(netdev, &ppid, false); if (!ret) - ret = sprintf(buf, "%*phN\n", attr.u.ppid.id_len, - attr.u.ppid.id); + ret = sprintf(buf, "%*phN\n", ppid.id_len, ppid.id); } rtnl_unlock(); diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index b02fb19df2cc..17f36317363d 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -778,6 +778,41 @@ nla_put_failure: return -EMSGSIZE; } +static int rtnl_net_valid_getid_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + int i, err; + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, + rtnl_net_policy, extack); + + err = nlmsg_parse_strict(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, + rtnl_net_policy, extack); + if (err) + return err; + + for (i = 0; i <= NETNSA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case NETNSA_PID: + case NETNSA_FD: + case NETNSA_NSID: + case NETNSA_TARGET_NSID: + break; + default: + NL_SET_ERR_MSG(extack, "Unsupported attribute in peer netns getid request"); + return -EINVAL; + } + } + + return 0; +} + static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -793,8 +828,7 @@ static int rtnl_net_getid(struct sk_buff *skb, struct nlmsghdr *nlh, struct sk_buff *msg; int err; - err = nlmsg_parse(nlh, sizeof(struct rtgenmsg), tb, NETNSA_MAX, - rtnl_net_policy, extack); + err = rtnl_net_valid_getid_req(skb, nlh, tb, extack); if (err < 0) return err; if (tb[NETNSA_PID]) { diff --git a/net/core/page_pool.c b/net/core/page_pool.c index 43a932cb609b..5b2252c6d49b 100644 --- a/net/core/page_pool.c +++ b/net/core/page_pool.c @@ -136,17 +136,19 @@ static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, if (!(pool->p.flags & PP_FLAG_DMA_MAP)) goto skip_dma_map; - /* Setup DMA mapping: use page->private for DMA-addr + /* Setup DMA mapping: use 'struct page' area for storing DMA-addr + * since dma_addr_t can be either 32 or 64 bits and does not always fit + * into page private data (i.e 32bit cpu with 64bit DMA caps) * This mapping is kept for lifetime of page, until leaving pool. */ - dma = dma_map_page(pool->p.dev, page, 0, - (PAGE_SIZE << pool->p.order), - pool->p.dma_dir); + dma = dma_map_page_attrs(pool->p.dev, page, 0, + (PAGE_SIZE << pool->p.order), + pool->p.dma_dir, DMA_ATTR_SKIP_CPU_SYNC); if (dma_mapping_error(pool->p.dev, dma)) { put_page(page); return NULL; } - set_page_private(page, dma); /* page->private = dma; */ + page->dma_addr = dma; skip_dma_map: /* When page just alloc'ed is should/must have refcnt 1. */ @@ -175,13 +177,17 @@ EXPORT_SYMBOL(page_pool_alloc_pages); static void __page_pool_clean_page(struct page_pool *pool, struct page *page) { + dma_addr_t dma; + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) return; + dma = page->dma_addr; /* DMA unmap */ - dma_unmap_page(pool->p.dev, page_private(page), - PAGE_SIZE << pool->p.order, pool->p.dma_dir); - set_page_private(page, 0); + dma_unmap_page_attrs(pool->p.dev, dma, + PAGE_SIZE << pool->p.order, pool->p.dma_dir, + DMA_ATTR_SKIP_CPU_SYNC); + page->dma_addr = 0; } /* Return a page to the page allocator, cleaning up our state */ diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 5ea1bed08ede..a51cab95ba64 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -46,7 +46,6 @@ #include <linux/inet.h> #include <linux/netdevice.h> -#include <net/switchdev.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> @@ -1146,22 +1145,17 @@ static int rtnl_phys_port_name_fill(struct sk_buff *skb, struct net_device *dev) static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { + struct netdev_phys_item_id ppid = { }; int err; - struct switchdev_attr attr = { - .orig_dev = dev, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - .flags = SWITCHDEV_F_NO_RECURSE, - }; - err = switchdev_port_attr_get(dev, &attr); + err = dev_get_port_parent_id(dev, &ppid, false); if (err) { if (err == -EOPNOTSUPP) return 0; return err; } - if (nla_put(skb, IFLA_PHYS_SWITCH_ID, attr.u.ppid.id_len, - attr.u.ppid.id)) + if (nla_put(skb, IFLA_PHYS_SWITCH_ID, ppid.id_len, ppid.id)) return -EMSGSIZE; return 0; @@ -3242,6 +3236,53 @@ static int rtnl_newlink(struct sk_buff *skb, struct nlmsghdr *nlh, return ret; } +static int rtnl_valid_getlink_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct ifinfomsg *ifm; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { + NL_SET_ERR_MSG(extack, "Invalid header for get link"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, + extack); + + ifm = nlmsg_data(nlh); + if (ifm->__ifi_pad || ifm->ifi_type || ifm->ifi_flags || + ifm->ifi_change) { + NL_SET_ERR_MSG(extack, "Invalid values in header for get link request"); + return -EINVAL; + } + + err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, + extack); + if (err) + return err; + + for (i = 0; i <= IFLA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case IFLA_IFNAME: + case IFLA_EXT_MASK: + case IFLA_TARGET_NETNSID: + break; + default: + NL_SET_ERR_MSG(extack, "Unsupported attribute in get link request"); + return -EINVAL; + } + } + + return 0; +} + static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -3256,7 +3297,7 @@ static int rtnl_getlink(struct sk_buff *skb, struct nlmsghdr *nlh, int err; u32 ext_filter_mask = 0; - err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFLA_MAX, ifla_policy, extack); + err = rtnl_valid_getlink_req(skb, nlh, tb, extack); if (err < 0) return err; @@ -3639,7 +3680,7 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, const struct net_device_ops *ops = br_dev->netdev_ops; err = ops->ndo_fdb_add(ndm, tb, dev, addr, vid, - nlh->nlmsg_flags); + nlh->nlmsg_flags, extack); if (err) goto out; else @@ -3651,7 +3692,8 @@ static int rtnl_fdb_add(struct sk_buff *skb, struct nlmsghdr *nlh, if (dev->netdev_ops->ndo_fdb_add) err = dev->netdev_ops->ndo_fdb_add(ndm, tb, dev, addr, vid, - nlh->nlmsg_flags); + nlh->nlmsg_flags, + extack); else err = ndo_dflt_fdb_add(ndm, tb, dev, addr, vid, nlh->nlmsg_flags); @@ -4901,6 +4943,40 @@ static size_t if_nlmsg_stats_size(const struct net_device *dev, return size; } +static int rtnl_valid_stats_req(const struct nlmsghdr *nlh, bool strict_check, + bool is_dump, struct netlink_ext_ack *extack) +{ + struct if_stats_msg *ifsm; + + if (nlh->nlmsg_len < sizeof(*ifsm)) { + NL_SET_ERR_MSG(extack, "Invalid header for stats dump"); + return -EINVAL; + } + + if (!strict_check) + return 0; + + ifsm = nlmsg_data(nlh); + + /* only requests using strict checks can pass data to influence + * the dump. The legacy exception is filter_mask. + */ + if (ifsm->pad1 || ifsm->pad2 || (is_dump && ifsm->ifindex)) { + NL_SET_ERR_MSG(extack, "Invalid values in header for stats dump request"); + return -EINVAL; + } + if (nlmsg_attrlen(nlh, sizeof(*ifsm))) { + NL_SET_ERR_MSG(extack, "Invalid attributes after stats header"); + return -EINVAL; + } + if (ifsm->filter_mask >= IFLA_STATS_FILTER_BIT(IFLA_STATS_MAX + 1)) { + NL_SET_ERR_MSG(extack, "Invalid stats requested through filter mask"); + return -EINVAL; + } + + return 0; +} + static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -4912,8 +4988,10 @@ static int rtnl_stats_get(struct sk_buff *skb, struct nlmsghdr *nlh, u32 filter_mask; int err; - if (nlmsg_len(nlh) < sizeof(*ifsm)) - return -EINVAL; + err = rtnl_valid_stats_req(nlh, netlink_strict_get_check(skb), + false, extack); + if (err) + return err; ifsm = nlmsg_data(nlh); if (ifsm->ifindex > 0) @@ -4965,27 +5043,11 @@ static int rtnl_stats_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->seq = net->dev_base_seq; - if (nlmsg_len(cb->nlh) < sizeof(*ifsm)) { - NL_SET_ERR_MSG(extack, "Invalid header for stats dump"); - return -EINVAL; - } + err = rtnl_valid_stats_req(cb->nlh, cb->strict_check, true, extack); + if (err) + return err; ifsm = nlmsg_data(cb->nlh); - - /* only requests using strict checks can pass data to influence - * the dump. The legacy exception is filter_mask. - */ - if (cb->strict_check) { - if (ifsm->pad1 || ifsm->pad2 || ifsm->ifindex) { - NL_SET_ERR_MSG(extack, "Invalid values in header for stats dump request"); - return -EINVAL; - } - if (nlmsg_attrlen(cb->nlh, sizeof(*ifsm))) { - NL_SET_ERR_MSG(extack, "Invalid attributes after stats header"); - return -EINVAL; - } - } - filter_mask = ifsm->filter_mask; if (!filter_mask) { NL_SET_ERR_MSG(extack, "Filter mask must be set for stats dump"); diff --git a/net/core/scm.c b/net/core/scm.c index b1ff8a441748..52ef219cf6df 100644 --- a/net/core/scm.c +++ b/net/core/scm.c @@ -29,6 +29,7 @@ #include <linux/pid.h> #include <linux/nsproxy.h> #include <linux/slab.h> +#include <linux/errqueue.h> #include <linux/uaccess.h> @@ -252,6 +253,32 @@ out: } EXPORT_SYMBOL(put_cmsg); +void put_cmsg_scm_timestamping64(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) +{ + struct scm_timestamping64 tss; + int i; + + for (i = 0; i < ARRAY_SIZE(tss.ts); i++) { + tss.ts[i].tv_sec = tss_internal->ts[i].tv_sec; + tss.ts[i].tv_nsec = tss_internal->ts[i].tv_nsec; + } + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_NEW, sizeof(tss), &tss); +} +EXPORT_SYMBOL(put_cmsg_scm_timestamping64); + +void put_cmsg_scm_timestamping(struct msghdr *msg, struct scm_timestamping_internal *tss_internal) +{ + struct scm_timestamping tss; + int i; + + for (i = 0; i < ARRAY_SIZE(tss.ts); i++) + tss.ts[i] = timespec64_to_timespec(tss_internal->ts[i]); + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPING_OLD, sizeof(tss), &tss); +} +EXPORT_SYMBOL(put_cmsg_scm_timestamping); + void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm) { struct cmsghdr __user *cm diff --git a/net/core/skmsg.c b/net/core/skmsg.c index 8c826603bf36..ae6f06e45737 100644 --- a/net/core/skmsg.c +++ b/net/core/skmsg.c @@ -78,11 +78,9 @@ int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, { int i = src->sg.start; struct scatterlist *sge = sk_msg_elem(src, i); + struct scatterlist *sgd = NULL; u32 sge_len, sge_off; - if (sk_msg_full(dst)) - return -ENOSPC; - while (off) { if (sge->length > off) break; @@ -94,16 +92,27 @@ int sk_msg_clone(struct sock *sk, struct sk_msg *dst, struct sk_msg *src, } while (len) { - if (sk_msg_full(dst)) - return -ENOSPC; - sge_len = sge->length - off; - sge_off = sge->offset + off; if (sge_len > len) sge_len = len; + + if (dst->sg.end) + sgd = sk_msg_elem(dst, dst->sg.end - 1); + + if (sgd && + (sg_page(sge) == sg_page(sgd)) && + (sg_virt(sge) + off == sg_virt(sgd) + sgd->length)) { + sgd->length += sge_len; + dst->sg.size += sge_len; + } else if (!sk_msg_full(dst)) { + sge_off = sge->offset + off; + sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off); + } else { + return -ENOSPC; + } + off = 0; len -= sge_len; - sk_msg_page_add(dst, sg_page(sge), sge_len, sge_off); sk_mem_charge(sk, sge_len); sk_msg_iter_var_next(i); if (i == src->sg.end && len) diff --git a/net/core/sock.c b/net/core/sock.c index bc3512f230a3..d9f0a817dca8 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -335,14 +335,68 @@ int __sk_backlog_rcv(struct sock *sk, struct sk_buff *skb) } EXPORT_SYMBOL(__sk_backlog_rcv); -static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) +static int sock_get_timeout(long timeo, void *optval, bool old_timeval) { - struct timeval tv; + struct __kernel_sock_timeval tv; + int size; - if (optlen < sizeof(tv)) - return -EINVAL; - if (copy_from_user(&tv, optval, sizeof(tv))) - return -EFAULT; + if (timeo == MAX_SCHEDULE_TIMEOUT) { + tv.tv_sec = 0; + tv.tv_usec = 0; + } else { + tv.tv_sec = timeo / HZ; + tv.tv_usec = ((timeo % HZ) * USEC_PER_SEC) / HZ; + } + + if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { + struct old_timeval32 tv32 = { tv.tv_sec, tv.tv_usec }; + *(struct old_timeval32 *)optval = tv32; + return sizeof(tv32); + } + + if (old_timeval) { + struct __kernel_old_timeval old_tv; + old_tv.tv_sec = tv.tv_sec; + old_tv.tv_usec = tv.tv_usec; + *(struct __kernel_old_timeval *)optval = old_tv; + size = sizeof(old_tv); + } else { + *(struct __kernel_sock_timeval *)optval = tv; + size = sizeof(tv); + } + + return size; +} + +static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen, bool old_timeval) +{ + struct __kernel_sock_timeval tv; + + if (in_compat_syscall() && !COMPAT_USE_64BIT_TIME) { + struct old_timeval32 tv32; + + if (optlen < sizeof(tv32)) + return -EINVAL; + + if (copy_from_user(&tv32, optval, sizeof(tv32))) + return -EFAULT; + tv.tv_sec = tv32.tv_sec; + tv.tv_usec = tv32.tv_usec; + } else if (old_timeval) { + struct __kernel_old_timeval old_tv; + + if (optlen < sizeof(old_tv)) + return -EINVAL; + if (copy_from_user(&old_tv, optval, sizeof(old_tv))) + return -EFAULT; + tv.tv_sec = old_tv.tv_sec; + tv.tv_usec = old_tv.tv_usec; + } else { + if (optlen < sizeof(tv)) + return -EINVAL; + if (copy_from_user(&tv, optval, sizeof(tv))) + return -EFAULT; + } if (tv.tv_usec < 0 || tv.tv_usec >= USEC_PER_SEC) return -EDOM; @@ -360,8 +414,8 @@ static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) *timeo_p = MAX_SCHEDULE_TIMEOUT; if (tv.tv_sec == 0 && tv.tv_usec == 0) return 0; - if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT/HZ - 1)) - *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP(tv.tv_usec, USEC_PER_SEC / HZ); + if (tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) + *timeo_p = tv.tv_sec * HZ + DIV_ROUND_UP((unsigned long)tv.tv_usec, USEC_PER_SEC / HZ); return 0; } @@ -520,14 +574,11 @@ struct dst_entry *sk_dst_check(struct sock *sk, u32 cookie) } EXPORT_SYMBOL(sk_dst_check); -static int sock_setbindtodevice(struct sock *sk, char __user *optval, - int optlen) +static int sock_setbindtodevice_locked(struct sock *sk, int ifindex) { int ret = -ENOPROTOOPT; #ifdef CONFIG_NETDEVICES struct net *net = sock_net(sk); - char devname[IFNAMSIZ]; - int index; /* Sorry... */ ret = -EPERM; @@ -535,6 +586,32 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, goto out; ret = -EINVAL; + if (ifindex < 0) + goto out; + + sk->sk_bound_dev_if = ifindex; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + sk_dst_reset(sk); + + ret = 0; + +out: +#endif + + return ret; +} + +static int sock_setbindtodevice(struct sock *sk, char __user *optval, + int optlen) +{ + int ret = -ENOPROTOOPT; +#ifdef CONFIG_NETDEVICES + struct net *net = sock_net(sk); + char devname[IFNAMSIZ]; + int index; + + ret = -EINVAL; if (optlen < 0) goto out; @@ -566,14 +643,9 @@ static int sock_setbindtodevice(struct sock *sk, char __user *optval, } lock_sock(sk); - sk->sk_bound_dev_if = index; - if (sk->sk_prot->rehash) - sk->sk_prot->rehash(sk); - sk_dst_reset(sk); + ret = sock_setbindtodevice_locked(sk, index); release_sock(sk); - ret = 0; - out: #endif @@ -815,10 +887,17 @@ set_rcvbuf: clear_bit(SOCK_PASSCRED, &sock->flags); break; - case SO_TIMESTAMP: - case SO_TIMESTAMPNS: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: + case SO_TIMESTAMPNS_OLD: + case SO_TIMESTAMPNS_NEW: if (valbool) { - if (optname == SO_TIMESTAMP) + if (optname == SO_TIMESTAMP_NEW || optname == SO_TIMESTAMPNS_NEW) + sock_set_flag(sk, SOCK_TSTAMP_NEW); + else + sock_reset_flag(sk, SOCK_TSTAMP_NEW); + + if (optname == SO_TIMESTAMP_OLD || optname == SO_TIMESTAMP_NEW) sock_reset_flag(sk, SOCK_RCVTSTAMPNS); else sock_set_flag(sk, SOCK_RCVTSTAMPNS); @@ -827,10 +906,14 @@ set_rcvbuf: } else { sock_reset_flag(sk, SOCK_RCVTSTAMP); sock_reset_flag(sk, SOCK_RCVTSTAMPNS); + sock_reset_flag(sk, SOCK_TSTAMP_NEW); } break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_NEW: + sock_set_flag(sk, SOCK_TSTAMP_NEW); + /* fall through */ + case SO_TIMESTAMPING_OLD: if (val & ~SOF_TIMESTAMPING_MASK) { ret = -EINVAL; break; @@ -861,9 +944,13 @@ set_rcvbuf: if (val & SOF_TIMESTAMPING_RX_SOFTWARE) sock_enable_timestamp(sk, SOCK_TIMESTAMPING_RX_SOFTWARE); - else + else { + if (optname == SO_TIMESTAMPING_NEW) + sock_reset_flag(sk, SOCK_TSTAMP_NEW); + sock_disable_timestamp(sk, (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE)); + } break; case SO_RCVLOWAT: @@ -875,12 +962,14 @@ set_rcvbuf: sk->sk_rcvlowat = val ? : 1; break; - case SO_RCVTIMEO: - ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen); + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + ret = sock_set_timeout(&sk->sk_rcvtimeo, optval, optlen, optname == SO_RCVTIMEO_OLD); break; - case SO_SNDTIMEO: - ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen); + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: + ret = sock_set_timeout(&sk->sk_sndtimeo, optval, optlen, optname == SO_SNDTIMEO_OLD); break; case SO_ATTACH_FILTER: @@ -1055,6 +1144,10 @@ set_rcvbuf: } break; + case SO_BINDTOIFINDEX: + ret = sock_setbindtodevice_locked(sk, val); + break; + default: ret = -ENOPROTOOPT; break; @@ -1099,7 +1192,9 @@ int sock_getsockopt(struct socket *sock, int level, int optname, int val; u64 val64; struct linger ling; - struct timeval tm; + struct old_timeval32 tm32; + struct __kernel_old_timeval tm; + struct __kernel_sock_timeval stm; struct sock_txtime txtime; } v; @@ -1186,39 +1281,36 @@ int sock_getsockopt(struct socket *sock, int level, int optname, sock_warn_obsolete_bsdism("getsockopt"); break; - case SO_TIMESTAMP: + case SO_TIMESTAMP_OLD: v.val = sock_flag(sk, SOCK_RCVTSTAMP) && + !sock_flag(sk, SOCK_TSTAMP_NEW) && !sock_flag(sk, SOCK_RCVTSTAMPNS); break; - case SO_TIMESTAMPNS: - v.val = sock_flag(sk, SOCK_RCVTSTAMPNS); + case SO_TIMESTAMPNS_OLD: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && !sock_flag(sk, SOCK_TSTAMP_NEW); break; - case SO_TIMESTAMPING: + case SO_TIMESTAMP_NEW: + v.val = sock_flag(sk, SOCK_RCVTSTAMP) && sock_flag(sk, SOCK_TSTAMP_NEW); + break; + + case SO_TIMESTAMPNS_NEW: + v.val = sock_flag(sk, SOCK_RCVTSTAMPNS) && sock_flag(sk, SOCK_TSTAMP_NEW); + break; + + case SO_TIMESTAMPING_OLD: v.val = sk->sk_tsflags; break; - case SO_RCVTIMEO: - lv = sizeof(struct timeval); - if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_rcvtimeo / HZ; - v.tm.tv_usec = ((sk->sk_rcvtimeo % HZ) * USEC_PER_SEC) / HZ; - } + case SO_RCVTIMEO_OLD: + case SO_RCVTIMEO_NEW: + lv = sock_get_timeout(sk->sk_rcvtimeo, &v, SO_RCVTIMEO_OLD == optname); break; - case SO_SNDTIMEO: - lv = sizeof(struct timeval); - if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { - v.tm.tv_sec = 0; - v.tm.tv_usec = 0; - } else { - v.tm.tv_sec = sk->sk_sndtimeo / HZ; - v.tm.tv_usec = ((sk->sk_sndtimeo % HZ) * USEC_PER_SEC) / HZ; - } + case SO_SNDTIMEO_OLD: + case SO_SNDTIMEO_NEW: + lv = sock_get_timeout(sk->sk_sndtimeo, &v, SO_SNDTIMEO_OLD == optname); break; case SO_RCVLOWAT: @@ -1399,6 +1491,10 @@ int sock_getsockopt(struct socket *sock, int level, int optname, SOF_TXTIME_REPORT_ERRORS : 0; break; + case SO_BINDTOIFINDEX: + v.val = sk->sk_bound_dev_if; + break; + default: /* We implement the SO_SNDLOWAT etc to not be settable * (1003.1g 7). @@ -1726,7 +1822,6 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority) newsk->sk_err_soft = 0; newsk->sk_priority = 0; newsk->sk_incoming_cpu = raw_smp_processor_id(); - atomic64_set(&newsk->sk_cookie, 0); if (likely(newsk->sk_net_refcnt)) sock_inuse_add(sock_net(newsk), 1); @@ -2122,7 +2217,7 @@ int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg, return -EINVAL; sockc->mark = *(u32 *)CMSG_DATA(cmsg); break; - case SO_TIMESTAMPING: + case SO_TIMESTAMPING_OLD: if (cmsg->cmsg_len != CMSG_LEN(sizeof(u32))) return -EINVAL; diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index d67ec17f2cc8..84bf2861f45f 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -36,6 +36,15 @@ static int net_msg_warn; /* Unused, but still a sysctl */ int sysctl_fb_tunnels_only_for_init_net __read_mostly = 0; EXPORT_SYMBOL(sysctl_fb_tunnels_only_for_init_net); +/* 0 - Keep current behavior: + * IPv4: inherit all current settings from init_net + * IPv6: reset all settings to default + * 1 - Both inherit all current settings from init_net + * 2 - Both reset all settings to default + */ +int sysctl_devconf_inherit_init_net __read_mostly; +EXPORT_SYMBOL(sysctl_devconf_inherit_init_net); + #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, void __user *buffer, size_t *lenp, loff_t *ppos) @@ -544,6 +553,15 @@ static struct ctl_table net_core_table[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "devconf_inherit_init_net", + .data = &sysctl_devconf_inherit_init_net, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &two, + }, { } }; diff --git a/net/dccp/input.c b/net/dccp/input.c index 85d6c879383d..8d03707abdac 100644 --- a/net/dccp/input.c +++ b/net/dccp/input.c @@ -480,7 +480,7 @@ static int dccp_rcv_request_sent_state_process(struct sock *sk, sk_wake_async(sk, SOCK_WAKE_IO, POLL_OUT); } - if (sk->sk_write_pending || icsk->icsk_ack.pingpong || + if (sk->sk_write_pending || inet_csk_in_pingpong_mode(sk) || icsk->icsk_accept_queue.rskq_defer_accept) { /* Save one ACK. Data will be ready after * several ticks, if write_pending is set. diff --git a/net/dccp/timer.c b/net/dccp/timer.c index 1501a20a94ca..74e138495d67 100644 --- a/net/dccp/timer.c +++ b/net/dccp/timer.c @@ -199,7 +199,7 @@ static void dccp_delack_timer(struct timer_list *t) icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { - if (!icsk->icsk_ack.pingpong) { + if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); @@ -207,7 +207,7 @@ static void dccp_delack_timer(struct timer_list *t) /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } dccp_send_ack(sk); diff --git a/net/decnet/dn_fib.c b/net/decnet/dn_fib.c index f78fe58eafc8..6cd3737593a6 100644 --- a/net/decnet/dn_fib.c +++ b/net/decnet/dn_fib.c @@ -282,7 +282,7 @@ struct dn_fib_info *dn_fib_create_info(const struct rtmsg *r, struct nlattr *att (nhs = dn_fib_count_nhs(attrs[RTA_MULTIPATH])) == 0) goto err_inval; - fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct dn_fib_nh), GFP_KERNEL); + fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); err = -ENOBUFS; if (fi == NULL) goto failure; diff --git a/net/dsa/dsa2.c b/net/dsa/dsa2.c index a1917025e155..8c431e0f3627 100644 --- a/net/dsa/dsa2.c +++ b/net/dsa/dsa2.c @@ -767,11 +767,10 @@ static int dsa_switch_probe(struct dsa_switch *ds) struct dsa_switch *dsa_switch_alloc(struct device *dev, size_t n) { - size_t size = sizeof(struct dsa_switch) + n * sizeof(struct dsa_port); struct dsa_switch *ds; int i; - ds = devm_kzalloc(dev, size, GFP_KERNEL); + ds = devm_kzalloc(dev, struct_size(ds, ports, n), GFP_KERNEL); if (!ds) return NULL; diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 026a05774bf7..1f4972dab9f2 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -103,7 +103,8 @@ static inline void dsa_legacy_unregister(void) { } int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags); + u16 flags, + struct netlink_ext_ack *extack); int dsa_legacy_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid); diff --git a/net/dsa/master.c b/net/dsa/master.c index 54f5551fb799..c58f33931be1 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -126,6 +126,17 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, } } +static int dsa_master_get_phys_port_name(struct net_device *dev, + char *name, size_t len) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + + if (snprintf(name, len, "p%d", cpu_dp->index) >= len) + return -EINVAL; + + return 0; +} + static int dsa_master_ethtool_setup(struct net_device *dev) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -158,6 +169,38 @@ static void dsa_master_ethtool_teardown(struct net_device *dev) cpu_dp->orig_ethtool_ops = NULL; } +static int dsa_master_ndo_setup(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + struct dsa_switch *ds = cpu_dp->ds; + struct net_device_ops *ops; + + if (dev->netdev_ops->ndo_get_phys_port_name) + return 0; + + ops = devm_kzalloc(ds->dev, sizeof(*ops), GFP_KERNEL); + if (!ops) + return -ENOMEM; + + cpu_dp->orig_ndo_ops = dev->netdev_ops; + if (cpu_dp->orig_ndo_ops) + memcpy(ops, cpu_dp->orig_ndo_ops, sizeof(*ops)); + + ops->ndo_get_phys_port_name = dsa_master_get_phys_port_name; + + dev->netdev_ops = ops; + + return 0; +} + +static void dsa_master_ndo_teardown(struct net_device *dev) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + + dev->netdev_ops = cpu_dp->orig_ndo_ops; + cpu_dp->orig_ndo_ops = NULL; +} + static ssize_t tagging_show(struct device *d, struct device_attribute *attr, char *buf) { @@ -227,16 +270,27 @@ int dsa_master_setup(struct net_device *dev, struct dsa_port *cpu_dp) if (ret) return ret; + ret = dsa_master_ndo_setup(dev); + if (ret) + goto out_err_ethtool_teardown; + ret = sysfs_create_group(&dev->dev.kobj, &dsa_group); if (ret) - dsa_master_ethtool_teardown(dev); + goto out_err_ndo_teardown; + + return ret; +out_err_ndo_teardown: + dsa_master_ndo_teardown(dev); +out_err_ethtool_teardown: + dsa_master_ethtool_teardown(dev); return ret; } void dsa_master_teardown(struct net_device *dev) { sysfs_remove_group(&dev->dev.kobj, &dsa_group); + dsa_master_ndo_teardown(dev); dsa_master_ethtool_teardown(dev); dsa_master_reset_mtu(dev); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a1c9fe155057..2e5e7c04821b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -365,18 +365,23 @@ static int dsa_slave_port_obj_del(struct net_device *dev, return err; } -static int dsa_slave_port_attr_get(struct net_device *dev, - struct switchdev_attr *attr) +static int dsa_slave_get_port_parent_id(struct net_device *dev, + struct netdev_phys_item_id *ppid) { struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_switch *ds = dp->ds; struct dsa_switch_tree *dst = ds->dst; + ppid->id_len = sizeof(dst->index); + memcpy(&ppid->id, &dst->index, ppid->id_len); + + return 0; +} + +static int dsa_slave_port_attr_get(struct net_device *dev, + struct switchdev_attr *attr) +{ switch (attr->id) { - case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: - attr->u.ppid.id_len = sizeof(dst->index); - memcpy(&attr->u.ppid.id, &dst->index, attr->u.ppid.id_len); - break; case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS_SUPPORT: attr->u.brport_flags_support = 0; break; @@ -1012,7 +1017,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { int dsa_legacy_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], struct net_device *dev, const unsigned char *addr, u16 vid, - u16 flags) + u16 flags, + struct netlink_ext_ack *extack) { struct dsa_port *dp = dsa_slave_to_port(dev); @@ -1048,6 +1054,7 @@ static const struct net_device_ops dsa_slave_netdev_ops = { .ndo_get_phys_port_name = dsa_slave_get_phys_port_name, .ndo_setup_tc = dsa_slave_setup_tc, .ndo_get_stats64 = dsa_slave_get_stats64, + .ndo_get_port_parent_id = dsa_slave_get_port_parent_id, }; static const struct switchdev_ops dsa_slave_switchdev_ops = { @@ -1453,7 +1460,7 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) } fdb_info->offloaded = true; call_switchdev_notifiers(SWITCHDEV_FDB_OFFLOADED, dev, - &fdb_info->info); + &fdb_info->info, NULL); break; case SWITCHDEV_FDB_DEL_TO_DEVICE: diff --git a/net/dsa/tag_ksz.c b/net/dsa/tag_ksz.c index da71b9e2af52..927e9c86f745 100644 --- a/net/dsa/tag_ksz.c +++ b/net/dsa/tag_ksz.c @@ -67,6 +67,8 @@ static struct sk_buff *ksz_common_rcv(struct sk_buff *skb, pskb_trim_rcsum(skb, skb->len - len); + skb->offload_fwd_mark = true; + return skb; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index e258a00b4a3d..cd9033245b98 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -2063,13 +2063,49 @@ static const struct nla_policy devconf_ipv4_policy[NETCONFA_MAX+1] = { [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; +static int inet_netconf_valid_get_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid header for netconf get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb, + NETCONFA_MAX, devconf_ipv4_policy, extack); + + err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb, + NETCONFA_MAX, devconf_ipv4_policy, extack); + if (err) + return err; + + for (i = 0; i <= NETCONFA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case NETCONFA_IFINDEX: + break; + default: + NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in netconf get request"); + return -EINVAL; + } + } + + return 0; +} + static int inet_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX+1]; - struct netconfmsg *ncm; struct sk_buff *skb; struct ipv4_devconf *devconf; struct in_device *in_dev; @@ -2077,9 +2113,8 @@ static int inet_netconf_get_devconf(struct sk_buff *in_skb, int ifindex; int err; - err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, - devconf_ipv4_policy, extack); - if (err < 0) + err = inet_netconf_valid_get_req(in_skb, nlh, tb, extack); + if (err) goto errout; err = -EINVAL; @@ -2556,32 +2591,32 @@ static __net_init int devinet_init_net(struct net *net) int err; struct ipv4_devconf *all, *dflt; #ifdef CONFIG_SYSCTL - struct ctl_table *tbl = ctl_forward_entry; + struct ctl_table *tbl; struct ctl_table_header *forw_hdr; #endif err = -ENOMEM; - all = &ipv4_devconf; - dflt = &ipv4_devconf_dflt; + all = kmemdup(&ipv4_devconf, sizeof(ipv4_devconf), GFP_KERNEL); + if (!all) + goto err_alloc_all; - if (!net_eq(net, &init_net)) { - all = kmemdup(all, sizeof(ipv4_devconf), GFP_KERNEL); - if (!all) - goto err_alloc_all; - - dflt = kmemdup(dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); - if (!dflt) - goto err_alloc_dflt; + dflt = kmemdup(&ipv4_devconf_dflt, sizeof(ipv4_devconf_dflt), GFP_KERNEL); + if (!dflt) + goto err_alloc_dflt; #ifdef CONFIG_SYSCTL - tbl = kmemdup(tbl, sizeof(ctl_forward_entry), GFP_KERNEL); - if (!tbl) - goto err_alloc_ctl; + tbl = kmemdup(ctl_forward_entry, sizeof(ctl_forward_entry), GFP_KERNEL); + if (!tbl) + goto err_alloc_ctl; - tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; - tbl[0].extra1 = all; - tbl[0].extra2 = net; + tbl[0].data = &all->data[IPV4_DEVCONF_FORWARDING - 1]; + tbl[0].extra1 = all; + tbl[0].extra2 = net; #endif + + if (sysctl_devconf_inherit_init_net != 2 && !net_eq(net, &init_net)) { + memcpy(all, init_net.ipv4.devconf_all, sizeof(ipv4_devconf)); + memcpy(dflt, init_net.ipv4.devconf_dflt, sizeof(ipv4_devconf_dflt)); } #ifdef CONFIG_SYSCTL @@ -2611,15 +2646,12 @@ err_reg_ctl: err_reg_dflt: __devinet_sysctl_unregister(net, all, NETCONFA_IFINDEX_ALL); err_reg_all: - if (tbl != ctl_forward_entry) - kfree(tbl); + kfree(tbl); err_alloc_ctl: #endif - if (dflt != &ipv4_devconf_dflt) - kfree(dflt); + kfree(dflt); err_alloc_dflt: - if (all != &ipv4_devconf) - kfree(all); + kfree(all); err_alloc_all: return err; } diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 5022bc63863a..8e185b5a2bf6 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1072,7 +1072,7 @@ struct fib_info *fib_create_info(struct fib_config *cfg, goto failure; } - fi = kzalloc(sizeof(*fi)+nhs*sizeof(struct fib_nh), GFP_KERNEL); + fi = kzalloc(struct_size(fi, fib_nh, nhs), GFP_KERNEL); if (!fi) goto failure; fi->fib_metrics = ip_fib_metrics_init(fi->fib_net, cfg->fc_mx, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 765b2b32c4a4..b448cf32296c 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -159,7 +159,8 @@ static int unsolicited_report_interval(struct in_device *in_dev) return interval_jiffies; } -static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im); +static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, + gfp_t gfp); static void igmpv3_del_delrec(struct in_device *in_dev, struct ip_mc_list *im); static void igmpv3_clear_delrec(struct in_device *in_dev); static int sf_setstate(struct ip_mc_list *pmc); @@ -1145,7 +1146,8 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) /* * deleted ip_mc_list manipulation */ -static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) +static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im, + gfp_t gfp) { struct ip_mc_list *pmc; struct net *net = dev_net(in_dev->dev); @@ -1156,7 +1158,7 @@ static void igmpv3_add_delrec(struct in_device *in_dev, struct ip_mc_list *im) * for deleted items allows change reports to use common code with * non-deleted or query-response MCA's. */ - pmc = kzalloc(sizeof(*pmc), GFP_KERNEL); + pmc = kzalloc(sizeof(*pmc), gfp); if (!pmc) return; spin_lock_init(&pmc->lock); @@ -1261,7 +1263,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) } #endif -static void igmp_group_dropped(struct ip_mc_list *im) +static void __igmp_group_dropped(struct ip_mc_list *im, gfp_t gfp) { struct in_device *in_dev = im->interface; #ifdef CONFIG_IP_MULTICAST @@ -1292,13 +1294,18 @@ static void igmp_group_dropped(struct ip_mc_list *im) return; } /* IGMPv3 */ - igmpv3_add_delrec(in_dev, im); + igmpv3_add_delrec(in_dev, im, gfp); igmp_ifc_event(in_dev); } #endif } +static void igmp_group_dropped(struct ip_mc_list *im) +{ + __igmp_group_dropped(im, GFP_KERNEL); +} + static void igmp_group_added(struct ip_mc_list *im) { struct in_device *in_dev = im->interface; @@ -1400,8 +1407,8 @@ static void ip_mc_hash_remove(struct in_device *in_dev, /* * A socket has joined a multicast group on device dev. */ -static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, - unsigned int mode) +static void ____ip_mc_inc_group(struct in_device *in_dev, __be32 addr, + unsigned int mode, gfp_t gfp) { struct ip_mc_list *im; @@ -1415,7 +1422,7 @@ static void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, } } - im = kzalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), gfp); if (!im) goto out; @@ -1448,6 +1455,12 @@ out: return; } +void __ip_mc_inc_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) +{ + ____ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE, gfp); +} +EXPORT_SYMBOL(__ip_mc_inc_group); + void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) { __ip_mc_inc_group(in_dev, addr, MCAST_EXCLUDE); @@ -1493,22 +1506,22 @@ static int ip_mc_check_igmp_reportv3(struct sk_buff *skb) len += sizeof(struct igmpv3_report); - return pskb_may_pull(skb, len) ? 0 : -EINVAL; + return ip_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ip_mc_check_igmp_query(struct sk_buff *skb) { - unsigned int len = skb_transport_offset(skb); - - len += sizeof(struct igmphdr); - if (skb->len < len) - return -EINVAL; + unsigned int transport_len = ip_transport_len(skb); + unsigned int len; /* IGMPv{1,2}? */ - if (skb->len != len) { + if (transport_len != sizeof(struct igmphdr)) { /* or IGMPv3? */ - len += sizeof(struct igmpv3_query) - sizeof(struct igmphdr); - if (skb->len < len || !pskb_may_pull(skb, len)) + if (transport_len < sizeof(struct igmpv3_query)) + return -EINVAL; + + len = skb_transport_offset(skb) + sizeof(struct igmpv3_query); + if (!ip_mc_may_pull(skb, len)) return -EINVAL; } @@ -1544,47 +1557,29 @@ static inline __sum16 ip_mc_validate_checksum(struct sk_buff *skb) return skb_checksum_simple_validate(skb); } -static int __ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) - +static int ip_mc_check_igmp_csum(struct sk_buff *skb) { - struct sk_buff *skb_chk; - unsigned int transport_len; unsigned int len = skb_transport_offset(skb) + sizeof(struct igmphdr); - int ret = -EINVAL; + unsigned int transport_len = ip_transport_len(skb); + struct sk_buff *skb_chk; - transport_len = ntohs(ip_hdr(skb)->tot_len) - ip_hdrlen(skb); + if (!ip_mc_may_pull(skb, len)) + return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ip_mc_validate_checksum); if (!skb_chk) - goto err; - - if (!pskb_may_pull(skb_chk, len)) - goto err; - - ret = ip_mc_check_igmp_msg(skb_chk); - if (ret) - goto err; - - if (skb_trimmed) - *skb_trimmed = skb_chk; - /* free now unneeded clone */ - else if (skb_chk != skb) - kfree_skb(skb_chk); - - ret = 0; + return -EINVAL; -err: - if (ret && skb_chk && skb_chk != skb) + if (skb_chk != skb) kfree_skb(skb_chk); - return ret; + return 0; } /** * ip_mc_check_igmp - checks whether this is a sane IGMP packet * @skb: the skb to validate - * @skb_trimmed: to store an skb pointer trimmed to IPv4 packet tail (optional) * * Checks whether an IPv4 packet is a valid IGMP packet. If so sets * skb transport header accordingly and returns zero. @@ -1594,18 +1589,10 @@ err: * -ENOMSG: IP header validation succeeded but it is not an IGMP packet. * -ENOMEM: A memory allocation failure happened. * - * Optionally, an skb pointer might be provided via skb_trimmed (or set it - * to NULL): After parsing an IGMP packet successfully it will point to - * an skb which has its tail aligned to the IP packet end. This might - * either be the originally provided skb or a trimmed, cloned version if - * the skb frame had data beyond the IP packet. A cloned skb allows us - * to leave the original skb and its full frame unchanged (which might be - * desirable for layer 2 frame jugglers). - * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ -int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) +int ip_mc_check_igmp(struct sk_buff *skb) { int ret = ip_mc_check_iphdr(skb); @@ -1615,7 +1602,11 @@ int ip_mc_check_igmp(struct sk_buff *skb, struct sk_buff **skb_trimmed) if (ip_hdr(skb)->protocol != IPPROTO_IGMP) return -ENOMSG; - return __ip_mc_check_igmp(skb, skb_trimmed); + ret = ip_mc_check_igmp_csum(skb); + if (ret < 0) + return ret; + + return ip_mc_check_igmp_msg(skb); } EXPORT_SYMBOL(ip_mc_check_igmp); @@ -1656,7 +1647,7 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) * A socket has left a multicast group on device dev */ -void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) +void __ip_mc_dec_group(struct in_device *in_dev, __be32 addr, gfp_t gfp) { struct ip_mc_list *i; struct ip_mc_list __rcu **ip; @@ -1671,7 +1662,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ip_mc_hash_remove(in_dev, i); *ip = i->next_rcu; in_dev->mc_count--; - igmp_group_dropped(i); + __igmp_group_dropped(i, gfp); ip_mc_clear_src(i); if (!in_dev->dead) @@ -1684,7 +1675,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) } } } -EXPORT_SYMBOL(ip_mc_dec_group); +EXPORT_SYMBOL(__ip_mc_dec_group); /* Device changing type */ diff --git a/net/ipv4/inet_fragment.c b/net/ipv4/inet_fragment.c index 760a9e52e02b..9f69411251d0 100644 --- a/net/ipv4/inet_fragment.c +++ b/net/ipv4/inet_fragment.c @@ -25,6 +25,62 @@ #include <net/sock.h> #include <net/inet_frag.h> #include <net/inet_ecn.h> +#include <net/ip.h> +#include <net/ipv6.h> + +/* Use skb->cb to track consecutive/adjacent fragments coming at + * the end of the queue. Nodes in the rb-tree queue will + * contain "runs" of one or more adjacent fragments. + * + * Invariants: + * - next_frag is NULL at the tail of a "run"; + * - the head of a "run" has the sum of all fragment lengths in frag_run_len. + */ +struct ipfrag_skb_cb { + union { + struct inet_skb_parm h4; + struct inet6_skb_parm h6; + }; + struct sk_buff *next_frag; + int frag_run_len; +}; + +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) + +static void fragcb_clear(struct sk_buff *skb) +{ + RB_CLEAR_NODE(&skb->rbnode); + FRAG_CB(skb)->next_frag = NULL; + FRAG_CB(skb)->frag_run_len = skb->len; +} + +/* Append skb to the last "run". */ +static void fragrun_append_to_last(struct inet_frag_queue *q, + struct sk_buff *skb) +{ + fragcb_clear(skb); + + FRAG_CB(q->last_run_head)->frag_run_len += skb->len; + FRAG_CB(q->fragments_tail)->next_frag = skb; + q->fragments_tail = skb; +} + +/* Create a new "run" with the skb. */ +static void fragrun_create(struct inet_frag_queue *q, struct sk_buff *skb) +{ + BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); + fragcb_clear(skb); + + if (q->last_run_head) + rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, + &q->last_run_head->rbnode.rb_right); + else + rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + + q->fragments_tail = skb; + q->last_run_head = skb; +} /* Given the OR values of all fragments, apply RFC 3168 5.3 requirements * Value : 0xff if frame should be dropped. @@ -123,6 +179,28 @@ static void inet_frag_destroy_rcu(struct rcu_head *head) kmem_cache_free(f->frags_cachep, q); } +unsigned int inet_frag_rbtree_purge(struct rb_root *root) +{ + struct rb_node *p = rb_first(root); + unsigned int sum = 0; + + while (p) { + struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); + + p = rb_next(p); + rb_erase(&skb->rbnode, root); + while (skb) { + struct sk_buff *next = FRAG_CB(skb)->next_frag; + + sum += skb->truesize; + kfree_skb(skb); + skb = next; + } + } + return sum; +} +EXPORT_SYMBOL(inet_frag_rbtree_purge); + void inet_frag_destroy(struct inet_frag_queue *q) { struct sk_buff *fp; @@ -224,3 +302,218 @@ struct inet_frag_queue *inet_frag_find(struct netns_frags *nf, void *key) return fq; } EXPORT_SYMBOL(inet_frag_find); + +int inet_frag_queue_insert(struct inet_frag_queue *q, struct sk_buff *skb, + int offset, int end) +{ + struct sk_buff *last = q->fragments_tail; + + /* RFC5722, Section 4, amended by Errata ID : 3089 + * When reassembling an IPv6 datagram, if + * one or more its constituent fragments is determined to be an + * overlapping fragment, the entire datagram (and any constituent + * fragments) MUST be silently discarded. + * + * Duplicates, however, should be ignored (i.e. skb dropped, but the + * queue/fragments kept for later reassembly). + */ + if (!last) + fragrun_create(q, skb); /* First fragment. */ + else if (last->ip_defrag_offset + last->len < end) { + /* This is the common case: skb goes to the end. */ + /* Detect and discard overlaps. */ + if (offset < last->ip_defrag_offset + last->len) + return IPFRAG_OVERLAP; + if (offset == last->ip_defrag_offset + last->len) + fragrun_append_to_last(q, skb); + else + fragrun_create(q, skb); + } else { + /* Binary search. Note that skb can become the first fragment, + * but not the last (covered above). + */ + struct rb_node **rbn, *parent; + + rbn = &q->rb_fragments.rb_node; + do { + struct sk_buff *curr; + int curr_run_end; + + parent = *rbn; + curr = rb_to_skb(parent); + curr_run_end = curr->ip_defrag_offset + + FRAG_CB(curr)->frag_run_len; + if (end <= curr->ip_defrag_offset) + rbn = &parent->rb_left; + else if (offset >= curr_run_end) + rbn = &parent->rb_right; + else if (offset >= curr->ip_defrag_offset && + end <= curr_run_end) + return IPFRAG_DUP; + else + return IPFRAG_OVERLAP; + } while (*rbn); + /* Here we have parent properly set, and rbn pointing to + * one of its NULL left/right children. Insert skb. + */ + fragcb_clear(skb); + rb_link_node(&skb->rbnode, parent, rbn); + rb_insert_color(&skb->rbnode, &q->rb_fragments); + } + + skb->ip_defrag_offset = offset; + + return IPFRAG_OK; +} +EXPORT_SYMBOL(inet_frag_queue_insert); + +void *inet_frag_reasm_prepare(struct inet_frag_queue *q, struct sk_buff *skb, + struct sk_buff *parent) +{ + struct sk_buff *fp, *head = skb_rb_first(&q->rb_fragments); + struct sk_buff **nextp; + int delta; + + if (head != skb) { + fp = skb_clone(skb, GFP_ATOMIC); + if (!fp) + return NULL; + FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; + if (RB_EMPTY_NODE(&skb->rbnode)) + FRAG_CB(parent)->next_frag = fp; + else + rb_replace_node(&skb->rbnode, &fp->rbnode, + &q->rb_fragments); + if (q->fragments_tail == skb) + q->fragments_tail = fp; + skb_morph(skb, head); + FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + consume_skb(head); + head = skb; + } + WARN_ON(head->ip_defrag_offset != 0); + + delta = -head->truesize; + + /* Head of list must not be cloned. */ + if (skb_unclone(head, GFP_ATOMIC)) + return NULL; + + delta += head->truesize; + if (delta) + add_frag_mem_limit(q->net, delta); + + /* If the first fragment is fragmented itself, we split + * it to two chunks: the first with data and paged part + * and the second, holding only fragments. + */ + if (skb_has_frag_list(head)) { + struct sk_buff *clone; + int i, plen = 0; + + clone = alloc_skb(0, GFP_ATOMIC); + if (!clone) + return NULL; + skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; + skb_frag_list_init(head); + for (i = 0; i < skb_shinfo(head)->nr_frags; i++) + plen += skb_frag_size(&skb_shinfo(head)->frags[i]); + clone->data_len = head->data_len - plen; + clone->len = clone->data_len; + head->truesize += clone->truesize; + clone->csum = 0; + clone->ip_summed = head->ip_summed; + add_frag_mem_limit(q->net, clone->truesize); + skb_shinfo(head)->frag_list = clone; + nextp = &clone->next; + } else { + nextp = &skb_shinfo(head)->frag_list; + } + + return nextp; +} +EXPORT_SYMBOL(inet_frag_reasm_prepare); + +void inet_frag_reasm_finish(struct inet_frag_queue *q, struct sk_buff *head, + void *reasm_data) +{ + struct sk_buff **nextp = (struct sk_buff **)reasm_data; + struct rb_node *rbn; + struct sk_buff *fp; + + skb_push(head, head->data - skb_network_header(head)); + + /* Traverse the tree in order, to build frag_list. */ + fp = FRAG_CB(head)->next_frag; + rbn = rb_next(&head->rbnode); + rb_erase(&head->rbnode, &q->rb_fragments); + while (rbn || fp) { + /* fp points to the next sk_buff in the current run; + * rbn points to the next run. + */ + /* Go through the current run. */ + while (fp) { + *nextp = fp; + nextp = &fp->next; + fp->prev = NULL; + memset(&fp->rbnode, 0, sizeof(fp->rbnode)); + fp->sk = NULL; + head->data_len += fp->len; + head->len += fp->len; + if (head->ip_summed != fp->ip_summed) + head->ip_summed = CHECKSUM_NONE; + else if (head->ip_summed == CHECKSUM_COMPLETE) + head->csum = csum_add(head->csum, fp->csum); + head->truesize += fp->truesize; + fp = FRAG_CB(fp)->next_frag; + } + /* Move to the next run. */ + if (rbn) { + struct rb_node *rbnext = rb_next(rbn); + + fp = rb_to_skb(rbn); + rb_erase(rbn, &q->rb_fragments); + rbn = rbnext; + } + } + sub_frag_mem_limit(q->net, head->truesize); + + *nextp = NULL; + skb_mark_not_on_list(head); + head->prev = NULL; + head->tstamp = q->stamp; +} +EXPORT_SYMBOL(inet_frag_reasm_finish); + +struct sk_buff *inet_frag_pull_head(struct inet_frag_queue *q) +{ + struct sk_buff *head; + + if (q->fragments) { + head = q->fragments; + q->fragments = head->next; + } else { + struct sk_buff *skb; + + head = skb_rb_first(&q->rb_fragments); + if (!head) + return NULL; + skb = FRAG_CB(head)->next_frag; + if (skb) + rb_replace_node(&head->rbnode, &skb->rbnode, + &q->rb_fragments); + else + rb_erase(&head->rbnode, &q->rb_fragments); + memset(&head->rbnode, 0, sizeof(head->rbnode)); + barrier(); + } + if (head == q->fragments_tail) + q->fragments_tail = NULL; + + sub_frag_mem_limit(q->net, head->truesize); + + return head; +} +EXPORT_SYMBOL(inet_frag_pull_head); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 867be8f7f1fa..486ecb0aeb87 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -57,57 +57,6 @@ */ static const char ip_frag_cache_name[] = "ip4-frags"; -/* Use skb->cb to track consecutive/adjacent fragments coming at - * the end of the queue. Nodes in the rb-tree queue will - * contain "runs" of one or more adjacent fragments. - * - * Invariants: - * - next_frag is NULL at the tail of a "run"; - * - the head of a "run" has the sum of all fragment lengths in frag_run_len. - */ -struct ipfrag_skb_cb { - struct inet_skb_parm h; - struct sk_buff *next_frag; - int frag_run_len; -}; - -#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) - -static void ip4_frag_init_run(struct sk_buff *skb) -{ - BUILD_BUG_ON(sizeof(struct ipfrag_skb_cb) > sizeof(skb->cb)); - - FRAG_CB(skb)->next_frag = NULL; - FRAG_CB(skb)->frag_run_len = skb->len; -} - -/* Append skb to the last "run". */ -static void ip4_frag_append_to_last_run(struct inet_frag_queue *q, - struct sk_buff *skb) -{ - RB_CLEAR_NODE(&skb->rbnode); - FRAG_CB(skb)->next_frag = NULL; - - FRAG_CB(q->last_run_head)->frag_run_len += skb->len; - FRAG_CB(q->fragments_tail)->next_frag = skb; - q->fragments_tail = skb; -} - -/* Create a new "run" with the skb. */ -static void ip4_frag_create_run(struct inet_frag_queue *q, struct sk_buff *skb) -{ - if (q->last_run_head) - rb_link_node(&skb->rbnode, &q->last_run_head->rbnode, - &q->last_run_head->rbnode.rb_right); - else - rb_link_node(&skb->rbnode, NULL, &q->rb_fragments.rb_node); - rb_insert_color(&skb->rbnode, &q->rb_fragments); - - ip4_frag_init_run(skb); - q->fragments_tail = skb; - q->last_run_head = skb; -} - /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { struct inet_frag_queue q; @@ -212,27 +161,9 @@ static void ip_expire(struct timer_list *t) * pull the head out of the tree in order to be able to * deal with head->dev. */ - if (qp->q.fragments) { - head = qp->q.fragments; - qp->q.fragments = head->next; - } else { - head = skb_rb_first(&qp->q.rb_fragments); - if (!head) - goto out; - if (FRAG_CB(head)->next_frag) - rb_replace_node(&head->rbnode, - &FRAG_CB(head)->next_frag->rbnode, - &qp->q.rb_fragments); - else - rb_erase(&head->rbnode, &qp->q.rb_fragments); - memset(&head->rbnode, 0, sizeof(head->rbnode)); - barrier(); - } - if (head == qp->q.fragments_tail) - qp->q.fragments_tail = NULL; - - sub_frag_mem_limit(qp->q.net, head->truesize); - + head = inet_frag_pull_head(&qp->q); + if (!head) + goto out; head->dev = dev_get_by_index_rcu(net, qp->iif); if (!head->dev) goto out; @@ -344,12 +275,10 @@ static int ip_frag_reinit(struct ipq *qp) static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); - struct rb_node **rbn, *parent; - struct sk_buff *skb1, *prev_tail; - int ihl, end, skb1_run_end; + int ihl, end, flags, offset; + struct sk_buff *prev_tail; struct net_device *dev; unsigned int fragsize; - int flags, offset; int err = -ENOENT; u8 ecn; @@ -413,62 +342,13 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* Makes sure compiler wont do silly aliasing games */ barrier(); - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - * - * We do the same here for IPv4 (and increment an snmp counter) but - * we do not want to drop the whole queue in response to a duplicate - * fragment. - */ - - err = -EINVAL; - /* Find out where to put this fragment. */ prev_tail = qp->q.fragments_tail; - if (!prev_tail) - ip4_frag_create_run(&qp->q, skb); /* First fragment. */ - else if (prev_tail->ip_defrag_offset + prev_tail->len < end) { - /* This is the common case: skb goes to the end. */ - /* Detect and discard overlaps. */ - if (offset < prev_tail->ip_defrag_offset + prev_tail->len) - goto overlap; - if (offset == prev_tail->ip_defrag_offset + prev_tail->len) - ip4_frag_append_to_last_run(&qp->q, skb); - else - ip4_frag_create_run(&qp->q, skb); - } else { - /* Binary search. Note that skb can become the first fragment, - * but not the last (covered above). - */ - rbn = &qp->q.rb_fragments.rb_node; - do { - parent = *rbn; - skb1 = rb_to_skb(parent); - skb1_run_end = skb1->ip_defrag_offset + - FRAG_CB(skb1)->frag_run_len; - if (end <= skb1->ip_defrag_offset) - rbn = &parent->rb_left; - else if (offset >= skb1_run_end) - rbn = &parent->rb_right; - else if (offset >= skb1->ip_defrag_offset && - end <= skb1_run_end) - goto err; /* No new data, potential duplicate */ - else - goto overlap; /* Found an overlap */ - } while (*rbn); - /* Here we have parent properly set, and rbn pointing to - * one of its NULL left/right children. Insert skb. - */ - ip4_frag_init_run(skb); - rb_link_node(&skb->rbnode, parent, rbn); - rb_insert_color(&skb->rbnode, &qp->q.rb_fragments); - } + err = inet_frag_queue_insert(&qp->q, skb, offset, end); + if (err) + goto insert_error; if (dev) qp->iif = dev->ifindex; - skb->ip_defrag_offset = offset; qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; @@ -501,10 +381,16 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) skb_dst_drop(skb); return -EINPROGRESS; -overlap: +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; __IP_INC_STATS(net, IPSTATS_MIB_REASM_OVERLAPS); discard_qp: inet_frag_kill(&qp->q); + __IP_INC_STATS(net, IPSTATS_MIB_REASMFAILS); err: kfree_skb(skb); return err; @@ -516,13 +402,8 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, { struct net *net = container_of(qp->q.net, struct net, ipv4.frags); struct iphdr *iph; - struct sk_buff *fp, *head = skb_rb_first(&qp->q.rb_fragments); - struct sk_buff **nextp; /* To build frag_list. */ - struct rb_node *rbn; - int len; - int ihlen; - int delta; - int err; + void *reasm_data; + int len, err; u8 ecn; ipq_kill(qp); @@ -532,117 +413,23 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, err = -EINVAL; goto out_fail; } - /* Make the one we just received the head. */ - if (head != skb) { - fp = skb_clone(skb, GFP_ATOMIC); - if (!fp) - goto out_nomem; - FRAG_CB(fp)->next_frag = FRAG_CB(skb)->next_frag; - if (RB_EMPTY_NODE(&skb->rbnode)) - FRAG_CB(prev_tail)->next_frag = fp; - else - rb_replace_node(&skb->rbnode, &fp->rbnode, - &qp->q.rb_fragments); - if (qp->q.fragments_tail == skb) - qp->q.fragments_tail = fp; - skb_morph(skb, head); - FRAG_CB(skb)->next_frag = FRAG_CB(head)->next_frag; - rb_replace_node(&head->rbnode, &skb->rbnode, - &qp->q.rb_fragments); - consume_skb(head); - head = skb; - } - WARN_ON(head->ip_defrag_offset != 0); - - /* Allocate a new buffer for the datagram. */ - ihlen = ip_hdrlen(head); - len = ihlen + qp->q.len; + /* Make the one we just received the head. */ + reasm_data = inet_frag_reasm_prepare(&qp->q, skb, prev_tail); + if (!reasm_data) + goto out_nomem; + len = ip_hdrlen(skb) + qp->q.len; err = -E2BIG; if (len > 65535) goto out_oversize; - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_nomem; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(qp->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_nomem; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->truesize += clone->truesize; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(qp->q.net, clone->truesize); - skb_shinfo(head)->frag_list = clone; - nextp = &clone->next; - } else { - nextp = &skb_shinfo(head)->frag_list; - } - - skb_push(head, head->data - skb_network_header(head)); + inet_frag_reasm_finish(&qp->q, skb, reasm_data); - /* Traverse the tree in order, to build frag_list. */ - fp = FRAG_CB(head)->next_frag; - rbn = rb_next(&head->rbnode); - rb_erase(&head->rbnode, &qp->q.rb_fragments); - while (rbn || fp) { - /* fp points to the next sk_buff in the current run; - * rbn points to the next run. - */ - /* Go through the current run. */ - while (fp) { - *nextp = fp; - nextp = &fp->next; - fp->prev = NULL; - memset(&fp->rbnode, 0, sizeof(fp->rbnode)); - fp->sk = NULL; - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp = FRAG_CB(fp)->next_frag; - } - /* Move to the next run. */ - if (rbn) { - struct rb_node *rbnext = rb_next(rbn); - - fp = rb_to_skb(rbn); - rb_erase(rbn, &qp->q.rb_fragments); - rbn = rbnext; - } - } - sub_frag_mem_limit(qp->q.net, head->truesize); - - *nextp = NULL; - skb_mark_not_on_list(head); - head->prev = NULL; - head->dev = dev; - head->tstamp = qp->q.stamp; - IPCB(head)->frag_max_size = max(qp->max_df_size, qp->q.max_size); + skb->dev = dev; + IPCB(skb)->frag_max_size = max(qp->max_df_size, qp->q.max_size); - iph = ip_hdr(head); + iph = ip_hdr(skb); iph->tot_len = htons(len); iph->tos |= ecn; @@ -655,7 +442,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *skb, * from one very small df-fragment and one large non-df frag. */ if (qp->max_df_size == qp->q.max_size) { - IPCB(head)->flags |= IPSKB_FRAG_PMTU; + IPCB(skb)->flags |= IPSKB_FRAG_PMTU; iph->frag_off = htons(IP_DF); } else { iph->frag_off = 0; @@ -753,28 +540,6 @@ struct sk_buff *ip_check_defrag(struct net *net, struct sk_buff *skb, u32 user) } EXPORT_SYMBOL(ip_check_defrag); -unsigned int inet_frag_rbtree_purge(struct rb_root *root) -{ - struct rb_node *p = rb_first(root); - unsigned int sum = 0; - - while (p) { - struct sk_buff *skb = rb_entry(p, struct sk_buff, rbnode); - - p = rb_next(p); - rb_erase(&skb->rbnode, root); - while (skb) { - struct sk_buff *next = FRAG_CB(skb)->next_frag; - - sum += skb->truesize; - kfree_skb(skb); - skb = next; - } - } - return sum; -} -EXPORT_SYMBOL(inet_frag_rbtree_purge); - #ifdef CONFIG_SYSCTL static int dist_min; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 3978f807fa8b..ccee9411dae1 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -449,81 +449,14 @@ static int gre_handle_offloads(struct sk_buff *skb, bool csum) return iptunnel_handle_offloads(skb, csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); } -static struct rtable *gre_get_rt(struct sk_buff *skb, - struct net_device *dev, - struct flowi4 *fl, - const struct ip_tunnel_key *key) -{ - struct net *net = dev_net(dev); - - memset(fl, 0, sizeof(*fl)); - fl->daddr = key->u.ipv4.dst; - fl->saddr = key->u.ipv4.src; - fl->flowi4_tos = RT_TOS(key->tos); - fl->flowi4_mark = skb->mark; - fl->flowi4_proto = IPPROTO_GRE; - - return ip_route_output_key(net, fl); -} - -static struct rtable *prepare_fb_xmit(struct sk_buff *skb, - struct net_device *dev, - struct flowi4 *fl, - int tunnel_hlen) -{ - struct ip_tunnel_info *tun_info; - const struct ip_tunnel_key *key; - struct rtable *rt = NULL; - int min_headroom; - bool use_cache; - int err; - - tun_info = skb_tunnel_info(skb); - key = &tun_info->key; - use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); - - if (use_cache) - rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl->saddr); - if (!rt) { - rt = gre_get_rt(skb, dev, fl, key); - if (IS_ERR(rt)) - goto err_free_skb; - if (use_cache) - dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, - fl->saddr); - } - - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + tunnel_hlen + sizeof(struct iphdr); - if (skb_headroom(skb) < min_headroom || skb_header_cloned(skb)) { - int head_delta = SKB_DATA_ALIGN(min_headroom - - skb_headroom(skb) + - 16); - err = pskb_expand_head(skb, max_t(int, head_delta, 0), - 0, GFP_ATOMIC); - if (unlikely(err)) - goto err_free_rt; - } - return rt; - -err_free_rt: - ip_rt_put(rt); -err_free_skb: - kfree_skb(skb); - dev->stats.tx_dropped++; - return NULL; -} - static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; - struct rtable *rt = NULL; - struct flowi4 fl; int tunnel_hlen; - __be16 df, flags; + __be16 flags; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -533,13 +466,12 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, key = &tun_info->key; tunnel_hlen = gre_calc_hlen(key->tun_flags); - rt = prepare_fb_xmit(skb, dev, &fl, tunnel_hlen); - if (!rt) - return; + if (skb_cow_head(skb, dev->needed_headroom)) + goto err_free_skb; /* Push Tunnel header. */ if (gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM))) - goto err_free_rt; + goto err_free_skb; flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY | TUNNEL_SEQ); @@ -547,14 +479,10 @@ static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev, tunnel_id_to_key32(tun_info->key.tun_id), (flags & TUNNEL_SEQ) ? htonl(tunnel->o_seqno++) : 0); - df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); - iptunnel_xmit(skb->sk, rt, skb, fl.saddr, key->u.ipv4.dst, IPPROTO_GRE, - key->tos, key->ttl, df, false); return; -err_free_rt: - ip_rt_put(rt); err_free_skb: kfree_skb(skb); dev->stats.tx_dropped++; @@ -566,10 +494,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; struct erspan_metadata *md; - struct rtable *rt = NULL; bool truncate = false; - __be16 df, proto; - struct flowi4 fl; + __be16 proto; int tunnel_hlen; int version; int nhoff; @@ -582,21 +508,20 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) key = &tun_info->key; if (!(tun_info->key.tun_flags & TUNNEL_ERSPAN_OPT)) - goto err_free_rt; + goto err_free_skb; md = ip_tunnel_info_opts(tun_info); if (!md) - goto err_free_rt; + goto err_free_skb; /* ERSPAN has fixed 8 byte GRE header */ version = md->version; tunnel_hlen = 8 + erspan_hdr_len(version); - rt = prepare_fb_xmit(skb, dev, &fl, tunnel_hlen); - if (!rt) - return; + if (skb_cow_head(skb, dev->needed_headroom)) + goto err_free_skb; if (gre_handle_offloads(skb, false)) - goto err_free_rt; + goto err_free_skb; if (skb->len > dev->mtu + dev->hard_header_len) { pskb_trim(skb, dev->mtu + dev->hard_header_len); @@ -625,20 +550,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev) truncate, true); proto = htons(ETH_P_ERSPAN2); } else { - goto err_free_rt; + goto err_free_skb; } gre_build_header(skb, 8, TUNNEL_SEQ, proto, 0, htonl(tunnel->o_seqno++)); - df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + ip_md_tunnel_xmit(skb, dev, IPPROTO_GRE, tunnel_hlen); - iptunnel_xmit(skb->sk, rt, skb, fl.saddr, key->u.ipv4.dst, IPPROTO_GRE, - key->tos, key->ttl, df, false); return; -err_free_rt: - ip_rt_put(rt); err_free_skb: kfree_skb(skb); dev->stats.tx_dropped++; @@ -647,13 +568,18 @@ err_free_skb: static int gre_fill_metadata_dst(struct net_device *dev, struct sk_buff *skb) { struct ip_tunnel_info *info = skb_tunnel_info(skb); + const struct ip_tunnel_key *key; struct rtable *rt; struct flowi4 fl4; if (ip_tunnel_info_af(info) != AF_INET) return -EINVAL; - rt = gre_get_rt(skb, dev, &fl4, &info->key); + key = &info->key; + ip_tunnel_init_flow(&fl4, IPPROTO_GRE, key->u.ipv4.dst, key->u.ipv4.src, + tunnel_id_to_key32(key->tun_id), key->tos, 0, + skb->mark); + rt = ip_route_output_key(dev_net(dev), &fl4); if (IS_ERR(rt)) return PTR_ERR(rt); diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 51d8efba6de2..cd6b5694f99e 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -429,7 +429,6 @@ static struct sk_buff *ip_rcv_core(struct sk_buff *skb, struct net *net) if (skb->pkt_type == PACKET_OTHERHOST) goto drop; - __IP_UPD_PO_STATS(net, IPSTATS_MIB_IN, skb->len); skb = skb_share_check(skb, GFP_ATOMIC); @@ -521,6 +520,7 @@ int ip_rcv(struct sk_buff *skb, struct net_device *dev, struct packet_type *pt, skb = ip_rcv_core(skb, net); if (skb == NULL) return NET_RX_DROP; + return NF_HOOK(NFPROTO_IPV4, NF_INET_PRE_ROUTING, net, NULL, skb, dev, NULL, ip_rcv_finish); diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 054d01c16dc6..893f013d5369 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -501,15 +501,19 @@ EXPORT_SYMBOL_GPL(ip_tunnel_encap_setup); static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, struct rtable *rt, __be16 df, - const struct iphdr *inner_iph) + const struct iphdr *inner_iph, + int tunnel_hlen, __be32 dst, bool md) { struct ip_tunnel *tunnel = netdev_priv(dev); - int pkt_size = skb->len - tunnel->hlen - dev->hard_header_len; + int pkt_size; int mtu; + tunnel_hlen = md ? tunnel_hlen : tunnel->hlen; + pkt_size = skb->len - tunnel_hlen - dev->hard_header_len; + if (df) mtu = dst_mtu(&rt->dst) - dev->hard_header_len - - sizeof(struct iphdr) - tunnel->hlen; + - sizeof(struct iphdr) - tunnel_hlen; else mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; @@ -527,11 +531,13 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, #if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); + __be32 daddr; + + daddr = md ? dst : tunnel->parms.iph.daddr; if (rt6 && mtu < dst_mtu(skb_dst(skb)) && mtu >= IPV6_MIN_MTU) { - if ((tunnel->parms.iph.daddr && - !ipv4_is_multicast(tunnel->parms.iph.daddr)) || + if ((daddr && !ipv4_is_multicast(daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); @@ -548,17 +554,19 @@ static int tnl_update_pmtu(struct net_device *dev, struct sk_buff *skb, return 0; } -void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) +void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, + u8 proto, int tunnel_hlen) { struct ip_tunnel *tunnel = netdev_priv(dev); u32 headroom = sizeof(struct iphdr); struct ip_tunnel_info *tun_info; const struct ip_tunnel_key *key; const struct iphdr *inner_iph; - struct rtable *rt; + struct rtable *rt = NULL; struct flowi4 fl4; __be16 df = 0; u8 tos, ttl; + bool use_cache; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -574,20 +582,39 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else if (skb->protocol == htons(ETH_P_IPV6)) tos = ipv6_get_dsfield((const struct ipv6hdr *)inner_iph); } - ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, 0, - RT_TOS(tos), tunnel->parms.link, tunnel->fwmark); + ip_tunnel_init_flow(&fl4, proto, key->u.ipv4.dst, key->u.ipv4.src, + tunnel_id_to_key32(key->tun_id), RT_TOS(tos), + 0, skb->mark); if (tunnel->encap.type != TUNNEL_ENCAP_NONE) goto tx_error; - rt = ip_route_output_key(tunnel->net, &fl4); - if (IS_ERR(rt)) { - dev->stats.tx_carrier_errors++; - goto tx_error; + + use_cache = ip_tunnel_dst_cache_usable(skb, tun_info); + if (use_cache) + rt = dst_cache_get_ip4(&tun_info->dst_cache, &fl4.saddr); + if (!rt) { + rt = ip_route_output_key(tunnel->net, &fl4); + if (IS_ERR(rt)) { + dev->stats.tx_carrier_errors++; + goto tx_error; + } + if (use_cache) + dst_cache_set_ip4(&tun_info->dst_cache, &rt->dst, + fl4.saddr); } if (rt->dst.dev == dev) { ip_rt_put(rt); dev->stats.collisions++; goto tx_error; } + + if (key->tun_flags & TUNNEL_DONT_FRAGMENT) + df = htons(IP_DF); + if (tnl_update_pmtu(dev, skb, rt, df, inner_iph, tunnel_hlen, + key->u.ipv4.dst, true)) { + ip_rt_put(rt); + goto tx_error; + } + tos = ip_tunnel_ecn_encap(tos, inner_iph, skb); ttl = key->ttl; if (ttl == 0) { @@ -598,10 +625,10 @@ void ip_md_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, u8 proto) else ttl = ip4_dst_hoplimit(&rt->dst); } - if (key->tun_flags & TUNNEL_DONT_FRAGMENT) - df = htons(IP_DF); - else if (skb->protocol == htons(ETH_P_IP)) + + if (!df && skb->protocol == htons(ETH_P_IP)) df = inner_iph->frag_off & htons(IP_DF); + headroom += LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len; if (headroom > dev->needed_headroom) dev->needed_headroom = headroom; @@ -737,7 +764,8 @@ void ip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev, goto tx_error; } - if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph)) { + if (tnl_update_pmtu(dev, skb, rt, tnl_params->frag_off, inner_iph, + 0, 0, false)) { ip_rt_put(rt); goto tx_error; } diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index b9a9873c25c6..9bcca08efec9 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -85,7 +85,6 @@ /* Define the friendly delay before and after opening net devices */ #define CONF_POST_OPEN 10 /* After opening: 10 msecs */ -#define CONF_CARRIER_TIMEOUT 120000 /* Wait for carrier timeout */ /* Define the timeout for waiting for a DHCP/BOOTP/RARP reply */ #define CONF_OPEN_RETRIES 2 /* (Re)open devices twice */ @@ -101,6 +100,9 @@ #define NONE cpu_to_be32(INADDR_NONE) #define ANY cpu_to_be32(INADDR_ANY) +/* Wait for carrier timeout default in seconds */ +static unsigned int carrier_timeout = 120; + /* * Public IP configuration */ @@ -268,9 +270,9 @@ static int __init ic_open_devs(void) /* wait for a carrier on at least one device */ start = jiffies; - next_msg = start + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12); + next_msg = start + msecs_to_jiffies(20000); while (time_before(jiffies, start + - msecs_to_jiffies(CONF_CARRIER_TIMEOUT))) { + msecs_to_jiffies(carrier_timeout * 1000))) { int wait, elapsed; for_each_netdev(&init_net, dev) @@ -283,9 +285,9 @@ static int __init ic_open_devs(void) continue; elapsed = jiffies_to_msecs(jiffies - start); - wait = (CONF_CARRIER_TIMEOUT - elapsed + 500)/1000; + wait = (carrier_timeout * 1000 - elapsed + 500) / 1000; pr_info("Waiting up to %d more seconds for network.