diff options
| author | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-03 17:08:17 +0200 |
|---|---|---|
| committer | Linus Torvalds <torvalds@linux-foundation.org> | 2015-09-03 17:08:17 +0200 |
| commit | dd5cdb48edfd34401799056a9acf61078d773f90 (patch) | |
| tree | 8e251fb4a4c196540fe9b6a6d8b13275f93a057c /net/ipv4 | |
| parent | Merge tag 'dm-4.3-changes' of git://git.kernel.org/pub/scm/linux/kernel/git/d... (diff) | |
| parent | netfilter: nf_conntrack: make nf_ct_zone_dflt built-in (diff) | |
| download | linux-dd5cdb48edfd34401799056a9acf61078d773f90.tar.xz linux-dd5cdb48edfd34401799056a9acf61078d773f90.zip | |
Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next
Pull networking updates from David Miller:
"Another merge window, another set of networking changes. I've heard
rumblings that the lightweight tunnels infrastructure has been voted
networking change of the year. But what do I know?
1) Add conntrack support to openvswitch, from Joe Stringer.
2) Initial support for VRF (Virtual Routing and Forwarding), which
allows the segmentation of routing paths without using multiple
devices. There are some semantic kinks to work out still, but
this is a reasonably strong foundation. From David Ahern.
3) Remove spinlock fro act_bpf fast path, from Alexei Starovoitov.
4) Ignore route nexthops with a link down state in ipv6, just like
ipv4. From Andy Gospodarek.
5) Remove spinlock from fast path of act_gact and act_mirred, from
Eric Dumazet.
6) Document the DSA layer, from Florian Fainelli.
7) Add netconsole support to bcmgenet, systemport, and DSA. Also
from Florian Fainelli.
8) Add Mellanox Switch Driver and core infrastructure, from Jiri
Pirko.
9) Add support for "light weight tunnels", which allow for
encapsulation and decapsulation without bearing the overhead of a
full blown netdevice. From Thomas Graf, Jiri Benc, and a cast of
others.
10) Add Identifier Locator Addressing support for ipv6, from Tom
Herbert.
11) Support fragmented SKBs in iwlwifi, from Johannes Berg.
12) Allow perf PMUs to be accessed from eBPF programs, from Kaixu Xia.
13) Add BQL support to 3c59x driver, from Loganaden Velvindron.
14) Stop using a zero TX queue length to mean that a device shouldn't
have a qdisc attached, use an explicit flag instead. From Phil
Sutter.
15) Use generic geneve netdevice infrastructure in openvswitch, from
Pravin B Shelar.
16) Add infrastructure to avoid re-forwarding a packet in software
that was already forwarded by a hardware switch. From Scott
Feldman.
17) Allow AF_PACKET fanout function to be implemented in a bpf
program, from Willem de Bruijn"
* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1458 commits)
netfilter: nf_conntrack: make nf_ct_zone_dflt built-in
netfilter: nf_dup{4, 6}: fix build error when nf_conntrack disabled
net: fec: clear receive interrupts before processing a packet
ipv6: fix exthdrs offload registration in out_rt path
xen-netback: add support for multicast control
bgmac: Update fixed_phy_register()
sock, diag: fix panic in sock_diag_put_filterinfo
flow_dissector: Use 'const' where possible.
flow_dissector: Fix function argument ordering dependency
ixgbe: Resolve "initialized field overwritten" warnings
ixgbe: Remove bimodal SR-IOV disabling
ixgbe: Add support for reporting 2.5G link speed
ixgbe: fix bounds checking in ixgbe_setup_tc for 82598
ixgbe: support for ethtool set_rxfh
ixgbe: Avoid needless PHY access on copper phys
ixgbe: cleanup to use cached mask value
ixgbe: Remove second instance of lan_id variable
ixgbe: use kzalloc for allocating one thing
flow: Move __get_hash_from_flowi{4,6} into flow_dissector.c
ixgbe: Remove unused PCI bus types
...
Diffstat (limited to 'net/ipv4')
62 files changed, 1682 insertions, 1188 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 6fb3c90ad726..416dfa004cfb 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -331,20 +331,6 @@ config NET_FOU_IP_TUNNELS When this option is enabled IP tunnels can be configured to use FOU or GUE encapsulation. -config GENEVE_CORE - tristate "Generic Network Virtualization Encapsulation library" - depends on INET - select NET_UDP_TUNNEL - ---help--- - This allows one to create Geneve virtual interfaces that provide - Layer 2 Networks over Layer 3 Networks. Geneve is often used - to tunnel virtual network infrastructure in virtualized environments. - For more information see: - http://tools.ietf.org/html/draft-gross-geneve-01 - - To compile this driver as a module, choose M here: the module - - config INET_AH tristate "IP: AH transformation" select XFRM_ALGO diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index efc43f300b8c..89aacb630a53 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -57,7 +57,6 @@ obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o obj-$(CONFIG_MEMCG_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o -obj-$(CONFIG_GENEVE_CORE) += geneve_core.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ xfrm4_output.o xfrm4_protocol.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 9532ee87151f..1d0c3adb6f34 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -112,12 +112,14 @@ #include <net/raw.h> #include <net/icmp.h> #include <net/inet_common.h> +#include <net/ip_tunnels.h> #include <net/xfrm.h> #include <net/net_namespace.h> #include <net/secure_seq.h> #ifdef CONFIG_IP_MROUTE #include <linux/mroute.h> #endif +#include <net/vrf.h> /* The inetsw table contains everything that inet_create needs to @@ -426,6 +428,7 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) struct net *net = sock_net(sk); unsigned short snum; int chk_addr_ret; + u32 tb_id = RT_TABLE_LOCAL; int err; /* If the socket has its own bind function then use it. (RAW) */ @@ -447,7 +450,8 @@ int inet_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) goto out; } - chk_addr_ret = inet_addr_type(net, addr->sin_addr.s_addr); + tb_id = vrf_dev_table_ifindex(net, sk->sk_bound_dev_if) ? : tb_id; + chk_addr_ret = inet_addr_type_table(net, addr->sin_addr.s_addr, tb_id); /* Not specified by any standard per-se, however it breaks too * many applications when removed. It is unfortunate since @@ -1448,38 +1452,51 @@ int inet_ctl_sock_create(struct sock **sk, unsigned short family, } EXPORT_SYMBOL_GPL(inet_ctl_sock_create); +u64 snmp_get_cpu_field(void __percpu *mib, int cpu, int offt) +{ + return *(((unsigned long *)per_cpu_ptr(mib, cpu)) + offt); +} +EXPORT_SYMBOL_GPL(snmp_get_cpu_field); + unsigned long snmp_fold_field(void __percpu *mib, int offt) { unsigned long res = 0; int i; for_each_possible_cpu(i) - res += *(((unsigned long *) per_cpu_ptr(mib, i)) + offt); + res += snmp_get_cpu_field(mib, i, offt); return res; } EXPORT_SYMBOL_GPL(snmp_fold_field); #if BITS_PER_LONG==32 +u64 snmp_get_cpu_field64(void __percpu *mib, int cpu, int offt, + size_t syncp_offset) +{ + void *bhptr; + struct u64_stats_sync *syncp; + u64 v; + unsigned int start; + + bhptr = per_cpu_ptr(mib, cpu); + syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); + do { + start = u64_stats_fetch_begin_irq(syncp); + v = *(((u64 *)bhptr) + offt); + } while (u64_stats_fetch_retry_irq(syncp, start)); + + return v; +} +EXPORT_SYMBOL_GPL(snmp_get_cpu_field64); + u64 snmp_fold_field64(void __percpu *mib, int offt, size_t syncp_offset) { u64 res = 0; int cpu; for_each_possible_cpu(cpu) { - void *bhptr; - struct u64_stats_sync *syncp; - u64 v; - unsigned int start; - - bhptr = per_cpu_ptr(mib, cpu); - syncp = (struct u64_stats_sync *)(bhptr + syncp_offset); - do { - start = u64_stats_fetch_begin_irq(syncp); - v = *(((u64 *) bhptr) + offt); - } while (u64_stats_fetch_retry_irq(syncp, start)); - - res += v; + res += snmp_get_cpu_field64(mib, cpu, offt, syncp_offset); } return res; } @@ -1780,6 +1797,8 @@ static int __init inet_init(void) dev_add_pack(&ip_packet_type); + ip_tunnel_core_init(); + rc = 0; out: return rc; diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index ac9a32ec3ee4..f2a71025a770 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -360,8 +360,10 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) work_iph = ah_alloc_tmp(ahash, nfrags + sglists, ihl + ahp->icv_trunc_len + seqhi_len); - if (!work_iph) + if (!work_iph) { + err = -ENOMEM; goto out; + } seqhi = (__be32 *)((char *)work_iph + ihl); auth_data = ah_tmp_auth(seqhi, seqhi_len); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 6c8b1fbafce8..30409b75e925 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -233,7 +233,7 @@ static int arp_constructor(struct neighbour *neigh) return -EINVAL; } - neigh->type = inet_addr_type(dev_net(dev), addr); + neigh->type = inet_addr_type_dev_table(dev_net(dev), dev, addr); parms = in_dev->arp_parms; __neigh_parms_put(neigh->parms); @@ -291,6 +291,40 @@ static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb) kfree_skb(skb); } +/* Create and send an arp packet. */ +static void arp_send_dst(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, + const unsigned char *src_hw, + const unsigned char *target_hw, struct sk_buff *oskb) +{ + struct sk_buff *skb; + + /* arp on this interface. */ + if (dev->flags & IFF_NOARP) + return; + + skb = arp_create(type, ptype, dest_ip, dev, src_ip, + dest_hw, src_hw, target_hw); + if (!skb) + return; + + if (oskb) + skb_dst_copy(skb, oskb); + + arp_xmit(skb); +} + +void arp_send(int type, int ptype, __be32 dest_ip, + struct net_device *dev, __be32 src_ip, + const unsigned char *dest_hw, const unsigned char *src_hw, + const unsigned char *target_hw) +{ + arp_send_dst(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, + target_hw, NULL); +} +EXPORT_SYMBOL(arp_send); + static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) { __be32 saddr = 0; @@ -309,7 +343,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ - if (skb && inet_addr_type(dev_net(dev), + if (skb && inet_addr_type_dev_table(dev_net(dev), dev, ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; @@ -317,7 +351,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (!skb) break; saddr = ip_hdr(skb)->saddr; - if (inet_addr_type(dev_net(dev), saddr) == RTN_LOCAL) { + if (inet_addr_type_dev_table(dev_net(dev), dev, + saddr) == RTN_LOCAL) { /* saddr should be known to target */ if (inet_addr_onlink(in_dev, target, saddr)) break; @@ -346,8 +381,9 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) } } - arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, - dst_hw, dev->dev_addr, NULL); + arp_send_dst(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, + dst_hw, dev->dev_addr, NULL, + dev->priv_flags & IFF_XMIT_DST_RELEASE ? NULL : skb); } static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) @@ -597,32 +633,6 @@ void arp_xmit(struct sk_buff *skb) EXPORT_SYMBOL(arp_xmit); /* - * Create and send an arp packet. - */ -void arp_send(int type, int ptype, __be32 dest_ip, - struct net_device *dev, __be32 src_ip, - const unsigned char *dest_hw, const unsigned char *src_hw, - const unsigned char *target_hw) -{ - struct sk_buff *skb; - - /* - * No arp on this interface. - */ - - if (dev->flags&IFF_NOARP) - return; - - skb = arp_create(type, ptype, dest_ip, dev, src_ip, - dest_hw, src_hw, target_hw); - if (!skb) - return; - - arp_xmit(skb); -} -EXPORT_SYMBOL(arp_send); - -/* * Process an arp request. */ @@ -742,7 +752,7 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) /* Special case: IPv4 duplicate address detection packet (RFC2131) */ if (sip == 0) { if (arp->ar_op == htons(ARPOP_REQUEST) && - inet_addr_type(net, tip) == RTN_LOCAL && + inet_addr_type_dev_table(net, dev, tip) == RTN_LOCAL && !arp_ignore(in_dev, sip, tip)) arp_send(ARPOP_REPLY, ETH_P_ARP, sip, dev, tip, sha, dev->dev_addr, sha); @@ -802,16 +812,18 @@ static int arp_process(struct sock *sk, struct sk_buff *skb) n = __neigh_lookup(&arp_tbl, &sip, dev, 0); if (IN_DEV_ARP_ACCEPT(in_dev)) { + unsigned int addr_type = inet_addr_type_dev_table(net, dev, sip); + /* Unsolicited ARP is not accepted by default. It is possible, that this option should be enabled for some devices (strip is candidate) */ is_garp = arp->ar_op == htons(ARPOP_REQUEST) && tip == sip && - inet_addr_type(net, sip) == RTN_UNICAST; + addr_type == RTN_UNICAST; if (!n && ((arp->ar_op == htons(ARPOP_REPLY) && - inet_addr_type(net, sip) == RTN_UNICAST) || is_garp)) + addr_type == RTN_UNICAST) || is_garp)) n = __neigh_lookup(&arp_tbl, &sip, dev, 1); } diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index 574fad9cca05..f915abff1350 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -74,7 +74,7 @@ int __ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len inet->inet_daddr = fl4->daddr; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; - inet_set_txhash(sk); + sk_set_txhash(sk); inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 6bbc54940eb4..6fcbd215cdbc 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -45,6 +45,8 @@ #include <net/ip_fib.h> #include <net/rtnetlink.h> #include <net/xfrm.h> +#include <net/vrf.h> +#include <trace/events/fib.h> #ifndef CONFIG_IP_MULTIPLE_TABLES @@ -211,12 +213,12 @@ void fib_flush_external(struct net *net) */ static inline unsigned int __inet_dev_addr_type(struct net *net, const struct net_device *dev, - __be32 addr) + __be32 addr, u32 tb_id) { struct flowi4 fl4 = { .daddr = addr }; struct fib_result res; unsigned int ret = RTN_BROADCAST; - struct fib_table *local_table; + struct fib_table *table; if (ipv4_is_zeronet(addr) || ipv4_is_lbcast(addr)) return RTN_BROADCAST; @@ -225,10 +227,10 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, rcu_read_lock(); - local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (local_table) { + table = fib_get_table(net, tb_id); + if (table) { ret = RTN_UNICAST; - if (!fib_table_lookup(local_table, &fl4, &res, FIB_LOOKUP_NOREF)) { + if (!fib_table_lookup(table, &fl4, &res, FIB_LOOKUP_NOREF)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; } @@ -238,19 +240,40 @@ static inline unsigned int __inet_dev_addr_type(struct net *net, return ret; } +unsigned int inet_addr_type_table(struct net *net, __be32 addr, u32 tb_id) +{ + return __inet_dev_addr_type(net, NULL, addr, tb_id); +} +EXPORT_SYMBOL(inet_addr_type_table); + unsigned int inet_addr_type(struct net *net, __be32 addr) { - return __inet_dev_addr_type(net, NULL, addr); + return __inet_dev_addr_type(net, NULL, addr, RT_TABLE_LOCAL); } EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - return __inet_dev_addr_type(net, dev, addr); + u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + + return __inet_dev_addr_type(net, dev, addr, rt_table); } EXPORT_SYMBOL(inet_dev_addr_type); +/* inet_addr_type with dev == NULL but using the table from a dev + * if one is associated + */ +unsigned int inet_addr_type_dev_table(struct net *net, + const struct net_device *dev, + __be32 addr) +{ + u32 rt_table = vrf_dev_table(dev) ? : RT_TABLE_LOCAL; + + return __inet_dev_addr_type(net, NULL, addr, rt_table); +} +EXPORT_SYMBOL(inet_addr_type_dev_table); + __be32 fib_compute_spec_dst(struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -280,6 +303,7 @@ __be32 fib_compute_spec_dst(struct sk_buff *skb) fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_scope = scope; fl4.flowi4_mark = IN_DEV_SRC_VMARK(in_dev) ? skb->mark : 0; + fl4.flowi4_tun_key.tun_id = 0; if (!fib_lookup(net, &fl4, &res, 0)) return FIB_RES_PREFSRC(net, res); } else { @@ -308,16 +332,21 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, bool dev_match; fl4.flowi4_oif = 0; - fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; + fl4.flowi4_iif = vrf_master_ifindex_rcu(dev); + if (!fl4.flowi4_iif) + fl4.flowi4_iif = oif ? : LOOPBACK_IFINDEX; fl4.daddr = src; fl4.saddr = dst; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_tun_key.tun_id = 0; no_addr = idev->ifa_list == NULL; fl4.flowi4_mark = IN_DEV_SRC_VMARK(idev) ? skb->mark : 0; + trace_fib_validate_source(dev, &fl4); + net = dev_net(dev); if (fib_lookup(net, &fl4, &res, 0)) goto last_resort; @@ -337,6 +366,9 @@ static int __fib_validate_source(struct sk_buff *skb, __be32 src, __be32 dst, if (nh->nh_dev == dev) { dev_match = true; break; + } else if (vrf_master_ifindex_rcu(nh->nh_dev) == dev->ifindex) { + dev_match = true; + break; } } #else @@ -494,9 +526,12 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, addr = sk_extract_addr(&rt->rt_gateway); if (rt->rt_gateway.sa_family == AF_INET && addr) { + unsigned int addr_type; + cfg->fc_gw = addr; + addr_type = inet_addr_type_table(net, addr, cfg->fc_table); if (rt->rt_flags & RTF_GATEWAY && - inet_addr_type(net, addr) == RTN_UNICAST) + addr_type == RTN_UNICAST) cfg->fc_scope = RT_SCOPE_UNIVERSE; } @@ -591,6 +626,8 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_METRICS] = { .type = NLA_NESTED }, [RTA_MULTIPATH] = { .len = sizeof(struct rtnexthop) }, [RTA_FLOW] = { .type = NLA_U32 }, + [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, + [RTA_ENCAP] = { .type = NLA_NESTED }, }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, @@ -656,6 +693,12 @@ static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, case RTA_TABLE: cfg->fc_table = nla_get_u32(attr); break; + case RTA_ENCAP: + cfg->fc_encap = attr; + break; + case RTA_ENCAP_TYPE: + cfg->fc_encap_type = nla_get_u16(attr); + break; } } @@ -760,6 +803,7 @@ out: static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); + u32 tb_id = vrf_dev_table_rtnl(ifa->ifa_dev->dev); struct fib_table *tb; struct fib_config cfg = { .fc_protocol = RTPROT_KERNEL, @@ -774,11 +818,10 @@ static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifad }, }; - if (type == RTN_UNICAST) - tb = fib_new_table(net, RT_TABLE_MAIN); - else - tb = fib_new_table(net, RT_TABLE_LOCAL); + if (!tb_id) + tb_id = (type == RTN_UNICAST) ? RT_TABLE_MAIN : RT_TABLE_LOCAL; + tb = fib_new_table(net, tb_id); if (!tb) return; @@ -960,11 +1003,14 @@ void fib_del_ifaddr(struct in_ifaddr *ifa, struct in_ifaddr *iprim) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); } if (!(ok & LOCAL_OK)) { + unsigned int addr_type; + fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ - if (gone && - inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { + addr_type = inet_addr_type_dev_table(dev_net(dev), dev, + ifa->ifa_local); + if (gone && addr_type != RTN_LOCAL) { /* And the last, but not the least thing. * We must flush stray FIB entries. * diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 3a06586b170c..064bd3caaa4f 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -42,6 +42,7 @@ #include <net/ip_fib.h> #include <net/netlink.h> #include <net/nexthop.h> +#include <net/lwtunnel.h> #include "fib_lookup.h" @@ -208,6 +209,7 @@ static void free_fib_info_rcu(struct rcu_head *head) change_nexthops(fi) { if (nexthop_nh->nh_dev) dev_put(nexthop_nh->nh_dev); + lwtstate_put(nexthop_nh->nh_lwtstate); free_nh_exceptions(nexthop_nh); rt_fibinfo_free_cpus(nexthop_nh->nh_pcpu_rth_output); rt_fibinfo_free(&nexthop_nh->nh_rth_input); @@ -266,6 +268,7 @@ static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) #ifdef CONFIG_IP_ROUTE_CLASSID nh->nh_tclassid != onh->nh_tclassid || #endif + lwtunnel_cmp_encap(nh->nh_lwtstate, onh->nh_lwtstate) || ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_COMPARE_MASK)) return -1; onh++; @@ -366,6 +369,7 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) payload += nla_total_size((RTAX_MAX * nla_total_size(4))); if (fi->fib_nhs) { + size_t nh_encapsize = 0; /* Also handles the special case fib_nhs == 1 */ /* each nexthop is packed in an attribute */ @@ -374,8 +378,21 @@ static inline size_t fib_nlmsg_size(struct fib_info *fi) /* may contain flow and gateway attribute */ nhsize += 2 * nla_total_size(4); + /* grab encap info */ + for_nexthops(fi) { + if (nh->nh_lwtstate) { + /* RTA_ENCAP_TYPE */ + nh_encapsize += lwtunnel_get_encap_size( + nh->nh_lwtstate); + /* RTA_ENCAP */ + nh_encapsize += nla_total_size(2); + } + } endfor_nexthops(fi); + /* all nexthops are packed in a nested attribute */ - payload += nla_total_size(fi->fib_nhs * nhsize); + payload += nla_total_size((fi->fib_nhs * nhsize) + + nh_encapsize); + } return payload; @@ -421,13 +438,15 @@ static int fib_detect_death(struct fib_info *fi, int order, if (n) { state = n->nud_state; neigh_release(n); + } else { + return 0; } if (state == NUD_REACHABLE) return 0; if ((state & NUD_VALID) && order != dflt) return 0; if ((state & NUD_VALID) || - (*last_idx < 0 && order > dflt)) { + (*last_idx < 0 && order > dflt && state != NUD_INCOMPLETE)) { *last_resort = fi; *last_idx = order; } @@ -452,6 +471,9 @@ static int fib_count_nexthops(struct rtnexthop *rtnh, int remaining) static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, int remaining, struct fib_config *cfg) { + struct net *net = cfg->fc_nlinfo.nl_net; + int ret; + change_nexthops(fi) { int attrlen; @@ -475,18 +497,70 @@ static int fib_get_nhs(struct fib_info *fi, struct rtnexthop *rtnh, if (nexthop_nh->nh_tclassid) fi->fib_net->ipv4.fib_num_tclassid_users++; #endif + nla = nla_find(attrs, attrlen, RTA_ENCAP); + if (nla) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + struct nlattr *nla_entype; + + nla_entype = nla_find(attrs, attrlen, + RTA_ENCAP_TYPE); + if (!nla_entype) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + ret = lwtunnel_build_state(dev, nla_get_u16( + nla_entype), + nla, AF_INET, cfg, + &lwtstate); + if (ret) + goto errout; + nexthop_nh->nh_lwtstate = + lwtstate_get(lwtstate); + } } rtnh = rtnh_next(rtnh, &remaining); } endfor_nexthops(fi); return 0; + +err_inval: + ret = -EINVAL; + +errout: + return ret; } #endif +static int fib_encap_match(struct net *net, u16 encap_type, + struct nlattr *encap, + int oif, const struct fib_nh *nh, + const struct fib_config *cfg) +{ + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + int ret, result = 0; + + if (encap_type == LWTUNNEL_ENCAP_NONE) + return 0; + + if (oif) + dev = __dev_get_by_index(net, oif); + ret = lwtunnel_build_state(dev, encap_type, encap, + AF_INET, cfg, &lwtstate); + if (!ret) { + result = lwtunnel_cmp_encap(lwtstate, nh->nh_lwtstate); + lwtstate_free(lwtstate); + } + + return result; +} + int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) { + struct net *net = cfg->fc_nlinfo.nl_net; #ifdef CONFIG_IP_ROUTE_MULTIPATH struct rtnexthop *rtnh; int remaining; @@ -496,6 +570,12 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) return 1; if (cfg->fc_oif || cfg->fc_gw) { + if (cfg->fc_encap) { + if (fib_encap_match(net, cfg->fc_encap_type, + cfg->fc_encap, cfg->fc_oif, + fi->fib_nh, cfg)) + return 1; + } if ((!cfg->fc_oif || cfg->fc_oif == fi->fib_nh->nh_oif) && (!cfg->fc_gw || cfg->fc_gw == fi->fib_nh->nh_gw)) return 0; @@ -585,7 +665,7 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_nh *nh) { - int err; + int err = 0; struct net *net; struct net_device *dev; @@ -594,16 +674,18 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_result res; if (nh->nh_flags & RTNH_F_ONLINK) { + unsigned int addr_type; if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; - if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST) - return -EINVAL; dev = __dev_get_by_index(net, nh->nh_oif); if (!dev) return -ENODEV; if (!(dev->flags & IFF_UP)) return -ENETDOWN; + addr_type = inet_addr_type_dev_table(net, dev, nh->nh_gw); + if (addr_type != RTN_UNICAST) + return -EINVAL; if (!netif_carrier_ok(dev)) nh->nh_flags |= RTNH_F_LINKDOWN; nh->nh_dev = dev; @@ -613,6 +695,7 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, } rcu_read_lock(); { + struct fib_table *tbl = NULL; struct flowi4 fl4 = { .daddr = nh->nh_gw, .flowi4_scope = cfg->fc_scope + 1, @@ -623,8 +706,24 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, /* It is not necessary, but requires a bit of thinking */ if (fl4.flowi4_scope < RT_SCOPE_LINK) fl4.flowi4_scope = RT_SCOPE_LINK; - err = fib_lookup(net, &fl4, &res, - FIB_LOOKUP_IGNORE_LINKSTATE); + + if (cfg->fc_table) + tbl = fib_get_table(net, cfg->fc_table); + + if (tbl) + err = fib_table_lookup(tbl, &fl4, &res, + FIB_LOOKUP_IGNORE_LINKSTATE | + FIB_LOOKUP_NOREF); + + /* on error or if no table given do full lookup. This + * is needed for example when nexthops are in the local + * table rather than the given table + */ + if (!tbl || err) { + err = fib_lookup(net, &fl4, &res, + FIB_LOOKUP_IGNORE_LINKSTATE); + } + if (err) { rcu_read_unlock(); return err; @@ -760,6 +859,67 @@ __be32 fib_info_update_nh_saddr(struct net *net, struct fib_nh *nh) return nh->nh_saddr; } +static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) +{ + if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || + fib_prefsrc != cfg->fc_dst) { + u32 tb_id = cfg->fc_table; + + if (tb_id == RT_TABLE_MAIN) + tb_id = RT_TABLE_LOCAL; + + if (inet_addr_type_table(cfg->fc_nlinfo.nl_net, + fib_prefsrc, tb_id) != RTN_LOCAL) { + return false; + } + } + return true; +} + +static int +fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) +{ + bool ecn_ca = false; + struct nlattr *nla; + int remaining; + + if (!cfg->fc_mx) + return 0; + + nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { + int type = nla_type(nla); + u32 val; + + if (!type) + continue; + if (type > RTAX_MAX) + return -EINVAL; + + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(tmp, &ecn_ca); + if (val == TCP_CA_UNSPEC) + return -EINVAL; + } else { + val = nla_get_u32(nla); + } + if (type == RTAX_ADVMSS && val > 65535 - 40) + val = 65535 - 40; + if (type == RTAX_MTU && val > 65535 - 15) + val = 65535 - 15; + if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) + return -EINVAL; + fi->fib_metrics[type - 1] = val; + } + + if (ecn_ca) + fi->fib_metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + + return 0; +} + struct fib_info *fib_create_info(struct fib_config *cfg) { int err; @@ -832,36 +992,9 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; } endfor_nexthops(fi) - if (cfg->fc_mx) { - struct nlattr *nla; - int remaining; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - - if (type) { - u32 val; - - if (type > RTAX_MAX) - goto err_inval; - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; - - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(tmp); - if (val == TCP_CA_UNSPEC) - goto err_inval; - } else { - val = nla_get_u32(nla); - } - if (type == RTAX_ADVMSS && val > 65535 - 40) - val = 65535 - 40; - if (type == RTAX_MTU && val > 65535 - 15) - val = 65535 - 15; - fi->fib_metrics[type - 1] = val; - } - } - } + err = fib_convert_metrics(fi, cfg); + if (err) + goto failure; if (cfg->fc_mp) { #ifdef CONFIG_IP_ROUTE_MULTIPATH @@ -882,6 +1015,22 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } else { struct fib_nh *nh = fi->fib_nh; + if (cfg->fc_encap) { + struct lwtunnel_state *lwtstate; + struct net_device *dev = NULL; + + if (cfg->fc_encap_type == LWTUNNEL_ENCAP_NONE) + goto err_inval; + if (cfg->fc_oif) + dev = __dev_get_by_index(net, cfg->fc_oif); + err = lwtunnel_build_state(dev, cfg->fc_encap_type, + cfg->fc_encap, AF_INET, cfg, + &lwtstate); + if (err) + goto failure; + + nh->nh_lwtstate = lwtstate_get(lwtstate); + } nh->nh_oif = cfg->fc_oif; nh->nh_gw = cfg->fc_gw; nh->nh_flags = cfg->fc_flags; @@ -940,12 +1089,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) fi->fib_flags |= RTNH_F_LINKDOWN; } - if (fi->fib_prefsrc) { - if (cfg->fc_type != RTN_LOCAL || !cfg->fc_dst || - fi->fib_prefsrc != cfg->fc_dst) - if (inet_addr_type(net, fi->fib_prefsrc) != RTN_LOCAL) - goto err_inval; - } + if (fi->fib_prefsrc && !fib_valid_prefsrc(cfg, fi->fib_prefsrc)) + goto err_inval; change_nexthops(fi) { fib_info_update_nh_saddr(net, nexthop_nh); @@ -1055,6 +1200,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, fi->fib_nh[0].nh_tclassid)) goto nla_put_failure; #endif + if (fi->fib_nh->nh_lwtstate) + lwtunnel_fill_encap(skb, fi->fib_nh->nh_lwtstate); } #ifdef CONFIG_IP_ROUTE_MULTIPATH if (fi->fib_nhs > 1) { @@ -1090,6 +1237,8 @@ int fib_dump_info(struct sk_buff *skb, u32 portid, u32 seq, int event, nla_put_u32(skb, RTA_FLOW, nh->nh_tclassid)) goto nla_put_failure; #endif + if (nh->nh_lwtstate) + lwtunnel_fill_encap(skb, nh->nh_lwtstate); /* length of rtnetlink header + attributes */ rtnh->rtnh_len = nlmsg_get_pos(skb) - (void *) rtnh; } endfor_nexthops(fi); diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index b0c6258ffb79..26d6ffb6d23c 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -81,6 +81,7 @@ #include <net/sock.h> #include <net/ip_fib.h> #include <net/switchdev.h> +#include <trace/events/fib.h> #include "fib_lookup.h" #define MAX_STAT_DEPTH 32 @@ -1278,6 +1279,8 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi4 *flp, unsigned long index; t_key cindex; + trace_fib_table_lookup(tb->tb_id, flp); + pn = t->kv; cindex = 0; @@ -1423,8 +1426,11 @@ found: nh->nh_flags & RTNH_F_LINKDOWN && !(fib_flags & FIB_LOOKUP_IGNORE_LINKSTATE)) continue; - if (flp->flowi4_oif && flp->flowi4_oif != nh->nh_oif) - continue; + if (!(flp->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + if (flp->flowi4_oif && + flp->flowi4_oif != nh->nh_oif) + continue; + } if (!(fib_flags & FIB_LOOKUP_NOREF)) atomic_inc(&fi->fib_clntref); @@ -1439,6 +1445,8 @@ found: #ifdef CONFIG_IP_FIB_TRIE_STATS this_cpu_inc(stats->semantic_match_passed); #endif + trace_fib_table_lookup_nh(nh); + return err; } } diff --git a/net/ipv4/fou.c b/net/ipv4/fou.c index 34968cd5c146..e0fcbbbcfe54 100644 --- a/net/ipv4/fou.c +++ b/net/ipv4/fou.c @@ -79,7 +79,11 @@ static struct guehdr *gue_remcsum(struct sk_buff *skb, struct guehdr *guehdr, __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); + size_t plen = sizeof(struct udphdr) + hdrlen + + max_t(size_t, offset + sizeof(u16), start); + + if (skb->remcsum_offload) + return guehdr; if (!pskb_may_pull(skb, plen)) return NULL; @@ -221,29 +225,21 @@ out_unlock: static struct guehdr *gue_gro_remcsum(struct sk_buff *skb, unsigned int off, struct guehdr *guehdr, void *data, - size_t hdrlen, u8 ipproto, - struct gro_remcsum *grc, bool nopartial) + size_t hdrlen, struct gro_remcsum *grc, + bool nopartial) { __be16 *pd = data; size_t start = ntohs(pd[0]); size_t offset = ntohs(pd[1]); - size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start); if (skb->remcsum_offload) - return NULL; + return guehdr; if (!NAPI_GRO_CB(skb)->csum_valid) return NULL; - /* Pull checksum that will be written */ - if (skb_gro_header_hard(skb, off + plen)) { - guehdr = skb_gro_header_slow(skb, off + plen, off); - if (!guehdr) - return NULL; - } - - skb_gro_remcsum_process(skb, (void *)guehdr + hdrlen, - start, offset, grc, nopartial); + guehdr = skb_gro_remcsum_process(skb, (void *)guehdr, off, hdrlen, + start, offset, grc, nopartial); skb->remcsum_offload = 1; @@ -307,10 +303,10 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, if (flags & GUE_PFLAG_REMCSUM) { guehdr = gue_gro_remcsum(skb, off, guehdr, - data + doffset, hdrlen, - guehdr->proto_ctype, &grc, + data + doffset, hdrlen, &grc, !!(fou->flags & FOU_F_REMCSUM_NOPARTIAL)); + if (!guehdr) goto out; @@ -351,7 +347,7 @@ static struct sk_buff **gue_gro_receive(struct sk_buff **head, rcu_read_lock(); offloads = NAPI_GRO_CB(skb)->is_ipv6 ? inet6_offloads : inet_offloads; ops = rcu_dereference(offloads[guehdr->proto_ctype]); - if (WARN_ON(!ops || !ops->callbacks.gro_receive)) + if (WARN_ON_ONCE(!ops || !ops->callbacks.gro_receive)) goto out_unlock; pp = ops->callbacks.gro_receive(head, skb); @@ -570,7 +566,7 @@ static int parse_nl_config(struct genl_info *info, if (info->attrs[FOU_ATTR_AF]) { u8 family = nla_get_u8(info->attrs[FOU_ATTR_AF]); - if (family != AF_INET && family != AF_INET6) + if (family != AF_INET) return -EINVAL; cfg->udp_config.family = family; diff --git a/net/ipv4/geneve_core.c b/net/ipv4/geneve_core.c deleted file mode 100644 index 311a4ba6950a..000000000000 --- a/net/ipv4/geneve_core.c +++ /dev/null @@ -1,447 +0,0 @@ -/* - * Geneve: Generic Network Virtualization Encapsulation - * - * Copyright (c) 2014 Nicira, Inc. - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; either version - * 2 of the License, or (at your option) any later version. - */ - -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt - -#include <linux/kernel.h> -#include <linux/types.h> -#include <linux/module.h> -#include <linux/errno.h> -#include <linux/slab.h> -#include <linux/skbuff.h> -#include <linux/list.h> -#include <linux/netdevice.h> -#include <linux/in.h> -#include <linux/ip.h> -#include <linux/udp.h> -#include <linux/igmp.h> -#include <linux/etherdevice.h> -#include <linux/if_ether.h> -#include <linux/if_vlan.h> -#include <linux/ethtool.h> -#include <linux/mutex.h> -#include <net/arp.h> -#include <net/ndisc.h> -#include <net/ip.h> -#include <net/ip_tunnels.h> -#include <net/icmp.h> -#include <net/udp.h> -#include <net/rtnetlink.h> -#include <net/route.h> -#include <net/dsfield.h> -#include <net/inet_ecn.h> -#include <net/net_namespace.h> -#include <net/netns/generic.h> -#include <net/geneve.h> -#include <net/protocol.h> -#include <net/udp_tunnel.h> -#if IS_ENABLED(CONFIG_IPV6) -#include <net/ipv6.h> -#include <net/addrconf.h> -#include <net/ip6_tunnel.h> -#include <net/ip6_checksum.h> -#endif - -/* Protects sock_list and refcounts. */ -static DEFINE_MUTEX(geneve_mutex); - -/* per-network namespace private data for this module */ -struct geneve_net { - struct list_head sock_list; -}; - -static int geneve_net_id; - -static struct geneve_sock *geneve_find_sock(struct net *net, - sa_family_t family, __be16 port) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - struct geneve_sock *gs; - - list_for_each_entry(gs, &gn->sock_list, list) { - if (inet_sk(gs->sock->sk)->inet_sport == port && - inet_sk(gs->sock->sk)->sk.sk_family == family) - return gs; - } - - return NULL; -} - -static void geneve_build_header(struct genevehdr *geneveh, - __be16 tun_flags, u8 vni[3], - u8 options_len, u8 *options) -{ - geneveh->ver = GENEVE_VER; - geneveh->opt_len = options_len / 4; - geneveh->oam = !!