\n", wait); - next_msg = jiffies + msecs_to_jiffies(CONF_CARRIER_TIMEOUT/12); + next_msg = jiffies + msecs_to_jiffies(20000); } have_carrier: rtnl_unlock(); @@ -1780,3 +1782,18 @@ static int __init vendor_class_identifier_setup(char *addrs) return 1; } __setup("dhcpclass=", vendor_class_identifier_setup); + +static int __init set_carrier_timeout(char *str) +{ + ssize_t ret; + + if (!str) + return 0; + + ret = kstrtouint(str, 0, &carrier_timeout); + if (ret) + return 0; + + return 1; +} +__setup("carrier_timeout=", set_carrier_timeout); diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 57c5dd283a2c..fe10b9a2efc8 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -302,7 +302,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, ipproto); if (tunnel->collect_md) - ip_md_tunnel_xmit(skb, dev, ipproto); + ip_md_tunnel_xmit(skb, dev, ipproto, 0); else ip_tunnel_xmit(skb, dev, tiph, ipproto); return NETDEV_TX_OK; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index ddbf8c9a1abb..e536970557dd 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -67,7 +67,6 @@ #include <net/fib_rules.h> #include <linux/netconf.h> #include <net/nexthop.h> -#include <net/switchdev.h> #include <linux/nospec.h> @@ -837,10 +836,8 @@ static void ipmr_update_thresholds(struct mr_table *mrt, struct mr_mfc *cache, static int vif_add(struct net *net, struct mr_table *mrt, struct vifctl *vifc, int mrtsock) { + struct netdev_phys_item_id ppid = { }; int vifi = vifc->vifc_vifi; - struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; struct vif_device *v = &mrt->vif_table[vifi]; struct net_device *dev; struct in_device *in_dev; @@ -919,10 +916,10 @@ static int vif_add(struct net *net, struct mr_table *mrt, vifc->vifc_flags | (!mrtsock ? VIFF_STATIC : 0), (VIFF_TUNNEL | VIFF_REGISTER)); - attr.orig_dev = dev; - if (!switchdev_port_attr_get(dev, &attr)) { - memcpy(v->dev_parent_id.id, attr.u.ppid.id, attr.u.ppid.id_len); - v->dev_parent_id.id_len = attr.u.ppid.id_len; + err = dev_get_port_parent_id(dev, &ppid, true); + if (err == 0) { + memcpy(v->dev_parent_id.id, ppid.id, ppid.id_len); + v->dev_parent_id.id_len = ppid.id_len; } else { v->dev_parent_id.id_len = 0; } @@ -2467,6 +2464,61 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_MROUTE_R, -ENOBUFS); } +static int ipmr_rtm_valid_getroute_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rtmsg *rtm; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid header for multicast route get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv4_policy, extack); + + rtm = nlmsg_data(nlh); + if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || + (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || + rtm->rtm_tos || rtm->rtm_table || rtm->rtm_protocol || + rtm->rtm_scope || rtm->rtm_type || rtm->rtm_flags) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for multicast route get request"); + return -EINVAL; + } + + err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv4_policy, extack); + if (err) + return err; + + if ((tb[RTA_SRC] && !rtm->rtm_src_len) || + (tb[RTA_DST] && !rtm->rtm_dst_len)) { + NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); + return -EINVAL; + } + + for (i = 0; i <= RTA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case RTA_SRC: + case RTA_DST: + case RTA_TABLE: + break; + default: + NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in multicast route get request"); + return -EINVAL; + } + } + + return 0; +} + static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -2475,18 +2527,14 @@ static int ipmr_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct sk_buff *skb = NULL; struct mfc_cache *cache; struct mr_table *mrt; - struct rtmsg *rtm; __be32 src, grp; u32 tableid; int err; - err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, - rtm_ipv4_policy, extack); + err = ipmr_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; - rtm = nlmsg_data(nlh); - src = tb[RTA_SRC] ? nla_get_in_addr(tb[RTA_SRC]) : 0; grp = tb[RTA_DST] ? nla_get_in_addr(tb[RTA_DST]) : 0; tableid = tb[RTA_TABLE] ? nla_get_u32(tb[RTA_TABLE]) : 0; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 8d2e5dc9a827..a058213b77a7 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -80,24 +80,6 @@ int ip_route_me_harder(struct net *net, struct sk_buff *skb, unsigned int addr_t } EXPORT_SYMBOL(ip_route_me_harder); -int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) -{ - const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); - - if (entry->state.hook == NF_INET_LOCAL_OUT) { - const struct iphdr *iph = ip_hdr(skb); - - if (!(iph->tos == rt_info->tos && - skb->mark == rt_info->mark && - iph->daddr == rt_info->daddr && - iph->saddr == rt_info->saddr)) - return ip_route_me_harder(entry->state.net, skb, - RTN_UNSPEC); - } - return 0; -} -EXPORT_SYMBOL_GPL(nf_ip_reroute); - int nf_ip_route(struct net *net, struct dst_entry **dst, struct flowi *fl, bool strict __always_unused) { diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index fa2ba7c500e4..4b07eb8a9b18 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -214,7 +214,7 @@ int nf_nat_icmp_reply_translation(struct sk_buff *skb, } /* Change outer to look like the reply to an incoming packet */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMP; if (!nf_nat_ipv4_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 5163b64f8fb3..ecc12a768191 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -1611,7 +1611,8 @@ int ip_mc_validate_source(struct sk_buff *skb, __be32 daddr, __be32 saddr, return -EINVAL; if (ipv4_is_zeronet(saddr)) { - if (!ipv4_is_local_multicast(daddr)) + if (!ipv4_is_local_multicast(daddr) && + ip_hdr(skb)->protocol != IPPROTO_IGMP) return -EINVAL; } else { err = fib_validate_source(skb, saddr, 0, tos, 0, dev, @@ -2766,6 +2767,75 @@ static struct sk_buff *inet_rtm_getroute_build_skb(__be32 src, __be32 dst, return skb; } +static int inet_rtm_valid_getroute_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rtmsg *rtm; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + NL_SET_ERR_MSG(extack, + "ipv4: Invalid header for route get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv4_policy, extack); + + rtm = nlmsg_data(nlh); + if ((rtm->rtm_src_len && rtm->rtm_src_len != 32) || + (rtm->rtm_dst_len && rtm->rtm_dst_len != 32) || + rtm->rtm_table || rtm->rtm_protocol || + rtm->rtm_scope || rtm->rtm_type) { + NL_SET_ERR_MSG(extack, "ipv4: Invalid values in header for route get request"); + return -EINVAL; + } + + if (rtm->rtm_flags & ~(RTM_F_NOTIFY | + RTM_F_LOOKUP_TABLE | + RTM_F_FIB_MATCH)) { + NL_SET_ERR_MSG(extack, "ipv4: Unsupported rtm_flags for route get request"); + return -EINVAL; + } + + err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv4_policy, extack); + if (err) + return err; + + if ((tb[RTA_SRC] && !rtm->rtm_src_len) || + (tb[RTA_DST] && !rtm->rtm_dst_len)) { + NL_SET_ERR_MSG(extack, "ipv4: rtm_src_len and rtm_dst_len must be 32 for IPv4"); + return -EINVAL; + } + + for (i = 0; i <= RTA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case RTA_IIF: + case RTA_OIF: + case RTA_SRC: + case RTA_DST: + case RTA_IP_PROTO: + case RTA_SPORT: + case RTA_DPORT: + case RTA_MARK: + case RTA_UID: + break; + default: + NL_SET_ERR_MSG(extack, "ipv4: Unsupported attribute in route get request"); + return -EINVAL; + } + } + + return 0; +} + static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -2786,8 +2856,7 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err; int mark; - err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv4_policy, - extack); + err = inet_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) return err; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 2079145a3b7c..cab6b2f2f61d 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1127,7 +1127,8 @@ void tcp_free_fastopen_req(struct tcp_sock *tp) } static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, - int *copied, size_t size) + int *copied, size_t size, + struct ubuf_info *uarg) { struct tcp_sock *tp = tcp_sk(sk); struct inet_sock *inet = inet_sk(sk); @@ -1147,6 +1148,7 @@ static int tcp_sendmsg_fastopen(struct sock *sk, struct msghdr *msg, return -ENOBUFS; tp->fastopen_req->data = msg; tp->fastopen_req->size = size; + tp->fastopen_req->uarg = uarg; if (inet->defer_connect) { err = tcp_connect(sk); @@ -1186,11 +1188,6 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) flags = msg->msg_flags; if (flags & MSG_ZEROCOPY && size && sock_flag(sk, SOCK_ZEROCOPY)) { - if ((1 << sk->sk_state) & ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)) { - err = -EINVAL; - goto out_err; - } - skb = tcp_write_queue_tail(sk); uarg = sock_zerocopy_realloc(sk, size, skb_zcopy(skb)); if (!uarg) { @@ -1205,7 +1202,7 @@ int tcp_sendmsg_locked(struct sock *sk, struct msghdr *msg, size_t size) if (unlikely(flags & MSG_FASTOPEN || inet_sk(sk)->defer_connect) && !tp->repair) { - err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size); + err = tcp_sendmsg_fastopen(sk, msg, &copied_syn, size, uarg); if (err == -EINPROGRESS && copied_syn > 0) goto out; else if (err) @@ -1554,7 +1551,7 @@ static void tcp_cleanup_rbuf(struct sock *sk, int copied) (copied > 0 && ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED2) || ((icsk->icsk_ack.pending & ICSK_ACK_PUSHED) && - !icsk->icsk_ack.pingpong)) && + !inet_csk_in_pingpong_mode(sk))) && !atomic_read(&sk->sk_rmem_alloc))) time_to_ack = true; } @@ -1847,57 +1844,78 @@ out: #endif static void tcp_update_recv_tstamps(struct sk_buff *skb, - struct scm_timestamping *tss) + struct scm_timestamping_internal *tss) { if (skb->tstamp) - tss->ts[0] = ktime_to_timespec(skb->tstamp); + tss->ts[0] = ktime_to_timespec64(skb->tstamp); else - tss->ts[0] = (struct timespec) {0}; + tss->ts[0] = (struct timespec64) {0}; if (skb_hwtstamps(skb)->hwtstamp) - tss->ts[2] = ktime_to_timespec(skb_hwtstamps(skb)->hwtstamp); + tss->ts[2] = ktime_to_timespec64(skb_hwtstamps(skb)->hwtstamp); else - tss->ts[2] = (struct timespec) {0}; + tss->ts[2] = (struct timespec64) {0}; } /* Similar to __sock_recv_timestamp, but does not require an skb */ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, - struct scm_timestamping *tss) + struct scm_timestamping_internal *tss) { - struct timeval tv; + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); bool has_timestamping = false; if (tss->ts[0].tv_sec || tss->ts[0].tv_nsec) { if (sock_flag(sk, SOCK_RCVTSTAMP)) { if (sock_flag(sk, SOCK_RCVTSTAMPNS)) { - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, - sizeof(tss->ts[0]), &tss->ts[0]); - } else { - tv.tv_sec = tss->ts[0].tv_sec; - tv.tv_usec = tss->ts[0].tv_nsec / 1000; + if (new_tstamp) { + struct __kernel_timespec kts = {tss->ts[0].tv_sec, tss->ts[0].tv_nsec}; - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(tv), &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(kts), &kts); + } else { + struct timespec ts_old = timespec64_to_timespec(tss->ts[0]); + + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(ts_old), &ts_old); + } + } else { + if (new_tstamp) { + struct __kernel_sock_timeval stv; + + stv.tv_sec = tss->ts[0].tv_sec; + stv.tv_usec = tss->ts[0].tv_nsec / 1000; + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(stv), &stv); + } else { + struct __kernel_old_timeval tv; + + tv.tv_sec = tss->ts[0].tv_sec; + tv.tv_usec = tss->ts[0].tv_nsec / 1000; + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } } if (sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) has_timestamping = true; else - tss->ts[0] = (struct timespec) {0}; + tss->ts[0] = (struct timespec64) {0}; } if (tss->ts[2].tv_sec || tss->ts[2].tv_nsec) { if (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) has_timestamping = true; else - tss->ts[2] = (struct timespec) {0}; + tss->ts[2] = (struct timespec64) {0}; } if (has_timestamping) { - tss->ts[1] = (struct timespec) {0}; - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPING, - sizeof(*tss), tss); + tss->ts[1] = (struct timespec64) {0}; + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, tss); + else + put_cmsg_scm_timestamping(msg, tss); } } @@ -1938,7 +1956,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; - struct scm_timestamping tss; + struct scm_timestamping_internal tss; bool has_tss = false; bool has_cmsg; @@ -2572,14 +2590,16 @@ int tcp_disconnect(struct sock *sk, int flags) sk->sk_shutdown = 0; sock_reset_flag(sk, SOCK_DONE); tp->srtt_us = 0; + tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); tp->rcv_rtt_last_tsecr = 0; tp->write_seq += tp->max_window + 2; if (tp->write_seq == 0) tp->write_seq = 1; icsk->icsk_backoff = 0; - tp->snd_cwnd = 2; icsk->icsk_probes_out = 0; + icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; + tp->snd_cwnd = TCP_INIT_CWND; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; tp->delivered_ce = 0; @@ -2603,6 +2623,23 @@ int tcp_disconnect(struct sock *sk, int flags) tp->duplicate_sack[0].end_seq = 0; tp->dsack_dups = 0; tp->reord_seen = 0; + tp->retrans_out = 0; + tp->sacked_out = 0; + tp->tlp_high_seq = 0; + tp->last_oow_ack_time = 0; + /* There's a bubble in the pipe until at least the first ACK. */ + tp->app_limited = ~0U; + tp->rack.mstamp = 0; + tp->rack.advanced = 0; + tp->rack.reo_wnd_steps = 1; + tp->rack.last_delivered = 0; + tp->rack.reo_wnd_persist = 0; + tp->rack.dsack_seen = 0; + tp->syn_data_acked = 0; + tp->rx_opt.saw_tstamp = 0; + tp->rx_opt.dsack = 0; + tp->rx_opt.num_sacks = 0; + /* Clean up fastopen related fields */ tcp_free_fastopen_req(tp); @@ -2968,16 +3005,16 @@ static int do_tcp_setsockopt(struct sock *sk, int level, case TCP_QUICKACK: if (!val) { - icsk->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); } else { - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_CLOSE_WAIT) && inet_csk_ack_scheduled(sk)) { icsk->icsk_ack.pending |= ICSK_ACK_PUSHED; tcp_cleanup_rbuf(sk, 1); if (!(val & 1)) - icsk->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); } } break; @@ -3391,7 +3428,7 @@ static int do_tcp_getsockopt(struct sock *sk, int level, return 0; } case TCP_QUICKACK: - val = !icsk->icsk_ack.pingpong; + val = !inet_csk_in_pingpong_mode(sk); break; case TCP_CONGESTION: diff --git a/net/ipv4/tcp_bbr.c b/net/ipv4/tcp_bbr.c index 0f497fc49c3f..56be7d27f208 100644 --- a/net/ipv4/tcp_bbr.c +++ b/net/ipv4/tcp_bbr.c @@ -115,6 +115,14 @@ struct bbr { unused_b:5; u32 prior_cwnd; /* prior cwnd upon entering loss recovery */ u32 full_bw; /* recent bw, to estimate if pipe is full */ + + /* For tracking ACK aggregation: */ + u64 ack_epoch_mstamp; /* start of ACK sampling epoch */ + u16 extra_acked[2]; /* max excess data ACKed in epoch */ + u32 ack_epoch_acked:20, /* packets (S)ACKed in sampling epoch */ + extra_acked_win_rtts:5, /* age of extra_acked, in round trips */ + extra_acked_win_idx:1, /* current index in extra_acked array */ + unused_c:6; }; #define CYCLE_LEN 8 /* number of phases in a pacing gain cycle */ @@ -182,6 +190,15 @@ static const u32 bbr_lt_bw_diff = 4000 / 8; /* If we estimate we're policed, use lt_bw for this many round trips: */ static const u32 bbr_lt_bw_max_rtts = 48; +/* Gain factor for adding extra_acked to target cwnd: */ +static const int bbr_extra_acked_gain = BBR_UNIT; +/* Window length of extra_acked window. */ +static const u32 bbr_extra_acked_win_rtts = 5; +/* Max allowed val for ack_epoch_acked, after which sampling epoch is reset */ +static const u32 bbr_ack_epoch_acked_reset_thresh = 1U << 20; +/* Time period for clamping cwnd increment due to ack aggregation */ +static const u32 bbr_extra_acked_max_us = 100 * 1000; + static void bbr_check_probe_rtt_done(struct sock *sk); /* Do we estimate that STARTUP filled the pipe? */ @@ -208,6 +225,16 @@ static u32 bbr_bw(const struct sock *sk) return bbr->lt_use_bw ? bbr->lt_bw : bbr_max_bw(sk); } +/* Return maximum extra acked in past k-2k round trips, + * where k = bbr_extra_acked_win_rtts. + */ +static u16 bbr_extra_acked(const struct sock *sk) +{ + struct bbr *bbr = inet_csk_ca(sk); + + return max(bbr->extra_acked[0], bbr->extra_acked[1]); +} + /* Return rate in bytes per second, optionally with a gain. * The order here is chosen carefully to avoid overflow of u64. This should * work for input rates of up to 2.9Tbit/sec and gain of 2.89x. @@ -305,6 +332,8 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) if (event == CA_EVENT_TX_START && tp->app_limited) { bbr->idle_restart = 1; + bbr->ack_epoch_mstamp = tp->tcp_mstamp; + bbr->ack_epoch_acked = 0; /* Avoid pointless buffer overflows: pace at est. bw if we don't * need more speed (we're restarting from idle and app-limited). */ @@ -315,30 +344,19 @@ static void bbr_cwnd_event(struct sock *sk, enum tcp_ca_event event) } } -/* Find target cwnd. Right-size the cwnd based on min RTT and the - * estimated bottleneck bandwidth: +/* Calculate bdp based on min RTT and the estimated bottleneck bandwidth: * - * cwnd = bw * min_rtt * gain = BDP * gain + * bdp = bw * min_rtt * gain * * The key factor, gain, controls the amount of queue. While a small gain * builds a smaller queue, it becomes more vulnerable to noise in RTT * measurements (e.g., delayed ACKs or other ACK compression effects). This * noise may cause BBR to under-estimate the rate. - * - * To achieve full performance in high-speed paths, we budget enough cwnd to - * fit full-sized skbs in-flight on both end hosts to fully utilize the path: - * - one skb in sending host Qdisc, - * - one skb in sending host TSO/GSO engine - * - one skb being received by receiver host LRO/GRO/delayed-ACK engine - * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because - * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, - * which allows 2 outstanding 2-packet sequences, to try to keep pipe - * full even with ACK-every-other-packet delayed ACKs. */ -static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) +static u32 bbr_bdp(struct sock *sk, u32 bw, int gain) { struct bbr *bbr = inet_csk_ca(sk); - u32 cwnd; + u32 bdp; u64 w; /* If we've never had a valid RTT sample, cap cwnd at the initial @@ -353,7 +371,24 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) w = (u64)bw * bbr->min_rtt_us; /* Apply a gain to the given value, then remove the BW_SCALE shift. */ - cwnd = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; + bdp = (((w * gain) >> BBR_SCALE) + BW_UNIT - 1) / BW_UNIT; + + return bdp; +} + +/* To achieve full performance in high-speed paths, we budget enough cwnd to + * fit full-sized skbs in-flight on both end hosts to fully utilize the path: + * - one skb in sending host Qdisc, + * - one skb in sending host TSO/GSO engine + * - one skb being received by receiver host LRO/GRO/delayed-ACK engine + * Don't worry, at low rates (bbr_min_tso_rate) this won't bloat cwnd because + * in such cases tso_segs_goal is 1. The minimum cwnd is 4 packets, + * which allows 2 outstanding 2-packet sequences, to try to keep pipe + * full even with ACK-every-other-packet delayed ACKs. + */ +static u32 bbr_quantization_budget(struct sock *sk, u32 cwnd, int gain) +{ + struct bbr *bbr = inet_csk_ca(sk); /* Allow enough full-sized skbs in flight to utilize end systems. */ cwnd += 3 * bbr_tso_segs_goal(sk); @@ -368,6 +403,17 @@ static u32 bbr_target_cwnd(struct sock *sk, u32 bw, int gain) return cwnd; } +/* Find inflight based on min RTT and the estimated bottleneck bandwidth. */ +static u32 bbr_inflight(struct sock *sk, u32 bw, int gain) +{ + u32 inflight; + + inflight = bbr_bdp(sk, bw, gain); + inflight = bbr_quantization_budget(sk, inflight, gain); + + return inflight; +} + /* With pacing at lower layers, there's often less data "in the network" than * "in flight". With TSQ and departure time pacing at lower layers (e.g. fq), * we often have several skbs queued in the pacing layer with a pre-scheduled @@ -401,6 +447,22 @@ static u32 bbr_packets_in_net_at_edt(struct sock *sk, u32 inflight_now) return inflight_at_edt - interval_delivered; } +/* Find the cwnd increment based on estimate of ack aggregation */ +static u32 bbr_ack_aggregation_cwnd(struct sock *sk) +{ + u32 max_aggr_cwnd, aggr_cwnd = 0; + + if (bbr_extra_acked_gain && bbr_full_bw_reached(sk)) { + max_aggr_cwnd = ((u64)bbr_bw(sk) * bbr_extra_acked_max_us) + / BW_UNIT; + aggr_cwnd = (bbr_extra_acked_gain * bbr_extra_acked(sk)) + >> BBR_SCALE; + aggr_cwnd = min(aggr_cwnd, max_aggr_cwnd); + } + + return aggr_cwnd; +} + /* An optimization in BBR to reduce losses: On the first round of recovery, we * follow the packet conservation principle: send P packets per P packets acked. * After that, we slow-start and send at most 2*P packets per P packets acked. @@ -461,8 +523,15 @@ static void bbr_set_cwnd(struct sock *sk, const struct rate_sample *rs, if (bbr_set_cwnd_to_recover_or_restore(sk, rs, acked, &cwnd)) goto done; + target_cwnd = bbr_bdp(sk, bw, gain); + + /* Increment the cwnd to account for excess ACKed data that seems + * due to aggregation (of data and/or ACKs) visible in the ACK stream. + */ + target_cwnd += bbr_ack_aggregation_cwnd(sk); + target_cwnd = bbr_quantization_budget(sk, target_cwnd, gain); + /* If we're below target cwnd, slow start cwnd toward target cwnd. */ - target_cwnd = bbr_target_cwnd(sk, bw, gain); if (bbr_full_bw_reached(sk)) /* only cut cwnd if we filled the pipe */ cwnd = min(cwnd + acked, target_cwnd); else if (cwnd < target_cwnd || tp->delivered < TCP_INIT_CWND) @@ -503,14 +572,14 @@ static bool bbr_is_next_cycle_phase(struct sock *sk, if (bbr->pacing_gain > BBR_UNIT) return is_full_length && (rs->losses || /* perhaps pacing_gain*BDP won't fit */ - inflight >= bbr_target_cwnd(sk, bw, bbr->pacing_gain)); + inflight >= bbr_inflight(sk, bw, bbr->pacing_gain)); /* A pacing_gain < 1.0 tries to drain extra queue we added if bw * probing didn't find more bw. If inflight falls to match BDP then we * estimate queue is drained; persisting would underutilize the pipe. */ return is_full_length || - inflight <= bbr_target_cwnd(sk, bw, BBR_UNIT); + inflight <= bbr_inflight(sk, bw, BBR_UNIT); } static void bbr_advance_cycle_phase(struct sock *sk) @@ -727,6 +796,67 @@ static void bbr_update_bw(struct sock *sk, const struct rate_sample *rs) } } +/* Estimates the windowed max degree of ack aggregation. + * This is used to provision extra in-flight data to keep sending during + * inter-ACK silences. + * + * Degree of ack aggregation is estimated as extra data acked beyond expected. + * + * max_extra_acked = "maximum recent excess data ACKed beyond max_bw * interval" + * cwnd += max_extra_acked + * + * Max extra_acked is clamped by cwnd and bw * bbr_extra_acked_max_us (100 ms). + * Max filter is an approximate sliding window of 5-10 (packet timed) round + * trips. + */ +static void bbr_update_ack_aggregation(struct sock *sk, + const struct rate_sample *rs) +{ + u32 epoch_us, expected_acked, extra_acked; + struct bbr *bbr = inet_csk_ca(sk); + struct tcp_sock *tp = tcp_sk(sk); + + if (!bbr_extra_acked_gain || rs->acked_sacked <= 0 || + rs->delivered < 0 || rs->interval_us <= 0) + return; + + if (bbr->round_start) { + bbr->extra_acked_win_rtts = min(0x1F, + bbr->extra_acked_win_rtts + 1); + if (bbr->extra_acked_win_rtts >= bbr_extra_acked_win_rtts) { + bbr->extra_acked_win_rtts = 0; + bbr->extra_acked_win_idx = bbr->extra_acked_win_idx ? + 0 : 1; + bbr->extra_acked[bbr->extra_acked_win_idx] = 0; + } + } + + /* Compute how many packets we expected to be delivered over epoch. */ + epoch_us = tcp_stamp_us_delta(tp->delivered_mstamp, + bbr->ack_epoch_mstamp); + expected_acked = ((u64)bbr_bw(sk) * epoch_us) / BW_UNIT; + + /* Reset the aggregation epoch if ACK rate is below expected rate or + * significantly large no. of ack received since epoch (potentially + * quite old epoch). + */ + if (bbr->ack_epoch_acked <= expected_acked || + (bbr->ack_epoch_acked + rs->acked_sacked >= + bbr_ack_epoch_acked_reset_thresh)) { + bbr->ack_epoch_acked = 0; + bbr->ack_epoch_mstamp = tp->delivered_mstamp; + expected_acked = 0; + } + + /* Compute excess data delivered, beyond what was expected. */ + bbr->ack_epoch_acked = min_t(u32, 0xFFFFF, + bbr->ack_epoch_acked + rs->acked_sacked); + extra_acked = bbr->ack_epoch_acked - expected_acked; + extra_acked = min(extra_acked, tp->snd_cwnd); + if (extra_acked > bbr->extra_acked[bbr->extra_acked_win_idx]) + bbr->extra_acked[bbr->extra_acked_win_idx] = extra_acked; +} + /* Estimate when the pipe is full, using the change in delivery rate: BBR * estimates that STARTUP filled the pipe if the estimated bw hasn't changed by * at least bbr_full_bw_thresh (25%) after bbr_full_bw_cnt (3) non-app-limited @@ -762,11 +892,11 @@ static void bbr_check_drain(struct sock *sk, const struct rate_sample *rs) if (bbr->mode == BBR_STARTUP && bbr_full_bw_reached(sk)) { bbr->mode = BBR_DRAIN; /* drain queue we created */ tcp_sk(sk)->snd_ssthresh = - bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT); + bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT); } /* fall through to check if in-flight is already small: */ if (bbr->mode == BBR_DRAIN && bbr_packets_in_net_at_edt(sk, tcp_packets_in_flight(tcp_sk(sk))) <= - bbr_target_cwnd(sk, bbr_max_bw(sk), BBR_UNIT)) + bbr_inflight(sk, bbr_max_bw(sk), BBR_UNIT)) bbr_reset_probe_bw_mode(sk); /* we estimate queue is drained */ } @@ -881,6 +1011,7 @@ static void bbr_update_gains(struct sock *sk) static void bbr_update_model(struct sock *sk, const struct rate_sample *rs) { bbr_update_bw(sk, rs); + bbr_update_ack_aggregation(sk, rs); bbr_update_cycle_phase(sk, rs); bbr_check_full_bw_reached(sk, rs); bbr_check_drain(sk, rs); @@ -932,6 +1063,13 @@ static void bbr_init(struct sock *sk) bbr_reset_lt_bw_sampling(sk); bbr_reset_startup_mode(sk); + bbr->ack_epoch_mstamp = tp->tcp_mstamp; + bbr->ack_epoch_acked = 0; + bbr->extra_acked_win_rtts = 0; + bbr->extra_acked_win_idx = 0; + bbr->extra_acked[0] = 0; + bbr->extra_acked[1] = 0; + cmpxchg(&sk->sk_pacing_status, SK_PACING_NONE, SK_PACING_NEEDED); } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 76858b14ebe9..7a027dec649b 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -221,7 +221,7 @@ void tcp_enter_quickack_mode(struct sock *sk, unsigned int max_quickacks) struct inet_connection_sock *icsk = inet_csk(sk); tcp_incr_quickack(sk, max_quickacks); - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } EXPORT_SYMBOL(tcp_enter_quickack_mode); @@ -236,7 +236,7 @@ static bool tcp_in_quickack_mode(struct sock *sk) const struct dst_entry *dst = __sk_dst_get(sk); return (dst && dst_metric(dst, RTAX_QUICKACK)) || - (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); + (icsk->icsk_ack.quick && !inet_csk_in_pingpong_mode(sk)); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) @@ -4094,7 +4094,7 @@ void tcp_fin(struct sock *sk) case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); - inet_csk(sk)->icsk_ack.pingpong = 1; + inet_csk_enter_pingpong_mode(sk); break; case TCP_CLOSE_WAIT: @@ -5889,7 +5889,7 @@ static int tcp_rcv_synsent_state_process(struct sock *sk, struct sk_buff *skb, return -1; if (sk->sk_write_pending || icsk->icsk_accept_queue.rskq_defer_accept || - icsk->icsk_ack.pingpong) { + inet_csk_in_pingpong_mode(sk)) { /* Save one ACK. Data will be ready after * several ticks, if write_pending is set. * diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index efc6fef692ff..662b034f1795 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2437,7 +2437,7 @@ static void get_tcp4_sock(struct sock *sk, struct seq_file *f, int i) refcount_read(&sk->sk_refcnt), sk, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), - (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sk), tp->snd_cwnd, state == TCP_LISTEN ? fastopenq->max_qlen : diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 12affb7864d9..182595e2d40f 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -479,43 +479,16 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, tcp_init_wl(newtp, treq->rcv_isn); - newtp->srtt_us = 0; - newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); minmax_reset(&newtp->rtt_min, tcp_jiffies32, ~0U); - newicsk->icsk_rto = TCP_TIMEOUT_INIT; newicsk->icsk_ack.lrcvtime = tcp_jiffies32; - newtp->packets_out = 0; - newtp->retrans_out = 0; - newtp->sacked_out = 0; - newtp->snd_ssthresh = TCP_INFINITE_SSTHRESH; - newtp->tlp_high_seq = 0; newtp->lsndtime = tcp_jiffies32; newsk->sk_txhash = treq->txhash; - newtp->last_oow_ack_time = 0; newtp->total_retrans = req->num_retrans; - /* So many TCP implementations out there (incorrectly) count the - * initial SYN frame in their delayed-ACK and congestion control - * algorithms that we must have the following bandaid to talk - * efficiently to them. -DaveM - */ - newtp->snd_cwnd = TCP_INIT_CWND; - newtp->snd_cwnd_cnt = 0; - - /* There's a bubble in the pipe until at least the first ACK. */ - newtp->app_limited = ~0U; - tcp_init_xmit_timers(newsk); newtp->write_seq = newtp->pushed_seq = treq->snt_isn + 1; - newtp->rx_opt.saw_tstamp = 0; - - newtp->rx_opt.dsack = 0; - newtp->rx_opt.num_sacks = 0; - - newtp->urg_data = 0; - if (sock_flag(newsk, SOCK_KEEPOPEN)) inet_csk_reset_keepalive_timer(newsk, keepalive_time_when(newtp)); @@ -556,13 +529,6 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, tcp_ecn_openreq_child(newtp, req); newtp->fastopen_req = NULL; newtp->fastopen_rsk = NULL; - newtp->syn_data_acked = 0; - newtp->rack.mstamp = 0; - newtp->rack.advanced = 0; - newtp->rack.reo_wnd_steps = 1; - newtp->rack.last_delivered = 0; - newtp->rack.reo_wnd_persist = 0; - newtp->rack.dsack_seen = 0; __TCP_INC_STATS(sock_net(sk), TCP_MIB_PASSIVEOPENS); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 730bc44dbad9..96bdb8eae9bb 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -165,13 +165,16 @@ static void tcp_event_data_sent(struct tcp_sock *tp, if (tcp_packets_in_flight(tp) == 0) tcp_ca_event(sk, CA_EVENT_TX_START); - tp->lsndtime = now; - - /* If it is a reply for ato after last received - * packet, enter pingpong mode. + /* If this is the first data packet sent in response to the + * previous received data, + * and it is a reply for ato after last received packet, + * increase pingpong count. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) - icsk->icsk_ack.pingpong = 1; + if (before(tp->lsndtime, icsk->icsk_ack.lrcvtime) && + (u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + inet_csk_inc_pingpong_cnt(sk); + + tp->lsndtime = now; } /* Account for an ACK we sent. */ @@ -980,7 +983,6 @@ static void tcp_update_skb_after_send(struct sock *sk, struct sk_buff *skb, { struct tcp_sock *tp = tcp_sk(sk); - skb->skb_mstamp_ns = tp->tcp_wstamp_ns; if (sk->sk_pacing_status != SK_PACING_NONE) { unsigned long rate = sk->sk_pacing_rate; @@ -1028,7 +1030,9 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, BUG_ON(!skb || !tcp_skb_pcount(skb)); tp = tcp_sk(sk); - + prior_wstamp = tp->tcp_wstamp_ns; + tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); + skb->skb_mstamp_ns = tp->tcp_wstamp_ns; if (clone_it) { TCP_SKB_CB(skb)->tx.in_flight = TCP_SKB_CB(skb)->end_seq - tp->snd_una; @@ -1045,11 +1049,6 @@ static int __tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, return -ENOBUFS; } - prior_wstamp = tp->tcp_wstamp_ns; - tp->tcp_wstamp_ns = max(tp->tcp_wstamp_ns, tp->tcp_clock_cache); - - skb->skb_mstamp_ns = tp->tcp_wstamp_ns; - inet = inet_sk(sk); tcb = TCP_SKB_CB(skb); memset(&opts, 0, sizeof(opts)); @@ -2937,12 +2936,16 @@ int __tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); } + /* To avoid taking spuriously low RTT samples based on a timestamp + * for a transmit that never happened, always mark EVER_RETRANS + */ + TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; + if (BPF_SOCK_OPS_TEST_FLAG(tp, BPF_SOCK_OPS_RETRANS_CB_FLAG)) tcp_call_bpf_3arg(sk, BPF_SOCK_OPS_RETRANS_CB, TCP_SKB_CB(skb)->seq, segs, err); if (likely(!err)) { - TCP_SKB_CB(skb)->sacked |= TCPCB_EVER_RETRANS; trace_tcp_retransmit_skb(sk, skb); } else if (err != -EBUSY) { NET_ADD_STATS(sock_net(sk), LINUX_MIB_TCPRETRANSFAIL, segs); @@ -2963,13 +2966,12 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb, int segs) #endif TCP_SKB_CB(skb)->sacked |= TCPCB_RETRANS; tp->retrans_out += tcp_skb_pcount(skb); - - /* Save stamp of the first retransmit. */ - if (!tp->retrans_stamp) - tp->retrans_stamp = tcp_skb_timestamp(skb); - } + /* Save stamp of the first (attempted) retransmit. */ + if (!tp->retrans_stamp) + tp->retrans_stamp = tcp_skb_timestamp(skb); + if (tp->undo_retrans < 0) tp->undo_retrans = 0; tp->undo_retrans += tcp_skb_pcount(skb); @@ -3456,6 +3458,7 @@ static int tcp_send_syn_data(struct sock *sk, struct sk_buff *syn) skb_trim(syn_data, copied); space = copied; } + skb_zcopy_set(syn_data, fo->uarg, NULL); } /* No more data pending in inet_wait_for_connect() */ if (space == fo->size) @@ -3569,7 +3572,7 @@ void tcp_send_delayed_ack(struct sock *sk) const struct tcp_sock *tp = tcp_sk(sk); int max_ato = HZ / 2; - if (icsk->icsk_ack.pingpong || + if (inet_csk_in_pingpong_mode(sk) || (icsk->icsk_ack.pending & ICSK_ACK_PUSHED)) max_ato = TCP_DELACK_MAX; @@ -3750,7 +3753,7 @@ void tcp_send_probe0(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); struct net *net = sock_net(sk); - unsigned long probe_max; + unsigned long timeout; int err; err = tcp_write_wakeup(sk, LINUX_MIB_TCPWINPROBE); @@ -3762,26 +3765,18 @@ void tcp_send_probe0(struct sock *sk) return; } + icsk->icsk_probes_out++; if (err <= 0) { if (icsk->icsk_backoff < net->ipv4.sysctl_tcp_retries2) icsk->icsk_backoff++; - icsk->icsk_probes_out++; - probe_max = TCP_RTO_MAX; + timeout = tcp_probe0_when(sk, TCP_RTO_MAX); } else { /* If packet was not sent due to local congestion, - * do not backoff and do not remember icsk_probes_out. - * Let local senders to fight for local resources. - * - * Use accumulated backoff yet. + * Let senders fight for local resources conservatively. */ - if (!icsk->icsk_probes_out) - icsk->icsk_probes_out = 1; - probe_max = TCP_RESOURCE_PROBE_INTERVAL; - } - tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, - tcp_probe0_when(sk, probe_max), - TCP_RTO_MAX, - NULL); + timeout = TCP_RESOURCE_PROBE_INTERVAL; + } + tcp_reset_xmit_timer(sk, ICSK_TIME_PROBE0, timeout, TCP_RTO_MAX, NULL); } int tcp_rtx_synack(const struct sock *sk, struct request_sock *req) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 71a29e9c0620..f0c86398e6a7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -22,28 +22,14 @@ #include <linux/gfp.h> #include <net/tcp.h> -static u32 tcp_retransmit_stamp(const struct sock *sk) -{ - u32 start_ts = tcp_sk(sk)->retrans_stamp; - - if (unlikely(!start_ts)) { - struct sk_buff *head = tcp_rtx_queue_head(sk); - - if (!head) - return 0; - start_ts = tcp_skb_timestamp(head); - } - return start_ts; -} - static u32 tcp_clamp_rto_to_user_timeout(const struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); u32 elapsed, start_ts; s32 remaining; - start_ts = tcp_retransmit_stamp(sk); - if (!icsk->icsk_user_timeout || !start_ts) + start_ts = tcp_sk(sk)->retrans_stamp; + if (!icsk->icsk_user_timeout) return icsk->icsk_rto; elapsed = tcp_time_stamp(tcp_sk(sk)) - start_ts; remaining = icsk->icsk_user_timeout - elapsed; @@ -173,7 +159,20 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } - +static unsigned int tcp_model_timeout(struct sock *sk, + unsigned int boundary, + unsigned int rto_base) +{ + unsigned int linear_backoff_thresh, timeout; + + linear_backoff_thresh = ilog2(TCP_RTO_MAX / rto_base); + if (boundary <= linear_backoff_thresh) + timeout = ((2 << boundary) - 1) * rto_base; + else + timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + return jiffies_to_msecs(timeout); +} /** * retransmits_timed_out() - returns true if this connection has timed out * @sk: The current socket @@ -191,26 +190,15 @@ static bool retransmits_timed_out(struct sock *sk, unsigned int boundary, unsigned int timeout) { - const unsigned int rto_base = TCP_RTO_MIN; - unsigned int linear_backoff_thresh, start_ts; + unsigned int start_ts; if (!inet_csk(sk)->icsk_retransmits) return false; - start_ts = tcp_retransmit_stamp(sk); - if (!start_ts) - return false; - - if (likely(timeout == 0)) { - linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); + start_ts = tcp_sk(sk)->retrans_stamp; + if (likely(timeout == 0)) + timeout = tcp_model_timeout(sk, boundary, TCP_RTO_MIN); - if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * rto_base; - else - timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + - (boundary - linear_backoff_thresh) * TCP_RTO_MAX; - timeout = jiffies_to_msecs(timeout); - } return (s32)(tcp_time_stamp(tcp_sk(sk)) - start_ts - timeout) >= 0; } @@ -289,14 +277,14 @@ void tcp_delack_timer_handler(struct sock *sk) icsk->icsk_ack.pending &= ~ICSK_ACK_TIMER; if (inet_csk_ack_scheduled(sk)) { - if (!icsk->icsk_ack.pingpong) { + if (!inet_csk_in_pingpong_mode(sk)) { /* Delayed ACK missed: inflate ATO. */ icsk->icsk_ack.ato = min(icsk->icsk_ack.ato << 1, icsk->icsk_rto); } else { /* Delayed ACK missed: leave pingpong mode and * deflate ATO. */ - icsk->icsk_ack.pingpong = 0; + inet_csk_exit_pingpong_mode(sk); icsk->icsk_ack.ato = TCP_ATO_MIN; } tcp_mstamp_refresh(tcp_sk(sk)); @@ -345,7 +333,6 @@ static void tcp_probe_timer(struct sock *sk) struct sk_buff *skb = tcp_send_head(sk); struct tcp_sock *tp = tcp_sk(sk); int max_probes; - u32 start_ts; if (tp->packets_out || !skb) { icsk->icsk_probes_out = 0; @@ -360,12 +347,13 @@ static void tcp_probe_timer(struct sock *sk) * corresponding system limit. We also implement similar policy when * we use RTO to probe window in tcp_retransmit_timer(). */ - start_ts = tcp_skb_timestamp(skb); - if (!start_ts) - skb->skb_mstamp_ns = tp->tcp_clock_cache; - else if (icsk->icsk_user_timeout && - (s32)(tcp_time_stamp(tp) - start_ts) > icsk->icsk_user_timeout) - goto abort; + if (icsk->icsk_user_timeout) { + u32 elapsed = tcp_model_timeout(sk, icsk->icsk_probes_out, + tcp_probe0_base(sk)); + + if (elapsed >= icsk->icsk_user_timeout) + goto abort; + } max_probes = sock_net(sk)->ipv4.sysctl_tcp_retries2; if (sock_flag(sk, SOCK_DEAD)) { @@ -395,6 +383,7 @@ static void tcp_fastopen_synack_timer(struct sock *sk) struct inet_connection_sock *icsk = inet_csk(sk); int max_retries = icsk->icsk_syn_retries ? : sock_net(sk)->ipv4.sysctl_tcp_synack_retries + 1; /* add one more retry for fastopen */ + struct tcp_sock *tp = tcp_sk(sk); struct request_sock *req; req = tcp_sk(sk)->fastopen_rsk; @@ -412,6 +401,8 @@ static void tcp_fastopen_synack_timer(struct sock *sk) inet_rtx_syn_ack(sk, req); req->num_timeout++; icsk->icsk_retransmits++; + if (!tp->retrans_stamp) + tp->retrans_stamp = tcp_time_stamp(tp); inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, TCP_TIMEOUT_INIT << req->num_timeout, TCP_RTO_MAX); } @@ -443,10 +434,8 @@ void tcp_retransmit_timer(struct sock *sk) */ return; } - if (!tp->packets_out) - goto out; - - WARN_ON(tcp_rtx_queue_empty(sk)); + if (!tp->packets_out || WARN_ON_ONCE(tcp_rtx_queue_empty(sk))) + return; tp->tlp_high_seq = 0; @@ -511,14 +500,13 @@ void tcp_retransmit_timer(struct sock *sk) tcp_enter_loss(sk); + icsk->icsk_retransmits++; if (tcp_retransmit_skb(sk, tcp_rtx_queue_head(sk), 1) > 0) { /* Retransmission failed because of local congestion, - * do not backoff. + * Let senders fight for local resources conservatively. */ - if (!icsk->icsk_retransmits) - icsk->icsk_retransmits = 1; inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - min(icsk->icsk_rto, TCP_RESOURCE_PROBE_INTERVAL), + TCP_RESOURCE_PROBE_INTERVAL, TCP_RTO_MAX); goto out; } @@ -539,7 +527,6 @@ void tcp_retransmit_timer(struct sock *sk) * the 120 second clamps though! */ icsk->icsk_backoff++; - icsk->icsk_retransmits++; out_reset_timer: /* If stream is thin, use linear timeouts. Since 'icsk_backoff' is diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index be8b5b2157d8..e93cc0379201 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -21,18 +21,9 @@ int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, goto error; if (cfg->bind_ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(net, cfg->bind_ifindex); - if (!dev) { - err = -ENODEV; - goto error; - } - - err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, - dev->name, strlen(dev->name) + 1); - dev_put(dev); - + err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTOIFINDEX, + (void *)&cfg->bind_ifindex, + sizeof(cfg->bind_ifindex)); if (err < 0) goto error; } diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 72ffd3d760ff..da5a21050ba9 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -597,6 +597,43 @@ static const struct nla_policy devconf_ipv6_policy[NETCONFA_MAX+1] = { [NETCONFA_IGNORE_ROUTES_WITH_LINKDOWN] = { .len = sizeof(int) }, }; +static int inet6_netconf_valid_get_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { + NL_SET_ERR_MSG_MOD(extack, "Invalid header for netconf get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb, + NETCONFA_MAX, devconf_ipv6_policy, extack); + + err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb, + NETCONFA_MAX, devconf_ipv6_policy, extack); + if (err) + return err; + + for (i = 0; i <= NETCONFA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case NETCONFA_IFINDEX: + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request"); + return -EINVAL; + } + } + + return 0; +} + static int inet6_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) @@ -605,14 +642,12 @@ static int inet6_netconf_get_devconf(struct sk_buff *in_skb, struct nlattr *tb[NETCONFA_MAX+1]; struct inet6_dev *in6_dev = NULL; struct net_device *dev = NULL; - struct netconfmsg *ncm; struct sk_buff *skb; struct ipv6_devconf *devconf; int ifindex; int err; - err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, - devconf_ipv6_policy, extack); + err = inet6_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) return err; @@ -5182,6 +5217,52 @@ static int inet6_dump_ifacaddr(struct sk_buff *skb, struct netlink_callback *cb) return inet6_dump_addr(skb, cb, type); } +static int inet6_rtm_valid_getaddr_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct ifaddrmsg *ifm; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifm))) { + NL_SET_ERR_MSG_MOD(extack, "Invalid header for get address request"); + return -EINVAL; + } + + ifm = nlmsg_data(nlh); + if (ifm->ifa_prefixlen || ifm->ifa_flags || ifm->ifa_scope) { + NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get address request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + + err = nlmsg_parse_strict(nlh, sizeof(*ifm), tb, IFA_MAX, + ifa_ipv6_policy, extack); + if (err) + return err; + + for (i = 0; i <= IFA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case IFA_TARGET_NETNSID: + case IFA_ADDRESS: + case IFA_LOCAL: + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get address request"); + return -EINVAL; + } + } + + return 0; +} + static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -5202,8 +5283,7 @@ static int inet6_rtm_getaddr(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct sk_buff *skb; int err; - err = nlmsg_parse(nlh, sizeof(*ifm), tb, IFA_MAX, ifa_ipv6_policy, - extack); + err = inet6_rtm_valid_getaddr_req(in_skb, nlh, tb, extack); if (err < 0) return err; @@ -6825,6 +6905,11 @@ static int __net_init addrconf_init_net(struct net *net) if (!dflt) goto err_alloc_dflt; + if (sysctl_devconf_inherit_init_net == 1 && !net_eq(net, &init_net)) { + memcpy(all, init_net.ipv6.devconf_all, sizeof(ipv6_devconf)); + memcpy(dflt, init_net.ipv6.devconf_dflt, sizeof(ipv6_devconf_dflt)); + } + /* these will be inherited by all namespaces */ dflt->autoconf = ipv6_defaults.autoconf; dflt->disable_ipv6 = ipv6_defaults.disable_ipv6; diff --git a/net/ipv6/addrlabel.c b/net/ipv6/addrlabel.c index 0d1ee82ee55b..d43d076c98f5 100644 --- a/net/ipv6/addrlabel.c +++ b/net/ipv6/addrlabel.c @@ -523,6 +523,50 @@ static inline int ip6addrlbl_msgsize(void) + nla_total_size(4); /* IFAL_LABEL */ } +static int ip6addrlbl_valid_get_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct ifaddrlblmsg *ifal; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*ifal))) { + NL_SET_ERR_MSG_MOD(extack, "Invalid header for addrlabel get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, + ifal_policy, extack); + + ifal = nlmsg_data(nlh); + if (ifal->__ifal_reserved || ifal->ifal_flags || ifal->ifal_seq) { + NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for addrlabel get request"); + return -EINVAL; + } + + err = nlmsg_parse_strict(nlh, sizeof(*ifal), tb, IFAL_MAX, + ifal_policy, extack); + if (err) + return err; + + for (i = 0; i <= IFAL_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case IFAL_ADDRESS: + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in addrlabel get request"); + return -EINVAL; + } + } + + return 0; +} + static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -535,8 +579,7 @@ static int ip6addrlbl_get(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct ip6addrlbl_entry *p; struct sk_buff *skb; - err = nlmsg_parse(nlh, sizeof(*ifal), tb, IFAL_MAX, ifal_policy, - extack); + err = ip6addrlbl_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) return err; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 801a9a0c217e..65a4f96dc462 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -524,7 +524,7 @@ static int ip6gre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) return PACKET_REJECT; } -static int ip6erspan_rcv(struct sk_buff *skb, int gre_hdr_len, +static int ip6erspan_rcv(struct sk_buff *skb, struct tnl_ptk_info *tpi) { struct erspan_base_hdr *ershdr; @@ -607,7 +607,7 @@ static int gre_rcv(struct sk_buff *skb) if (unlikely(tpi.proto == htons(ETH_P_ERSPAN) || tpi.proto == htons(ETH_P_ERSPAN2))) { - if (ip6erspan_rcv(skb, hdr_len, &tpi) == PACKET_RCVD) + if (ip6erspan_rcv(skb, &tpi) == PACKET_RCVD) return 0; goto out; } diff --git a/net/ipv6/ip6_udp_tunnel.c b/net/ipv6/ip6_udp_tunnel.c index ad1a9ccd4b44..25430c991cea 100644 --- a/net/ipv6/ip6_udp_tunnel.c +++ b/net/ipv6/ip6_udp_tunnel.c @@ -32,18 +32,9 @@ int udp_sock_create6(struct net *net, struct udp_port_cfg *cfg, goto error; } if (cfg->bind_ifindex) { - struct net_device *dev; - - dev = dev_get_by_index(net, cfg->bind_ifindex); - if (!dev) { - err = -ENODEV; - goto error; - } - - err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTODEVICE, - dev->name, strlen(dev->name) + 1); - dev_put(dev); - + err = kernel_setsockopt(sock, SOL_SOCKET, SO_BINDTOIFINDEX, + (void *)&cfg->bind_ifindex, + sizeof(cfg->bind_ifindex)); if (err < 0) goto error; } diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 21f6deb2aec9..42f3f5cd349f 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -940,6 +940,7 @@ int ipv6_dev_mc_inc(struct net_device *dev, const struct in6_addr *addr) { return __ipv6_dev_mc_inc(dev, addr, MCAST_EXCLUDE); } +EXPORT_SYMBOL(ipv6_dev_mc_inc); /* * device multicast group del @@ -987,6 +988,7 @@ int ipv6_dev_mc_dec(struct net_device *dev, const struct in6_addr *addr) return err; } +EXPORT_SYMBOL(ipv6_dev_mc_dec); /* * check if the interface/address pair is valid diff --git a/net/ipv6/mcast_snoop.c b/net/ipv6/mcast_snoop.c index 9405b04eecc6..55e2ac179f28 100644 --- a/net/ipv6/mcast_snoop.c +++ b/net/ipv6/mcast_snoop.c @@ -41,6 +41,8 @@ static int ipv6_mc_check_ip6hdr(struct sk_buff *skb) if (skb->len < len || len <= offset) return -EINVAL; + skb_set_transport_header(skb, offset); + return 0; } @@ -77,27 +79,27 @@ static int ipv6_mc_check_mld_reportv2(struct sk_buff *skb) len += sizeof(struct mld2_report); - return pskb_may_pull(skb, len) ? 0 : -EINVAL; + return ipv6_mc_may_pull(skb, len) ? 0 : -EINVAL; } static int ipv6_mc_check_mld_query(struct sk_buff *skb) { + unsigned int transport_len = ipv6_transport_len(skb); struct mld_msg *mld; - unsigned int len = skb_transport_offset(skb); + unsigned int len; /* RFC2710+RFC3810 (MLDv1+MLDv2) require link-local source addresses */ if (!(ipv6_addr_type(&ipv6_hdr(skb)->saddr) & IPV6_ADDR_LINKLOCAL)) return -EINVAL; - len += sizeof(struct mld_msg); - if (skb->len < len) - return -EINVAL; - /* MLDv1? */ - if (skb->len != len) { + if (transport_len != sizeof(struct mld_msg)) { /* or MLDv2? */ - len += sizeof(struct mld2_query) - sizeof(struct mld_msg); - if (skb->len < len || !pskb_may_pull(skb, len)) + if (transport_len < sizeof(struct mld2_query)) + return -EINVAL; + + len = skb_transport_offset(skb) + sizeof(struct mld2_query); + if (!ipv6_mc_may_pull(skb, len)) return -EINVAL; } @@ -115,7 +117,13 @@ static int ipv6_mc_check_mld_query(struct sk_buff *skb) static int ipv6_mc_check_mld_msg(struct sk_buff *skb) { - struct mld_msg *mld = (struct mld_msg *)skb_transport_header(skb); + unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg); + struct mld_msg *mld; + + if (!ipv6_mc_may_pull(skb, len)) + return -EINVAL; + + mld = (struct mld_msg *)skb_transport_header(skb); switch (mld->mld_type) { case ICMPV6_MGM_REDUCTION: @@ -136,49 +144,30 @@ static inline __sum16 ipv6_mc_validate_checksum(struct sk_buff *skb) return skb_checksum_validate(skb, IPPROTO_ICMPV6, ip6_compute_pseudo); } -static int __ipv6_mc_check_mld(struct sk_buff *skb, - struct sk_buff **skb_trimmed) - +int ipv6_mc_check_icmpv6(struct sk_buff *skb) { - struct sk_buff *skb_chk = NULL; - unsigned int transport_len; - unsigned int len = skb_transport_offset(skb) + sizeof(struct mld_msg); - int ret = -EINVAL; + unsigned int len = skb_transport_offset(skb) + sizeof(struct icmp6hdr); + unsigned int transport_len = ipv6_transport_len(skb); + struct sk_buff *skb_chk; - transport_len = ntohs(ipv6_hdr(skb)->payload_len); - transport_len -= skb_transport_offset(skb) - sizeof(struct ipv6hdr); + if (!ipv6_mc_may_pull(skb, len)) + return -EINVAL; skb_chk = skb_checksum_trimmed(skb, transport_len, ipv6_mc_validate_checksum); if (!skb_chk) - goto err; - - if (!pskb_may_pull(skb_chk, len)) - goto err; - - ret = ipv6_mc_check_mld_msg(skb_chk); - if (ret) - goto err; - - if (skb_trimmed) - *skb_trimmed = skb_chk; - /* free now unneeded clone */ - else if (skb_chk != skb) - kfree_skb(skb_chk); - - ret = 0; + return -EINVAL; -err: - if (ret && skb_chk && skb_chk != skb) + if (skb_chk != skb) kfree_skb(skb_chk); - return ret; + return 0; } +EXPORT_SYMBOL(ipv6_mc_check_icmpv6); /** * ipv6_mc_check_mld - checks whether this is a sane MLD packet * @skb: the skb to validate - * @skb_trimmed: to store an skb pointer trimmed to IPv6 packet tail (optional) * * Checks whether an IPv6 packet is a valid MLD packet. If so sets * skb transport header accordingly and returns zero. @@ -188,18 +177,10 @@ err: * -ENOMSG: IP header validation succeeded but it is not an MLD packet. * -ENOMEM: A memory allocation failure happened. * - * Optionally, an skb pointer might be provided via skb_trimmed (or set it - * to NULL): After parsing an MLD packet successfully it will point to - * an skb which has its tail aligned to the IP packet end. This might - * either be the originally provided skb or a trimmed, cloned version if - * the skb frame had data beyond the IP packet. A cloned skb allows us - * to leave the original skb and its full frame unchanged (which might be - * desirable for layer 2 frame jugglers). - * * Caller needs to set the skb network header and free any returned skb if it * differs from the provided skb. */ -int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed) +int ipv6_mc_check_mld(struct sk_buff *skb) { int ret; @@ -211,6 +192,10 @@ int ipv6_mc_check_mld(struct sk_buff *skb, struct sk_buff **skb_trimmed) if (ret < 0) return ret; - return __ipv6_mc_check_mld(skb, skb_trimmed); + ret = ipv6_mc_check_icmpv6(skb); + if (ret < 0) + return ret; + + return ipv6_mc_check_mld_msg(skb); } EXPORT_SYMBOL(ipv6_mc_check_mld); diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index 181da2c40f9a..cb1b4772dac0 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -136,6 +136,9 @@ static void __net_exit nf_ct_frags6_sysctl_unregister(struct net *net) } #endif +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); + static inline u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) { return 1 << (ipv6_get_dsfield(ipv6h) & INET_ECN_MASK); @@ -177,9 +180,10 @@ static struct frag_queue *fq_find(struct net *net, __be32 id, u32 user, static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, const struct frag_hdr *fhdr, int nhoff) { - struct sk_buff *prev, *next; unsigned int payload_len; - int offset, end; + struct net_device *dev; + struct sk_buff *prev; + int offset, end, err; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) { @@ -254,55 +258,18 @@ static int nf_ct_frag6_queue(struct frag_queue *fq, struct sk_buff *skb, goto err; } - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4: - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments, including those not yet received) MUST be silently - * discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (prev->ip_defrag_offset + prev->len) > offset) - goto discard_fq; - - /* Look for overlap with succeeding segment. */ - if (next && next->ip_defrag_offset < end) - goto discard_fq; - - /* Note : skb->ip_defrag_offset and skb->dev share the same location */ - if (skb->dev) - fq->iif = skb->dev->ifindex; + /* Note : skb->rbnode and skb->dev share the same location. */ + dev = skb->dev; /* Makes sure compiler wont do silly aliasing games */ barrier(); - skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error; + + if (dev) + fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; @@ -319,11 +286,25 @@ found: fq->q.flags |= INET_FRAG_FIRST_IN; } - return 0; + if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && + fq->q.meat == fq->q.len) { + unsigned long orefdst = skb->_skb_refdst; + + skb->_skb_refdst = 0UL; + err = nf_ct_frag6_reasm(fq, skb, prev, dev); + skb->_skb_refdst = orefdst; + return err; + } + + skb_dst_drop(skb); + return -EINPROGRESS; -discard_fq: +insert_error: + if (err == IPFRAG_DUP) + goto err; inet_frag_kill(&fq->q); err: + skb_dst_drop(skb); return -EINVAL; } @@ -333,147 +314,67 @@ err: * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. - * - * returns true if *prev skb has been transformed into the reassembled - * skb, false otherwise. */ -static bool -nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) +static int nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; + void *reasm_data; + int payload_len; u8 ecn; inet_frag_kill(&fq->q); - WARN_ON(head == NULL); - WARN_ON(head->ip_defrag_offset != 0); - ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) - return false; + goto err; + + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto err; - /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) { net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", payload_len); - return false; - } - - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - return false; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (clone == NULL) - return false; - - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - - add_frag_mem_limit(fq->q.net, clone->truesize); - } - - /* morph head into last received skb: prev. - * - * This allows callers of ipv6 conntrack defrag to continue - * to use the last skb(frag) passed into the reasm engine. - * The last skb frag 'silently' turns into the full reassembled skb. - * - * Since prev is also part of q->fragments we have to clone it first. - */ - if (head != prev) { - struct sk_buff *iter; - - fp = skb_clone(prev, GFP_ATOMIC); - if (!fp) - return false; - - fp->next = prev->next; - - iter = head; - while (iter) { - if (iter->next == prev) { - iter->next = fp; - break; - } - iter = iter->next; - } - - skb_morph(prev, head); - prev->next = head->next; - consume_skb(head); - head = prev; + goto err; } /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ - skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_shinfo(head)->frag_list = head->next; - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - for (fp = head->next; fp; fp = fp->next) { - head->data_len += fp->len; - head->len += fp->len; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - head->truesize += fp->truesize; - fp->sk = NULL; - } - sub_frag_mem_limit(fq->q.net, head->truesize); + skb_network_header(skb)[fq->nhoffset] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data); - head->ignore_df = 1; - skb_mark_not_on_list(head); - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; + skb->ignore_df = 1; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->frag_max_size = sizeof(struct ipv6hdr) + fq->q.max_size; /* Yes, and fold redundant checksum back. 8) */ - if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_partial(skb_network_header(head), - skb_network_header_len(head), - head->csum); + if (skb->ip_summed == CHECKSUM_COMPLETE) + skb->csum = csum_partial(skb_network_header(skb), + skb_network_header_len(skb), + skb->csum); fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; - return true; + return 0; + +err: + inet_frag_kill(&fq->q); + return -EINVAL; } /* @@ -542,7 +443,6 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { u16 savethdr = skb->transport_header; - struct net_device *dev = skb->dev; int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; @@ -565,10 +465,6 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) hdr = ipv6_hdr(skb); fhdr = (struct frag_hdr *)skb_transport_header(skb); - if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - return -EINVAL; - skb_orphan(skb); fq = fq_find(net, fhdr->identification, user, hdr, skb->dev ? skb->dev->ifindex : 0); @@ -580,31 +476,17 @@ int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) spin_lock_bh(&fq->q.lock); ret = nf_ct_frag6_queue(fq, skb, fhdr, nhoff); - if (ret < 0) { - if (ret == -EPROTO) { - skb->transport_header = savethdr; - ret = 0; - } - goto out_unlock; + if (ret == -EPROTO) { + skb->transport_header = savethdr; + ret = 0; } /* after queue has assumed skb ownership, only 0 or -EINPROGRESS * must be returned. */ - ret = -EINPROGRESS; - if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) { - unsigned long orefdst = skb->_skb_refdst; - - skb->_skb_refdst = 0UL; - if (nf_ct_frag6_reasm(fq, skb, dev)) - ret = 0; - skb->_skb_refdst = orefdst; - } else { - skb_dst_drop(skb); - } + if (ret) + ret = -EINPROGRESS; -out_unlock: spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q); return ret; diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 7a41ee3c11b4..f0ec31933c15 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -225,7 +225,7 @@ int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, skb->len - hdrlen, 0)); } - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); target.dst.protonum = IPPROTO_ICMPV6; if (!nf_nat_ipv6_manip_pkt(skb, 0, &target, manip)) return 0; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 36a3d8dc61f5..24264d0a4b85 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -69,8 +69,8 @@ static u8 ip6_frag_ecn(const struct ipv6hdr *ipv6h) static struct inet_frags ip6_frags; -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev); +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev); static void ip6_frag_expire(struct timer_list *t) { @@ -111,21 +111,26 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, struct frag_hdr *fhdr, int nhoff, u32 *prob_offset) { - struct sk_buff *prev, *next; - struct net_device *dev; - int offset, end, fragsize; struct net *net = dev_net(skb_dst(skb)->dev); + int offset, end, fragsize; + struct sk_buff *prev_tail; + struct net_device *dev; + int err = -ENOENT; u8 ecn; if (fq->q.flags & INET_FRAG_COMPLETE) goto err; + err = -EINVAL; offset = ntohs(fhdr->frag_off) & ~0x7; end = offset + (ntohs(ipv6_hdr(skb)->payload_len) - ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); + /* note that if prob_offset is set, the skb is freed elsewhere, + * we do not free it here. + */ return -1; } @@ -170,62 +175,27 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, if (end == offset) goto discard_fq; + err = -ENOMEM; /* Point into the IP datagram 'data' part. */ if (!pskb_pull(skb, (u8 *) (fhdr + 1) - skb->data)) goto discard_fq; - if (pskb_trim_rcsum(skb, end - offset)) + err = pskb_trim_rcsum(skb, end - offset); + if (err) goto discard_fq; - /* Find out which fragments are in front and at the back of us - * in the chain of fragments so far. We must know where to put - * this fragment, right? - */ - prev = fq->q.fragments_tail; - if (!prev || prev->ip_defrag_offset < offset) { - next = NULL; - goto found; - } - prev = NULL; - for (next = fq->q.fragments; next != NULL; next = next->next) { - if (next->ip_defrag_offset >= offset) - break; /* bingo! */ - prev = next; - } - -found: - /* RFC5722, Section 4, amended by Errata ID : 3089 - * When reassembling an IPv6 datagram, if - * one or more its constituent fragments is determined to be an - * overlapping fragment, the entire datagram (and any constituent - * fragments) MUST be silently discarded. - */ - - /* Check for overlap with preceding fragment. */ - if (prev && - (prev->ip_defrag_offset + prev->len) > offset) - goto discard_fq; - - /* Look for overlap with succeeding segment. */ - if (next && next->ip_defrag_offset < end) - goto discard_fq; - - /* Note : skb->ip_defrag_offset and skb->sk share the same location */ + /* Note : skb->rbnode and skb->dev share the same location. */ dev = skb->dev; - if (dev) - fq->iif = dev->ifindex; /* Makes sure compiler wont do silly aliasing games */ barrier(); - skb->ip_defrag_offset = offset; - /* Insert this fragment in the chain of fragments. */ - skb->next = next; - if (!next) - fq->q.fragments_tail = skb; - if (prev) - prev->next = skb; - else - fq->q.fragments = skb; + prev_tail = fq->q.fragments_tail; + err = inet_frag_queue_insert(&fq->q, skb, offset, end); + if (err) + goto insert_error; + + if (dev) + fq->iif = dev->ifindex; fq->q.stamp = skb->tstamp; fq->q.meat += skb->len; @@ -246,44 +216,48 @@ found: if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && fq->q.meat == fq->q.len) { - int res; unsigned long orefdst = skb->_skb_refdst; skb->_skb_refdst = 0UL; - res = ip6_frag_reasm(fq, prev, dev); + err = ip6_frag_reasm(fq, skb, prev_tail, dev); skb->_skb_refdst = orefdst; - return res; + return err; } skb_dst_drop(skb); - return -1; + return -EINPROGRESS; +insert_error: + if (err == IPFRAG_DUP) { + kfree_skb(skb); + return -EINVAL; + } + err = -EINVAL; + __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + IPSTATS_MIB_REASM_OVERLAPS); discard_fq: inet_frag_kill(&fq->q); -err: __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_REASMFAILS); +err: kfree_skb(skb); - return -1; + return err; } /* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. */ -static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, - struct net_device *dev) +static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *skb, + struct sk_buff *prev_tail, struct net_device *dev) { struct net *net = container_of(fq->q.net, struct net, ipv6.frags); - struct sk_buff *fp, *head = fq->q.fragments; - int payload_len, delta; unsigned int nhoff; - int sum_truesize; + void *reasm_data; + int payload_len; u8 ecn; inet_frag_kill(&fq->q); @@ -292,121 +266,40 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, if (unlikely(ecn == 0xff)) goto out_fail; - /* Make the one we just received the head. */ - if (prev) { - head = prev->next; - fp = skb_clone(head, GFP_ATOMIC); - - if (!fp) - goto out_oom; - - fp->next = head->next; - if (!fp->next) - fq->q.fragments_tail = fp; - prev->next = fp; - - skb_morph(head, fq->q.fragments); - head->next = fq->q.fragments->next; - - consume_skb(fq->q.fragments); - fq->q.fragments = head; - } - - WARN_ON(head == NULL); - WARN_ON(head->ip_defrag_offset != 0); + reasm_data = inet_frag_reasm_prepare(&fq->q, skb, prev_tail); + if (!reasm_data) + goto out_oom; - /* Unfragmented part is taken from the first segment. */ - payload_len = ((head->data - skb_network_header(head)) - + payload_len = ((skb->data - skb_network_header(skb)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) goto out_oversize; - delta = - head->truesize; - - /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) - goto out_oom; - - delta += head->truesize; - if (delta) - add_frag_mem_limit(fq->q.net, delta); - - /* If the first fragment is fragmented itself, we split - * it to two chunks: the first with data and paged part - * and the second, holding only fragments. */ - if (skb_has_frag_list(head)) { - struct sk_buff *clone; - int i, plen = 0; - - clone = alloc_skb(0, GFP_ATOMIC); - if (!clone) - goto out_oom; - clone->next = head->next; - head->next = clone; - skb_shinfo(clone)->frag_list = skb_shinfo(head)->frag_list; - skb_frag_list_init(head); - for (i = 0; i < skb_shinfo(head)->nr_frags; i++) - plen += skb_frag_size(&skb_shinfo(head)->frags[i]); - clone->len = clone->data_len = head->data_len - plen; - head->data_len -= clone->len; - head->len -= clone->len; - clone->csum = 0; - clone->ip_summed = head->ip_summed; - add_frag_mem_limit(fq->q.net, clone->truesize); - } - /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ nhoff = fq->nhoffset; - skb_network_header(head)[nhoff] = skb_transport_header(head)[0]; - memmove(head->head + sizeof(struct frag_hdr), head->head, - (head->data - head->head) - sizeof(struct frag_hdr)); - if (skb_mac_header_was_set(head)) - head->mac_header += sizeof(struct frag_hdr); - head->network_header += sizeof(struct frag_hdr); - - skb_reset_transport_header(head); - skb_push(head, head->data - skb_network_header(head)); - - sum_truesize = head->truesize; - for (fp = head->next; fp;) { - bool headstolen; - int delta; - struct sk_buff *next = fp->next; - - sum_truesize += fp->truesize; - if (head->ip_summed != fp->ip_summed) - head->ip_summed = CHECKSUM_NONE; - else if (head->ip_summed == CHECKSUM_COMPLETE) - head->csum = csum_add(head->csum, fp->csum); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - fp->sk = NULL; - if (!skb_shinfo(head)->frag_list) - skb_shinfo(head)->frag_list = fp; - head->data_len += fp->len; - head->len += fp->len; - head->truesize += fp->truesize; - } - fp = next; - } - sub_frag_mem_limit(fq->q.net, sum_truesize); + skb_network_header(skb)[nhoff] = skb_transport_header(skb)[0]; + memmove(skb->head + sizeof(struct frag_hdr), skb->head, + (skb->data - skb->head) - sizeof(struct frag_hdr)); + if (skb_mac_header_was_set(skb)) + skb->mac_header += sizeof(struct frag_hdr); + skb->network_header += sizeof(struct frag_hdr); + + skb_reset_transport_header(skb); + + inet_frag_reasm_finish(&fq->q, skb, reasm_data); - skb_mark_not_on_list(head); - head->dev = dev; - head->tstamp = fq->q.stamp; - ipv6_hdr(head)->payload_len = htons(payload_len); - ipv6_change_dsfield(ipv6_hdr(head), 0xff, ecn); - IP6CB(head)->nhoff = nhoff; - IP6CB(head)->flags |= IP6SKB_FRAGMENTED; - IP6CB(head)->frag_max_size = fq->q.max_size; + skb->dev = dev; + ipv6_hdr(skb)->payload_len = htons(payload_len); + ipv6_change_dsfield(ipv6_hdr(skb), 0xff, ecn); + IP6CB(skb)->nhoff = nhoff; + IP6CB(skb)->flags |= IP6SKB_FRAGMENTED; + IP6CB(skb)->frag_max_size = fq->q.max_size; /* Yes, and fold redundant checksum back. 8) */ - skb_postpush_rcsum(head, skb_network_header(head), - skb_network_header_len(head)); + skb_postpush_rcsum(skb, skb_network_header(skb), + skb_network_header_len(skb)); rcu_read_lock(); __IP6_INC_STATS(net, __in6_dev_get(dev), IPSTATS_MIB_REASMOKS); @@ -414,6 +307,7 @@ static int ip6_frag_reasm(struct frag_queue *fq, struct sk_buff *prev, fq->q.fragments = NULL; fq->q.rb_fragments = RB_ROOT; fq->q.fragments_tail = NULL; + fq->q.last_run_head = NULL; return 1; out_oversize: @@ -464,10 +358,6 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return 1; } - if (skb->len - skb_network_offset(skb) < IPV6_MIN_MTU && - fhdr->frag_off & htons(IP6_MF)) - goto fail_hdr; - iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { @@ -485,6 +375,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) if (prob_offset) { __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); + /* icmpv6_param_prob() calls kfree_skb(skb) */ icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); } return ret; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 964491cf3672..dc066fdf7e46 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -4812,6 +4812,73 @@ int rt6_dump_route(struct fib6_info *rt, void *p_arg) arg->cb->nlh->nlmsg_seq, flags); } +static int inet6_rtm_valid_getroute_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rtmsg *rtm; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid header for get route request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv6_policy, extack); + + rtm = nlmsg_data(nlh); + if ((rtm->rtm_src_len && rtm->rtm_src_len != 128) || + (rtm->rtm_dst_len && rtm->rtm_dst_len != 128) || + rtm->rtm_table || rtm->rtm_protocol || rtm->rtm_scope || + rtm->rtm_type) { + NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); + return -EINVAL; + } + if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid flags for get route request"); + return -EINVAL; + } + + err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_ipv6_policy, extack); + if (err) + return err; + + if ((tb[RTA_SRC] && !rtm->rtm_src_len) || + (tb[RTA_DST] && !rtm->rtm_dst_len)) { + NL_SET_ERR_MSG_MOD(extack, "rtm_src_len and rtm_dst_len must be 128 for IPv6"); + return -EINVAL; + } + + for (i = 0; i <= RTA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case RTA_SRC: + case RTA_DST: + case RTA_IIF: + case RTA_OIF: + case RTA_MARK: + case RTA_UID: + case RTA_SPORT: + case RTA_DPORT: + case RTA_IP_PROTO: + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); + return -EINVAL; + } + } + + return 0; +} + static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { @@ -4826,8 +4893,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct flowi6 fl6 = {}; bool fibmatch; - err = nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, rtm_ipv6_policy, - extack); + err = inet6_rtm_valid_getroute_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index b81eb7cb815e..e51cda79f0cc 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1864,7 +1864,7 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) refcount_read(&sp->sk_refcnt), sp, jiffies_to_clock_t(icsk->icsk_rto), jiffies_to_clock_t(icsk->icsk_ack.ato), - (icsk->icsk_ack.quick << 1) | icsk->icsk_ack.pingpong, + (icsk->icsk_ack.quick << 1) | inet_csk_in_pingpong_mode(sp), tp->snd_cwnd, state == TCP_LISTEN ? fastopenq->max_qlen : diff --git a/net/mac80211/agg-tx.c b/net/mac80211/agg-tx.c index 54821fb1a960..2c4cd4183bf9 100644 --- a/net/mac80211/agg-tx.c +++ b/net/mac80211/agg-tx.c @@ -229,7 +229,7 @@ ieee80211_agg_start_txq(struct sta_info *sta, int tid, bool enable) clear_bit(IEEE80211_TXQ_STOP, &txqi->flags); local_bh_disable(); rcu_read_lock(); - drv_wake_tx_queue(sta->sdata->local, txqi); + schedule_and_wake_txq(sta->sdata->local, txqi); rcu_read_unlock(); local_bh_enable(); } diff --git a/net/mac80211/cfg.c b/net/mac80211/cfg.c index 2493c74c2d37..d65aa019ce85 100644 --- a/net/mac80211/cfg.c +++ b/net/mac80211/cfg.c @@ -1231,6 +1231,11 @@ static void sta_apply_mesh_params(struct ieee80211_local *local, ieee80211_mps_sta_status_update(sta); changed |= ieee80211_mps_set_sta_local_pm(sta, sdata->u.mesh.mshcfg.power_mode); + + ewma_mesh_tx_rate_avg_init(&sta->mesh->tx_rate_avg); + /* init at low value */ + ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, 10); + break; case NL80211_PLINK_LISTEN: case NL80211_PLINK_BLOCKED: @@ -1447,6 +1452,9 @@ static int sta_apply_parameters(struct ieee80211_local *local, if (ieee80211_vif_is_mesh(&sdata->vif)) sta_apply_mesh_params(local, sta, params); + if (params->airtime_weight) + sta->airtime_weight = params->airtime_weight; + /* set the STA state after all sta info from usermode has been set */ if (test_sta_flag(sta, WLAN_STA_TDLS_PEER) || set & BIT(NL80211_STA_FLAG_ASSOCIATED)) { @@ -1746,7 +1754,9 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, MPATH_INFO_EXPTIME | MPATH_INFO_DISCOVERY_TIMEOUT | MPATH_INFO_DISCOVERY_RETRIES | - MPATH_INFO_FLAGS; + MPATH_INFO_FLAGS | + MPATH_INFO_HOP_COUNT | + MPATH_INFO_PATH_CHANGE; pinfo->frame_qlen = mpath->frame_queue.qlen; pinfo->sn = mpath->sn; @@ -1766,6 +1776,8 @@ static void mpath_set_pinfo(struct mesh_path *mpath, u8 *next_hop, pinfo->flags |= NL80211_MPATH_FLAG_FIXED; if (mpath->flags & MESH_PATH_RESOLVED) pinfo->flags |= NL80211_MPATH_FLAG_RESOLVED; + pinfo->hop_count = mpath->hop_count; + pinfo->path_change_count = mpath->path_change_count; } static int ieee80211_get_mpath(struct wiphy *wiphy, struct net_device *dev, diff --git a/net/mac80211/debugfs.c b/net/mac80211/debugfs.c index 3fe541e358f3..343ad0a915e4 100644 --- a/net/mac80211/debugfs.c +++ b/net/mac80211/debugfs.c @@ -218,6 +218,7 @@ static const char *hw_flag_names[] = { FLAG(BUFF_MMPDU_TXQ), FLAG(SUPPORTS_VHT_EXT_NSS_BW), FLAG(STA_MMPDU_TXQ), + FLAG(TX_STATUS_NO_AMPDU_LEN), #undef FLAG }; @@ -383,6 +384,9 @@ void debugfs_hw_add(struct ieee80211_local *local) if (local->ops->wake_tx_queue) DEBUGFS_ADD_MODE(aqm, 0600); + debugfs_create_u16("airtime_flags", 0600, + phyd, &local->airtime_flags); + statsd = debugfs_create_dir("statistics", phyd); /* if the dir failed, don't put all the other things into the root! */ diff --git a/net/mac80211/debugfs_sta.c b/net/mac80211/debugfs_sta.c index b753194710ad..3aa618dcc58e 100644 --- a/net/mac80211/debugfs_sta.c +++ b/net/mac80211/debugfs_sta.c @@ -181,9 +181,9 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, txqi->tin.tx_bytes, txqi->tin.tx_packets, txqi->flags, - txqi->flags & (1<<IEEE80211_TXQ_STOP) ? "STOP" : "RUN", - txqi->flags & (1<<IEEE80211_TXQ_AMPDU) ? " AMPDU" : "", - txqi->flags & (1<<IEEE80211_TXQ_NO_AMSDU) ? " NO-AMSDU" : ""); + test_bit(IEEE80211_TXQ_STOP, &txqi->flags) ? "STOP" : "RUN", + test_bit(IEEE80211_TXQ_AMPDU, &txqi->flags) ? " AMPDU" : "", + test_bit(IEEE80211_TXQ_NO_AMSDU, &txqi->flags) ? " NO-AMSDU" : ""); } rcu_read_unlock(); @@ -195,6 +195,64 @@ static ssize_t sta_aqm_read(struct file *file, char __user *userbuf, } STA_OPS(aqm); +static ssize_t sta_airtime_read(struct file *file, char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + size_t bufsz = 200; + char *buf = kzalloc(bufsz, GFP_KERNEL), *p = buf; + u64 rx_airtime = 0, tx_airtime = 0; + s64 deficit[IEEE80211_NUM_ACS]; + ssize_t rv; + int ac; + + if (!buf) + return -ENOMEM; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + rx_airtime += sta->airtime[ac].rx_airtime; + tx_airtime += sta->airtime[ac].tx_airtime; + deficit[ac] = sta->airtime[ac].deficit; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + p += scnprintf(p, bufsz + buf - p, + "RX: %llu us\nTX: %llu us\nWeight: %u\n" + "Deficit: VO: %lld us VI: %lld us BE: %lld us BK: %lld us\n", + rx_airtime, + tx_airtime, + sta->airtime_weight, + deficit[0], + deficit[1], + deficit[2], + deficit[3]); + + rv = simple_read_from_buffer(userbuf, count, ppos, buf, p - buf); + kfree(buf); + return rv; +} + +static ssize_t sta_airtime_write(struct file *file, const char __user *userbuf, + size_t count, loff_t *ppos) +{ + struct sta_info *sta = file->private_data; + struct ieee80211_local *local = sta->sdata->local; + int ac; + + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) { + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].rx_airtime = 0; + sta->airtime[ac].tx_airtime = 0; + sta->airtime[ac].deficit = sta->airtime_weight; + spin_unlock_bh(&local->active_txq_lock[ac]); + } + + return count; +} +STA_OPS_RW(airtime); + static ssize_t sta_agg_status_read(struct file *file, char __user *userbuf, size_t count, loff_t *ppos) { @@ -906,6 +964,10 @@ void ieee80211_sta_debugfs_add(struct sta_info *sta) if (local->ops->wake_tx_queue) DEBUGFS_ADD(aqm); + if (wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + DEBUGFS_ADD(airtime); + if (sizeof(sta->driver_buffered_tids) == sizeof(u32)) debugfs_create_x32("driver_buffered_tids", 0400, sta->debugfs_dir, diff --git a/net/mac80211/driver-ops.h b/net/mac80211/driver-ops.h index 3e0d5922a440..ba3c07b10cd0 100644 --- a/net/mac80211/driver-ops.h +++ b/net/mac80211/driver-ops.h @@ -1173,6 +1173,13 @@ static inline void drv_wake_tx_queue(struct ieee80211_local *local, local->ops->wake_tx_queue(&local->hw, &txq->txq); } +static inline void schedule_and_wake_txq(struct ieee80211_local *local, + struct txq_info *txqi) +{ + ieee80211_schedule_txq(&local->hw, &txqi->txq); + drv_wake_tx_queue(local, txqi); +} + static inline int drv_can_aggregate_in_amsdu(struct ieee80211_local *local, struct sk_buff *head, struct sk_buff *skb) diff --git a/net/mac80211/ht.c b/net/mac80211/ht.c index f849ea814993..e03c46ac8e4d 100644 --- a/net/mac80211/ht.c +++ b/net/mac80211/ht.c @@ -107,6 +107,14 @@ void ieee80211_apply_htcap_overrides(struct ieee80211_sub_if_data *sdata, __check_htcap_enable(ht_capa, ht_capa_mask, ht_cap, IEEE80211_HT_CAP_40MHZ_INTOLERANT); + /* Allow user to enable TX STBC bit */ + __check_htcap_enable(ht_capa, ht_capa_mask, ht_cap, + IEEE80211_HT_CAP_TX_STBC); + + /* Allow user to configure RX STBC bits */ + if (ht_capa_mask->cap_info & IEEE80211_HT_CAP_RX_STBC) + ht_cap->cap |= ht_capa->cap_info & IEEE80211_HT_CAP_RX_STBC; + /* Allow user to decrease AMPDU factor */ if (ht_capa_mask->ampdu_params_info & IEEE80211_HT_AMPDU_PARM_FACTOR) { diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index 7dfb4e2f98b2..056b16bce3b0 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -831,6 +831,8 @@ enum txq_info_flags { * a fq_flow which is already owned by a different tin * @def_cvars: codel vars for @def_flow * @frags: used to keep fragments created after dequeue + * @schedule_order: used with ieee80211_local->active_txqs + * @schedule_round: counter to prevent infinite loops on TXQ scheduling */ struct txq_info { struct fq_tin tin; @@ -838,6 +840,8 @@ struct txq_info { struct codel_vars def_cvars; struct codel_stats cstats; struct sk_buff_head frags; + struct list_head schedule_order; + u16 schedule_round; unsigned long flags; /* keep last! */ @@ -1129,6 +1133,13 @@ struct ieee80211_local { struct codel_vars *cvars; struct codel_params cparams; + /* protects active_txqs and txqi->schedule_order */ + spinlock_t active_txq_lock[IEEE80211_NUM_ACS]; + struct list_head active_txqs[IEEE80211_NUM_ACS]; + u16 schedule_round[IEEE80211_NUM_ACS]; + + u16 airtime_flags; + const struct ieee80211_ops *ops; /* diff --git a/net/mac80211/main.c b/net/mac80211/main.c index 87a729926734..71005b6dfcd1 100644 --- a/net/mac80211/main.c +++ b/net/mac80211/main.c @@ -478,6 +478,8 @@ static const struct ieee80211_ht_cap mac80211_ht_capa_mod_mask = { IEEE80211_HT_CAP_MAX_AMSDU | IEEE80211_HT_CAP_SGI_20 | IEEE80211_HT_CAP_SGI_40 | + IEEE80211_HT_CAP_TX_STBC | + IEEE80211_HT_CAP_RX_STBC | IEEE80211_HT_CAP_LDPC_CODING | IEEE80211_HT_CAP_40MHZ_INTOLERANT), .mcs = { @@ -663,6 +665,12 @@ struct ieee80211_hw *ieee80211_alloc_hw_nm(size_t priv_data_len, spin_lock_init(&local->rx_path_lock); spin_lock_init(&local->queue_stop_reason_lock); + for (i = 0; i < IEEE80211_NUM_ACS; i++) { + INIT_LIST_HEAD(&local->active_txqs[i]); + spin_lock_init(&local->active_txq_lock[i]); + } + local->airtime_flags = AIRTIME_USE_TX | AIRTIME_USE_RX; + INIT_LIST_HEAD(&local->chanctx_list); mutex_init(&local->chanctx_mtx); @@ -1148,6 +1156,9 @@ int ieee80211_register_hw(struct ieee80211_hw *hw) if (!local->hw.max_nan_de_entries) local->hw.max_nan_de_entries = IEEE80211_MAX_NAN_INSTANCE_ID; + if (!local->hw.weight_multiplier) + local->hw.weight_multiplier = 1; + result = ieee80211_wep_init(local); if (result < 0) wiphy_debug(local->hw.wiphy, "Failed to initialize wep: %d\n", diff --git a/net/mac80211/mesh.h b/net/mac80211/mesh.h index cad6592c52a1..8b26858ab4d5 100644 --- a/net/mac80211/mesh.h +++ b/net/mac80211/mesh.h @@ -94,6 +94,7 @@ enum mesh_deferred_task_flags { * @last_preq_to_root: Timestamp of last PREQ sent to root * @is_root: the destination station of this path is a root node * @is_gate: the destination station of this path is a mesh gate + * @path_change_count: the number of path changes to destination * * * The dst address is unique in the mesh path table. Since the mesh_path is @@ -124,6 +125,7 @@ struct mesh_path { unsigned long last_preq_to_root; bool is_root; bool is_gate; + u32 path_change_count; }; /** diff --git a/net/mac80211/mesh_hwmp.c b/net/mac80211/mesh_hwmp.c index 6950cd0bf594..e00284afdda5 100644 --- a/net/mac80211/mesh_hwmp.c +++ b/net/mac80211/mesh_hwmp.c @@ -300,6 +300,7 @@ void ieee80211s_update_metric(struct ieee80211_local *local, { struct ieee80211_tx_info *txinfo = st->info; int failed; + struct rate_info rinfo; failed = !(txinfo->flags & IEEE80211_TX_STAT_ACK); @@ -310,12 +311,15 @@ void ieee80211s_update_metric(struct ieee80211_local *local, if (ewma_mesh_fail_avg_read(&sta->mesh->fail_avg) > LINK_FAIL_THRESH) mesh_plink_broken(sta); + + sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo); + ewma_mesh_tx_rate_avg_add(&sta->mesh->tx_rate_avg, + cfg80211_calculate_bitrate(&rinfo)); } static u32 airtime_link_metric_get(struct ieee80211_local *local, struct sta_info *sta) { - struct rate_info rinfo; /* This should be adjusted for each device */ int device_constant = 1 << ARITH_SHIFT; int test_frame_len = TEST_FRAME_LEN << ARITH_SHIFT; @@ -339,8 +343,7 @@ static u32 airtime_link_metric_get(struct ieee80211_local *local, if (fail_avg > LINK_FAIL_THRESH) return MAX_METRIC; - sta_set_rate_info_tx(sta, &sta->tx_stats.last_rate, &rinfo); - rate = cfg80211_calculate_bitrate(&rinfo); + rate = ewma_mesh_tx_rate_avg_read(&sta->mesh->tx_rate_avg); if (WARN_ON(!rate)) return MAX_METRIC; @@ -386,6 +389,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, unsigned long orig_lifetime, exp_time; u32 last_hop_metric, new_metric; bool process = true; + u8 hopcount; rcu_read_lock(); sta = sta_info_get(sdata, mgmt->sa); @@ -404,6 +408,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, orig_sn = PREQ_IE_ORIG_SN(hwmp_ie); orig_lifetime = PREQ_IE_LIFETIME(hwmp_ie); orig_metric = PREQ_IE_METRIC(hwmp_ie); + hopcount = PREQ_IE_HOPCOUNT(hwmp_ie) + 1; break; case MPATH_PREP: /* Originator here refers to the MP that was the target in the @@ -415,6 +420,7 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, orig_sn = PREP_IE_TARGET_SN(hwmp_ie); orig_lifetime = PREP_IE_LIFETIME(hwmp_ie); orig_metric = PREP_IE_METRIC(hwmp_ie); + hopcount = PREP_IE_HOPCOUNT(hwmp_ie) + 1; break; default: rcu_read_unlock(); @@ -441,7 +447,10 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, (mpath->flags & MESH_PATH_SN_VALID)) { if (SN_GT(mpath->sn, orig_sn) || (mpath->sn == orig_sn && - new_metric >= mpath->metric)) { + (rcu_access_pointer(mpath->next_hop) != + sta ? + mult_frac(new_metric, 10, 9) : + new_metric) >= mpath->metric)) { process = false; fresh_info = false; } @@ -476,12 +485,15 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, } if (fresh_info) { + if (rcu_access_pointer(mpath->next_hop) != sta) + mpath->path_change_count++; mesh_path_assign_nexthop(mpath, sta); mpath->flags |= MESH_PATH_SN_VALID; mpath->metric = new_metric; mpath->sn = orig_sn; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; + mpath->hop_count = hopcount; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); ewma_mesh_fail_avg_init(&sta->mesh->fail_avg); @@ -506,8 +518,10 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, if (mpath) { spin_lock_bh(&mpath->state_lock); if ((mpath->flags & MESH_PATH_FIXED) || - ((mpath->flags & MESH_PATH_ACTIVE) && - (last_hop_metric > mpath->metric))) + ((mpath->flags & MESH_PATH_ACTIVE) && + ((rcu_access_pointer(mpath->next_hop) != sta ? + mult_frac(last_hop_metric, 10, 9) : + last_hop_metric) > mpath->metric))) fresh_info = false; } else { mpath = mesh_path_add(sdata, ta); @@ -519,10 +533,13 @@ static u32 hwmp_route_info_get(struct ieee80211_sub_if_data *sdata, } if (fresh_info) { + if (rcu_access_pointer(mpath->next_hop) != sta) + mpath->path_change_count++; mesh_path_assign_nexthop(mpath, sta); mpath->metric = last_hop_metric; mpath->exp_time = time_after(mpath->exp_time, exp_time) ? mpath->exp_time : exp_time; + mpath->hop_count = 1; mesh_path_activate(mpath); spin_unlock_bh(&mpath->state_lock); ewma_mesh_fail_avg_init(&sta->mesh->fail_avg); diff --git a/net/mac80211/rc80211_minstrel_ht.c b/net/mac80211/rc80211_minstrel_ht.c index f466ec37d161..ccaf951e4e31 100644 --- a/net/mac80211/rc80211_minstrel_ht.c +++ b/net/mac80211/rc80211_minstrel_ht.c @@ -294,6 +294,15 @@ minstrel_get_ratestats(struct minstrel_ht_sta *mi, int index) return &mi->groups[index / MCS_GROUP_RATES].rates[index % MCS_GROUP_RATES]; } +static unsigned int +minstrel_ht_avg_ampdu_len(struct minstrel_ht_sta *mi) +{ + if (!mi->avg_ampdu_len) + return AVG_AMPDU_SIZE; + + return MINSTREL_TRUNC(mi->avg_ampdu_len); +} + /* * Return current throughput based on the average A-MPDU length, taking into * account the expected number of retransmissions and their expected length @@ -309,7 +318,7 @@ minstrel_ht_get_tp_avg(struct minstrel_ht_sta *mi, int group, int rate, return 0; if (group != MINSTREL_CCK_GROUP) - nsecs = 1000 * mi->overhead / MINSTREL_TRUNC(mi->avg_ampdu_len); + nsecs = 1000 * mi->overhead / minstrel_ht_avg_ampdu_len(mi); nsecs += minstrel_mcs_groups[group].duration[rate] << minstrel_mcs_groups[group].shift; @@ -503,8 +512,12 @@ minstrel_ht_update_stats(struct minstrel_priv *mp, struct minstrel_ht_sta *mi) u16 tmp_cck_tp_rate[MAX_THR_RATES], index; if (mi->ampdu_packets > 0) { - mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, - MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), EWMA_LEVEL); + if (!ieee80211_hw_check(mp->hw, TX_STATUS_NO_AMPDU_LEN)) + mi->avg_ampdu_len = minstrel_ewma(mi->avg_ampdu_len, + MINSTREL_FRAC(mi->ampdu_len, mi->ampdu_packets), + EWMA_LEVEL); + else + mi->avg_ampdu_len = 0; mi->ampdu_len = 0; mi->ampdu_packets = 0; } @@ -709,7 +722,9 @@ minstrel_ht_tx_status(void *priv, struct ieee80211_supported_band *sband, mi->ampdu_len += info->status.ampdu_len; if (!mi->sample_wait && !mi->sample_tries && mi->sample_count > 0) { - mi->sample_wait = 16 + 2 * MINSTREL_TRUNC(mi->avg_ampdu_len); + int avg_ampdu_len = minstrel_ht_avg_ampdu_len(mi); + + mi->sample_wait = 16 + 2 * avg_ampdu_len; mi->sample_tries = 1; mi->sample_count--; } @@ -777,7 +792,7 @@ minstrel_calc_retransmit(struct minstrel_priv *mp, struct minstrel_ht_sta *mi, unsigned int cw = mp->cw_min; unsigned int ctime = 0; unsigned int t_slot = 9; /* FIXME */ - unsigned int ampdu_len = MINSTREL_TRUNC(mi->avg_ampdu_len); + unsigned int ampdu_len = minstrel_ht_avg_ampdu_len(mi); unsigned int overhead = 0, overhead_rtscts = 0; mrs = minstrel_get_ratestats(mi, index); diff --git a/net/mac80211/rc80211_minstrel_ht_debugfs.c b/net/mac80211/rc80211_minstrel_ht_debugfs.c index 57820a5f2c16..31641d0b0f5c 100644 --- a/net/mac80211/rc80211_minstrel_ht_debugfs.c +++ b/net/mac80211/rc80211_minstrel_ht_debugfs.c @@ -160,9 +160,10 @@ minstrel_ht_stats_open(struct inode *inode, struct file *file) "lookaround %d\n", max(0, (int) mi->total_packets - (int) mi->sample_packets), mi->sample_packets); - p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", - MINSTREL_TRUNC(mi->avg_ampdu_len), - MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); + if (mi->avg_ampdu_len) + p += sprintf(p, "Average # of aggregated frames per A-MPDU: %d.%d\n", + MINSTREL_TRUNC(mi->avg_ampdu_len), + MINSTREL_TRUNC(mi->avg_ampdu_len * 10) % 10); ms->len = p - ms->buf; WARN_ON(ms->len + sizeof(*ms) > 32768); diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c index c4a8f115ed33..11f058987a54 100644 --- a/net/mac80211/sta_info.c +++ b/net/mac80211/sta_info.c @@ -90,7 +90,6 @@ static void __cleanup_single_sta(struct sta_info *sta) struct tid_ampdu_tx *tid_tx; struct ieee80211_sub_if_data *sdata = sta->sdata; struct ieee80211_local *local = sdata->local; - struct fq *fq = &local->fq; struct ps_data *ps; if (test_sta_flag(sta, WLAN_STA_PS_STA) || @@ -120,9 +119,7 @@ static void __cleanup_single_sta(struct sta_info *sta) txqi = to_txq_info(sta->sta.txq[i]); - spin_lock_bh(&fq->lock); ieee80211_txq_purge(local, txqi); - spin_unlock_bh(&fq->lock); } } @@ -387,9 +384,12 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata, if (sta_prepare_rate_control(local, sta, gfp)) goto free_txq; + sta->airtime_weight = IEEE80211_DEFAULT_AIRTIME_WEIGHT; + for (i = 0; i < IEEE80211_NUM_ACS; i++) { skb_queue_head_init(&sta->ps_tx_buf[i]); skb_queue_head_init(&sta->tx_filtered[i]); + sta->airtime[i].deficit = sta->airtime_weight; } for (i = 0; i < IEEE80211_NUM_TIDS; i++) @@ -1249,7 +1249,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta) if (!sta->sta.txq[i] || !txq_has_queue(sta->sta.txq[i])) continue; - drv_wake_tx_queue(local, to_txq_info(sta->sta.txq[i])); + schedule_and_wake_txq(local, to_txq_info(sta->sta.txq[i])); } skb_queue_head_init(&pending); @@ -1826,6 +1826,27 @@ void ieee80211_sta_set_buffered(struct ieee80211_sta *pubsta, } EXPORT_SYMBOL(ieee80211_sta_set_buffered); +void ieee80211_sta_register_airtime(struct ieee80211_sta *pubsta, u8 tid, + u32 tx_airtime, u32 rx_airtime) +{ + struct sta_info *sta = container_of(pubsta, struct sta_info, sta); + struct ieee80211_local *local = sta->sdata->local; + u8 ac = ieee80211_ac_from_tid(tid); + u32 airtime = 0; + + if (sta->local->airtime_flags & AIRTIME_USE_TX) + airtime += tx_airtime; + if (sta->local->airtime_flags & AIRTIME_USE_RX) + airtime += rx_airtime; + + spin_lock_bh(&local->active_txq_lock[ac]); + sta->airtime[ac].tx_airtime += tx_airtime; + sta->airtime[ac].rx_airtime += rx_airtime; + sta->airtime[ac].deficit -= airtime; + spin_unlock_bh(&local->active_txq_lock[ac]); +} +EXPORT_SYMBOL(ieee80211_sta_register_airtime); + int sta_info_move_state(struct sta_info *sta, enum ieee80211_sta_state new_state) { @@ -2188,6 +2209,23 @@ void sta_set_sinfo(struct sta_info *sta, struct station_info *sinfo, sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_FAILED); } + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_RX_DURATION))) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->rx_duration += sta->airtime[ac].rx_airtime; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_RX_DURATION); + } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_TX_DURATION))) { + for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) + sinfo->tx_duration += sta->airtime[ac].tx_airtime; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_TX_DURATION); + } + + if (!(sinfo->filled & BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT))) { + sinfo->airtime_weight = sta->airtime_weight; + sinfo->filled |= BIT_ULL(NL80211_STA_INFO_AIRTIME_WEIGHT); + } + sinfo->rx_dropped_misc = sta->rx_stats.dropped; if (sta->pcpu_rx_stats) { for_each_possible_cpu(cpu) { diff --git a/net/mac80211/sta_info.h b/net/mac80211/sta_info.h index 8eb29041be54..71f7e4973329 100644 --- a/net/mac80211/sta_info.h +++ b/net/mac80211/sta_info.h @@ -127,6 +127,16 @@ enum ieee80211_agg_stop_reason { AGG_STOP_DESTROY_STA, }; +/* Debugfs flags to enable/disable use of RX/TX airtime in scheduler */ +#define AIRTIME_USE_TX BIT(0) +#define AIRTIME_USE_RX BIT(1) + +struct airtime_info { + u64 rx_airtime; + u64 tx_airtime; + s64 deficit; +}; + struct sta_info; /** @@ -343,6 +353,7 @@ struct ieee80211_fast_rx { /* we use only values in the range 0-100, so pick a large precision */ DECLARE_EWMA(mesh_fail_avg, 20, 8) +DECLARE_EWMA(mesh_tx_rate_avg, 8, 16) /** * struct mesh_sta - mesh STA information @@ -366,6 +377,7 @@ DECLARE_EWMA(mesh_fail_avg, 20, 8) * processed * @connected_to_gate: true if mesh STA has a path to a mesh gate * @fail_avg: moving percentage of failed MSDUs + * @tx_rate_avg: moving average of tx bitrate */ struct mesh_sta { struct timer_list plink_timer; @@ -394,6 +406,8 @@ struct mesh_sta { /* moving percentage of failed MSDUs */ struct ewma_mesh_fail_avg fail_avg; + /* moving average of tx bitrate */ + struct ewma_mesh_tx_rate_avg tx_rate_avg; }; DECLARE_EWMA(signal, 10, 8) @@ -459,6 +473,9 @@ struct ieee80211_sta_rx_stats { * @last_seq_ctrl: last received seq/frag number from this STA (per TID * plus one for non-QoS frames) * @tid_seq: per-TID sequence numbers for sending to this STA + * @airtime: per-AC struct airtime_info describing airtime statistics for this + * station + * @airtime_weight: station weight for airtime fairness calculation purposes * @ampdu_mlme: A-MPDU state machine state * @mesh: mesh STA information * @debugfs_dir: debug filesystem directory dentry @@ -480,10 +497,28 @@ struct ieee80211_sta_rx_stats { * @tdls_chandef: a TDLS peer can have a wider chandef that is compatible to * the BSS one. * @tx_stats: TX statistics + * @tx_stats.packets: # of packets transmitted + * @tx_stats.bytes: # of bytes in all packets transmitted + * @tx_stats.last_rate: last TX rate + * @tx_stats.msdu: # of transmitted MSDUs per TID * @rx_stats: RX statistics + * @rx_stats_avg: averaged RX statistics + * @rx_stats_avg.signal: averaged signal + * @rx_stats_avg.chain_signal: averaged per-chain signal * @pcpu_rx_stats: per-CPU RX statistics, assigned only if the driver needs * this (by advertising the USES_RSS hw flag) * @status_stats: TX status statistics + * @status_stats.filtered: # of filtered frames + * @status_stats.retry_failed: # of frames that failed after retry + * @status_stats.retry_count: # of retries attempted + * @status_stats.lost_packets: # of lost packets + * @status_stats.last_tdls_pkt_time: timestamp of last TDLS packet + * @status_stats.msdu_retries: # of MSDU retries + * @status_stats.msdu_failed: # of failed MSDUs + * @status_stats.last_ack: last ack timestamp (jiffies) + * @status_stats.last_ack_signal: last ACK signal + * @status_stats.ack_signal_filled: last ACK signal validity + * @status_stats.avg_ack_signal: average ACK signal */ struct sta_info { /* General information, mostly static */ @@ -565,6 +600,9 @@ struct sta_info { } tx_stats; u16 tid_seq[IEEE80211_QOS_CTL_TID_MASK + 1]; + struct airtime_info airtime[IEEE80211_NUM_ACS]; + u16 airtime_weight; + /* * Aggregation information, locked with lock. */ diff --git a/net/mac80211/status.c b/net/mac80211/status.c index 3f0b96e1e02f..5b9952b1caf3 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -823,6 +823,12 @@ static void __ieee80211_tx_status(struct ieee80211_hw *hw, ieee80211_sta_tx_notify(sta->sdata, (void *) skb->data, acked, info->status.tx_time); + if (info->status.tx_time && + wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + ieee80211_sta_register_airtime(&sta->sta, tid, + info->status.tx_time, 0); + if (ieee80211_hw_check(&local->hw, REPORTS_TX_ACK_STATUS)) { if (info->flags & IEEE80211_TX_STAT_ACK) { if (sta->status_stats.lost_packets) diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c index 928f13a208b0..8a49a74c0a37 100644 --- a/net/mac80211/tx.c +++ b/net/mac80211/tx.c @@ -1449,6 +1449,7 @@ void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata, codel_vars_init(&txqi->def_cvars); codel_stats_init(&txqi->cstats); __skb_queue_head_init(&txqi->frags); + INIT_LIST_HEAD(&txqi->schedule_order); txqi->txq.vif = &sdata->vif; @@ -1487,8 +1488,14 @@ void ieee80211_txq_purge(struct ieee80211_local *local, struct fq *fq = &local->fq; struct fq_tin *tin = &txqi->tin; + spin_lock_bh(&fq->lock); fq_tin_reset(fq, tin, fq_skb_free_func); ieee80211_purge_tx_queue(&local->hw, &txqi->frags); + spin_unlock_bh(&fq->lock); + + spin_lock_bh(&local->active_txq_lock[txqi->txq.ac]); + list_del_init(&txqi->schedule_order); + spin_unlock_bh(&local->active_txq_lock[txqi->txq.ac]); } void ieee80211_txq_set_params(struct ieee80211_local *local) @@ -1605,7 +1612,7 @@ static bool ieee80211_queue_skb(struct ieee80211_local *local, ieee80211_txq_enqueue(local, txqi, skb); spin_unlock_bh(&fq->lock); - drv_wake_tx_queue(local, txqi); + schedule_and_wake_txq(local, txqi); return true; } @@ -3636,6 +3643,151 @@ out: } EXPORT_SYMBOL(ieee80211_tx_dequeue); +struct ieee80211_txq *ieee80211_next_txq(struct ieee80211_hw *hw, u8 ac) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = NULL; + + lockdep_assert_held(&local->active_txq_lock[ac]); + + begin: + txqi = list_first_entry_or_null(&local->active_txqs[ac], + struct txq_info, + schedule_order); + if (!txqi) + return NULL; + + if (txqi->txq.sta) { + struct sta_info *sta = container_of(txqi->txq.sta, + struct sta_info, sta); + + if (sta->airtime[txqi->txq.ac].deficit < 0) { + sta->airtime[txqi->txq.ac].deficit += + sta->airtime_weight; + list_move_tail(&txqi->schedule_order, + &local->active_txqs[txqi->txq.ac]); + goto begin; + } + } + + + if (txqi->schedule_round == local->schedule_round[ac]) + return NULL; + + list_del_init(&txqi->schedule_order); + txqi->schedule_round = local->schedule_round[ac]; + return &txqi->txq; +} +EXPORT_SYMBOL(ieee80211_next_txq); + +void ieee80211_return_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *txqi = to_txq_info(txq); + + lockdep_assert_held(&local->active_txq_lock[txq->ac]); + + if (list_empty(&txqi->schedule_order) && + (!skb_queue_empty(&txqi->frags) || txqi->tin.backlog_packets)) { + /* If airtime accounting is active, always enqueue STAs at the + * head of the list to ensure that they only get moved to the + * back by the airtime DRR scheduler once they have a negative + * deficit. A station that already has a negative deficit will + * get immediately moved to the back of the list on the next + * call to ieee80211_next_txq(). + */ + if (txqi->txq.sta && + wiphy_ext_feature_isset(local->hw.wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + list_add(&txqi->schedule_order, + &local->active_txqs[txq->ac]); + else + list_add_tail(&txqi->schedule_order, + &local->active_txqs[txq->ac]); + } +} +EXPORT_SYMBOL(ieee80211_return_txq); + +void ieee80211_schedule_txq(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) + __acquires(txq_lock) __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->active_txq_lock[txq->ac]); + ieee80211_return_txq(hw, txq); + spin_unlock_bh(&local->active_txq_lock[txq->ac]); +} +EXPORT_SYMBOL(ieee80211_schedule_txq); + +bool ieee80211_txq_may_transmit(struct ieee80211_hw *hw, + struct ieee80211_txq *txq) +{ + struct ieee80211_local *local = hw_to_local(hw); + struct txq_info *iter, *tmp, *txqi = to_txq_info(txq); + struct sta_info *sta; + u8 ac = txq->ac; + + lockdep_assert_held(&local->active_txq_lock[ac]); + + if (!txqi->txq.sta) + goto out; + + if (list_empty(&txqi->schedule_order)) + goto out; + + list_for_each_entry_safe(iter, tmp, &local->active_txqs[ac], + schedule_order) { + if (iter == txqi) + break; + + if (!iter->txq.sta) { + list_move_tail(&iter->schedule_order, + &local->active_txqs[ac]); + continue; + } + sta = container_of(iter->txq.sta, struct sta_info, sta); + if (sta->airtime[ac].deficit < 0) + sta->airtime[ac].deficit += sta->airtime_weight; + list_move_tail(&iter->schedule_order, &local->active_txqs[ac]); + } + + sta = container_of(txqi->txq.sta, struct sta_info, sta); + if (sta->airtime[ac].deficit >= 0) + goto out; + + sta->airtime[ac].deficit += sta->airtime_weight; + list_move_tail(&txqi->schedule_order, &local->active_txqs[ac]); + + return false; +out: + if (!list_empty(&txqi->schedule_order)) + list_del_init(&txqi->schedule_order); + + return true; +} +EXPORT_SYMBOL(ieee80211_txq_may_transmit); + +void ieee80211_txq_schedule_start(struct ieee80211_hw *hw, u8 ac) + __acquires(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_lock_bh(&local->active_txq_lock[ac]); + local->schedule_round[ac]++; +} +EXPORT_SYMBOL(ieee80211_txq_schedule_start); + +void ieee80211_txq_schedule_end(struct ieee80211_hw *hw, u8 ac) + __releases(txq_lock) +{ + struct ieee80211_local *local = hw_to_local(hw); + + spin_unlock_bh(&local->active_txq_lock[ac]); +} +EXPORT_SYMBOL(ieee80211_txq_schedule_end); + void __ieee80211_subif_start_xmit(struct sk_buff *skb, struct net_device *dev, u32 info_flags) diff --git a/net/mpls/af_mpls.c b/net/mpls/af_mpls.c index 7d55d4c04088..2662a23c658e 100644 --- a/net/mpls/af_mpls.c +++ b/net/mpls/af_mpls.c @@ -1209,21 +1209,57 @@ static const struct nla_policy devconf_mpls_policy[NETCONFA_MAX + 1] = { [NETCONFA_IFINDEX] = { .len = sizeof(int) }, }; +static int mpls_netconf_valid_get_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(struct netconfmsg))) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid header for netconf get request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(struct netconfmsg), tb, + NETCONFA_MAX, devconf_mpls_policy, extack); + + err = nlmsg_parse_strict(nlh, sizeof(struct netconfmsg), tb, + NETCONFA_MAX, devconf_mpls_policy, extack); + if (err) + return err; + + for (i = 0; i <= NETCONFA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case NETCONFA_IFINDEX: + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in netconf get request"); + return -EINVAL; + } + } + + return 0; +} + static int mpls_netconf_get_devconf(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct netlink_ext_ack *extack) { struct net *net = sock_net(in_skb->sk); struct nlattr *tb[NETCONFA_MAX + 1]; - struct netconfmsg *ncm; struct net_device *dev; struct mpls_dev *mdev; struct sk_buff *skb; int ifindex; int err; - err = nlmsg_parse(nlh, sizeof(*ncm), tb, NETCONFA_MAX, - devconf_mpls_policy, extack); + err = mpls_netconf_valid_get_req(in_skb, nlh, tb, extack); if (err < 0) goto errout; @@ -2236,6 +2272,64 @@ errout: rtnl_set_sk_err(net, RTNLGRP_MPLS_ROUTE, err); } +static int mpls_valid_getroute_req(struct sk_buff *skb, + const struct nlmsghdr *nlh, + struct nlattr **tb, + struct netlink_ext_ack *extack) +{ + struct rtmsg *rtm; + int i, err; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*rtm))) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid header for get route request"); + return -EINVAL; + } + + if (!netlink_strict_get_check(skb)) + return nlmsg_parse(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_mpls_policy, extack); + + rtm = nlmsg_data(nlh); + if ((rtm->rtm_dst_len && rtm->rtm_dst_len != 20) || + rtm->rtm_src_len || rtm->rtm_tos || rtm->rtm_table || + rtm->rtm_protocol || rtm->rtm_scope || rtm->rtm_type) { + NL_SET_ERR_MSG_MOD(extack, "Invalid values in header for get route request"); + return -EINVAL; + } + if (rtm->rtm_flags & ~RTM_F_FIB_MATCH) { + NL_SET_ERR_MSG_MOD(extack, + "Invalid flags for get route request"); + return -EINVAL; + } + + err = nlmsg_parse_strict(nlh, sizeof(*rtm), tb, RTA_MAX, + rtm_mpls_policy, extack); + if (err) + return err; + + if ((tb[RTA_DST] || tb[RTA_NEWDST]) && !rtm->rtm_dst_len) { + NL_SET_ERR_MSG_MOD(extack, "rtm_dst_len must be 20 for MPLS"); + return -EINVAL; + } + + for (i = 0; i <= RTA_MAX; i++) { + if (!tb[i]) + continue; + + switch (i) { + case RTA_DST: + case RTA_NEWDST: + break; + default: + NL_SET_ERR_MSG_MOD(extack, "Unsupported attribute in get route request"); + return -EINVAL; + } + } + + return 0; +} + static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, struct netlink_ext_ack *extack) { @@ -2255,8 +2349,7 @@ static int mpls_getroute(struct sk_buff *in_skb, struct nlmsghdr *in_nlh, u8 n_labels; int err; - err = nlmsg_parse(in_nlh, sizeof(*rtm), tb, RTA_MAX, - rtm_mpls_policy, extack); + err = mpls_valid_getroute_req(in_skb, in_nlh, tb, extack); if (err < 0) goto errout; diff --git a/net/mpls/mpls_iptunnel.c b/net/mpls/mpls_iptunnel.c index 94f53a9b7d1a..dda8930f20e7 100644 --- a/net/mpls/mpls_iptunnel.c +++ b/net/mpls/mpls_iptunnel.c @@ -183,8 +183,8 @@ static int mpls_build_state(struct nlattr *nla, &n_labels, NULL, extack)) return -EINVAL; - newts = lwtunnel_state_alloc(sizeof(*tun_encap_info) + - n_labels * sizeof(u32)); + newts = lwtunnel_state_alloc(struct_size(tun_encap_info, label, + n_labels)); if (!newts) return -ENOMEM; diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index beb3a69ce1d4..fefd63a243f2 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -174,7 +174,7 @@ config NF_CT_PROTO_DCCP If unsure, say Y. config NF_CT_PROTO_GRE - tristate + bool config NF_CT_PROTO_SCTP bool 'SCTP protocol connection tracking support' diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index 1ae65a314d7a..e66067befa42 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -13,6 +13,7 @@ nf_conntrack-$(CONFIG_NF_CONNTRACK_EVENTS) += nf_conntrack_ecache.o nf_conntrack-$(CONFIG_NF_CONNTRACK_LABELS) += nf_conntrack_labels.o nf_conntrack-$(CONFIG_NF_CT_PROTO_DCCP) += nf_conntrack_proto_dccp.o nf_conntrack-$(CONFIG_NF_CT_PROTO_SCTP) += nf_conntrack_proto_sctp.o +nf_conntrack-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o obj-$(CONFIG_NETFILTER) = netfilter.o @@ -25,8 +26,6 @@ obj-$(CONFIG_NETFILTER_NETLINK_OSF) += nfnetlink_osf.o # connection tracking obj-$(CONFIG_NF_CONNTRACK) += nf_conntrack.o -obj-$(CONFIG_NF_CT_PROTO_GRE) += nf_conntrack_proto_gre.o - # netlink interface for nf_conntrack obj-$(CONFIG_NF_CT_NETLINK) += nf_conntrack_netlink.o obj-$(CONFIG_NF_CT_NETLINK_TIMEOUT) += nfnetlink_cttimeout.o diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 235205c93e14..43bbaa32b1d6 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -53,6 +53,7 @@ #endif #include <net/ip_vs.h> +#include <linux/indirect_call_wrapper.h> EXPORT_SYMBOL(register_ip_vs_scheduler); @@ -70,6 +71,29 @@ EXPORT_SYMBOL(ip_vs_get_debug_level); #endif EXPORT_SYMBOL(ip_vs_new_conn_out); +#ifdef CONFIG_IP_VS_PROTO_TCP +INDIRECT_CALLABLE_DECLARE(int + tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)); +#endif + +#ifdef CONFIG_IP_VS_PROTO_UDP +INDIRECT_CALLABLE_DECLARE(int + udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, + struct ip_vs_conn *cp, struct ip_vs_iphdr *iph)); +#endif + +#if defined(CONFIG_IP_VS_PROTO_TCP) && defined(CONFIG_IP_VS_PROTO_UDP) +#define SNAT_CALL(f, ...) \ + INDIRECT_CALL_2(f, tcp_snat_handler, udp_snat_handler, __VA_ARGS__) +#elif defined(CONFIG_IP_VS_PROTO_TCP) +#define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, tcp_snat_handler, __VA_ARGS__) +#elif defined(CONFIG_IP_VS_PROTO_UDP) +#define SNAT_CALL(f, ...) INDIRECT_CALL_1(f, udp_snat_handler, __VA_ARGS__) +#else +#define SNAT_CALL(f, ...) f(__VA_ARGS__) +#endif + static unsigned int ip_vs_net_id __read_mostly; /* netns cnt used for uniqueness */ static atomic_t ipvs_netns_cnt = ATOMIC_INIT(0); @@ -478,7 +502,9 @@ ip_vs_schedule(struct ip_vs_service *svc, struct sk_buff *skb, */ if ((!skb->dev || skb->dev->flags & IFF_LOOPBACK)) { iph->hdr_flags ^= IP_VS_HDR_INVERSE; - cp = pp->conn_in_get(svc->ipvs, svc->af, skb, iph); + cp = INDIRECT_CALL_1(pp->conn_in_get, + ip_vs_conn_in_get_proto, svc->ipvs, + svc->af, skb, iph); iph->hdr_flags ^= IP_VS_HDR_INVERSE; if (cp) { @@ -972,7 +998,8 @@ static int ip_vs_out_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, ip_vs_fill_iph_skb_icmp(AF_INET, skb, offset, true, &ciph); /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(ipvs, AF_INET, skb, &ciph); + cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, + ipvs, AF_INET, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1028,7 +1055,8 @@ static int ip_vs_out_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, return NF_ACCEPT; /* The embedded headers contain source and dest in reverse order */ - cp = pp->conn_out_get(ipvs, AF_INET6, skb, &ciph); + cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, + ipvs, AF_INET6, skb, &ciph); if (!cp) return NF_ACCEPT; @@ -1263,7 +1291,8 @@ handle_response(int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, goto drop; /* mangle the packet */ - if (pp->snat_handler && !pp->snat_handler(skb, pp, cp, iph)) + if (pp->snat_handler && + !SNAT_CALL(pp->snat_handler, skb, pp, cp, iph)) goto drop; #ifdef CONFIG_IP_VS_IPV6 @@ -1389,7 +1418,8 @@ ip_vs_out(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, in /* * Check if the packet belongs to an existing entry */ - cp = pp->conn_out_get(ipvs, af, skb, &iph); + cp = INDIRECT_CALL_1(pp->conn_out_get, ip_vs_conn_out_get_proto, + ipvs, af, skb, &iph); if (likely(cp)) { if (IP_VS_FWD_METHOD(cp) != IP_VS_CONN_F_MASQ) @@ -1642,7 +1672,8 @@ ip_vs_in_icmp(struct netns_ipvs *ipvs, struct sk_buff *skb, int *related, /* The embedded headers contain source and dest in reverse order. * For IPIP this is error for request, not for reply. */ - cp = pp->conn_in_get(ipvs, AF_INET, skb, &ciph); + cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, + ipvs, AF_INET, skb, &ciph); if (!cp) { int v; @@ -1794,7 +1825,8 @@ static int ip_vs_in_icmp_v6(struct netns_ipvs *ipvs, struct sk_buff *skb, /* The embedded headers contain source and dest in reverse order * if not from localhost */ - cp = pp->conn_in_get(ipvs, AF_INET6, skb, &ciph); + cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, + ipvs, AF_INET6, skb, &ciph); if (!cp) { int v; @@ -1923,7 +1955,8 @@ ip_vs_in(struct netns_ipvs *ipvs, unsigned int hooknum, struct sk_buff *skb, int /* * Check if the packet belongs to an existing connection entry */ - cp = pp->conn_in_get(ipvs, af, skb, &iph); + cp = INDIRECT_CALL_1(pp->conn_in_get, ip_vs_conn_in_get_proto, + ipvs, af, skb, &iph); conn_reuse_mode = sysctl_conn_reuse_mode(ipvs); if (conn_reuse_mode && !iph.fragoffs && is_new_conn(skb, &iph) && cp) { diff --git a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c index 5320d39976e1..480598cb0f05 100644 --- a/net/netfilter/ipvs/ip_vs_proto_ah_esp.c +++ b/net/netfilter/ipvs/ip_vs_proto_ah_esp.c @@ -129,7 +129,6 @@ struct ip_vs_protocol ip_vs_protocol_ah = { .conn_out_get = ah_esp_conn_out_get, .snat_handler = NULL, .dnat_handler = NULL, - .csum_check = NULL, .state_transition = NULL, .register_app = NULL, .unregister_app = NULL, @@ -152,7 +151,6 @@ struct ip_vs_protocol ip_vs_protocol_esp = { .conn_out_get = ah_esp_conn_out_get, .snat_handler = NULL, .dnat_handler = NULL, - .csum_check = NULL, .state_transition = NULL, .register_app = NULL, .unregister_app = NULL, diff --git a/net/netfilter/ipvs/ip_vs_proto_sctp.c b/net/netfilter/ipvs/ip_vs_proto_sctp.c index b0cd7d08f2a7..bc3d1625ecc8 100644 --- a/net/netfilter/ipvs/ip_vs_proto_sctp.c +++ b/net/netfilter/ipvs/ip_vs_proto_sctp.c @@ -10,6 +10,9 @@ #include <net/ip_vs.h> static int +sctp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); + +static int sctp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, @@ -105,7 +108,7 @@ sctp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!sctp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -152,7 +155,7 @@ sctp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!sctp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -587,7 +590,6 @@ struct ip_vs_protocol ip_vs_protocol_sctp = { .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = sctp_snat_handler, .dnat_handler = sctp_dnat_handler, - .csum_check = sctp_csum_check, .state_name = sctp_state_name, .state_transition = sctp_state_transition, .app_conn_bind = sctp_app_conn_bind, diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index 1770fc6ce960..479419759983 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -28,10 +28,14 @@ #include <net/ip6_checksum.h> #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> +#include <linux/indirect_call_wrapper.h> #include <net/ip_vs.h> static int +tcp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); + +static int tcp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, @@ -143,7 +147,7 @@ tcp_partial_csum_update(int af, struct tcphdr *tcph, } -static int +INDIRECT_CALLABLE_SCOPE int tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { @@ -166,7 +170,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* Call application helper if needed */ @@ -192,7 +196,7 @@ tcp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, tcp_fast_csum_update(cp->af, tcph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -244,7 +248,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!tcp_csum_check(cp->af, skb, pp)) return 0; /* @@ -275,7 +279,7 @@ tcp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, tcp_fast_csum_update(cp->af, tcph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -736,7 +740,6 @@ struct ip_vs_protocol ip_vs_protocol_tcp = { .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = tcp_snat_handler, .dnat_handler = tcp_dnat_handler, - .csum_check = tcp_csum_check, .state_name = tcp_state_name, .state_transition = tcp_state_transition, .app_conn_bind = tcp_app_conn_bind, diff --git a/net/netfilter/ipvs/ip_vs_proto_udp.c b/net/netfilter/ipvs/ip_vs_proto_udp.c index 0f53c49025f8..646c384910fb 100644 --- a/net/netfilter/ipvs/ip_vs_proto_udp.c +++ b/net/netfilter/ipvs/ip_vs_proto_udp.c @@ -23,12 +23,16 @@ #include <linux/netfilter.h> #include <linux/netfilter_ipv4.h> #include <linux/udp.h> +#include <linux/indirect_call_wrapper.h> #include <net/ip_vs.h> #include <net/ip.h> #include <net/ip6_checksum.h> static int +udp_csum_check(int af, struct sk_buff *skb, struct ip_vs_protocol *pp); + +static int udp_conn_schedule(struct netns_ipvs *ipvs, int af, struct sk_buff *skb, struct ip_vs_proto_data *pd, int *verdict, struct ip_vs_conn **cpp, @@ -133,7 +137,7 @@ udp_partial_csum_update(int af, struct udphdr *uhdr, } -static int +INDIRECT_CALLABLE_SCOPE int udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, struct ip_vs_conn *cp, struct ip_vs_iphdr *iph) { @@ -156,7 +160,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!udp_csum_check(cp->af, skb, pp)) return 0; /* @@ -186,7 +190,7 @@ udp_snat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, udp_fast_csum_update(cp->af, udph, &cp->daddr, &cp->vaddr, cp->dport, cp->vport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -239,7 +243,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, int ret; /* Some checks before mangling */ - if (pp->csum_check && !pp->csum_check(cp->af, skb, pp)) + if (!udp_csum_check(cp->af, skb, pp)) return 0; /* @@ -270,7 +274,7 @@ udp_dnat_handler(struct sk_buff *skb, struct ip_vs_protocol *pp, udp_fast_csum_update(cp->af, udph, &cp->vaddr, &cp->daddr, cp->vport, cp->dport); if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = (cp->app && pp->csum_check) ? + skb->ip_summed = cp->app ? CHECKSUM_UNNECESSARY : CHECKSUM_NONE; } else { /* full checksum calculation */ @@ -494,7 +498,6 @@ struct ip_vs_protocol ip_vs_protocol_udp = { .conn_out_get = ip_vs_conn_out_get_proto, .snat_handler = udp_snat_handler, .dnat_handler = udp_dnat_handler, - .csum_check = udp_csum_check, .state_transition = udp_state_transition, .state_name = udp_state_name, .register_app = udp_register_app, diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index db4d46332e86..08ee03407ace 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -222,6 +222,24 @@ static u32 hash_conntrack(const struct net *net, return scale_hash(hash_conntrack_raw(tuple, net)); } +static bool nf_ct_get_tuple_ports(const struct sk_buff *skb, + unsigned int dataoff, + struct nf_conntrack_tuple *tuple) +{ struct { + __be16 sport; + __be16 dport; + } _inet_hdr, *inet_hdr; + + /* Actually only need first 4 bytes to get ports. */ + inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr); + if (!inet_hdr) + return false; + + tuple->src.u.udp.port = inet_hdr->sport; + tuple->dst.u.udp.port = inet_hdr->dport; + return true; +} + static bool nf_ct_get_tuple(const struct sk_buff *skb, unsigned int nhoff, @@ -229,16 +247,11 @@ nf_ct_get_tuple(const struct sk_buff *skb, u_int16_t l3num, u_int8_t protonum, struct net *net, - struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l4proto *l4proto) + struct nf_conntrack_tuple *tuple) { unsigned int size; const __be32 *ap; __be32 _addrs[8]; - struct { - __be16 sport; - __be16 dport; - } _inet_hdr, *inet_hdr; memset(tuple, 0, sizeof(*tuple)); @@ -274,16 +287,36 @@ nf_ct_get_tuple(const struct sk_buff *skb, tuple->dst.protonum = protonum; tuple->dst.dir = IP_CT_DIR_ORIGINAL; - if (unlikely(l4proto->pkt_to_tuple)) - return l4proto->pkt_to_tuple(skb, dataoff, net, tuple); - - /* Actually only need first 4 bytes to get ports. */ - inet_hdr = skb_header_pointer(skb, dataoff, sizeof(_inet_hdr), &_inet_hdr); - if (!inet_hdr) - return false; + switch (protonum) { +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: + return icmpv6_pkt_to_tuple(skb, dataoff, net, tuple); +#endif + case IPPROTO_ICMP: + return icmp_pkt_to_tuple(skb, dataoff, net, tuple); +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: + return gre_pkt_to_tuple(skb, dataoff, net, tuple); +#endif + case IPPROTO_TCP: + case IPPROTO_UDP: /* fallthrough */ + return nf_ct_get_tuple_ports(skb, dataoff, tuple); +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + case IPPROTO_UDPLITE: + return nf_ct_get_tuple_ports(skb, dataoff, tuple); +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + case IPPROTO_SCTP: + return nf_ct_get_tuple_ports(skb, dataoff, tuple); +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP + case IPPROTO_DCCP: + return nf_ct_get_tuple_ports(skb, dataoff, tuple); +#endif + default: + break; + } - tuple->src.u.udp.port = inet_hdr->sport; - tuple->dst.u.udp.port = inet_hdr->dport; return true; } @@ -366,33 +399,20 @@ bool nf_ct_get_tuplepr(const struct sk_buff *skb, unsigned int nhoff, u_int16_t l3num, struct net *net, struct nf_conntrack_tuple *tuple) { - const struct nf_conntrack_l4proto *l4proto; u8 protonum; int protoff; - int ret; - - rcu_read_lock(); protoff = get_l4proto(skb, nhoff, l3num, &protonum); - if (protoff <= 0) { - rcu_read_unlock(); + if (protoff <= 0) return false; - } - - l4proto = __nf_ct_l4proto_find(protonum); - ret = nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple, - l4proto); - - rcu_read_unlock(); - return ret; + return nf_ct_get_tuple(skb, nhoff, protoff, l3num, protonum, net, tuple); } EXPORT_SYMBOL_GPL(nf_ct_get_tuplepr); bool nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig, - const struct nf_conntrack_l4proto *l4proto) + const struct nf_conntrack_tuple *orig) { memset(inverse, 0, sizeof(*inverse)); @@ -415,8 +435,14 @@ nf_ct_invert_tuple(struct nf_conntrack_tuple *inverse, inverse->dst.protonum = orig->dst.protonum; - if (unlikely(l4proto->invert_tuple)) - return l4proto->invert_tuple(inverse, orig); + switch (orig->dst.protonum) { + case IPPROTO_ICMP: + return nf_conntrack_invert_icmp_tuple(inverse, orig); +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: + return nf_conntrack_invert_icmpv6_tuple(inverse, orig); +#endif + } inverse->src.u.all = orig->dst.u.all; inverse->dst.u.all = orig->src.u.all; @@ -526,11 +552,20 @@ void nf_ct_tmpl_free(struct nf_conn *tmpl) } EXPORT_SYMBOL_GPL(nf_ct_tmpl_free); +static void destroy_gre_conntrack(struct nf_conn *ct) +{ +#ifdef CONFIG_NF_CT_PROTO_GRE + struct nf_conn *master = ct->master; + + if (master) + nf_ct_gre_keymap_destroy(master); +#endif +} + static void destroy_conntrack(struct nf_conntrack *nfct) { struct nf_conn *ct = (struct nf_conn *)nfct; - const struct nf_conntrack_l4proto *l4proto; pr_debug("destroy_conntrack(%p)\n", ct); WARN_ON(atomic_read(&nfct->use) != 0); @@ -539,9 +574,9 @@ destroy_conntrack(struct nf_conntrack *nfct) nf_ct_tmpl_free(ct); return; } - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); - if (l4proto->destroy) - l4proto->destroy(ct); + + if (unlikely(nf_ct_protonum(ct) == IPPROTO_GRE)) + destroy_gre_conntrack(ct); local_bh_disable(); /* Expectations will have been removed in clean_from_lists, @@ -840,7 +875,7 @@ static int nf_ct_resolve_clash(struct net *net, struct sk_buff *skb, enum ip_conntrack_info oldinfo; struct nf_conn *loser_ct = nf_ct_get(skb, &oldinfo); - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->allow_clash && !nf_ct_is_dying(ct) && atomic_inc_not_zero(&ct->ct_general.use)) { @@ -1128,7 +1163,7 @@ static bool gc_worker_can_early_drop(const struct nf_conn *ct) if (!test_bit(IPS_ASSURED_BIT, &ct->status)) return true; - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->can_early_drop && l4proto->can_early_drop(ct)) return true; @@ -1358,7 +1393,6 @@ EXPORT_SYMBOL_GPL(nf_conntrack_free); static noinline struct nf_conntrack_tuple_hash * init_conntrack(struct net *net, struct nf_conn *tmpl, const struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_l4proto *l4proto, struct sk_buff *skb, unsigned int dataoff, u32 hash) { @@ -1371,7 +1405,7 @@ init_conntrack(struct net *net, struct nf_conn *tmpl, struct nf_conn_timeout *timeout_ext; struct nf_conntrack_zone tmp; - if (!nf_ct_invert_tuple(&repl_tuple, tuple, l4proto)) { + if (!nf_ct_invert_tuple(&repl_tuple, tuple)) { pr_debug("Can't invert tuple.