(tun_flags & TUNNEL_OAM); - geneveh->critical = !!(tun_flags & TUNNEL_CRIT_OPT); - geneveh->rsvd1 = 0; - memcpy(geneveh->vni, vni, 3); - geneveh->proto_type = htons(ETH_P_TEB); - geneveh->rsvd2 = 0; - - memcpy(geneveh->options, options, options_len); -} - -/* Transmit a fully formatted Geneve frame. - * - * When calling this function. The skb->data should point - * to the geneve header which is fully formed. - * - * This function will add other UDP tunnel headers. - */ -int geneve_xmit_skb(struct geneve_sock *gs, struct rtable *rt, - struct sk_buff *skb, __be32 src, __be32 dst, __u8 tos, - __u8 ttl, __be16 df, __be16 src_port, __be16 dst_port, - __be16 tun_flags, u8 vni[3], u8 opt_len, u8 *opt, - bool csum, bool xnet) -{ - struct genevehdr *gnvh; - int min_headroom; - int err; - - min_headroom = LL_RESERVED_SPACE(rt->dst.dev) + rt->dst.header_len - + GENEVE_BASE_HLEN + opt_len + sizeof(struct iphdr) - + (skb_vlan_tag_present(skb) ? VLAN_HLEN : 0); - - err = skb_cow_head(skb, min_headroom); - if (unlikely(err)) { - kfree_skb(skb); - return err; - } - - skb = vlan_hwaccel_push_inside(skb); - if (unlikely(!skb)) - return -ENOMEM; - - skb = udp_tunnel_handle_offloads(skb, csum); - if (IS_ERR(skb)) - return PTR_ERR(skb); - - gnvh = (struct genevehdr *)__skb_push(skb, sizeof(*gnvh) + opt_len); - geneve_build_header(gnvh, tun_flags, vni, opt_len, opt); - - skb_set_inner_protocol(skb, htons(ETH_P_TEB)); - - return udp_tunnel_xmit_skb(rt, gs->sock->sk, skb, src, dst, - tos, ttl, df, src_port, dst_port, xnet, - !csum); -} -EXPORT_SYMBOL_GPL(geneve_xmit_skb); - -static int geneve_hlen(struct genevehdr *gh) -{ - return sizeof(*gh) + gh->opt_len * 4; -} - -static struct sk_buff **geneve_gro_receive(struct sk_buff **head, - struct sk_buff *skb, - struct udp_offload *uoff) -{ - struct sk_buff *p, **pp = NULL; - struct genevehdr *gh, *gh2; - unsigned int hlen, gh_len, off_gnv; - const struct packet_offload *ptype; - __be16 type; - int flush = 1; - - off_gnv = skb_gro_offset(skb); - hlen = off_gnv + sizeof(*gh); - gh = skb_gro_header_fast(skb, off_gnv); - if (skb_gro_header_hard(skb, hlen)) { - gh = skb_gro_header_slow(skb, hlen, off_gnv); - if (unlikely(!gh)) - goto out; - } - - if (gh->ver != GENEVE_VER || gh->oam) - goto out; - gh_len = geneve_hlen(gh); - - hlen = off_gnv + gh_len; - if (skb_gro_header_hard(skb, hlen)) { - gh = skb_gro_header_slow(skb, hlen, off_gnv); - if (unlikely(!gh)) - goto out; - } - - flush = 0; - - for (p = *head; p; p = p->next) { - if (!NAPI_GRO_CB(p)->same_flow) - continue; - - gh2 = (struct genevehdr *)(p->data + off_gnv); - if (gh->opt_len != gh2->opt_len || - memcmp(gh, gh2, gh_len)) { - NAPI_GRO_CB(p)->same_flow = 0; - continue; - } - } - - type = gh->proto_type; - - rcu_read_lock(); - ptype = gro_find_receive_by_type(type); - if (!ptype) { - flush = 1; - goto out_unlock; - } - - skb_gro_pull(skb, gh_len); - skb_gro_postpull_rcsum(skb, gh, gh_len); - pp = ptype->callbacks.gro_receive(head, skb); - -out_unlock: - rcu_read_unlock(); -out: - NAPI_GRO_CB(skb)->flush |= flush; - - return pp; -} - -static int geneve_gro_complete(struct sk_buff *skb, int nhoff, - struct udp_offload *uoff) -{ - struct genevehdr *gh; - struct packet_offload *ptype; - __be16 type; - int gh_len; - int err = -ENOSYS; - - udp_tunnel_gro_complete(skb, nhoff); - - gh = (struct genevehdr *)(skb->data + nhoff); - gh_len = geneve_hlen(gh); - type = gh->proto_type; - - rcu_read_lock(); - ptype = gro_find_complete_by_type(type); - if (ptype) - err = ptype->callbacks.gro_complete(skb, nhoff + gh_len); - - rcu_read_unlock(); - return err; -} - -static void geneve_notify_add_rx_port(struct geneve_sock *gs) -{ - struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; - int err; - - if (sa_family == AF_INET) { - err = udp_add_offload(&gs->udp_offloads); - if (err) - pr_warn("geneve: udp_add_offload failed with status %d\n", - err); - } -} - -static void geneve_notify_del_rx_port(struct geneve_sock *gs) -{ - struct sock *sk = gs->sock->sk; - sa_family_t sa_family = sk->sk_family; - - if (sa_family == AF_INET) - udp_del_offload(&gs->udp_offloads); -} - -/* Callback from net/ipv4/udp.c to receive packets */ -static int geneve_udp_encap_recv(struct sock *sk, struct sk_buff *skb) -{ - struct genevehdr *geneveh; - struct geneve_sock *gs; - int opts_len; - - /* Need Geneve and inner Ethernet header to be present */ - if (unlikely(!pskb_may_pull(skb, GENEVE_BASE_HLEN))) - goto error; - - /* Return packets with reserved bits set */ - geneveh = geneve_hdr(skb); - - if (unlikely(geneveh->ver != GENEVE_VER)) - goto error; - - if (unlikely(geneveh->proto_type != htons(ETH_P_TEB))) - goto error; - - opts_len = geneveh->opt_len * 4; - if (iptunnel_pull_header(skb, GENEVE_BASE_HLEN + opts_len, - htons(ETH_P_TEB))) - goto drop; - - gs = rcu_dereference_sk_user_data(sk); - if (!gs) - goto drop; - - gs->rcv(gs, skb); - return 0; - -drop: - /* Consume bad packet */ - kfree_skb(skb); - return 0; - -error: - /* Let the UDP layer deal with the skb */ - return 1; -} - -static struct socket *geneve_create_sock(struct net *net, bool ipv6, - __be16 port) -{ - struct socket *sock; - struct udp_port_cfg udp_conf; - int err; - - memset(&udp_conf, 0, sizeof(udp_conf)); - - if (ipv6) { - udp_conf.family = AF_INET6; - } else { - udp_conf.family = AF_INET; - udp_conf.local_ip.s_addr = htonl(INADDR_ANY); - } - - udp_conf.local_udp_port = port; - - /* Open UDP socket */ - err = udp_sock_create(net, &udp_conf, &sock); - if (err < 0) - return ERR_PTR(err); - - return sock; -} - -/* Create new listen socket if needed */ -static struct geneve_sock *geneve_socket_create(struct net *net, __be16 port, - geneve_rcv_t *rcv, void *data, - bool ipv6) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - struct geneve_sock *gs; - struct socket *sock; - struct udp_tunnel_sock_cfg tunnel_cfg; - - gs = kzalloc(sizeof(*gs), GFP_KERNEL); - if (!gs) - return ERR_PTR(-ENOMEM); - - sock = geneve_create_sock(net, ipv6, port); - if (IS_ERR(sock)) { - kfree(gs); - return ERR_CAST(sock); - } - - gs->sock = sock; - gs->refcnt = 1; - gs->rcv = rcv; - gs->rcv_data = data; - - /* Initialize the geneve udp offloads structure */ - gs->udp_offloads.port = port; - gs->udp_offloads.callbacks.gro_receive = geneve_gro_receive; - gs->udp_offloads.callbacks.gro_complete = geneve_gro_complete; - geneve_notify_add_rx_port(gs); - - /* Mark socket as an encapsulation socket */ - tunnel_cfg.sk_user_data = gs; - tunnel_cfg.encap_type = 1; - tunnel_cfg.encap_rcv = geneve_udp_encap_recv; - tunnel_cfg.encap_destroy = NULL; - setup_udp_tunnel_sock(net, sock, &tunnel_cfg); - - list_add(&gs->list, &gn->sock_list); - - return gs; -} - -struct geneve_sock *geneve_sock_add(struct net *net, __be16 port, - geneve_rcv_t *rcv, void *data, - bool no_share, bool ipv6) -{ - struct geneve_sock *gs; - - mutex_lock(&geneve_mutex); - - gs = geneve_find_sock(net, ipv6 ? AF_INET6 : AF_INET, port); - if (gs) { - if (!no_share && gs->rcv == rcv) - gs->refcnt++; - else - gs = ERR_PTR(-EBUSY); - } else { - gs = geneve_socket_create(net, port, rcv, data, ipv6); - } - - mutex_unlock(&geneve_mutex); - - return gs; -} -EXPORT_SYMBOL_GPL(geneve_sock_add); - -void geneve_sock_release(struct geneve_sock *gs) -{ - mutex_lock(&geneve_mutex); - - if (--gs->refcnt) - goto unlock; - - list_del(&gs->list); - geneve_notify_del_rx_port(gs); - udp_tunnel_sock_release(gs->sock); - kfree_rcu(gs, rcu); - -unlock: - mutex_unlock(&geneve_mutex); -} -EXPORT_SYMBOL_GPL(geneve_sock_release); - -static __net_init int geneve_init_net(struct net *net) -{ - struct geneve_net *gn = net_generic(net, geneve_net_id); - - INIT_LIST_HEAD(&gn->sock_list); - - return 0; -} - -static struct pernet_operations geneve_net_ops = { - .init = geneve_init_net, - .id = &geneve_net_id, - .size = sizeof(struct geneve_net), -}; - -static int __init geneve_init_module(void) -{ - int rc; - - rc = register_pernet_subsys(&geneve_net_ops); - if (rc) - return rc; - - pr_info("Geneve core logic\n"); - - return 0; -} -module_init(geneve_init_module); - -static void __exit geneve_cleanup_module(void) -{ - unregister_pernet_subsys(&geneve_net_ops); -} -module_exit(geneve_cleanup_module); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Jesse Gross <jesse@nicira.com>"); -MODULE_DESCRIPTION("Driver library for GENEVE encapsulated traffic"); diff --git a/net/ipv4/gre_demux.c b/net/ipv4/gre_demux.c index 4a7b5b2a1ce3..d9c552a721fc 100644 --- a/net/ipv4/gre_demux.c +++ b/net/ipv4/gre_demux.c @@ -31,7 +31,6 @@ #include <net/xfrm.h> static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; -static struct gre_cisco_protocol __rcu *gre_cisco_proto_list[GRE_IP_PROTO_MAX]; int gre_add_protocol(const struct gre_protocol *proto, u8 version) { @@ -61,197 +60,6 @@ int gre_del_protocol(const struct gre_protocol *proto, u8 version) } EXPORT_SYMBOL_GPL(gre_del_protocol); -void gre_build_header(struct sk_buff *skb, const struct tnl_ptk_info *tpi, - int hdr_len) -{ - struct gre_base_hdr *greh; - - skb_push(skb, hdr_len); - - skb_reset_transport_header(skb); - greh = (struct gre_base_hdr *)skb->data; - greh->flags = tnl_flags_to_gre_flags(tpi->flags); - greh->protocol = tpi->proto; - - if (tpi->flags&(TUNNEL_KEY|TUNNEL_CSUM|TUNNEL_SEQ)) { - __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); - - if (tpi->flags&TUNNEL_SEQ) { - *ptr = tpi->seq; - ptr--; - } - if (tpi->flags&TUNNEL_KEY) { - *ptr = tpi->key; - ptr--; - } - if (tpi->flags&TUNNEL_CSUM && - !(skb_shinfo(skb)->gso_type & - (SKB_GSO_GRE|SKB_GSO_GRE_CSUM))) { - *ptr = 0; - *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, - skb->len, 0)); - } - } -} -EXPORT_SYMBOL_GPL(gre_build_header); - -static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, - bool *csum_err) -{ - const struct gre_base_hdr *greh; - __be32 *options; - int hdr_len; - - if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) - return -EINVAL; - - greh = (struct gre_base_hdr *)skb_transport_header(skb); - if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) - return -EINVAL; - - tpi->flags = gre_flags_to_tnl_flags(greh->flags); - hdr_len = ip_gre_calc_hlen(tpi->flags); - - if (!pskb_may_pull(skb, hdr_len)) - return -EINVAL; - - greh = (struct gre_base_hdr *)skb_transport_header(skb); - tpi->proto = greh->protocol; - - options = (__be32 *)(greh + 1); - if (greh->flags & GRE_CSUM) { - if (skb_checksum_simple_validate(skb)) { - *csum_err = true; - return -EINVAL; - } - - skb_checksum_try_convert(skb, IPPROTO_GRE, 0, - null_compute_pseudo); - - options++; - } - - if (greh->flags & GRE_KEY) { - tpi->key = *options; - options++; - } else - tpi->key = 0; - - if (unlikely(greh->flags & GRE_SEQ)) { - tpi->seq = *options; - options++; - } else - tpi->seq = 0; - - /* WCCP version 1 and 2 protocol decoding. - * - Change protocol to IP - * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header - */ - if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { - tpi->proto = htons(ETH_P_IP); - if ((*(u8 *)options & 0xF0) != 0x40) { - hdr_len += 4; - if (!pskb_may_pull(skb, hdr_len)) - return -EINVAL; - } - } - - return iptunnel_pull_header(skb, hdr_len, tpi->proto); -} - -static int gre_cisco_rcv(struct sk_buff *skb) -{ - struct tnl_ptk_info tpi; - int i; - bool csum_err = false; - -#ifdef CONFIG_NET_IPGRE_BROADCAST - if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { - /* Looped back packet, drop it! */ - if (rt_is_output_route(skb_rtable(skb))) - goto drop; - } -#endif - - if (parse_gre_header(skb, &tpi, &csum_err) < 0) - goto drop; - - rcu_read_lock(); - for (i = 0; i < GRE_IP_PROTO_MAX; i++) { - struct gre_cisco_protocol *proto; - int ret; - - proto = rcu_dereference(gre_cisco_proto_list[i]); - if (!proto) - continue; - ret = proto->handler(skb, &tpi); - if (ret == PACKET_RCVD) { - rcu_read_unlock(); - return 0; - } - } - rcu_read_unlock(); - - icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); -drop: - kfree_skb(skb); - return 0; -} - -static void gre_cisco_err(struct sk_buff *skb, u32 info) -{ - /* All the routers (except for Linux) return only - * 8 bytes of packet payload. It means, that precise relaying of - * ICMP in the real Internet is absolutely infeasible. - * - * Moreover, Cisco "wise men" put GRE key to the third word - * in GRE header. It makes impossible maintaining even soft - * state for keyed - * GRE tunnels with enabled checksum. Tell them "thank you". - * - * Well, I wonder, rfc1812 was written by Cisco employee, - * what the hell these idiots break standards established - * by themselves??? - */ - - const int type = icmp_hdr(skb)->type; - const int code = icmp_hdr(skb)->code; - struct tnl_ptk_info tpi; - bool csum_err = false; - int i; - - if (parse_gre_header(skb, &tpi, &csum_err)) { - if (!csum_err) /* ignore csum errors. */ - return; - } - - if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { - ipv4_update_pmtu(skb, dev_net(skb->dev), info, - skb->dev->ifindex, 0, IPPROTO_GRE, 0); - return; - } - if (type == ICMP_REDIRECT) { - ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0, - IPPROTO_GRE, 0); - return; - } - - rcu_read_lock(); - for (i = 0; i < GRE_IP_PROTO_MAX; i++) { - struct gre_cisco_protocol *proto; - - proto = rcu_dereference(gre_cisco_proto_list[i]); - if (!proto) - continue; - - if (proto->err_handler(skb, info, &tpi) == PACKET_RCVD) - goto out; - - } -out: - rcu_read_unlock(); -} - static int gre_rcv(struct sk_buff *skb) { const struct gre_protocol *proto; @@ -302,60 +110,19 @@ static const struct net_protocol net_gre_protocol = { .netns_ok = 1, }; -static const struct gre_protocol ipgre_protocol = { - .handler = gre_cisco_rcv, - .err_handler = gre_cisco_err, -}; - -int gre_cisco_register(struct gre_cisco_protocol *newp) -{ - struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **) - &gre_cisco_proto_list[newp->priority]; - - return (cmpxchg(proto, NULL, newp) == NULL) ? 0 : -EBUSY; -} -EXPORT_SYMBOL_GPL(gre_cisco_register); - -int gre_cisco_unregister(struct gre_cisco_protocol *del_proto) -{ - struct gre_cisco_protocol **proto = (struct gre_cisco_protocol **) - &gre_cisco_proto_list[del_proto->priority]; - int ret; - - ret = (cmpxchg(proto, del_proto, NULL) == del_proto) ? 0 : -EINVAL; - - if (ret) - return ret; - - synchronize_net(); - return 0; -} -EXPORT_SYMBOL_GPL(gre_cisco_unregister); - static int __init gre_init(void) { pr_info("GRE over IPv4 demultiplexor driver\n"); if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { pr_err("can't add protocol\n"); - goto err; - } - - if (gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0) { - pr_info("%s: can't add ipgre handler\n", __func__); - goto err_gre; + return -EAGAIN; } - return 0; -err_gre: - inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); -err: - return -EAGAIN; } static void __exit gre_exit(void) { - gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); } diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f5203fba6236..79fe05befcae 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -96,6 +96,7 @@ #include <net/xfrm.h> #include <net/inet_common.h> #include <net/ip_fib.h> +#include <net/vrf.h> /* * Build xmit assembly blocks @@ -308,9 +309,10 @@ static bool icmpv4_xrlim_allow(struct net *net, struct rtable *rt, rc = false; if (icmp_global_allow()) { + int vif = vrf_master_ifindex(dst->dev); struct inet_peer *peer; - peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, fl4->daddr, vif, 1); rc = inet_peer_xrlim_allow(peer, net->ipv4.sysctl_icmp_ratelimit); if (peer) @@ -425,6 +427,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) fl4.flowi4_mark = mark; fl4.flowi4_tos = RT_TOS(ip_hdr(skb)->tos); fl4.flowi4_proto = IPPROTO_ICMP; + fl4.flowi4_oif = vrf_master_ifindex(skb->dev) ? : skb->dev->ifindex; security_skb_classify_flow(skb, flowi4_to_flowi(&fl4)); rt = ip_route_output_key(net, &fl4); if (IS_ERR(rt)) @@ -458,6 +461,8 @@ static struct rtable *icmp_route_lookup(struct net *net, fl4->flowi4_proto = IPPROTO_ICMP; fl4->fl4_icmp_type = type; fl4->fl4_icmp_code = code; + fl4->flowi4_oif = vrf_master_ifindex(skb_in->dev) ? : skb_in->dev->ifindex; + security_skb_classify_flow(skb_in, flowi4_to_flowi(fl4)); rt = __ip_route_output_key(net, fl4); if (IS_ERR(rt)) @@ -480,7 +485,8 @@ static struct rtable *icmp_route_lookup(struct net *net, if (err) goto relookup_failed; - if (inet_addr_type(net, fl4_dec.saddr) == RTN_LOCAL) { + if (inet_addr_type_dev_table(net, skb_in->dev, + fl4_dec.saddr) == RTN_LOCAL) { rt2 = __ip_route_output_key(net, &fl4_dec); if (IS_ERR(rt2)) err = PTR_ERR(rt2); @@ -496,6 +502,7 @@ static struct rtable *icmp_route_lookup(struct net *net, } /* Ugh! */ orefdst = skb_in->_skb_refdst; /* save old refdst */ + skb_dst_set(skb_in, NULL); err = ip_route_input(skb_in, fl4_dec.daddr, fl4_dec.saddr, RT_TOS(tos), rt2->dst.dev); @@ -828,7 +835,7 @@ static bool icmp_unreach(struct sk_buff *skb) */ if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && - inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { + inet_addr_type_dev_table(net, skb->dev, iph->daddr) == RTN_BROADCAST) { net_warn_ratelimited("%pI4 sent an invalid ICMP type %u, code %u error to a broadcast: %pI4 on %s\n", &ip_hdr(skb)->saddr, icmph->type, icmph->code, diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 9fdfd9deac11..d38b8b61eaee 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -110,6 +110,9 @@ #define IP_MAX_MEMBERSHIPS 20 #define IP_MAX_MSF 10 +/* IGMP reports for link-local multicast groups are enabled by default */ +int sysctl_igmp_llm_reports __read_mostly = 1; + #ifdef CONFIG_IP_MULTICAST /* Parameter names and values are taken from igmp-v2-06 draft */ @@ -437,6 +440,8 @@ static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, if (pmc->multiaddr == IGMP_ALL_HOSTS) return skb; + if (ipv4_is_local_multicast(pmc->multiaddr) && !sysctl_igmp_llm_reports) + return skb; isquery = type == IGMPV3_MODE_IS_INCLUDE || type == IGMPV3_MODE_IS_EXCLUDE; @@ -545,6 +550,9 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(pmc->multiaddr) && + !sysctl_igmp_llm_reports) + continue; spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) type = IGMPV3_MODE_IS_EXCLUDE; @@ -678,7 +686,11 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); - else if (type == IGMP_HOST_LEAVE_MESSAGE) + + if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + return 0; + + if (type == IGMP_HOST_LEAVE_MESSAGE) dst = IGMP_ALL_ROUTER; else dst = group; @@ -851,6 +863,8 @@ static bool igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return false; + if (ipv4_is_local_multicast(group) && !sysctl_igmp_llm_reports) + return false; rcu_read_lock(); for_each_pmc_rcu(in_dev, im) { @@ -957,6 +971,9 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, continue; if (im->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(im->multiaddr) && + !sysctl_igmp_llm_reports) + continue; spin_lock_bh(&im->lock); if (im->tm_running) im->gsquery = im->gsquery && mark; @@ -1181,6 +1198,8 @@ static void igmp_group_dropped(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; + if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + return; reporter = im->reporter; igmp_stop_timer(im); @@ -1213,6 +1232,8 @@ static void igmp_group_added(struct ip_mc_list *im) #ifdef CONFIG_IP_MULTICAST if (im->multiaddr == IGMP_ALL_HOSTS) return; + if (ipv4_is_local_multicast(im->multiaddr) && !sysctl_igmp_llm_reports) + return; if (in_dev->dead) return; @@ -1518,6 +1539,9 @@ static void ip_mc_rejoin_groups(struct in_device *in_dev) for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == IGMP_ALL_HOSTS) continue; + if (ipv4_is_local_multicast(im->multiaddr) && + !sysctl_igmp_llm_reports) + continue; /* a failover is happening and switches * must be notified immediately diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 0cb9165421d4..89120196a949 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -343,7 +343,6 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw = NULL; - int twrefcnt = 0; spin_lock(lock); @@ -371,21 +370,17 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); if (tw) { - twrefcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); } spin_unlock(lock); - if (twrefcnt) - inet_twsk_put(tw); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); if (twp) { *twp = tw; } else if (tw) { /* Silly. Should hash-dance instead... */ - inet_twsk_deschedule(tw); - - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); } return 0; @@ -403,13 +398,12 @@ static u32 inet_sk_port_offset(const struct sock *sk) inet->inet_dport); } -int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash_nolisten(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct hlist_nulls_head *list; struct inet_ehash_bucket *head; spinlock_t *lock; - int twrefcnt = 0; WARN_ON(!sk_unhashed(sk)); @@ -420,23 +414,22 @@ int __inet_hash_nolisten(struct sock *sk, struct inet_timewait_sock *tw) spin_lock(lock); __sk_nulls_add_node_rcu(sk, list); - if (tw) { - WARN_ON(sk->sk_hash != tw->tw_hash); - twrefcnt = inet_twsk_unhash(tw); + if (osk) { + WARN_ON(sk->sk_hash != osk->sk_hash); + sk_nulls_del_node_init_rcu(osk); } spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - return twrefcnt; } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); -int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) +void __inet_hash(struct sock *sk, struct sock *osk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; struct inet_listen_hashbucket *ilb; if (sk->sk_state != TCP_LISTEN) - return __inet_hash_nolisten(sk, tw); + return __inet_hash_nolisten(sk, osk); WARN_ON(!sk_unhashed(sk)); ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; @@ -445,7 +438,6 @@ int __inet_hash(struct sock *sk, struct inet_timewait_sock *tw) __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); spin_unlock(&ilb->lock); - return 0; } EXPORT_SYMBOL(__inet_hash); @@ -492,7 +484,6 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, struct inet_bind_bucket *tb; int ret; struct net *net = sock_net(sk); - int twrefcnt = 1; if (!snum) { int i, remaining, low, high, port; @@ -560,19 +551,14 @@ ok: inet_bind_hash(sk, tb, port); if (sk_unhashed(sk)) { inet_sk(sk)->inet_sport = htons(port); - twrefcnt += __inet_hash_nolisten(sk, tw); + __inet_hash_nolisten(sk, (struct sock *)tw); } if (tw) - twrefcnt += inet_twsk_bind_unhash(tw, hinfo); + inet_twsk_bind_unhash(tw, hinfo); spin_unlock(&head->lock); - if (tw) { - inet_twsk_deschedule(tw); - while (twrefcnt) { - twrefcnt--; - inet_twsk_put(tw); - } - } + if (tw) + inet_twsk_deschedule_put(tw); ret = 0; goto out; diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 2ffbd16b79e0..ae22cc24fbe8 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -18,28 +18,6 @@ /** - * inet_twsk_unhash - unhash a timewait socket from established hash - * @tw: timewait socket - * - * unhash a timewait socket from established hash, if hashed. - * ehash lock must be held by caller. - * Returns 1 if caller should call inet_twsk_put() after lock release. - */ -int inet_twsk_unhash(struct inet_timewait_sock *tw) -{ - if (hlist_nulls_unhashed(&tw->tw_node)) - return 0; - - hlist_nulls_del_rcu(&tw->tw_node); - sk_nulls_node_init(&tw->tw_node); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; -} - -/** * inet_twsk_bind_unhash - unhash a timewait socket from bind hash * @tw: timewait socket * @hashinfo: hashinfo pointer @@ -48,35 +26,29 @@ int inet_twsk_unhash(struct inet_timewait_sock *tw) * bind hash lock must be held by caller. * Returns 1 if caller should call inet_twsk_put() after lock release. */ -int inet_twsk_bind_unhash(struct inet_timewait_sock *tw, +void inet_twsk_bind_unhash(struct inet_timewait_sock *tw, struct inet_hashinfo *hashinfo) { struct inet_bind_bucket *tb = tw->tw_tb; if (!tb) - return 0; + return; __hlist_del(&tw->tw_bind_node); tw->tw_tb = NULL; inet_bind_bucket_destroy(hashinfo->bind_bucket_cachep, tb); - /* - * We cannot call inet_twsk_put() ourself under lock, - * caller must call it for us. - */ - return 1; + __sock_put((struct sock *)tw); } /* Must be called with locally disabled BHs. */ static void inet_twsk_kill(struct inet_timewait_sock *tw) { struct inet_hashinfo *hashinfo = tw->tw_dr->hashinfo; - struct inet_bind_hashbucket *bhead; - int refcnt; - /* Unlink from established hashes. */ spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + struct inet_bind_hashbucket *bhead; spin_lock(lock); - refcnt = inet_twsk_unhash(tw); + sk_nulls_del_node_init_rcu((struct sock *)tw); spin_unlock(lock); /* Disassociate with bind bucket. */ @@ -84,11 +56,9 @@ static void inet_twsk_kill(struct inet_timewait_sock *tw) hashinfo->bhash_size)]; spin_lock(&bhead->lock); - refcnt += inet_twsk_bind_unhash(tw, hashinfo); + inet_twsk_bind_unhash(tw, hashinfo); spin_unlock(&bhead->lock); - BUG_ON(refcnt >= atomic_read(&tw->tw_refcnt)); - atomic_sub(refcnt, &tw->tw_refcnt); atomic_dec(&tw->tw_dr->tw_count); inet_twsk_put(tw); } @@ -235,13 +205,17 @@ EXPORT_SYMBOL_GPL(inet_twsk_alloc); * tcp_input.c to verify this. */ -/* This is for handling early-kills of TIME_WAIT sockets. */ -void inet_twsk_deschedule(struct inet_timewait_sock *tw) +/* This is for handling early-kills of TIME_WAIT sockets. + * Warning : consume reference. + * Caller should not access tw anymore. + */ +void inet_twsk_deschedule_put(struct inet_timewait_sock *tw) { if (del_timer_sync(&tw->tw_timer)) inet_twsk_kill(tw); + inet_twsk_put(tw); } -EXPORT_SYMBOL(inet_twsk_deschedule); +EXPORT_SYMBOL(inet_twsk_deschedule_put); void inet_twsk_schedule(struct inet_timewait_sock *tw, const int timeo) { @@ -311,9 +285,8 @@ restart: rcu_read_unlock(); local_bh_disable(); - inet_twsk_deschedule(tw); + inet_twsk_deschedule_put(tw); local_bh_enable(); - inet_twsk_put(tw); goto restart_rcu; } /* If the nulls value we got at the end of this lookup is diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 241afd743d2c..86fa45809540 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -157,22 +157,6 @@ void __init inet_initpeers(void) INIT_DEFERRABLE_WORK(&gc_work, inetpeer_gc_worker); } -static int addr_compare(const struct inetpeer_addr *a, - const struct inetpeer_addr *b) -{ - int i, n = (a->family == AF_INET ? 1 : 4); - - for (i = 0; i < n; i++) { - if (a->addr.a6[i] == b->addr.a6[i]) - continue; - if ((__force u32)a->addr.a6[i] < (__force u32)b->addr.a6[i]) - return -1; - return 1; - } - - return 0; -} - #define rcu_deref_locked(X, BASE) \ rcu_dereference_protected(X, lockdep_is_held(&(BASE)->lock.lock)) @@ -188,7 +172,7 @@ static int addr_compare(const struct inetpeer_addr *a, *stackptr++ = &_base->root; \ for (u = rcu_deref_locked(_base->root, _base); \ u != peer_avl_empty;) { \ - int cmp = addr_compare(_daddr, &u->daddr); \ + int cmp = inetpeer_addr_cmp(_daddr, &u->daddr); \ if (cmp == 0) \ break; \ if (cmp == -1) \ @@ -215,7 +199,7 @@ static struct inet_peer *lookup_rcu(const struct inetpeer_addr *daddr, int count = 0; while (u != peer_avl_empty) { - int cmp = addr_compare(daddr, &u->daddr); + int cmp = inetpeer_addr_cmp(daddr, &u->daddr); if (cmp == 0) { /* Before taking a reference, check if this entry was * deleted (refcnt=-1) diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 921138f6c97c..fa7f15305f9a 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -48,6 +48,7 @@ #include <linux/inet.h> #include <linux/netfilter_ipv4.h> #include <net/inet_ecn.h> +#include <net/vrf.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c @@ -77,6 +78,7 @@ struct ipq { u8 ecn; /* RFC3168 support */ u16 max_df_size; /* largest frag with DF set seen */ int iif; + int vif; /* VRF device index */ unsigned int rid; struct inet_peer *peer; }; @@ -99,6 +101,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, struct ip4_create_arg { struct iphdr *iph; u32 user; + int vif; }; static unsigned int ipqhashfn(__be16 id, __be32 saddr, __be32 daddr, u8 prot) @@ -127,7 +130,8 @@ static bool ip4_frag_match(const struct inet_frag_queue *q, const void *a) qp->saddr == arg->iph->saddr && qp->daddr == arg->iph->daddr && qp->protocol == arg->iph->protocol && - qp->user == arg->user; + qp->user == arg->user && + qp->vif == arg->vif; } static void ip4_frag_init(struct inet_frag_queue *q, const void *a) @@ -144,9 +148,11 @@ static void ip4_frag_init(struct inet_frag_queue *q, const void *a) qp->ecn = ip4_frag_ecn(arg->iph->tos); qp->saddr = arg->iph->saddr; qp->daddr = arg->iph->daddr; + qp->vif = arg->vif; qp->user = arg->user; qp->peer = sysctl_ipfrag_max_dist ? - inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, 1) : NULL; + inet_getpeer_v4(net->ipv4.peers, arg->iph->saddr, arg->vif, 1) : + NULL; } static void ip4_frag_free(struct inet_frag_queue *q) @@ -244,7 +250,8 @@ out: /* Find the correct entry in the "incomplete datagrams" queue for * this IP datagram, and create new one, if nothing is found. */ -static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) +static struct ipq *ip_find(struct net *net, struct iphdr *iph, + u32 user, int vif) { struct inet_frag_queue *q; struct ip4_create_arg arg; @@ -252,6 +259,7 @@ static struct ipq *ip_find(struct net *net, struct iphdr *iph, u32 user) arg.iph = iph; arg.user = user; + arg.vif = vif; hash = ipqhashfn(iph->id, iph->saddr, iph->daddr, iph->protocol); @@ -522,7 +530,6 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, int len; int ihlen; int err; - int sum_truesize; u8 ecn; ipq_kill(qp); @@ -590,32 +597,19 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, add_frag_mem_limit(qp->q.net, clone->truesize); } + skb_shinfo(head)->frag_list = head->next; 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; + 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); - - if (skb_try_coalesce(head, fp, &headstolen, &delta)) { - kfree_skb_partial(fp, headstolen); - } else { - 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; + head->truesize += fp->truesize; } - sub_frag_mem_limit(qp->q.net, sum_truesize); + sub_frag_mem_limit(qp->q.net, head->truesize); head->next = NULL; head->dev = dev; @@ -662,14 +656,15 @@ out_fail: /* Process an incoming IP datagram fragment. */ int ip_defrag(struct sk_buff *skb, u32 user) { + struct net_device *dev = skb->dev ? : skb_dst(skb)->dev; + int vif = vrf_master_ifindex_rcu(dev); + struct net *net = dev_net(dev); struct ipq *qp; - struct net *net; - net = skb->dev ? dev_net(skb->dev) : dev_net(skb_dst(skb)->dev); IP_INC_STATS_BH(net, IPSTATS_MIB_REASMREQDS); /* Lookup (or create) queue header */ - qp = ip_find(net, ip_hdr(skb), user); + qp = ip_find(net, ip_hdr(skb), user, vif); if (qp) { int ret; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 5fd706473c73..bd0679d90519 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -25,6 +25,7 @@ #include <linux/udp.h> #include <linux/if_arp.h> #include <linux/mroute.h> +#include <linux/if_vlan.