\n"); return NULL; } @@ -1453,7 +1487,6 @@ resolve_normal_ct(struct nf_conn *tmpl, struct sk_buff *skb, unsigned int dataoff, u_int8_t protonum, - const struct nf_conntrack_l4proto *l4proto, const struct nf_hook_state *state) { const struct nf_conntrack_zone *zone; @@ -1466,7 +1499,7 @@ resolve_normal_ct(struct nf_conn *tmpl, if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, state->pf, protonum, state->net, - &tuple, l4proto)) { + &tuple)) { pr_debug("Can't get tuple\n"); return 0; } @@ -1476,7 +1509,7 @@ resolve_normal_ct(struct nf_conn *tmpl, hash = hash_conntrack_raw(&tuple, state->net); h = __nf_conntrack_find_get(state->net, zone, &tuple, hash); if (!h) { - h = init_conntrack(state->net, tmpl, &tuple, l4proto, + h = init_conntrack(state->net, tmpl, &tuple, skb, dataoff, hash); if (!h) return 0; @@ -1538,10 +1571,66 @@ nf_conntrack_handle_icmp(struct nf_conn *tmpl, return ret; } +static int generic_packet(struct nf_conn *ct, struct sk_buff *skb, + enum ip_conntrack_info ctinfo) +{ + const unsigned int *timeout = nf_ct_timeout_lookup(ct); + + if (!timeout) + timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; + + nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); + return NF_ACCEPT; +} + +/* Returns verdict for packet, or -1 for invalid. */ +static int nf_conntrack_handle_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) +{ + switch (nf_ct_protonum(ct)) { + case IPPROTO_TCP: + return nf_conntrack_tcp_packet(ct, skb, dataoff, + ctinfo, state); + case IPPROTO_UDP: + return nf_conntrack_udp_packet(ct, skb, dataoff, + ctinfo, state); + case IPPROTO_ICMP: + return nf_conntrack_icmp_packet(ct, skb, ctinfo, state); +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: + return nf_conntrack_icmpv6_packet(ct, skb, ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + case IPPROTO_UDPLITE: + return nf_conntrack_udplite_packet(ct, skb, dataoff, + ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + case IPPROTO_SCTP: + return nf_conntrack_sctp_packet(ct, skb, dataoff, + ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP + case IPPROTO_DCCP: + return nf_conntrack_dccp_packet(ct, skb, dataoff, + ctinfo, state); +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: + return nf_conntrack_gre_packet(ct, skb, dataoff, + ctinfo, state); +#endif + } + + return generic_packet(ct, skb, ctinfo); +} + unsigned int nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) { - const struct nf_conntrack_l4proto *l4proto; enum ip_conntrack_info ctinfo; struct nf_conn *ct, *tmpl; u_int8_t protonum; @@ -1568,8 +1657,6 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) goto out; } - l4proto = __nf_ct_l4proto_find(protonum); - if (protonum == IPPROTO_ICMP || protonum == IPPROTO_ICMPV6) { ret = nf_conntrack_handle_icmp(tmpl, skb, dataoff, protonum, state); @@ -1583,7 +1670,7 @@ nf_conntrack_in(struct sk_buff *skb, const struct nf_hook_state *state) } repeat: ret = resolve_normal_ct(tmpl, skb, dataoff, - protonum, l4proto, state); + protonum, state); if (ret < 0) { /* Too stressed to deal. */ NF_CT_STAT_INC_ATOMIC(state->net, drop); @@ -1599,7 +1686,7 @@ repeat: goto out; } - ret = l4proto->packet(ct, skb, dataoff, ctinfo, state); + ret = nf_conntrack_handle_packet(ct, skb, dataoff, ctinfo, state); if (ret <= 0) { /* Invalid: inverse of the return code tells * the netfilter core what to do */ @@ -1630,19 +1717,6 @@ out: } EXPORT_SYMBOL_GPL(nf_conntrack_in); -bool nf_ct_invert_tuplepr(struct nf_conntrack_tuple *inverse, - const struct nf_conntrack_tuple *orig) -{ - bool ret; - - rcu_read_lock(); - ret = nf_ct_invert_tuple(inverse, orig, - __nf_ct_l4proto_find(orig->dst.protonum)); - rcu_read_unlock(); - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_invert_tuplepr); - /* Alter reply tuple (maybe alter helper). This is for NAT, and is implicitly racy: see __nf_conntrack_confirm */ void nf_conntrack_alter_reply(struct nf_conn *ct, @@ -1773,7 +1847,6 @@ static void nf_conntrack_attach(struct sk_buff *nskb, const struct sk_buff *skb) static int nf_conntrack_update(struct net *net, struct sk_buff *skb) { - const struct nf_conntrack_l4proto *l4proto; struct nf_conntrack_tuple_hash *h; struct nf_conntrack_tuple tuple; enum ip_conntrack_info ctinfo; @@ -1794,10 +1867,8 @@ static int nf_conntrack_update(struct net *net, struct sk_buff *skb) if (dataoff <= 0) return -1; - l4proto = nf_ct_l4proto_find_get(l4num); - if (!nf_ct_get_tuple(skb, skb_network_offset(skb), dataoff, l3num, - l4num, net, &tuple, l4proto)) + l4num, net, &tuple)) return -1; if (ct->status & IPS_SRC_NAT) { @@ -2429,15 +2500,10 @@ int nf_conntrack_init_net(struct net *net) nf_conntrack_tstamp_pernet_init(net); nf_conntrack_ecache_pernet_init(net); nf_conntrack_helper_pernet_init(net); + nf_conntrack_proto_pernet_init(net); - ret = nf_conntrack_proto_pernet_init(net); - if (ret < 0) - goto err_proto; return 0; -err_proto: - nf_conntrack_ecache_pernet_fini(net); - nf_conntrack_expect_pernet_fini(net); err_expect: free_percpu(net->ct.stat); err_pcpu_lists: diff --git a/net/netfilter/nf_conntrack_expect.c b/net/netfilter/nf_conntrack_expect.c index 3034038bfdf0..334d6e5b7762 100644 --- a/net/netfilter/nf_conntrack_expect.c +++ b/net/netfilter/nf_conntrack_expect.c @@ -610,7 +610,7 @@ static int exp_seq_show(struct seq_file *s, void *v) expect->tuple.src.l3num, expect->tuple.dst.protonum); print_tuple(s, &expect->tuple, - __nf_ct_l4proto_find(expect->tuple.dst.protonum)); + nf_ct_l4proto_find(expect->tuple.dst.protonum)); if (expect->flags & NF_CT_EXPECT_PERMANENT) { seq_puts(s, "PERMANENT"); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 1213beb5a714..8071bb04a849 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -134,7 +134,7 @@ static int ctnetlink_dump_tuples(struct sk_buff *skb, ret = ctnetlink_dump_tuples_ip(skb, tuple); if (ret >= 0) { - l4proto = __nf_ct_l4proto_find(tuple->dst.protonum); + l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, tuple, l4proto); } rcu_read_unlock(); @@ -182,7 +182,7 @@ static int ctnetlink_dump_protoinfo(struct sk_buff *skb, struct nf_conn *ct) struct nlattr *nest_proto; int ret; - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (!l4proto->to_nlattr) return 0; @@ -590,7 +590,7 @@ static size_t ctnetlink_proto_size(const struct nf_conn *ct) len = nla_policy_len(cta_ip_nla_policy, CTA_IP_MAX + 1); len *= 3u; /* ORIG, REPLY, MASTER */ - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); len += l4proto->nlattr_size; if (l4proto->nlattr_tuple_size) { len4 = l4proto->nlattr_tuple_size(); @@ -1059,7 +1059,7 @@ static int ctnetlink_parse_tuple_proto(struct nlattr *attr, tuple->dst.protonum = nla_get_u8(tb[CTA_PROTO_NUM]); rcu_read_lock(); - l4proto = __nf_ct_l4proto_find(tuple->dst.protonum); + l4proto = nf_ct_l4proto_find(tuple->dst.protonum); if (likely(l4proto->nlattr_to_tuple)) { ret = nla_validate_nested(attr, CTA_PROTO_MAX, @@ -1722,11 +1722,9 @@ static int ctnetlink_change_protoinfo(struct nf_conn *ct, if (err < 0) return err; - rcu_read_lock(); - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); if (l4proto->from_nlattr) err = l4proto->from_nlattr(tb, ct); - rcu_read_unlock(); return err; } @@ -2676,7 +2674,7 @@ static int ctnetlink_exp_dump_mask(struct sk_buff *skb, rcu_read_lock(); ret = ctnetlink_dump_tuples_ip(skb, &m); if (ret >= 0) { - l4proto = __nf_ct_l4proto_find(tuple->dst.protonum); + l4proto = nf_ct_l4proto_find(tuple->dst.protonum); ret = ctnetlink_dump_tuples_proto(skb, &m, l4proto); } rcu_read_unlock(); diff --git a/net/netfilter/nf_conntrack_pptp.c b/net/netfilter/nf_conntrack_pptp.c index 11562f2a08bb..976f1dcb97f0 100644 --- a/net/netfilter/nf_conntrack_pptp.c +++ b/net/netfilter/nf_conntrack_pptp.c @@ -121,7 +121,7 @@ static void pptp_expectfn(struct nf_conn *ct, struct nf_conntrack_expect *exp_other; /* obviously this tuple inversion only works until you do NAT */ - nf_ct_invert_tuplepr(&inv_t, &exp->tuple); + nf_ct_invert_tuple(&inv_t, &exp->tuple); pr_debug("trying to unexpect other dir: "); nf_ct_dump_tuple(&inv_t); diff --git a/net/netfilter/nf_conntrack_proto.c b/net/netfilter/nf_conntrack_proto.c index 859f5d07a915..b9403a266a2e 100644 --- a/net/netfilter/nf_conntrack_proto.c +++ b/net/netfilter/nf_conntrack_proto.c @@ -43,40 +43,9 @@ extern unsigned int nf_conntrack_net_id; -static struct nf_conntrack_l4proto __rcu *nf_ct_protos[MAX_NF_CT_PROTO + 1] __read_mostly; - static DEFINE_MUTEX(nf_ct_proto_mutex); #ifdef CONFIG_SYSCTL -static int -nf_ct_register_sysctl(struct net *net, - struct ctl_table_header **header, - const char *path, - struct ctl_table *table) -{ - if (*header == NULL) { - *header = register_net_sysctl(net, path, table); - if (*header == NULL) - return -ENOMEM; - } - - return 0; -} - -static void -nf_ct_unregister_sysctl(struct ctl_table_header **header, - struct ctl_table **table, - unsigned int users) -{ - if (users > 0) - return; - - unregister_net_sysctl_table(*header); - kfree(*table); - *header = NULL; - *table = NULL; -} - __printf(5, 6) void nf_l4proto_log_invalid(const struct sk_buff *skb, struct net *net, @@ -124,295 +93,82 @@ void nf_ct_l4proto_log_invalid(const struct sk_buff *skb, EXPORT_SYMBOL_GPL(nf_ct_l4proto_log_invalid); #endif -const struct nf_conntrack_l4proto *__nf_ct_l4proto_find(u8 l4proto) -{ - if (unlikely(l4proto >= ARRAY_SIZE(nf_ct_protos))) - return &nf_conntrack_l4proto_generic; - - return rcu_dereference(nf_ct_protos[l4proto]); -} -EXPORT_SYMBOL_GPL(__nf_ct_l4proto_find); - -const struct nf_conntrack_l4proto *nf_ct_l4proto_find_get(u8 l4num) -{ - const struct nf_conntrack_l4proto *p; - - rcu_read_lock(); - p = __nf_ct_l4proto_find(l4num); - if (!try_module_get(p->me)) - p = &nf_conntrack_l4proto_generic; - rcu_read_unlock(); - - return p; -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_find_get); - -void nf_ct_l4proto_put(const struct nf_conntrack_l4proto *p) -{ - module_put(p->me); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_put); - -static int kill_l4proto(struct nf_conn *i, void *data) -{ - const struct nf_conntrack_l4proto *l4proto; - l4proto = data; - return nf_ct_protonum(i) == l4proto->l4proto; -} - -static struct nf_proto_net *nf_ct_l4proto_net(struct net *net, - const struct nf_conntrack_l4proto *l4proto) -{ - if (l4proto->get_net_proto) { - /* statically built-in protocols use static per-net */ - return l4proto->get_net_proto(net); - } else if (l4proto->net_id) { - /* ... and loadable protocols use dynamic per-net */ - return net_generic(net, *l4proto->net_id); - } - return NULL; -} - -static -int nf_ct_l4proto_register_sysctl(struct net *net, - struct nf_proto_net *pn) -{ - int err = 0; - -#ifdef CONFIG_SYSCTL - if (pn->ctl_table != NULL) { - err = nf_ct_register_sysctl(net, - &pn->ctl_table_header, - "net/netfilter", - pn->ctl_table); - if (err < 0) { - if (!pn->users) { - kfree(pn->ctl_table); - pn->ctl_table = NULL; - } - } - } -#endif /* CONFIG_SYSCTL */ - return err; -} - -static -void nf_ct_l4proto_unregister_sysctl(struct nf_proto_net *pn) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table_header != NULL) - nf_ct_unregister_sysctl(&pn->ctl_table_header, - &pn->ctl_table, - pn->users); -#endif /* CONFIG_SYSCTL */ -} - -/* FIXME: Allow NULL functions and sub in pointers to generic for - them. --RR */ -int nf_ct_l4proto_register_one(const struct nf_conntrack_l4proto *l4proto) -{ - int ret = 0; - - if ((l4proto->to_nlattr && l4proto->nlattr_size == 0) || - (l4proto->tuple_to_nlattr && !l4proto->nlattr_tuple_size)) - return -EINVAL; - - mutex_lock(&nf_ct_proto_mutex); - if (rcu_dereference_protected( - nf_ct_protos[l4proto->l4proto], - lockdep_is_held(&nf_ct_proto_mutex) - ) != &nf_conntrack_l4proto_generic) { - ret = -EBUSY; - goto out_unlock; - } - - rcu_assign_pointer(nf_ct_protos[l4proto->l4proto], l4proto); -out_unlock: - mutex_unlock(&nf_ct_proto_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_register_one); - -int nf_ct_l4proto_pernet_register_one(struct net *net, - const struct nf_conntrack_l4proto *l4proto) -{ - int ret = 0; - struct nf_proto_net *pn = NULL; - - if (l4proto->init_net) { - ret = l4proto->init_net(net); - if (ret < 0) - goto out; - } - - pn = nf_ct_l4proto_net(net, l4proto); - if (pn == NULL) - goto out; - - ret = nf_ct_l4proto_register_sysctl(net, pn); - if (ret < 0) - goto out; - - pn->users++; -out: - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register_one); - -static void __nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) - -{ - BUG_ON(l4proto->l4proto >= ARRAY_SIZE(nf_ct_protos)); - - BUG_ON(rcu_dereference_protected( - nf_ct_protos[l4proto->l4proto], - lockdep_is_held(&nf_ct_proto_mutex) - ) != l4proto); - rcu_assign_pointer(nf_ct_protos[l4proto->l4proto], - &nf_conntrack_l4proto_generic); -} - -void nf_ct_l4proto_unregister_one(const struct nf_conntrack_l4proto *l4proto) -{ - mutex_lock(&nf_ct_proto_mutex); - __nf_ct_l4proto_unregister_one(l4proto); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_net(); - /* Remove all contrack entries for this protocol */ - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_unregister_one); - -void nf_ct_l4proto_pernet_unregister_one(struct net *net, - const struct nf_conntrack_l4proto *l4proto) -{ - struct nf_proto_net *pn = nf_ct_l4proto_net(net, l4proto); - - if (pn == NULL) - return; - - pn->users--; - nf_ct_l4proto_unregister_sysctl(pn); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister_one); - -static void -nf_ct_l4proto_unregister(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) -{ - int i; - - mutex_lock(&nf_ct_proto_mutex); - for (i = 0; i < num_proto; i++) - __nf_ct_l4proto_unregister_one(l4proto[i]); - mutex_unlock(&nf_ct_proto_mutex); - - synchronize_net(); - - for (i = 0; i < num_proto; i++) - nf_ct_iterate_destroy(kill_l4proto, (void *)l4proto[i]); -} - -static int -nf_ct_l4proto_register(const struct nf_conntrack_l4proto * const l4proto[], - unsigned int num_proto) -{ - int ret = -EINVAL; - unsigned int i; - - for (i = 0; i < num_proto; i++) { - ret = nf_ct_l4proto_register_one(l4proto[i]); - if (ret < 0) - break; - } - if (i != num_proto) { - pr_err("nf_conntrack: can't register l4 %d proto.\n", - l4proto[i]->l4proto); - nf_ct_l4proto_unregister(l4proto, i); - } - return ret; -} - -int nf_ct_l4proto_pernet_register(struct net *net, - const struct nf_conntrack_l4proto *const l4proto[], - unsigned int num_proto) +const struct nf_conntrack_l4proto *nf_ct_l4proto_find(u8 l4proto) { - int ret = -EINVAL; - unsigned int i; - - for (i = 0; i < num_proto; i++) { - ret = nf_ct_l4proto_pernet_register_one(net, l4proto[i]); - if (ret < 0) - break; - } - if (i != num_proto) { - pr_err("nf_conntrack %d: pernet registration failed\n", - l4proto[i]->l4proto); - nf_ct_l4proto_pernet_unregister(net, l4proto, i); + switch (l4proto) { + case IPPROTO_UDP: return &nf_conntrack_l4proto_udp; + case IPPROTO_TCP: return &nf_conntrack_l4proto_tcp; + case IPPROTO_ICMP: return &nf_conntrack_l4proto_icmp; +#ifdef CONFIG_NF_CT_PROTO_DCCP + case IPPROTO_DCCP: return &nf_conntrack_l4proto_dccp; +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + case IPPROTO_SCTP: return &nf_conntrack_l4proto_sctp; +#endif +#ifdef CONFIG_NF_CT_PROTO_UDPLITE + case IPPROTO_UDPLITE: return &nf_conntrack_l4proto_udplite; +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + case IPPROTO_GRE: return &nf_conntrack_l4proto_gre; +#endif +#if IS_ENABLED(CONFIG_IPV6) + case IPPROTO_ICMPV6: return &nf_conntrack_l4proto_icmpv6; +#endif /* CONFIG_IPV6 */ } - return ret; -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_register); -void nf_ct_l4proto_pernet_unregister(struct net *net, - const struct nf_conntrack_l4proto *const l4proto[], - unsigned int num_proto) -{ - while (num_proto-- != 0) - nf_ct_l4proto_pernet_unregister_one(net, l4proto[num_proto]); -} -EXPORT_SYMBOL_GPL(nf_ct_l4proto_pernet_unregister); + return &nf_conntrack_l4proto_generic; +}; +EXPORT_SYMBOL_GPL(nf_ct_l4proto_find); -static unsigned int ipv4_helper(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) +static unsigned int nf_confirm(struct sk_buff *skb, + unsigned int protoff, + struct nf_conn *ct, + enum ip_conntrack_info ctinfo) { - struct nf_conn *ct; - enum ip_conntrack_info ctinfo; const struct nf_conn_help *help; - const struct nf_conntrack_helper *helper; - - /* This is where we call the helper: as the packet goes out. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; help = nfct_help(ct); - if (!help) - return NF_ACCEPT; + if (help) { + const struct nf_conntrack_helper *helper; + int ret; + + /* rcu_read_lock()ed by nf_hook_thresh */ + helper = rcu_dereference(help->helper); + if (helper) { + ret = helper->help(skb, + protoff, + ct, ctinfo); + if (ret != NF_ACCEPT) + return ret; + } + } - /* rcu_read_lock()ed by nf_hook_thresh */ - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; + if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && + !nf_is_loopback_packet(skb)) { + if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { + NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); + return NF_DROP; + } + } - return helper->help(skb, skb_network_offset(skb) + ip_hdrlen(skb), - ct, ctinfo); + /* We've seen it coming out the other side: confirm it */ + return nf_conntrack_confirm(skb); } static unsigned int ipv4_confirm(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - struct nf_conn *ct; enum ip_conntrack_info ctinfo; + struct nf_conn *ct; ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return nf_conntrack_confirm(skb); - /* adjust seqs for loopback traffic only in outgoing direction */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_is_loopback_packet(skb)) { - if (!nf_ct_seq_adjust(skb, ct, ctinfo, ip_hdrlen(skb))) { - NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return NF_DROP; - } - } -out: - /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(skb); + return nf_confirm(skb, + skb_network_offset(skb) + ip_hdrlen(skb), + ct, ctinfo); } static unsigned int ipv4_conntrack_in(void *priv, @@ -461,24 +217,12 @@ static const struct nf_hook_ops ipv4_conntrack_ops[] = { .priority = NF_IP_PRI_CONNTRACK, }, { - .hook = ipv4_helper, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP_PRI_CONNTRACK_HELPER, - }, - { .hook = ipv4_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP_PRI_CONNTRACK_CONFIRM, }, { - .hook = ipv4_helper, - .pf = NFPROTO_IPV4, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP_PRI_CONNTRACK_HELPER, - }, - { .hook = ipv4_confirm, .pf = NFPROTO_IPV4, .hooknum = NF_INET_LOCAL_IN, @@ -623,31 +367,21 @@ static unsigned int ipv6_confirm(void *priv, struct nf_conn *ct; enum ip_conntrack_info ctinfo; unsigned char pnum = ipv6_hdr(skb)->nexthdr; - int protoff; __be16 frag_off; + int protoff; ct = nf_ct_get(skb, &ctinfo); if (!ct || ctinfo == IP_CT_RELATED_REPLY) - goto out; + return nf_conntrack_confirm(skb); protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &pnum, &frag_off); if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { pr_debug("proto header not found\n"); - goto out; + return nf_conntrack_confirm(skb); } - /* adjust seqs for loopback traffic only in outgoing direction */ - if (test_bit(IPS_SEQ_ADJUST_BIT, &ct->status) && - !nf_is_loopback_packet(skb)) { - if (!nf_ct_seq_adjust(skb, ct, ctinfo, protoff)) { - NF_CT_STAT_INC_ATOMIC(nf_ct_net(ct), drop); - return NF_DROP; - } - } -out: - /* We've seen it coming out the other side: confirm it */ - return nf_conntrack_confirm(skb); + return nf_confirm(skb, protoff, ct, ctinfo); } static unsigned int ipv6_conntrack_in(void *priv, @@ -664,42 +398,6 @@ static unsigned int ipv6_conntrack_local(void *priv, return nf_conntrack_in(skb, state); } -static unsigned int ipv6_helper(void *priv, - struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct nf_conn *ct; - const struct nf_conn_help *help; - const struct nf_conntrack_helper *helper; - enum ip_conntrack_info ctinfo; - __be16 frag_off; - int protoff; - u8 nexthdr; - - /* This is where we call the helper: as the packet goes out. */ - ct = nf_ct_get(skb, &ctinfo); - if (!ct || ctinfo == IP_CT_RELATED_REPLY) - return NF_ACCEPT; - - help = nfct_help(ct); - if (!help) - return NF_ACCEPT; - /* rcu_read_lock()ed by nf_hook_thresh */ - helper = rcu_dereference(help->helper); - if (!helper) - return NF_ACCEPT; - - nexthdr = ipv6_hdr(skb)->nexthdr; - protoff = ipv6_skip_exthdr(skb, sizeof(struct ipv6hdr), &nexthdr, - &frag_off); - if (protoff < 0 || (frag_off & htons(~0x7)) != 0) { - pr_debug("proto header not found\n"); - return NF_ACCEPT; - } - - return helper->help(skb, protoff, ct, ctinfo); -} - static const struct nf_hook_ops ipv6_conntrack_ops[] = { { .hook = ipv6_conntrack_in, @@ -714,24 +412,12 @@ static const struct nf_hook_ops ipv6_conntrack_ops[] = { .priority = NF_IP6_PRI_CONNTRACK, }, { - .hook = ipv6_helper, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_POST_ROUTING, - .priority = NF_IP6_PRI_CONNTRACK_HELPER, - }, - { .hook = ipv6_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_POST_ROUTING, .priority = NF_IP6_PRI_LAST, }, { - .hook = ipv6_helper, - .pf = NFPROTO_IPV6, - .hooknum = NF_INET_LOCAL_IN, - .priority = NF_IP6_PRI_CONNTRACK_HELPER, - }, - { .hook = ipv6_confirm, .pf = NFPROTO_IPV6, .hooknum = NF_INET_LOCAL_IN, @@ -874,27 +560,9 @@ void nf_ct_netns_put(struct net *net, uint8_t nfproto) } EXPORT_SYMBOL_GPL(nf_ct_netns_put); -static const struct nf_conntrack_l4proto * const builtin_l4proto[] = { - &nf_conntrack_l4proto_tcp, - &nf_conntrack_l4proto_udp, - &nf_conntrack_l4proto_icmp, -#ifdef CONFIG_NF_CT_PROTO_DCCP - &nf_conntrack_l4proto_dccp, -#endif -#ifdef CONFIG_NF_CT_PROTO_SCTP - &nf_conntrack_l4proto_sctp, -#endif -#ifdef CONFIG_NF_CT_PROTO_UDPLITE - &nf_conntrack_l4proto_udplite, -#endif -#if IS_ENABLED(CONFIG_IPV6) - &nf_conntrack_l4proto_icmpv6, -#endif /* CONFIG_IPV6 */ -}; - int nf_conntrack_proto_init(void) { - int ret = 0, i; + int ret; ret = nf_register_sockopt(&so_getorigdst); if (ret < 0) @@ -906,18 +574,8 @@ int nf_conntrack_proto_init(void) goto cleanup_sockopt; #endif - for (i = 0; i < ARRAY_SIZE(nf_ct_protos); i++) - RCU_INIT_POINTER(nf_ct_protos[i], - &nf_conntrack_l4proto_generic); - - ret = nf_ct_l4proto_register(builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); - if (ret < 0) - goto cleanup_sockopt2; - return ret; -cleanup_sockopt2: - nf_unregister_sockopt(&so_getorigdst); + #if IS_ENABLED(CONFIG_IPV6) cleanup_sockopt: nf_unregister_sockopt(&so_getorigdst6); @@ -933,43 +591,33 @@ void nf_conntrack_proto_fini(void) #endif } -int nf_conntrack_proto_pernet_init(struct net *net) +void nf_conntrack_proto_pernet_init(struct net *net) { - int err; - struct nf_proto_net *pn = nf_ct_l4proto_net(net, - &nf_conntrack_l4proto_generic); - - err = nf_conntrack_l4proto_generic.init_net(net); - if (err < 0) - return err; - err = nf_ct_l4proto_register_sysctl(net, - pn); - if (err < 0) - return err; - - err = nf_ct_l4proto_pernet_register(net, builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); - if (err < 0) { - nf_ct_l4proto_unregister_sysctl(pn); - return err; - } - - pn->users++; - return 0; + nf_conntrack_generic_init_net(net); + nf_conntrack_udp_init_net(net); + nf_conntrack_tcp_init_net(net); + nf_conntrack_icmp_init_net(net); +#if IS_ENABLED(CONFIG_IPV6) + nf_conntrack_icmpv6_init_net(net); +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP + nf_conntrack_dccp_init_net(net); +#endif +#ifdef CONFIG_NF_CT_PROTO_SCTP + nf_conntrack_sctp_init_net(net); +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + nf_conntrack_gre_init_net(net); +#endif } void nf_conntrack_proto_pernet_fini(struct net *net) { - struct nf_proto_net *pn = nf_ct_l4proto_net(net, - &nf_conntrack_l4proto_generic); - - nf_ct_l4proto_pernet_unregister(net, builtin_l4proto, - ARRAY_SIZE(builtin_l4proto)); - pn->users--; - nf_ct_l4proto_unregister_sysctl(pn); +#ifdef CONFIG_NF_CT_PROTO_GRE + nf_ct_gre_keymap_flush(net); +#endif } - module_param_call(hashsize, nf_conntrack_set_hashsize, param_get_uint, &nf_conntrack_htable_size, 0600); diff --git a/net/netfilter/nf_conntrack_proto_dccp.c b/net/netfilter/nf_conntrack_proto_dccp.c index 023c1445bc39..6fca80587505 100644 --- a/net/netfilter/nf_conntrack_proto_dccp.c +++ b/net/netfilter/nf_conntrack_proto_dccp.c @@ -472,9 +472,10 @@ out_invalid: return true; } -static int dccp_packet(struct nf_conn *ct, struct sk_buff *skb, - unsigned int dataoff, enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_dccp_packet(struct nf_conn *ct, struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); struct dccp_hdr _dh, *dh; @@ -723,123 +724,28 @@ dccp_timeout_nla_policy[CTA_TIMEOUT_DCCP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -/* template, data assigned later */ -static struct ctl_table dccp_sysctl_table[] = { - { - .procname = "nf_conntrack_dccp_timeout_request", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_timeout_respond", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_timeout_partopen", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_timeout_open", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_timeout_closereq", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_timeout_closing", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_timeout_timewait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_dccp_loose", - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int dccp_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *pn, - struct nf_dccp_net *dn) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table) - return 0; - - pn->ctl_table = kmemdup(dccp_sysctl_table, - sizeof(dccp_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &dn->dccp_timeout[CT_DCCP_REQUEST]; - pn->ctl_table[1].data = &dn->dccp_timeout[CT_DCCP_RESPOND]; - pn->ctl_table[2].data = &dn->dccp_timeout[CT_DCCP_PARTOPEN]; - pn->ctl_table[3].data = &dn->dccp_timeout[CT_DCCP_OPEN]; - pn->ctl_table[4].data = &dn->dccp_timeout[CT_DCCP_CLOSEREQ]; - pn->ctl_table[5].data = &dn->dccp_timeout[CT_DCCP_CLOSING]; - pn->ctl_table[6].data = &dn->dccp_timeout[CT_DCCP_TIMEWAIT]; - pn->ctl_table[7].data = &dn->dccp_loose; - - /* Don't export sysctls to unprivileged users */ - if (net->user_ns != &init_user_ns) - pn->ctl_table[0].procname = NULL; -#endif - return 0; -} - -static int dccp_init_net(struct net *net) +void nf_conntrack_dccp_init_net(struct net *net) { struct nf_dccp_net *dn = nf_dccp_pernet(net); - struct nf_proto_net *pn = &dn->pn; - - if (!pn->users) { - /* default values */ - dn->dccp_loose = 1; - dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; - dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; - dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; - dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; - dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; - - /* timeouts[0] is unused, make it same as SYN_SENT so - * ->timeouts[0] contains 'new' timeout, like udp or icmp. - */ - dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; - } - return dccp_kmemdup_sysctl_table(net, pn, dn); -} - -static struct nf_proto_net *dccp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.dccp.pn; + /* default values */ + dn->dccp_loose = 1; + dn->dccp_timeout[CT_DCCP_REQUEST] = 2 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_RESPOND] = 4 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_PARTOPEN] = 4 * DCCP_MSL; + dn->dccp_timeout[CT_DCCP_OPEN] = 12 * 3600 * HZ; + dn->dccp_timeout[CT_DCCP_CLOSEREQ] = 64 * HZ; + dn->dccp_timeout[CT_DCCP_CLOSING] = 64 * HZ; + dn->dccp_timeout[CT_DCCP_TIMEWAIT] = 2 * DCCP_MSL; + + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + dn->dccp_timeout[CT_DCCP_NONE] = dn->dccp_timeout[CT_DCCP_REQUEST]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { .l4proto = IPPROTO_DCCP, - .packet = dccp_packet, .can_early_drop = dccp_can_early_drop, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = dccp_print_conntrack, @@ -862,6 +768,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_dccp = { .nla_policy = dccp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = dccp_init_net, - .get_net_proto = dccp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_generic.c b/net/netfilter/nf_conntrack_proto_generic.c index 5da19d5fbc76..0f526fafecae 100644 --- a/net/netfilter/nf_conntrack_proto_generic.c +++ b/net/netfilter/nf_conntrack_proto_generic.c @@ -15,50 +15,6 @@ static const unsigned int nf_ct_generic_timeout = 600*HZ; -static bool nf_generic_should_process(u8 proto) -{ - switch (proto) { -#ifdef CONFIG_NF_CT_PROTO_GRE_MODULE - case IPPROTO_GRE: - return false; -#endif - default: - return true; - } -} - -static bool generic_pkt_to_tuple(const struct sk_buff *skb, - unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) -{ - tuple->src.u.all = 0; - tuple->dst.u.all = 0; - - return true; -} - -/* Returns verdict for packet, or -1 for invalid. */ -static int generic_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) -{ - const unsigned int *timeout = nf_ct_timeout_lookup(ct); - - if (!nf_generic_should_process(nf_ct_protonum(ct))) { - pr_warn_once("conntrack: generic helper won't handle protocol %d. Please consider loading the specific helper module.\n", - nf_ct_protonum(ct)); - return -NF_ACCEPT; - } - - if (!timeout) - timeout = &nf_generic_pernet(nf_ct_net(ct))->timeout; - - nf_ct_refresh_acct(ct, ctinfo, skb, *timeout); - return NF_ACCEPT; -} - #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> @@ -104,53 +60,16 @@ generic_timeout_nla_policy[CTA_TIMEOUT_GENERIC_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -static struct ctl_table generic_sysctl_table[] = { - { - .procname = "nf_conntrack_generic_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int generic_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_generic_net *gn) -{ -#ifdef CONFIG_SYSCTL - pn->ctl_table = kmemdup(generic_sysctl_table, - sizeof(generic_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &gn->timeout; -#endif - return 0; -} - -static int generic_init_net(struct net *net) +void nf_conntrack_generic_init_net(struct net *net) { struct nf_generic_net *gn = nf_generic_pernet(net); - struct nf_proto_net *pn = &gn->pn; gn->timeout = nf_ct_generic_timeout; - - return generic_kmemdup_sysctl_table(pn, gn); -} - -static struct nf_proto_net *generic_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.generic.pn; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = { .l4proto = 255, - .pkt_to_tuple = generic_pkt_to_tuple, - .packet = generic_packet, #ifdef CONFIG_NF_CONNTRACK_TIMEOUT .ctnl_timeout = { .nlattr_to_obj = generic_timeout_nlattr_to_obj, @@ -160,6 +79,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_generic = .nla_policy = generic_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = generic_init_net, - .get_net_proto = generic_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_gre.c b/net/netfilter/nf_conntrack_proto_gre.c index 8899b51aad44..ee9ab10a32e4 100644 --- a/net/netfilter/nf_conntrack_proto_gre.c +++ b/net/netfilter/nf_conntrack_proto_gre.c @@ -48,24 +48,25 @@ static const unsigned int gre_timeouts[GRE_CT_MAX] = { [GRE_CT_REPLIED] = 180*HZ, }; -static unsigned int proto_gre_net_id __read_mostly; +/* used when expectation is added */ +static DEFINE_SPINLOCK(keymap_lock); -static inline struct netns_proto_gre *gre_pernet(struct net *net) +static inline struct nf_gre_net *gre_pernet(struct net *net) { - return net_generic(net, proto_gre_net_id); + return &net->ct.nf_ct_proto.gre; } -static void nf_ct_gre_keymap_flush(struct net *net) +void nf_ct_gre_keymap_flush(struct net *net) { - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km, *tmp; - write_lock_bh(&net_gre->keymap_lock); + spin_lock_bh(&keymap_lock); list_for_each_entry_safe(km, tmp, &net_gre->keymap_list, list) { - list_del(&km->list); - kfree(km); + list_del_rcu(&km->list); + kfree_rcu(km, rcu); } - write_unlock_bh(&net_gre->keymap_lock); + spin_unlock_bh(&keymap_lock); } static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, @@ -81,18 +82,16 @@ static inline int gre_key_cmpfn(const struct nf_ct_gre_keymap *km, /* look up the source key for a given tuple */ static __be16 gre_keymap_lookup(struct net *net, struct nf_conntrack_tuple *t) { - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_gre_keymap *km; __be16 key = 0; - read_lock_bh(&net_gre->keymap_lock); - list_for_each_entry(km, &net_gre->keymap_list, list) { + list_for_each_entry_rcu(km, &net_gre->keymap_list, list) { if (gre_key_cmpfn(km, t)) { key = km->tuple.src.u.gre.key; break; } } - read_unlock_bh(&net_gre->keymap_lock); pr_debug("lookup src key 0x%x for ", key); nf_ct_dump_tuple(t); @@ -105,21 +104,17 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, struct nf_conntrack_tuple *t) { struct net *net = nf_ct_net(ct); - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); struct nf_ct_gre_keymap **kmp, *km; kmp = &ct_pptp_info->keymap[dir]; if (*kmp) { /* check whether it's a retransmission */ - read_lock_bh(&net_gre->keymap_lock); - list_for_each_entry(km, &net_gre->keymap_list, list) { - if (gre_key_cmpfn(km, t) && km == *kmp) { - read_unlock_bh(&net_gre->keymap_lock); + list_for_each_entry_rcu(km, &net_gre->keymap_list, list) { + if (gre_key_cmpfn(km, t) && km == *kmp) return 0; - } } - read_unlock_bh(&net_gre->keymap_lock); pr_debug("trying to override keymap_%s for ct %p\n", dir == IP_CT_DIR_REPLY ? "reply" : "orig", ct); return -EEXIST; @@ -134,9 +129,9 @@ int nf_ct_gre_keymap_add(struct nf_conn *ct, enum ip_conntrack_dir dir, pr_debug("adding new entry %p: ", km); nf_ct_dump_tuple(&km->tuple); - write_lock_bh(&net_gre->keymap_lock); + spin_lock_bh(&keymap_lock); list_add_tail(&km->list, &net_gre->keymap_list); - write_unlock_bh(&net_gre->keymap_lock); + spin_unlock_bh(&keymap_lock); return 0; } @@ -145,32 +140,30 @@ EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_add); /* destroy the keymap entries associated with specified master ct */ void nf_ct_gre_keymap_destroy(struct nf_conn *ct) { - struct net *net = nf_ct_net(ct); - struct netns_proto_gre *net_gre = gre_pernet(net); struct nf_ct_pptp_master *ct_pptp_info = nfct_help_data(ct); enum ip_conntrack_dir dir; pr_debug("entering for ct %p\n", ct); - write_lock_bh(&net_gre->keymap_lock); + spin_lock_bh(&keymap_lock); for (dir = IP_CT_DIR_ORIGINAL; dir < IP_CT_DIR_MAX; dir++) { if (ct_pptp_info->keymap[dir]) { pr_debug("removing %p from list\n", ct_pptp_info->keymap[dir]); - list_del(&ct_pptp_info->keymap[dir]->list); - kfree(ct_pptp_info->keymap[dir]); + list_del_rcu(&ct_pptp_info->keymap[dir]->list); + kfree_rcu(ct_pptp_info->keymap[dir], rcu); ct_pptp_info->keymap[dir] = NULL; } } - write_unlock_bh(&net_gre->keymap_lock); + spin_unlock_bh(&keymap_lock); } EXPORT_SYMBOL_GPL(nf_ct_gre_keymap_destroy); /* PUBLIC CONNTRACK PROTO HELPER FUNCTIONS */ /* gre hdr info to tuple */ -static bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) +bool gre_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct pptp_gre_header *pgrehdr; struct pptp_gre_header _pgrehdr; @@ -216,15 +209,15 @@ static void gre_print_conntrack(struct seq_file *s, struct nf_conn *ct) static unsigned int *gre_get_timeouts(struct net *net) { - return gre_pernet(net)->gre_timeouts; + return gre_pernet(net)->timeouts; } /* Returns verdict for packet, and may modify conntrack */ -static int gre_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_gre_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { if (state->pf != NFPROTO_IPV4) return -NF_ACCEPT; @@ -256,19 +249,6 @@ static int gre_packet(struct nf_conn *ct, return NF_ACCEPT; } -/* Called when a conntrack entry has already been removed from the hashes - * and is about to be deleted from memory */ -static void gre_destroy(struct nf_conn *ct) -{ - struct nf_conn *master = ct->master; - pr_debug(" entering\n"); - - if (!master) - pr_debug("no master !?!\n"); - else - nf_ct_gre_keymap_destroy(master); -} - #ifdef CONFIG_NF_CONNTRACK_TIMEOUT #include <linux/netfilter/nfnetlink.h> @@ -278,13 +258,13 @@ static int gre_timeout_nlattr_to_obj(struct nlattr *tb[], struct net *net, void *data) { unsigned int *timeouts = data; - struct netns_proto_gre *net_gre = gre_pernet(net); + struct nf_gre_net *net_gre = gre_pernet(net); if (!timeouts) timeouts = gre_get_timeouts(net); /* set default timeouts for GRE. */ - timeouts[GRE_CT_UNREPLIED] = net_gre->gre_timeouts[GRE_CT_UNREPLIED]; - timeouts[GRE_CT_REPLIED] = net_gre->gre_timeouts[GRE_CT_REPLIED]; + timeouts[GRE_CT_UNREPLIED] = net_gre->timeouts[GRE_CT_UNREPLIED]; + timeouts[GRE_CT_REPLIED] = net_gre->timeouts[GRE_CT_REPLIED]; if (tb[CTA_TIMEOUT_GRE_UNREPLIED]) { timeouts[GRE_CT_UNREPLIED] = @@ -320,69 +300,22 @@ gre_timeout_nla_policy[CTA_TIMEOUT_GRE_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -static struct ctl_table gre_sysctl_table[] = { - { - .procname = "nf_conntrack_gre_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_gre_timeout_stream", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - {} -}; -#endif - -static int gre_kmemdup_sysctl_table(struct net *net, struct nf_proto_net *nf, - struct netns_proto_gre *net_gre) -{ -#ifdef CONFIG_SYSCTL - int i; - - if (nf->ctl_table) - return 0; - - nf->ctl_table = kmemdup(gre_sysctl_table, - sizeof(gre_sysctl_table), - GFP_KERNEL); - if (!nf->ctl_table) - return -ENOMEM; - - for (i = 0; i < GRE_CT_MAX; i++) - nf->ctl_table[i].data = &net_gre->gre_timeouts[i]; -#endif - return 0; -} - -static int gre_init_net(struct net *net) +void nf_conntrack_gre_init_net(struct net *net) { - struct netns_proto_gre *net_gre = gre_pernet(net); - struct nf_proto_net *nf = &net_gre->nf; + struct nf_gre_net *net_gre = gre_pernet(net); int i; - rwlock_init(&net_gre->keymap_lock); INIT_LIST_HEAD(&net_gre->keymap_list); for (i = 0; i < GRE_CT_MAX; i++) - net_gre->gre_timeouts[i] = gre_timeouts[i]; - - return gre_kmemdup_sysctl_table(net, nf, net_gre); + net_gre->timeouts[i] = gre_timeouts[i]; } /* protocol helper struct */ -static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { +const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre = { .l4proto = IPPROTO_GRE, - .pkt_to_tuple = gre_pkt_to_tuple, #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = gre_print_conntrack, #endif - .packet = gre_packet, - .destroy = gre_destroy, - .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_tuple_size = nf_ct_port_nlattr_tuple_size, @@ -398,61 +331,4 @@ static const struct nf_conntrack_l4proto nf_conntrack_l4proto_gre4 = { .nla_policy = gre_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .net_id = &proto_gre_net_id, - .init_net = gre_init_net, }; - -static int proto_gre_net_init(struct net *net) -{ - int ret = 0; - - ret = nf_ct_l4proto_pernet_register_one(net, - &nf_conntrack_l4proto_gre4); - if (ret < 0) - pr_err("nf_conntrack_gre4: pernet registration failed.\n"); - return ret; -} - -static void proto_gre_net_exit(struct net *net) -{ - nf_ct_l4proto_pernet_unregister_one(net, &nf_conntrack_l4proto_gre4); - nf_ct_gre_keymap_flush(net); -} - -static struct pernet_operations proto_gre_net_ops = { - .init = proto_gre_net_init, - .exit = proto_gre_net_exit, - .id = &proto_gre_net_id, - .size = sizeof(struct netns_proto_gre), -}; - -static int __init nf_ct_proto_gre_init(void) -{ - int ret; - - BUILD_BUG_ON(offsetof(struct netns_proto_gre, nf) != 0); - - ret = register_pernet_subsys(&proto_gre_net_ops); - if (ret < 0) - goto out_pernet; - ret = nf_ct_l4proto_register_one(&nf_conntrack_l4proto_gre4); - if (ret < 0) - goto out_gre4; - - return 0; -out_gre4: - unregister_pernet_subsys(&proto_gre_net_ops); -out_pernet: - return ret; -} - -static void __exit nf_ct_proto_gre_fini(void) -{ - nf_ct_l4proto_unregister_one(&nf_conntrack_l4proto_gre4); - unregister_pernet_subsys(&proto_gre_net_ops); -} - -module_init(nf_ct_proto_gre_init); -module_exit(nf_ct_proto_gre_fini); - -MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_conntrack_proto_icmp.c b/net/netfilter/nf_conntrack_proto_icmp.c index de64d8a5fdfd..7df477996b16 100644 --- a/net/netfilter/nf_conntrack_proto_icmp.c +++ b/net/netfilter/nf_conntrack_proto_icmp.c @@ -25,8 +25,8 @@ static const unsigned int nf_ct_icmp_timeout = 30*HZ; -static bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, - struct net *net, struct nf_conntrack_tuple *tuple) +bool icmp_pkt_to_tuple(const struct sk_buff *skb, unsigned int dataoff, + struct net *net, struct nf_conntrack_tuple *tuple) { const struct icmphdr *hp; struct icmphdr _hdr; @@ -54,8 +54,8 @@ static const u_int8_t invmap[] = { [ICMP_ADDRESSREPLY] = ICMP_ADDRESS + 1 }; -static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) +bool nf_conntrack_invert_icmp_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) { if (orig->dst.u.icmp.type >= sizeof(invmap) || !invmap[orig->dst.u.icmp.type]) @@ -68,11 +68,10 @@ static bool icmp_invert_tuple(struct nf_conntrack_tuple *tuple, } /* Returns verdict for packet, or -1 for invalid. */ -static int icmp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_icmp_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { /* Do not immediately delete the connection after the first successful reply to avoid excessive conntrackd traffic @@ -110,7 +109,6 @@ icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, const struct nf_hook_state *state) { struct nf_conntrack_tuple innertuple, origtuple; - const struct nf_conntrack_l4proto *innerproto; const struct nf_conntrack_tuple_hash *h; const struct nf_conntrack_zone *zone; enum ip_conntrack_info ctinfo; @@ -128,12 +126,9 @@ icmp_error_message(struct nf_conn *tmpl, struct sk_buff *skb, return -NF_ACCEPT; } - /* rcu_read_lock()ed by nf_hook_thresh */ - innerproto = __nf_ct_l4proto_find(origtuple.dst.protonum); - /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&innertuple, &origtuple, innerproto)) { + if (!nf_ct_invert_tuple(&innertuple, &origtuple)) { pr_debug("icmp_error_message: no match\n"); return -NF_ACCEPT; } @@ -303,56 +298,16 @@ icmp_timeout_nla_policy[CTA_TIMEOUT_ICMP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -static struct ctl_table icmp_sysctl_table[] = { - { - .procname = "nf_conntrack_icmp_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int icmp_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_icmp_net *in) -{ -#ifdef CONFIG_SYSCTL - pn->ctl_table = kmemdup(icmp_sysctl_table, - sizeof(icmp_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &in->timeout; -#endif - return 0; -} - -static int icmp_init_net(struct net *net) +void nf_conntrack_icmp_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmp_pernet(net); - struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmp_timeout; - - return icmp_kmemdup_sysctl_table(pn, in); -} - -static struct nf_proto_net *icmp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.icmp.pn; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = { .l4proto = IPPROTO_ICMP, - .pkt_to_tuple = icmp_pkt_to_tuple, - .invert_tuple = icmp_invert_tuple, - .packet = icmp_packet, - .destroy = NULL, - .me = NULL, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmp_tuple_to_nlattr, .nlattr_tuple_size = icmp_nlattr_tuple_size, @@ -368,6 +323,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmp = .nla_policy = icmp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = icmp_init_net, - .get_net_proto = icmp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_icmpv6.c b/net/netfilter/nf_conntrack_proto_icmpv6.c index a15eefb8e317..bec4a3211658 100644 --- a/net/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/netfilter/nf_conntrack_proto_icmpv6.c @@ -30,10 +30,10 @@ static const unsigned int nf_ct_icmpv6_timeout = 30*HZ; -static bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, - unsigned int dataoff, - struct net *net, - struct nf_conntrack_tuple *tuple) +bool icmpv6_pkt_to_tuple(const struct sk_buff *skb, + unsigned int dataoff, + struct net *net, + struct nf_conntrack_tuple *tuple) { const struct icmp6hdr *hp; struct icmp6hdr _hdr; @@ -67,8 +67,8 @@ static const u_int8_t noct_valid_new[] = { [ICMPV6_MLD2_REPORT - 130] = 1 }; -static bool icmpv6_invert_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_conntrack_tuple *orig) +bool nf_conntrack_invert_icmpv6_tuple(struct nf_conntrack_tuple *tuple, + const struct nf_conntrack_tuple *orig) { int type = orig->dst.u.icmp.type - 128; if (type < 0 || type >= sizeof(invmap) || !invmap[type]) @@ -86,11 +86,10 @@ static unsigned int *icmpv6_get_timeouts(struct net *net) } /* Returns verdict for packet, or -1 for invalid. */ -static int icmpv6_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_icmpv6_packet(struct nf_conn *ct, + struct sk_buff *skb, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { unsigned int *timeout = nf_ct_timeout_lookup(ct); static const u8 valid_new[] = { @@ -131,7 +130,6 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, { struct nf_conntrack_tuple intuple, origtuple; const struct nf_conntrack_tuple_hash *h; - const struct nf_conntrack_l4proto *inproto; enum ip_conntrack_info ctinfo; struct nf_conntrack_zone tmp; @@ -147,12 +145,9 @@ icmpv6_error_message(struct net *net, struct nf_conn *tmpl, return -NF_ACCEPT; } - /* rcu_read_lock()ed by nf_hook_thresh */ - inproto = __nf_ct_l4proto_find(origtuple.dst.protonum); - /* Ordinarily, we'd expect the inverted tupleproto, but it's been preserved inside the ICMP. */ - if (!nf_ct_invert_tuple(&intuple, &origtuple, inproto)) { + if (!nf_ct_invert_tuple(&intuple, &origtuple)) { pr_debug("icmpv6_error: Can't invert tuple\n"); return -NF_ACCEPT; } @@ -314,54 +309,16 @@ icmpv6_timeout_nla_policy[CTA_TIMEOUT_ICMPV6_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -static struct ctl_table icmpv6_sysctl_table[] = { - { - .procname = "nf_conntrack_icmpv6_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int icmpv6_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_icmp_net *in) -{ -#ifdef CONFIG_SYSCTL - pn->ctl_table = kmemdup(icmpv6_sysctl_table, - sizeof(icmpv6_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &in->timeout; -#endif - return 0; -} - -static int icmpv6_init_net(struct net *net) +void nf_conntrack_icmpv6_init_net(struct net *net) { struct nf_icmp_net *in = nf_icmpv6_pernet(net); - struct nf_proto_net *pn = &in->pn; in->timeout = nf_ct_icmpv6_timeout; - - return icmpv6_kmemdup_sysctl_table(pn, in); -} - -static struct nf_proto_net *icmpv6_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.icmpv6.pn; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = { .l4proto = IPPROTO_ICMPV6, - .pkt_to_tuple = icmpv6_pkt_to_tuple, - .invert_tuple = icmpv6_invert_tuple, - .packet = icmpv6_packet, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = icmpv6_tuple_to_nlattr, .nlattr_tuple_size = icmpv6_nlattr_tuple_size, @@ -377,6 +334,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_icmpv6 = .nla_policy = icmpv6_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = icmpv6_init_net, - .get_net_proto = icmpv6_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_sctp.c b/net/netfilter/nf_conntrack_proto_sctp.c index d53e3e78f605..a7818101ad80 100644 --- a/net/netfilter/nf_conntrack_proto_sctp.c +++ b/net/netfilter/nf_conntrack_proto_sctp.c @@ -357,11 +357,11 @@ out_invalid: } /* Returns verdict for packet, or -NF_ACCEPT for invalid. */ -static int sctp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_sctp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { enum sctp_conntrack new_state, old_state; enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); @@ -642,116 +642,18 @@ sctp_timeout_nla_policy[CTA_TIMEOUT_SCTP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - -#ifdef CONFIG_SYSCTL -static struct ctl_table sctp_sysctl_table[] = { - { - .procname = "nf_conntrack_sctp_timeout_closed", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_cookie_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_cookie_echoed", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_established", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_shutdown_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_shutdown_recd", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_shutdown_ack_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_heartbeat_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif - -static int sctp_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_sctp_net *sn) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table) - return 0; - - pn->ctl_table = kmemdup(sctp_sysctl_table, - sizeof(sctp_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &sn->timeouts[SCTP_CONNTRACK_CLOSED]; - pn->ctl_table[1].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_WAIT]; - pn->ctl_table[2].data = &sn->timeouts[SCTP_CONNTRACK_COOKIE_ECHOED]; - pn->ctl_table[3].data = &sn->timeouts[SCTP_CONNTRACK_ESTABLISHED]; - pn->ctl_table[4].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_SENT]; - pn->ctl_table[5].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_RECD]; - pn->ctl_table[6].data = &sn->timeouts[SCTP_CONNTRACK_SHUTDOWN_ACK_SENT]; - pn->ctl_table[7].data = &sn->timeouts[SCTP_CONNTRACK_HEARTBEAT_SENT]; - pn->ctl_table[8].data = &sn->timeouts[SCTP_CONNTRACK_HEARTBEAT_ACKED]; -#endif - return 0; -} - -static int sctp_init_net(struct net *net) +void nf_conntrack_sctp_init_net(struct net *net) { struct nf_sctp_net *sn = nf_sctp_pernet(net); - struct nf_proto_net *pn = &sn->pn; - - if (!pn->users) { - int i; - - for (i = 0; i < SCTP_CONNTRACK_MAX; i++) - sn->timeouts[i] = sctp_timeouts[i]; - - /* timeouts[0] is unused, init it so ->timeouts[0] contains - * 'new' timeout, like udp or icmp. - */ - sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; - } + int i; - return sctp_kmemdup_sysctl_table(pn, sn); -} + for (i = 0; i < SCTP_CONNTRACK_MAX; i++) + sn->timeouts[i] = sctp_timeouts[i]; -static struct nf_proto_net *sctp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.sctp.pn; + /* timeouts[0] is unused, init it so ->timeouts[0] contains + * 'new' timeout, like udp or icmp. + */ + sn->timeouts[0] = sctp_timeouts[SCTP_CONNTRACK_CLOSED]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { @@ -759,9 +661,7 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = sctp_print_conntrack, #endif - .packet = sctp_packet, .can_early_drop = sctp_can_early_drop, - .me = THIS_MODULE, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .nlattr_size = SCTP_NLATTR_SIZE, .to_nlattr = sctp_to_nlattr, @@ -780,6 +680,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_sctp = { .nla_policy = sctp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = sctp_init_net, - .get_net_proto = sctp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_tcp.c b/net/netfilter/nf_conntrack_proto_tcp.c index 4dcbd51a8e97..01c748fa8913 100644 --- a/net/netfilter/nf_conntrack_proto_tcp.c +++ b/net/netfilter/nf_conntrack_proto_tcp.c @@ -829,11 +829,11 @@ static noinline bool tcp_new(struct nf_conn *ct, const struct sk_buff *skb, } /* Returns verdict for packet, or -1 for invalid. */ -static int tcp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_tcp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { struct net *net = nf_ct_net(ct); struct nf_tcp_net *tn = nf_tcp_pernet(net); @@ -1387,146 +1387,21 @@ static const struct nla_policy tcp_timeout_nla_policy[CTA_TIMEOUT_TCP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -static struct ctl_table tcp_sysctl_table[] = { - { - .procname = "nf_conntrack_tcp_timeout_syn_sent", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_syn_recv", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_established", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_fin_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_close_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_last_ack", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_time_wait", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_close", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_max_retrans", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_timeout_unacknowledged", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_tcp_loose", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "nf_conntrack_tcp_be_liberal", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { - .procname = "nf_conntrack_tcp_max_retrans", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int tcp_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_tcp_net *tn) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table) - return 0; - - pn->ctl_table = kmemdup(tcp_sysctl_table, - sizeof(tcp_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - - pn->ctl_table[0].data = &tn->timeouts[TCP_CONNTRACK_SYN_SENT]; - pn->ctl_table[1].data = &tn->timeouts[TCP_CONNTRACK_SYN_RECV]; - pn->ctl_table[2].data = &tn->timeouts[TCP_CONNTRACK_ESTABLISHED]; - pn->ctl_table[3].data = &tn->timeouts[TCP_CONNTRACK_FIN_WAIT]; - pn->ctl_table[4].data = &tn->timeouts[TCP_CONNTRACK_CLOSE_WAIT]; - pn->ctl_table[5].data = &tn->timeouts[TCP_CONNTRACK_LAST_ACK]; - pn->ctl_table[6].data = &tn->timeouts[TCP_CONNTRACK_TIME_WAIT]; - pn->ctl_table[7].data = &tn->timeouts[TCP_CONNTRACK_CLOSE]; - pn->ctl_table[8].data = &tn->timeouts[TCP_CONNTRACK_RETRANS]; - pn->ctl_table[9].data = &tn->timeouts[TCP_CONNTRACK_UNACK]; - pn->ctl_table[10].data = &tn->tcp_loose; - pn->ctl_table[11].data = &tn->tcp_be_liberal; - pn->ctl_table[12].data = &tn->tcp_max_retrans; -#endif - return 0; -} - -static int tcp_init_net(struct net *net) +void nf_conntrack_tcp_init_net(struct net *net) { struct nf_tcp_net *tn = nf_tcp_pernet(net); - struct nf_proto_net *pn = &tn->pn; - - if (!pn->users) { - int i; - - for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) - tn->timeouts[i] = tcp_timeouts[i]; - - /* timeouts[0] is unused, make it same as SYN_SENT so - * ->timeouts[0] contains 'new' timeout, like udp or icmp. - */ - tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; - tn->tcp_loose = nf_ct_tcp_loose; - tn->tcp_be_liberal = nf_ct_tcp_be_liberal; - tn->tcp_max_retrans = nf_ct_tcp_max_retrans; - } + int i; - return tcp_kmemdup_sysctl_table(pn, tn); -} + for (i = 0; i < TCP_CONNTRACK_TIMEOUT_MAX; i++) + tn->timeouts[i] = tcp_timeouts[i]; -static struct nf_proto_net *tcp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.tcp.pn; + /* timeouts[0] is unused, make it same as SYN_SENT so + * ->timeouts[0] contains 'new' timeout, like udp or icmp. + */ + tn->timeouts[0] = tcp_timeouts[TCP_CONNTRACK_SYN_SENT]; + tn->tcp_loose = nf_ct_tcp_loose; + tn->tcp_be_liberal = nf_ct_tcp_be_liberal; + tn->tcp_max_retrans = nf_ct_tcp_max_retrans; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = @@ -1535,7 +1410,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = #ifdef CONFIG_NF_CONNTRACK_PROCFS .print_conntrack = tcp_print_conntrack, #endif - .packet = tcp_packet, .can_early_drop = tcp_can_early_drop, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .to_nlattr = tcp_to_nlattr, @@ -1556,6 +1430,4 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_tcp = .nla_policy = tcp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = tcp_init_net, - .get_net_proto = tcp_get_net_proto, }; diff --git a/net/netfilter/nf_conntrack_proto_udp.c b/net/netfilter/nf_conntrack_proto_udp.c index b4f5d5e82031..951366dfbec3 100644 --- a/net/netfilter/nf_conntrack_proto_udp.c +++ b/net/netfilter/nf_conntrack_proto_udp.c @@ -85,11 +85,11 @@ static bool udp_error(struct sk_buff *skb, } /* Returns verdict for packet, and may modify conntracktype */ -static int udp_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_udp_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { unsigned int *timeouts; @@ -177,11 +177,11 @@ static bool udplite_error(struct sk_buff *skb, } /* Returns verdict for packet, and may modify conntracktype */ -static int udplite_packet(struct nf_conn *ct, - struct sk_buff *skb, - unsigned int dataoff, - enum ip_conntrack_info ctinfo, - const struct nf_hook_state *state) +int nf_conntrack_udplite_packet(struct nf_conn *ct, + struct sk_buff *skb, + unsigned int dataoff, + enum ip_conntrack_info ctinfo, + const struct nf_hook_state *state) { unsigned int *timeouts; @@ -260,66 +260,19 @@ udp_timeout_nla_policy[CTA_TIMEOUT_UDP_MAX+1] = { }; #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ -#ifdef CONFIG_SYSCTL -static struct ctl_table udp_sysctl_table[] = { - { - .procname = "nf_conntrack_udp_timeout", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { - .procname = "nf_conntrack_udp_timeout_stream", - .maxlen = sizeof(unsigned int), - .mode = 0644, - .proc_handler = proc_dointvec_jiffies, - }, - { } -}; -#endif /* CONFIG_SYSCTL */ - -static int udp_kmemdup_sysctl_table(struct nf_proto_net *pn, - struct nf_udp_net *un) -{ -#ifdef CONFIG_SYSCTL - if (pn->ctl_table) - return 0; - pn->ctl_table = kmemdup(udp_sysctl_table, - sizeof(udp_sysctl_table), - GFP_KERNEL); - if (!pn->ctl_table) - return -ENOMEM; - pn->ctl_table[0].data = &un->timeouts[UDP_CT_UNREPLIED]; - pn->ctl_table[1].data = &un->timeouts[UDP_CT_REPLIED]; -#endif - return 0; -} - -static int udp_init_net(struct net *net) +void nf_conntrack_udp_init_net(struct net *net) { struct nf_udp_net *un = nf_udp_pernet(net); - struct nf_proto_net *pn = &un->pn; + int i; - if (!pn->users) { - int i; - - for (i = 0; i < UDP_CT_MAX; i++) - un->timeouts[i] = udp_timeouts[i]; - } - - return udp_kmemdup_sysctl_table(pn, un); -} - -static struct nf_proto_net *udp_get_net_proto(struct net *net) -{ - return &net->ct.nf_ct_proto.udp.pn; + for (i = 0; i < UDP_CT_MAX; i++) + un->timeouts[i] = udp_timeouts[i]; } const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = { .l4proto = IPPROTO_UDP, .allow_clash = true, - .packet = udp_packet, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, @@ -335,8 +288,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udp = .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = udp_init_net, - .get_net_proto = udp_get_net_proto, }; #ifdef CONFIG_NF_CT_PROTO_UDPLITE @@ -344,7 +295,6 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite = { .l4proto = IPPROTO_UDPLITE, .allow_clash = true, - .packet = udplite_packet, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) .tuple_to_nlattr = nf_ct_port_tuple_to_nlattr, .nlattr_to_tuple = nf_ct_port_nlattr_to_tuple, @@ -360,7 +310,5 @@ const struct nf_conntrack_l4proto nf_conntrack_l4proto_udplite = .nla_policy = udp_timeout_nla_policy, }, #endif /* CONFIG_NF_CONNTRACK_TIMEOUT */ - .init_net = udp_init_net, - .get_net_proto = udp_get_net_proto, }; #endif diff --git a/net/netfilter/nf_conntrack_standalone.c b/net/netfilter/nf_conntrack_standalone.c index b6177fd73304..c2ae14c720b4 100644 --- a/net/netfilter/nf_conntrack_standalone.c +++ b/net/netfilter/nf_conntrack_standalone.c @@ -24,6 +24,10 @@ #include <net/netfilter/nf_conntrack_timestamp.h> #include <linux/rculist_nulls.h> +static bool enable_hooks __read_mostly; +MODULE_PARM_DESC(enable_hooks, "Always enable conntrack hooks"); +module_param(enable_hooks, bool, 0000); + unsigned int nf_conntrack_net_id __read_mostly; #ifdef CONFIG_NF_CONNTRACK_PROCFS @@ -310,8 +314,7 @@ static int ct_seq_show(struct seq_file *s, void *v) if (!net_eq(nf_ct_net(ct), net)) goto release; - l4proto = __nf_ct_l4proto_find(nf_ct_protonum(ct)); - WARN_ON(!l4proto); + l4proto = nf_ct_l4proto_find(nf_ct_protonum(ct)); ret = -ENOSPC; seq_printf(s, "%-8s %u %-8s %u ", @@ -547,8 +550,55 @@ enum nf_ct_sysctl_index { #ifdef CONFIG_NF_CONNTRACK_TIMESTAMP NF_SYSCTL_CT_TIMESTAMP, #endif + NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_SENT, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_RECV, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ESTABLISHED, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_FIN_WAIT, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE_WAIT, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_LAST_ACK, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_TIME_WAIT, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS, + NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK, + NF_SYSCTL_CT_PROTO_TCP_LOOSE, + NF_SYSCTL_CT_PROTO_TCP_LIBERAL, + NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS, + NF_SYSCTL_CT_PROTO_TIMEOUT_UDP, + NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM, + NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP, + NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6, +#ifdef CONFIG_NF_CT_PROTO_SCTP + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_CLOSED, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_WAIT, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_ECHOED, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ESTABLISHED, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_SENT, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT, + NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED, +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST, + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_RESPOND, + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_PARTOPEN, + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_OPEN, + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSEREQ, + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSING, + NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_TIMEWAIT, + NF_SYSCTL_CT_PROTO_DCCP_LOOSE, +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + NF_SYSCTL_CT_PROTO_TIMEOUT_GRE, + NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM, +#endif + + __NF_SYSCTL_CT_LAST_SYSCTL, }; +#define NF_SYSCTL_CT_LAST_SYSCTL (__NF_SYSCTL_CT_LAST_SYSCTL + 1) + static struct ctl_table nf_ct_sysctl_table[] = { [NF_SYSCTL_CT_MAX] = { .procname = "nf_conntrack_max", @@ -626,7 +676,235 @@ static struct ctl_table nf_ct_sysctl_table[] = { .proc_handler = proc_dointvec, }, #endif - { } + [NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC] = { + .procname = "nf_conntrack_generic_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_SENT] = { + .procname = "nf_conntrack_tcp_timeout_syn_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_SYN_RECV] = { + .procname = "nf_conntrack_tcp_timeout_syn_recv", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ESTABLISHED] = { + .procname = "nf_conntrack_tcp_timeout_established", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_FIN_WAIT] = { + .procname = "nf_conntrack_tcp_timeout_fin_wait", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE_WAIT] = { + .procname = "nf_conntrack_tcp_timeout_close_wait", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_LAST_ACK] = { + .procname = "nf_conntrack_tcp_timeout_last_ack", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_TIME_WAIT] = { + .procname = "nf_conntrack_tcp_timeout_time_wait", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_CLOSE] = { + .procname = "nf_conntrack_tcp_timeout_close", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_RETRANS] = { + .procname = "nf_conntrack_tcp_timeout_max_retrans", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_UNACK] = { + .procname = "nf_conntrack_tcp_timeout_unacknowledged", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TCP_LOOSE] = { + .procname = "nf_conntrack_tcp_loose", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + [NF_SYSCTL_CT_PROTO_TCP_LIBERAL] = { + .procname = "nf_conntrack_tcp_be_liberal", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + [NF_SYSCTL_CT_PROTO_TCP_MAX_RETRANS] = { + .procname = "nf_conntrack_tcp_max_retrans", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP] = { + .procname = "nf_conntrack_udp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM] = { + .procname = "nf_conntrack_udp_timeout_stream", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP] = { + .procname = "nf_conntrack_icmp_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6] = { + .procname = "nf_conntrack_icmpv6_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#ifdef CONFIG_NF_CT_PROTO_SCTP + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_CLOSED] = { + .procname = "nf_conntrack_sctp_timeout_closed", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_WAIT] = { + .procname = "nf_conntrack_sctp_timeout_cookie_wait", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_COOKIE_ECHOED] = { + .procname = "nf_conntrack_sctp_timeout_cookie_echoed", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ESTABLISHED] = { + .procname = "nf_conntrack_sctp_timeout_established", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_SENT] = { + .procname = "nf_conntrack_sctp_timeout_shutdown_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_RECD] = { + .procname = "nf_conntrack_sctp_timeout_shutdown_recd", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_SHUTDOWN_ACK_SENT] = { + .procname = "nf_conntrack_sctp_timeout_shutdown_ack_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_SENT] = { + .procname = "nf_conntrack_sctp_timeout_heartbeat_sent", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_HEARTBEAT_ACKED] = { + .procname = "nf_conntrack_sctp_timeout_heartbeat_acked", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif +#ifdef CONFIG_NF_CT_PROTO_DCCP + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_REQUEST] = { + .procname = "nf_conntrack_dccp_timeout_request", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_RESPOND] = { + .procname = "nf_conntrack_dccp_timeout_respond", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_PARTOPEN] = { + .procname = "nf_conntrack_dccp_timeout_partopen", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_OPEN] = { + .procname = "nf_conntrack_dccp_timeout_open", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSEREQ] = { + .procname = "nf_conntrack_dccp_timeout_closereq", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_CLOSING] = { + .procname = "nf_conntrack_dccp_timeout_closing", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_TIMEWAIT] = { + .procname = "nf_conntrack_dccp_timeout_timewait", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_DCCP_LOOSE] = { + .procname = "nf_conntrack_dccp_loose", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, +#endif +#ifdef CONFIG_NF_CT_PROTO_GRE + [NF_SYSCTL_CT_PROTO_TIMEOUT_GRE] = { + .procname = "nf_conntrack_gre_timeout", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + [NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM] = { + .procname = "nf_conntrack_gre_timeout_stream", + .maxlen = sizeof(unsigned int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, +#endif + {} }; static struct ctl_table nf_ct_netfilter_table[] = { @@ -640,14 +918,103 @@ static struct ctl_table nf_ct_netfilter_table[] = { { } }; +static void nf_conntrack_standalone_init_tcp_sysctl(struct net *net, + struct ctl_table *table) +{ + struct nf_tcp_net *tn = nf_tcp_pernet(net); + +#define XASSIGN(XNAME, tn) \ + table[NF_SYSCTL_CT_PROTO_TIMEOUT_TCP_ ## XNAME].data = \ + &(tn)->timeouts[TCP_CONNTRACK_ ## XNAME] + + XASSIGN(SYN_SENT, tn); + XASSIGN(SYN_RECV, tn); + XASSIGN(ESTABLISHED, tn); + XASSIGN(FIN_WAIT, tn); + XASSIGN(CLOSE_WAIT, tn); + XASSIGN(LAST_ACK, tn); + XASSIGN(TIME_WAIT, tn); + XASSIGN(CLOSE, tn); + XASSIGN(RETRANS, tn); + XASSIGN(UNACK, tn); +#undef XASSIGN +#define XASSIGN(XNAME, rval) \ + table[NF_SYSCTL_CT_PROTO_TCP_ ## XNAME].data = (rval) + + XASSIGN(LOOSE, &tn->tcp_loose); + XASSIGN(LIBERAL, &tn->tcp_be_liberal); + XASSIGN(MAX_RETRANS, &tn->tcp_max_retrans); +#undef XASSIGN +} + +static void nf_conntrack_standalone_init_sctp_sysctl(struct net *net, + struct ctl_table *table) +{ +#ifdef CONFIG_NF_CT_PROTO_SCTP + struct nf_sctp_net *sn = nf_sctp_pernet(net); + +#define XASSIGN(XNAME, sn) \ + table[NF_SYSCTL_CT_PROTO_TIMEOUT_SCTP_ ## XNAME].data = \ + &(sn)->timeouts[SCTP_CONNTRACK_ ## XNAME] + + XASSIGN(CLOSED, sn); + XASSIGN(COOKIE_WAIT, sn); + XASSIGN(COOKIE_ECHOED, sn); + XASSIGN(ESTABLISHED, sn); + XASSIGN(SHUTDOWN_SENT, sn); + XASSIGN(SHUTDOWN_RECD, sn); + XASSIGN(SHUTDOWN_ACK_SENT, sn); + XASSIGN(HEARTBEAT_SENT, sn); + XASSIGN(HEARTBEAT_ACKED, sn); +#undef XASSIGN +#endif +} + +static void nf_conntrack_standalone_init_dccp_sysctl(struct net *net, + struct ctl_table *table) +{ +#ifdef CONFIG_NF_CT_PROTO_DCCP + struct nf_dccp_net *dn = nf_dccp_pernet(net); + +#define XASSIGN(XNAME, dn) \ + table[NF_SYSCTL_CT_PROTO_TIMEOUT_DCCP_ ## XNAME].data = \ + &(dn)->dccp_timeout[CT_DCCP_ ## XNAME] + + XASSIGN(REQUEST, dn); + XASSIGN(RESPOND, dn); + XASSIGN(PARTOPEN, dn); + XASSIGN(OPEN, dn); + XASSIGN(CLOSEREQ, dn); + XASSIGN(CLOSING, dn); + XASSIGN(TIMEWAIT, dn); +#undef XASSIGN + + table[NF_SYSCTL_CT_PROTO_DCCP_LOOSE].data = &dn->dccp_loose; +#endif +} + +static void nf_conntrack_standalone_init_gre_sysctl(struct net *net, + struct ctl_table *table) +{ +#ifdef CONFIG_NF_CT_PROTO_GRE + struct nf_gre_net *gn = nf_gre_pernet(net); + + table[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE].data = &gn->timeouts[GRE_CT_UNREPLIED]; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_GRE_STREAM].data = &gn->timeouts[GRE_CT_REPLIED]; +#endif +} + static int nf_conntrack_standalone_init_sysctl(struct net *net) { + struct nf_udp_net *un = nf_udp_pernet(net); struct ctl_table *table; + BUILD_BUG_ON(ARRAY_SIZE(nf_ct_sysctl_table) != NF_SYSCTL_CT_LAST_SYSCTL); + table = kmemdup(nf_ct_sysctl_table, sizeof(nf_ct_sysctl_table), GFP_KERNEL); if (!table) - goto out_kmemdup; + return -ENOMEM; table[NF_SYSCTL_CT_COUNT].data = &net->ct.count; table[NF_SYSCTL_CT_CHECKSUM].data = &net->ct.sysctl_checksum; @@ -655,6 +1022,16 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) #ifdef CONFIG_NF_CONNTRACK_EVENTS table[NF_SYSCTL_CT_EVENTS].data = &net->ct.sysctl_events; #endif + table[NF_SYSCTL_CT_PROTO_TIMEOUT_GENERIC].data = &nf_generic_pernet(net)->timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMP].data = &nf_icmp_pernet(net)->timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_ICMPV6].data = &nf_icmpv6_pernet(net)->timeout; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP].data = &un->timeouts[UDP_CT_UNREPLIED]; + table[NF_SYSCTL_CT_PROTO_TIMEOUT_UDP_STREAM].data = &un->timeouts[UDP_CT_REPLIED]; + + nf_conntrack_standalone_init_tcp_sysctl(net, table); + nf_conntrack_standalone_init_sctp_sysctl(net, table); + nf_conntrack_standalone_init_dccp_sysctl(net, table); + nf_conntrack_standalone_init_gre_sysctl(net, table); /* Don't export sysctls to unprivileged users */ if (net->user_ns != &init_user_ns) { @@ -680,7 +1057,6 @@ static int nf_conntrack_standalone_init_sysctl(struct net *net) out_unregister_netfilter: kfree(table); -out_kmemdup: return -ENOMEM; } @@ -703,31 +1079,47 @@ static void nf_conntrack_standalone_fini_sysctl(struct net *net) } #endif /* CONFIG_SYSCTL */ +static void nf_conntrack_fini_net(struct net *net) +{ + if (enable_hooks) + nf_ct_netns_put(net, NFPROTO_INET); + + nf_conntrack_standalone_fini_proc(net); + nf_conntrack_standalone_fini_sysctl(net); +} + static int nf_conntrack_pernet_init(struct net *net) { int ret; - ret = nf_conntrack_init_net(net); + net->ct.sysctl_checksum = 1; + + ret = nf_conntrack_standalone_init_sysctl(net); if (ret < 0) - goto out_init; + return ret; ret = nf_conntrack_standalone_init_proc(net); if (ret < 0) goto out_proc; - net->ct.sysctl_checksum = 1; - net->ct.sysctl_log_invalid = 0; - ret = nf_conntrack_standalone_init_sysctl(net); + ret = nf_conntrack_init_net(net); if (ret < 0) - goto out_sysctl; + goto out_init_net; + + if (enable_hooks) { + ret = nf_ct_netns_get(net, NFPROTO_INET); + if (ret < 0) + goto out_hooks; + } return 0; -out_sysctl: +out_hooks: + nf_conntrack_cleanup_net(net); +out_init_net: nf_conntrack_standalone_fini_proc(net); out_proc: - nf_conntrack_cleanup_net(net); -out_init: + nf_conntrack_standalone_fini_sysctl(net); return ret; } @@ -735,10 +1127,9 @@ static void nf_conntrack_pernet_exit(struct list_head *net_exit_list) { struct net *net; - list_for_each_entry(net, net_exit_list, exit_list) { - nf_conntrack_standalone_fini_sysctl(net); - nf_conntrack_standalone_fini_proc(net); - } + list_for_each_entry(net, net_exit_list, exit_list) + nf_conntrack_fini_net(net); + nf_conntrack_cleanup_net_list(net_exit_list); } diff --git a/net/netfilter/nf_flow_table_core.c b/net/netfilter/nf_flow_table_core.c index c0c72ae9df42..7aabfd4b1e50 100644 --- a/net/netfilter/nf_flow_table_core.c +++ b/net/netfilter/nf_flow_table_core.c @@ -121,7 +121,7 @@ static void flow_offload_fixup_ct_state(struct nf_conn *ct) if (l4num == IPPROTO_TCP) flow_offload_fixup_tcp(&ct->proto.tcp); - l4proto = __nf_ct_l4proto_find(l4num); + l4proto = nf_ct_l4proto_find(l4num); if (!l4proto) return; diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index d159e9e7835b..35e61038ae96 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -146,7 +146,7 @@ hash_by_src(const struct net *n, const struct nf_conntrack_tuple *tuple) } /* Is this tuple already taken? (not by us) */ -int +static int nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, const struct nf_conn *ignored_conntrack) { @@ -158,10 +158,9 @@ nf_nat_used_tuple(const struct nf_conntrack_tuple *tuple, */ struct nf_conntrack_tuple reply; - nf_ct_invert_tuplepr(&reply, tuple); + nf_ct_invert_tuple(&reply, tuple); return nf_conntrack_tuple_taken(&reply, ignored_conntrack); } -EXPORT_SYMBOL(nf_nat_used_tuple); static bool nf_nat_inet_in_range(const struct nf_conntrack_tuple *t, const struct nf_nat_range2 *range) @@ -253,7 +252,7 @@ find_appropriate_src(struct net *net, net_eq(net, nf_ct_net(ct)) && nf_ct_zone_equal(ct, zone, IP_CT_DIR_ORIGINAL)) { /* Copy source part from reply tuple. */ - nf_ct_invert_tuplepr(result, + nf_ct_invert_tuple(result, &ct->tuplehash[IP_CT_DIR_REPLY].tuple); result->dst = tuple->dst; @@ -560,8 +559,8 @@ nf_nat_setup_info(struct nf_conn *ct, * manipulations (future optimization: if num_manips == 0, * orig_tp = ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple) */ - nf_ct_invert_tuplepr(&curr_tuple, - &ct->tuplehash[IP_CT_DIR_REPLY].tuple); + nf_ct_invert_tuple(&curr_tuple, + &ct->tuplehash[IP_CT_DIR_REPLY].tuple); get_unique_tuple(&new_tuple, &curr_tuple, range, ct, maniptype); @@ -569,7 +568,7 @@ nf_nat_setup_info(struct nf_conn *ct, struct nf_conntrack_tuple reply; /* Alter conntrack table so will recognize replies. */ - nf_ct_invert_tuplepr(&reply, &new_tuple); + nf_ct_invert_tuple(&reply, &new_tuple); nf_conntrack_alter_reply(ct, &reply); /* Non-atomic: we own this at the moment. */ @@ -640,7 +639,7 @@ static unsigned int nf_nat_manip_pkt(struct sk_buff *skb, struct nf_conn *ct, struct nf_conntrack_tuple target; /* We are aiming to look like inverse of other direction. */ - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + nf_ct_invert_tuple(&target, &ct->tuplehash[!dir].tuple); l3proto = __nf_nat_l3proto_find(target.src.l3num); if (!l3proto->manip_pkt(skb, 0, &target, mtype)) diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 5a92f23f179f..5ca5ec8f3cf0 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -37,10 +37,16 @@ enum { NFT_VALIDATE_DO, }; +static struct rhltable nft_objname_ht; + static u32 nft_chain_hash(const void *data, u32 len, u32 seed); static u32 nft_chain_hash_obj(const void *data, u32 len, u32 seed); static int nft_chain_hash_cmp(struct rhashtable_compare_arg *, const void *); +static u32 nft_objname_hash(const void *data, u32 len, u32 seed); +static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed); +static int nft_objname_hash_cmp(struct rhashtable_compare_arg *, const void *); + static const struct rhashtable_params nft_chain_ht_params = { .head_offset = offsetof(struct nft_chain, rhlhead), .key_offset = offsetof(struct nft_chain, name), @@ -51,6 +57,15 @@ static const struct rhashtable_params nft_chain_ht_params = { .automatic_shrinking = true, }; +static const struct rhashtable_params nft_objname_ht_params = { + .head_offset = offsetof(struct nft_object, rhlhead), + .key_offset = offsetof(struct nft_object, key), + .hashfn = nft_objname_hash, + .obj_hashfn = nft_objname_hash_obj, + .obj_cmpfn = nft_objname_hash_cmp, + .automatic_shrinking = true, +}; + static void nft_validate_state_update(struct net *net, u8 new_validate_state) { switch (net->nft.validate_state) { @@ -820,6 +835,34 @@ static int nft_chain_hash_cmp(struct rhashtable_compare_arg *arg, return strcmp(chain->name, name); } +static u32 nft_objname_hash(const void *data, u32 len, u32 seed) +{ + const struct nft_object_hash_key *k = data; + + seed ^= hash_ptr(k->table, 32); + + return jhash(k->name, strlen(k->name), seed); +} + +static u32 nft_objname_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct nft_object *obj = data; + + return nft_objname_hash(&obj->key, 0, seed); +} + +static int nft_objname_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct nft_object_hash_key *k = arg->key; + const struct nft_object *obj = ptr; + + if (obj->key.table != k->table) + return -1; + + return strcmp(obj->key.name, k->name); +} + static int nf_tables_newtable(struct net *net, struct sock *nlsk, struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], @@ -1076,7 +1119,7 @@ nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) return ERR_PTR(-ENOENT); } -static bool lockdep_commit_lock_is_held(struct net *net) +static bool lockdep_commit_lock_is_held(const struct net *net) { #ifdef CONFIG_PROVE_LOCKING return lockdep_is_held(&net->nft.commit_mutex); @@ -2564,6 +2607,9 @@ static int nft_table_validate(struct net *net, const struct nft_table *table) return 0; } +static struct nft_rule *nft_rule_lookup_byid(const struct net *net, + const struct nlattr *nla); + #define NFT_RULE_MAXEXPRS 128 static int nf_tables_newrule(struct net *net, struct sock *nlsk, @@ -2633,6 +2679,12 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); } + } else if (nla[NFTA_RULE_POSITION_ID]) { + old_rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_POSITION_ID]); + if (IS_ERR(old_rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION_ID]); + return PTR_ERR(old_rule); + } } } @@ -3841,7 +3893,7 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_OBJREF) && nla_put_string(skb, NFTA_SET_ELEM_OBJREF, - (*nft_set_ext_obj(ext))->name) < 0) + (*nft_set_ext_obj(ext))->key.name) < 0) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_FLAGS) && @@ -4374,7 +4426,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EINVAL; goto err2; } - obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], + obj = nft_obj_lookup(ctx->net, ctx->table, + nla[NFTA_SET_ELEM_OBJREF], set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); @@ -4809,18 +4862,36 @@ void nft_unregister_obj(struct nft_object_type *obj_type) } EXPORT_SYMBOL_GPL(nft_unregister_obj); -struct nft_object *nft_obj_lookup(const struct nft_table *table, +struct nft_object *nft_obj_lookup(const struct net *net, + const struct nft_table *table, const struct nlattr *nla, u32 objtype, u8 genmask) { + struct nft_object_hash_key k = { .table = table }; + char search[NFT_OBJ_MAXNAMELEN]; + struct rhlist_head *tmp, *list; struct nft_object *obj; - list_for_each_entry_rcu(obj, &table->objects, list) { - if (!nla_strcmp(nla, obj->name) && - objtype == obj->ops->type->type && - nft_active_genmask(obj, genmask)) + nla_strlcpy(search, nla, sizeof(search)); + k.name = search; + + WARN_ON_ONCE(!rcu_read_lock_held() && + !lockdep_commit_lock_is_held(net)); + + rcu_read_lock(); + list = rhltable_lookup(&nft_objname_ht, &k, nft_objname_ht_params); + if (!list) + goto out; + + rhl_for_each_entry_rcu(obj, tmp, list, rhlhead) { + if (objtype == obj->ops->type->type && + nft_active_genmask(obj, genmask)) { + rcu_read_unlock(); return obj; + } } +out: + rcu_read_unlock(); return ERR_PTR(-ENOENT); } EXPORT_SYMBOL_GPL(nft_obj_lookup); @@ -4978,7 +5049,7 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); if (err != -ENOENT) { @@ -5004,11 +5075,11 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, err = PTR_ERR(obj); goto err1; } - obj->table = table; + obj->key.table = table; obj->handle = nf_tables_alloc_handle(table); - obj->name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); - if (!obj->name) { + obj->key.name = nla_strdup(nla[NFTA_OBJ_NAME], GFP_KERNEL); + if (!obj->key.name) { err = -ENOMEM; goto err2; } @@ -5017,11 +5088,20 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, if (err < 0) goto err3; + err = rhltable_insert(&nft_objname_ht, &obj->rhlhead, + nft_objname_ht_params); + if (err < 0) + goto err4; + list_add_tail_rcu(&obj->list, &table->objects); table->use++; return 0; +err4: + /* queued in transaction log */ + INIT_LIST_HEAD(&obj->list); + return err; err3: - kfree(obj->name); + kfree(obj->key.name); err2: if (obj->ops->destroy) obj->ops->destroy(&ctx, obj); @@ -5050,7 +5130,7 @@ static int nf_tables_fill_obj_info(struct sk_buff *skb, struct net *net, nfmsg->res_id = htons(net->nft.base_seq & 0xffff); if (nla_put_string(skb, NFTA_OBJ_TABLE, table->name) || - nla_put_string(skb, NFTA_OBJ_NAME, obj->name) || + nla_put_string(skb, NFTA_OBJ_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJ_TYPE, htonl(obj->ops->type->type)) || nla_put_be32(skb, NFTA_OBJ_USE, htonl(obj->use)) || nft_object_dump(skb, NFTA_OBJ_DATA, obj, reset) || @@ -5205,7 +5285,7 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + obj = nft_obj_lookup(net, table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return PTR_ERR(obj); @@ -5236,7 +5316,7 @@ static void nft_obj_destroy(const struct nft_ctx *ctx, struct nft_object *obj) obj->ops->destroy(ctx, obj); module_put(obj->ops->type->owner); - kfree(obj->name); + kfree(obj->key.name); kfree(obj); } @@ -5270,7 +5350,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask); } else { attr = nla[NFTA_OBJ_NAME]; - obj = nft_obj_lookup(table, attr, objtype, genmask); + obj = nft_obj_lookup(net, table, attr, objtype, genmask); } if (IS_ERR(obj)) { @@ -5287,7 +5367,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, return nft_delobj(&ctx, obj); } -void nft_obj_notify(struct net *net, struct nft_table *table, +void nft_obj_notify(struct net *net, const struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, int event, int family, int report, gfp_t gfp) { @@ -6394,6 +6474,12 @@ static void nf_tables_commit_chain(struct net *net, struct nft_chain *chain) nf_tables_commit_chain_free_rules_old(g0); } +static void nft_obj_del(struct nft_object *obj) +{ + rhltable_remove(&nft_objname_ht, &obj->rhlhead, nft_objname_ht_params); + list_del_rcu(&obj->list); +} + static void nft_chain_del(struct nft_chain *chain) { struct nft_table *table = chain->table; @@ -6573,7 +6659,7 @@ static int nf_tables_commit(struct net *net, struct sk_buff *skb) nft_trans_destroy(trans); break; case NFT_MSG_DELOBJ: - list_del_rcu(&nft_trans_obj(trans)->list); + nft_obj_del(nft_trans_obj(trans)); nf_tables_obj_notify(&trans->ctx, nft_trans_obj(trans), NFT_MSG_DELOBJ); break; @@ -6713,7 +6799,7 @@ static int __nf_tables_abort(struct net *net) break; case NFT_MSG_NEWOBJ: trans->ctx.table->use--; - list_del_rcu(&nft_trans_obj(trans)->list); + nft_obj_del(nft_trans_obj(trans)); break; case NFT_MSG_DELOBJ: trans->ctx.table->use++; @@ -7327,7 +7413,7 @@ static void __nft_release_tables(struct net *net) nft_set_destroy(set); } list_for_each_entry_safe(obj, ne, &table->objects, list) { - list_del(&obj->list); + nft_obj_del(obj); table->use--; nft_obj_destroy(&ctx, obj); } @@ -7389,12 +7475,18 @@ static int __init nf_tables_module_init(void) if (err < 0) goto err3; + err = rhltable_init(&nft_objname_ht, &nft_objname_ht_params); + if (err < 0) + goto err4; + /* must be last */ err = nfnetlink_subsys_register(&nf_tables_subsys); if (err < 0) - goto err4; + goto err5; return err; +err5: + rhltable_destroy(&nft_objname_ht); err4: unregister_netdevice_notifier(&nf_tables_flowtable_notifier); err3: @@ -7414,6 +7506,7 @@ static void __exit nf_tables_module_exit(void) unregister_pernet_subsys(&nf_tables_net_ops); cancel_work_sync(&trans_destroy_work); rcu_barrier(); + rhltable_destroy(&nft_objname_ht); nf_tables_core_module_exit(); } diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index a50500232b0a..2a00aef7b6d4 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -124,14 +124,25 @@ static void expr_call_ops_eval(const struct nft_expr *expr, struct nft_regs *regs, struct nft_pktinfo *pkt) { +#ifdef CONFIG_RETPOLINE unsigned long e = (unsigned long)expr->ops->eval; - - if (e == (unsigned long)nft_meta_get_eval) - nft_meta_get_eval(expr, regs, pkt); - else if (e == (unsigned long)nft_lookup_eval) - nft_lookup_eval(expr, regs, pkt); - else - expr->ops->eval(expr, regs, pkt); +#define X(e, fun) \ + do { if ((e) == (unsigned long)(fun)) \ + return fun(expr, regs, pkt); } while (0) + + X(e, nft_payload_eval); + X(e, nft_cmp_eval); + X(e, nft_meta_get_eval); + X(e, nft_lookup_eval); + X(e, nft_range_eval); + X(e, nft_immediate_eval); + X(e, nft_byteorder_eval); + X(e, nft_dynset_eval); + X(e, nft_rt_get_eval); + X(e, nft_bitwise_eval); +#undef X +#endif /* CONFIG_RETPOLINE */ + expr->ops->eval(expr, regs, pkt); } unsigned int diff --git a/net/netfilter/nfnetlink_cttimeout.c b/net/netfilter/nfnetlink_cttimeout.c index 109b0d27345a..c69b11ca5aad 100644 --- a/net/netfilter/nfnetlink_cttimeout.c +++ b/net/netfilter/nfnetlink_cttimeout.c @@ -122,7 +122,7 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, return -EBUSY; } - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); /* This protocol is not supportted, skip. */ if (l4proto->l4proto != l4num) { @@ -152,7 +152,6 @@ static int cttimeout_new_timeout(struct net *net, struct sock *ctnl, err: kfree(timeout); err_proto_put: - nf_ct_l4proto_put(l4proto); return ret; } @@ -302,7 +301,6 @@ static int ctnl_timeout_try_del(struct net *net, struct ctnl_timeout *timeout) if (refcount_dec_if_one(&timeout->refcnt)) { /* We are protected by nfnl mutex. */ list_del_rcu(&timeout->head); - nf_ct_l4proto_put(timeout->timeout.l4proto); nf_ct_untimeout(net, &timeout->timeout); kfree_rcu(timeout, rcu_head); } else { @@ -359,7 +357,7 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, return -EINVAL; l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); /* This protocol is not supported, skip. */ if (l4proto->l4proto != l4num) { @@ -372,10 +370,8 @@ static int cttimeout_default_set(struct net *net, struct sock *ctnl, if (ret < 0) goto err; - nf_ct_l4proto_put(l4proto); return 0; err: - nf_ct_l4proto_put(l4proto); return ret; } @@ -442,7 +438,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, l3num = ntohs(nla_get_be16(cda[CTA_TIMEOUT_L3PROTO])); l4num = nla_get_u8(cda[CTA_TIMEOUT_L4PROTO]); - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); err = -EOPNOTSUPP; if (l4proto->l4proto != l4num) @@ -474,12 +470,7 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, break; case IPPROTO_GRE: #ifdef CONFIG_NF_CT_PROTO_GRE - if (l4proto->net_id) { - struct netns_proto_gre *net_gre; - - net_gre = net_generic(net, *l4proto->net_id); - timeouts = net_gre->gre_timeouts; - } + timeouts = nf_gre_pernet(net)->timeouts; #endif break; case 255: @@ -516,7 +507,6 @@ static int cttimeout_default_get(struct net *net, struct sock *ctnl, /* this avoids a loop in nfnetlink. */ return ret == -EAGAIN ? -ENOBUFS : ret; err: - nf_ct_l4proto_put(l4proto); return err; } @@ -597,7 +587,6 @@ static void __net_exit cttimeout_net_exit(struct net *net) list_for_each_entry_safe(cur, tmp, &net->nfct_timeout_list, head) { list_del_rcu(&cur->head); - nf_ct_l4proto_put(cur->timeout.l4proto); if (refcount_dec_and_test(&cur->refcnt)) kfree_rcu(cur, rcu_head); diff --git a/net/netfilter/nft_bitwise.c b/net/netfilter/nft_bitwise.c index fff8073e2a56..2c75b9e0474e 100644 --- a/net/netfilter/nft_bitwise.c +++ b/net/netfilter/nft_bitwise.c @@ -25,9 +25,8 @@ struct nft_bitwise { struct nft_data xor; }; -static void nft_bitwise_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +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]; diff --git a/net/netfilter/nft_byteorder.c b/net/netfilter/nft_byteorder.c index 13d4e421a6b3..19dbc34cc75e 100644 --- a/net/netfilter/nft_byteorder.c +++ b/net/netfilter/nft_byteorder.c @@ -26,9 +26,9 @@ struct nft_byteorder { u8 size; }; -static void nft_byteorder_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_byteorder_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_byteorder *priv = nft_expr_priv(expr); u32 *src = ®s->data[priv->sreg]; diff --git a/net/netfilter/nft_cmp.c b/net/netfilter/nft_cmp.c index 79d48c1d06f4..f9f1fa66a16e 100644 --- a/net/netfilter/nft_cmp.c +++ b/net/netfilter/nft_cmp.c @@ -24,9 +24,9 @@ struct nft_cmp_expr { enum nft_cmp_ops op:8; }; -static void nft_cmp_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_cmp_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_cmp_expr *priv = nft_expr_priv(expr); int d; diff --git a/net/netfilter/nft_counter.c b/net/netfilter/nft_counter.c index a61d7edfc290..1a6b06ce6b5b 100644 --- a/net/netfilter/nft_counter.c +++ b/net/netfilter/nft_counter.c @@ -104,7 +104,7 @@ static void nft_counter_obj_destroy(const struct nft_ctx *ctx, nft_counter_do_destroy(priv); } -static void nft_counter_reset(struct nft_counter_percpu_priv __percpu *priv, +static void nft_counter_reset(struct nft_counter_percpu_priv *priv, struct nft_counter *total) { struct nft_counter *this_cpu; diff --git a/net/netfilter/nft_ct.c b/net/netfilter/nft_ct.c index 586627c361df..7b717fad6cdc 100644 --- a/net/netfilter/nft_ct.c +++ b/net/netfilter/nft_ct.c @@ -870,7 +870,7 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, l4num = nla_get_u8(tb[NFTA_CT_TIMEOUT_L4PROTO]); priv->l4proto = l4num; - l4proto = nf_ct_l4proto_find_get(l4num); + l4proto = nf_ct_l4proto_find(l4num); if (l4proto->l4proto != l4num) { ret = -EOPNOTSUPP; @@ -902,7 +902,6 @@ static int nft_ct_timeout_obj_init(const struct nft_ctx *ctx, err_free_timeout: kfree(timeout); err_proto_put: - nf_ct_l4proto_put(l4proto); return ret; } @@ -913,7 +912,6 @@ static void nft_ct_timeout_obj_destroy(const struct nft_ctx *ctx, struct nf_ct_timeout *timeout = priv->timeout; nf_ct_untimeout(ctx->net, timeout); - nf_ct_l4proto_put(timeout->l4proto); nf_ct_netns_put(ctx->net, ctx->family); kfree(priv->timeout); } diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index f1172f99752b..a8a74a16f9c4 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -62,9 +62,8 @@ err1: return NULL; } -static void nft_dynset_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_dynset_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_dynset *priv = nft_expr_priv(expr); struct nft_set *set = priv->set; diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index c2d237144f74..ea658e6c53e3 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -25,7 +25,6 @@ struct nft_jhash { u32 modulus; u32 seed; u32 offset; - struct nft_set *map; }; static void nft_jhash_eval(const struct nft_expr *expr, @@ -42,33 +41,10 @@ static void nft_jhash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } -static void nft_jhash_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_jhash *priv = nft_expr_priv(expr); - const void *data = ®s->data[priv->sreg]; - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = reciprocal_scale(jhash(data, priv->len, priv->seed), - priv->modulus) + priv->offset; - - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - struct nft_symhash { enum nft_registers dreg:8; u32 modulus; u32 offset; - struct nft_set *map; }; static void nft_symhash_eval(const struct nft_expr *expr, @@ -84,28 +60,6 @@ static void nft_symhash_eval(const struct nft_expr *expr, regs->data[priv->dreg] = h + priv->offset; } -static void nft_symhash_map_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - struct nft_symhash *priv = nft_expr_priv(expr); - struct sk_buff *skb = pkt->skb; - const struct nft_set *map = priv->map; - const struct nft_set_ext *ext; - u32 result; - bool found; - - result = reciprocal_scale(__skb_get_hash_symmetric(skb), - priv->modulus) + priv->offset; - - found = map->ops->lookup(nft_net(pkt), map, &result, &ext); - if (!found) - return; - - nft_data_copy(®s->data[priv->dreg], - nft_set_ext_data(ext), map->dlen); -} - static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SREG] = { .type = NLA_U32 }, [NFTA_HASH_DREG] = { .type = NLA_U32 }, @@ -114,9 +68,6 @@ static const struct nla_policy nft_hash_policy[NFTA_HASH_MAX + 1] = { [NFTA_HASH_SEED] = { .type = NLA_U32 }, [NFTA_HASH_OFFSET] = { .type = NLA_U32 }, [NFTA_HASH_TYPE] = { .type = NLA_U32 }, - [NFTA_HASH_SET_NAME] = { .type = NLA_STRING, - .len = NFT_SET_MAXNAMELEN - 1 }, - [NFTA_HASH_SET_ID] = { .type = NLA_U32 }, }; static int nft_jhash_init(const struct nft_ctx *ctx, @@ -166,20 +117,6 @@ static int nft_jhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_jhash_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_jhash *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_jhash_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_HASH_SET_NAME], - tb[NFTA_HASH_SET_ID], genmask); - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_symhash_init(const struct nft_ctx *ctx, const struct nft_expr *expr, const struct nlattr * const tb[]) @@ -206,20 +143,6 @@ static int nft_symhash_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } -static int nft_symhash_map_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_jhash *priv = nft_expr_priv(expr); - u8 genmask = nft_genmask_next(ctx->net); - - nft_symhash_init(ctx, expr, tb); - priv->map = nft_set_lookup_global(ctx->net, ctx->table, - tb[NFTA_HASH_SET_NAME], - tb[NFTA_HASH_SET_ID], genmask); - return PTR_ERR_OR_ZERO(priv->map); -} - static int nft_jhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -247,18 +170,6 @@ nla_put_failure: return -1; } -static int nft_jhash_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_jhash *priv = nft_expr_priv(expr); - - if (nft_jhash_dump(skb, expr) || - nla_put_string(skb, NFTA_HASH_SET_NAME, priv->map->name)) - return -1; - - return 0; -} - static int nft_symhash_dump(struct sk_buff *skb, const struct nft_expr *expr) { @@ -279,18 +190,6 @@ nla_put_failure: return -1; } -static int nft_symhash_map_dump(struct sk_buff *skb, - const struct nft_expr *expr) -{ - const struct nft_symhash *priv = nft_expr_priv(expr); - - if (nft_symhash_dump(skb, expr) || - nla_put_string(skb, NFTA_HASH_SET_NAME, priv->map->name)) - return -1; - - return 0; -} - static struct nft_expr_type nft_hash_type; static const struct nft_expr_ops nft_jhash_ops = { .type = &nft_hash_type, @@ -300,14 +199,6 @@ static const struct nft_expr_ops nft_jhash_ops = { .dump = nft_jhash_dump, }; -static const struct nft_expr_ops nft_jhash_map_ops = { - .type = &nft_hash_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_jhash)), - .eval = nft_jhash_map_eval, - .init = nft_jhash_map_init, - .dump = nft_jhash_map_dump, -}; - static const struct nft_expr_ops nft_symhash_ops = { .type = &nft_hash_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), @@ -316,14 +207,6 @@ static const struct nft_expr_ops nft_symhash_ops = { .dump = nft_symhash_dump, }; -static const struct nft_expr_ops nft_symhash_map_ops = { - .type = &nft_hash_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_symhash)), - .eval = nft_symhash_map_eval, - .init = nft_symhash_map_init, - .dump = nft_symhash_map_dump, -}; - static const struct nft_expr_ops * nft_hash_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) @@ -336,12 +219,8 @@ nft_hash_select_ops(const struct nft_ctx *ctx, type = ntohl(nla_get_be32(tb[NFTA_HASH_TYPE])); switch (type) { case NFT_HASH_SYM: - if (tb[NFTA_HASH_SET_NAME]) - return &nft_symhash_map_ops; return &nft_symhash_ops; case NFT_HASH_JENKINS: - if (tb[NFTA_HASH_SET_NAME]) - return &nft_jhash_map_ops; return &nft_jhash_ops; default: break; diff --git a/net/netfilter/nft_immediate.c b/net/netfilter/nft_immediate.c index 3f6d1d2a6281..5ec43124cbca 100644 --- a/net/netfilter/nft_immediate.c +++ b/net/netfilter/nft_immediate.c @@ -17,9 +17,9 @@ #include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> -static void nft_immediate_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_immediate_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_immediate_expr *priv = nft_expr_priv(expr); diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 6df486c5ebd3..987d2d6ce624 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -244,6 +244,16 @@ void nft_meta_get_eval(const struct nft_expr *expr, strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); return; #endif + case NFT_META_IIFKIND: + if (in == NULL || in->rtnl_link_ops == NULL) + goto err; + strncpy((char *)dest, in->rtnl_link_ops->kind, IFNAMSIZ); + break; + case NFT_META_OIFKIND: + if (out == NULL || out->rtnl_link_ops == NULL) + goto err; + strncpy((char *)dest, out->rtnl_link_ops->kind, IFNAMSIZ); + break; default: WARN_ON(1); goto err; @@ -340,6 +350,8 @@ static int nft_meta_get_init(const struct nft_ctx *ctx, break; case NFT_META_IIFNAME: case NFT_META_OIFNAME: + case NFT_META_IIFKIND: + case NFT_META_OIFKIND: len = IFNAMSIZ; break; case NFT_META_PRANDOM: diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index ae178e914486..79ef074c18ca 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -38,7 +38,8 @@ static int nft_objref_init(const struct nft_ctx *ctx, return -EINVAL; objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE])); - obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, + obj = nft_obj_lookup(ctx->net, ctx->table, + tb[NFTA_OBJREF_IMM_NAME], objtype, genmask); if (IS_ERR(obj)) return -ENOENT; @@ -53,7 +54,7 @@ static int nft_objref_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_object *obj = nft_objref_priv(expr); - if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->name) || + if (nla_put_string(skb, NFTA_OBJREF_IMM_NAME, obj->key.name) || nla_put_be32(skb, NFTA_OBJREF_IMM_TYPE, htonl(obj->ops->type->type))) goto nla_put_failure; diff --git a/net/netfilter/nft_payload.c b/net/netfilter/nft_payload.c index e110b0ebbf58..54e15de4b79a 100644 --- a/net/netfilter/nft_payload.c +++ b/net/netfilter/nft_payload.c @@ -70,9 +70,9 @@ nft_payload_copy_vlan(u32 *d, const struct sk_buff *skb, u8 offset, u8 len) return skb_copy_bits(skb, offset + mac_off, dst_u8, len) == 0; } -static void nft_payload_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_payload_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_payload *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; diff --git a/net/netfilter/nft_quota.c b/net/netfilter/nft_quota.c index 0ed124a93fcf..354cde67bca9 100644 --- a/net/netfilter/nft_quota.c +++ b/net/netfilter/nft_quota.c @@ -61,7 +61,7 @@ static void nft_quota_obj_eval(struct nft_object *obj, if (overquota && !test_and_set_bit(NFT_QUOTA_DEPLETED_BIT, &priv->flags)) - nft_obj_notify(nft_net(pkt), obj->table, obj, 0, 0, + nft_obj_notify(nft_net(pkt), obj->key.table, obj, 0, 0, NFT_MSG_NEWOBJ, nft_pf(pkt), 0, GFP_ATOMIC); } diff --git a/net/netfilter/nft_range.c b/net/netfilter/nft_range.c index cedb96c3619f..529ac8acb19d 100644 --- a/net/netfilter/nft_range.c +++ b/net/netfilter/nft_range.c @@ -23,9 +23,8 @@ struct nft_range_expr { enum nft_range_ops op:8; }; -static void nft_range_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_range_eval(const struct nft_expr *expr, + struct nft_regs *regs, const struct nft_pktinfo *pkt) { const struct nft_range_expr *priv = nft_expr_priv(expr); int d1, d2; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index f35fa33913ae..c48daed5c46b 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -53,9 +53,9 @@ static u16 get_tcpmss(const struct nft_pktinfo *pkt, const struct dst_entry *skb return mtu - minlen; } -static void nft_rt_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +void nft_rt_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_rt *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; diff --git a/net/netfilter/utils.c b/net/netfilter/utils.c index e8da9a9bba73..55af9f247993 100644 --- a/net/netfilter/utils.c +++ b/net/netfilter/utils.c @@ -180,6 +180,25 @@ int nf_route(struct net *net, struct dst_entry **dst, struct flowi *fl, } EXPORT_SYMBOL_GPL(nf_route); +static int nf_ip_reroute(struct sk_buff *skb, const struct nf_queue_entry *entry) +{ +#ifdef CONFIG_INET + const struct ip_rt_info *rt_info = nf_queue_entry_reroute(entry); + + if (entry->state.hook == NF_INET_LOCAL_OUT) { + const struct iphdr *iph = ip_hdr(skb); + + if (!(iph->tos == rt_info->tos && + skb->mark == rt_info->mark && + iph->daddr == rt_info->daddr && + iph->saddr == rt_info->saddr)) + return ip_route_me_harder(entry->state.net, skb, + RTN_UNSPEC); + } +#endif + return 0; +} + int nf_reroute(struct sk_buff *skb, struct nf_queue_entry *entry) { const struct nf_ipv6_ops *v6ops; diff --git a/net/netfilter/xt_CT.c b/net/netfilter/xt_CT.c index 2c7a4b80206f..0fa863f57575 100644 --- a/net/netfilter/xt_CT.c +++ b/net/netfilter/xt_CT.c @@ -159,7 +159,7 @@ xt_ct_set_timeout(struct nf_conn *ct, const struct xt_tgchk_param *par, /* Make sure the timeout policy matches any existing protocol tracker, * otherwise default to generic. */ - l4proto = __nf_ct_l4proto_find(proto); + l4proto = nf_ct_l4proto_find(proto); if (timeout->l4proto->l4proto != l4proto->l4proto) { ret = -EINVAL; pr_info_ratelimited("Timeout policy `%s' can only be used by L%d protocol number %d\n", diff --git a/net/netfilter/xt_physdev.c b/net/netfilter/xt_physdev.c index 4034d70bff39..b2e39cb6a590 100644 --- a/net/netfilter/xt_physdev.c +++ b/net/netfilter/xt_physdev.c @@ -96,8 +96,7 @@ match_outdev: static int physdev_mt_check(const struct xt_mtchk_param *par) { const struct xt_physdev_info *info = par->matchinfo; - - br_netfilter_enable(); + static bool brnf_probed __read_mostly; if (!(info->bitmask & XT_PHYSDEV_OP_MASK) || info->bitmask & ~XT_PHYSDEV_OP_MASK) @@ -111,6 +110,12 @@ static int physdev_mt_check(const struct xt_mtchk_param *par) if (par->hook_mask & (1 << NF_INET_LOCAL_OUT)) return -EINVAL; } + + if (!brnf_probed) { + brnf_probed = true; + request_module("br_netfilter"); + } + return 0; } diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c index 3c023d6120f6..8fa35df94c07 100644 --- a/net/netlink/af_netlink.c +++ b/net/netlink/af_netlink.c @@ -1371,6 +1371,14 @@ int netlink_has_listeners(struct sock *sk, unsigned int group) } EXPORT_SYMBOL_GPL(netlink_has_listeners); +bool netlink_strict_get_check(struct sk_buff *skb) +{ + const struct netlink_sock *nlk = nlk_sk(NETLINK_CB(skb).sk); + + return nlk->flags & NETLINK_F_STRICT_CHK; +} +EXPORT_SYMBOL_GPL(netlink_strict_get_check); + static int netlink_broadcast_deliver(struct sock *sk, struct sk_buff *skb) { struct netlink_sock *nlk = nlk_sk(sk); diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index cd94f925495a..35884f836260 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -622,7 +622,7 @@ ovs_ct_find_existing(struct net *net, const struct nf_conntrack_zone *zone, if (natted) { struct nf_conntrack_tuple inverse; - if (!nf_ct_invert_tuplepr(&inverse, &tuple)) { + if (!nf_ct_invert_tuple(&inverse, &tuple)) { pr_debug("ovs_ct_find_existing: Inversion failed!\n"); return NULL; } diff --git a/net/openvswitch/meter.c b/net/openvswitch/meter.c index c038e021a591..43849d752a1e 100644 --- a/net/openvswitch/meter.c +++ b/net/openvswitch/meter.c @@ -206,8 +206,7 @@ static struct dp_meter *dp_meter_create(struct nlattr **a) return ERR_PTR(-EINVAL); /* Allocate and set up the meter before locking anything. */ - meter = kzalloc(n_bands * sizeof(struct dp_meter_band) + - sizeof(*meter), GFP_KERNEL); + meter = kzalloc(struct_size(meter, bands, n_bands), GFP_KERNEL); if (!meter) return ERR_PTR(-ENOMEM); diff --git a/net/rds/af_rds.c b/net/rds/af_rds.c index 65387e1e6964..d6cc97fbbbb0 100644 --- a/net/rds/af_rds.c +++ b/net/rds/af_rds.c @@ -254,7 +254,40 @@ static __poll_t rds_poll(struct file *file, struct socket *sock, static int rds_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { - return -ENOIOCTLCMD; + struct rds_sock *rs = rds_sk_to_rs(sock->sk); + rds_tos_t utos, tos = 0; + + switch (cmd) { + case SIOCRDSSETTOS: + if (get_user(utos, (rds_tos_t __user *)arg)) + return -EFAULT; + + if (rs->rs_transport && + rs->rs_transport->get_tos_map) + tos = rs->rs_transport->get_tos_map(utos); + else + return -ENOIOCTLCMD; + + spin_lock_bh(&rds_sock_lock); + if (rs->rs_tos || rs->rs_conn) { + spin_unlock_bh(&rds_sock_lock); + return -EINVAL; + } + rs->rs_tos = tos; + spin_unlock_bh(&rds_sock_lock); + break; + case SIOCRDSGETTOS: + spin_lock_bh(&rds_sock_lock); + tos = rs->rs_tos; + spin_unlock_bh(&rds_sock_lock); + if (put_user(tos, (rds_tos_t __user *)arg)) + return -EFAULT; + break; + default: + return -ENOIOCTLCMD; + } + + return 0; } static int rds_cancel_sent_to(struct rds_sock *rs, char __user *optval, @@ -348,7 +381,7 @@ static int rds_set_transport(struct rds_sock *rs, char __user *optval, } static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, - int optlen) + int optlen, int optname) { int val, valbool; @@ -360,6 +393,9 @@ static int rds_enable_recvtstamp(struct sock *sk, char __user *optval, valbool = val ? 1 : 0; + if (optname == SO_TIMESTAMP_NEW) + sock_set_flag(sk, SOCK_TSTAMP_NEW); + if (valbool) sock_set_flag(sk, SOCK_RCVTSTAMP); else @@ -430,9 +466,10 @@ static int rds_setsockopt(struct socket *sock, int level, int optname, ret = rds_set_transport(rs, optval, optlen); release_sock(sock->sk); break; - case SO_TIMESTAMP: + case SO_TIMESTAMP_OLD: + case SO_TIMESTAMP_NEW: lock_sock(sock->sk); - ret = rds_enable_recvtstamp(sock->sk, optval, optlen); + ret = rds_enable_recvtstamp(sock->sk, optval, optlen, optname); release_sock(sock->sk); break; case SO_RDS_MSG_RXPATH_LATENCY: @@ -646,6 +683,8 @@ static int __rds_create(struct socket *sock, struct sock *sk, int protocol) spin_lock_init(&rs->rs_rdma_lock); rs->rs_rdma_keys = RB_ROOT; rs->rs_rx_traces = 0; + rs->rs_tos = 0; + rs->rs_conn = NULL; spin_lock_bh(&rds_sock_lock); list_add_tail(&rs->rs_item, &rds_sock_list); diff --git a/net/rds/connection.c b/net/rds/connection.c index 3bd2f4a5a30d..7ea134f9a825 100644 --- a/net/rds/connection.c +++ b/net/rds/connection.c @@ -84,7 +84,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - int dev_if) + u8 tos, int dev_if) { struct rds_connection *conn, *ret = NULL; @@ -92,6 +92,7 @@ static struct rds_connection *rds_conn_lookup(struct net *net, if (ipv6_addr_equal(&conn->c_faddr, faddr) && ipv6_addr_equal(&conn->c_laddr, laddr) && conn->c_trans == trans && + conn->c_tos == tos && net == rds_conn_net(conn) && conn->c_dev_if == dev_if) { ret = conn; @@ -139,6 +140,7 @@ static void __rds_conn_path_init(struct rds_connection *conn, atomic_set(&cp->cp_state, RDS_CONN_DOWN); cp->cp_send_gen = 0; cp->cp_reconnect_jiffies = 0; + cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION; INIT_DELAYED_WORK(&cp->cp_send_w, rds_send_worker); INIT_DELAYED_WORK(&cp->cp_recv_w, rds_recv_worker); INIT_DELAYED_WORK(&cp->cp_conn_w, rds_connect_worker); @@ -159,7 +161,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, + gfp_t gfp, u8 tos, int is_outgoing, int dev_if) { @@ -171,7 +173,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, int npaths = (trans->t_mp_capable ? RDS_MPATH_WORKERS : 1); rcu_read_lock(); - conn = rds_conn_lookup(net, head, laddr, faddr, trans, dev_if); + conn = rds_conn_lookup(net, head, laddr, faddr, trans, tos, dev_if); if (conn && conn->c_loopback && conn->c_trans != &rds_loop_transport && @@ -205,6 +207,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, conn->c_isv6 = !ipv6_addr_v4mapped(laddr); conn->c_faddr = *faddr; conn->c_dev_if = dev_if; + conn->c_tos = tos; #if IS_ENABLED(CONFIG_IPV6) /* If the local address is link local, set c_bound_if to be the @@ -297,7 +300,7 @@ static struct rds_connection *__rds_conn_create(struct net *net, struct rds_connection *found; found = rds_conn_lookup(net, head, laddr, faddr, trans, - dev_if); + tos, dev_if); if (found) { struct rds_conn_path *cp; int i; @@ -332,10 +335,10 @@ out: struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, - struct rds_transport *trans, gfp_t gfp, - int dev_if) + struct rds_transport *trans, u8 tos, + gfp_t gfp, int dev_if) { - return __rds_conn_create(net, laddr, faddr, trans, gfp, 0, dev_if); + return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 0, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create); @@ -343,9 +346,9 @@ struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, int dev_if) + u8 tos, gfp_t gfp, int dev_if) { - return __rds_conn_create(net, laddr, faddr, trans, gfp, 1, dev_if); + return __rds_conn_create(net, laddr, faddr, trans, gfp, tos, 1, dev_if); } EXPORT_SYMBOL_GPL(rds_conn_create_outgoing); diff --git a/net/rds/ib.c b/net/rds/ib.c index 9d7b7586f240..2da9b75bad16 100644 --- a/net/rds/ib.c +++ b/net/rds/ib.c @@ -301,6 +301,7 @@ static int rds_ib_conn_info_visitor(struct rds_connection *conn, iinfo->src_addr = conn->c_laddr.s6_addr32[3]; iinfo->dst_addr = conn->c_faddr.s6_addr32[3]; + iinfo->tos = conn->c_tos; memset(&iinfo->src_gid, 0, sizeof(iinfo->src_gid)); memset(&iinfo->dst_gid, 0, sizeof(iinfo->dst_gid)); @@ -514,6 +515,15 @@ void rds_ib_exit(void) rds_ib_mr_exit(); } +static u8 rds_ib_get_tos_map(u8 tos) +{ + /* 1:1 user to transport map for RDMA transport. + * In future, if custom map is desired, hook can export + * user configurable map. + */ + return tos; +} + struct rds_transport rds_ib_transport = { .laddr_check = rds_ib_laddr_check, .xmit_path_complete = rds_ib_xmit_path_complete, @@ -536,6 +546,7 @@ struct rds_transport rds_ib_transport = { .sync_mr = rds_ib_sync_mr, .free_mr = rds_ib_free_mr, .flush_mrs = rds_ib_flush_mrs, + .get_tos_map = rds_ib_get_tos_map, .t_owner = THIS_MODULE, .t_name = "infiniband", .t_unloading = rds_ib_is_unloading, diff --git a/net/rds/ib.h b/net/rds/ib.h index 71ff356ee702..752f92235a38 100644 --- a/net/rds/ib.h +++ b/net/rds/ib.h @@ -67,7 +67,9 @@ struct rds_ib_conn_priv_cmn { u8 ricpc_protocol_major; u8 ricpc_protocol_minor; __be16 ricpc_protocol_minor_mask; /* bitmask */ - __be32 ricpc_reserved1; + u8 ricpc_dp_toss; + u8 ripc_reserved1; + __be16 ripc_reserved2; __be64 ricpc_ack_seq; __be32 ricpc_credit; /* non-zero enables flow ctl */ }; diff --git a/net/rds/ib_cm.c b/net/rds/ib_cm.c index bfbb31f0c7fd..66c6eb56072b 100644 --- a/net/rds/ib_cm.c +++ b/net/rds/ib_cm.c @@ -133,23 +133,24 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even rds_ib_set_flow_control(conn, be32_to_cpu(credit)); } - if (conn->c_version < RDS_PROTOCOL(3, 1)) { - pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n", - &conn->c_laddr, &conn->c_faddr, - RDS_PROTOCOL_MAJOR(conn->c_version), - RDS_PROTOCOL_MINOR(conn->c_version)); - set_bit(RDS_DESTROY_PENDING, &conn->c_path[0].cp_flags); - rds_conn_destroy(conn); - return; - } else { - pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c> version %u.%u%s\n", - ic->i_active_side ? "Active" : "Passive", - &conn->c_laddr, &conn->c_faddr, - RDS_PROTOCOL_MAJOR(conn->c_version), - RDS_PROTOCOL_MINOR(conn->c_version), - ic->i_flowctl ? ", flow control" : ""); + if (conn->c_version < RDS_PROTOCOL_VERSION) { + if (conn->c_version != RDS_PROTOCOL_COMPAT_VERSION) { + pr_notice("RDS/IB: Connection <%pI6c,%pI6c> version %u.%u no longer supported\n", + &conn->c_laddr, &conn->c_faddr, + RDS_PROTOCOL_MAJOR(conn->c_version), + RDS_PROTOCOL_MINOR(conn->c_version)); + rds_conn_destroy(conn); + return; + } } + pr_notice("RDS/IB: %s conn connected <%pI6c,%pI6c,%d> version %u.%u%s\n", + ic->i_active_side ? "Active" : "Passive", + &conn->c_laddr, &conn->c_faddr, conn->c_tos, + RDS_PROTOCOL_MAJOR(conn->c_version), + RDS_PROTOCOL_MINOR(conn->c_version), + ic->i_flowctl ? ", flow control" : ""); + atomic_set(&ic->i_cq_quiesce, 0); /* Init rings and fill recv. this needs to wait until protocol @@ -184,6 +185,7 @@ void rds_ib_cm_connect_complete(struct rds_connection *conn, struct rdma_cm_even NULL); } + conn->c_proposed_version = conn->c_version; rds_connect_complete(conn); } @@ -220,6 +222,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); dp->ricp_v6.dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic)); + dp->ricp_v6.dp_cmn.ricpc_dp_toss = conn->c_tos; conn_param->private_data = &dp->ricp_v6; conn_param->private_data_len = sizeof(dp->ricp_v6); @@ -234,6 +237,7 @@ static void rds_ib_cm_fill_conn_param(struct rds_connection *conn, cpu_to_be16(RDS_IB_SUPPORTED_PROTOCOLS); dp->ricp_v4.dp_ack_seq = cpu_to_be64(rds_ib_piggyb_ack(ic)); + dp->ricp_v4.dp_cmn.ricpc_dp_toss = conn->c_tos; conn_param->private_data = &dp->ricp_v4; conn_param->private_data_len = sizeof(dp->ricp_v4); @@ -389,10 +393,9 @@ static void rds_ib_qp_event_handler(struct ib_event *event, void *data) rdma_notify(ic->i_cm_id, IB_EVENT_COMM_EST); break; default: - rdsdebug("Fatal QP Event %u (%s) " - "- connection %pI6c->%pI6c, reconnecting\n", - event->event, ib_event_msg(event->event), - &conn->c_laddr, &conn->c_faddr); + rdsdebug("Fatal QP Event %u (%s) - connection %pI6c->%pI6c, reconnecting\n", + event->event, ib_event_msg(event->event), + &conn->c_laddr, &conn->c_faddr); rds_conn_drop(conn); break; } @@ -660,13 +663,16 @@ static u32 rds_ib_protocol_compatible(struct rdma_cm_event *event, bool isv6) /* Even if len is crap *now* I still want to check it. -ASG */ if (event->param.conn.private_data_len < data_len || major == 0) - return RDS_PROTOCOL_3_0; + return RDS_PROTOCOL_4_0; common = be16_to_cpu(mask) & RDS_IB_SUPPORTED_PROTOCOLS; - if (major == 3 && common) { - version = RDS_PROTOCOL_3_0; + if (major == 4 && common) { + version = RDS_PROTOCOL_4_0; while ((common >>= 1) != 0) version++; + } else if (RDS_PROTOCOL_COMPAT_VERSION == + RDS_PROTOCOL(major, minor)) { + version = RDS_PROTOCOL_COMPAT_VERSION; } else { if (isv6) printk_ratelimited(KERN_NOTICE "RDS: Connection from %pI6c using incompatible protocol version %u.%u\n", @@ -729,8 +735,10 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, /* Check whether the remote protocol version matches ours. */ version = rds_ib_protocol_compatible(event, isv6); - if (!version) + if (!version) { + err = RDS_RDMA_REJ_INCOMPAT; goto out; + } dp = event->param.conn.private_data; if (isv6) { @@ -771,15 +779,16 @@ int rds_ib_cm_handle_connect(struct rdma_cm_id *cm_id, daddr6 = &d_mapped_addr; } - rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid " - "0x%llx\n", saddr6, daddr6, - RDS_PROTOCOL_MAJOR(version), RDS_PROTOCOL_MINOR(version), + rdsdebug("saddr %pI6c daddr %pI6c RDSv%u.%u lguid 0x%llx fguid 0x%llx, tos:%d\n", + saddr6, daddr6, RDS_PROTOCOL_MAJOR(version), + RDS_PROTOCOL_MINOR(version), (unsigned long long)be64_to_cpu(lguid), - (unsigned long long)be64_to_cpu(fguid)); + (unsigned long long)be64_to_cpu(fguid), dp_cmn->ricpc_dp_toss); /* RDS/IB is not currently netns aware, thus init_net */ conn = rds_conn_create(&init_net, daddr6, saddr6, - &rds_ib_transport, GFP_KERNEL, ifindex); + &rds_ib_transport, dp_cmn->ricpc_dp_toss, + GFP_KERNEL, ifindex); if (IS_ERR(conn)) { rdsdebug("rds_conn_create failed (%ld)\n", PTR_ERR(conn)); conn = NULL; @@ -846,7 +855,7 @@ out: if (conn) mutex_unlock(&conn->c_cm_lock); if (err) - rdma_reject(cm_id, NULL, 0); + rdma_reject(cm_id, &err, sizeof(int)); return destroy; } @@ -861,7 +870,7 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6) /* If the peer doesn't do protocol negotiation, we must * default to RDSv3.0 */ - rds_ib_set_protocol(conn, RDS_PROTOCOL_3_0); + rds_ib_set_protocol(conn, RDS_PROTOCOL_4_1); ic->i_flowctl = rds_ib_sysctl_flow_control; /* advertise flow control */ ret = rds_ib_setup_qp(conn); @@ -870,7 +879,8 @@ int rds_ib_cm_initiate_connect(struct rdma_cm_id *cm_id, bool isv6) goto out; } - rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, RDS_PROTOCOL_VERSION, + rds_ib_cm_fill_conn_param(conn, &conn_param, &dp, + conn->c_proposed_version, UINT_MAX, UINT_MAX, isv6); ret = rdma_connect(cm_id, &conn_param); if (ret) diff --git a/net/rds/ib_recv.c b/net/rds/ib_recv.c index 2f16146e4ec9..d395eec98959 100644 --- a/net/rds/ib_recv.c +++ b/net/rds/ib_recv.c @@ -986,9 +986,9 @@ void rds_ib_recv_cqe_handler(struct rds_ib_connection *ic, } else { /* We expect errors as the qp is drained during shutdown */ if (rds_conn_up(conn) || rds_conn_connecting(conn)) - rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n", + rds_ib_conn_error(conn, "recv completion on <%pI6c,%pI6c, %d> had status %u (%s), disconnecting and reconnecting\n", &conn->c_laddr, &conn->c_faddr, - wc->status, + conn->c_tos, wc->status, ib_wc_status_msg(wc->status)); } diff --git a/net/rds/ib_send.c b/net/rds/ib_send.c index 4e0c36acf866..09c46f2e97fa 100644 --- a/net/rds/ib_send.c +++ b/net/rds/ib_send.c @@ -305,8 +305,9 @@ void rds_ib_send_cqe_handler(struct rds_ib_connection *ic, struct ib_wc *wc) /* We expect errors as the qp is drained during shutdown */ if (wc->status != IB_WC_SUCCESS && rds_conn_up(conn)) { - rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c> had status %u (%s), disconnecting and reconnecting\n", - &conn->c_laddr, &conn->c_faddr, wc->status, + rds_ib_conn_error(conn, "send completion on <%pI6c,%pI6c,%d> had status %u (%s), disconnecting and reconnecting\n", + &conn->c_laddr, &conn->c_faddr, + conn->c_tos, wc->status, ib_wc_status_msg(wc->status)); } } diff --git a/net/rds/rdma_transport.c b/net/rds/rdma_transport.c index 6b0f57c83a2a..46bce8389066 100644 --- a/net/rds/rdma_transport.c +++ b/net/rds/rdma_transport.c @@ -51,6 +51,8 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, struct rds_connection *conn = cm_id->context; struct rds_transport *trans; int ret = 0; + int *err; + u8 len; rdsdebug("conn %p id %p handling event %u (%s)\n", conn, cm_id, event->event, rdma_event_msg(event->event)); @@ -81,6 +83,7 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_ADDR_RESOLVED: + rdma_set_service_type(cm_id, conn->c_tos); /* XXX do we need to clean up if this fails? */ ret = rdma_resolve_route(cm_id, RDS_RDMA_RESOLVE_TIMEOUT_MS); @@ -106,8 +109,19 @@ static int rds_rdma_cm_event_handler_cmn(struct rdma_cm_id *cm_id, break; case RDMA_CM_EVENT_REJECTED: + if (!conn) + break; + err = (int *)rdma_consumer_reject_data(cm_id, event, &len); + if (!err || (err && ((*err) == RDS_RDMA_REJ_INCOMPAT))) { + pr_warn("RDS/RDMA: conn <%pI6c, %pI6c> rejected, dropping connection\n", + &conn->c_laddr, &conn->c_faddr); + conn->c_proposed_version = RDS_PROTOCOL_COMPAT_VERSION; + conn->c_tos = 0; + rds_conn_drop(conn); + } rdsdebug("Connection rejected: %s\n", rdma_reject_msg(cm_id, event->status)); + break; /* FALLTHROUGH */ case RDMA_CM_EVENT_ADDR_ERROR: case RDMA_CM_EVENT_ROUTE_ERROR: diff --git a/net/rds/rdma_transport.h b/net/rds/rdma_transport.h index 200d3134aaae..bfafd4a6d827 100644 --- a/net/rds/rdma_transport.h +++ b/net/rds/rdma_transport.h @@ -11,6 +11,12 @@ #define RDS_RDMA_RESOLVE_TIMEOUT_MS 5000 +/* Below reject reason is for legacy interoperability issue with non-linux + * RDS endpoints where older version incompatibility is conveyed via value 1. + * For future version(s), proper encoded reject reason should be be used. + */ +#define RDS_RDMA_REJ_INCOMPAT 1 + int rds_rdma_conn_connect(struct rds_connection *conn); int rds_rdma_cm_event_handler(struct rdma_cm_id *cm_id, struct rdma_cm_event *event); diff --git a/net/rds/rds.h b/net/rds/rds.h index 4ffe100ff5e6..0d8f67cadd74 100644 --- a/net/rds/rds.h +++ b/net/rds/rds.h @@ -19,10 +19,13 @@ */ #define RDS_PROTOCOL_3_0 0x0300 #define RDS_PROTOCOL_3_1 0x0301 +#define RDS_PROTOCOL_4_0 0x0400 +#define RDS_PROTOCOL_4_1 0x0401 #define RDS_PROTOCOL_VERSION RDS_PROTOCOL_3_1 #define RDS_PROTOCOL_MAJOR(v) ((v) >> 8) #define RDS_PROTOCOL_MINOR(v) ((v) & 255) #define RDS_PROTOCOL(maj, min) (((maj) << 8) | min) +#define RDS_PROTOCOL_COMPAT_VERSION RDS_PROTOCOL_3_1 /* The following ports, 16385, 18634, 18635, are registered with IANA as * the ports to be used for RDS over TCP and UDP. Currently, only RDS over @@ -151,9 +154,13 @@ struct rds_connection { struct rds_cong_map *c_fcong; /* Protocol version */ + unsigned int c_proposed_version; unsigned int c_version; possible_net_t c_net; + /* TOS */ + u8 c_tos; + struct list_head c_map_item; unsigned long c_map_queued; @@ -567,6 +574,7 @@ struct rds_transport { void (*free_mr)(void *trans_private, int invalidate); void (*flush_mrs)(void); bool (*t_unloading)(struct rds_connection *conn); + u8 (*get_tos_map)(u8 tos); }; /* Bind hash table key length. It is the sum of the size of a struct @@ -648,6 +656,7 @@ struct rds_sock { u8 rs_rx_traces; u8 rs_rx_trace[RDS_MSG_RX_DGRAM_TRACE_MAX]; struct rds_msg_zcopy_queue rs_zcookie_queue; + u8 rs_tos; }; static inline struct rds_sock *rds_sk_to_rs(const struct sock *sk) @@ -756,13 +765,14 @@ void rds_conn_exit(void); struct rds_connection *rds_conn_create(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, - struct rds_transport *trans, gfp_t gfp, + struct rds_transport *trans, + u8 tos, gfp_t gfp, int dev_if); struct rds_connection *rds_conn_create_outgoing(struct net *net, const struct in6_addr *laddr, const struct in6_addr *faddr, struct rds_transport *trans, - gfp_t gfp, int dev_if); + u8 tos, gfp_t gfp, int dev_if); void rds_conn_shutdown(struct rds_conn_path *cpath); void rds_conn_destroy(struct rds_connection *conn); void rds_conn_drop(struct rds_connection *conn); diff --git a/net/rds/recv.c b/net/rds/recv.c index 727639dac8a7..853de4876088 100644 --- a/net/rds/recv.c +++ b/net/rds/recv.c @@ -549,9 +549,21 @@ static int rds_cmsg_recv(struct rds_incoming *inc, struct msghdr *msg, if ((inc->i_rx_tstamp != 0) && sock_flag(rds_rs_to_sk(rs), SOCK_RCVTSTAMP)) { - struct timeval tv = ktime_to_timeval(inc->i_rx_tstamp); - ret = put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(tv), &tv); + struct __kernel_old_timeval tv = ns_to_kernel_old_timeval(inc->i_rx_tstamp); + + if (!sock_flag(rds_rs_to_sk(rs), SOCK_TSTAMP_NEW)) { + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } else { + struct __kernel_sock_timeval sk_tv; + + sk_tv.tv_sec = tv.tv_sec; + sk_tv.tv_usec = tv.tv_usec; + + ret = put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(sk_tv), &sk_tv); + } + if (ret) goto out; } @@ -770,6 +782,7 @@ void rds_inc_info_copy(struct rds_incoming *inc, minfo.seq = be64_to_cpu(inc->i_hdr.h_sequence); minfo.len = be32_to_cpu(inc->i_hdr.h_len); + minfo.tos = inc->i_conn->c_tos; if (flip) { minfo.laddr = daddr; diff --git a/net/rds/send.c b/net/rds/send.c index fd8b687d5c05..166dd578c1cc 100644 --- a/net/rds/send.c +++ b/net/rds/send.c @@ -1277,12 +1277,13 @@ int rds_sendmsg(struct socket *sock, struct msghdr *msg, size_t payload_len) /* rds_conn_create has a spinlock that runs with IRQ off. * Caching the conn in the socket helps a lot. */ - if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr)) + if (rs->rs_conn && ipv6_addr_equal(&rs->rs_conn->c_faddr, &daddr) && + rs->rs_tos == rs->rs_conn->c_tos) { conn = rs->rs_conn; - else { + } else { conn = rds_conn_create_outgoing(sock_net(sock->sk), &rs->rs_bound_addr, &daddr, - rs->rs_transport, + rs->rs_transport, rs->rs_tos, sock->sk->sk_allocation, scope_id); if (IS_ERR(conn)) { diff --git a/net/rds/tcp.c b/net/rds/tcp.c index c16f0a362c32..fd2694174607 100644 --- a/net/rds/tcp.c +++ b/net/rds/tcp.c @@ -267,6 +267,7 @@ static void rds_tcp_tc_info(struct socket *rds_sock, unsigned int len, tsinfo.last_sent_nxt = tc->t_last_sent_nxt; tsinfo.last_expected_una = tc->t_last_expected_una; tsinfo.last_seen_una = tc->t_last_seen_una; + tsinfo.tos = tc->t_cpath->cp_conn->c_tos; rds_info_copy(iter, &tsinfo, sizeof(tsinfo)); } @@ -452,6 +453,12 @@ static void rds_tcp_destroy_conns(void) static void rds_tcp_exit(void); +static u8 rds_tcp_get_tos_map(u8 tos) +{ + /* all user tos mapped to default 0 for TCP transport */ + return 0; +} + struct rds_transport rds_tcp_transport = { .laddr_check = rds_tcp_laddr_check, .xmit_path_prepare = rds_tcp_xmit_path_prepare, @@ -466,6 +473,7 @@ struct rds_transport rds_tcp_transport = { .inc_free = rds_tcp_inc_free, .stats_info_copy = rds_tcp_stats_info_copy, .exit = rds_tcp_exit, + .get_tos_map = rds_tcp_get_tos_map, .t_owner = THIS_MODULE, .t_name = "tcp", .t_type = RDS_TRANS_TCP, diff --git a/net/rds/tcp_listen.c b/net/rds/tcp_listen.c index c12203f646da..810a3a49e947 100644 --- a/net/rds/tcp_listen.c +++ b/net/rds/tcp_listen.c @@ -200,7 +200,7 @@ int rds_tcp_accept_one(struct socket *sock) conn = rds_conn_create(sock_net(sock->sk), my_addr, peer_addr, - &rds_tcp_transport, GFP_KERNEL, dev_if); + &rds_tcp_transport, 0, GFP_KERNEL, dev_if); if (IS_ERR(conn)) { ret = PTR_ERR(conn); diff --git a/net/rds/threads.c b/net/rds/threads.c index e64f9e4c3cda..32dc50f0a303 100644 --- a/net/rds/threads.c +++ b/net/rds/threads.c @@ -93,6 +93,7 @@ void rds_connect_path_complete(struct rds_conn_path *cp, int curr) queue_delayed_work(rds_wq, &cp->cp_recv_w, 0); } rcu_read_unlock(); + cp->cp_conn->c_proposed_version = RDS_PROTOCOL_VERSION; } EXPORT_SYMBOL_GPL(rds_connect_path_complete); diff --git a/net/rxrpc/local_object.c b/net/rxrpc/local_object.c index 0906e51d3cfb..15cf42d5b53a 100644 --- a/net/rxrpc/local_object.c +++ b/net/rxrpc/local_object.c @@ -202,7 +202,7 @@ static int rxrpc_open_socket(struct rxrpc_local *local, struct net *net) /* We want receive timestamps. */ opt = 1; - ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS, + ret = kernel_setsockopt(local->socket, SOL_SOCKET, SO_TIMESTAMPNS_OLD, (char *)&opt, sizeof(opt)); if (ret < 0) { _debug("setsockopt failed"); diff --git a/net/sched/act_api.c b/net/sched/act_api.c index d4b8355737d8..aecf1bf233c8 100644 --- a/net/sched/act_api.c +++ b/net/sched/act_api.c @@ -543,7 +543,7 @@ int tcf_register_action(struct tc_action_ops *act, write_lock(&act_mod_lock); list_for_each_entry(a, &act_base, head) { - if (act->type == a->type || (strcmp(act->kind, a->kind) == 0)) { + if (act->id == a->id || (strcmp(act->kind, a->kind) == 0)) { write_unlock(&act_mod_lock); unregister_pernet_subsys(ops); return -EEXIST; diff --git a/net/sched/act_bpf.c b/net/sched/act_bpf.c index c7633843e223..aa5c38d11a30 100644 --- a/net/sched/act_bpf.c +++ b/net/sched/act_bpf.c @@ -396,7 +396,7 @@ static int tcf_bpf_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_bpf_ops __read_mostly = { .kind = "bpf", - .type = TCA_ACT_BPF, + .id = TCA_ID_BPF, .owner = THIS_MODULE, .act = tcf_bpf_act, .dump = tcf_bpf_dump, diff --git a/net/sched/act_connmark.c b/net/sched/act_connmark.c index 8475913f2070..5d24993cccfe 100644 --- a/net/sched/act_connmark.c +++ b/net/sched/act_connmark.c @@ -204,7 +204,7 @@ static int tcf_connmark_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_connmark_ops = { .kind = "connmark", - .type = TCA_ACT_CONNMARK, + .id = TCA_ID_CONNMARK, .owner = THIS_MODULE, .act = tcf_connmark_act, .dump = tcf_connmark_dump, diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 3dc25b7806d7..945fb34ae721 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -660,7 +660,7 @@ static size_t tcf_csum_get_fill_size(const struct tc_action *act) static struct tc_action_ops act_csum_ops = { .kind = "csum", - .type = TCA_ACT_CSUM, + .id = TCA_ID_CSUM, .owner = THIS_MODULE, .act = tcf_csum_act, .dump = tcf_csum_dump, diff --git a/net/sched/act_gact.c b/net/sched/act_gact.c index b61c20ebb314..93da0004e9f4 100644 --- a/net/sched/act_gact.c +++ b/net/sched/act_gact.c @@ -253,7 +253,7 @@ static size_t tcf_gact_get_fill_size(const struct tc_action *act) static struct tc_action_ops act_gact_ops = { .kind = "gact", - .type = TCA_ACT_GACT, + .id = TCA_ID_GACT, .owner = THIS_MODULE, .act = tcf_gact_act, .stats_update = tcf_gact_stats_update, diff --git a/net/sched/act_ife.c b/net/sched/act_ife.c index 30b63fa23ee2..9b1f2b3990ee 100644 --- a/net/sched/act_ife.c +++ b/net/sched/act_ife.c @@ -864,7 +864,7 @@ static int tcf_ife_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_ife_ops = { .kind = "ife", - .type = TCA_ACT_IFE, + .id = TCA_ID_IFE, .owner = THIS_MODULE, .act = tcf_ife_act, .dump = tcf_ife_dump, diff --git a/net/sched/act_ipt.c b/net/sched/act_ipt.c index 8af6c11d2482..1bad190710ad 100644 --- a/net/sched/act_ipt.c +++ b/net/sched/act_ipt.c @@ -338,7 +338,7 @@ static int tcf_ipt_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_ipt_ops = { .kind = "ipt", - .type = TCA_ACT_IPT, + .id = TCA_ID_IPT, .owner = THIS_MODULE, .act = tcf_ipt_act, .dump = tcf_ipt_dump, @@ -387,7 +387,7 @@ static int tcf_xt_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_xt_ops = { .kind = "xt", - .type = TCA_ACT_XT, + .id = TCA_ID_XT, .owner = THIS_MODULE, .act = tcf_ipt_act, .dump = tcf_ipt_dump, diff --git a/net/sched/act_mirred.c b/net/sched/act_mirred.c index c8cf4d10c435..6692fd054617 100644 --- a/net/sched/act_mirred.c +++ b/net/sched/act_mirred.c @@ -400,7 +400,7 @@ static void tcf_mirred_put_dev(struct net_device *dev) static struct tc_action_ops act_mirred_ops = { .kind = "mirred", - .type = TCA_ACT_MIRRED, + .id = TCA_ID_MIRRED, .owner = THIS_MODULE, .act = tcf_mirred_act, .stats_update = tcf_stats_update, diff --git a/net/sched/act_nat.c b/net/sched/act_nat.c index c5c1e23add77..543eab9193f1 100644 --- a/net/sched/act_nat.c +++ b/net/sched/act_nat.c @@ -304,7 +304,7 @@ static int tcf_nat_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_nat_ops = { .kind = "nat", - .type = TCA_ACT_NAT, + .id = TCA_ID_NAT, .owner = THIS_MODULE, .act = tcf_nat_act, .dump = tcf_nat_dump, diff --git a/net/sched/act_pedit.c b/net/sched/act_pedit.c index 2b372a06b432..a80373878df7 100644 --- a/net/sched/act_pedit.c +++ b/net/sched/act_pedit.c @@ -406,7 +406,7 @@ static int tcf_pedit_dump(struct sk_buff *skb, struct tc_action *a, struct tcf_t t; int s; - s = sizeof(*opt) + p->tcfp_nkeys * sizeof(struct tc_pedit_key); + s = struct_size(opt, keys, p->tcfp_nkeys); /* netlink spinlocks held above us - must use ATOMIC */ opt = kzalloc(s, GFP_ATOMIC); @@ -470,7 +470,7 @@ static int tcf_pedit_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_pedit_ops = { .kind = "pedit", - .type = TCA_ACT_PEDIT, + .id = TCA_ID_PEDIT, .owner = THIS_MODULE, .act = tcf_pedit_act, .dump = tcf_pedit_dump, diff --git a/net/sched/act_police.c b/net/sched/act_police.c index ec8ec55e0fe8..8271a6263824 100644 --- a/net/sched/act_police.c +++ b/net/sched/act_police.c @@ -366,7 +366,7 @@ MODULE_LICENSE("GPL"); static struct tc_action_ops act_police_ops = { .kind = "police", - .type = TCA_ID_POLICE, + .id = TCA_ID_POLICE, .owner = THIS_MODULE, .act = tcf_police_act, .dump = tcf_police_dump, diff --git a/net/sched/act_sample.c b/net/sched/act_sample.c index 1a0c682fd734..203e399e5c85 100644 --- a/net/sched/act_sample.c +++ b/net/sched/act_sample.c @@ -233,7 +233,7 @@ static int tcf_sample_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_sample_ops = { .kind = "sample", - .type = TCA_ACT_SAMPLE, + .id = TCA_ID_SAMPLE, .owner = THIS_MODULE, .act = tcf_sample_act, .dump = tcf_sample_dump, diff --git a/net/sched/act_simple.c b/net/sched/act_simple.c index 902957beceb3..d54cb608dbaf 100644 --- a/net/sched/act_simple.c +++ b/net/sched/act_simple.c @@ -19,8 +19,6 @@ #include <net/netlink.h> #include <net/pkt_sched.h> -#define TCA_ACT_SIMP 22 - #include <linux/tc_act/tc_defact.h> #include <net/tc_act/tc_defact.h> @@ -197,7 +195,7 @@ static int tcf_simp_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_simp_ops = { .kind = "simple", - .type = TCA_ACT_SIMP, + .id = TCA_ID_SIMP, .owner = THIS_MODULE, .act = tcf_simp_act, .dump = tcf_simp_dump, diff --git a/net/sched/act_skbedit.c b/net/sched/act_skbedit.c index 64dba3708fce..39f8a67ea940 100644 --- a/net/sched/act_skbedit.c +++ b/net/sched/act_skbedit.c @@ -305,7 +305,7 @@ static int tcf_skbedit_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_skbedit_ops = { .kind = "skbedit", - .type = TCA_ACT_SKBEDIT, + .id = TCA_ID_SKBEDIT, .owner = THIS_MODULE, .act = tcf_skbedit_act, .dump = tcf_skbedit_dump, diff --git a/net/sched/act_skbmod.c b/net/sched/act_skbmod.c index 59710a183bd3..7bac1d78e7a3 100644 --- a/net/sched/act_skbmod.c +++ b/net/sched/act_skbmod.c @@ -260,7 +260,7 @@ static int tcf_skbmod_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_skbmod_ops = { .kind = "skbmod", - .type = TCA_ACT_SKBMOD, + .id = TCA_ACT_SKBMOD, .owner = THIS_MODULE, .act = tcf_skbmod_act, .dump = tcf_skbmod_dump, diff --git a/net/sched/act_tunnel_key.c b/net/sched/act_tunnel_key.c index 8b43fe0130f7..9104b8e36482 100644 --- a/net/sched/act_tunnel_key.c +++ b/net/sched/act_tunnel_key.c @@ -563,7 +563,7 @@ static int tunnel_key_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_tunnel_key_ops = { .kind = "tunnel_key", - .type = TCA_ACT_TUNNEL_KEY, + .id = TCA_ID_TUNNEL_KEY, .owner = THIS_MODULE, .act = tunnel_key_act, .dump = tunnel_key_dump, diff --git a/net/sched/act_vlan.c b/net/sched/act_vlan.c index 93fdaf707313..ac0061599225 100644 --- a/net/sched/act_vlan.c +++ b/net/sched/act_vlan.c @@ -297,7 +297,7 @@ static int tcf_vlan_search(struct net *net, struct tc_action **a, u32 index) static struct tc_action_ops act_vlan_ops = { .kind = "vlan", - .type = TCA_ACT_VLAN, + .id = TCA_ID_VLAN, .owner = THIS_MODULE, .act = tcf_vlan_act, .dump = tcf_vlan_dump, diff --git a/net/sched/cls_api.c b/net/sched/cls_api.c index e2b5cb2eb34e..9ad53895e604 100644 --- a/net/sched/cls_api.c +++ b/net/sched/cls_api.c @@ -31,6 +31,13 @@ #include <net/netlink.h> #include <net/pkt_sched.h> #include <net/pkt_cls.h> +#include <net/tc_act/tc_pedit.h> +#include <net/tc_act/tc_mirred.h> +#include <net/tc_act/tc_vlan.h> +#include <net/tc_act/tc_tunnel_key.h> +#include <net/tc_act/tc_csum.h> +#include <net/tc_act/tc_gact.h> +#include <net/tc_act/tc_skbedit.h> extern const struct nla_policy rtm_tca_policy[TCA_MAX + 1]; @@ -61,7 +68,8 @@ static const struct tcf_proto_ops *__tcf_proto_lookup_ops(const char *kind) } static const struct tcf_proto_ops * -tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack) +tcf_proto_lookup_ops(const char *kind, bool rtnl_held, + struct netlink_ext_ack *extack) { const struct tcf_proto_ops *ops; @@ -69,9 +77,11 @@ tcf_proto_lookup_ops(const char *kind, struct netlink_ext_ack *extack) if (ops) return ops; #ifdef CONFIG_MODULES - rtnl_unlock(); + if (rtnl_held) + rtnl_unlock(); request_module("cls_%s", kind); - rtnl_lock(); + if (rtnl_held) + rtnl_lock(); ops = __tcf_proto_lookup_ops(kind); /* We dropped the RTNL semaphore in order to perform * the module load. So, even if we succeeded in loading @@ -152,8 +162,26 @@ static inline u32 tcf_auto_prio(struct tcf_proto *tp) return TC_H_MAJ(first); } +static bool tcf_proto_is_unlocked(const char *kind) +{ + const struct tcf_proto_ops *ops; + bool ret; + + ops = tcf_proto_lookup_ops(kind, false, NULL); + /* On error return false to take rtnl lock. Proto lookup/create + * functions will perform lookup again and properly handle errors. + */ + if (IS_ERR(ops)) + return false; + + ret = !!(ops->flags & TCF_PROTO_OPS_DOIT_UNLOCKED); + module_put(ops->owner); + return ret; +} + static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, u32 prio, struct tcf_chain *chain, + bool rtnl_held, struct netlink_ext_ack *extack) { struct tcf_proto *tp; @@ -163,7 +191,7 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, if (!tp) return ERR_PTR(-ENOBUFS); - tp->ops = tcf_proto_lookup_ops(kind, extack); + tp->ops = tcf_proto_lookup_ops(kind, rtnl_held, extack); if (IS_ERR(tp->ops)) { err = PTR_ERR(tp->ops); goto errout; @@ -172,6 +200,8 @@ static struct tcf_proto *tcf_proto_create(const char *kind, u32 protocol, tp->protocol = protocol; tp->prio = prio; tp->chain = chain; + spin_lock_init(&tp->lock); + refcount_set(&tp->refcnt, 1); err = tp->ops->init(tp); if (err) { @@ -185,14 +215,75 @@ errout: return ERR_PTR(err); } -static void tcf_proto_destroy(struct tcf_proto *tp, +static void tcf_proto_get(struct tcf_proto *tp) +{ + refcount_inc(&tp->refcnt); +} + +static void tcf_chain_put(struct tcf_chain *chain); + +static void tcf_proto_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { - tp->ops->destroy(tp, extack); + tp->ops->destroy(tp, rtnl_held, extack); + tcf_chain_put(tp->chain); module_put(tp->ops->owner); kfree_rcu(tp, rcu); } +static void tcf_proto_put(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + if (refcount_dec_and_test(&tp->refcnt)) + tcf_proto_destroy(tp, rtnl_held, extack); +} + +static int walker_noop(struct tcf_proto *tp, void *d, struct tcf_walker *arg) +{ + return -1; +} + +static bool tcf_proto_is_empty(struct tcf_proto *tp, bool rtnl_held) +{ + struct tcf_walker walker = { .fn = walker_noop, }; + + if (tp->ops->walk) { + tp->ops->walk(tp, &walker, rtnl_held); + return !walker.stop; + } + return true; +} + +static bool tcf_proto_check_delete(struct tcf_proto *tp, bool rtnl_held) +{ + spin_lock(&tp->lock); + if (tcf_proto_is_empty(tp, rtnl_held)) + tp->deleting = true; + spin_unlock(&tp->lock); + return tp->deleting; +} + +static void tcf_proto_mark_delete(struct tcf_proto *tp) +{ + spin_lock(&tp->lock); + tp->deleting = true; + spin_unlock(&tp->lock); +} + +static bool tcf_proto_is_deleting(struct tcf_proto *tp) +{ + bool deleting; + + spin_lock(&tp->lock); + deleting = tp->deleting; + spin_unlock(&tp->lock); + + return deleting; +} + +#define ASSERT_BLOCK_LOCKED(block) \ + lockdep_assert_held(&(block)->lock) + struct tcf_filter_chain_list_item { struct list_head list; tcf_chain_head_change_t *chain_head_change; @@ -204,10 +295,13 @@ static struct tcf_chain *tcf_chain_create(struct tcf_block *block, { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + chain = kzalloc(sizeof(*chain), GFP_KERNEL); if (!chain) return NULL; list_add_tail(&chain->list, &block->chain_list); + mutex_init(&chain->filter_chain_lock); chain->block = block; chain->index = chain_index; chain->refcnt = 1; @@ -231,29 +325,59 @@ static void tcf_chain0_head_change(struct tcf_chain *chain, if (chain->index) return; + + mutex_lock(&block->lock); list_for_each_entry(item, &block->chain0.filter_chain_list, list) tcf_chain_head_change_item(item, tp_head); + mutex_unlock(&block->lock); } -static void tcf_chain_destroy(struct tcf_chain *chain) +/* Returns true if block can be safely freed. */ + +static bool tcf_chain_detach(struct tcf_chain *chain) { struct tcf_block *block = chain->block; + ASSERT_BLOCK_LOCKED(block); + list_del(&chain->list); if (!chain->index) block->chain0.chain = NULL; + + if (list_empty(&block->chain_list) && + refcount_read(&block->refcnt) == 0) + return true; + + return false; +} + +static void tcf_block_destroy(struct tcf_block *block) +{ + mutex_destroy(&block->lock); + kfree_rcu(block, rcu); +} + +static void tcf_chain_destroy(struct tcf_chain *chain, bool free_block) +{ + struct tcf_block *block = chain->block; + + mutex_destroy(&chain->filter_chain_lock); kfree(chain); - if (list_empty(&block->chain_list) && !refcount_read(&block->refcnt)) - kfree_rcu(block, rcu); + if (free_block) + tcf_block_destroy(block); } static void tcf_chain_hold(struct tcf_chain *chain) { + ASSERT_BLOCK_LOCKED(chain->block); + ++chain->refcnt; } static bool tcf_chain_held_by_acts_only(struct tcf_chain *chain) { + ASSERT_BLOCK_LOCKED(chain->block); + /* In case all the references are action references, this * chain should not be shown to the user. */ @@ -265,6 +389,8 @@ static struct tcf_chain *tcf_chain_lookup(struct tcf_block *block, { struct tcf_chain *chain; + ASSERT_BLOCK_LOCKED(block); + list_for_each_entry(chain, &block->chain_list, list) { if (chain->index == chain_index) return chain; @@ -279,31 +405,40 @@ static struct tcf_chain *__tcf_chain_get(struct tcf_block *block, u32 chain_index, bool create, bool by_act) { - struct tcf_chain *chain = tcf_chain_lookup(block, chain_index); + struct tcf_chain *chain = NULL; + bool is_first_reference; + mutex_lock(&block->lock); + chain = tcf_chain_lookup(block, chain_index); if (chain) { tcf_chain_hold(chain); } else { if (!create) - return NULL; + goto errout; chain = tcf_chain_create(block, chain_index); if (!chain) - return NULL; + goto errout; } if (by_act) ++chain->action_refcnt; + is_first_reference = chain->refcnt - chain->action_refcnt == 1; + mutex_unlock(&block->lock); /* Send notification only in case we got the first * non-action reference. Until then, the chain acts only as * a placeholder for actions pointing to it and user ought * not know about them. */ - if (chain->refcnt - chain->action_refcnt == 1 && !by_act) + if (is_first_reference && !by_act) tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, RTM_NEWCHAIN, false); return chain; + +errout: + mutex_unlock(&block->lock); + return chain; } static struct tcf_chain *tcf_chain_get(struct tcf_block *block, u32 chain_index, @@ -318,51 +453,94 @@ struct tcf_chain *tcf_chain_get_by_act(struct tcf_block *block, u32 chain_index) } EXPORT_SYMBOL(tcf_chain_get_by_act); -static void tc_chain_tmplt_del(struct tcf_chain *chain); +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv); +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags, bool unicast); -static void __tcf_chain_put(struct tcf_chain *chain, bool by_act) +static void __tcf_chain_put(struct tcf_chain *chain, bool by_act, + bool explicitly_created) { + struct tcf_block *block = chain->block; + const struct tcf_proto_ops *tmplt_ops; + bool is_last, free_block = false; + unsigned int refcnt; + void *tmplt_priv; + u32 chain_index; + + mutex_lock(&block->lock); + if (explicitly_created) { + if (!chain->explicitly_created) { + mutex_unlock(&block->lock); + return; + } + chain->explicitly_created = false; + } + if (by_act) chain->action_refcnt--; - chain->refcnt--; + + /* tc_chain_notify_delete can't be called while holding block lock. + * However, when block is unlocked chain can be changed concurrently, so + * save these to temporary variables. + */ + refcnt = --chain->refcnt; + is_last = refcnt - chain->action_refcnt == 0; + tmplt_ops = chain->tmplt_ops; + tmplt_priv = chain->tmplt_priv; + chain_index = chain->index; + + if (refcnt == 0) + free_block = tcf_chain_detach(chain); + mutex_unlock(&block->lock); /* The last dropped non-action reference will trigger notification. */ - if (chain->refcnt - chain->action_refcnt == 0 && !by_act) - tc_chain_notify(chain, NULL, 0, 0, RTM_DELCHAIN, false); + if (is_last && !by_act) { + tc_chain_notify_delete(tmplt_ops, tmplt_priv, chain_index, + block, NULL, 0, 0, false); + /* Last reference to chain, no need to lock. */ + chain->flushing = false; + } - if (chain->refcnt == 0) { - tc_chain_tmplt_del(chain); - tcf_chain_destroy(chain); + if (refcnt == 0) { + tc_chain_tmplt_del(tmplt_ops, tmplt_priv); + tcf_chain_destroy(chain, free_block); } } static void tcf_chain_put(struct tcf_chain *chain) { - __tcf_chain_put(chain, false); + __tcf_chain_put(chain, false, false); } void tcf_chain_put_by_act(struct tcf_chain *chain) { - __tcf_chain_put(chain, true); + __tcf_chain_put(chain, true, false); } EXPORT_SYMBOL(tcf_chain_put_by_act); static void tcf_chain_put_explicitly_created(struct tcf_chain *chain) { - if (chain->explicitly_created) - tcf_chain_put(chain); + __tcf_chain_put(chain, false, true); } -static void tcf_chain_flush(struct tcf_chain *chain) +static void tcf_chain_flush(struct tcf_chain *chain, bool rtnl_held) { - struct tcf_proto *tp = rtnl_dereference(chain->filter_chain); + struct tcf_proto *tp, *tp_next; + mutex_lock(&chain->filter_chain_lock); + tp = tcf_chain_dereference(chain->filter_chain, chain); + RCU_INIT_POINTER(chain->filter_chain, NULL); tcf_chain0_head_change(chain, NULL); + chain->flushing = true; + mutex_unlock(&chain->filter_chain_lock); + while (tp) { - RCU_INIT_POINTER(chain->filter_chain, tp->next); - tcf_proto_destroy(tp, NULL); - tp = rtnl_dereference(chain->filter_chain); - tcf_chain_put(chain); + tp_next = rcu_dereference_protected(tp->next, 1); + tcf_proto_put(tp, rtnl_held, NULL); + tp = tp_next; } } @@ -684,8 +862,8 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block, struct tcf_block_ext_info *ei, struct netlink_ext_ack *extack) { - struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; + struct tcf_chain *chain0; item = kmalloc(sizeof(*item), GFP_KERNEL); if (!item) { @@ -694,9 +872,32 @@ tcf_chain0_head_change_cb_add(struct tcf_block *block, } item->chain_head_change = ei->chain_head_change; item->chain_head_change_priv = ei->chain_head_change_priv; - if (chain0 && chain0->filter_chain) - tcf_chain_head_change_item(item, chain0->filter_chain); - list_add(&item->list, &block->chain0.filter_chain_list); + + mutex_lock(&block->lock); + chain0 = block->chain0.chain; + if (chain0) + tcf_chain_hold(chain0); + else + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + if (chain0) { + struct tcf_proto *tp_head; + + mutex_lock(&chain0->filter_chain_lock); + + tp_head = tcf_chain_dereference(chain0->filter_chain, chain0); + if (tp_head) + tcf_chain_head_change_item(item, tp_head); + + mutex_lock(&block->lock); + list_add(&item->list, &block->chain0.filter_chain_list); + mutex_unlock(&block->lock); + + mutex_unlock(&chain0->filter_chain_lock); + tcf_chain_put(chain0); + } + return 0; } @@ -704,20 +905,23 @@ static void tcf_chain0_head_change_cb_del(struct tcf_block *block, struct tcf_block_ext_info *ei) { - struct tcf_chain *chain0 = block->chain0.chain; struct tcf_filter_chain_list_item *item; + mutex_lock(&block->lock); list_for_each_entry(item, &block->chain0.filter_chain_list, list) { if ((!ei->chain_head_change && !ei->chain_head_change_priv) || (item->chain_head_change == ei->chain_head_change && item->chain_head_change_priv == ei->chain_head_change_priv)) { - if (chain0) + if (block->chain0.chain) tcf_chain_head_change_item(item, NULL); list_del(&item->list); + mutex_unlock(&block->lock); + kfree(item); return; } } + mutex_unlock(&block->lock); WARN_ON(1); } @@ -764,6 +968,7 @@ static struct tcf_block *tcf_block_create(struct net *net, struct Qdisc *q, NL_SET_ERR_MSG(extack, "Memory allocation for block failed"); return ERR_PTR(-ENOMEM); } + mutex_init(&block->lock); INIT_LIST_HEAD(&block->chain_list); INIT_LIST_HEAD(&block->cb_list); INIT_LIST_HEAD(&block->owner_list); @@ -799,157 +1004,241 @@ static struct tcf_block *tcf_block_refcnt_get(struct net *net, u32 block_index) return block; } -static void tcf_block_flush_all_chains(struct tcf_block *block) +static struct tcf_chain * +__tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) { - struct tcf_chain *chain; + mutex_lock(&block->lock); + if (chain) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + else + chain = list_first_entry_or_null(&block->chain_list, + struct tcf_chain, list); - /* Hold a refcnt for all chains, so that they don't disappear - * while we are iterating. - */ - list_for_each_entry(chain, &block->chain_list, list) + /* skip all action-only chains */ + while (chain && tcf_chain_held_by_acts_only(chain)) + chain = list_is_last(&chain->list, &block->chain_list) ? + NULL : list_next_entry(chain, list); + + if (chain) tcf_chain_hold(chain); + mutex_unlock(&block->lock); - list_for_each_entry(chain, &block->chain_list, list) - tcf_chain_flush(chain); + return chain; } -static void tcf_block_put_all_chains(struct tcf_block *block) +/* Function to be used by all clients that want to iterate over all chains on + * block. It properly obtains block->lock and takes reference to chain before + * returning it. Users of this function must be tolerant to concurrent chain + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_chain * +tcf_get_next_chain(struct tcf_block *block, struct tcf_chain *chain) { - struct tcf_chain *chain, *tmp; + struct tcf_chain *chain_next = __tcf_get_next_chain(block, chain); - /* At this point, all the chains should have refcnt >= 1. */ - list_for_each_entry_safe(chain, tmp, &block->chain_list, list) { - tcf_chain_put_explicitly_created(chain); + if (chain) tcf_chain_put(chain); - } + + return chain_next; } +EXPORT_SYMBOL(tcf_get_next_chain); -static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, - struct tcf_block_ext_info *ei) +static struct tcf_proto * +__tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp) { - if (refcount_dec_and_test(&block->refcnt)) { - /* Flushing/putting all chains will cause the block to be - * deallocated when last chain is freed. However, if chain_list - * is empty, block has to be manually deallocated. After block - * reference counter reached 0, it is no longer possible to - * increment it or add new chains to block. - */ - bool free_block = list_empty(&block->chain_list); + u32 prio = 0; - if (tcf_block_shared(block)) - tcf_block_remove(block, block->net); - if (!free_block) - tcf_block_flush_all_chains(block); + ASSERT_RTNL(); + mutex_lock(&chain->filter_chain_lock); - if (q) - tcf_block_offload_unbind(block, q, ei); + if (!tp) { + tp = tcf_chain_dereference(chain->filter_chain, chain); + } else if (tcf_proto_is_deleting(tp)) { + /* 'deleting' flag is set and chain->filter_chain_lock was + * unlocked, which means next pointer could be invalid. Restart + * search. + */ + prio = tp->prio + 1; + tp = tcf_chain_dereference(chain->filter_chain, chain); - if (free_block) - kfree_rcu(block, rcu); - else - tcf_block_put_all_chains(block); - } else if (q) { - tcf_block_offload_unbind(block, q, ei); + for (; tp; tp = tcf_chain_dereference(tp->next, chain)) + if (!tp->deleting && tp->prio >= prio) + break; + } else { + tp = tcf_chain_dereference(tp->next, chain); } + + if (tp) + tcf_proto_get(tp); + + mutex_unlock(&chain->filter_chain_lock); + + return tp; } -static void tcf_block_refcnt_put(struct tcf_block *block) +/* Function to be used by all clients that want to iterate over all tp's on + * chain. Users of this function must be tolerant to concurrent tp + * insertion/deletion or ensure that no concurrent chain modification is + * possible. Note that all netlink dump callbacks cannot guarantee to provide + * consistent dump because rtnl lock is released each time skb is filled with + * data and sent to user-space. + */ + +struct tcf_proto * +tcf_get_next_proto(struct tcf_chain *chain, struct tcf_proto *tp, + bool rtnl_held) { - __tcf_block_put(block, NULL, NULL); + struct tcf_proto *tp_next = __tcf_get_next_proto(chain, tp); + + if (tp) + tcf_proto_put(tp, rtnl_held, NULL); + + return tp_next; } +EXPORT_SYMBOL(tcf_get_next_proto); -/* Find tcf block. - * Set q, parent, cl when appropriate. +static void tcf_block_flush_all_chains(struct tcf_block *block, bool rtnl_held) +{ + struct tcf_chain *chain; + + /* Last reference to block. At this point chains cannot be added or + * removed concurrently. + */ + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { + tcf_chain_put_explicitly_created(chain); + tcf_chain_flush(chain, rtnl_held); + } +} + +/* Lookup Qdisc and increments its reference counter. + * Set parent, if necessary. */ -static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, - u32 *parent, unsigned long *cl, - int ifindex, u32 block_index, - struct netlink_ext_ack *extack) +static int __tcf_qdisc_find(struct net *net, struct Qdisc **q, + u32 *parent, int ifindex, bool rtnl_held, + struct netlink_ext_ack *extack) { - struct tcf_block *block; + const struct Qdisc_class_ops *cops; + struct net_device *dev; int err = 0; - if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { - block = tcf_block_refcnt_get(net, block_index); - if (!block) { - NL_SET_ERR_MSG(extack, "Block of given index was not found"); - return ERR_PTR(-EINVAL); - } - } else { - const struct Qdisc_class_ops *cops; - struct net_device *dev; - - rcu_read_lock(); + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; - /* Find link */ - dev = dev_get_by_index_rcu(net, ifindex); - if (!dev) { - rcu_read_unlock(); - return ERR_PTR(-ENODEV); - } + rcu_read_lock(); - /* Find qdisc */ - if (!*parent) { - *q = dev->qdisc; - *parent = (*q)->handle; - } else { - *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); - if (!*q) { - NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); - err = -EINVAL; - goto errout_rcu; - } - } + /* Find link */ + dev = dev_get_by_index_rcu(net, ifindex); + if (!dev) { + rcu_read_unlock(); + return -ENODEV; + } - *q = qdisc_refcount_inc_nz(*q); + /* Find qdisc */ + if (!*parent) { + *q = dev->qdisc; + *parent = (*q)->handle; + } else { + *q = qdisc_lookup_rcu(dev, TC_H_MAJ(*parent)); if (!*q) { NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); err = -EINVAL; goto errout_rcu; } + } - /* Is it classful? */ - cops = (*q)->ops->cl_ops; - if (!cops) { - NL_SET_ERR_MSG(extack, "Qdisc not classful"); - err = -EINVAL; - goto errout_rcu; - } + *q = qdisc_refcount_inc_nz(*q); + if (!*q) { + NL_SET_ERR_MSG(extack, "Parent Qdisc doesn't exists"); + err = -EINVAL; + goto errout_rcu; + } - if (!cops->tcf_block) { - NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); - err = -EOPNOTSUPP; - goto errout_rcu; - } + /* Is it classful? */ + cops = (*q)->ops->cl_ops; + if (!cops) { + NL_SET_ERR_MSG(extack, "Qdisc not classful"); + err = -EINVAL; + goto errout_qdisc; + } - /* At this point we know that qdisc is not noop_qdisc, - * which means that qdisc holds a reference to net_device - * and we hold a reference to qdisc, so it is safe to release - * rcu read lock. - */ - rcu_read_unlock(); + if (!cops->tcf_block) { + NL_SET_ERR_MSG(extack, "Class doesn't support blocks"); + err = -EOPNOTSUPP; + goto errout_qdisc; + } - /* Do we search for filter, attached to class? */ - if (TC_H_MIN(*parent)) { - *cl = cops->find(*q, *parent); - if (*cl == 0) { - NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); - err = -ENOENT; - goto errout_qdisc; - } +errout_rcu: + /* At this point we know that qdisc is not noop_qdisc, + * which means that qdisc holds a reference to net_device + * and we hold a reference to qdisc, so it is safe to release + * rcu read lock. + */ + rcu_read_unlock(); + return err; + +errout_qdisc: + rcu_read_unlock(); + + if (rtnl_held) + qdisc_put(*q); + else + qdisc_put_unlocked(*q); + *q = NULL; + + return err; +} + +static int __tcf_qdisc_cl_find(struct Qdisc *q, u32 parent, unsigned long *cl, + int ifindex, struct netlink_ext_ack *extack) +{ + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) + return 0; + + /* Do we search for filter, attached to class? */ + if (TC_H_MIN(parent)) { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + *cl = cops->find(q, parent); + if (*cl == 0) { + NL_SET_ERR_MSG(extack, "Specified class doesn't exist"); + return -ENOENT; } + } - /* And the last stroke */ - block = cops->tcf_block(*q, *cl, extack); + return 0; +} + +static struct tcf_block *__tcf_block_find(struct net *net, struct Qdisc *q, + unsigned long cl, int ifindex, + u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + + if (ifindex == TCM_IFINDEX_MAGIC_BLOCK) { + block = tcf_block_refcnt_get(net, block_index); if (!block) { - err = -EINVAL; - goto errout_qdisc; + NL_SET_ERR_MSG(extack, "Block of given index was not found"); + return ERR_PTR(-EINVAL); } + } else { + const struct Qdisc_class_ops *cops = q->ops->cl_ops; + + block = cops->tcf_block(q, cl, extack); + if (!block) + return ERR_PTR(-EINVAL); + if (tcf_block_shared(block)) { NL_SET_ERR_MSG(extack, "This filter block is shared. Please use the block index to manipulate the filters"); - err = -EOPNOTSUPP; - goto errout_qdisc; + return ERR_PTR(-EOPNOTSUPP); } /* Always take reference to block in order to support execution @@ -962,24 +1251,89 @@ static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, } return block; +} + +static void __tcf_block_put(struct tcf_block *block, struct Qdisc *q, + struct tcf_block_ext_info *ei, bool rtnl_held) +{ + if (refcount_dec_and_mutex_lock(&block->refcnt, &block->lock)) { + /* Flushing/putting all chains will cause the block to be + * deallocated when last chain is freed. However, if chain_list + * is empty, block has to be manually deallocated. After block + * reference counter reached 0, it is no longer possible to + * increment it or add new chains to block. + */ + bool free_block = list_empty(&block->chain_list); + + mutex_unlock(&block->lock); + if (tcf_block_shared(block)) + tcf_block_remove(block, block->net); + + if (q) + tcf_block_offload_unbind(block, q, ei); + + if (free_block) + tcf_block_destroy(block); + else + tcf_block_flush_all_chains(block, rtnl_held); + } else if (q) { + tcf_block_offload_unbind(block, q, ei); + } +} + +static void tcf_block_refcnt_put(struct tcf_block *block, bool rtnl_held) +{ + __tcf_block_put(block, NULL, NULL, rtnl_held); +} + +/* Find tcf block. + * Set q, parent, cl when appropriate. + */ + +static struct tcf_block *tcf_block_find(struct net *net, struct Qdisc **q, + u32 *parent, unsigned long *cl, + int ifindex, u32 block_index, + struct netlink_ext_ack *extack) +{ + struct tcf_block *block; + int err = 0; + + ASSERT_RTNL(); + + err = __tcf_qdisc_find(net, q, parent, ifindex, true, extack); + if (err) + goto errout; + + err = __tcf_qdisc_cl_find(*q, *parent, cl, ifindex, extack); + if (err) + goto errout_qdisc; + + block = __tcf_block_find(net, *q, *cl, ifindex, block_index, extack); + if (IS_ERR(block)) + goto errout_qdisc; + + return block; -errout_rcu: - rcu_read_unlock(); errout_qdisc: - if (*q) { + if (*q) qdisc_put(*q); - *q = NULL; - } +errout: + *q = NULL; return ERR_PTR(err); } -static void tcf_block_release(struct Qdisc *q, struct tcf_block *block) +static void tcf_block_release(struct Qdisc *q, struct tcf_block *block, + bool rtnl_held) { if (!IS_ERR_OR_NULL(block)) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, rtnl_held); - if (q) - qdisc_put(q); + if (q) { + if (rtnl_held) + qdisc_put(q); + else + qdisc_put_unlocked(q); + } } struct tcf_block_owner_item { @@ -1087,7 +1441,7 @@ err_chain0_head_change_cb_add: tcf_block_owner_del(block, q, ei->binder_type); err_block_owner_add: err_block_insert: - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); return err; } EXPORT_SYMBOL(tcf_block_get_ext); @@ -1124,7 +1478,7 @@ void tcf_block_put_ext(struct tcf_block *block, struct Qdisc *q, tcf_chain0_head_change_cb_del(block, ei); tcf_block_owner_del(block, q, ei->binder_type); - __tcf_block_put(block, q, ei); + __tcf_block_put(block, q, ei, true); } EXPORT_SYMBOL(tcf_block_put_ext); @@ -1181,13 +1535,19 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, void *cb_priv, bool add, bool offload_in_use, struct netlink_ext_ack *extack) { - struct tcf_chain *chain; - struct tcf_proto *tp; + struct tcf_chain *chain, *chain_prev; + struct tcf_proto *tp, *tp_prev; int err; - list_for_each_entry(chain, &block->chain_list, list) { - for (tp = rtnl_dereference(chain->filter_chain); tp; - tp = rtnl_dereference(tp->next)) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { + for (tp = __tcf_get_next_proto(chain, NULL); tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL)) { if (tp->ops->reoffload) { err = tp->ops->reoffload(tp, add, cb, cb_priv, extack); @@ -1204,6 +1564,8 @@ tcf_block_playback_offloads(struct tcf_block *block, tc_setup_cb_t *cb, return 0; err_playback_remove: + tcf_proto_put(tp, true, NULL); + tcf_chain_put(chain); tcf_block_playback_offloads(block, cb, cb_priv, false, offload_in_use, extack); return err; @@ -1329,32 +1691,116 @@ struct tcf_chain_info { struct tcf_proto __rcu *next; }; -static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain_info *chain_info) +static struct tcf_proto *tcf_chain_tp_prev(struct tcf_chain *chain, + struct tcf_chain_info *chain_info) { - return rtnl_dereference(*chain_info->pprev); + return tcf_chain_dereference(*chain_info->pprev, chain); } -static void tcf_chain_tp_insert(struct tcf_chain *chain, - struct tcf_chain_info *chain_info, - struct tcf_proto *tp) +static int tcf_chain_tp_insert(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + struct tcf_proto *tp) { + if (chain->flushing) + return -EAGAIN; + if (*chain_info->pprev == chain->filter_chain) tcf_chain0_head_change(chain, tp); - RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain_info)); + tcf_proto_get(tp); + RCU_INIT_POINTER(tp->next, tcf_chain_tp_prev(chain, chain_info)); rcu_assign_pointer(*chain_info->pprev, tp); - tcf_chain_hold(chain); + + return 0; } static void tcf_chain_tp_remove(struct tcf_chain *chain, struct tcf_chain_info *chain_info, struct tcf_proto *tp) { - struct tcf_proto *next = rtnl_dereference(chain_info->next); + struct tcf_proto *next = tcf_chain_dereference(chain_info->next, chain); + tcf_proto_mark_delete(tp); if (tp == chain->filter_chain) tcf_chain0_head_change(chain, next); RCU_INIT_POINTER(*chain_info->pprev, next); - tcf_chain_put(chain); +} + +static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, + struct tcf_chain_info *chain_info, + u32 protocol, u32 prio, + bool prio_allocate); + +/* Try to insert new proto. + * If proto with specified priority already exists, free new proto + * and return existing one. + */ + +static struct tcf_proto *tcf_chain_tp_insert_unique(struct tcf_chain *chain, + struct tcf_proto *tp_new, + u32 protocol, u32 prio, + bool rtnl_held) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp; + int err = 0; + + mutex_lock(&chain->filter_chain_lock); + + tp = tcf_chain_tp_find(chain, &chain_info, + protocol, prio, false); + if (!tp) + err = tcf_chain_tp_insert(chain, &chain_info, tp_new); + mutex_unlock(&chain->filter_chain_lock); + + if (tp) { + tcf_proto_destroy(tp_new, rtnl_held, NULL); + tp_new = tp; + } else if (err) { + tcf_proto_destroy(tp_new, rtnl_held, NULL); + tp_new = ERR_PTR(err); + } + + return tp_new; +} + +static void tcf_chain_tp_delete_empty(struct tcf_chain *chain, + struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) +{ + struct tcf_chain_info chain_info; + struct tcf_proto *tp_iter; + struct tcf_proto **pprev; + struct tcf_proto *next; + + mutex_lock(&chain->filter_chain_lock); + + /* Atomically find and remove tp from chain. */ + for (pprev = &chain->filter_chain; + (tp_iter = tcf_chain_dereference(*pprev, chain)); + pprev = &tp_iter->next) { + if (tp_iter == tp) { + chain_info.pprev = pprev; + chain_info.next = tp_iter->next; + WARN_ON(tp_iter->deleting); + break; + } + } + /* Verify that tp still exists and no new filters were inserted + * concurrently. + * Mark tp for deletion if it is empty. + */ + if (!tp_iter || !tcf_proto_check_delete(tp, rtnl_held)) { + mutex_unlock(&chain->filter_chain_lock); + return; + } + + next = tcf_chain_dereference(chain_info.next, chain); + if (tp == chain->filter_chain) + tcf_chain0_head_change(chain, next); + RCU_INIT_POINTER(*chain_info.pprev, next); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, extack); } static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, @@ -1367,7 +1813,8 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, /* Check the chain for existence of proto-tcf with this priority */ for (pprev = &chain->filter_chain; - (tp = rtnl_dereference(*pprev)); pprev = &tp->next) { + (tp = tcf_chain_dereference(*pprev, chain)); + pprev = &tp->next) { if (tp->prio >= prio) { if (tp->prio == prio) { if (prio_allocate || @@ -1380,14 +1827,20 @@ static struct tcf_proto *tcf_chain_tp_find(struct tcf_chain *chain, } } chain_info->pprev = pprev; - chain_info->next = tp ? tp->next : NULL; + if (tp) { + chain_info->next = tp->next; + tcf_proto_get(tp); + } else { + chain_info->next = NULL; + } return tp; } static int tcf_fill_node(struct net *net, struct sk_buff *skb, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, - u32 portid, u32 seq, u16 flags, int event) + u32 portid, u32 seq, u16 flags, int event, + bool rtnl_held) { struct tcmsg *tcm; struct nlmsghdr *nlh; @@ -1415,7 +1868,8 @@ static int tcf_fill_node(struct net *net, struct sk_buff *skb, if (!fh) { tcm->tcm_handle = 0; } else { - if (tp->ops->dump && tp->ops->dump(net, tp, fh, skb, tcm) < 0) + if (tp->ops->dump && + tp->ops->dump(net, tp, fh, skb, tcm, rtnl_held) < 0) goto nla_put_failure; } nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -1430,7 +1884,8 @@ nla_put_failure: static int tfilter_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, - u32 parent, void *fh, int event, bool unicast) + u32 parent, void *fh, int event, bool unicast, + bool rtnl_held) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1440,7 +1895,8 @@ static int tfilter_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, event) <= 0) { + n->nlmsg_seq, n->nlmsg_flags, event, + rtnl_held) <= 0) { kfree_skb(skb); return -EINVAL; } @@ -1456,7 +1912,7 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, struct nlmsghdr *n, struct tcf_proto *tp, struct tcf_block *block, struct Qdisc *q, u32 parent, void *fh, bool unicast, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct sk_buff *skb; u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; @@ -1467,13 +1923,14 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, return -ENOBUFS; if (tcf_fill_node(net, skb, tp, block, q, parent, fh, portid, - n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER) <= 0) { + n->nlmsg_seq, n->nlmsg_flags, RTM_DELTFILTER, + rtnl_held) <= 0) { NL_SET_ERR_MSG(extack, "Failed to build del event notification"); kfree_skb(skb); return -EINVAL; } - err = tp->ops->delete(tp, fh, last, extack); + err = tp->ops->delete(tp, fh, last, rtnl_held, extack); if (err) { kfree_skb(skb); return err; @@ -1492,14 +1949,21 @@ static int tfilter_del_notify(struct net *net, struct sk_buff *oskb, static void tfilter_notify_chain(struct net *net, struct sk_buff *oskb, struct tcf_block *block, struct Qdisc *q, u32 parent, struct nlmsghdr *n, - struct tcf_chain *chain, int event) + struct tcf_chain *chain, int event, + bool rtnl_held) { struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) + for (tp = tcf_get_next_proto(chain, NULL, rtnl_held); + tp; tp = tcf_get_next_proto(chain, tp, rtnl_held)) tfilter_notify(net, oskb, n, tp, block, - q, parent, NULL, event, false); + q, parent, NULL, event, false, rtnl_held); +} + +static void tfilter_put(struct tcf_proto *tp, void *fh) +{ + if (tp->ops->put && fh) + tp->ops->put(tp, fh); } static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1522,6 +1986,7 @@ static int tc_new_tfilter(struct sk_buff *skb, struct nlmsghdr *n, void *fh; int err; int tp_created; + bool rtnl_held = false; if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1538,7 +2003,9 @@ replay: prio = TC_H_MAJ(t->tcm_info); prio_allocate = false; parent = t->tcm_parent; + tp = NULL; cl = 0; + block = NULL; if (prio == 0) { /* If no priority is provided by the user, @@ -1555,8 +2022,27 @@ replay: /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + /* Take rtnl mutex if rtnl_held was set to true on previous iteration, + * block is shared (no qdisc found), qdisc is not unlocked, classifier + * type is not specified, classifier is not unlocked. + */ + if (rtnl_held || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; @@ -1575,40 +2061,62 @@ replay: goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, prio_allocate); if (IS_ERR(tp)) { NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = PTR_ERR(tp); - goto errout; + goto errout_locked; } if (tp == NULL) { + struct tcf_proto *tp_new = NULL; + + if (chain->flushing) { + err = -EAGAIN; + goto errout_locked; + } + /* Proto-tcf does not exist, create new one */ if (tca[TCA_KIND] == NULL || !protocol) { NL_SET_ERR_MSG(extack, "Filter kind and protocol must be specified"); err = -EINVAL; - goto errout; + goto errout_locked; } if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWTFILTER and NLM_F_CREATE to create a new filter"); err = -ENOENT; - goto errout; + goto errout_locked; } if (prio_allocate) - prio = tcf_auto_prio(tcf_chain_tp_prev(&chain_info)); + prio = tcf_auto_prio(tcf_chain_tp_prev(chain, + &chain_info)); - tp = tcf_proto_create(nla_data(tca[TCA_KIND]), - protocol, prio, chain, extack); + mutex_unlock(&chain->filter_chain_lock); + tp_new = tcf_proto_create(nla_data(tca[TCA_KIND]), + protocol, prio, chain, rtnl_held, + extack); + if (IS_ERR(tp_new)) { + err = PTR_ERR(tp_new); + goto errout_tp; + } + + tp_created = 1; + tp = tcf_chain_tp_insert_unique(chain, tp_new, protocol, prio, + rtnl_held); if (IS_ERR(tp)) { err = PTR_ERR(tp); - goto errout; + goto errout_tp; } - tp_created = 1; - } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { + } else { + mutex_unlock(&chain->filter_chain_lock); + } + + if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; goto errout; @@ -1623,6 +2131,7 @@ replay: goto errout; } } else if (n->nlmsg_flags & NLM_F_EXCL) { + tfilter_put(tp, fh); NL_SET_ERR_MSG(extack, "Filter already exists"); err = -EEXIST; goto errout; @@ -1636,25 +2145,41 @@ replay: err = tp->ops->change(net, skb, tp, cl, t->tcm_handle, tca, &fh, n->nlmsg_flags & NLM_F_CREATE ? TCA_ACT_NOREPLACE : TCA_ACT_REPLACE, - extack); + rtnl_held, extack); if (err == 0) { - if (tp_created) - tcf_chain_tp_insert(chain, &chain_info, tp); tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_NEWTFILTER, false); - } else { - if (tp_created) - tcf_proto_destroy(tp, NULL); + RTM_NEWTFILTER, false, rtnl_held); + tfilter_put(tp, fh); } errout: - if (chain) - tcf_chain_put(chain); - tcf_block_release(q, block); - if (err == -EAGAIN) + if (err && tp_created) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, NULL); +errout_tp: + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); + if (!tp_created) + tcf_chain_put(chain); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + + if (err == -EAGAIN) { + /* Take rtnl lock in case EAGAIN is caused by concurrent flush + * of target chain. + */ + rtnl_held = true; /* Replay the request. */ goto replay; + } return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1670,11 +2195,12 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; - struct tcf_block *block; + struct tcf_block *block = NULL; struct tcf_proto *tp = NULL; unsigned long cl = 0; void *fh = NULL; int err; + bool rtnl_held = false; if (!netlink_ns_capable(skb, net->user_ns, CAP_NET_ADMIN)) return -EPERM; @@ -1695,8 +2221,27 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + /* Take rtnl mutex if flushing whole chain, block is shared (no qdisc + * found), qdisc is not unlocked, classifier type is not specified, + * classifier is not unlocked. + */ + if (!prio || + (q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; @@ -1724,56 +2269,69 @@ static int tc_del_tfilter(struct sk_buff *skb, struct nlmsghdr *n, if (prio == 0) { tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); - tcf_chain_flush(chain); + chain, RTM_DELTFILTER, rtnl_held); + tcf_chain_flush(chain, rtnl_held); err = 0; goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); if (!tp || IS_ERR(tp)) { NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = tp ? PTR_ERR(tp) : -ENOENT; - goto errout; + goto errout_locked; } else if (tca[TCA_KIND] && nla_strcmp(tca[TCA_KIND], tp->ops->kind)) { NL_SET_ERR_MSG(extack, "Specified filter kind does not match existing one"); err = -EINVAL; + goto errout_locked; + } else if (t->tcm_handle == 0) { + tcf_chain_tp_remove(chain, &chain_info, tp); + mutex_unlock(&chain->filter_chain_lock); + + tcf_proto_put(tp, rtnl_held, NULL); + tfilter_notify(net, skb, n, tp, block, q, parent, fh, + RTM_DELTFILTER, false, rtnl_held); + err = 0; goto errout; } + mutex_unlock(&chain->filter_chain_lock); fh = tp->ops->get(tp, t->tcm_handle); if (!fh) { - if (t->tcm_handle == 0) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tfilter_notify(net, skb, n, tp, block, q, parent, fh, - RTM_DELTFILTER, false); - tcf_proto_destroy(tp, extack); - err = 0; - } else { - NL_SET_ERR_MSG(extack, "Specified filter handle not found"); - err = -ENOENT; - } + NL_SET_ERR_MSG(extack, "Specified filter handle not found"); + err = -ENOENT; } else { bool last; err = tfilter_del_notify(net, skb, n, tp, block, q, parent, fh, false, &last, - extack); + rtnl_held, extack); + if (err) goto errout; - if (last) { - tcf_chain_tp_remove(chain, &chain_info, tp); - tcf_proto_destroy(tp, extack); - } + if (last) + tcf_chain_tp_delete_empty(chain, tp, rtnl_held, extack); } errout: - if (chain) + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); tcf_chain_put(chain); - tcf_block_release(q, block); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + return err; + +errout_locked: + mutex_unlock(&chain->filter_chain_lock); + goto errout; } static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, @@ -1789,11 +2347,12 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, struct Qdisc *q = NULL; struct tcf_chain_info chain_info; struct tcf_chain *chain = NULL; - struct tcf_block *block; + struct tcf_block *block = NULL; struct tcf_proto *tp = NULL; unsigned long cl = 0; void *fh = NULL; int err; + bool rtnl_held = false; err = nlmsg_parse(n, sizeof(*t), tca, TCA_MAX, rtm_tca_policy, extack); if (err < 0) @@ -1811,8 +2370,26 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, /* Find head of filter chain. */ - block = tcf_block_find(net, &q, &parent, &cl, - t->tcm_ifindex, t->tcm_block_index, extack); + err = __tcf_qdisc_find(net, &q, &parent, t->tcm_ifindex, false, extack); + if (err) + return err; + + /* Take rtnl mutex if block is shared (no qdisc found), qdisc is not + * unlocked, classifier type is not specified, classifier is not + * unlocked. + */ + if ((q && !(q->ops->cl_ops->flags & QDISC_CLASS_OPS_DOIT_UNLOCKED)) || + !tca[TCA_KIND] || !tcf_proto_is_unlocked(nla_data(tca[TCA_KIND]))) { + rtnl_held = true; + rtnl_lock(); + } + + err = __tcf_qdisc_cl_find(q, parent, &cl, t->tcm_ifindex, extack); + if (err) + goto errout; + + block = __tcf_block_find(net, q, cl, t->tcm_ifindex, t->tcm_block_index, + extack); if (IS_ERR(block)) { err = PTR_ERR(block); goto errout; @@ -1831,8 +2408,10 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, goto errout; } + mutex_lock(&chain->filter_chain_lock); tp = tcf_chain_tp_find(chain, &chain_info, protocol, prio, false); + mutex_unlock(&chain->filter_chain_lock); if (!tp || IS_ERR(tp)) { NL_SET_ERR_MSG(extack, "Filter with specified priority/protocol not found"); err = tp ? PTR_ERR(tp) : -ENOENT; @@ -1850,15 +2429,23 @@ static int tc_get_tfilter(struct sk_buff *skb, struct nlmsghdr *n, err = -ENOENT; } else { err = tfilter_notify(net, skb, n, tp, block, q, parent, - fh, RTM_NEWTFILTER, true); + fh, RTM_NEWTFILTER, true, rtnl_held); if (err < 0) NL_SET_ERR_MSG(extack, "Failed to send filter notify message"); } + tfilter_put(tp, fh); errout: - if (chain) + if (chain) { + if (tp && !IS_ERR(tp)) + tcf_proto_put(tp, rtnl_held, NULL); tcf_chain_put(chain); - tcf_block_release(q, block); + } + tcf_block_release(q, block, rtnl_held); + + if (rtnl_held) + rtnl_unlock(); + return err; } @@ -1879,7 +2466,7 @@ static int tcf_node_dump(struct tcf_proto *tp, void *n, struct tcf_walker *arg) return tcf_fill_node(net, a->skb, tp, a->block, a->q, a->parent, n, NETLINK_CB(a->cb->skb).portid, a->cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER); + RTM_NEWTFILTER, true); } static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, @@ -1889,11 +2476,15 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, struct net *net = sock_net(skb->sk); struct tcf_block *block = chain->block; struct tcmsg *tcm = nlmsg_data(cb->nlh); + struct tcf_proto *tp, *tp_prev; struct tcf_dump_args arg; - struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next), (*p_index)++) { + for (tp = __tcf_get_next_proto(chain, NULL); + tp; + tp_prev = tp, + tp = __tcf_get_next_proto(chain, tp), + tcf_proto_put(tp_prev, true, NULL), + (*p_index)++) { if (*p_index < index_start) continue; if (TC_H_MAJ(tcm->tcm_info) && @@ -1909,9 +2500,8 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, if (tcf_fill_node(net, skb, tp, block, q, parent, NULL, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, - RTM_NEWTFILTER) <= 0) - return false; - + RTM_NEWTFILTER, true) <= 0) + goto errout; cb->args[1] = 1; } if (!tp->ops->walk) @@ -1926,23 +2516,27 @@ static bool tcf_chain_dump(struct tcf_chain *chain, struct Qdisc *q, u32 parent, arg.w.skip = cb->args[1] - 1; arg.w.count = 0; arg.w.cookie = cb->args[2]; - tp->ops->walk(tp, &arg.w); + tp->ops->walk(tp, &arg.w, true); cb->args[2] = arg.w.cookie; cb->args[1] = arg.w.count + 1; if (arg.w.stop) - return false; + goto errout; } return true; + +errout: + tcf_proto_put(tp, true, NULL); + return false; } /* called with RTNL */ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) { + struct tcf_chain *chain, *chain_prev; struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); long index_start; long index; @@ -2006,19 +2600,24 @@ static int tc_dump_tfilter(struct sk_buff *skb, struct netlink_callback *cb) index_start = cb->args[0]; index = 0; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { if (tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index) continue; if (!tcf_chain_dump(chain, q, parent, skb, cb, index_start, &index)) { + tcf_chain_put(chain); err = -EMSGSIZE; break; } } if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); cb->args[0] = index; out: @@ -2028,8 +2627,10 @@ out: return skb->len; } -static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, - struct sk_buff *skb, struct tcf_block *block, +static int tc_chain_fill_node(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct net *net, struct sk_buff *skb, + struct tcf_block *block, u32 portid, u32 seq, u16 flags, int event) { unsigned char *b = skb_tail_pointer(skb); @@ -2038,8 +2639,8 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, struct tcmsg *tcm; void *priv; - ops = chain->tmplt_ops; - priv = chain->tmplt_priv; + ops = tmplt_ops; + priv = tmplt_priv; nlh = nlmsg_put(skb, portid, seq, event, sizeof(*tcm), flags); if (!nlh) @@ -2057,7 +2658,7 @@ static int tc_chain_fill_node(struct tcf_chain *chain, struct net *net, tcm->tcm_block_index = block->index; } - if (nla_put_u32(skb, TCA_CHAIN, chain->index)) + if (nla_put_u32(skb, TCA_CHAIN, chain_index)) goto nla_put_failure; if (ops) { @@ -2088,7 +2689,8 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, if (!skb) return -ENOBUFS; - if (tc_chain_fill_node(chain, net, skb, block, portid, + if (tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, portid, seq, flags, event) <= 0) { kfree_skb(skb); return -EINVAL; @@ -2100,6 +2702,31 @@ static int tc_chain_notify(struct tcf_chain *chain, struct sk_buff *oskb, return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); } +static int tc_chain_notify_delete(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv, u32 chain_index, + struct tcf_block *block, struct sk_buff *oskb, + u32 seq, u16 flags, bool unicast) +{ + u32 portid = oskb ? NETLINK_CB(oskb).portid : 0; + struct net *net = block->net; + struct sk_buff *skb; + + skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); + if (!skb) + return -ENOBUFS; + + if (tc_chain_fill_node(tmplt_ops, tmplt_priv, chain_index, net, skb, + block, portid, seq, flags, RTM_DELCHAIN) <= 0) { + kfree_skb(skb); + return -EINVAL; + } + + if (unicast) + return netlink_unicast(net->rtnl, skb, portid, MSG_DONTWAIT); + + return rtnetlink_send(skb, net, portid, RTNLGRP_TC, flags & NLM_F_ECHO); +} + static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, struct nlattr **tca, struct netlink_ext_ack *extack) @@ -2111,7 +2738,7 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, if (!tca[TCA_KIND]) return 0; - ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), extack); + ops = tcf_proto_lookup_ops(nla_data(tca[TCA_KIND]), true, extack); if (IS_ERR(ops)) return PTR_ERR(ops); if (!ops->tmplt_create || !ops->tmplt_destroy || !ops->tmplt_dump) { @@ -2129,16 +2756,15 @@ static int tc_chain_tmplt_add(struct tcf_chain *chain, struct net *net, return 0; } -static void tc_chain_tmplt_del(struct tcf_chain *chain) +static void tc_chain_tmplt_del(const struct tcf_proto_ops *tmplt_ops, + void *tmplt_priv) { - const struct tcf_proto_ops *ops = chain->tmplt_ops; - /* If template ops are set, no work to do for us. */ - if (!ops) + if (!tmplt_ops) return; - ops->tmplt_destroy(chain->tmplt_priv); - module_put(ops->owner); + tmplt_ops->tmplt_destroy(tmplt_priv); + module_put(tmplt_ops->owner); } /* Add/delete/get a chain */ @@ -2181,6 +2807,8 @@ replay: err = -EINVAL; goto errout_block; } + + mutex_lock(&block->lock); chain = tcf_chain_lookup(block, chain_index); if (n->nlmsg_type == RTM_NEWCHAIN) { if (chain) { @@ -2192,54 +2820,61 @@ replay: } else { NL_SET_ERR_MSG(extack, "Filter chain already exists"); err = -EEXIST; - goto errout_block; + goto errout_block_locked; } } else { if (!(n->nlmsg_flags & NLM_F_CREATE)) { NL_SET_ERR_MSG(extack, "Need both RTM_NEWCHAIN and NLM_F_CREATE to create a new chain"); err = -ENOENT; - goto errout_block; + goto errout_block_locked; } chain = tcf_chain_create(block, chain_index); if (!chain) { NL_SET_ERR_MSG(extack, "Failed to create filter chain"); err = -ENOMEM; - goto errout_block; + goto errout_block_locked; } } } else { if (!chain || tcf_chain_held_by_acts_only(chain)) { NL_SET_ERR_MSG(extack, "Cannot find specified filter chain"); err = -EINVAL; - goto errout_block; + goto errout_block_locked; } tcf_chain_hold(chain); } + if (n->nlmsg_type == RTM_NEWCHAIN) { + /* Modifying chain requires holding parent block lock. In case + * the chain was successfully added, take a reference to the + * chain. This ensures that an empty chain does not disappear at + * the end of this function. + */ + tcf_chain_hold(chain); + chain->explicitly_created = true; + } + mutex_unlock(&block->lock); + switch (n->nlmsg_type) { case RTM_NEWCHAIN: err = tc_chain_tmplt_add(chain, net, tca, extack); - if (err) + if (err) { + tcf_chain_put_explicitly_created(chain); goto errout; - /* In case the chain was successfully added, take a reference - * to the chain. This ensures that an empty chain - * does not disappear at the end of this function. - */ - tcf_chain_hold(chain); - chain->explicitly_created = true; + } + tc_chain_notify(chain, NULL, 0, NLM_F_CREATE | NLM_F_EXCL, RTM_NEWCHAIN, false); break; case RTM_DELCHAIN: tfilter_notify_chain(net, skb, block, q, parent, n, - chain, RTM_DELTFILTER); + chain, RTM_DELTFILTER, true); /* Flush the chain first as the user requested chain removal. */ - tcf_chain_flush(chain); + tcf_chain_flush(chain, true); /* In case the chain was successfully deleted, put a reference * to the chain previously taken during addition. */ tcf_chain_put_explicitly_created(chain); - chain->explicitly_created = false; break; case RTM_GETCHAIN: err = tc_chain_notify(chain, skb, n->nlmsg_seq, @@ -2256,21 +2891,25 @@ replay: errout: tcf_chain_put(chain); errout_block: - tcf_block_release(q, block); + tcf_block_release(q, block, true); if (err == -EAGAIN) /* Replay the request. */ goto replay; return err; + +errout_block_locked: + mutex_unlock(&block->lock); + goto errout_block; } /* called with RTNL */ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) { + struct tcf_chain *chain, *chain_prev; struct net *net = sock_net(skb->sk); struct nlattr *tca[TCA_MAX + 1]; struct Qdisc *q = NULL; struct tcf_block *block; - struct tcf_chain *chain; struct tcmsg *tcm = nlmsg_data(cb->nlh); long index_start; long index; @@ -2334,7 +2973,11 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index_start = cb->args[0]; index = 0; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = __tcf_get_next_chain(block, NULL); + chain; + chain_prev = chain, + chain = __tcf_get_next_chain(block, chain), + tcf_chain_put(chain_prev)) { if ((tca[TCA_CHAIN] && nla_get_u32(tca[TCA_CHAIN]) != chain->index)) continue; @@ -2342,19 +2985,20 @@ static int tc_dump_chain(struct sk_buff *skb, struct netlink_callback *cb) index++; continue; } - if (tcf_chain_held_by_acts_only(chain)) - continue; - err = tc_chain_fill_node(chain, net, skb, block, + err = tc_chain_fill_node(chain->tmplt_ops, chain->tmplt_priv, + chain->index, net, skb, block, NETLINK_CB(cb->skb).portid, cb->nlh->nlmsg_seq, NLM_F_MULTI, RTM_NEWCHAIN); - if (err <= 0) + if (err <= 0) { + tcf_chain_put(chain); break; + } index++; } if (tcm->tcm_ifindex == TCM_IFINDEX_MAGIC_BLOCK) - tcf_block_refcnt_put(block); + tcf_block_refcnt_put(block, true); cb->args[0] = index; out: @@ -2376,7 +3020,7 @@ EXPORT_SYMBOL(tcf_exts_destroy); int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, struct nlattr *rate_tlv, struct tcf_exts *exts, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { #ifdef CONFIG_NET_CLS_ACT { @@ -2386,7 +3030,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, if (exts->police && tb[exts->police]) { act = tcf_action_init_1(net, tp, tb[exts->police], rate_tlv, "police", ovr, - TCA_ACT_BIND, true, extack); + TCA_ACT_BIND, rtnl_held, + extack); if (IS_ERR(act)) return PTR_ERR(act); @@ -2398,8 +3043,8 @@ int tcf_exts_validate(struct net *net, struct tcf_proto *tp, struct nlattr **tb, err = tcf_action_init(net, tp, tb[exts->action], rate_tlv, NULL, ovr, TCA_ACT_BIND, - exts->actions, &attr_size, true, - extack); + exts->actions, &attr_size, + rtnl_held, extack); if (err < 0) return err; exts->nr_actions = err; @@ -2515,6 +3160,114 @@ int tc_setup_cb_call(struct tcf_block *block, enum tc_setup_type type, } EXPORT_SYMBOL(tc_setup_cb_call); +int tc_setup_flow_action(struct flow_action *flow_action, + const struct tcf_exts *exts) +{ + const struct tc_action *act; + int i, j, k; + + if (!exts) + return 0; + + j = 0; + tcf_exts_for_each_action(i, act, exts) { + struct flow_action_entry *entry; + + entry = &flow_action->entries[j]; + if (is_tcf_gact_ok(act)) { + entry->id = FLOW_ACTION_ACCEPT; + } else if (is_tcf_gact_shot(act)) { + entry->id = FLOW_ACTION_DROP; + } else if (is_tcf_gact_trap(act)) { + entry->id = FLOW_ACTION_TRAP; + } else if (is_tcf_gact_goto_chain(act)) { + entry->id = FLOW_ACTION_GOTO; + entry->chain_index = tcf_gact_goto_chain_index(act); + } else if (is_tcf_mirred_egress_redirect(act)) { + entry->id = FLOW_ACTION_REDIRECT; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_mirred_egress_mirror(act)) { + entry->id = FLOW_ACTION_MIRRED; + entry->dev = tcf_mirred_dev(act); + } else if (is_tcf_vlan(act)) { + switch (tcf_vlan_action(act)) { + case TCA_VLAN_ACT_PUSH: + entry->id = FLOW_ACTION_VLAN_PUSH; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + case TCA_VLAN_ACT_POP: + entry->id = FLOW_ACTION_VLAN_POP; + break; + case TCA_VLAN_ACT_MODIFY: + entry->id = FLOW_ACTION_VLAN_MANGLE; + entry->vlan.vid = tcf_vlan_push_vid(act); + entry->vlan.proto = tcf_vlan_push_proto(act); + entry->vlan.prio = tcf_vlan_push_prio(act); + break; + default: + goto err_out; + } + } else if (is_tcf_tunnel_set(act)) { + entry->id = FLOW_ACTION_TUNNEL_ENCAP; + entry->tunnel = tcf_tunnel_info(act); + } else if (is_tcf_tunnel_release(act)) { + entry->id = FLOW_ACTION_TUNNEL_DECAP; + entry->tunnel = tcf_tunnel_info(act); + } else if (is_tcf_pedit(act)) { + for (k = 0; k < tcf_pedit_nkeys(act); k++) { + switch (tcf_pedit_cmd(act, k)) { + case TCA_PEDIT_KEY_EX_CMD_SET: + entry->id = FLOW_ACTION_MANGLE; + break; + case TCA_PEDIT_KEY_EX_CMD_ADD: + entry->id = FLOW_ACTION_ADD; + break; + default: + goto err_out; + } + entry->mangle.htype = tcf_pedit_htype(act, k); + entry->mangle.mask = tcf_pedit_mask(act, k); + entry->mangle.val = tcf_pedit_val(act, k); + entry->mangle.offset = tcf_pedit_offset(act, k); + entry = &flow_action->entries[++j]; + } + } else if (is_tcf_csum(act)) { + entry->id = FLOW_ACTION_CSUM; + entry->csum_flags = tcf_csum_update_flags(act); + } else if (is_tcf_skbedit_mark(act)) { + entry->id = FLOW_ACTION_MARK; + entry->mark = tcf_skbedit_mark(act); + } else { + goto err_out; + } + + if (!is_tcf_pedit(act)) + j++; + } + return 0; +err_out: + return -EOPNOTSUPP; +} +EXPORT_SYMBOL(tc_setup_flow_action); + +unsigned int tcf_exts_num_actions(struct tcf_exts *exts) +{ + unsigned int num_acts = 0; + struct tc_action *act; + int i; + + tcf_exts_for_each_action(i, act, exts) { + if (is_tcf_pedit(act)) + num_acts += tcf_pedit_nkeys(act); + else + num_acts++; + } + return num_acts; +} +EXPORT_SYMBOL(tcf_exts_num_actions); + static __net_init int tcf_net_init(struct net *net) { struct tcf_net *tn = net_generic(net, tcf_net_id); @@ -2555,10 +3308,12 @@ static int __init tc_filter_init(void) if (err) goto err_rhash_setup_block_ht; - rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, 0); - rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, 0); + rtnl_register(PF_UNSPEC, RTM_NEWTFILTER, tc_new_tfilter, NULL, + RTNL_FLAG_DOIT_UNLOCKED); + rtnl_register(PF_UNSPEC, RTM_DELTFILTER, tc_del_tfilter, NULL, + RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_GETTFILTER, tc_get_tfilter, - tc_dump_tfilter, 0); + tc_dump_tfilter, RTNL_FLAG_DOIT_UNLOCKED); rtnl_register(PF_UNSPEC, RTM_NEWCHAIN, tc_ctl_chain, NULL, 0); rtnl_register(PF_UNSPEC, RTM_DELCHAIN, tc_ctl_chain, NULL, 0); rtnl_register(PF_UNSPEC, RTM_GETCHAIN, tc_ctl_chain, diff --git a/net/sched/cls_basic.c b/net/sched/cls_basic.c index 6a5dce8baf19..2383f449d2bc 100644 --- a/net/sched/cls_basic.c +++ b/net/sched/cls_basic.c @@ -18,6 +18,7 @@ #include <linux/rtnetlink.h> #include <linux/skbuff.h> #include <linux/idr.h> +#include <linux/percpu.h> #include <net/netlink.h> #include <net/act_api.h> #include <net/pkt_cls.h> @@ -35,6 +36,7 @@ struct basic_filter { struct tcf_result res; struct tcf_proto *tp; struct list_head link; + struct tc_basic_pcnt __percpu *pf; struct rcu_work rwork; }; @@ -46,8 +48,10 @@ static int basic_classify(struct sk_buff *skb, const struct tcf_proto *tp, struct basic_filter *f; list_for_each_entry_rcu(f, &head->flist, link) { + __this_cpu_inc(f->pf->rcnt); if (!tcf_em_tree_match(skb, &f->ematches, NULL)) continue; + __this_cpu_inc(f->pf->rhit); *res = f->res; r = tcf_exts_exec(skb, &f->exts, res); if (r < 0) @@ -89,6 +93,7 @@ static void __basic_delete_filter(struct basic_filter *f) tcf_exts_destroy(&f->exts); tcf_em_tree_destroy(&f->ematches); tcf_exts_put_net(&f->exts); + free_percpu(f->pf); kfree(f); } @@ -102,7 +107,8 @@ static void basic_delete_filter_work(struct work_struct *work) rtnl_unlock(); } -static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void basic_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f, *n; @@ -121,7 +127,7 @@ static void basic_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int basic_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f = arg; @@ -148,7 +154,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack); if (err < 0) return err; @@ -168,7 +174,7 @@ static int basic_set_parms(struct net *net, struct tcf_proto *tp, static int basic_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { int err; struct basic_head *head = rtnl_dereference(tp->root); @@ -208,6 +214,11 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout; fnew->handle = handle; + fnew->pf = alloc_percpu(struct tc_basic_pcnt); + if (!fnew->pf) { + err = -ENOMEM; + goto errout; + } err = basic_set_parms(net, tp, fnew, base, tb, tca[TCA_RATE], ovr, extack); @@ -231,12 +242,14 @@ static int basic_change(struct net *net, struct sk_buff *in_skb, return 0; errout: + free_percpu(fnew->pf); tcf_exts_destroy(&fnew->exts); kfree(fnew); return err; } -static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void basic_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct basic_head *head = rtnl_dereference(tp->root); struct basic_filter *f; @@ -263,10 +276,12 @@ static void basic_bind_class(void *fh, u32 classid, unsigned long cl) } static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { + struct tc_basic_pcnt gpf = {}; struct basic_filter *f = fh; struct nlattr *nest; + int cpu; if (f == NULL) return skb->len; @@ -281,6 +296,18 @@ static int basic_dump(struct net *net, struct tcf_proto *tp, void *fh, nla_put_u32(skb, TCA_BASIC_CLASSID, f->res.classid)) goto nla_put_failure; + for_each_possible_cpu(cpu) { + struct tc_basic_pcnt *pf = per_cpu_ptr(f->pf, cpu); + + gpf.rcnt += pf->rcnt; + gpf.rhit += pf->rhit; + } + + if (nla_put_64bit(skb, TCA_BASIC_PCNT, + sizeof(struct tc_basic_pcnt), + &gpf, TCA_BASIC_PAD)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &f->exts) < 0 || tcf_em_tree_dump(skb, &f->ematches, TCA_BASIC_EMATCHES) < 0) goto nla_put_failure; diff --git a/net/sched/cls_bpf.c b/net/sched/cls_bpf.c index a95cb240a606..062350c6621c 100644 --- a/net/sched/cls_bpf.c +++ b/net/sched/cls_bpf.c @@ -298,7 +298,7 @@ static void __cls_bpf_delete(struct tcf_proto *tp, struct cls_bpf_prog *prog, } static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); @@ -307,7 +307,7 @@ static int cls_bpf_delete(struct tcf_proto *tp, void *arg, bool *last, return 0; } -static void cls_bpf_destroy(struct tcf_proto *tp, +static void cls_bpf_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); @@ -417,7 +417,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, if ((!is_bpf && !is_ebpf) || (is_bpf && is_ebpf)) return -EINVAL; - ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, extack); + ret = tcf_exts_validate(net, tp, tb, est, &prog->exts, ovr, true, + extack); if (ret < 0) return ret; @@ -455,7 +456,8 @@ static int cls_bpf_set_parms(struct net *net, struct tcf_proto *tp, static int cls_bpf_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *oldprog = *arg; @@ -575,7 +577,7 @@ static int cls_bpf_dump_ebpf_info(const struct cls_bpf_prog *prog, } static int cls_bpf_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *tm) + struct sk_buff *skb, struct tcmsg *tm, bool rtnl_held) { struct cls_bpf_prog *prog = fh; struct nlattr *nest; @@ -635,7 +637,8 @@ static void cls_bpf_bind_class(void *fh, u32 classid, unsigned long cl) prog->res.class = cl; } -static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void cls_bpf_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_bpf_head *head = rtnl_dereference(tp->root); struct cls_bpf_prog *prog; diff --git a/net/sched/cls_cgroup.c b/net/sched/cls_cgroup.c index 3bc01bdde165..1cef3b416094 100644 --- a/net/sched/cls_cgroup.c +++ b/net/sched/cls_cgroup.c @@ -78,7 +78,7 @@ static void cls_cgroup_destroy_work(struct work_struct *work) static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, + void **arg, bool ovr, bool rtnl_held, struct netlink_ext_ack *extack) { struct nlattr *tb[TCA_CGROUP_MAX + 1]; @@ -110,7 +110,7 @@ static int cls_cgroup_change(struct net *net, struct sk_buff *in_skb, goto errout; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &new->exts, ovr, - extack); + true, extack); if (err < 0) goto errout; @@ -130,7 +130,7 @@ errout: return err; } -static void cls_cgroup_destroy(struct tcf_proto *tp, +static void cls_cgroup_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); @@ -145,12 +145,13 @@ static void cls_cgroup_destroy(struct tcf_proto *tp, } static int cls_cgroup_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void cls_cgroup_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); @@ -166,7 +167,7 @@ skip: } static int cls_cgroup_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct cls_cgroup_head *head = rtnl_dereference(tp->root); struct nlattr *nest; diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 2bb043cd436b..204e2edae8d5 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -391,7 +391,8 @@ static void flow_destroy_filter_work(struct work_struct *work) static int flow_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *fold, *fnew; @@ -445,7 +446,7 @@ static int flow_change(struct net *net, struct sk_buff *in_skb, goto err2; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &fnew->exts, ovr, - extack); + true, extack); if (err < 0) goto err2; @@ -566,7 +567,7 @@ err1: } static int flow_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f = arg; @@ -590,7 +591,8 @@ static int flow_init(struct tcf_proto *tp) return 0; } -static void flow_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void flow_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f, *next; @@ -617,7 +619,7 @@ static void *flow_get(struct tcf_proto *tp, u32 