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> @@ -47,6 +48,7 @@ #include <net/netns/generic.h> #include <net/rtnetlink.h> #include <net/gre.h> +#include <net/dst_metadata.h> #if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> @@ -121,8 +123,127 @@ static int ipgre_tunnel_init(struct net_device *dev); static int ipgre_net_id __read_mostly; static int gre_tap_net_id __read_mostly; -static int ipgre_err(struct sk_buff *skb, u32 info, - const struct tnl_ptk_info *tpi) +static int ip_gre_calc_hlen(__be16 o_flags) +{ + int addend = 4; + + if (o_flags & TUNNEL_CSUM) + addend += 4; + if (o_flags & TUNNEL_KEY) + addend += 4; + if (o_flags & TUNNEL_SEQ) + addend += 4; + return addend; +} + +static __be16 gre_flags_to_tnl_flags(__be16 flags) +{ + __be16 tflags = 0; + + if (flags & GRE_CSUM) + tflags |= TUNNEL_CSUM; + if (flags & GRE_ROUTING) + tflags |= TUNNEL_ROUTING; + if (flags & GRE_KEY) + tflags |= TUNNEL_KEY; + if (flags & GRE_SEQ) + tflags |= TUNNEL_SEQ; + if (flags & GRE_STRICT) + tflags |= TUNNEL_STRICT; + if (flags & GRE_REC) + tflags |= TUNNEL_REC; + if (flags & GRE_VERSION) + tflags |= TUNNEL_VERSION; + + return tflags; +} + +static __be16 tnl_flags_to_gre_flags(__be16 tflags) +{ + __be16 flags = 0; + + if (tflags & TUNNEL_CSUM) + flags |= GRE_CSUM; + if (tflags & TUNNEL_ROUTING) + flags |= GRE_ROUTING; + if (tflags & TUNNEL_KEY) + flags |= GRE_KEY; + if (tflags & TUNNEL_SEQ) + flags |= GRE_SEQ; + if (tflags & TUNNEL_STRICT) + flags |= GRE_STRICT; + if (tflags & TUNNEL_REC) + flags |= GRE_REC; + if (tflags & TUNNEL_VERSION) + flags |= GRE_VERSION; + + return flags; +} + +static int parse_gre_header(struct sk_buff *skb, struct tnl_ptk_info *tpi, + bool *csum_err) +{ + const struct gre_base_hdr *greh; + __be32 *options; + int hdr_len; + + if (unlikely(!pskb_may_pull(skb, sizeof(struct gre_base_hdr)))) + return -EINVAL; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + if (unlikely(greh->flags & (GRE_VERSION | GRE_ROUTING))) + return -EINVAL; + + tpi->flags = gre_flags_to_tnl_flags(greh->flags); + hdr_len = ip_gre_calc_hlen(tpi->flags); + + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + + greh = (struct gre_base_hdr *)skb_transport_header(skb); + tpi->proto = greh->protocol; + + options = (__be32 *)(greh + 1); + if (greh->flags & GRE_CSUM) { + if (skb_checksum_simple_validate(skb)) { + *csum_err = true; + return -EINVAL; + } + + skb_checksum_try_convert(skb, IPPROTO_GRE, 0, + null_compute_pseudo); + options++; + } + + if (greh->flags & GRE_KEY) { + tpi->key = *options; + options++; + } else { + tpi->key = 0; + } + if (unlikely(greh->flags & GRE_SEQ)) { + tpi->seq = *options; + options++; + } else { + tpi->seq = 0; + } + /* WCCP version 1 and 2 protocol decoding. + * - Change protocol to IP + * - When dealing with WCCPv2, Skip extra 4 bytes in GRE header + */ + if (greh->flags == 0 && tpi->proto == htons(ETH_P_WCCP)) { + tpi->proto = htons(ETH_P_IP); + if ((*(u8 *)options & 0xF0) != 0x40) { + hdr_len += 4; + if (!pskb_may_pull(skb, hdr_len)) + return -EINVAL; + } + } + return iptunnel_pull_header(skb, hdr_len, tpi->proto); +} + +static void ipgre_err(struct sk_buff *skb, u32 info, + const struct tnl_ptk_info *tpi) { /* All the routers (except for Linux) return only @@ -148,14 +269,14 @@ static int ipgre_err(struct sk_buff *skb, u32 info, switch (type) { default: case ICMP_PARAMETERPROB: - return PACKET_RCVD; + return; case ICMP_DEST_UNREACH: switch (code) { case ICMP_SR_FAILED: case ICMP_PORT_UNREACH: /* Impossible event. */ - return PACKET_RCVD; + return; default: /* All others are translated to HOST_UNREACH. rfc2003 contains "deep thoughts" about NET_UNREACH, @@ -164,9 +285,10 @@ static int ipgre_err(struct sk_buff *skb, u32 info, break; } break; + case ICMP_TIME_EXCEEDED: if (code != ICMP_EXC_TTL) - return PACKET_RCVD; + return; break; case ICMP_REDIRECT: @@ -183,26 +305,85 @@ static int ipgre_err(struct sk_buff *skb, u32 info, iph->daddr, iph->saddr, tpi->key); if (!t) - return PACKET_REJECT; + return; if (t->parms.iph.daddr == 0 || ipv4_is_multicast(t->parms.iph.daddr)) - return PACKET_RCVD; + return; if (t->parms.iph.ttl == 0 && type == ICMP_TIME_EXCEEDED) - return PACKET_RCVD; + return; if (time_before(jiffies, t->err_time + IPTUNNEL_ERR_TIMEO)) t->err_count++; else t->err_count = 1; t->err_time = jiffies; - return PACKET_RCVD; +} + +static void gre_err(struct sk_buff *skb, u32 info) +{ + /* All the routers (except for Linux) return only + * 8 bytes of packet payload. It means, that precise relaying of + * ICMP in the real Internet is absolutely infeasible. + * + * Moreover, Cisco "wise men" put GRE key to the third word + * in GRE header. It makes impossible maintaining even soft + * state for keyed + * GRE tunnels with enabled checksum. Tell them "thank you". + * + * Well, I wonder, rfc1812 was written by Cisco employee, + * what the hell these idiots break standards established + * by themselves??? + */ + + const int type = icmp_hdr(skb)->type; + const int code = icmp_hdr(skb)->code; + struct tnl_ptk_info tpi; + bool csum_err = false; + + if (parse_gre_header(skb, &tpi, &csum_err)) { + if (!csum_err) /* ignore csum errors. */ + return; + } + + if (type == ICMP_DEST_UNREACH && code == ICMP_FRAG_NEEDED) { + ipv4_update_pmtu(skb, dev_net(skb->dev), info, + skb->dev->ifindex, 0, IPPROTO_GRE, 0); + return; + } + if (type == ICMP_REDIRECT) { + ipv4_redirect(skb, dev_net(skb->dev), skb->dev->ifindex, 0, + IPPROTO_GRE, 0); + return; + } + + ipgre_err(skb, info, &tpi); +} + +static __be64 key_to_tunnel_id(__be32 key) +{ +#ifdef __BIG_ENDIAN + return (__force __be64)((__force u32)key); +#else + return (__force __be64)((__force u64)key << 32); +#endif +} + +/* Returns the least-significant 32 bits of a __be64. */ +static __be32 tunnel_id_to_key(__be64 x) +{ +#ifdef __BIG_ENDIAN + return (__force __be32)x; +#else + return (__force __be32)((__force u64)x >> 32); +#endif } static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) { struct net *net = dev_net(skb->dev); + struct metadata_dst *tun_dst = NULL; struct ip_tunnel_net *itn; const struct iphdr *iph; struct ip_tunnel *tunnel; @@ -218,40 +399,184 @@ static int ipgre_rcv(struct sk_buff *skb, const struct tnl_ptk_info *tpi) if (tunnel) { skb_pop_mac_header(skb); - ip_tunnel_rcv(tunnel, skb, tpi, log_ecn_error); + if (tunnel->collect_md) { + __be16 flags; + __be64 tun_id; + + flags = tpi->flags & (TUNNEL_CSUM | TUNNEL_KEY); + tun_id = key_to_tunnel_id(tpi->key); + tun_dst = ip_tun_rx_dst(skb, flags, tun_id, 0); + if (!tun_dst) + return PACKET_REJECT; + } + + ip_tunnel_rcv(tunnel, skb, tpi, tun_dst, log_ecn_error); return PACKET_RCVD; } return PACKET_REJECT; } +static int gre_rcv(struct sk_buff *skb) +{ + struct tnl_ptk_info tpi; + bool csum_err = false; + +#ifdef CONFIG_NET_IPGRE_BROADCAST + if (ipv4_is_multicast(ip_hdr(skb)->daddr)) { + /* Looped back packet, drop it! */ + if (rt_is_output_route(skb_rtable(skb))) + goto drop; + } +#endif + + if (parse_gre_header(skb, &tpi, &csum_err) < 0) + goto drop; + + if (ipgre_rcv(skb, &tpi) == PACKET_RCVD) + return 0; + + icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); +drop: + kfree_skb(skb); + return 0; +} + +static void build_header(struct sk_buff *skb, int hdr_len, __be16 flags, + __be16 proto, __be32 key, __be32 seq) +{ + struct gre_base_hdr *greh; + + skb_push(skb, hdr_len); + + skb_reset_transport_header(skb); + greh = (struct gre_base_hdr *)skb->data; + greh->flags = tnl_flags_to_gre_flags(flags); + greh->protocol = proto; + + if (flags & (TUNNEL_KEY | TUNNEL_CSUM | TUNNEL_SEQ)) { + __be32 *ptr = (__be32 *)(((u8 *)greh) + hdr_len - 4); + + if (flags & TUNNEL_SEQ) { + *ptr = seq; + ptr--; + } + if (flags & TUNNEL_KEY) { + *ptr = key; + ptr--; + } + if (flags & TUNNEL_CSUM && + !(skb_shinfo(skb)->gso_type & + (SKB_GSO_GRE | SKB_GSO_GRE_CSUM))) { + *ptr = 0; + *(__sum16 *)ptr = csum_fold(skb_checksum(skb, 0, + skb->len, 0)); + } + } +} + static void __gre_xmit(struct sk_buff *skb, struct net_device *dev, const struct iphdr *tnl_params, __be16 proto) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct tnl_ptk_info tpi; - tpi.flags = tunnel->parms.o_flags; - tpi.proto = proto; - tpi.key = tunnel->parms.o_key; if (tunnel->parms.o_flags & TUNNEL_SEQ) tunnel->o_seqno++; - tpi.seq = htonl(tunnel->o_seqno); /* Push GRE header. */ - gre_build_header(skb, &tpi, tunnel->tun_hlen); - - skb_set_inner_protocol(skb, tpi.proto); + build_header(skb, tunnel->tun_hlen, tunnel->parms.o_flags, + proto, tunnel->parms.o_key, htonl(tunnel->o_seqno)); + skb_set_inner_protocol(skb, proto); ip_tunnel_xmit(skb, dev, tnl_params, tnl_params->protocol); } +static struct sk_buff *gre_handle_offloads(struct sk_buff *skb, + bool csum) +{ + return iptunnel_handle_offloads(skb, csum, + csum ? SKB_GSO_GRE_CSUM : SKB_GSO_GRE); +} + +static void gre_fb_xmit(struct sk_buff *skb, struct net_device *dev) +{ + struct ip_tunnel_info *tun_info; + struct net *net = dev_net(dev); + const struct ip_tunnel_key *key; + struct flowi4 fl; + struct rtable *rt; + int min_headroom; + int tunnel_hlen; + __be16 df, flags; + int err; + + tun_info = skb_tunnel_info(skb); + if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || + ip_tunnel_info_af(tun_info) != AF_INET)) + goto err_free_skb; + + key = &tun_info->key; + 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; + + rt = ip_route_output_key(net, &fl); + if (IS_ERR(rt)) + goto err_free_skb; + + tunnel_hlen = ip_gre_calc_hlen(key->tun_flags); + + 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; + } + + /* Push Tunnel header. */ + skb = gre_handle_offloads(skb, !!(tun_info->key.tun_flags & TUNNEL_CSUM)); + if (IS_ERR(skb)) { + skb = NULL; + goto err_free_rt; + } + + flags = tun_info->key.tun_flags & (TUNNEL_CSUM | TUNNEL_KEY); + build_header(skb, tunnel_hlen, flags, htons(ETH_P_TEB), + tunnel_id_to_key(tun_info->key.tun_id), 0); + + df = key->tun_flags & TUNNEL_DONT_FRAGMENT ? htons(IP_DF) : 0; + err = iptunnel_xmit(skb->sk, rt, skb, fl.saddr, + key->u.ipv4.dst, IPPROTO_GRE, + key->tos, key->ttl, df, false); + iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + return; + +err_free_rt: + ip_rt_put(rt); +err_free_skb: + kfree_skb(skb); + dev->stats.tx_dropped++; +} + static netdev_tx_t ipgre_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); const struct iphdr *tnl_params; + if (tunnel->collect_md) { + gre_fb_xmit(skb, dev); + return NETDEV_TX_OK; + } + if (dev->header_ops) { /* Need space for new headers */ if (skb_cow_head(skb, dev->needed_headroom - @@ -277,7 +602,6 @@ static netdev_tx_t ipgre_xmit(struct sk_buff *skb, goto out; __gre_xmit(skb, dev, tnl_params, skb->protocol); - return NETDEV_TX_OK; free_skb: @@ -292,6 +616,11 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, { struct ip_tunnel *tunnel = netdev_priv(dev); + if (tunnel->collect_md) { + gre_fb_xmit(skb, dev); + return NETDEV_TX_OK; + } + skb = gre_handle_offloads(skb, !!(tunnel->parms.o_flags&TUNNEL_CSUM)); if (IS_ERR(skb)) goto out; @@ -300,7 +629,6 @@ static netdev_tx_t gre_tap_xmit(struct sk_buff *skb, goto free_skb; __gre_xmit(skb, dev, &tunnel->parms.iph, htons(ETH_P_TEB)); - return NETDEV_TX_OK; free_skb: @@ -530,10 +858,9 @@ static int ipgre_tunnel_init(struct net_device *dev) return ip_tunnel_init(dev); } -static struct gre_cisco_protocol ipgre_protocol = { - .handler = ipgre_rcv, - .err_handler = ipgre_err, - .priority = 0, +static const struct gre_protocol ipgre_protocol = { + .handler = gre_rcv, + .err_handler = gre_err, }; static int __net_init ipgre_init_net(struct net *net) @@ -596,8 +923,10 @@ out: return ipgre_tunnel_validate(tb, data); } -static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], - struct ip_tunnel_parm *parms) +static void ipgre_netlink_parms(struct net_device *dev, + struct nlattr *data[], + struct nlattr *tb[], + struct ip_tunnel_parm *parms) { memset(parms, 0, sizeof(*parms)); @@ -635,6 +964,12 @@ static void ipgre_netlink_parms(struct nlattr *data[], struct nlattr *tb[], if (!data[IFLA_GRE_PMTUDISC] || nla_get_u8(data[IFLA_GRE_PMTUDISC])) parms->iph.frag_off = htons(IP_DF); + + if (data[IFLA_GRE_COLLECT_METADATA]) { + struct ip_tunnel *t = netdev_priv(dev); + + t->collect_md = true; + } } /* This function returns true when ENCAP attributes are present in the nl msg */ @@ -712,7 +1047,7 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, return err; } - ipgre_netlink_parms(data, tb, &p); + ipgre_netlink_parms(dev, data, tb, &p); return ip_tunnel_newlink(dev, tb, &p); } @@ -730,7 +1065,7 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], return err; } - ipgre_netlink_parms(data, tb, &p); + ipgre_netlink_parms(dev, data, tb, &p); return ip_tunnel_changelink(dev, tb, &p); } @@ -765,6 +1100,8 @@ static size_t ipgre_get_size(const struct net_device *dev) nla_total_size(2) + /* IFLA_GRE_ENCAP_DPORT */ nla_total_size(2) + + /* IFLA_GRE_COLLECT_METADATA */ + nla_total_size(0) + 0; } @@ -796,6 +1133,11 @@ static int ipgre_fill_info(struct sk_buff *skb, const struct net_device *dev) t->encap.flags)) goto nla_put_failure; + if (t->collect_md) { + if (nla_put_flag(skb, IFLA_GRE_COLLECT_METADATA)) + goto nla_put_failure; + } + return 0; nla_put_failure: @@ -817,6 +1159,7 @@ static const struct nla_policy ipgre_policy[IFLA_GRE_MAX + 1] = { [IFLA_GRE_ENCAP_FLAGS] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_SPORT] = { .type = NLA_U16 }, [IFLA_GRE_ENCAP_DPORT] = { .type = NLA_U16 }, + [IFLA_GRE_COLLECT_METADATA] = { .type = NLA_FLAG }, }; static struct rtnl_link_ops ipgre_link_ops __read_mostly = { @@ -849,9 +1192,38 @@ static struct rtnl_link_ops ipgre_tap_ops __read_mostly = { .get_link_net = ip_tunnel_get_link_net, }; +struct net_device *gretap_fb_dev_create(struct net *net, const char *name, + u8 name_assign_type) +{ + struct nlattr *tb[IFLA_MAX + 1]; + struct net_device *dev; + struct ip_tunnel *t; + int err; + + memset(&tb, 0, sizeof(tb)); + + dev = rtnl_create_link(net, name, name_assign_type, + &ipgre_tap_ops, tb); + if (IS_ERR(dev)) + return dev; + + /* Configure flow based GRE device. */ + t = netdev_priv(dev); + t->collect_md = true; + + err = ipgre_newlink(net, dev, tb, NULL); + if (err < 0) + goto out; + return dev; +out: + free_netdev(dev); + return ERR_PTR(err); +} +EXPORT_SYMBOL_GPL(gretap_fb_dev_create); + static int __net_init ipgre_tap_init_net(struct net *net) { - return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, NULL); + return ip_tunnel_init_net(net, gre_tap_net_id, &ipgre_tap_ops, "gretap0"); } static void __net_exit ipgre_tap_exit_net(struct net *net) @@ -881,7 +1253,7 @@ static int __init ipgre_init(void) if (err < 0) goto pnet_tap_faied; - err = gre_cisco_register(&ipgre_protocol); + err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { pr_info("%s: can't add protocol\n", __func__); goto add_proto_failed; @@ -900,7 +1272,7 @@ static int __init ipgre_init(void) tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - gre_cisco_unregister(&ipgre_protocol); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&ipgre_tap_net_ops); pnet_tap_faied: @@ -912,7 +1284,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - gre_cisco_unregister(&ipgre_protocol); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); unregister_pernet_device(&ipgre_tap_net_ops); unregister_pernet_device(&ipgre_net_ops); } diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index 2db4c8773c1b..f4fc8a77aaa7 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -146,6 +146,7 @@ #include <net/xfrm.h> #include <linux/mroute.h> #include <linux/netlink.h> +#include <net/dst_metadata.h> /* * Process Router Attention IP option (RFC 2113) @@ -331,7 +332,7 @@ static int ip_rcv_finish(struct sock *sk, struct sk_buff *skb) * Initialise the virtual path cache for the packet. It describes * how the packet travels inside Linux networking. */ - if (!skb_dst(skb)) { + if (!skb_valid_dst(skb)) { int err = ip_route_input_noref(skb, iph->daddr, iph->saddr, iph->tos, skb->dev); if (unlikely(err)) { diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 6bf89a6312bc..0138fada0951 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -1542,6 +1542,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, struct net *net = sock_net(sk); struct sk_buff *nskb; int err; + int oif; if (__ip_options_echo(&replyopts.opt.opt, skb, sopt)) return; @@ -1559,7 +1560,11 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, daddr = replyopts.opt.opt.faddr; } - flowi4_init_output(&fl4, arg->bound_dev_if, + oif = arg->bound_dev_if; + if (!oif && netif_index_is_vrf(net, skb->skb_iif)) + oif = skb->skb_iif; + + flowi4_init_output(&fl4, oif, IP4_REPLY_MARK(net, skb->mark), RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, diff --git a/net/ipv4/ip_tunnel.c b/net/ipv4/ip_tunnel.c index 626d9e56a6bd..cbb51f3fac06 100644 --- a/net/ipv4/ip_tunnel.c +++ b/net/ipv4/ip_tunnel.c @@ -230,10 +230,13 @@ skip_key_lookup: if (cand) return cand; + t = rcu_dereference(itn->collect_md_tun); + if (t) + return t; + if (itn->fb_tunnel_dev && itn->fb_tunnel_dev->flags & IFF_UP) return netdev_priv(itn->fb_tunnel_dev); - return NULL; } EXPORT_SYMBOL_GPL(ip_tunnel_lookup); @@ -261,11 +264,15 @@ static void ip_tunnel_add(struct ip_tunnel_net *itn, struct ip_tunnel *t) { struct hlist_head *head = ip_bucket(itn, &t->parms); + if (t->collect_md) + rcu_assign_pointer(itn->collect_md_tun, t); hlist_add_head_rcu(&t->hash_node, head); } -static void ip_tunnel_del(struct ip_tunnel *t) +static void ip_tunnel_del(struct ip_tunnel_net *itn, struct ip_tunnel *t) { + if (t->collect_md) + rcu_assign_pointer(itn->collect_md_tun, NULL); hlist_del_init_rcu(&t->hash_node); } @@ -419,7 +426,8 @@ static struct ip_tunnel *ip_tunnel_create(struct net *net, } int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, - const struct tnl_ptk_info *tpi, bool log_ecn_error) + const struct tnl_ptk_info *tpi, struct metadata_dst *tun_dst, + bool log_ecn_error) { struct pcpu_sw_netstats *tstats; const struct iphdr *iph = ip_hdr(skb); @@ -478,6 +486,9 @@ int ip_tunnel_rcv(struct ip_tunnel *tunnel, struct sk_buff *skb, skb->dev = tunnel->dev; } + if (tun_dst) + skb_dst_set(skb, (struct dst_entry *)tun_dst); + gro_cells_receive(&tunnel->gro_cells, skb); return 0; @@ -806,7 +817,7 @@ static void ip_tunnel_update(struct ip_tunnel_net *itn, struct ip_tunnel_parm *p, bool set_mtu) { - ip_tunnel_del(t); + ip_tunnel_del(itn, t); t->parms.iph.saddr = p->iph.saddr; t->parms.iph.daddr = p->iph.daddr; t->parms.i_key = p->i_key; @@ -967,7 +978,7 @@ void ip_tunnel_dellink(struct net_device *dev, struct list_head *head) itn = net_generic(tunnel->net, tunnel->ip_tnl_net_id); if (itn->fb_tunnel_dev != dev) { - ip_tunnel_del(netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); unregister_netdevice_queue(dev, head); } } @@ -1072,8 +1083,13 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], nt = netdev_priv(dev); itn = net_generic(net, nt->ip_tnl_net_id); - if (ip_tunnel_find(itn, p, dev->type)) - return -EEXIST; + if (nt->collect_md) { + if (rtnl_dereference(itn->collect_md_tun)) + return -EEXIST; + } else { + if (ip_tunnel_find(itn, p, dev->type)) + return -EEXIST; + } nt->net = net; nt->parms = *p; @@ -1089,7 +1105,6 @@ int ip_tunnel_newlink(struct net_device *dev, struct nlattr *tb[], dev->mtu = mtu; ip_tunnel_add(itn, nt); - out: return err; } @@ -1163,6 +1178,10 @@ int ip_tunnel_init(struct net_device *dev) iph->version = 4; iph->ihl = 5; + if (tunnel->collect_md) { + dev->features |= NETIF_F_NETNS_LOCAL; + netif_keep_dst(dev); + } return 0; } EXPORT_SYMBOL_GPL(ip_tunnel_init); @@ -1176,7 +1195,7 @@ void ip_tunnel_uninit(struct net_device *dev) itn = net_generic(net, tunnel->ip_tnl_net_id); /* fb_tunnel_dev will be unregisted in net-exit call. */ if (itn->fb_tunnel_dev != dev) - ip_tunnel_del(netdev_priv(dev)); + ip_tunnel_del(itn, netdev_priv(dev)); ip_tunnel_dst_reset_all(tunnel); } diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 6a51a71a6c67..29ed6c5a5185 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -32,6 +32,7 @@ #include <linux/etherdevice.h> #include <linux/if_ether.h> #include <linux/if_vlan.h> +#include <linux/static_key.h> #include <net/ip.h> #include <net/icmp.h> @@ -190,3 +191,232 @@ struct rtnl_link_stats64 *ip_tunnel_get_stats64(struct net_device *dev, return tot; } EXPORT_SYMBOL_GPL(ip_tunnel_get_stats64); + +static const struct nla_policy ip_tun_policy[LWTUNNEL_IP_MAX + 1] = { + [LWTUNNEL_IP_ID] = { .type = NLA_U64 }, + [LWTUNNEL_IP_DST] = { .type = NLA_U32 }, + [LWTUNNEL_IP_SRC] = { .type = NLA_U32 }, + [LWTUNNEL_IP_TTL] = { .type = NLA_U8 }, + [LWTUNNEL_IP_TOS] = { .type = NLA_U8 }, + [LWTUNNEL_IP_SPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP_DPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP_FLAGS] = { .type = NLA_U16 }, +}; + +static int ip_tun_build_state(struct net_device *dev, struct nlattr *attr, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct ip_tunnel_info *tun_info; + struct lwtunnel_state *new_state; + struct nlattr *tb[LWTUNNEL_IP_MAX + 1]; + int err; + + err = nla_parse_nested(tb, LWTUNNEL_IP_MAX, attr, ip_tun_policy); + if (err < 0) + return err; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + if (!new_state) + return -ENOMEM; + + new_state->type = LWTUNNEL_ENCAP_IP; + + tun_info = lwt_tun_info(new_state); + + if (tb[LWTUNNEL_IP_ID]) + tun_info->key.tun_id = nla_get_u64(tb[LWTUNNEL_IP_ID]); + + if (tb[LWTUNNEL_IP_DST]) + tun_info->key.u.ipv4.dst = nla_get_be32(tb[LWTUNNEL_IP_DST]); + + if (tb[LWTUNNEL_IP_SRC]) + tun_info->key.u.ipv4.src = nla_get_be32(tb[LWTUNNEL_IP_SRC]); + + if (tb[LWTUNNEL_IP_TTL]) + tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP_TTL]); + + if (tb[LWTUNNEL_IP_TOS]) + tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP_TOS]); + + if (tb[LWTUNNEL_IP_SPORT]) + tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP_SPORT]); + + if (tb[LWTUNNEL_IP_DPORT]) + tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP_DPORT]); + + if (tb[LWTUNNEL_IP_FLAGS]) + tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP_FLAGS]); + + tun_info->mode = IP_TUNNEL_INFO_TX; + tun_info->options_len = 0; + + *ts = new_state; + + return 0; +} + +static int ip_tun_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); + + if (nla_put_u64(skb, LWTUNNEL_IP_ID, tun_info->key.tun_id) || + nla_put_be32(skb, LWTUNNEL_IP_DST, tun_info->key.u.ipv4.dst) || + nla_put_be32(skb, LWTUNNEL_IP_SRC, tun_info->key.u.ipv4.src) || + nla_put_u8(skb, LWTUNNEL_IP_TOS, tun_info->key.tos) || + nla_put_u8(skb, LWTUNNEL_IP_TTL, tun_info->key.ttl) || + nla_put_u16(skb, LWTUNNEL_IP_SPORT, tun_info->key.tp_src) || + nla_put_u16(skb, LWTUNNEL_IP_DPORT, tun_info->key.tp_dst) || + nla_put_u16(skb, LWTUNNEL_IP_FLAGS, tun_info->key.tun_flags)) + return -ENOMEM; + + return 0; +} + +static int ip_tun_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + return nla_total_size(8) /* LWTUNNEL_IP_ID */ + + nla_total_size(4) /* LWTUNNEL_IP_DST */ + + nla_total_size(4) /* LWTUNNEL_IP_SRC */ + + nla_total_size(1) /* LWTUNNEL_IP_TOS */ + + nla_total_size(1) /* LWTUNNEL_IP_TTL */ + + nla_total_size(2) /* LWTUNNEL_IP_SPORT */ + + nla_total_size(2) /* LWTUNNEL_IP_DPORT */ + + nla_total_size(2); /* LWTUNNEL_IP_FLAGS */ +} + +static int ip_tun_cmp_encap(struct lwtunnel_state *a, struct lwtunnel_state *b) +{ + return memcmp(lwt_tun_info(a), lwt_tun_info(b), + sizeof(struct ip_tunnel_info)); +} + +static const struct lwtunnel_encap_ops ip_tun_lwt_ops = { + .build_state = ip_tun_build_state, + .fill_encap = ip_tun_fill_encap_info, + .get_encap_size = ip_tun_encap_nlsize, + .cmp_encap = ip_tun_cmp_encap, +}; + +static const struct nla_policy ip6_tun_policy[LWTUNNEL_IP6_MAX + 1] = { + [LWTUNNEL_IP6_ID] = { .type = NLA_U64 }, + [LWTUNNEL_IP6_DST] = { .len = sizeof(struct in6_addr) }, + [LWTUNNEL_IP6_SRC] = { .len = sizeof(struct in6_addr) }, + [LWTUNNEL_IP6_HOPLIMIT] = { .type = NLA_U8 }, + [LWTUNNEL_IP6_TC] = { .type = NLA_U8 }, + [LWTUNNEL_IP6_SPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP6_DPORT] = { .type = NLA_U16 }, + [LWTUNNEL_IP6_FLAGS] = { .type = NLA_U16 }, +}; + +static int ip6_tun_build_state(struct net_device *dev, struct nlattr *attr, + unsigned int family, const void *cfg, + struct lwtunnel_state **ts) +{ + struct ip_tunnel_info *tun_info; + struct lwtunnel_state *new_state; + struct nlattr *tb[LWTUNNEL_IP6_MAX + 1]; + int err; + + err = nla_parse_nested(tb, LWTUNNEL_IP6_MAX, attr, ip6_tun_policy); + if (err < 0) + return err; + + new_state = lwtunnel_state_alloc(sizeof(*tun_info)); + if (!new_state) + return -ENOMEM; + + new_state->type = LWTUNNEL_ENCAP_IP6; + + tun_info = lwt_tun_info(new_state); + + if (tb[LWTUNNEL_IP6_ID]) + tun_info->key.tun_id = nla_get_u64(tb[LWTUNNEL_IP6_ID]); + + if (tb[LWTUNNEL_IP6_DST]) + tun_info->key.u.ipv6.dst = nla_get_in6_addr(tb[LWTUNNEL_IP6_DST]); + + if (tb[LWTUNNEL_IP6_SRC]) + tun_info->key.u.ipv6.src = nla_get_in6_addr(tb[LWTUNNEL_IP6_SRC]); + + if (tb[LWTUNNEL_IP6_HOPLIMIT]) + tun_info->key.ttl = nla_get_u8(tb[LWTUNNEL_IP6_HOPLIMIT]); + + if (tb[LWTUNNEL_IP6_TC]) + tun_info->key.tos = nla_get_u8(tb[LWTUNNEL_IP6_TC]); + + if (tb[LWTUNNEL_IP6_SPORT]) + tun_info->key.tp_src = nla_get_be16(tb[LWTUNNEL_IP6_SPORT]); + + if (tb[LWTUNNEL_IP6_DPORT]) + tun_info->key.tp_dst = nla_get_be16(tb[LWTUNNEL_IP6_DPORT]); + + if (tb[LWTUNNEL_IP6_FLAGS]) + tun_info->key.tun_flags = nla_get_u16(tb[LWTUNNEL_IP6_FLAGS]); + + tun_info->mode = IP_TUNNEL_INFO_TX | IP_TUNNEL_INFO_IPV6; + tun_info->options_len = 0; + + *ts = new_state; + + return 0; +} + +static int ip6_tun_fill_encap_info(struct sk_buff *skb, + struct lwtunnel_state *lwtstate) +{ + struct ip_tunnel_info *tun_info = lwt_tun_info(lwtstate); + + if (nla_put_u64(skb, LWTUNNEL_IP6_ID, tun_info->key.tun_id) || + nla_put_in6_addr(skb, LWTUNNEL_IP6_DST, &tun_info->key.u.ipv6.dst) || + nla_put_in6_addr(skb, LWTUNNEL_IP6_SRC, &tun_info->key.u.ipv6.src) || + nla_put_u8(skb, LWTUNNEL_IP6_HOPLIMIT, tun_info->key.tos) || + nla_put_u8(skb, LWTUNNEL_IP6_TC, tun_info->key.ttl) || + nla_put_u16(skb, LWTUNNEL_IP6_SPORT, tun_info->key.tp_src) || + nla_put_u16(skb, LWTUNNEL_IP6_DPORT, tun_info->key.tp_dst) || + nla_put_u16(skb, LWTUNNEL_IP6_FLAGS, tun_info->key.tun_flags)) + return -ENOMEM; + + return 0; +} + +static int ip6_tun_encap_nlsize(struct lwtunnel_state *lwtstate) +{ + return nla_total_size(8) /* LWTUNNEL_IP6_ID */ + + nla_total_size(16) /* LWTUNNEL_IP6_DST */ + + nla_total_size(16) /* LWTUNNEL_IP6_SRC */ + + nla_total_size(1) /* LWTUNNEL_IP6_HOPLIMIT */ + + nla_total_size(1) /* LWTUNNEL_IP6_TC */ + + nla_total_size(2) /* LWTUNNEL_IP6_SPORT */ + + nla_total_size(2) /* LWTUNNEL_IP6_DPORT */ + + nla_total_size(2); /* LWTUNNEL_IP6_FLAGS */ +} + +static const struct lwtunnel_encap_ops ip6_tun_lwt_ops = { + .build_state = ip6_tun_build_state, + .fill_encap = ip6_tun_fill_encap_info, + .get_encap_size = ip6_tun_encap_nlsize, + .cmp_encap = ip_tun_cmp_encap, +}; + +void __init ip_tunnel_core_init(void) +{ + lwtunnel_encap_add_ops(&ip_tun_lwt_ops, LWTUNNEL_ENCAP_IP); + lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6); +} + +struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE; +EXPORT_SYMBOL(ip_tunnel_metadata_cnt); + +void ip_tunnel_need_metadata(void) +{ + static_key_slow_inc(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); + +void ip_tunnel_unneed_metadata(void) +{ + static_key_slow_dec(&ip_tunnel_metadata_cnt); +} +EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 8e7328c6a390..ed4ef09c2136 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -94,7 +94,7 @@ /* Define the timeout for waiting for a DHCP/BOOTP/RARP reply */ #define CONF_OPEN_RETRIES 2 /* (Re)open devices twice */ #define CONF_SEND_RETRIES 6 /* Send six requests per open */ -#define CONF_INTER_TIMEOUT (HZ/2) /* Inter-device timeout: 1/2 second */ +#define CONF_INTER_TIMEOUT (HZ) /* Inter-device timeout: 1 second */ #define CONF_BASE_TIMEOUT (HZ*2) /* Initial timeout: 2 seconds */ #define CONF_TIMEOUT_RANDOM (HZ) /* Maximum amount of randomization */ #define CONF_TIMEOUT_MULT *7/4 /* Rate of timeout growth */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 254238daf58b..f34c31defafe 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -198,7 +198,7 @@ static int ipip_rcv(struct sk_buff *skb) goto drop; if (iptunnel_pull_header(skb, 0, tpi.proto)) goto drop; - return ip_tunnel_rcv(tunnel, skb, &tpi, log_ecn_error); + return ip_tunnel_rcv(tunnel, skb, &tpi, NULL, log_ecn_error); } return -1; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 2199a5db25e6..690d27d3f2f9 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -58,6 +58,12 @@ config NFT_REJECT_IPV4 default NFT_REJECT tristate +config NFT_DUP_IPV4 + tristate "IPv4 nf_tables packet duplication support" + select NF_DUP_IPV4 + help + This module enables IPv4 packet duplication support for nf_tables. + endif # NF_TABLES_IPV4 config NF_TABLES_ARP @@ -67,6 +73,12 @@ config NF_TABLES_ARP endif # NF_TABLES +config NF_DUP_IPV4 + tristate "Netfilter IPv4 packet duplication to alternate destination" + help + This option enables the nf_dup_ipv4 core, which duplicates an IPv4 + packet to be rerouted to another destination. + config NF_LOG_ARP tristate "ARP packet logging" default m if NETFILTER_ADVANCED=n diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 7fe6c703528f..87b073da14c9 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -41,6 +41,7 @@ obj-$(CONFIG_NFT_CHAIN_NAT_IPV4) += nft_chain_nat_ipv4.o obj-$(CONFIG_NFT_REJECT_IPV4) += nft_reject_ipv4.o obj-$(CONFIG_NFT_MASQ_IPV4) += nft_masq_ipv4.o obj-$(CONFIG_NFT_REDIR_IPV4) += nft_redir_ipv4.o +obj-$(CONFIG_NFT_DUP_IPV4) += nft_dup_ipv4.o obj-$(CONFIG_NF_TABLES_ARP) += nf_tables_arp.o # generic IP tables @@ -70,3 +71,5 @@ obj-$(CONFIG_IP_NF_ARP_MANGLE) += arpt_mangle.o # just filtering instance of ARP tables for now obj-$(CONFIG_IP_NF_ARPFILTER) += arptable_filter.o + +obj-$(CONFIG_NF_DUP_IPV4) += nf_dup_ipv4.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 92305a1a021a..8f87fc38ccde 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -240,7 +240,7 @@ get_entry(const void *base, unsigned int offset) return (struct arpt_entry *)(base + offset); } -static inline __pure +static inline struct arpt_entry *arpt_next_entry(const struct arpt_entry *entry) { return (void *)entry + entry->next_offset; @@ -280,6 +280,9 @@ unsigned int arpt_do_table(struct sk_buff *skb, table_base = private->entries; jumpstack = (struct arpt_entry **)private->jumpstack[cpu]; + /* No TEE support for arptables, so no need to switch to alternate + * stack. All targets that reenter must return absolute verdicts. + */ e = get_entry(table_base, private->hook_entry[hook]); acpar.in = state->in; @@ -325,11 +328,6 @@ unsigned int arpt_do_table(struct sk_buff *skb, } if (table_base + v != arpt_next_entry(e)) { - - if (stackidx >= private->stacksize) { - verdict = NF_DROP; - break; - } jumpstack[stackidx++] = e; } @@ -337,9 +335,6 @@ unsigned int arpt_do_table(struct sk_buff *skb, continue; } - /* Targets which reenter must return - * abs. verdicts - */ acpar.target = t->u.kernel.target; acpar.targinfo = t->data; verdict = t->u.kernel.target->target(skb, &acpar); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 6c72fbb7b49e..b0a86e73451c 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -276,7 +276,7 @@ static void trace_packet(const struct sk_buff *skb, } #endif -static inline __pure +static inline struct ipt_entry *ipt_next_entry(const struct ipt_entry *entry) { return (void *)entry + entry->next_offset; @@ -296,12 +296,13 @@ ipt_do_table(struct sk_buff *skb, const char *indev, *outdev; const void *table_base; struct ipt_entry *e, **jumpstack; - unsigned int *stackptr, origptr, cpu; + unsigned int stackidx, cpu; const struct xt_table_info *private; struct xt_action_param acpar; unsigned int addend; /* Initialization */ + stackidx = 0; ip = ip_hdr(skb); indev = state->in ? state->in->name : nulldevname; outdev = state->out ? state->out->name : nulldevname; @@ -331,13 +332,21 @@ ipt_do_table(struct sk_buff *skb, smp_read_barrier_depends(); table_base = private->entries; jumpstack = (struct ipt_entry **)private->jumpstack[cpu]; - stackptr = per_cpu_ptr(private->stackptr, cpu); - origptr = *stackptr; + + /* Switch to alternate jumpstack if we're being invoked via TEE. + * TEE issues XT_CONTINUE verdict on original skb so we must not + * clobber the jumpstack. + * + * For recursion via REJECT or SYNPROXY the stack will be clobbered + * but it is no problem since absolute verdict is issued by these. + */ + if (static_key_false(&xt_tee_enabled)) + jumpstack += private->stacksize * __this_cpu_read(nf_skb_duplicated); e = get_entry(table_base, private->hook_entry[hook]); - pr_debug("Entering %s(hook %u); sp at %u (UF %p)\n", - table->name, hook, origptr, + pr_debug("Entering %s(hook %u), UF %p\n", + table->name, hook, get_entry(table_base, private->underflow[hook])); do { @@ -383,28 +392,24 @@ ipt_do_table(struct sk_buff *skb, verdict = (unsigned int)(-v) - 1; break; } - if (*stackptr <= origptr) { + if (stackidx == 0) { e = get_entry(table_base, private->underflow[hook]); pr_debug("Underflow (this is normal) " "to %p\n", e); } else { - e = jumpstack[--*stackptr]; + e = jumpstack[--stackidx]; pr_debug("Pulled %p out from pos %u\n", - e, *stackptr); + e, stackidx); e = ipt_next_entry(e); } continue; } if (table_base + v != ipt_next_entry(e) && !