handle) } static int flow_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct flow_filter *f = fh; struct nlattr *nest; @@ -677,7 +679,8 @@ nla_put_failure: return -1; } -static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void flow_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct flow_head *head = rtnl_dereference(tp->root); struct flow_filter *f; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index 12ca9d13db83..640f83e7f93f 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -381,16 +381,31 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, bool skip_sw = tc_skip_sw(f->flags); int err; + cls_flower.rule = flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) + return -ENOMEM; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; - cls_flower.dissector = &f->mask->dissector; - cls_flower.mask = &f->mask->key; - cls_flower.key = &f->mkey; - cls_flower.exts = &f->exts; + cls_flower.rule->match.dissector = &f->mask->dissector; + cls_flower.rule->match.mask = &f->mask->key; + cls_flower.rule->match.key = &f->mkey; cls_flower.classid = f->res.classid; + err = tc_setup_flow_action(&cls_flower.rule->action, &f->exts); + if (err) { + kfree(cls_flower.rule); + if (skip_sw) { + NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); + return err; + } + return 0; + } + err = tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, skip_sw); + kfree(cls_flower.rule); + if (err < 0) { fl_hw_destroy_filter(tp, f, NULL); return err; @@ -413,10 +428,13 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, NULL); cls_flower.command = TC_CLSFLOWER_STATS; cls_flower.cookie = (unsigned long) f; - cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + + tcf_exts_stats_update(&f->exts, cls_flower.stats.bytes, + cls_flower.stats.pkts, + cls_flower.stats.lastused); } static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, @@ -451,7 +469,8 @@ static void fl_destroy_sleepable(struct work_struct *work) module_put(THIS_MODULE); } -static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void fl_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct fl_flow_mask *mask, *next_mask; @@ -1258,7 +1277,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, + extack); if (err < 0) return err; @@ -1285,7 +1305,8 @@ static int fl_set_parms(struct net *net, struct tcf_proto *tp, static int fl_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *fold = *arg; @@ -1422,7 +1443,7 @@ errout_mask_alloc: } static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = arg; @@ -1434,7 +1455,8 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, return 0; } -static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; @@ -1467,18 +1489,36 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, if (tc_skip_hw(f->flags)) continue; + cls_flower.rule = + flow_rule_alloc(tcf_exts_num_actions(&f->exts)); + if (!cls_flower.rule) + return -ENOMEM; + tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = add ? TC_CLSFLOWER_REPLACE : TC_CLSFLOWER_DESTROY; cls_flower.cookie = (unsigned long)f; - cls_flower.dissector = &mask->dissector; - cls_flower.mask = &mask->key; - cls_flower.key = &f->mkey; - cls_flower.exts = &f->exts; + cls_flower.rule->match.dissector = &mask->dissector; + cls_flower.rule->match.mask = &mask->key; + cls_flower.rule->match.key = &f->mkey; + + err = tc_setup_flow_action(&cls_flower.rule->action, + &f->exts); + if (err) { + kfree(cls_flower.rule); + if (tc_skip_sw(f->flags)) { + NL_SET_ERR_MSG_MOD(extack, "Failed to setup flow action"); + return err; + } + continue; + } + cls_flower.classid = f->res.classid; err = cb(TC_SETUP_CLSFLOWER, &cls_flower, cb_priv); + kfree(cls_flower.rule); + if (err) { if (add && tc_skip_sw(f->flags)) return err; @@ -1493,25 +1533,30 @@ static int fl_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, return 0; } -static void fl_hw_create_tmplt(struct tcf_chain *chain, - struct fl_flow_tmplt *tmplt) +static int fl_hw_create_tmplt(struct tcf_chain *chain, + struct fl_flow_tmplt *tmplt) { struct tc_cls_flower_offload cls_flower = {}; struct tcf_block *block = chain->block; - struct tcf_exts dummy_exts = { 0, }; + + cls_flower.rule = flow_rule_alloc(0); + if (!cls_flower.rule) + return -ENOMEM; cls_flower.common.chain_index = chain->index; cls_flower.command = TC_CLSFLOWER_TMPLT_CREATE; cls_flower.cookie = (unsigned long) tmplt; - cls_flower.dissector = &tmplt->dissector; - cls_flower.mask = &tmplt->mask; - cls_flower.key = &tmplt->dummy_key; - cls_flower.exts = &dummy_exts; + cls_flower.rule->match.dissector = &tmplt->dissector; + cls_flower.rule->match.mask = &tmplt->mask; + cls_flower.rule->match.key = &tmplt->dummy_key; /* We don't care if driver (any of them) fails to handle this * call. It serves just as a hint for it. */ tc_setup_cb_call(block, TC_SETUP_CLSFLOWER, &cls_flower, false); + kfree(cls_flower.rule); + + return 0; } static void fl_hw_destroy_tmplt(struct tcf_chain *chain, @@ -1555,12 +1600,14 @@ static void *fl_tmplt_create(struct net *net, struct tcf_chain *chain, err = fl_set_key(net, tb, &tmplt->dummy_key, &tmplt->mask, extack); if (err) goto errout_tmplt; - kfree(tb); fl_init_dissector(&tmplt->dissector, &tmplt->mask); - fl_hw_create_tmplt(chain, tmplt); + err = fl_hw_create_tmplt(chain, tmplt); + if (err) + goto errout_tmplt; + kfree(tb); return tmplt; errout_tmplt: @@ -2008,7 +2055,7 @@ nla_put_failure: } static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct cls_fl_filter *f = fh; struct nlattr *nest; diff --git a/net/sched/cls_fw.c b/net/sched/cls_fw.c index 29eeeaf3ea44..317151bae73b 100644 --- a/net/sched/cls_fw.c +++ b/net/sched/cls_fw.c @@ -139,7 +139,8 @@ static void fw_delete_filter_work(struct work_struct *work) rtnl_unlock(); } -static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void fw_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f; @@ -163,7 +164,7 @@ static void fw_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int fw_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = arg; @@ -217,7 +218,7 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, int err; err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &f->exts, ovr, - extack); + true, extack); if (err < 0) return err; @@ -250,7 +251,8 @@ static int fw_set_parms(struct net *net, struct tcf_proto *tp, static int fw_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, - bool ovr, struct netlink_ext_ack *extack) + bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = *arg; @@ -354,7 +356,8 @@ errout: return err; } -static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct fw_head *head = rtnl_dereference(tp->root); int h; @@ -384,7 +387,7 @@ static void fw_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int fw_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct fw_head *head = rtnl_dereference(tp->root); struct fw_filter *f = fh; diff --git a/net/sched/cls_matchall.c b/net/sched/cls_matchall.c index 0e408ee9dcec..a37137430e61 100644 --- a/net/sched/cls_matchall.c +++ b/net/sched/cls_matchall.c @@ -12,6 +12,7 @@ #include <linux/kernel.h> #include <linux/init.h> #include <linux/module.h> +#include <linux/percpu.h> #include <net/sch_generic.h> #include <net/pkt_cls.h> @@ -22,6 +23,7 @@ struct cls_mall_head { u32 handle; u32 flags; unsigned int in_hw_count; + struct tc_matchall_pcnt __percpu *pf; struct rcu_work rwork; }; @@ -34,6 +36,7 @@ static int mall_classify(struct sk_buff *skb, const struct tcf_proto *tp, return -1; *res = head->res; + __this_cpu_inc(head->pf->rhit); return tcf_exts_exec(skb, &head->exts, res); } @@ -46,6 +49,7 @@ static void __mall_destroy(struct cls_mall_head *head) { tcf_exts_destroy(&head->exts); tcf_exts_put_net(&head->exts); + free_percpu(head->pf); kfree(head); } @@ -105,7 +109,8 @@ static int mall_replace_hw_filter(struct tcf_proto *tp, return 0; } -static void mall_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void mall_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); @@ -141,7 +146,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &head->exts, ovr, true, + extack); if (err < 0) return err; @@ -155,7 +161,8 @@ static int mall_set_parms(struct net *net, struct tcf_proto *tp, static int mall_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct cls_mall_head *head = rtnl_dereference(tp->root); struct nlattr *tb[TCA_MATCHALL_MAX + 1]; @@ -192,6 +199,11 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, handle = 1; new->handle = handle; new->flags = flags; + new->pf = alloc_percpu(struct tc_matchall_pcnt); + if (!new->pf) { + err = -ENOMEM; + goto err_alloc_percpu; + } err = mall_set_parms(net, tp, new, base, tb, tca[TCA_RATE], ovr, extack); @@ -214,6 +226,8 @@ static int mall_change(struct net *net, struct sk_buff *in_skb, err_replace_hw_filter: err_set_parms: + free_percpu(new->pf); +err_alloc_percpu: tcf_exts_destroy(&new->exts); err_exts_init: kfree(new); @@ -221,12 +235,13 @@ err_exts_init: } static int mall_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { return -EOPNOTSUPP; } -static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void mall_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct cls_mall_head *head = rtnl_dereference(tp->root); @@ -268,10 +283,12 @@ static int mall_reoffload(struct tcf_proto *tp, bool add, tc_setup_cb_t *cb, } static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { + struct tc_matchall_pcnt gpf = {}; struct cls_mall_head *head = fh; struct nlattr *nest; + int cpu; if (!head) return skb->len; @@ -289,6 +306,17 @@ static int mall_dump(struct net *net, struct tcf_proto *tp, void *fh, if (head->flags && nla_put_u32(skb, TCA_MATCHALL_FLAGS, head->flags)) goto nla_put_failure; + for_each_possible_cpu(cpu) { + struct tc_matchall_pcnt *pf = per_cpu_ptr(head->pf, cpu); + + gpf.rhit += pf->rhit; + } + + if (nla_put_64bit(skb, TCA_MATCHALL_PCNT, + sizeof(struct tc_matchall_pcnt), + &gpf, TCA_MATCHALL_PAD)) + goto nla_put_failure; + if (tcf_exts_dump(skb, &head->exts)) goto nla_put_failure; diff --git a/net/sched/cls_route.c b/net/sched/cls_route.c index 0404aa5fa7cb..e590c3a2999d 100644 --- a/net/sched/cls_route.c +++ b/net/sched/cls_route.c @@ -276,7 +276,8 @@ static void route4_queue_work(struct route4_filter *f) tcf_queue_work(&f->rwork, route4_delete_filter_work); } -static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void route4_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); int h1, h2; @@ -312,7 +313,7 @@ static void route4_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int route4_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter *f = arg; @@ -393,7 +394,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, struct route4_bucket *b; int err; - err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &f->exts, ovr, true, extack); if (err < 0) return err; @@ -468,7 +469,7 @@ static int route4_set_parms(struct net *net, struct tcf_proto *tp, static int route4_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct route4_head *head = rtnl_dereference(tp->root); struct route4_filter __rcu **fp; @@ -560,7 +561,8 @@ errout: return err; } -static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct route4_head *head = rtnl_dereference(tp->root); unsigned int h, h1; @@ -597,7 +599,7 @@ static void route4_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int route4_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct route4_filter *f = fh; struct nlattr *nest; diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index e9ccf7daea7d..4d3836178fa5 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -312,7 +312,8 @@ static void rsvp_delete_filter(struct tcf_proto *tp, struct rsvp_filter *f) __rsvp_delete_filter(f); } -static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void rsvp_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); int h1, h2; @@ -341,7 +342,7 @@ static void rsvp_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int rsvp_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct rsvp_head *head = rtnl_dereference(tp->root); struct rsvp_filter *nfp, *f = arg; @@ -477,7 +478,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, - void **arg, bool ovr, struct netlink_ext_ack *extack) + void **arg, bool ovr, bool rtnl_held, + struct netlink_ext_ack *extack) { struct rsvp_head *data = rtnl_dereference(tp->root); struct rsvp_filter *f, *nfp; @@ -502,7 +504,8 @@ static int rsvp_change(struct net *net, struct sk_buff *in_skb, err = tcf_exts_init(&e, TCA_RSVP_ACT, TCA_RSVP_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, extack); + err = tcf_exts_validate(net, tp, tb, tca[TCA_RATE], &e, ovr, true, + extack); if (err < 0) goto errout2; @@ -654,7 +657,8 @@ errout2: return err; } -static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct rsvp_head *head = rtnl_dereference(tp->root); unsigned int h, h1; @@ -688,7 +692,7 @@ static void rsvp_walk(struct tcf_proto *tp, struct tcf_walker *arg) } static int rsvp_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct rsvp_filter *f = fh; struct rsvp_session *s; diff --git a/net/sched/cls_tcindex.c b/net/sched/cls_tcindex.c index 38bb882bb958..e1981628047b 100644 --- a/net/sched/cls_tcindex.c +++ b/net/sched/cls_tcindex.c @@ -48,7 +48,7 @@ struct tcindex_data { u32 hash; /* hash table size; 0 if undefined */ u32 alloc_hash; /* allocated size */ u32 fall_through; /* 0: only classify if explicit match */ - struct rcu_work rwork; + struct rcu_head rcu; }; static inline int tcindex_filter_is_set(struct tcindex_filter_result *r) @@ -173,7 +173,7 @@ static void tcindex_destroy_fexts_work(struct work_struct *work) } static int tcindex_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = arg; @@ -221,11 +221,17 @@ found: return 0; } -static void tcindex_destroy_work(struct work_struct *work) +static int tcindex_destroy_element(struct tcf_proto *tp, + void *arg, struct tcf_walker *walker) +{ + bool last; + + return tcindex_delete(tp, arg, &last, false, NULL); +} + +static void __tcindex_destroy(struct rcu_head *head) { - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); + struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); kfree(p->perfect); kfree(p->h); @@ -252,11 +258,9 @@ static int tcindex_filter_result_init(struct tcindex_filter_result *r) return tcf_exts_init(&r->exts, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); } -static void tcindex_partial_destroy_work(struct work_struct *work) +static void __tcindex_partial_destroy(struct rcu_head *head) { - struct tcindex_data *p = container_of(to_rcu_work(work), - struct tcindex_data, - rwork); + struct tcindex_data *p = container_of(head, struct tcindex_data, rcu); kfree(p->perfect); kfree(p); @@ -313,7 +317,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, err = tcf_exts_init(&e, TCA_TCINDEX_ACT, TCA_TCINDEX_POLICE); if (err < 0) return err; - err = tcf_exts_validate(net, tp, tb, est, &e, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &e, ovr, true, extack); if (err < 0) goto errout; @@ -476,7 +480,7 @@ tcindex_set_parms(struct net *net, struct tcf_proto *tp, unsigned long base, } if (oldp) - tcf_queue_work(&oldp->rwork, tcindex_partial_destroy_work); + call_rcu(&oldp->rcu, __tcindex_partial_destroy); return 0; errout_alloc: @@ -496,7 +500,7 @@ static int tcindex_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, struct nlattr **tca, void **arg, bool ovr, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct nlattr *opt = tca[TCA_OPTIONS]; struct nlattr *tb[TCA_TCINDEX_MAX + 1]; @@ -519,7 +523,8 @@ tcindex_change(struct net *net, struct sk_buff *in_skb, tca[TCA_RATE], ovr, extack); } -static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) +static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker, + bool rtnl_held) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter *f, *next; @@ -555,43 +560,24 @@ static void tcindex_walk(struct tcf_proto *tp, struct tcf_walker *walker) } } -static void tcindex_destroy(struct tcf_proto *tp, +static void tcindex_destroy(struct tcf_proto *tp, bool rtnl_held, struct netlink_ext_ack *extack) { struct tcindex_data *p = rtnl_dereference(tp->root); - int i; + struct tcf_walker walker; pr_debug("tcindex_destroy(tp %p),p %p\n", tp, p); + walker.count = 0; + walker.skip = 0; + walker.fn = tcindex_destroy_element; + tcindex_walk(tp, &walker, true); - if (p->perfect) { - for (i = 0; i < p->hash; i++) { - struct tcindex_filter_result *r = p->perfect + i; - - tcf_unbind_filter(tp, &r->res); - if (tcf_exts_get_net(&r->exts)) - tcf_queue_work(&r->rwork, - tcindex_destroy_rexts_work); - else - __tcindex_destroy_rexts(r); - } - } - - for (i = 0; p->h && i < p->hash; i++) { - struct tcindex_filter *f, *next; - bool last; - - for (f = rtnl_dereference(p->h[i]); f; f = next) { - next = rtnl_dereference(f->next); - tcindex_delete(tp, &f->result, &last, NULL); - } - } - - tcf_queue_work(&p->rwork, tcindex_destroy_work); + call_rcu(&p->rcu, __tcindex_destroy); } static int tcindex_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tcindex_data *p = rtnl_dereference(tp->root); struct tcindex_filter_result *r = fh; diff --git a/net/sched/cls_u32.c b/net/sched/cls_u32.c index dcea21004604..27d29c04dcc9 100644 --- a/net/sched/cls_u32.c +++ b/net/sched/cls_u32.c @@ -629,7 +629,8 @@ static int u32_destroy_hnode(struct tcf_proto *tp, struct tc_u_hnode *ht, return -ENOENT; } -static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) +static void u32_destroy(struct tcf_proto *tp, bool rtnl_held, + struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *root_ht = rtnl_dereference(tp->root); @@ -663,7 +664,7 @@ static void u32_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) } static int u32_delete(struct tcf_proto *tp, void *arg, bool *last, - struct netlink_ext_ack *extack) + bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_u_hnode *ht = arg; struct tc_u_common *tp_c = tp->data; @@ -726,7 +727,7 @@ static int u32_set_parms(struct net *net, struct tcf_proto *tp, { int err; - err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, extack); + err = tcf_exts_validate(net, tp, tb, est, &n->exts, ovr, true, extack); if (err < 0) return err; @@ -858,7 +859,7 @@ static struct tc_u_knode *u32_init_knode(struct tcf_proto *tp, static int u32_change(struct net *net, struct sk_buff *in_skb, struct tcf_proto *tp, unsigned long base, u32 handle, - struct nlattr **tca, void **arg, bool ovr, + struct nlattr **tca, void **arg, bool ovr, bool rtnl_held, struct netlink_ext_ack *extack) { struct tc_u_common *tp_c = tp->data; @@ -1123,7 +1124,8 @@ erridr: return err; } -static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg) +static void u32_walk(struct tcf_proto *tp, struct tcf_walker *arg, + bool rtnl_held) { struct tc_u_common *tp_c = tp->data; struct tc_u_hnode *ht; @@ -1281,7 +1283,7 @@ static void u32_bind_class(void *fh, u32 classid, unsigned long cl) } static int u32_dump(struct net *net, struct tcf_proto *tp, void *fh, - struct sk_buff *skb, struct tcmsg *t) + struct sk_buff *skb, struct tcmsg *t, bool rtnl_held) { struct tc_u_knode *n = fh; struct tc_u_hnode *ht_up, *ht_down; diff --git a/net/sched/sch_api.c b/net/sched/sch_api.c index 7e4d1ccf4c87..2283924fb56d 100644 --- a/net/sched/sch_api.c +++ b/net/sched/sch_api.c @@ -758,8 +758,7 @@ static u32 qdisc_alloc_handle(struct net_device *dev) return 0; } -void qdisc_tree_reduce_backlog(struct Qdisc *sch, unsigned int n, - unsigned int len) +void qdisc_tree_reduce_backlog(struct Qdisc *sch, int n, int len) { bool qdisc_is_offloaded = sch->flags & TCQ_F_OFFLOADED; const struct Qdisc_class_ops *cops; @@ -1910,17 +1909,19 @@ static void tc_bind_tclass(struct Qdisc *q, u32 portid, u32 clid, block = cops->tcf_block(q, cl, NULL); if (!block) return; - list_for_each_entry(chain, &block->chain_list, list) { + for (chain = tcf_get_next_chain(block, NULL); + chain; + chain = tcf_get_next_chain(block, chain)) { struct tcf_proto *tp; - for (tp = rtnl_dereference(chain->filter_chain); - tp; tp = rtnl_dereference(tp->next)) { + for (tp = tcf_get_next_proto(chain, NULL, true); + tp; tp = tcf_get_next_proto(chain, tp, true)) { struct tcf_bind_args arg = {}; arg.w.fn = tcf_node_bind; arg.classid = clid; arg.cl = new_cl; - tp->ops->walk(tp, &arg.w); + tp->ops->walk(tp, &arg.w, true); } } } diff --git a/net/sched/sch_generic.c b/net/sched/sch_generic.c index 968a85fe4d4a..38e5add14fab 100644 --- a/net/sched/sch_generic.c +++ b/net/sched/sch_generic.c @@ -1366,7 +1366,11 @@ static void mini_qdisc_rcu_func(struct rcu_head *head) void mini_qdisc_pair_swap(struct mini_Qdisc_pair *miniqp, struct tcf_proto *tp_head) { - struct mini_Qdisc *miniq_old = rtnl_dereference(*miniqp->p_miniq); + /* Protected with chain0->filter_chain_lock. + * Can't access chain directly because tp_head can be NULL. + */ + struct mini_Qdisc *miniq_old = + rcu_dereference_protected(*miniqp->p_miniq, 1); struct mini_Qdisc *miniq; if (!tp_head) { diff --git a/net/sctp/associola.c b/net/sctp/associola.c index 201c888604e4..d2c7d0d2abc1 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -101,7 +101,7 @@ static struct sctp_association *sctp_association_init( * socket values. */ asoc->max_retrans = sp->assocparams.sasoc_asocmaxrxt; - asoc->pf_retrans = net->sctp.pf_retrans; + asoc->pf_retrans = sp->pf_retrans; asoc->rto_initial = msecs_to_jiffies(sp->rtoinfo.srto_initial); asoc->rto_max = msecs_to_jiffies(sp->rtoinfo.srto_max); @@ -1651,8 +1651,11 @@ int sctp_assoc_set_id(struct sctp_association *asoc, gfp_t gfp) if (preload) idr_preload(gfp); spin_lock_bh(&sctp_assocs_id_lock); - /* 0 is not a valid assoc_id, must be >= 1 */ - ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, 1, 0, GFP_NOWAIT); + /* 0, 1, 2 are used as SCTP_FUTURE_ASSOC, SCTP_CURRENT_ASSOC and + * SCTP_ALL_ASSOC, so an available id must be > SCTP_ALL_ASSOC. + */ + ret = idr_alloc_cyclic(&sctp_assocs_id, asoc, SCTP_ALL_ASSOC + 1, 0, + GFP_NOWAIT); spin_unlock_bh(&sctp_assocs_id_lock); if (preload) idr_preload_end(); diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index c37e1c2dec9d..fd33281999b5 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -212,7 +212,7 @@ void sctp_outq_init(struct sctp_association *asoc, struct sctp_outq *q) INIT_LIST_HEAD(&q->retransmit); INIT_LIST_HEAD(&q->sacked); INIT_LIST_HEAD(&q->abandoned); - sctp_sched_set_sched(asoc, SCTP_SS_DEFAULT); + sctp_sched_set_sched(asoc, sctp_sk(asoc->base.sk)->default_ss); } /* Free the outqueue structure and any related pending chunks. diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 65d6d04546ae..a78e55a1bb9c 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -248,7 +248,7 @@ struct sctp_association *sctp_id2assoc(struct sock *sk, sctp_assoc_t id) } /* Otherwise this is a UDP-style socket. */ - if (!id || (id == (sctp_assoc_t)-1)) + if (id <= SCTP_ALL_ASSOC) return NULL; spin_lock_bh(&sctp_assocs_id_lock); @@ -2750,12 +2750,13 @@ static int sctp_setsockopt_peer_addr_params(struct sock *sk, return -EINVAL; } - /* Get association, if assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spp_assoc_id); - if (!asoc && params.spp_assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.spp_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Heartbeat demand can only be sent on a transport or @@ -2797,6 +2798,43 @@ static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) return (param_flags & ~SPP_SACKDELAY) | SPP_SACKDELAY_DISABLE; } +static void sctp_apply_asoc_delayed_ack(struct sctp_sack_info *params, + struct sctp_association *asoc) +{ + struct sctp_transport *trans; + + if (params->sack_delay) { + asoc->sackdelay = msecs_to_jiffies(params->sack_delay); + asoc->param_flags = + sctp_spp_sackdelay_enable(asoc->param_flags); + } + if (params->sack_freq == 1) { + asoc->param_flags = + sctp_spp_sackdelay_disable(asoc->param_flags); + } else if (params->sack_freq > 1) { + asoc->sackfreq = params->sack_freq; + asoc->param_flags = + sctp_spp_sackdelay_enable(asoc->param_flags); + } + + list_for_each_entry(trans, &asoc->peer.transport_addr_list, + transports) { + if (params->sack_delay) { + trans->sackdelay = msecs_to_jiffies(params->sack_delay); + trans->param_flags = + sctp_spp_sackdelay_enable(trans->param_flags); + } + if (params->sack_freq == 1) { + trans->param_flags = + sctp_spp_sackdelay_disable(trans->param_flags); + } else if (params->sack_freq > 1) { + trans->sackfreq = params->sack_freq; + trans->param_flags = + sctp_spp_sackdelay_enable(trans->param_flags); + } + } +} + /* * 7.1.23. Get or set delayed ack timer (SCTP_DELAYED_SACK) * @@ -2836,10 +2874,9 @@ static inline __u32 sctp_spp_sackdelay_disable(__u32 param_flags) static int sctp_setsockopt_delayed_ack(struct sock *sk, char __user *optval, unsigned int optlen) { - struct sctp_sack_info params; - struct sctp_transport *trans = NULL; - struct sctp_association *asoc = NULL; - struct sctp_sock *sp = sctp_sk(sk); + struct sctp_sock *sp = sctp_sk(sk); + struct sctp_association *asoc; + struct sctp_sack_info params; if (optlen == sizeof(struct sctp_sack_info)) { if (copy_from_user(¶ms, optval, optlen)) @@ -2867,67 +2904,42 @@ static int sctp_setsockopt_delayed_ack(struct sock *sk, if (params.sack_delay > 500) return -EINVAL; - /* Get association, if sack_assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.sack_assoc_id); - if (!asoc && params.sack_assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.sack_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - if (params.sack_delay) { - if (asoc) { - asoc->sackdelay = - msecs_to_jiffies(params.sack_delay); - asoc->param_flags = - sctp_spp_sackdelay_enable(asoc->param_flags); - } else { + if (asoc) { + sctp_apply_asoc_delayed_ack(¶ms, asoc); + + return 0; + } + + if (params.sack_assoc_id == SCTP_FUTURE_ASSOC || + params.sack_assoc_id == SCTP_ALL_ASSOC) { + if (params.sack_delay) { sp->sackdelay = params.sack_delay; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } - } - - if (params.sack_freq == 1) { - if (asoc) { - asoc->param_flags = - sctp_spp_sackdelay_disable(asoc->param_flags); - } else { + if (params.sack_freq == 1) { sp->param_flags = sctp_spp_sackdelay_disable(sp->param_flags); - } - } else if (params.sack_freq > 1) { - if (asoc) { - asoc->sackfreq = params.sack_freq; - asoc->param_flags = - sctp_spp_sackdelay_enable(asoc->param_flags); - } else { + } else if (params.sack_freq > 1) { sp->sackfreq = params.sack_freq; sp->param_flags = sctp_spp_sackdelay_enable(sp->param_flags); } } - /* If change is for association, also apply to each transport. */ - if (asoc) { - list_for_each_entry(trans, &asoc->peer.transport_addr_list, - transports) { - if (params.sack_delay) { - trans->sackdelay = - msecs_to_jiffies(params.sack_delay); - trans->param_flags = - sctp_spp_sackdelay_enable(trans->param_flags); - } - if (params.sack_freq == 1) { - trans->param_flags = - sctp_spp_sackdelay_disable(trans->param_flags); - } else if (params.sack_freq > 1) { - trans->sackfreq = params.sack_freq; - trans->param_flags = - sctp_spp_sackdelay_enable(trans->param_flags); - } - } - } + if (params.sack_assoc_id == SCTP_CURRENT_ASSOC || + params.sack_assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &sp->ep->asocs, asocs) + sctp_apply_asoc_delayed_ack(¶ms, asoc); return 0; } @@ -2997,15 +3009,22 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, return -EINVAL; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); - if (!asoc && info.sinfo_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.sinfo_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { asoc->default_stream = info.sinfo_stream; asoc->default_flags = info.sinfo_flags; asoc->default_ppid = info.sinfo_ppid; asoc->default_context = info.sinfo_context; asoc->default_timetolive = info.sinfo_timetolive; - } else { + + return 0; + } + + if (info.sinfo_assoc_id == SCTP_FUTURE_ASSOC || + info.sinfo_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info.sinfo_stream; sp->default_flags = info.sinfo_flags; sp->default_ppid = info.sinfo_ppid; @@ -3013,6 +3032,17 @@ static int sctp_setsockopt_default_send_param(struct sock *sk, sp->default_timetolive = info.sinfo_timetolive; } + if (info.sinfo_assoc_id == SCTP_CURRENT_ASSOC || + info.sinfo_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + asoc->default_stream = info.sinfo_stream; + asoc->default_flags = info.sinfo_flags; + asoc->default_ppid = info.sinfo_ppid; + asoc->default_context = info.sinfo_context; + asoc->default_timetolive = info.sinfo_timetolive; + } + } + return 0; } @@ -3037,20 +3067,37 @@ static int sctp_setsockopt_default_sndinfo(struct sock *sk, return -EINVAL; asoc = sctp_id2assoc(sk, info.snd_assoc_id); - if (!asoc && info.snd_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.snd_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { asoc->default_stream = info.snd_sid; asoc->default_flags = info.snd_flags; asoc->default_ppid = info.snd_ppid; asoc->default_context = info.snd_context; - } else { + + return 0; + } + + if (info.snd_assoc_id == SCTP_FUTURE_ASSOC || + info.snd_assoc_id == SCTP_ALL_ASSOC) { sp->default_stream = info.snd_sid; sp->default_flags = info.snd_flags; sp->default_ppid = info.snd_ppid; sp->default_context = info.snd_context; } + if (info.snd_assoc_id == SCTP_CURRENT_ASSOC || + info.snd_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + asoc->default_stream = info.snd_sid; + asoc->default_flags = info.snd_flags; + asoc->default_ppid = info.snd_ppid; + asoc->default_context = info.snd_context; + } + } + return 0; } @@ -3144,7 +3191,8 @@ static int sctp_setsockopt_rtoinfo(struct sock *sk, char __user *optval, unsigne asoc = sctp_id2assoc(sk, rtoinfo.srto_assoc_id); /* Set the values to the specific association */ - if (!asoc && rtoinfo.srto_assoc_id && sctp_style(sk, UDP)) + if (!asoc && rtoinfo.srto_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; rto_max = rtoinfo.srto_max; @@ -3206,7 +3254,8 @@ static int sctp_setsockopt_associnfo(struct sock *sk, char __user *optval, unsig asoc = sctp_id2assoc(sk, assocparams.sasoc_assoc_id); - if (!asoc && assocparams.sasoc_assoc_id && sctp_style(sk, UDP)) + if (!asoc && assocparams.sasoc_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Set the values to the specific association */ @@ -3319,7 +3368,7 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned current->comm, task_pid_nr(current)); if (copy_from_user(&val, optval, optlen)) return -EFAULT; - params.assoc_id = 0; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (optlen == sizeof(struct sctp_assoc_value)) { if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; @@ -3329,6 +3378,9 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned } asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; if (val) { int min_len, max_len; @@ -3346,8 +3398,6 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned asoc->user_frag = val; sctp_assoc_update_frag_point(asoc); } else { - if (params.assoc_id && sctp_style(sk, UDP)) - return -EINVAL; sp->user_frag = val; } @@ -3460,8 +3510,8 @@ static int sctp_setsockopt_adaptation_layer(struct sock *sk, char __user *optval static int sctp_setsockopt_context(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; if (optlen != sizeof(struct sctp_assoc_value)) @@ -3469,17 +3519,26 @@ static int sctp_setsockopt_context(struct sock *sk, char __user *optval, if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (params.assoc_id != 0) { - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - return -EINVAL; + if (asoc) { asoc->default_rcv_context = params.assoc_value; - } else { - sp->default_rcv_context = params.assoc_value; + + return 0; } + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->default_rcv_context = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &sp->ep->asocs, asocs) + asoc->default_rcv_context = params.assoc_value; + return 0; } @@ -3580,11 +3639,9 @@ static int sctp_setsockopt_maxburst(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; - int val; - int assoc_id = 0; if (optlen == sizeof(int)) { pr_warn_ratelimited(DEPRECATED @@ -3592,25 +3649,34 @@ static int sctp_setsockopt_maxburst(struct sock *sk, "Use of int in max_burst socket option deprecated.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); - if (copy_from_user(&val, optval, optlen)) + if (copy_from_user(¶ms.assoc_value, optval, optlen)) return -EFAULT; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (optlen == sizeof(struct sctp_assoc_value)) { if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; - val = params.assoc_value; - assoc_id = params.assoc_id; } else return -EINVAL; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (assoc_id != 0) { - asoc = sctp_id2assoc(sk, assoc_id); - if (!asoc) - return -EINVAL; - asoc->max_burst = val; - } else - sp->max_burst = val; + if (asoc) { + asoc->max_burst = params.assoc_value; + + return 0; + } + + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->max_burst = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &sp->ep->asocs, asocs) + asoc->max_burst = params.assoc_value; return 0; } @@ -3702,7 +3768,7 @@ static int sctp_setsockopt_auth_key(struct sock *sk, struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_authkey *authkey; struct sctp_association *asoc; - int ret; + int ret = -EINVAL; if (!ep->auth_enable) return -EACCES; @@ -3712,25 +3778,44 @@ static int sctp_setsockopt_auth_key(struct sock *sk, /* authkey->sca_keylength is u16, so optlen can't be bigger than * this. */ - optlen = min_t(unsigned int, optlen, USHRT_MAX + - sizeof(struct sctp_authkey)); + optlen = min_t(unsigned int, optlen, USHRT_MAX + sizeof(*authkey)); authkey = memdup_user(optval, optlen); if (IS_ERR(authkey)) return PTR_ERR(authkey); - if (authkey->sca_keylength > optlen - sizeof(struct sctp_authkey)) { - ret = -EINVAL; + if (authkey->sca_keylength > optlen - sizeof(*authkey)) goto out; - } asoc = sctp_id2assoc(sk, authkey->sca_assoc_id); - if (!asoc && authkey->sca_assoc_id && sctp_style(sk, UDP)) { - ret = -EINVAL; + if (!asoc && authkey->sca_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + goto out; + + if (asoc) { + ret = sctp_auth_set_key(ep, asoc, authkey); goto out; } - ret = sctp_auth_set_key(ep, asoc, authkey); + if (authkey->sca_assoc_id == SCTP_FUTURE_ASSOC || + authkey->sca_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_set_key(ep, asoc, authkey); + if (ret) + goto out; + } + + ret = 0; + + if (authkey->sca_assoc_id == SCTP_CURRENT_ASSOC || + authkey->sca_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_set_key(ep, asoc, authkey); + + if (res && !ret) + ret = res; + } + } + out: kzfree(authkey); return ret; @@ -3747,8 +3832,9 @@ static int sctp_setsockopt_active_key(struct sock *sk, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct sctp_authkeyid val; struct sctp_association *asoc; + struct sctp_authkeyid val; + int ret = 0; if (!ep->auth_enable) return -EACCES; @@ -3759,10 +3845,32 @@ static int sctp_setsockopt_active_key(struct sock *sk, return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); - if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.scact_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + if (asoc) + return sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_set_active_key(ep, asoc, val.scact_keynumber); + if (ret) + return ret; + } + + if (val.scact_assoc_id == SCTP_CURRENT_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_set_active_key(ep, asoc, + val.scact_keynumber); + + if (res && !ret) + ret = res; + } + } + + return ret; } /* @@ -3775,8 +3883,9 @@ static int sctp_setsockopt_del_key(struct sock *sk, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct sctp_authkeyid val; struct sctp_association *asoc; + struct sctp_authkeyid val; + int ret = 0; if (!ep->auth_enable) return -EACCES; @@ -3787,11 +3896,32 @@ static int sctp_setsockopt_del_key(struct sock *sk, return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); - if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.scact_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + if (asoc) + return sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_del_key_id(ep, asoc, val.scact_keynumber); + if (ret) + return ret; + } + + if (val.scact_assoc_id == SCTP_CURRENT_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_del_key_id(ep, asoc, + val.scact_keynumber); + + if (res && !ret) + ret = res; + } + } + return ret; } /* @@ -3803,8 +3933,9 @@ static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_endpoint *ep = sctp_sk(sk)->ep; - struct sctp_authkeyid val; struct sctp_association *asoc; + struct sctp_authkeyid val; + int ret = 0; if (!ep->auth_enable) return -EACCES; @@ -3815,10 +3946,32 @@ static int sctp_setsockopt_deactivate_key(struct sock *sk, char __user *optval, return -EFAULT; asoc = sctp_id2assoc(sk, val.scact_assoc_id); - if (!asoc && val.scact_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.scact_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + if (asoc) + return sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + + if (val.scact_assoc_id == SCTP_FUTURE_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + ret = sctp_auth_deact_key_id(ep, asoc, val.scact_keynumber); + if (ret) + return ret; + } + + if (val.scact_assoc_id == SCTP_CURRENT_ASSOC || + val.scact_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &ep->asocs, asocs) { + int res = sctp_auth_deact_key_id(ep, asoc, + val.scact_keynumber); + + if (res && !ret) + ret = res; + } + } + + return ret; } /* @@ -3884,11 +4037,25 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, sizeof(struct sctp_paddrthlds))) return -EFAULT; - - if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { - asoc = sctp_id2assoc(sk, val.spt_assoc_id); - if (!asoc) + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { + trans = sctp_addr_id2transport(sk, &val.spt_address, + val.spt_assoc_id); + if (!trans) return -ENOENT; + + if (val.spt_pathmaxrxt) + trans->pathmaxrxt = val.spt_pathmaxrxt; + trans->pf_retrans = val.spt_pathpfthld; + + return 0; + } + + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { if (val.spt_pathmaxrxt) @@ -3900,14 +4067,11 @@ static int sctp_setsockopt_paddr_thresholds(struct sock *sk, asoc->pathmaxrxt = val.spt_pathmaxrxt; asoc->pf_retrans = val.spt_pathpfthld; } else { - trans = sctp_addr_id2transport(sk, &val.spt_address, - val.spt_assoc_id); - if (!trans) - return -ENOENT; + struct sctp_sock *sp = sctp_sk(sk); if (val.spt_pathmaxrxt) - trans->pathmaxrxt = val.spt_pathmaxrxt; - trans->pf_retrans = val.spt_pathpfthld; + sp->pathmaxrxt = val.spt_pathmaxrxt; + sp->pf_retrans = val.spt_pathpfthld; } return 0; @@ -3950,6 +4114,7 @@ static int sctp_setsockopt_pr_supported(struct sock *sk, unsigned int optlen) { struct sctp_assoc_value params; + struct sctp_association *asoc; if (optlen != sizeof(params)) return -EINVAL; @@ -3957,6 +4122,11 @@ static int sctp_setsockopt_pr_supported(struct sock *sk, if (copy_from_user(¶ms, optval, optlen)) return -EFAULT; + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + sctp_sk(sk)->ep->prsctp_enable = !!params.assoc_value; return 0; @@ -3966,6 +4136,7 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_default_prinfo info; struct sctp_association *asoc; int retval = -EINVAL; @@ -3985,19 +4156,31 @@ static int sctp_setsockopt_default_prinfo(struct sock *sk, info.pr_value = 0; asoc = sctp_id2assoc(sk, info.pr_assoc_id); + if (!asoc && info.pr_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + goto out; + + retval = 0; + if (asoc) { SCTP_PR_SET_POLICY(asoc->default_flags, info.pr_policy); asoc->default_timetolive = info.pr_value; - } else if (!info.pr_assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); + goto out; + } + if (info.pr_assoc_id == SCTP_FUTURE_ASSOC || + info.pr_assoc_id == SCTP_ALL_ASSOC) { SCTP_PR_SET_POLICY(sp->default_flags, info.pr_policy); sp->default_timetolive = info.pr_value; - } else { - goto out; } - retval = 0; + if (info.pr_assoc_id == SCTP_CURRENT_ASSOC || + info.pr_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + SCTP_PR_SET_POLICY(asoc->default_flags, info.pr_policy); + asoc->default_timetolive = info.pr_value; + } + } out: return retval; @@ -4020,15 +4203,14 @@ static int sctp_setsockopt_reconfig_supported(struct sock *sk, } asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - asoc->reconf_enable = !!params.assoc_value; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - sp->ep->reconf_enable = !!params.assoc_value; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) goto out; - } + + if (asoc) + asoc->reconf_enable = !!params.assoc_value; + else + sctp_sk(sk)->ep->reconf_enable = !!params.assoc_value; retval = 0; @@ -4040,6 +4222,7 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_endpoint *ep = sctp_sk(sk)->ep; struct sctp_assoc_value params; struct sctp_association *asoc; int retval = -EINVAL; @@ -4056,17 +4239,25 @@ static int sctp_setsockopt_enable_strreset(struct sock *sk, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + goto out; + + retval = 0; + if (asoc) { asoc->strreset_enable = params.assoc_value; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - sp->ep->strreset_enable = params.assoc_value; - } else { goto out; } - retval = 0; + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + ep->strreset_enable = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + list_for_each_entry(asoc, &ep->asocs, asocs) + asoc->strreset_enable = params.assoc_value; out: return retval; @@ -4161,29 +4352,44 @@ static int sctp_setsockopt_scheduler(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; struct sctp_assoc_value params; - int retval = -EINVAL; + int retval = 0; if (optlen < sizeof(params)) - goto out; + return -EINVAL; optlen = sizeof(params); - if (copy_from_user(¶ms, optval, optlen)) { - retval = -EFAULT; - goto out; - } + if (copy_from_user(¶ms, optval, optlen)) + return -EFAULT; if (params.assoc_value > SCTP_SS_MAX) - goto out; + return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - goto out; + if (!asoc && params.assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - retval = sctp_sched_set_sched(asoc, params.assoc_value); + if (asoc) + return sctp_sched_set_sched(asoc, params.assoc_value); + + if (params.assoc_id == SCTP_FUTURE_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) + sp->default_ss = params.assoc_value; + + if (params.assoc_id == SCTP_CURRENT_ASSOC || + params.assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + int ret = sctp_sched_set_sched(asoc, + params.assoc_value); + + if (ret && !retval) + retval = ret; + } + } -out: return retval; } @@ -4191,8 +4397,8 @@ static int sctp_setsockopt_scheduler_value(struct sock *sk, char __user *optval, unsigned int optlen) { - struct sctp_association *asoc; struct sctp_stream_value params; + struct sctp_association *asoc; int retval = -EINVAL; if (optlen < sizeof(params)) @@ -4205,11 +4411,24 @@ static int sctp_setsockopt_scheduler_value(struct sock *sk, } asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) + if (!asoc && params.assoc_id != SCTP_CURRENT_ASSOC && + sctp_style(sk, UDP)) goto out; - retval = sctp_sched_set_value(asoc, params.stream_id, - params.stream_value, GFP_KERNEL); + if (asoc) { + retval = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + goto out; + } + + retval = 0; + + list_for_each_entry(asoc, &sctp_sk(sk)->ep->asocs, asocs) { + int ret = sctp_sched_set_value(asoc, params.stream_id, + params.stream_value, GFP_KERNEL); + if (ret && !retval) /* try to return the 1st error. */ + retval = ret; + } out: return retval; @@ -4220,8 +4439,8 @@ static int sctp_setsockopt_interleaving_supported(struct sock *sk, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); - struct net *net = sock_net(sk); struct sctp_assoc_value params; + struct sctp_association *asoc; int retval = -EINVAL; if (optlen < sizeof(params)) @@ -4233,10 +4452,12 @@ static int sctp_setsockopt_interleaving_supported(struct sock *sk, goto out; } - if (params.assoc_id) + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) goto out; - if (!net->sctp.intl_enable || !sp->frag_interleave) { + if (!sock_net(sk)->sctp.intl_enable || !sp->frag_interleave) { retval = -EPERM; goto out; } @@ -4271,54 +4492,69 @@ static int sctp_setsockopt_reuse_port(struct sock *sk, char __user *optval, return 0; } +static int sctp_assoc_ulpevent_type_set(struct sctp_event *param, + struct sctp_association *asoc) +{ + struct sctp_ulpevent *event; + + sctp_ulpevent_type_set(&asoc->subscribe, param->se_type, param->se_on); + + if (param->se_type == SCTP_SENDER_DRY_EVENT && param->se_on) { + if (sctp_outq_is_empty(&asoc->outqueue)) { + event = sctp_ulpevent_make_sender_dry_event(asoc, + GFP_USER | __GFP_NOWARN); + if (!event) + return -ENOMEM; + + asoc->stream.si->enqueue_event(&asoc->ulpq, event); + } + } + + return 0; +} + static int sctp_setsockopt_event(struct sock *sk, char __user *optval, unsigned int optlen) { + struct sctp_sock *sp = sctp_sk(sk); struct sctp_association *asoc; - struct sctp_ulpevent *event; struct sctp_event param; int retval = 0; - if (optlen < sizeof(param)) { - retval = -EINVAL; - goto out; - } + if (optlen < sizeof(param)) + return -EINVAL; optlen = sizeof(param); - if (copy_from_user(¶m, optval, optlen)) { - retval = -EFAULT; - goto out; - } + if (copy_from_user(¶m, optval, optlen)) + return -EFAULT; if (param.se_type < SCTP_SN_TYPE_BASE || - param.se_type > SCTP_SN_TYPE_MAX) { - retval = -EINVAL; - goto out; - } + param.se_type > SCTP_SN_TYPE_MAX) + return -EINVAL; asoc = sctp_id2assoc(sk, param.se_assoc_id); - if (!asoc) { - sctp_ulpevent_type_set(&sctp_sk(sk)->subscribe, - param.se_type, param.se_on); - goto out; - } + if (!asoc && param.se_assoc_id > SCTP_ALL_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - sctp_ulpevent_type_set(&asoc->subscribe, param.se_type, param.se_on); + if (asoc) + return sctp_assoc_ulpevent_type_set(¶m, asoc); - if (param.se_type == SCTP_SENDER_DRY_EVENT && param.se_on) { - if (sctp_outq_is_empty(&asoc->outqueue)) { - event = sctp_ulpevent_make_sender_dry_event(asoc, - GFP_USER | __GFP_NOWARN); - if (!event) { - retval = -ENOMEM; - goto out; - } + if (param.se_assoc_id == SCTP_FUTURE_ASSOC || + param.se_assoc_id == SCTP_ALL_ASSOC) + sctp_ulpevent_type_set(&sp->subscribe, + param.se_type, param.se_on); - asoc->stream.si->enqueue_event(&asoc->ulpq, event); + if (param.se_assoc_id == SCTP_CURRENT_ASSOC || + param.se_assoc_id == SCTP_ALL_ASSOC) { + list_for_each_entry(asoc, &sp->ep->asocs, asocs) { + int ret = sctp_assoc_ulpevent_type_set(¶m, asoc); + + if (ret && !retval) + retval = ret; } } -out: return retval; } @@ -4777,12 +5013,14 @@ static int sctp_init_sock(struct sock *sk) */ sp->hbinterval = net->sctp.hb_interval; sp->pathmaxrxt = net->sctp.max_retrans_path; + sp->pf_retrans = net->sctp.pf_retrans; sp->pathmtu = 0; /* allow default discovery */ sp->sackdelay = net->sctp.sack_timeout; sp->sackfreq = 2; sp->param_flags = SPP_HB_ENABLE | SPP_PMTUD_ENABLE | SPP_SACKDELAY_ENABLE; + sp->default_ss = SCTP_SS_DEFAULT; /* If enabled no SCTP message fragmentation will be performed. * Configure through SCTP_DISABLE_FRAGMENTS socket option. @@ -5676,12 +5914,13 @@ static int sctp_getsockopt_peer_addr_params(struct sock *sk, int len, } } - /* Get association, if assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.spp_assoc_id); - if (!asoc && params.spp_assoc_id && sctp_style(sk, UDP)) { + if (!asoc && params.spp_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { pr_debug("%s: failed no association\n", __func__); return -EINVAL; } @@ -5810,19 +6049,19 @@ static int sctp_getsockopt_delayed_ack(struct sock *sk, int len, } else return -EINVAL; - /* Get association, if sack_assoc_id != 0 and the socket is a one - * to many style socket, and an association was not found, then - * the id was invalid. + /* Get association, if sack_assoc_id != SCTP_FUTURE_ASSOC and the + * socket is a one to many style socket, and an association + * was not found, then the id was invalid. */ asoc = sctp_id2assoc(sk, params.sack_assoc_id); - if (!asoc && params.sack_assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.sack_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; if (asoc) { /* Fetch association values. */ if (asoc->param_flags & SPP_SACKDELAY_ENABLE) { - params.sack_delay = jiffies_to_msecs( - asoc->sackdelay); + params.sack_delay = jiffies_to_msecs(asoc->sackdelay); params.sack_freq = asoc->sackfreq; } else { @@ -6175,8 +6414,10 @@ static int sctp_getsockopt_default_send_param(struct sock *sk, return -EFAULT; asoc = sctp_id2assoc(sk, info.sinfo_assoc_id); - if (!asoc && info.sinfo_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.sinfo_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { info.sinfo_stream = asoc->default_stream; info.sinfo_flags = asoc->default_flags; @@ -6219,8 +6460,10 @@ static int sctp_getsockopt_default_sndinfo(struct sock *sk, int len, return -EFAULT; asoc = sctp_id2assoc(sk, info.snd_assoc_id); - if (!asoc && info.snd_assoc_id && sctp_style(sk, UDP)) + if (!asoc && info.snd_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; + if (asoc) { info.snd_sid = asoc->default_stream; info.snd_flags = asoc->default_flags; @@ -6296,7 +6539,8 @@ static int sctp_getsockopt_rtoinfo(struct sock *sk, int len, asoc = sctp_id2assoc(sk, rtoinfo.srto_assoc_id); - if (!asoc && rtoinfo.srto_assoc_id && sctp_style(sk, UDP)) + if (!asoc && rtoinfo.srto_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Values corresponding to the specific association. */ @@ -6353,7 +6597,8 @@ static int sctp_getsockopt_associnfo(struct sock *sk, int len, asoc = sctp_id2assoc(sk, assocparams.sasoc_assoc_id); - if (!asoc && assocparams.sasoc_assoc_id && sctp_style(sk, UDP)) + if (!asoc && assocparams.sasoc_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; /* Values correspoinding to the specific association */ @@ -6428,7 +6673,6 @@ static int sctp_getsockopt_context(struct sock *sk, int len, char __user *optval, int __user *optlen) { struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; if (len < sizeof(struct sctp_assoc_value)) @@ -6439,16 +6683,13 @@ static int sctp_getsockopt_context(struct sock *sk, int len, if (copy_from_user(¶ms, optval, len)) return -EFAULT; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (params.assoc_id != 0) { - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - return -EINVAL; - params.assoc_value = asoc->default_rcv_context; - } else { - params.assoc_value = sp->default_rcv_context; - } + params.assoc_value = asoc ? asoc->default_rcv_context + : sctp_sk(sk)->default_rcv_context; if (put_user(len, optlen)) return -EFAULT; @@ -6497,7 +6738,7 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len, "Use of int in maxseg socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); - params.assoc_id = 0; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) @@ -6506,7 +6747,8 @@ static int sctp_getsockopt_maxseg(struct sock *sk, int len, return -EINVAL; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc && params.assoc_id && sctp_style(sk, UDP)) + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; if (asoc) @@ -6583,7 +6825,6 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, int __user *optlen) { struct sctp_assoc_value params; - struct sctp_sock *sp; struct sctp_association *asoc; if (len == sizeof(int)) { @@ -6592,7 +6833,7 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, "Use of int in max_burst socket option.\n" "Use struct sctp_assoc_value instead\n", current->comm, task_pid_nr(current)); - params.assoc_id = 0; + params.assoc_id = SCTP_FUTURE_ASSOC; } else if (len >= sizeof(struct sctp_assoc_value)) { len = sizeof(struct sctp_assoc_value); if (copy_from_user(¶ms, optval, len)) @@ -6600,15 +6841,12 @@ static int sctp_getsockopt_maxburst(struct sock *sk, int len, } else return -EINVAL; - sp = sctp_sk(sk); + asoc = sctp_id2assoc(sk, params.assoc_id); + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; - if (params.assoc_id != 0) { - asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) - return -EINVAL; - params.assoc_value = asoc->max_burst; - } else - params.assoc_value = sp->max_burst; + params.assoc_value = asoc ? asoc->max_burst : sctp_sk(sk)->max_burst; if (len == sizeof(int)) { if (copy_to_user(optval, ¶ms.assoc_value, len)) @@ -6759,14 +6997,12 @@ static int sctp_getsockopt_local_auth_chunks(struct sock *sk, int len, to = p->gauth_chunks; asoc = sctp_id2assoc(sk, val.gauth_assoc_id); - if (!asoc && val.gauth_assoc_id && sctp_style(sk, UDP)) + if (!asoc && val.gauth_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) return -EINVAL; - if (asoc) - ch = (struct sctp_chunks_param *)asoc->c.auth_chunks; - else - ch = ep->auth_chunk_list; - + ch = asoc ? (struct sctp_chunks_param *)asoc->c.auth_chunks + : ep->auth_chunk_list; if (!ch) goto num; @@ -6911,14 +7147,7 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, if (copy_from_user(&val, (struct sctp_paddrthlds __user *)optval, len)) return -EFAULT; - if (sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { - asoc = sctp_id2assoc(sk, val.spt_assoc_id); - if (!asoc) - return -ENOENT; - - val.spt_pathpfthld = asoc->pf_retrans; - val.spt_pathmaxrxt = asoc->pathmaxrxt; - } else { + if (!sctp_is_any(sk, (const union sctp_addr *)&val.spt_address)) { trans = sctp_addr_id2transport(sk, &val.spt_address, val.spt_assoc_id); if (!trans) @@ -6926,6 +7155,23 @@ static int sctp_getsockopt_paddr_thresholds(struct sock *sk, val.spt_pathmaxrxt = trans->pathmaxrxt; val.spt_pathpfthld = trans->pf_retrans; + + return 0; + } + + asoc = sctp_id2assoc(sk, val.spt_assoc_id); + if (!asoc && val.spt_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + + if (asoc) { + val.spt_pathpfthld = asoc->pf_retrans; + val.spt_pathmaxrxt = asoc->pathmaxrxt; + } else { + struct sctp_sock *sp = sctp_sk(sk); + + val.spt_pathpfthld = sp->pf_retrans; + val.spt_pathmaxrxt = sp->pathmaxrxt; } if (put_user(len, optlen) || copy_to_user(optval, &val, len)) @@ -7056,17 +7302,15 @@ static int sctp_getsockopt_pr_supported(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->prsctp_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->ep->prsctp_enable; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->prsctp_enable + : sctp_sk(sk)->ep->prsctp_enable; + if (put_user(len, optlen)) goto out; @@ -7097,17 +7341,20 @@ static int sctp_getsockopt_default_prinfo(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, info.pr_assoc_id); + if (!asoc && info.pr_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { + retval = -EINVAL; + goto out; + } + if (asoc) { info.pr_policy = SCTP_PR_POLICY(asoc->default_flags); info.pr_value = asoc->default_timetolive; - } else if (!info.pr_assoc_id) { + } else { struct sctp_sock *sp = sctp_sk(sk); info.pr_policy = SCTP_PR_POLICY(sp->default_flags); info.pr_value = sp->default_timetolive; - } else { - retval = -EINVAL; - goto out; } if (put_user(len, optlen)) @@ -7263,17 +7510,15 @@ static int sctp_getsockopt_reconfig_supported(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->reconf_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->ep->reconf_enable; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->reconf_enable + : sctp_sk(sk)->ep->reconf_enable; + if (put_user(len, optlen)) goto out; @@ -7304,17 +7549,15 @@ static int sctp_getsockopt_enable_strreset(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->strreset_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->ep->strreset_enable; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->strreset_enable + : sctp_sk(sk)->ep->strreset_enable; + if (put_user(len, optlen)) goto out; @@ -7345,12 +7588,14 @@ static int sctp_getsockopt_scheduler(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (!asoc) { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } - params.assoc_value = sctp_sched_get_sched(asoc); + params.assoc_value = asoc ? sctp_sched_get_sched(asoc) + : sctp_sk(sk)->default_ss; if (put_user(len, optlen)) goto out; @@ -7424,17 +7669,15 @@ static int sctp_getsockopt_interleaving_supported(struct sock *sk, int len, goto out; asoc = sctp_id2assoc(sk, params.assoc_id); - if (asoc) { - params.assoc_value = asoc->intl_enable; - } else if (!params.assoc_id) { - struct sctp_sock *sp = sctp_sk(sk); - - params.assoc_value = sp->strm_interleave; - } else { + if (!asoc && params.assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) { retval = -EINVAL; goto out; } + params.assoc_value = asoc ? asoc->intl_enable + : sctp_sk(sk)->strm_interleave; + if (put_user(len, optlen)) goto out; @@ -7486,6 +7729,10 @@ static int sctp_getsockopt_event(struct sock *sk, int len, char __user *optval, return -EINVAL; asoc = sctp_id2assoc(sk, param.se_assoc_id); + if (!asoc && param.se_assoc_id != SCTP_FUTURE_ASSOC && + sctp_style(sk, UDP)) + return -EINVAL; + subscribe = asoc ? asoc->subscribe : sctp_sk(sk)->subscribe; param.se_on = sctp_ulpevent_type_enabled(subscribe, param.se_type); diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index b04a813fc865..46fa9f3016cc 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -42,8 +42,11 @@ #include "smc_rx.h" #include "smc_close.h" -static DEFINE_MUTEX(smc_create_lgr_pending); /* serialize link group - * creation +static DEFINE_MUTEX(smc_server_lgr_pending); /* serialize link group + * creation on server + */ +static DEFINE_MUTEX(smc_client_lgr_pending); /* serialize link group + * creation on client */ static void smc_tcp_listen_work(struct work_struct *); @@ -145,32 +148,33 @@ static int smc_release(struct socket *sock) rc = smc_close_active(smc); sock_set_flag(sk, SOCK_DEAD); sk->sk_shutdown |= SHUTDOWN_MASK; - } - - sk->sk_prot->unhash(sk); - - if (smc->clcsock) { - if (smc->use_fallback && sk->sk_state == SMC_LISTEN) { + } else { + if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) + sock_put(sk); /* passive closing */ + if (sk->sk_state == SMC_LISTEN) { /* wake up clcsock accept */ rc = kernel_sock_shutdown(smc->clcsock, SHUT_RDWR); } - mutex_lock(&smc->clcsock_release_lock); - sock_release(smc->clcsock); - smc->clcsock = NULL; - mutex_unlock(&smc->clcsock_release_lock); - } - if (smc->use_fallback) { - if (sk->sk_state != SMC_LISTEN && sk->sk_state != SMC_INIT) - sock_put(sk); /* passive closing */ sk->sk_state = SMC_CLOSED; sk->sk_state_change(sk); } + sk->sk_prot->unhash(sk); + + if (sk->sk_state == SMC_CLOSED) { + if (smc->clcsock) { + mutex_lock(&smc->clcsock_release_lock); + sock_release(smc->clcsock); + smc->clcsock = NULL; + mutex_unlock(&smc->clcsock_release_lock); + } + if (!smc->use_fallback) + smc_conn_free(&smc->conn); + } + /* detach socket */ sock_orphan(sk); sock->sk = NULL; - if (!smc->use_fallback && sk->sk_state == SMC_CLOSED) - smc_conn_free(&smc->conn); release_sock(sk); sock_put(sk); /* final sock_put */ @@ -291,7 +295,8 @@ static void smc_copy_sock_settings(struct sock *nsk, struct sock *osk, (1UL << SOCK_RXQ_OVFL) | \ (1UL << SOCK_WIFI_STATUS) | \ (1UL << SOCK_NOFCS) | \ - (1UL << SOCK_FILTER_LOCKED)) + (1UL << SOCK_FILTER_LOCKED) | \ + (1UL << SOCK_TSTAMP_NEW)) /* copy only relevant settings and flags of SOL_SOCKET level from smc to * clc socket (since smc is not called for these options from net/core) */ @@ -475,7 +480,12 @@ static int smc_connect_abort(struct smc_sock *smc, int reason_code, { if (local_contact == SMC_FIRST_CONTACT) smc_lgr_forget(smc->conn.lgr); - mutex_unlock(&smc_create_lgr_pending); + if (smc->conn.lgr->is_smcd) + /* there is only one lgr role for SMC-D; use server lock */ + mutex_unlock(&smc_server_lgr_pending); + else + mutex_unlock(&smc_client_lgr_pending); + smc_conn_free(&smc->conn); return reason_code; } @@ -560,7 +570,7 @@ static int smc_connect_rdma(struct smc_sock *smc, struct smc_link *link; int reason_code = 0; - mutex_lock(&smc_create_lgr_pending); + mutex_lock(&smc_client_lgr_pending); local_contact = smc_conn_create(smc, false, aclc->hdr.flag, ibdev, ibport, ntoh24(aclc->qpn), &aclc->lcl, NULL, 0); @@ -571,7 +581,8 @@ static int smc_connect_rdma(struct smc_sock *smc, reason_code = SMC_CLC_DECL_SYNCERR; /* synchr. error */ else reason_code = SMC_CLC_DECL_INTERR; /* other error */ - return smc_connect_abort(smc, reason_code, 0); + mutex_unlock(&smc_client_lgr_pending); + return reason_code; } link = &smc->conn.lgr->lnk[SMC_SINGLE_LINK]; @@ -615,7 +626,7 @@ static int smc_connect_rdma(struct smc_sock *smc, return smc_connect_abort(smc, reason_code, local_contact); } - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_client_lgr_pending); smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) @@ -632,11 +643,14 @@ static int smc_connect_ism(struct smc_sock *smc, int local_contact = SMC_FIRST_CONTACT; int rc = 0; - mutex_lock(&smc_create_lgr_pending); + /* there is only one lgr role for SMC-D; use server lock */ + mutex_lock(&smc_server_lgr_pending); local_contact = smc_conn_create(smc, true, aclc->hdr.flag, NULL, 0, 0, NULL, ismdev, aclc->gid); - if (local_contact < 0) - return smc_connect_abort(smc, SMC_CLC_DECL_MEM, 0); + if (local_contact < 0) { + mutex_unlock(&smc_server_lgr_pending); + return SMC_CLC_DECL_MEM; + } /* Create send and receive buffers */ if (smc_buf_create(smc, true)) @@ -650,7 +664,7 @@ static int smc_connect_ism(struct smc_sock *smc, rc = smc_clc_send_confirm(smc); if (rc) return smc_connect_abort(smc, rc, local_contact); - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_server_lgr_pending); smc_copy_sock_settings_to_clc(smc); if (smc->sk.sk_state == SMC_INIT) @@ -1249,7 +1263,7 @@ static void smc_listen_work(struct work_struct *work) return; } - mutex_lock(&smc_create_lgr_pending); + mutex_lock(&smc_server_lgr_pending); smc_close_init(new_smc); smc_rx_init(new_smc); smc_tx_init(new_smc); @@ -1271,7 +1285,7 @@ static void smc_listen_work(struct work_struct *work) &local_contact) || smc_listen_rdma_reg(new_smc, local_contact))) { /* SMC not supported, decline */ - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_server_lgr_pending); smc_listen_decline(new_smc, SMC_CLC_DECL_MODEUNSUPP, local_contact); return; @@ -1280,29 +1294,33 @@ static void smc_listen_work(struct work_struct *work) /* send SMC Accept CLC message */ rc = smc_clc_send_accept(new_smc, local_contact); if (rc) { - mutex_unlock(&smc_create_lgr_pending); + mutex_unlock(&smc_server_lgr_pending); smc_listen_decline(new_smc, rc, local_contact); return; } + /* SMC-D does not need this lock any more */ + if (ism_supported) + mutex_unlock(&smc_server_lgr_pending); + /* receive SMC Confirm CLC message */ reason_code = smc_clc_wait_msg(new_smc, &cclc, sizeof(cclc), SMC_CLC_CONFIRM, CLC_WAIT_TIME); if (reason_code) { - mutex_unlock(&smc_create_lgr_pending); + if (!ism_supported) + mutex_unlock(&smc_server_lgr_pending); smc_listen_decline(new_smc, reason_code, local_contact); return; } /* finish worker */ if (!ism_supported) { - if (smc_listen_rdma_finish(new_smc, &cclc, local_contact)) { - mutex_unlock(&smc_create_lgr_pending); + rc = smc_listen_rdma_finish(new_smc, &cclc, local_contact); + mutex_unlock(&smc_server_lgr_pending); + if (rc) return; - } } smc_conn_save_peer_info(new_smc, &cclc); - mutex_unlock(&smc_create_lgr_pending); smc_listen_out_connected(new_smc); } diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index fb07ad8d69a6..d0b0f4c865b4 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -103,8 +103,10 @@ int smc_cdc_msg_send(struct smc_connection *conn, conn->local_tx_ctrl.seqno = conn->tx_cdc_seq; smc_host_msg_to_cdc((struct smc_cdc_msg *)wr_buf, conn, &cfed); rc = smc_wr_tx_send(link, (struct smc_wr_tx_pend_priv *)pend); - if (!rc) + if (!rc) { smc_curs_copy(&conn->rx_curs_confirmed, &cfed, conn); + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; + } return rc; } @@ -192,6 +194,7 @@ int smcd_cdc_msg_send(struct smc_connection *conn) if (rc) return