(e->ip.flags & IPT_F_GOTO)) { - if (*stackptr >= private->stacksize) { - verdict = NF_DROP; - break; - } - jumpstack[(*stackptr)++] = e; + jumpstack[stackidx++] = e; pr_debug("Pushed %p into pos %u\n", - e, *stackptr - 1); + e, stackidx - 1); } e = get_entry(table_base, v); @@ -423,9 +428,8 @@ ipt_do_table(struct sk_buff *skb, /* Verdict */ break; } while (!acpar.hotdrop); - pr_debug("Exiting %s; resetting sp from %u to %u\n", - __func__, *stackptr, origptr); - *stackptr = origptr; + pr_debug("Exiting %s; sp at %u\n", __func__, stackidx); + xt_write_recseq_end(addend); local_bh_enable(); diff --git a/net/ipv4/netfilter/ipt_ECN.c b/net/ipv4/netfilter/ipt_ECN.c index 4bf3dc49ad1e..270765236f5e 100644 --- a/net/ipv4/netfilter/ipt_ECN.c +++ b/net/ipv4/netfilter/ipt_ECN.c @@ -72,7 +72,7 @@ set_ect_tcp(struct sk_buff *skb, const struct ipt_ECN_info *einfo) tcph->cwr = einfo->proto.tcp.cwr; inet_proto_csum_replace2(&tcph->check, skb, - oldval, ((__be16 *)tcph)[6], 0); + oldval, ((__be16 *)tcph)[6], false); return true; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 30ad9554b5e9..8a2caaf3940b 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -280,7 +280,7 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) return -EINVAL; } - h = nf_conntrack_find_get(sock_net(sk), NF_CT_DEFAULT_ZONE, &tuple); + h = nf_conntrack_find_get(sock_net(sk), &nf_ct_zone_dflt, &tuple); if (h) { struct sockaddr_in sin; struct nf_conn *ct = nf_ct_tuplehash_to_ctrack(h); diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 80d5554b9a88..cdde3ec496e9 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -134,9 +134,11 @@ icmp_error_message(struct net *net, struct nf_conn *tmpl, struct sk_buff *skb, struct nf_conntrack_tuple innertuple, origtuple; const struct nf_conntrack_l4proto *innerproto; const struct nf_conntrack_tuple_hash *h; - u16 zone = tmpl ? nf_ct_zone(tmpl) : NF_CT_DEFAULT_ZONE; + const struct nf_conntrack_zone *zone; + struct nf_conntrack_zone tmp; NF_CT_ASSERT(skb->nfct == NULL); + zone = nf_ct_zone_tmpl(tmpl, skb, &tmp); /* Are they talking about one of our connections? */ if (!nf_ct_get_tuplepr(skb, diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index c88b7d434718..9306ec4fab41 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -43,22 +43,22 @@ static int nf_ct_ipv4_gather_frags(struct sk_buff *skb, u_int32_t user) static enum ip_defrag_users nf_ct_defrag_user(unsigned int hooknum, struct sk_buff *skb) { - u16 zone = NF_CT_DEFAULT_ZONE; - + u16 zone_id = NF_CT_DEFAULT_ZONE_ID; #if IS_ENABLED(CONFIG_NF_CONNTRACK) - if (skb->nfct) - zone = nf_ct_zone((struct nf_conn *)skb->nfct); -#endif + if (skb->nfct) { + enum ip_conntrack_info ctinfo; + const struct nf_conn *ct = nf_ct_get(skb, &ctinfo); -#if IS_ENABLED(CONFIG_BRIDGE_NETFILTER) - if (skb->nf_bridge && - skb->nf_bridge->mask & BRNF_NF_BRIDGE_PREROUTING) - return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone; + zone_id = nf_ct_zone_id(nf_ct_zone(ct), CTINFO2DIR(ctinfo)); + } #endif + if (nf_bridge_in_prerouting(skb)) + return IP_DEFRAG_CONNTRACK_BRIDGE_IN + zone_id; + if (hooknum == NF_INET_PRE_ROUTING) - return IP_DEFRAG_CONNTRACK_IN + zone; + return IP_DEFRAG_CONNTRACK_IN + zone_id; else - return IP_DEFRAG_CONNTRACK_OUT + zone; + return IP_DEFRAG_CONNTRACK_OUT + zone_id; } static unsigned int ipv4_conntrack_defrag(const struct nf_hook_ops *ops, diff --git a/net/ipv4/netfilter/nf_dup_ipv4.c b/net/ipv4/netfilter/nf_dup_ipv4.c new file mode 100644 index 000000000000..2d79e6e8d934 --- /dev/null +++ b/net/ipv4/netfilter/nf_dup_ipv4.c @@ -0,0 +1,121 @@ +/* + * (C) 2007 by Sebastian Claßen <sebastian.classen@freenet.ag> + * (C) 2007-2010 by Jan Engelhardt <jengelh@medozas.de> + * + * Extracted from xt_TEE.c + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 or later, as + * published by the Free Software Foundation. + */ +#include <linux/ip.h> +#include <linux/module.h> +#include <linux/percpu.h> +#include <linux/route.h> +#include <linux/skbuff.h> +#include <linux/netfilter.h> +#include <net/checksum.h> +#include <net/icmp.h> +#include <net/ip.h> +#include <net/route.h> +#include <net/netfilter/ipv4/nf_dup_ipv4.h> +#if IS_ENABLED(CONFIG_NF_CONNTRACK) +#include <net/netfilter/nf_conntrack.h> +#endif + +static struct net *pick_net(struct sk_buff *skb) +{ +#ifdef CONFIG_NET_NS + const struct dst_entry *dst; + + if (skb->dev != NULL) + return dev_net(skb->dev); + dst = skb_dst(skb); + if (dst != NULL && dst->dev != NULL) + return dev_net(dst->dev); +#endif + return &init_net; +} + +static bool nf_dup_ipv4_route(struct sk_buff *skb, const struct in_addr *gw, + int oif) +{ + const struct iphdr *iph = ip_hdr(skb); + struct net *net = pick_net(skb); + struct rtable *rt; + struct flowi4 fl4; + + memset(&fl4, 0, sizeof(fl4)); + if (oif != -1) + fl4.flowi4_oif = oif; + + fl4.daddr = gw->s_addr; + fl4.flowi4_tos = RT_TOS(iph->tos); + fl4.flowi4_scope = RT_SCOPE_UNIVERSE; + fl4.flowi4_flags = FLOWI_FLAG_KNOWN_NH; + rt = ip_route_output_key(net, &fl4); + if (IS_ERR(rt)) + return false; + + skb_dst_drop(skb); + skb_dst_set(skb, &rt->dst); + skb->dev = rt->dst.dev; + skb->protocol = htons(ETH_P_IP); + + return true; +} + +void nf_dup_ipv4(struct sk_buff *skb, unsigned int hooknum, + const struct in_addr *gw, int oif) +{ + struct iphdr *iph; + + if (this_cpu_read(nf_skb_duplicated)) + return; + /* + * Copy the skb, and route the copy. Will later return %XT_CONTINUE for + * the original skb, which should continue on its way as if nothing has + * happened. The copy should be independently delivered to the gateway. + */ + skb = pskb_copy(skb, GFP_ATOMIC); + if (skb == NULL) + return; + +#if IS_ENABLED(CONFIG_NF_CONNTRACK) + /* Avoid counting cloned packets towards the original connection. */ + nf_conntrack_put(skb->nfct); + skb->nfct = &nf_ct_untracked_get()->ct_general; + skb->nfctinfo = IP_CT_NEW; + nf_conntrack_get(skb->nfct); +#endif + /* + * If we are in PREROUTING/INPUT, the checksum must be recalculated + * since the length could have changed as a result of defragmentation. + * + * We also decrease the TTL to mitigate potential loops between two + * hosts. + * + * Set %IP_DF so that the original source is notified of a potentially + * decreased MTU on the clone route. IPv6 does this too. + */ + iph = ip_hdr(skb); + iph->frag_off |= htons(IP_DF); + if (hooknum == NF_INET_PRE_ROUTING || + hooknum == NF_INET_LOCAL_IN) + --iph->ttl; + ip_send_check(iph); + + if (nf_dup_ipv4_route(skb, gw, oif)) { + __this_cpu_write(nf_skb_duplicated, true); + ip_local_out(skb); + __this_cpu_write(nf_skb_duplicated, false); + } else { + kfree_skb(skb); + } +} +EXPORT_SYMBOL_GPL(nf_dup_ipv4); + +MODULE_AUTHOR("Sebastian Claßen <sebastian.classen@freenet.ag>"); +MODULE_AUTHOR("Jan Engelhardt <jengelh@medozas.de>"); +MODULE_DESCRIPTION("nf_dup_ipv4: Duplicate IPv4 packet"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index e59cc05c09e9..22f4579b0c2a 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -120,7 +120,7 @@ static void nf_nat_ipv4_csum_update(struct sk_buff *skb, oldip = iph->daddr; newip = t->dst.u3.ip; } - inet_proto_csum_replace4(check, skb, oldip, newip, 1); + inet_proto_csum_replace4(check, skb, oldip, newip, true); } static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, @@ -151,7 +151,7 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, } } else inet_proto_csum_replace2(check, skb, - htons(oldlen), htons(datalen), 1); + htons(oldlen), htons(datalen), true); } #if IS_ENABLED(CONFIG_NF_CT_NETLINK) diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index 4557b4ab8342..7b98baa13ede 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -67,7 +67,7 @@ icmp_manip_pkt(struct sk_buff *skb, hdr = (struct icmphdr *)(skb->data + hdroff); inet_proto_csum_replace2(&hdr->checksum, skb, - hdr->un.echo.id, tuple->src.u.icmp.id, 0); + hdr->un.echo.id, tuple->src.u.icmp.id, false); hdr->un.echo.id = tuple->src.u.icmp.id; return true; } diff --git a/net/ipv4/netfilter/nft_dup_ipv4.c b/net/ipv4/netfilter/nft_dup_ipv4.c new file mode 100644 index 000000000000..b45932d43b69 --- /dev/null +++ b/net/ipv4/netfilter/nft_dup_ipv4.c @@ -0,0 +1,110 @@ +/* + * Copyright (c) 2015 Pablo Neira Ayuso <pablo@netfilter.org> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published by + * the Free Software Foundation. + */ + +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netlink.h> +#include <linux/netfilter.h> +#include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables.h> +#include <net/netfilter/ipv4/nf_dup_ipv4.h> + +struct nft_dup_ipv4 { + enum nft_registers sreg_addr:8; + enum nft_registers sreg_dev:8; +}; + +static void nft_dup_ipv4_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_dup_ipv4 *priv = nft_expr_priv(expr); + struct in_addr gw = { + .s_addr = (__force __be32)regs->data[priv->sreg_addr], + }; + int oif = regs->data[priv->sreg_dev]; + + nf_dup_ipv4(pkt->skb, pkt->ops->hooknum, &gw, oif); +} + +static int nft_dup_ipv4_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_dup_ipv4 *priv = nft_expr_priv(expr); + int err; + + if (tb[NFTA_DUP_SREG_ADDR] == NULL) + return -EINVAL; + + priv->sreg_addr = nft_parse_register(tb[NFTA_DUP_SREG_ADDR]); + err = nft_validate_register_load(priv->sreg_addr, sizeof(struct in_addr)); + if (err < 0) + return err; + + if (tb[NFTA_DUP_SREG_DEV] != NULL) { + priv->sreg_dev = nft_parse_register(tb[NFTA_DUP_SREG_DEV]); + return nft_validate_register_load(priv->sreg_dev, sizeof(int)); + } + return 0; +} + +static int nft_dup_ipv4_dump(struct sk_buff *skb, const struct nft_expr *expr) +{ + struct nft_dup_ipv4 *priv = nft_expr_priv(expr); + + if (nft_dump_register(skb, NFTA_DUP_SREG_ADDR, priv->sreg_addr) || + nft_dump_register(skb, NFTA_DUP_SREG_DEV, priv->sreg_dev)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + +static struct nft_expr_type nft_dup_ipv4_type; +static const struct nft_expr_ops nft_dup_ipv4_ops = { + .type = &nft_dup_ipv4_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_dup_ipv4)), + .eval = nft_dup_ipv4_eval, + .init = nft_dup_ipv4_init, + .dump = nft_dup_ipv4_dump, +}; + +static const struct nla_policy nft_dup_ipv4_policy[NFTA_DUP_MAX + 1] = { + [NFTA_DUP_SREG_ADDR] = { .type = NLA_U32 }, + [NFTA_DUP_SREG_DEV] = { .type = NLA_U32 }, +}; + +static struct nft_expr_type nft_dup_ipv4_type __read_mostly = { + .family = NFPROTO_IPV4, + .name = "dup", + .ops = &nft_dup_ipv4_ops, + .policy = nft_dup_ipv4_policy, + .maxattr = NFTA_DUP_MAX, + .owner = THIS_MODULE, +}; + +static int __init nft_dup_ipv4_module_init(void) +{ + return nft_register_expr(&nft_dup_ipv4_type); +} + +static void __exit nft_dup_ipv4_module_exit(void) +{ + nft_unregister_expr(&nft_dup_ipv4_type); +} + +module_init(nft_dup_ipv4_module_init); +module_exit(nft_dup_ipv4_module_exit); + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Pablo Neira Ayuso <pablo@netfilter.org>"); +MODULE_ALIAS_NFT_AF_EXPR(AF_INET, "dup"); diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index 05ff44b758df..e89094ab5ddb 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -363,7 +363,8 @@ static int ping_check_bind_addr(struct sock *sk, struct inet_sock *isk, scoped); rcu_read_unlock(); - if (!(isk->freebind || isk->transparent || has_addr || + if (!(net->ipv6.sysctl.ip_nonlocal_bind || + isk->freebind || isk->transparent || has_addr || addr_type == IPV6_ADDR_ANY)) return -EADDRNOTAVAIL; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index da5d483e236a..3abd9d7a3adf 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -300,6 +300,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPACKSkippedChallenge", LINUX_MIB_TCPACKSKIPPEDCHALLENGE), SNMP_MIB_ITEM("TCPWinProbe", LINUX_MIB_TCPWINPROBE), SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), + SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), + SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index e681b852ced1..5f4a5565ad8b 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/slab.h> #include <linux/jhash.h> #include <net/dst.h> +#include <net/dst_metadata.h> #include <net/net_namespace.h> #include <net/protocol.h> #include <net/ip.h> @@ -102,6 +103,7 @@ #include <net/tcp.h> #include <net/icmp.h> #include <net/xfrm.h> +#include <net/lwtunnel.h> #include <net/netevent.h> #include <net/rtnetlink.h> #ifdef CONFIG_SYSCTL @@ -109,6 +111,8 @@ #include <linux/kmemleak.h> #endif #include <net/secure_seq.h> +#include <net/ip_tunnels.h> +#include <net/vrf.h> #define RT_FL_TOS(oldflp4) \ ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) @@ -834,6 +838,7 @@ void ip_rt_send_redirect(struct sk_buff *skb) struct inet_peer *peer; struct net *net; int log_martians; + int vif; rcu_read_lock(); in_dev = __in_dev_get_rcu(rt->dst.dev); @@ -842,10 +847,11 @@ void ip_rt_send_redirect(struct sk_buff *skb) return; } log_martians = IN_DEV_LOG_MARTIANS(in_dev); + vif = vrf_master_ifindex_rcu(rt->dst.dev); rcu_read_unlock(); net = dev_net(rt->dst.dev); - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, vif, 1); if (!peer) { icmp_send(skb, ICMP_REDIRECT, ICMP_REDIR_HOST, rt_nexthop(rt, ip_hdr(skb)->daddr)); @@ -934,7 +940,8 @@ static int ip_error(struct sk_buff *skb) break; } - peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, 1); + peer = inet_getpeer_v4(net->ipv4.peers, ip_hdr(skb)->saddr, + vrf_master_ifindex(skb->dev), 1); send = true; if (peer) { @@ -1403,6 +1410,7 @@ static void rt_set_nexthop(struct rtable *rt, __be32 daddr, #ifdef CONFIG_IP_ROUTE_CLASSID rt->dst.tclassid = nh->nh_tclassid; #endif + rt->dst.lwtstate = lwtstate_get(nh->nh_lwtstate); if (unlikely(fnhe)) cached = rt_bind_exception(rt, fnhe, daddr); else if (!(rt->dst.flags & DST_NOCACHE)) @@ -1546,7 +1554,6 @@ static int __mkroute_input(struct sk_buff *skb, struct rtable *rth; int err; struct in_device *out_dev; - unsigned int flags = 0; bool do_cache; u32 itag = 0; @@ -1610,7 +1617,7 @@ static int __mkroute_input(struct sk_buff *skb, } rth->rt_genid = rt_genid_ipv4(dev_net(rth->dst.dev)); - rth->rt_flags = flags; + rth->rt_flags = 0; rth->rt_type = res->type; rth->rt_is_input = 1; rth->rt_iif = 0; @@ -1624,6 +1631,14 @@ static int __mkroute_input(struct sk_buff *skb, rth->dst.output = ip_output; rt_set_nexthop(rth, daddr, res, fnhe, res->fi, res->type, itag); + if (lwtunnel_output_redirect(rth->dst.lwtstate)) { + rth->dst.lwtstate->orig_output = rth->dst.output; + rth->dst.output = lwtunnel_output; + } + if (lwtunnel_input_redirect(rth->dst.lwtstate)) { + rth->dst.lwtstate->orig_input = rth->dst.input; + rth->dst.input = lwtunnel_input; + } skb_dst_set(skb, &rth->dst); out: err = 0; @@ -1662,6 +1677,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); + struct ip_tunnel_info *tun_info; struct flowi4 fl4; unsigned int flags = 0; u32 itag = 0; @@ -1679,6 +1695,13 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, by fib_lookup. */ + tun_info = skb_tunnel_info(skb); + if (tun_info && !(tun_info->mode & IP_TUNNEL_INFO_TX)) + fl4.flowi4_tun_key.tun_id = tun_info->key.tun_id; + else + fl4.flowi4_tun_key.tun_id = 0; + skb_dst_drop(skb); + if (ipv4_is_multicast(saddr) || ipv4_is_lbcast(saddr)) goto martian_source; @@ -1710,7 +1733,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, * Now we are ready to route packet. */ fl4.flowi4_oif = 0; - fl4.flowi4_iif = dev->ifindex; + fl4.flowi4_iif = vrf_master_ifindex_rcu(dev) ? : dev->ifindex; fl4.flowi4_mark = skb->mark; fl4.flowi4_tos = tos; fl4.flowi4_scope = RT_SCOPE_UNIVERSE; @@ -1792,6 +1815,7 @@ local_input: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); + RT_CACHE_STAT_INC(in_slow_tot); if (res.type == RTN_UNREACHABLE) { rth->dst.input= ip_error; @@ -1981,7 +2005,6 @@ add: rth->rt_gateway = 0; rth->rt_uses_gateway = 0; INIT_LIST_HEAD(&rth->rt_uncached); - RT_CACHE_STAT_INC(out_slow_tot); if (flags & RTCF_LOCAL) @@ -2004,6 +2027,8 @@ add: } rt_set_nexthop(rth, fl4->daddr, res, fnhe, fi, type, 0); + if (lwtunnel_output_redirect(rth->dst.lwtstate)) + rth->dst.output = lwtunnel_output; return rth; } @@ -2110,6 +2135,11 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *fl4) fl4->saddr = inet_select_addr(dev_out, 0, RT_SCOPE_HOST); } + if (netif_is_vrf(dev_out) && + !