rc; smc_curs_copy(&conn->rx_curs_confirmed, &curs, conn); + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; /* Calculate transmitted data and increment free send buffer space */ diff = smc_curs_diff(conn->sndbuf_desc->len, &conn->tx_curs_fin, &conn->tx_curs_sent); @@ -268,26 +271,18 @@ static void smc_cdc_msg_recv_action(struct smc_sock *smc, smp_mb__after_atomic(); smc->sk.sk_data_ready(&smc->sk); } else { - if (conn->local_rx_ctrl.prod_flags.write_blocked || - conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || - conn->local_rx_ctrl.prod_flags.urg_data_pending) { - if (conn->local_rx_ctrl.prod_flags.urg_data_pending) - conn->urg_state = SMC_URG_NOTYET; - /* force immediate tx of current consumer cursor, but - * under send_lock to guarantee arrival in seqno-order - */ - if (smc->sk.sk_state != SMC_INIT) - smc_tx_sndbuf_nonempty(conn); - } + if (conn->local_rx_ctrl.prod_flags.write_blocked) + smc->sk.sk_data_ready(&smc->sk); + if (conn->local_rx_ctrl.prod_flags.urg_data_pending) + conn->urg_state = SMC_URG_NOTYET; } - /* piggy backed tx info */ /* trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ - if (diff_cons && smc_tx_prepared_sends(conn)) { + if ((diff_cons && smc_tx_prepared_sends(conn)) || + conn->local_rx_ctrl.prod_flags.cons_curs_upd_req || + conn->local_rx_ctrl.prod_flags.urg_data_pending) smc_tx_sndbuf_nonempty(conn); - /* trigger socket release if connection closed */ - smc_close_wake_tx_prepared(smc); - } + if (diff_cons && conn->urg_tx_pend && atomic_read(&conn->peer_rmbe_space) == conn->peer_rmbe_size) { /* urg data confirmed by peer, indicate we're ready for more */ diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index f1cdde9d4b89..861dc24c588c 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -270,17 +270,18 @@ static inline void smcr_cdc_msg_to_host(struct smc_host_cdc_msg *local, } static inline void smcd_cdc_msg_to_host(struct smc_host_cdc_msg *local, - struct smcd_cdc_msg *peer) + struct smcd_cdc_msg *peer, + struct smc_connection *conn) { union smc_host_cursor temp; temp.wrap = peer->prod.wrap; temp.count = peer->prod.count; - atomic64_set(&local->prod.acurs, atomic64_read(&temp.acurs)); + smc_curs_copy(&local->prod, &temp, conn); temp.wrap = peer->cons.wrap; temp.count = peer->cons.count; - atomic64_set(&local->cons.acurs, atomic64_read(&temp.acurs)); + smc_curs_copy(&local->cons, &temp, conn); local->prod_flags = peer->cons.prod_flags; local->conn_state_flags = peer->cons.conn_state_flags; } @@ -290,7 +291,7 @@ static inline void smc_cdc_msg_to_host(struct smc_host_cdc_msg *local, struct smc_connection *conn) { if (conn->lgr->is_smcd) - smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer); + smcd_cdc_msg_to_host(local, (struct smcd_cdc_msg *)peer, conn); else smcr_cdc_msg_to_host(local, peer, conn); } diff --git a/net/smc/smc_close.c b/net/smc/smc_close.c index e39cadda1bf5..2ad37e998509 100644 --- a/net/smc/smc_close.c +++ b/net/smc/smc_close.c @@ -398,8 +398,13 @@ wakeup: if (old_state != sk->sk_state) { sk->sk_state_change(sk); if ((sk->sk_state == SMC_CLOSED) && - (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) + (sock_flag(sk, SOCK_DEAD) || !sk->sk_socket)) { smc_conn_free(conn); + if (smc->clcsock) { + sock_release(smc->clcsock); + smc->clcsock = NULL; + } + } } release_sock(sk); sock_put(sk); /* sock_hold done by schedulers of close_work */ diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index aa1c551cee81..53a17cfa61af 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -118,7 +118,6 @@ static void __smc_lgr_unregister_conn(struct smc_connection *conn) rb_erase(&conn->alert_node, &lgr->conns_all); lgr->conns_num--; conn->alert_token_local = 0; - conn->lgr = NULL; sock_put(&smc->sk); /* sock_hold in smc_lgr_register_conn() */ } @@ -161,8 +160,6 @@ static void smc_lgr_free_work(struct work_struct *work) bool conns; spin_lock_bh(&smc_lgr_list.lock); - if (list_empty(&lgr->list)) - goto free; read_lock_bh(&lgr->conns_lock); conns = RB_EMPTY_ROOT(&lgr->conns_all); read_unlock_bh(&lgr->conns_lock); @@ -170,8 +167,8 @@ static void smc_lgr_free_work(struct work_struct *work) spin_unlock_bh(&smc_lgr_list.lock); return; } - list_del_init(&lgr->list); /* remove from smc_lgr_list */ -free: + if (!list_empty(&lgr->list)) + list_del_init(&lgr->list); /* remove from smc_lgr_list */ spin_unlock_bh(&smc_lgr_list.lock); if (!lgr->is_smcd && !lgr->terminating) { @@ -333,8 +330,9 @@ void smc_conn_free(struct smc_connection *conn) } else { smc_cdc_tx_dismiss_slots(conn); } - smc_lgr_unregister_conn(conn); /* unsets conn->lgr */ + smc_lgr_unregister_conn(conn); smc_buf_unuse(conn, lgr); /* allow buffer reuse */ + conn->lgr = NULL; if (!lgr->conns_num) smc_lgr_schedule_free_work(lgr); @@ -464,6 +462,7 @@ static void __smc_lgr_terminate(struct smc_link_group *lgr) sock_hold(&smc->sk); /* sock_put in close work */ conn->local_tx_ctrl.conn_state_flags.peer_conn_abort = 1; __smc_lgr_unregister_conn(conn); + conn->lgr = NULL; write_unlock_bh(&lgr->conns_lock); if (!schedule_work(&conn->close_work)) sock_put(&smc->sk); diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index dbf64a93d68a..371b4cf31fcd 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -38,6 +38,7 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); + r->diag_family = sk->sk_family; if (!smc->clcsock) return; r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); @@ -45,14 +46,12 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; sock_diag_save_cookie(sk, r->id.idiag_cookie); if (sk->sk_protocol == SMCPROTO_SMC) { - r->diag_family = PF_INET; memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; #if IS_ENABLED(CONFIG_IPV6) } else if (sk->sk_protocol == SMCPROTO_SMC6) { - r->diag_family = PF_INET6; memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr, sizeof(smc->clcsock->sk->sk_v6_rcv_saddr)); memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr, diff --git a/net/smc/smc_ib.c b/net/smc/smc_ib.c index 76487a16934e..0b244be24fe0 100644 --- a/net/smc/smc_ib.c +++ b/net/smc/smc_ib.c @@ -257,12 +257,20 @@ static void smc_ib_global_event_handler(struct ib_event_handler *handler, smcibdev = container_of(handler, struct smc_ib_device, event_handler); switch (ibevent->event) { - case IB_EVENT_PORT_ERR: case IB_EVENT_DEVICE_FATAL: + /* terminate all ports on device */ + for (port_idx = 0; port_idx < SMC_MAX_PORTS; port_idx++) + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); + break; + case IB_EVENT_PORT_ERR: case IB_EVENT_PORT_ACTIVE: + case IB_EVENT_GID_CHANGE: port_idx = ibevent->element.port_num - 1; - set_bit(port_idx, &smcibdev->port_event_mask); - schedule_work(&smcibdev->port_event_work); + if (port_idx < SMC_MAX_PORTS) { + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); + } break; default: break; @@ -294,13 +302,13 @@ static void smc_ib_qp_event_handler(struct ib_event *ibevent, void *priv) u8 port_idx; switch (ibevent->event) { - case IB_EVENT_DEVICE_FATAL: - case IB_EVENT_GID_CHANGE: - case IB_EVENT_PORT_ERR: + case IB_EVENT_QP_FATAL: case IB_EVENT_QP_ACCESS_ERR: port_idx = ibevent->element.qp->port - 1; - set_bit(port_idx, &smcibdev->port_event_mask); - schedule_work(&smcibdev->port_event_work); + if (port_idx < SMC_MAX_PORTS) { + set_bit(port_idx, &smcibdev->port_event_mask); + schedule_work(&smcibdev->port_event_work); + } break; default: break; diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index f93f3580c100..a3bff08ff8c8 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -24,10 +24,11 @@ #include "smc.h" #include "smc_wr.h" #include "smc_cdc.h" +#include "smc_close.h" #include "smc_ism.h" #include "smc_tx.h" -#define SMC_TX_WORK_DELAY HZ +#define SMC_TX_WORK_DELAY 0 #define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ /***************************** sndbuf producer *******************************/ @@ -554,6 +555,12 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) else rc = smcr_tx_sndbuf_nonempty(conn); + if (!rc) { + /* trigger socket release if connection is closing */ + struct smc_sock *smc = container_of(conn, struct smc_sock, + conn); + smc_close_wake_tx_prepared(smc); + } return rc; } @@ -610,9 +617,6 @@ void smc_tx_consumer_update(struct smc_connection *conn, bool force) SMC_TX_WORK_DELAY); return; } - smc_curs_copy(&conn->rx_curs_confirmed, - &conn->local_tx_ctrl.cons, conn); - conn->local_rx_ctrl.prod_flags.cons_curs_upd_req = 0; } if (conn->local_rx_ctrl.prod_flags.write_blocked && !atomic_read(&conn->bytes_to_rcv)) diff --git a/net/socket.c b/net/socket.c index d80d87a395ea..643a1648fcc2 100644 --- a/net/socket.c +++ b/net/socket.c @@ -669,7 +669,7 @@ static bool skb_is_err_queue(const struct sk_buff *skb) * before the software timestamp is received, a hardware TX timestamp may be * returned only if there is no software TX timestamp. Ignore false software * timestamps, which may be made in the __sock_recv_timestamp() call when the - * option SO_TIMESTAMP(NS) is enabled on the socket, even when the skb has a + * option SO_TIMESTAMP_OLD(NS) is enabled on the socket, even when the skb has a * hardware timestamp. */ static bool skb_is_swtx_tstamp(const struct sk_buff *skb, int false_tstamp) @@ -705,7 +705,9 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, struct sk_buff *skb) { int need_software_tstamp = sock_flag(sk, SOCK_RCVTSTAMP); - struct scm_timestamping tss; + int new_tstamp = sock_flag(sk, SOCK_TSTAMP_NEW); + struct scm_timestamping_internal tss; + int empty = 1, false_tstamp = 0; struct skb_shared_hwtstamps *shhwtstamps = skb_hwtstamps(skb); @@ -719,34 +721,54 @@ void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk, if (need_software_tstamp) { if (!sock_flag(sk, SOCK_RCVTSTAMPNS)) { - struct timeval tv; - skb_get_timestamp(skb, &tv); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMP, - sizeof(tv), &tv); + if (new_tstamp) { + struct __kernel_sock_timeval tv; + + skb_get_new_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_NEW, + sizeof(tv), &tv); + } else { + struct __kernel_old_timeval tv; + + skb_get_timestamp(skb, &tv); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMP_OLD, + sizeof(tv), &tv); + } } else { - struct timespec ts; - skb_get_timestampns(skb, &ts); - put_cmsg(msg, SOL_SOCKET, SCM_TIMESTAMPNS, - sizeof(ts), &ts); + if (new_tstamp) { + struct __kernel_timespec ts; + + skb_get_new_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_NEW, + sizeof(ts), &ts); + } else { + struct timespec ts; + + skb_get_timestampns(skb, &ts); + put_cmsg(msg, SOL_SOCKET, SO_TIMESTAMPNS_OLD, + sizeof(ts), &ts); + } } } memset(&tss, 0, sizeof(tss)); if ((sk->sk_tsflags & SOF_TIMESTAMPING_SOFTWARE) && - ktime_to_timespec_cond(skb->tstamp, tss.ts + 0)) + ktime_to_timespec64_cond(skb->tstamp, tss.ts + 0)) empty = 0; if (shhwtstamps && (sk->sk_tsflags & SOF_TIMESTAMPING_RAW_HARDWARE) && !skb_is_swtx_tstamp(skb, false_tstamp) && - ktime_to_timespec_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { + ktime_to_timespec64_cond(shhwtstamps->hwtstamp, tss.ts + 2)) { empty = 0; if ((sk->sk_tsflags & SOF_TIMESTAMPING_OPT_PKTINFO) && !skb_is_err_queue(skb)) put_ts_pktinfo(msg, skb); } if (!empty) { - put_cmsg(msg, SOL_SOCKET, - SCM_TIMESTAMPING, sizeof(tss), &tss); + if (sock_flag(sk, SOCK_TSTAMP_NEW)) + put_cmsg_scm_timestamping64(msg, &tss); + else + put_cmsg_scm_timestamping(msg, &tss); if (skb_is_err_queue(skb) && skb->len && SKB_EXT_ERR(skb)->opt_stats) diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5df9d1138ac9..7e1357db33d7 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -556,10 +556,11 @@ EXPORT_SYMBOL_GPL(unregister_switchdev_notifier); * Call all network notifier blocks. */ int call_switchdev_notifiers(unsigned long val, struct net_device *dev, - struct switchdev_notifier_info *info) + struct switchdev_notifier_info *info, + struct netlink_ext_ack *extack) { info->dev = dev; - info->extack = NULL; + info->extack = extack; return atomic_notifier_call_chain(&switchdev_notif_chain, val, info); } EXPORT_SYMBOL_GPL(call_switchdev_notifiers); @@ -591,26 +592,6 @@ int call_switchdev_blocking_notifiers(unsigned long val, struct net_device *dev, } EXPORT_SYMBOL_GPL(call_switchdev_blocking_notifiers); -bool switchdev_port_same_parent_id(struct net_device *a, - struct net_device *b) -{ - struct switchdev_attr a_attr = { - .orig_dev = a, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; - struct switchdev_attr b_attr = { - .orig_dev = b, - .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, - }; - - if (switchdev_port_attr_get(a, &a_attr) || - switchdev_port_attr_get(b, &b_attr)) - return false; - - return netdev_phys_item_id_same(&a_attr.u.ppid, &b_attr.u.ppid); -} -EXPORT_SYMBOL_GPL(switchdev_port_same_parent_id); - static int __switchdev_handle_port_obj_add(struct net_device *dev, struct switchdev_notifier_port_obj_info *port_obj_info, bool (*check_cb)(const struct net_device *dev), diff --git a/net/tipc/link.c b/net/tipc/link.c index 85ad5c0678d0..341ecd796aa4 100644 --- a/net/tipc/link.c +++ b/net/tipc/link.c @@ -1126,7 +1126,7 @@ static bool tipc_data_input(struct tipc_link *l, struct sk_buff *skb, skb_queue_tail(mc_inputq, skb); return true; } - /* else: fall through */ + /* fall through */ case CONN_MANAGER: skb_queue_tail(inputq, skb); return true; diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 1217c90a363b..8fc5acd4820d 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -735,7 +735,7 @@ static __poll_t tipc_poll(struct file *file, struct socket *sock, case TIPC_CONNECTING: if (!tsk->cong_link_cnt && !tsk_conn_cong(tsk)) revents |= EPOLLOUT; - /* fall thru' */ + /* fall through */ case TIPC_LISTEN: if (!skb_queue_empty(&sk->sk_receive_queue)) revents |= EPOLLIN | EPOLLRDNORM; @@ -2416,7 +2416,7 @@ static int tipc_connect(struct socket *sock, struct sockaddr *dest, * case is EINPROGRESS, rather than EALREADY. */ res = -EINPROGRESS; - /* fall thru' */ + /* fall through */ case TIPC_CONNECTING: if (!timeout) { if (previous == TIPC_CONNECTING) diff --git a/net/tipc/topsrv.c b/net/tipc/topsrv.c index a457c0fbbef1..4a708a4e8583 100644 --- a/net/tipc/topsrv.c +++ b/net/tipc/topsrv.c @@ -60,7 +60,6 @@ * @awork: accept work item * @rcv_wq: receive workqueue * @send_wq: send workqueue - * @max_rcvbuf_size: maximum permitted receive message length * @listener: topsrv listener socket * @name: server name */ @@ -72,7 +71,6 @@ struct tipc_topsrv { struct work_struct awork; struct workqueue_struct *rcv_wq; struct workqueue_struct *send_wq; - int max_rcvbuf_size; struct socket *listener; char name[TIPC_SERVER_NAME_LEN]; }; @@ -648,7 +646,6 @@ int tipc_topsrv_start(struct net *net) return -ENOMEM; srv->net = net; - srv->max_rcvbuf_size = sizeof(struct tipc_subscr); INIT_WORK(&srv->awork, tipc_topsrv_accept); strscpy(srv->name, name, sizeof(srv->name)); diff --git a/net/tipc/trace.c b/net/tipc/trace.c index 964823841efe..265f6a26aa3d 100644 --- a/net/tipc/trace.c +++ b/net/tipc/trace.c @@ -111,7 +111,7 @@ int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf) break; default: break; - }; + } i += scnprintf(buf + i, sz - i, " | %u", msg_src_droppable(hdr)); i += scnprintf(buf + i, sz - i, " %u", @@ -122,7 +122,7 @@ int tipc_skb_dump(struct sk_buff *skb, bool more, char *buf) default: /* need more? */ break; - }; + } i += scnprintf(buf + i, sz - i, "\n"); if (!more) diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c index d753e362d2d9..7ee9008b2187 100644 --- a/net/tls/tls_device.c +++ b/net/tls/tls_device.c @@ -257,7 +257,8 @@ static int tls_push_record(struct sock *sk, tls_fill_prepend(ctx, skb_frag_address(frag), record->len - ctx->tx.prepend_size, - record_type); + record_type, + ctx->crypto_send.info.version); /* HW doesn't care about the data in the tag, because it fills it. */ dummy_tag_frag.page = skb_frag_page(frag); @@ -270,7 +271,7 @@ static int tls_push_record(struct sock *sk, spin_unlock_irq(&offload_ctx->lock); offload_ctx->open_record = NULL; set_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); - tls_advance_record_sn(sk, &ctx->tx); + tls_advance_record_sn(sk, &ctx->tx, ctx->crypto_send.info.version); for (i = 0; i < record->num_frags; i++) { frag = &record->frags[i]; diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c index 450a6dbc5a88..54c3a758f2a7 100644 --- a/net/tls/tls_device_fallback.c +++ b/net/tls/tls_device_fallback.c @@ -73,7 +73,8 @@ static int tls_enc_record(struct aead_request *aead_req, len -= TLS_CIPHER_AES_GCM_128_IV_SIZE; tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE, - (char *)&rcd_sn, sizeof(rcd_sn), buf[0]); + (char *)&rcd_sn, sizeof(rcd_sn), buf[0], + TLS_1_2_VERSION); memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE, TLS_CIPHER_AES_GCM_128_IV_SIZE); diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 78cb4a584080..d1c2fd9a3f63 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -61,6 +61,8 @@ static LIST_HEAD(device_list); static DEFINE_SPINLOCK(device_spinlock); static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_sw_proto_ops; +static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + struct proto *base); static void update_sk_prot(struct sock *sk, struct tls_context *ctx) { @@ -264,8 +266,10 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if ((ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) || - (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE)) { + if (ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) + goto skip_tx_cleanup; + + if (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE) { free_ctx = true; goto skip_tx_cleanup; } @@ -368,6 +372,30 @@ static int do_tls_getsockopt_tx(struct sock *sk, char __user *optval, rc = -EFAULT; break; } + case TLS_CIPHER_AES_GCM_256: { + struct tls12_crypto_info_aes_gcm_256 * + crypto_info_aes_gcm_256 = + container_of(crypto_info, + struct tls12_crypto_info_aes_gcm_256, + info); + + if (len != sizeof(*crypto_info_aes_gcm_256)) { + rc = -EINVAL; + goto out; + } + lock_sock(sk); + memcpy(crypto_info_aes_gcm_256->iv, + ctx->tx.iv + TLS_CIPHER_AES_GCM_256_SALT_SIZE, + TLS_CIPHER_AES_GCM_256_IV_SIZE); + memcpy(crypto_info_aes_gcm_256->rec_seq, ctx->tx.rec_seq, + TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE); + release_sock(sk); + if (copy_to_user(optval, + crypto_info_aes_gcm_256, + sizeof(*crypto_info_aes_gcm_256))) + rc = -EFAULT; + break; + } default: rc = -EINVAL; } @@ -408,6 +436,7 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, { struct tls_crypto_info *crypto_info; struct tls_context *ctx = tls_get_ctx(sk); + size_t optsize; int rc = 0; int conf; @@ -434,14 +463,19 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, } /* check version */ - if (crypto_info->version != TLS_1_2_VERSION) { + if (crypto_info->version != TLS_1_2_VERSION && + crypto_info->version != TLS_1_3_VERSION) { rc = -ENOTSUPP; goto err_crypto_info; } switch (crypto_info->cipher_type) { - case TLS_CIPHER_AES_GCM_128: { - if (optlen != sizeof(struct tls12_crypto_info_aes_gcm_128)) { + case TLS_CIPHER_AES_GCM_128: + case TLS_CIPHER_AES_GCM_256: { + optsize = crypto_info->cipher_type == TLS_CIPHER_AES_GCM_128 ? + sizeof(struct tls12_crypto_info_aes_gcm_128) : + sizeof(struct tls12_crypto_info_aes_gcm_256); + if (optlen != optsize) { rc = -EINVAL; goto err_crypto_info; } @@ -551,6 +585,43 @@ static struct tls_context *create_ctx(struct sock *sk) return ctx; } +static void tls_build_proto(struct sock *sk) +{ + int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; + + /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ + if (ip_ver == TLSV6 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { + mutex_lock(&tcpv6_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv6_prot)) { + build_protos(tls_prots[TLSV6], sk->sk_prot); + smp_store_release(&saved_tcpv6_prot, sk->sk_prot); + } + mutex_unlock(&tcpv6_prot_mutex); + } + + if (ip_ver == TLSV4 && + unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv4_prot))) { + mutex_lock(&tcpv4_prot_mutex); + if (likely(sk->sk_prot != saved_tcpv4_prot)) { + build_protos(tls_prots[TLSV4], sk->sk_prot); + smp_store_release(&saved_tcpv4_prot, sk->sk_prot); + } + mutex_unlock(&tcpv4_prot_mutex); + } +} + +static void tls_hw_sk_destruct(struct sock *sk) +{ + struct tls_context *ctx = tls_get_ctx(sk); + struct inet_connection_sock *icsk = inet_csk(sk); + + ctx->sk_destruct(sk); + /* Free ctx */ + kfree(ctx); + icsk->icsk_ulp_data = NULL; +} + static int tls_hw_prot(struct sock *sk) { struct tls_context *ctx; @@ -564,12 +635,17 @@ static int tls_hw_prot(struct sock *sk) if (!ctx) goto out; + spin_unlock_bh(&device_spinlock); + tls_build_proto(sk); ctx->hash = sk->sk_prot->hash; ctx->unhash = sk->sk_prot->unhash; ctx->sk_proto_close = sk->sk_prot->close; + ctx->sk_destruct = sk->sk_destruct; + sk->sk_destruct = tls_hw_sk_destruct; ctx->rx_conf = TLS_HW_RECORD; ctx->tx_conf = TLS_HW_RECORD; update_sk_prot(sk, ctx); + spin_lock_bh(&device_spinlock); rc = 1; break; } @@ -668,7 +744,6 @@ static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], static int tls_init(struct sock *sk) { - int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; struct tls_context *ctx; int rc = 0; @@ -691,27 +766,7 @@ static int tls_init(struct sock *sk) goto out; } - /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ - if (ip_ver == TLSV6 && - unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { - mutex_lock(&tcpv6_prot_mutex); - if (likely(sk->sk_prot != saved_tcpv6_prot)) { - build_protos(tls_prots[TLSV6], sk->sk_prot); - smp_store_release(&saved_tcpv6_prot, sk->sk_prot); - } - mutex_unlock(&tcpv6_prot_mutex); - } - - if (ip_ver == TLSV4 && - unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv4_prot))) { - mutex_lock(&tcpv4_prot_mutex); - if (likely(sk->sk_prot != saved_tcpv4_prot)) { - build_protos(tls_prots[TLSV4], sk->sk_prot); - smp_store_release(&saved_tcpv4_prot, sk->sk_prot); - } - mutex_unlock(&tcpv4_prot_mutex); - } - + tls_build_proto(sk); ctx->tx_conf = TLS_BASE; ctx->rx_conf = TLS_BASE; update_sk_prot(sk, ctx); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index bf5b54b513bc..ae4784734547 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -120,10 +120,39 @@ static int skb_nsg(struct sk_buff *skb, int offset, int len) return __skb_nsg(skb, offset, len, 0); } +static int padding_length(struct tls_sw_context_rx *ctx, + struct tls_context *tls_ctx, struct sk_buff *skb) +{ + struct strp_msg *rxm = strp_msg(skb); + int sub = 0; + + /* Determine zero-padding length */ + if (tls_ctx->crypto_recv.info.version == TLS_1_3_VERSION) { + char content_type = 0; + int err; + int back = 17; + + while (content_type == 0) { + if (back > rxm->full_len) + return -EBADMSG; + err = skb_copy_bits(skb, + rxm->offset + rxm->full_len - back, + &content_type, 1); + if (content_type) + break; + sub++; + back++; + } + ctx->control = content_type; + } + return sub; +} + static void tls_decrypt_done(struct crypto_async_request *req, int err) { struct aead_request *aead_req = (struct aead_request *)req; struct scatterlist *sgout = aead_req->dst; + struct scatterlist *sgin = aead_req->src; struct tls_sw_context_rx *ctx; struct tls_context *tls_ctx; struct scatterlist *sg; @@ -134,12 +163,16 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) skb = (struct sk_buff *)req->data; tls_ctx = tls_get_ctx(skb->sk); ctx = tls_sw_ctx_rx(tls_ctx); - pending = atomic_dec_return(&ctx->decrypt_pending); /* Propagate if there was an err */ if (err) { ctx->async_wait.err = err; tls_err_abort(skb->sk, err); + } else { + struct strp_msg *rxm = strp_msg(skb); + rxm->full_len -= padding_length(ctx, tls_ctx, skb); + rxm->offset += tls_ctx->rx.prepend_size; + rxm->full_len -= tls_ctx->rx.overhead_size; } /* After using skb->sk to propagate sk through crypto async callback @@ -147,18 +180,21 @@ static void tls_decrypt_done(struct crypto_async_request *req, int err) */ skb->sk = NULL; - /* Release the skb, pages and memory allocated for crypto req */ - kfree_skb(skb); - /* Skip the first S/G entry as it points to AAD */ - for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { - if (!sg) - break; - put_page(sg_page(sg)); + /* Free the destination pages if skb was not decrypted inplace */ + if (sgout != sgin) { + /* Skip the first S/G entry as it points to AAD */ + for_each_sg(sg_next(sgout), sg, UINT_MAX, pages) { + if (!sg) + break; + put_page(sg_page(sg)); + } } kfree(aead_req); + pending = atomic_dec_return(&ctx->decrypt_pending); + if (!pending && READ_ONCE(ctx->async_notify)) complete(&ctx->async_wait.completion); } @@ -177,7 +213,7 @@ static int tls_do_decryption(struct sock *sk, int ret; aead_request_set_tfm(aead_req, ctx->aead_recv); - aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_ad(aead_req, tls_ctx->rx.aad_size); aead_request_set_crypt(aead_req, sgin, sgout, data_len + tls_ctx->rx.tag_size, (u8 *)iv_recv); @@ -281,12 +317,12 @@ static struct tls_rec *tls_get_rec(struct sock *sk) sg_init_table(rec->sg_aead_in, 2); sg_set_buf(&rec->sg_aead_in[0], rec->aad_space, - sizeof(rec->aad_space)); + tls_ctx->tx.aad_size); sg_unmark_end(&rec->sg_aead_in[1]); sg_init_table(rec->sg_aead_out, 2); sg_set_buf(&rec->sg_aead_out[0], rec->aad_space, - sizeof(rec->aad_space)); + tls_ctx->tx.aad_size); sg_unmark_end(&rec->sg_aead_out[1]); return rec; @@ -440,6 +476,8 @@ static int tls_do_encryption(struct sock *sk, int rc; memcpy(rec->iv_data, tls_ctx->tx.iv, sizeof(rec->iv_data)); + xor_iv_with_seq(tls_ctx->crypto_send.info.version, rec->iv_data, + tls_ctx->tx.rec_seq); sge->offset += tls_ctx->tx.prepend_size; sge->length -= tls_ctx->tx.prepend_size; @@ -447,7 +485,7 @@ static int tls_do_encryption(struct sock *sk, msg_en->sg.curr = start; aead_request_set_tfm(aead_req, ctx->aead_send); - aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); + aead_request_set_ad(aead_req, tls_ctx->tx.aad_size); aead_request_set_crypt(aead_req, rec->sg_aead_in, rec->sg_aead_out, data_len, rec->iv_data); @@ -475,7 +513,8 @@ static int tls_do_encryption(struct sock *sk, /* Unhook the record from context if encryption is not failure */ ctx->open_rec = NULL; - tls_advance_record_sn(sk, &tls_ctx->tx); + tls_advance_record_sn(sk, &tls_ctx->tx, + tls_ctx->crypto_send.info.version); return rc; } @@ -632,7 +671,17 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_pl->sg.end; sk_msg_iter_var_prev(i); - sg_mark_end(sk_msg_elem(msg_pl, i)); + + rec->content_type = record_type; + if (tls_ctx->crypto_send.info.version == TLS_1_3_VERSION) { + /* Add content type to end of message. No padding added */ + sg_set_buf(&rec->sg_content_type, &rec->content_type, 1); + sg_mark_end(&rec->sg_content_type); + sg_chain(msg_pl->sg.data, msg_pl->sg.end + 1, + &rec->sg_content_type); + } else { + sg_mark_end(sk_msg_elem(msg_pl, i)); + } i = msg_pl->sg.start; sg_chain(rec->sg_aead_in, 2, rec->inplace_crypto ? @@ -645,18 +694,22 @@ static int tls_push_record(struct sock *sk, int flags, i = msg_en->sg.start; sg_chain(rec->sg_aead_out, 2, &msg_en->sg.data[i]); - tls_make_aad(rec->aad_space, msg_pl->sg.size, + tls_make_aad(rec->aad_space, msg_pl->sg.size + tls_ctx->tx.tail_size, tls_ctx->tx.rec_seq, tls_ctx->tx.rec_seq_size, - record_type); + record_type, + tls_ctx->crypto_send.info.version); tls_fill_prepend(tls_ctx, page_address(sg_page(&msg_en->sg.data[i])) + - msg_en->sg.data[i].offset, msg_pl->sg.size, - record_type); + msg_en->sg.data[i].offset, + msg_pl->sg.size + tls_ctx->tx.tail_size, + record_type, + tls_ctx->crypto_send.info.version); tls_ctx->pending_open_record_frags = false; - rc = tls_do_encryption(sk, tls_ctx, ctx, req, msg_pl->sg.size, i); + rc = tls_do_encryption(sk, tls_ctx, ctx, req, + msg_pl->sg.size + tls_ctx->tx.tail_size, i); if (rc < 0) { if (rc != -EINPROGRESS) { tls_err_abort(sk, EBADMSG); @@ -665,6 +718,7 @@ static int tls_push_record(struct sock *sk, int flags, tls_merge_open_record(sk, rec, tmp, orig_end); } } + ctx->async_capable = 1; return rc; } else if (split) { msg_pl = &tmp->msg_plaintext; @@ -806,8 +860,7 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); - struct crypto_tfm *tfm = crypto_aead_tfm(ctx->aead_send); - bool async_capable = tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + bool async_capable = ctx->async_capable; unsigned char record_type = TLS_RECORD_TYPE_DATA; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); bool eor = !(msg->msg_flags & MSG_MORE); @@ -1022,8 +1075,8 @@ send_end: return copied ? copied : ret; } -int tls_sw_do_sendpage(struct sock *sk, struct page *page, - int offset, size_t size, int flags) +static int tls_sw_do_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) { long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); struct tls_context *tls_ctx = tls_get_ctx(sk); @@ -1145,16 +1198,6 @@ sendpage_end: return copied ? copied : ret; } -int tls_sw_sendpage_locked(struct sock *sk, struct page *page, - int offset, size_t size, int flags) -{ - if (flags & ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | - MSG_SENDPAGE_NOTLAST | MSG_SENDPAGE_NOPOLICY)) - return -ENOTSUPP; - - return tls_sw_do_sendpage(sk, page, offset, size, flags); -} - int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { @@ -1283,7 +1326,7 @@ out: static int decrypt_internal(struct sock *sk, struct sk_buff *skb, struct iov_iter *out_iov, struct scatterlist *out_sg, - int *chunk, bool *zc) + int *chunk, bool *zc, bool async) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); @@ -1294,7 +1337,8 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, u8 *aad, *iv, *mem = NULL; struct scatterlist *sgin = NULL; struct scatterlist *sgout = NULL; - const int data_len = rxm->full_len - tls_ctx->rx.overhead_size; + const int data_len = rxm->full_len - tls_ctx->rx.overhead_size + + tls_ctx->rx.tail_size; if (*zc && (out_iov || out_sg)) { if (out_iov) @@ -1319,7 +1363,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, aead_size = sizeof(*aead_req) + crypto_aead_reqsize(ctx->aead_recv); mem_size = aead_size + (nsg * sizeof(struct scatterlist)); - mem_size = mem_size + TLS_AAD_SPACE_SIZE; + mem_size = mem_size + tls_ctx->rx.aad_size; mem_size = mem_size + crypto_aead_ivsize(ctx->aead_recv); /* Allocate a single block of memory which contains @@ -1335,7 +1379,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, sgin = (struct scatterlist *)(mem + aead_size); sgout = sgin + n_sgin; aad = (u8 *)(sgout + n_sgout); - iv = aad + TLS_AAD_SPACE_SIZE; + iv = aad + tls_ctx->rx.aad_size; /* Prepare IV */ err = skb_copy_bits(skb, rxm->offset + TLS_HEADER_SIZE, @@ -1345,16 +1389,24 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, kfree(mem); return err; } - memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + if (tls_ctx->crypto_recv.info.version == TLS_1_3_VERSION) + memcpy(iv, tls_ctx->rx.iv, crypto_aead_ivsize(ctx->aead_recv)); + else + memcpy(iv, tls_ctx->rx.iv, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + + xor_iv_with_seq(tls_ctx->crypto_recv.info.version, iv, + tls_ctx->rx.rec_seq); /* Prepare AAD */ - tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size, + tls_make_aad(aad, rxm->full_len - tls_ctx->rx.overhead_size + + tls_ctx->rx.tail_size, tls_ctx->rx.rec_seq, tls_ctx->rx.rec_seq_size, - ctx->control); + ctx->control, + tls_ctx->crypto_recv.info.version); /* Prepare sgin */ sg_init_table(sgin, n_sgin); - sg_set_buf(&sgin[0], aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(&sgin[0], aad, tls_ctx->rx.aad_size); err = skb_to_sgvec(skb, &sgin[1], rxm->offset + tls_ctx->rx.prepend_size, rxm->full_len - tls_ctx->rx.prepend_size); @@ -1366,7 +1418,7 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, if (n_sgout) { if (out_iov) { sg_init_table(sgout, n_sgout); - sg_set_buf(&sgout[0], aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(&sgout[0], aad, tls_ctx->rx.aad_size); *chunk = 0; err = tls_setup_from_iter(sk, out_iov, data_len, @@ -1383,13 +1435,13 @@ static int decrypt_internal(struct sock *sk, struct sk_buff *skb, fallback_to_reg_recv: sgout = sgin; pages = 0; - *chunk = 0; + *chunk = data_len; *zc = false; } /* Prepare and submit AEAD request */ err = tls_do_decryption(sk, skb, sgin, sgout, iv, - data_len, aead_req, *zc); + data_len, aead_req, async); if (err == -EINPROGRESS) return err; @@ -1402,10 +1454,12 @@ fallback_to_reg_recv: } static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, - struct iov_iter *dest, int *chunk, bool *zc) + struct iov_iter *dest, int *chunk, bool *zc, + bool async) { struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + int version = tls_ctx->crypto_recv.info.version; struct strp_msg *rxm = strp_msg(skb); int err = 0; @@ -1415,23 +1469,26 @@ static int decrypt_skb_update(struct sock *sk, struct sk_buff *skb, return err; #endif if (!ctx->decrypted) { - err = decrypt_internal(sk, skb, dest, NULL, chunk, zc); + err = decrypt_internal(sk, skb, dest, NULL, chunk, zc, async); if (err < 0) { if (err == -EINPROGRESS) - tls_advance_record_sn(sk, &tls_ctx->rx); + tls_advance_record_sn(sk, &tls_ctx->rx, + version); return err; } + + rxm->full_len -= padding_length(ctx, tls_ctx, skb); + + rxm->offset += tls_ctx->rx.prepend_size; + rxm->full_len -= tls_ctx->rx.overhead_size; + tls_advance_record_sn(sk, &tls_ctx->rx, version); + ctx->decrypted = true; + ctx->saved_data_ready(sk); } else { *zc = false; } - rxm->offset += tls_ctx->rx.prepend_size; - rxm->full_len -= tls_ctx->rx.overhead_size; - tls_advance_record_sn(sk, &tls_ctx->rx); - ctx->decrypted = true; - ctx->saved_data_ready(sk); - return err; } @@ -1441,7 +1498,7 @@ int decrypt_skb(struct sock *sk, struct sk_buff *skb, bool zc = true; int chunk; - return decrypt_internal(sk, skb, NULL, sgout, &chunk, &zc); + return decrypt_internal(sk, skb, NULL, sgout, &chunk, &zc, false); } static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, @@ -1468,6 +1525,77 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, return true; } +/* This function traverses the rx_list in tls receive context to copies the + * decrypted data records into the buffer provided by caller zero copy is not + * true. Further, the records are removed from the rx_list if it is not a peek + * case and the record has been consumed completely. + */ +static int process_rx_list(struct tls_sw_context_rx *ctx, + struct msghdr *msg, + size_t skip, + size_t len, + bool zc, + bool is_peek) +{ + struct sk_buff *skb = skb_peek(&ctx->rx_list); + ssize_t copied = 0; + + while (skip && skb) { + struct strp_msg *rxm = strp_msg(skb); + + if (skip < rxm->full_len) + break; + + skip = skip - rxm->full_len; + skb = skb_peek_next(skb, &ctx->rx_list); + } + + while (len && skb) { + struct sk_buff *next_skb; + struct strp_msg *rxm = strp_msg(skb); + int chunk = min_t(unsigned int, rxm->full_len - skip, len); + + if (!zc || (rxm->full_len - skip) > len) { + int err = skb_copy_datagram_msg(skb, rxm->offset + skip, + msg, chunk); + if (err < 0) + return err; + } + + len = len - chunk; + copied = copied + chunk; + + /* Consume the data from record if it is non-peek case*/ + if (!is_peek) { + rxm->offset = rxm->offset + chunk; + rxm->full_len = rxm->full_len - chunk; + + /* Return if there is unconsumed data in the record */ + if (rxm->full_len - skip) + break; + } + + /* The remaining skip-bytes must lie in 1st record in rx_list. + * So from the 2nd record, 'skip' should be 0. + */ + skip = 0; + + if (msg) + msg->msg_flags |= MSG_EOR; + + next_skb = skb_peek_next(skb, &ctx->rx_list); + + if (!is_peek) { + skb_unlink(skb, &ctx->rx_list); + kfree_skb(skb); + } + + skb = next_skb; + } + + return copied; +} + int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, @@ -1478,7 +1606,8 @@ int tls_sw_recvmsg(struct sock *sk, struct tls_context *tls_ctx = tls_get_ctx(sk); struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_psock *psock; - unsigned char control; + unsigned char control = 0; + ssize_t decrypted = 0; struct strp_msg *rxm; struct sk_buff *skb; ssize_t copied = 0; @@ -1486,6 +1615,7 @@ int tls_sw_recvmsg(struct sock *sk, int target, err = 0; long timeo; bool is_kvec = iov_iter_is_kvec(&msg->msg_iter); + bool is_peek = flags & MSG_PEEK; int num_async = 0; flags |= nonblock; @@ -1496,12 +1626,29 @@ int tls_sw_recvmsg(struct sock *sk, psock = sk_psock_get(sk); lock_sock(sk); - target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + /* Process pending decrypted records. It must be non-zero-copy */ + err = process_rx_list(ctx, msg, 0, len, false, is_peek); + if (err < 0) { + tls_err_abort(sk, err); + goto end; + } else { + copied = err; + } + + len = len - copied; + if (len) { + target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + } else { + goto recv_end; + } + do { + bool retain_skb = false; bool zc = false; - bool async = false; + int to_decrypt; int chunk = 0; + bool async; skb = tls_wait_data(sk, psock, flags, timeo, &err); if (!skb) { @@ -1510,7 +1657,7 @@ int tls_sw_recvmsg(struct sock *sk, msg, len, flags); if (ret > 0) { - copied += ret; + decrypted += ret; len -= ret; continue; } @@ -1520,6 +1667,29 @@ int tls_sw_recvmsg(struct sock *sk, rxm = strp_msg(skb); + to_decrypt = rxm->full_len - tls_ctx->rx.overhead_size; + + if (to_decrypt <= len && !is_kvec && !is_peek && + ctx->control == TLS_RECORD_TYPE_DATA && + tls_ctx->crypto_recv.info.version != TLS_1_3_VERSION) + zc = true; + + /* Do not use async mode if record is non-data */ + if (ctx->control == TLS_RECORD_TYPE_DATA) + async = ctx->async_capable; + else + async = false; + + err = decrypt_skb_update(sk, skb, &msg->msg_iter, + &chunk, &zc, async); + if (err < 0 && err != -EINPROGRESS) { + tls_err_abort(sk, EBADMSG); + goto recv_end; + } + + if (err == -EINPROGRESS) + num_async++; + if (!cmsg) { int cerr; @@ -1537,70 +1707,55 @@ int tls_sw_recvmsg(struct sock *sk, goto recv_end; } - if (!ctx->decrypted) { - int to_copy = rxm->full_len - tls_ctx->rx.overhead_size; + if (async) + goto pick_next_record; - if (!is_kvec && to_copy <= len && - likely(!(flags & MSG_PEEK))) - zc = true; + if (!zc) { + if (rxm->full_len > len) { + retain_skb = true; + chunk = len; + } else { + chunk = rxm->full_len; + } - err = decrypt_skb_update(sk, skb, &msg->msg_iter, - &chunk, &zc); - if (err < 0 && err != -EINPROGRESS) { - tls_err_abort(sk, EBADMSG); + err = skb_copy_datagram_msg(skb, rxm->offset, + msg, chunk); + if (err < 0) goto recv_end; - } - if (err == -EINPROGRESS) { - async = true; - num_async++; - goto pick_next_record; + if (!is_peek) { + rxm->offset = rxm->offset + chunk; + rxm->full_len = rxm->full_len - chunk; } - - ctx->decrypted = true; } - if (!zc) { - chunk = min_t(unsigned int, rxm->full_len, len); +pick_next_record: + if (chunk > len) + chunk = len; - err = skb_copy_datagram_msg(skb, rxm->offset, msg, - chunk); - if (err < 0) - goto recv_end; + decrypted += chunk; + len -= chunk; + + /* For async or peek case, queue the current skb */ + if (async || is_peek || retain_skb) { + skb_queue_tail(&ctx->rx_list, skb); + skb = NULL; } -pick_next_record: - copied += chunk; - len -= chunk; - if (likely(!(flags & MSG_PEEK))) { - u8 control = ctx->control; - - /* For async, drop current skb reference */ - if (async) - skb = NULL; - - if (tls_sw_advance_skb(sk, skb, chunk)) { - /* Return full control message to - * userspace before trying to parse - * another message type - */ - msg->msg_flags |= MSG_EOR; - if (control != TLS_RECORD_TYPE_DATA) - goto recv_end; - } else { - break; - } - } else { - /* MSG_PEEK right now cannot look beyond current skb - * from strparser, meaning we cannot advance skb here - * and thus unpause strparser since we'd loose original - * one. + if (tls_sw_advance_skb(sk, skb, chunk)) { + /* Return full control message to + * userspace before trying to parse + * another message type */ + msg->msg_flags |= MSG_EOR; + if (ctx->control != TLS_RECORD_TYPE_DATA) + goto recv_end; + } else { break; } /* If we have a new message from strparser, continue now. */ - if (copied >= target && !ctx->recv_pkt) + if (decrypted >= target && !ctx->recv_pkt) break; } while (len); @@ -1614,13 +1769,33 @@ recv_end: /* one of async decrypt failed */ tls_err_abort(sk, err); copied = 0; + decrypted = 0; + goto end; } } else { reinit_completion(&ctx->async_wait.completion); } WRITE_ONCE(ctx->async_notify, false); + + /* Drain records from the rx_list & copy if required */ + if (is_peek || is_kvec) + err = process_rx_list(ctx, msg, copied, + decrypted, false, is_peek); + else + err = process_rx_list(ctx, msg, 0, + decrypted, true, is_peek); + if (err < 0) { + tls_err_abort(sk, err); + copied = 0; + goto end; + } + + WARN_ON(decrypted != err); } + copied += decrypted; + +end: release_sock(sk); if (psock) sk_psock_put(sk, psock); @@ -1650,14 +1825,14 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, if (!skb) goto splice_read_end; - /* splice does not support reading control messages */ - if (ctx->control != TLS_RECORD_TYPE_DATA) { - err = -ENOTSUPP; - goto splice_read_end; - } - if (!ctx->decrypted) { - err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc); + err = decrypt_skb_update(sk, skb, NULL, &chunk, &zc, false); + + /* splice does not support reading control messages */ + if (ctx->control != TLS_RECORD_TYPE_DATA) { + err = -ENOTSUPP; + goto splice_read_end; + } if (err < 0) { tls_err_abort(sk, EBADMSG); @@ -1726,9 +1901,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) data_len = ((header[4] & 0xFF) | (header[3] << 8)); - cipher_overhead = tls_ctx->rx.tag_size + tls_ctx->rx.iv_size; + cipher_overhead = tls_ctx->rx.tag_size; + if (tls_ctx->crypto_recv.info.version != TLS_1_3_VERSION) + cipher_overhead += tls_ctx->rx.iv_size; - if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead) { + if (data_len > TLS_MAX_PAYLOAD_SIZE + cipher_overhead + + tls_ctx->rx.tail_size) { ret = -EMSGSIZE; goto read_failure; } @@ -1737,12 +1915,12 @@ static int tls_read_size(struct strparser *strp, struct sk_buff *skb) goto read_failure; } - if (header[1] != TLS_VERSION_MINOR(tls_ctx->crypto_recv.info.version) || - header[2] != TLS_VERSION_MAJOR(tls_ctx->crypto_recv.info.version)) { + /* Note that both TLS1.3 and TLS1.2 use TLS_1_2 version here */ + if (header[1] != TLS_1_2_VERSION_MINOR || + header[2] != TLS_1_2_VERSION_MAJOR) { ret = -EINVAL; goto read_failure; } - #ifdef CONFIG_TLS_DEVICE handle_device_resync(strp->sk, TCP_SKB_CB(skb)->seq + rxm->offset, *(u64*)tls_ctx->rx.rec_seq); @@ -1846,6 +2024,7 @@ void tls_sw_release_resources_rx(struct sock *sk) if (ctx->aead_recv) { kfree_skb(ctx->recv_pkt); ctx->recv_pkt = NULL; + skb_queue_purge(&ctx->rx_list); crypto_free_aead(ctx->aead_recv); strp_stop(&ctx->strp); write_lock_bh(&sk->sk_callback_lock); @@ -1889,13 +2068,16 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) { struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; + struct tls12_crypto_info_aes_gcm_256 *gcm_256_info; struct tls_sw_context_tx *sw_ctx_tx = NULL; struct tls_sw_context_rx *sw_ctx_rx = NULL; struct cipher_context *cctx; struct crypto_aead **aead; struct strp_callbacks cb; u16 nonce_size, tag_size, iv_size, rec_seq_size; - char *iv, *rec_seq; + struct crypto_tfm *tfm; + char *iv, *rec_seq, *key, *salt; + size_t keysize; int rc = 0; if (!ctx) { @@ -1941,6 +2123,7 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) crypto_init_wait(&sw_ctx_rx->async_wait); crypto_info = &ctx->crypto_recv.info; cctx = &ctx->rx; + skb_queue_head_init(&sw_ctx_rx->rx_list); aead = &sw_ctx_rx->aead_recv; } @@ -1955,6 +2138,24 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; gcm_128_info = (struct tls12_crypto_info_aes_gcm_128 *)crypto_info; + keysize = TLS_CIPHER_AES_GCM_128_KEY_SIZE; + key = gcm_128_info->key; + salt = gcm_128_info->salt; + break; + } + case TLS_CIPHER_AES_GCM_256: { + nonce_size = TLS_CIPHER_AES_GCM_256_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_256_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_256_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_256_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_256 *)crypto_info)->rec_seq; + gcm_256_info = + (struct tls12_crypto_info_aes_gcm_256 *)crypto_info; + keysize = TLS_CIPHER_AES_GCM_256_KEY_SIZE; + key = gcm_256_info->key; + salt = gcm_256_info->salt; break; } default: @@ -1968,9 +2169,19 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_priv; } + if (crypto_info->version == TLS_1_3_VERSION) { + nonce_size = 0; + cctx->aad_size = TLS_HEADER_SIZE; + cctx->tail_size = 1; + } else { + cctx->aad_size = TLS_AAD_SPACE_SIZE; + cctx->tail_size = 0; + } + cctx->prepend_size = TLS_HEADER_SIZE + nonce_size; cctx->tag_size = tag_size; - cctx->overhead_size = cctx->prepend_size + cctx->tag_size; + cctx->overhead_size = cctx->prepend_size + cctx->tag_size + + cctx->tail_size; cctx->iv_size = iv_size; cctx->iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, GFP_KERNEL); @@ -1978,7 +2189,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) rc = -ENOMEM; goto free_priv; } - memcpy(cctx->iv, gcm_128_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + /* Note: 128 & 256 bit salt are the same size */ + memcpy(cctx->iv, salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); memcpy(cctx->iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); cctx->rec_seq_size = rec_seq_size; cctx->rec_seq = kmemdup(rec_seq, rec_seq_size, GFP_KERNEL); @@ -1998,8 +2210,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) ctx->push_pending_record = tls_sw_push_pending_record; - rc = crypto_aead_setkey(*aead, gcm_128_info->key, - TLS_CIPHER_AES_GCM_128_KEY_SIZE); + rc = crypto_aead_setkey(*aead, key, keysize); + if (rc) goto free_aead; @@ -2008,6 +2220,14 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto free_aead; if (sw_ctx_rx) { + tfm = crypto_aead_tfm(sw_ctx_rx->aead_recv); + + if (crypto_info->version == TLS_1_3_VERSION) + sw_ctx_rx->async_capable = false; + else + sw_ctx_rx->async_capable = + tfm->__crt_alg->cra_flags & CRYPTO_ALG_ASYNC; + /* Set up strparser */ memset(&cb, 0, sizeof(cb)); cb.rcv_msg = tls_queue; diff --git a/net/vmw_vsock/af_vsock.c b/net/vmw_vsock/af_vsock.c index 43a1dec08825..d892000770cf 100644 --- a/net/vmw_vsock/af_vsock.c +++ b/net/vmw_vsock/af_vsock.c @@ -505,7 +505,7 @@ out: static int __vsock_bind_stream(struct vsock_sock *vsk, struct sockaddr_vm *addr) { - static u32 port = 0; + static u32 port; struct sockaddr_vm new_addr; if (!port) @@ -1439,7 +1439,7 @@ static int vsock_stream_setsockopt(struct socket *sock, break; case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct timeval tv; + struct __kernel_old_timeval tv; COPY_IN(tv); if (tv.tv_sec >= 0 && tv.tv_usec < USEC_PER_SEC && tv.tv_sec < (MAX_SCHEDULE_TIMEOUT / HZ - 1)) { @@ -1517,7 +1517,7 @@ static int vsock_stream_getsockopt(struct socket *sock, break; case SO_VM_SOCKETS_CONNECT_TIMEOUT: { - struct timeval tv; + struct __kernel_old_timeval tv; tv.tv_sec = vsk->connect_timeout / HZ; tv.tv_usec = (vsk->connect_timeout - diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index d91a408db113..e36437abc45a 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -259,15 +259,13 @@ nl80211_pmsr_ftm_req_attr_policy[NL80211_PMSR_FTM_REQ_ATTR_MAX + 1] = { static const struct nla_policy nl80211_pmsr_req_data_policy[NL80211_PMSR_TYPE_MAX + 1] = { [NL80211_PMSR_TYPE_FTM] = - NLA_POLICY_NESTED(NL80211_PMSR_FTM_REQ_ATTR_MAX, - nl80211_pmsr_ftm_req_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_ftm_req_attr_policy), }; static const struct nla_policy nl80211_pmsr_req_attr_policy[NL80211_PMSR_REQ_ATTR_MAX + 1] = { [NL80211_PMSR_REQ_ATTR_DATA] = - NLA_POLICY_NESTED(NL80211_PMSR_TYPE_MAX, - nl80211_pmsr_req_data_policy), + NLA_POLICY_NESTED(nl80211_pmsr_req_data_policy), [NL80211_PMSR_REQ_ATTR_GET_AP_TSF] = { .type = NLA_FLAG }, }; @@ -280,8 +278,7 @@ nl80211_psmr_peer_attr_policy[NL80211_PMSR_PEER_ATTR_MAX + 1] = { */ [NL80211_PMSR_PEER_ATTR_CHAN] = { .type = NLA_NESTED }, [NL80211_PMSR_PEER_ATTR_REQ] = - NLA_POLICY_NESTED(NL80211_PMSR_REQ_ATTR_MAX, - nl80211_pmsr_req_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_req_attr_policy), [NL80211_PMSR_PEER_ATTR_RESP] = { .type = NLA_REJECT }, }; @@ -292,8 +289,7 @@ nl80211_pmsr_attr_policy[NL80211_PMSR_ATTR_MAX + 1] = { [NL80211_PMSR_ATTR_RANDOMIZE_MAC_ADDR] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_TYPE_CAPA] = { .type = NLA_REJECT }, [NL80211_PMSR_ATTR_PEERS] = - NLA_POLICY_NESTED_ARRAY(NL80211_PMSR_PEER_ATTR_MAX, - nl80211_psmr_peer_attr_policy), + NLA_POLICY_NESTED_ARRAY(nl80211_psmr_peer_attr_policy), }; const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { @@ -555,8 +551,8 @@ const struct nla_policy nl80211_policy[NUM_NL80211_ATTR] = { }, [NL80211_ATTR_TIMEOUT] = NLA_POLICY_MIN(NLA_U32, 1), [NL80211_ATTR_PEER_MEASUREMENTS] = - NLA_POLICY_NESTED(NL80211_PMSR_ATTR_MAX, - nl80211_pmsr_attr_policy), + NLA_POLICY_NESTED(nl80211_pmsr_attr_policy), + [NL80211_ATTR_AIRTIME_WEIGHT] = NLA_POLICY_MIN(NLA_U16, 1), }; /* policy for the key attributes */ @@ -2278,6 +2274,15 @@ static int nl80211_send_wiphy(struct cfg80211_registered_device *rdev, if (nl80211_send_pmsr_capa(rdev, msg)) goto nla_put_failure; + state->split_start++; + break; + case 15: + if (rdev->wiphy.akm_suites && + nla_put(msg, NL80211_ATTR_AKM_SUITES, + sizeof(u32) * rdev->wiphy.n_akm_suites, + rdev->wiphy.akm_suites)) + goto nla_put_failure; + /* done */ state->split_start = 0; break; @@ -4540,6 +4545,9 @@ static int nl80211_start_ap(struct sk_buff *skb, struct genl_info *info) nl80211_calculate_ap_params(¶ms); + if (info->attrs[NL80211_ATTR_EXTERNAL_AUTH_SUPPORT]) + params.flags |= AP_SETTINGS_EXTERNAL_AUTH_SUPPORT; + wdev_lock(wdev); err = rdev_start_ap(rdev, dev, ¶ms); if (!err) { @@ -4851,6 +4859,11 @@ static int nl80211_send_station(struct sk_buff *msg, u32 cmd, u32 portid, PUT_SINFO(PLID, plid, u16); PUT_SINFO(PLINK_STATE, plink_state, u8); PUT_SINFO_U64(RX_DURATION, rx_duration); + PUT_SINFO_U64(TX_DURATION, tx_duration); + + if (wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + PUT_SINFO(AIRTIME_WEIGHT, airtime_weight, u16); switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: @@ -5470,6 +5483,15 @@ static int nl80211_set_station(struct sk_buff *skb, struct genl_info *info) nla_get_u8(info->attrs[NL80211_ATTR_OPMODE_NOTIF]); } + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) + params.airtime_weight = + nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); + + if (params.airtime_weight && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + return -EOPNOTSUPP; + /* Include parameters for TDLS peer (will check later) */ err = nl80211_set_station_tdls(info, ¶ms); if (err) @@ -5598,6 +5620,15 @@ static int nl80211_new_station(struct sk_buff *skb, struct genl_info *info) params.plink_action = nla_get_u8(info->attrs[NL80211_ATTR_STA_PLINK_ACTION]); + if (info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]) + params.airtime_weight = + nla_get_u16(info->attrs[NL80211_ATTR_AIRTIME_WEIGHT]); + + if (params.airtime_weight && + !wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AIRTIME_FAIRNESS)) + return -EOPNOTSUPP; + err = nl80211_parse_sta_channel_info(info, ¶ms); if (err) return err; @@ -5803,7 +5834,13 @@ static int nl80211_send_mpath(struct sk_buff *msg, u32 portid, u32 seq, pinfo->discovery_timeout)) || ((pinfo->filled & MPATH_INFO_DISCOVERY_RETRIES) && nla_put_u8(msg, NL80211_MPATH_INFO_DISCOVERY_RETRIES, - pinfo->discovery_retries))) + pinfo->discovery_retries)) || + ((pinfo->filled & MPATH_INFO_HOP_COUNT) && + nla_put_u8(msg, NL80211_MPATH_INFO_HOP_COUNT, + pinfo->hop_count)) || + ((pinfo->filled & MPATH_INFO_PATH_CHANGE) && + nla_put_u32(msg, NL80211_MPATH_INFO_PATH_CHANGE, + pinfo->path_change_count))) goto nla_put_failure; nla_nest_end(msg, pinfoattr); @@ -9857,7 +9894,10 @@ static int nl80211_setdel_pmksa(struct sk_buff *skb, struct genl_info *info) } if (dev->ieee80211_ptr->iftype != NL80211_IFTYPE_STATION && - dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT) + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_CLIENT && + !(dev->ieee80211_ptr->iftype == NL80211_IFTYPE_AP && + wiphy_ext_feature_isset(&rdev->wiphy, + NL80211_EXT_FEATURE_AP_PMKSA_CACHING))) return -EOPNOTSUPP; switch (info->genlhdr->cmd) { @@ -13047,7 +13087,9 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) if (!rdev->ops->external_auth) return -EOPNOTSUPP; - if (!info->attrs[NL80211_ATTR_SSID]) + if (!info->attrs[NL80211_ATTR_SSID] && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_AP && + dev->ieee80211_ptr->iftype != NL80211_IFTYPE_P2P_GO) return -EINVAL; if (!info->attrs[NL80211_ATTR_BSSID]) @@ -13058,18 +13100,24 @@ static int nl80211_external_auth(struct sk_buff *skb, struct genl_info *info) memset(¶ms, 0, sizeof(params)); - params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); - if (params.ssid.ssid_len == 0 || - params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) - return -EINVAL; - memcpy(params.ssid.ssid, nla_data(info->attrs[NL80211_ATTR_SSID]), - params.ssid.ssid_len); + if (info->attrs[NL80211_ATTR_SSID]) { + params.ssid.ssid_len = nla_len(info->attrs[NL80211_ATTR_SSID]); + if (params.ssid.ssid_len == 0 || + params.ssid.ssid_len > IEEE80211_MAX_SSID_LEN) + return -EINVAL; + memcpy(params.ssid.ssid, + nla_data(info->attrs[NL80211_ATTR_SSID]), + params.ssid.ssid_len); + } memcpy(params.bssid, nla_data(info->attrs[NL80211_ATTR_BSSID]), ETH_ALEN); params.status = nla_get_u16(info->attrs[NL80211_ATTR_STATUS_CODE]); + if (info->attrs[NL80211_ATTR_PMKID]) + params.pmkid = nla_data(info->attrs[NL80211_ATTR_PMKID]); + return rdev_external_auth(rdev, dev, ¶ms); } diff --git a/net/wireless/reg.c b/net/wireless/reg.c index dd58b9909ac9..adfa58fa6536 100644 --- a/net/wireless/reg.c +++ b/net/wireless/reg.c @@ -2729,9 +2729,7 @@ static void notify_self_managed_wiphys(struct regulatory_request *request) list_for_each_entry(rdev, &cfg80211_rdev_list, list) { wiphy = &rdev->wiphy; if (wiphy->regulatory_flags & REGULATORY_WIPHY_SELF_MANAGED && - request->initiator == NL80211_REGDOM_SET_BY_USER && - request->user_reg_hint_type == - NL80211_USER_REG_HINT_CELL_BASE) + request->initiator == NL80211_REGDOM_SET_BY_USER) reg_call_notifier(wiphy, request); } } diff --git a/net/wireless/wext-compat.c b/net/wireless/wext-compat.c index 06943d9c9835..d522787c7354 100644 --- a/net/wireless/wext-compat.c +++ b/net/wireless/wext-compat.c @@ -1337,6 +1337,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sig + 110; break; } + /* fall through */ case CFG80211_SIGNAL_TYPE_UNSPEC: if (sinfo.filled & BIT_ULL(NL80211_STA_INFO_SIGNAL)) { wstats.qual.updated |= IW_QUAL_LEVEL_UPDATED; @@ -1345,6 +1346,7 @@ static struct iw_statistics *cfg80211_wireless_stats(struct net_device *dev) wstats.qual.qual = sinfo.signal; break; } + /* fall through */ default: wstats.qual.updated |= IW_QUAL_LEVEL_INVALID; wstats.qual.updated |= IW_QUAL_QUAL_INVALID; diff --git a/net/xdp/Kconfig b/net/xdp/Kconfig index 90e4a7152854..0255b33cff4b 100644 --- a/net/xdp/Kconfig +++ b/net/xdp/Kconfig @@ -5,3 +5,11 @@ config XDP_SOCKETS help XDP sockets allows a channel between XDP programs and userspace applications. + +config XDP_SOCKETS_DIAG + tristate "XDP sockets: monitoring interface" + depends on XDP_SOCKETS + default n + help + Support for PF_XDP sockets monitoring interface used by the ss tool. + If unsure, say Y. diff --git a/net/xdp/Makefile b/net/xdp/Makefile index 04f073146256..59dbfdf93dca 100644 --- a/net/xdp/Makefile +++ b/net/xdp/Makefile @@ -1 +1,2 @@ obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o +obj-$(CONFIG_XDP_SOCKETS_DIAG) += xsk_diag.o diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c index d4de871e7d4d..5ab236c5c9a5 100644 --- a/net/xdp/xdp_umem.c +++ b/net/xdp/xdp_umem.c @@ -13,12 +13,15 @@ #include <linux/mm.h> #include <linux/netdevice.h> #include <linux/rtnetlink.h> +#include <linux/idr.h> #include "xdp_umem.h" #include "xsk_queue.h" #define XDP_UMEM_MIN_CHUNK_SIZE 2048 +static DEFINE_IDA(umem_ida); + void xdp_add_sk_umem(struct xdp_umem *umem, struct xdp_sock *xs) { unsigned long flags; @@ -67,6 +70,7 @@ struct xdp_umem *xdp_get_umem_from_qid(struct net_device *dev, return NULL; } +EXPORT_SYMBOL(xdp_get_umem_from_qid); static void xdp_clear_umem_at_qid(struct net_device *dev, u16 queue_id) { @@ -193,6 +197,8 @@ static void xdp_umem_release(struct xdp_umem *umem) xdp_umem_clear_dev(umem); + ida_simple_remove(&umem_ida, umem->id); + if (umem->fq) { xskq_destroy(umem->fq); umem->fq = NULL; @@ -399,8 +405,16 @@ struct xdp_umem *xdp_umem_create(struct xdp_umem_reg *mr) if (!umem) return ERR_PTR(-ENOMEM); + err = ida_simple_get(&umem_ida, 0, 0, GFP_KERNEL); + if (err < 0) { + kfree(umem); + return ERR_PTR(err); + } + umem->id = err; + err = xdp_umem_reg(umem, mr); if (err) { + ida_simple_remove(&umem_ida, umem->id); kfree(umem); return ERR_PTR(err); } diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c index a03268454a27..949d3bbccb2f 100644 --- a/net/xdp/xsk.c +++ b/net/xdp/xsk.c @@ -27,14 +27,10 @@ #include "xsk_queue.h" #include "xdp_umem.h" +#include "xsk.h" #define TX_BATCH_SIZE 16 -static struct xdp_sock *xdp_sk(struct sock *sk) -{ - return (struct xdp_sock *)sk; -} - bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) { return READ_ONCE(xs->rx) && READ_ONCE(xs->umem) && @@ -350,6 +346,10 @@ static int xsk_release(struct socket *sock) net = sock_net(sk); + mutex_lock(&net->xdp.lock); + sk_del_node_init_rcu(sk); + mutex_unlock(&net->xdp.lock); + local_bh_disable(); sock_prot_inuse_add(net, sk->sk_prot, -1); local_bh_enable(); @@ -746,6 +746,10 @@ static int xsk_create(struct net *net, struct socket *sock, int protocol, mutex_init(&xs->mutex); spin_lock_init(&xs->tx_completion_lock); + mutex_lock(&net->xdp.lock); + sk_add_node_rcu(sk, &net->xdp.list); + mutex_unlock(&net->xdp.lock); + local_bh_disable(); sock_prot_inuse_add(net, &xsk_proto, 1); local_bh_enable(); @@ -759,6 +763,23 @@ static const struct net_proto_family xsk_family_ops = { .owner = THIS_MODULE, }; +static int __net_init xsk_net_init(struct net *net) +{ + mutex_init(&net->xdp.lock); + INIT_HLIST_HEAD(&net->xdp.list); + return 0; +} + +static void __net_exit xsk_net_exit(struct net *net) +{ + WARN_ON_ONCE(!hlist_empty(&net->xdp.list)); +} + +static struct pernet_operations xsk_net_ops = { + .init = xsk_net_init, + .exit = xsk_net_exit, +}; + static int __init xsk_init(void) { int err; @@ -771,8 +792,13 @@ static int __init xsk_init(void) if (err) goto out_proto; + err = register_pernet_subsys(&xsk_net_ops); + if (err) + goto out_sk; return 0; +out_sk: + sock_unregister(PF_XDP); out_proto: proto_unregister(&xsk_proto); out: diff --git a/net/xdp/xsk.h b/net/xdp/xsk.h new file mode 100644 index 000000000000..ba8120610426 --- /dev/null +++ b/net/xdp/xsk.h @@ -0,0 +1,12 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2019 Intel Corporation. */ + +#ifndef XSK_H_ +#define XSK_H_ + +static inline struct xdp_sock *xdp_sk(struct sock *sk) +{ + return (struct xdp_sock *)sk; +} + +#endif /* XSK_H_ */ diff --git a/net/xdp/xsk_diag.c b/net/xdp/xsk_diag.c new file mode 100644 index 000000000000..661d007c3b28 --- /dev/null +++ b/net/xdp/xsk_diag.c @@ -0,0 +1,191 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP sockets monitoring support + * + * Copyright(c) 2019 Intel Corporation. + * + * Author: Björn Töpel <bjorn.topel@intel.com> + */ + +#include <linux/module.h> +#include <net/xdp_sock.h> +#include <linux/xdp_diag.h> +#include <linux/sock_diag.h> + +#include "xsk_queue.h" +#include "xsk.h" + +static int xsk_diag_put_info(const struct xdp_sock *xs, struct sk_buff *nlskb) +{ + struct xdp_diag_info di = {}; + + di.ifindex = xs->dev ? xs->dev->ifindex : 0; + di.queue_id = xs->queue_id; + return nla_put(nlskb, XDP_DIAG_INFO, sizeof(di), &di); +} + +static int xsk_diag_put_ring(const struct xsk_queue *queue, int nl_type, + struct sk_buff *nlskb) +{ + struct xdp_diag_ring dr = {}; + + dr.entries = queue->nentries; + return nla_put(nlskb, nl_type, sizeof(dr), &dr); +} + +static int xsk_diag_put_rings_cfg(const struct xdp_sock *xs, + struct sk_buff *nlskb) +{ + int err = 0; + + if (xs->rx) + err = xsk_diag_put_ring(xs->rx, XDP_DIAG_RX_RING, nlskb); + if (!err && xs->tx) + err = xsk_diag_put_ring(xs->tx, XDP_DIAG_TX_RING, nlskb); + return err; +} + +static int xsk_diag_put_umem(const struct xdp_sock *xs, struct sk_buff *nlskb) +{ + struct xdp_umem *umem = xs->umem; + struct xdp_diag_umem du = {}; + int err; + + if (!umem) + return 0; + + du.id = umem->id; + du.size = umem->size; + du.num_pages = umem->npgs; + du.chunk_size = (__u32)(~umem->chunk_mask + 1); + du.headroom = umem->headroom; + du.ifindex = umem->dev ? umem->dev->ifindex : 0; + du.queue_id = umem->queue_id; + du.flags = 0; + if (umem->zc) + du.flags |= XDP_DU_F_ZEROCOPY; + du.refs = refcount_read(&umem->users); + + err = nla_put(nlskb, XDP_DIAG_UMEM, sizeof(du), &du); + + if (!err && umem->fq) + err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_FILL_RING, nlskb); + if (!err && umem->cq) { + err = xsk_diag_put_ring(xs->tx, XDP_DIAG_UMEM_COMPLETION_RING, + nlskb); + } + return err; +} + +static int xsk_diag_fill(struct sock *sk, struct sk_buff *nlskb, + struct xdp_diag_req *req, + struct user_namespace *user_ns, + u32 portid, u32 seq, u32 flags, int sk_ino) +{ + struct xdp_sock *xs = xdp_sk(sk); + struct xdp_diag_msg *msg; + struct nlmsghdr *nlh; + + nlh = nlmsg_put(nlskb, portid, seq, SOCK_DIAG_BY_FAMILY, sizeof(*msg), + flags); + if (!nlh) + return -EMSGSIZE; + + msg = nlmsg_data(nlh); + memset(msg, 0, sizeof(*msg)); + msg->xdiag_family = AF_XDP; + msg->xdiag_type = sk->sk_type; + msg->xdiag_ino = sk_ino; + sock_diag_save_cookie(sk, msg->xdiag_cookie); + + if ((req->xdiag_show & XDP_SHOW_INFO) && xsk_diag_put_info(xs, nlskb)) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_INFO) && + nla_put_u32(nlskb, XDP_DIAG_UID, + from_kuid_munged(user_ns, sock_i_uid(sk)))) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_RING_CFG) && + xsk_diag_put_rings_cfg(xs, nlskb)) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_UMEM) && + xsk_diag_put_umem(xs, nlskb)) + goto out_nlmsg_trim; + + if ((req->xdiag_show & XDP_SHOW_MEMINFO) && + sock_diag_put_meminfo(sk, nlskb, XDP_DIAG_MEMINFO)) + goto out_nlmsg_trim; + + nlmsg_end(nlskb, nlh); + return 0; + +out_nlmsg_trim: + nlmsg_cancel(nlskb, nlh); + return -EMSGSIZE; +} + +static int xsk_diag_dump(struct sk_buff *nlskb, struct netlink_callback *cb) +{ + struct xdp_diag_req *req = nlmsg_data(cb->nlh); + struct net *net = sock_net(nlskb->sk); + int num = 0, s_num = cb->args[0]; + struct sock *sk; + + mutex_lock(&net->xdp.lock); + + sk_for_each(sk, &net->xdp.list) { + if (!net_eq(sock_net(sk), net)) + continue; + if (num++ < s_num) + continue; + + if (xsk_diag_fill(sk, nlskb, req, + sk_user_ns(NETLINK_CB(cb->skb).sk), + NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + sock_i_ino(sk)) < 0) { + num--; + break; + } + } + + mutex_unlock(&net->xdp.lock); + cb->args[0] = num; + return nlskb->len; +} + +static int xsk_diag_handler_dump(struct sk_buff *nlskb, struct nlmsghdr *hdr) +{ + struct netlink_dump_control c = { .dump = xsk_diag_dump }; + int hdrlen = sizeof(struct xdp_diag_req); + struct net *net = sock_net(nlskb->sk); + + if (nlmsg_len(hdr) < hdrlen) + return -EINVAL; + + if (!(hdr->nlmsg_flags & NLM_F_DUMP)) + return -EOPNOTSUPP; + + return netlink_dump_start(net->diag_nlsk, nlskb, hdr, &c); +} + +static const struct sock_diag_handler xsk_diag_handler = { + .family = AF_XDP, + .dump = xsk_diag_handler_dump, +}; + +static int __init xsk_diag_init(void) +{ + return sock_diag_register(&xsk_diag_handler); +} + +static void __exit xsk_diag_exit(void) +{ + sock_diag_unregister(&xsk_diag_handler); +} + +module_init(xsk_diag_init); +module_exit(xsk_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, AF_XDP); |