(fl4->flowi4_flags & FLOWI_FLAG_VRFSRC)) { + rth = vrf_dev_get_rth(dev_out); + goto out; + } } if (!fl4->daddr) { @@ -2261,7 +2291,6 @@ struct dst_entry *ipv4_blackhole_route(struct net *net, struct dst_entry *dst_or rt->rt_uses_gateway = ort->rt_uses_gateway; INIT_LIST_HEAD(&rt->rt_uncached); - dst_free(new); } diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 0330ab2e2b63..894da3a70aff 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -29,6 +29,7 @@ static int zero; static int one = 1; static int four = 4; +static int thousand = 1000; static int gso_max_segs = GSO_MAX_SEGS; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; @@ -712,6 +713,24 @@ static struct ctl_table ipv4_table[] = { .extra2 = &gso_max_segs, }, { + .procname = "tcp_pacing_ss_ratio", + .data = &sysctl_tcp_pacing_ss_ratio, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &thousand, + }, + { + .procname = "tcp_pacing_ca_ratio", + .data = &sysctl_tcp_pacing_ca_ratio, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_minmax, + .extra1 = &zero, + .extra2 = &thousand, + }, + { .procname = "tcp_autocorking", .data = &sysctl_tcp_autocorking, .maxlen = sizeof(int), @@ -910,6 +929,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "igmp_link_local_mcast_reports", + .data = &sysctl_igmp_llm_reports, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 45534a5ab430..b8b8fa184f75 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -627,6 +627,8 @@ static void skb_entail(struct sock *sk, struct sk_buff *skb) sk_mem_charge(sk, skb->truesize); if (tp->nonagle & TCP_NAGLE_PUSH) tp->nonagle &= ~TCP_NAGLE_PUSH; + + tcp_slow_start_after_idle_check(sk); } static inline void tcp_mark_urg(struct tcp_sock *tp, int flags) diff --git a/net/ipv4/tcp_bic.c b/net/ipv4/tcp_bic.c index c037644eafb7..fd1405d37c14 100644 --- a/net/ipv4/tcp_bic.c +++ b/net/ipv4/tcp_bic.c @@ -146,7 +146,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { bictcp_update(ca, tp->snd_cwnd); diff --git a/net/ipv4/tcp_cdg.c b/net/ipv4/tcp_cdg.c index 8c6fd3d5e40f..167b6a3e1b98 100644 --- a/net/ipv4/tcp_cdg.c +++ b/net/ipv4/tcp_cdg.c @@ -264,7 +264,7 @@ static void tcp_cdg_cong_avoid(struct sock *sk, u32 ack, u32 acked) u32 prior_snd_cwnd; u32 incr; - if (tp->snd_cwnd < tp->snd_ssthresh && hystart_detect) + if (tcp_in_slow_start(tp) && hystart_detect) tcp_cdg_hystart_update(sk); if (after(ack, ca->rtt_seq) && ca->rtt.v64) { diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 84be008c945c..93c4dc3ab23f 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -114,16 +114,19 @@ void tcp_unregister_congestion_control(struct tcp_congestion_ops *ca) } EXPORT_SYMBOL_GPL(tcp_unregister_congestion_control); -u32 tcp_ca_get_key_by_name(const char *name) +u32 tcp_ca_get_key_by_name(const char *name, bool *ecn_ca) { const struct tcp_congestion_ops *ca; - u32 key; + u32 key = TCP_CA_UNSPEC; might_sleep(); rcu_read_lock(); ca = __tcp_ca_find_autoload(name); - key = ca ? ca->key : TCP_CA_UNSPEC; + if (ca) { + key = ca->key; + *ecn_ca = ca->flags & TCP_CONG_NEEDS_ECN; + } rcu_read_unlock(); return key; @@ -365,10 +368,8 @@ int tcp_set_congestion_control(struct sock *sk, const char *name) */ u32 tcp_slow_start(struct tcp_sock *tp, u32 acked) { - u32 cwnd = tp->snd_cwnd + acked; + u32 cwnd = min(tp->snd_cwnd + acked, tp->snd_ssthresh); - if (cwnd > tp->snd_ssthresh) - cwnd = tp->snd_ssthresh + 1; acked -= cwnd - tp->snd_cwnd; tp->snd_cwnd = min(cwnd, tp->snd_cwnd_clamp); @@ -413,7 +414,7 @@ void tcp_reno_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In "safe" area, increase. */ - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { acked = tcp_slow_start(tp, acked); if (!acked) return; diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 06d3d665a9fd..28011fb1f4a2 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -320,7 +320,7 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { if (hystart && after(ack, ca->end_seq)) bictcp_hystart_reset(sk); acked = tcp_slow_start(tp, acked); @@ -439,7 +439,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) ca->delay_min = delay; /* hystart triggers when cwnd is larger than some threshold */ - if (hystart && tp->snd_cwnd <= tp->snd_ssthresh && + if (hystart && tcp_in_slow_start(tp) && tp->snd_cwnd >= hystart_low_window) hystart_update(sk, delay); } diff --git a/net/ipv4/tcp_highspeed.c b/net/ipv4/tcp_highspeed.c index 882c08aae2f5..db7842495a64 100644 --- a/net/ipv4/tcp_highspeed.c +++ b/net/ipv4/tcp_highspeed.c @@ -116,7 +116,7 @@ static void hstcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* Update AIMD parameters. diff --git a/net/ipv4/tcp_htcp.c b/net/ipv4/tcp_htcp.c index 58469fff6c18..82f0d9ed60f5 100644 --- a/net/ipv4/tcp_htcp.c +++ b/net/ipv4/tcp_htcp.c @@ -236,7 +236,7 @@ static void htcp_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { /* In dangerous area, increase slowly. diff --git a/net/ipv4/tcp_hybla.c b/net/ipv4/tcp_hybla.c index f963b274f2b0..083831e359df 100644 --- a/net/ipv4/tcp_hybla.c +++ b/net/ipv4/tcp_hybla.c @@ -112,7 +112,7 @@ static void hybla_cong_avoid(struct sock *sk, u32 ack, u32 acked) rho_fractions = ca->rho_3ls - (ca->rho << 3); - if (tp->snd_cwnd < tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* * slow start * INC = 2^RHO - 1 diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index f71002e4db0b..2ab9bbb6faff 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -268,7 +268,7 @@ static void tcp_illinois_cong_avoid(struct sock *sk, u32 ack, u32 acked) return; /* In slow start */ - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else { diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 728f5b3d3c64..a8f515bb19c4 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -109,6 +109,7 @@ int sysctl_tcp_invalid_ratelimit __read_mostly = HZ/2; #define FLAG_SYN_ACKED 0x10 /* This ACK acknowledged SYN. */ #define FLAG_DATA_SACKED 0x20 /* New SACK. */ #define FLAG_ECE 0x40 /* ECE in this ACK */ +#define FLAG_LOST_RETRANS 0x80 /* This ACK marks some retransmission lost */ #define FLAG_SLOWPATH 0x100 /* Do not skip RFC checks for window update.*/ #define FLAG_ORIG_SACK_ACKED 0x200 /* Never retransmitted data are (s)acked */ #define FLAG_SND_UNA_ADVANCED 0x400 /* Snd_una was changed (!= FLAG_DATA_ACKED) */ @@ -196,11 +197,13 @@ static void tcp_enter_quickack_mode(struct sock *sk) * and the session is not interactive. */ -static inline bool tcp_in_quickack_mode(const struct sock *sk) +static bool tcp_in_quickack_mode(struct sock *sk) { const struct inet_connection_sock *icsk = inet_csk(sk); + const struct dst_entry *dst = __sk_dst_get(sk); - return icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong; + return (dst && dst_metric(dst, RTAX_QUICKACK)) || + (icsk->icsk_ack.quick && !icsk->icsk_ack.pingpong); } static void tcp_ecn_queue_cwr(struct tcp_sock *tp) @@ -750,13 +753,29 @@ static void tcp_rtt_estimator(struct sock *sk, long mrtt_us) * TCP pacing, to smooth the burst on large writes when packets * in flight is significantly lower than cwnd (or rwin) */ +int sysctl_tcp_pacing_ss_ratio __read_mostly = 200; +int sysctl_tcp_pacing_ca_ratio __read_mostly = 120; + static void tcp_update_pacing_rate(struct sock *sk) { const struct tcp_sock *tp = tcp_sk(sk); u64 rate; /* set sk_pacing_rate to 200 % of current rate (mss * cwnd / srtt) */ - rate = (u64)tp->mss_cache * 2 * (USEC_PER_SEC << 3); + rate = (u64)tp->mss_cache * ((USEC_PER_SEC / 100) << 3); + + /* current rate is (cwnd * mss) / srtt + * In Slow Start [1], set sk_pacing_rate to 200 % the current rate. + * In Congestion Avoidance phase, set it to 120 % the current rate. + * + * [1] : Normal Slow Start condition is (tp->snd_cwnd < tp->snd_ssthresh) + * If snd_cwnd >= (tp->snd_ssthresh / 2), we are approaching + * end of slow start and should slow down. + */ + if (tp->snd_cwnd < tp->snd_ssthresh / 2) + rate *= sysctl_tcp_pacing_ss_ratio; + else + rate *= sysctl_tcp_pacing_ca_ratio; rate *= max(tp->snd_cwnd, tp->packets_out); @@ -1037,7 +1056,7 @@ static bool tcp_is_sackblock_valid(struct tcp_sock *tp, bool is_dsack, * highest SACK block). Also calculate the lowest snd_nxt among the remaining * retransmitted skbs to avoid some costly processing per ACKs. */ -static void tcp_mark_lost_retrans(struct sock *sk) +static void tcp_mark_lost_retrans(struct sock *sk, int *flag) { const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); @@ -1078,7 +1097,7 @@ static void tcp_mark_lost_retrans(struct sock *sk) if (after(received_upto, ack_seq)) { TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; tp->retrans_out -= tcp_skb_pcount(skb); - + *flag |= FLAG_LOST_RETRANS; tcp_skb_mark_lost_uncond_verify(tp, skb); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSTRETRANSMIT); } else { @@ -1818,7 +1837,7 @@ advance_sp: ((inet_csk(sk)->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker)) tcp_update_reordering(sk, tp->fackets_out - state->reord, 0); - tcp_mark_lost_retrans(sk); + tcp_mark_lost_retrans(sk, &state->flag); tcp_verify_left_out(tp); out: @@ -2474,15 +2493,14 @@ static bool tcp_try_undo_loss(struct sock *sk, bool frto_undo) return false; } -/* The cwnd reduction in CWR and Recovery use the PRR algorithm - * https://datatracker.ietf.org/doc/draft-ietf-tcpm-proportional-rate-reduction/ +/* The cwnd reduction in CWR and Recovery uses the PRR algorithm in RFC 6937. * It computes the number of packets to send (sndcnt) based on packets newly * delivered: * 1) If the packets in flight is larger than ssthresh, PRR spreads the * cwnd reductions across a full RTT. - * 2) If packets in flight is lower than ssthresh (such as due to excess - * losses and/or application stalls), do not perform any further cwnd - * reductions, but instead slow start up to ssthresh. + * 2) Otherwise PRR uses packet conservation to send as much as delivered. + * But when the retransmits are acked without further losses, PRR + * slow starts cwnd up to ssthresh to speed up the recovery. */ static void tcp_init_cwnd_reduction(struct sock *sk) { @@ -2499,7 +2517,7 @@ static void tcp_init_cwnd_reduction(struct sock *sk) } static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, - int fast_rexmit) + int fast_rexmit, int flag) { struct tcp_sock *tp = tcp_sk(sk); int sndcnt = 0; @@ -2508,16 +2526,18 @@ static void tcp_cwnd_reduction(struct sock *sk, const int prior_unsacked, (tp->packets_out - tp->sacked_out); tp->prr_delivered += newly_acked_sacked; - if (tcp_packets_in_flight(tp) > tp->snd_ssthresh) { + if (delta < 0) { u64 dividend = (u64)tp->snd_ssthresh * tp->prr_delivered + tp->prior_cwnd - 1; sndcnt = div_u64(dividend, tp->prior_cwnd) - tp->prr_out; - } else { + } else if ((flag & FLAG_RETRANS_DATA_ACKED) && + !(flag & FLAG_LOST_RETRANS)) { sndcnt = min_t(int, delta, max_t(int, tp->prr_delivered - tp->prr_out, newly_acked_sacked) + 1); + } else { + sndcnt = min(delta, newly_acked_sacked); } - sndcnt = max(sndcnt, (fast_rexmit ? 1 : 0)); tp->snd_cwnd = tcp_packets_in_flight(tp) + sndcnt; } @@ -2578,7 +2598,7 @@ static void tcp_try_to_open(struct sock *sk, int flag, const int prior_unsacked) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); } else { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); } } @@ -2588,6 +2608,7 @@ static void tcp_mtup_probe_failed(struct sock *sk) icsk->icsk_mtup.search_high = icsk->icsk_mtup.probe_size - 1; icsk->icsk_mtup.probe_size = 0; + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPFAIL); } static void tcp_mtup_probe_success(struct sock *sk) @@ -2607,6 +2628,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPMTUPSUCCESS); } /* Do a simple retransmit without using the backoff mechanisms in @@ -2675,7 +2697,7 @@ static void tcp_enter_recovery(struct sock *sk, bool ece_ack) tp->prior_ssthresh = 0; tcp_init_undo(tp); - if (inet_csk(sk)->icsk_ca_state < TCP_CA_CWR) { + if (!tcp_in_cwnd_reduction(sk)) { if (!ece_ack) tp->prior_ssthresh = tcp_current_ssthresh(sk); tcp_init_cwnd_reduction(sk); @@ -2735,7 +2757,7 @@ static void tcp_process_loss(struct sock *sk, int flag, bool is_dupack) /* Undo during fast recovery after partial ACK. */ static bool tcp_try_undo_partial(struct sock *sk, const int acked, - const int prior_unsacked) + const int prior_unsacked, int flag) { struct tcp_sock *tp = tcp_sk(sk); @@ -2751,7 +2773,7 @@ static bool tcp_try_undo_partial(struct sock *sk, const int acked, * mark more packets lost or retransmit more. */ if (tp->retrans_out) { - tcp_cwnd_reduction(sk, prior_unsacked, 0); + tcp_cwnd_reduction(sk, prior_unsacked, 0, flag); return true; } @@ -2838,7 +2860,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (tcp_is_reno(tp) && is_dupack) tcp_add_reno_sack(sk); } else { - if (tcp_try_undo_partial(sk, acked, prior_unsacked)) + if (tcp_try_undo_partial(sk, acked, prior_unsacked, flag)) return; /* Partial ACK arrived. Force fast retransmit. */ do_lost = tcp_is_reno(tp) || @@ -2851,9 +2873,10 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, break; case TCP_CA_Loss: tcp_process_loss(sk, flag, is_dupack); - if (icsk->icsk_ca_state != TCP_CA_Open) + if (icsk->icsk_ca_state != TCP_CA_Open && + !(flag & FLAG_LOST_RETRANS)) return; - /* Fall through to processing in Open state. */ + /* Change state if cwnd is undone or retransmits are lost */ default: if (tcp_is_reno(tp)) { if (flag & FLAG_SND_UNA_ADVANCED) @@ -2888,7 +2911,7 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, if (do_lost) tcp_update_scoreboard(sk, fast_rexmit); - tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit); + tcp_cwnd_reduction(sk, prior_unsacked, fast_rexmit, flag); tcp_xmit_retransmit_queue(sk); } @@ -3325,6 +3348,9 @@ static int tcp_ack_update_window(struct sock *sk, const struct sk_buff *skb, u32 tp->pred_flags = 0; tcp_fast_path_check(sk); + if (tcp_send_head(sk)) + tcp_slow_start_after_idle_check(sk); + if (nwin > tp->max_window) { tp->max_window = nwin; tcp_sync_mss(sk, inet_csk(sk)->icsk_pmtu_cookie); @@ -3562,10 +3588,6 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) &sack_state); acked -= tp->packets_out; - /* Advance cwnd if state allows */ - if (tcp_may_raise_cwnd(sk, flag)) - tcp_cong_avoid(sk, ack, acked); - if (tcp_ack_is_dubious(sk, flag)) { is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); tcp_fastretrans_alert(sk, acked, prior_unsacked, @@ -3574,6 +3596,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (tp->tlp_high_seq) tcp_process_tlp_ack(sk, ack, flag); + /* Advance cwnd if state allows */ + if (tcp_may_raise_cwnd(sk, flag)) + tcp_cong_avoid(sk, ack, acked); + if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) { struct dst_entry *dst = __sk_dst_get(sk); if (dst) @@ -3947,7 +3973,6 @@ void tcp_reset(struct sock *sk) static void tcp_fin(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); - const struct dst_entry *dst; inet_csk_schedule_ack(sk); @@ -3959,9 +3984,7 @@ static void tcp_fin(struct sock *sk) case TCP_ESTABLISHED: /* Move to CLOSE_WAIT */ tcp_set_state(sk, TCP_CLOSE_WAIT); - dst = __sk_dst_get(sk); - if (!dst || !dst_metric(dst, RTAX_QUICKACK)) - inet_csk(sk)->icsk_ack.pingpong = 1; + inet_csk(sk)->icsk_ack.pingpong = 1; break; case TCP_CLOSE_WAIT: @@ -5980,14 +6003,17 @@ static void tcp_ecn_create_request(struct request_sock *req, const struct net *net = sock_net(listen_sk); bool th_ecn = th->ece && th->cwr; bool ect, ecn_ok; + u32 ecn_ok_dst; if (!th_ecn) return; ect = !INET_ECN_is_not_ect(TCP_SKB_CB(skb)->ip_dsfield); - ecn_ok = net->ipv4.sysctl_tcp_ecn || dst_feature(dst, RTAX_FEATURE_ECN); + ecn_ok_dst = dst_feature(dst, DST_FEATURE_ECN_MASK); + ecn_ok = net->ipv4.sysctl_tcp_ecn || ecn_ok_dst; - if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk)) + if ((!ect && ecn_ok) || tcp_ca_needs_ecn(listen_sk) || + (ecn_ok_dst & DST_FEATURE_ECN_CA)) inet_rsk(req)->ecn_ok = 1; } diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 0ea2e1c5d395..93898e093d4e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -222,7 +222,7 @@ int tcp_v4_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (err) goto failure; - inet_set_txhash(sk); + sk_set_txhash(sk); rt = ip_route_newports(fl4, rt, orig_sport, orig_dport, inet->inet_sport, inet->inet_dport, sk); @@ -1277,7 +1277,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newinet->mc_ttl = ip_hdr(skb)->ttl; newinet->rcv_tos = ip_hdr(skb)->tos; inet_csk(newsk)->icsk_ext_hdr_len = 0; - inet_set_txhash(newsk); + sk_set_txhash(newsk); if (inet_opt) inet_csk(newsk)->icsk_ext_hdr_len = inet_opt->opt.optlen; newinet->inet_id = newtp->write_seq ^ jiffies; @@ -1683,8 +1683,7 @@ do_time_wait: iph->daddr, th->dest, inet_iif(skb)); if (sk2) { - inet_twsk_deschedule(inet_twsk(sk)); - inet_twsk_put(inet_twsk(sk)); + inet_twsk_deschedule_put(inet_twsk(sk)); sk = sk2; goto process; } diff --git a/net/ipv4/tcp_metrics.c b/net/ipv4/tcp_metrics.c index a51d63a43e33..c8cbc2b4b792 100644 --- a/net/ipv4/tcp_metrics.c +++ b/net/ipv4/tcp_metrics.c @@ -81,11 +81,7 @@ static void tcp_metric_set(struct tcp_metrics_block *tm, static bool addr_same(const struct inetpeer_addr *a, const struct inetpeer_addr *b) { - if (a->family != b->family) - return false; - if (a->family == AF_INET) - return a->addr.a4 == b->addr.a4; - return ipv6_addr_equal(&a->addr.in6, &b->addr.in6); + return inetpeer_addr_cmp(a, b) == 0; } struct tcpm_hash_bucket { @@ -247,14 +243,14 @@ static struct tcp_metrics_block *__tcp_get_metrics_req(struct request_sock *req, daddr.family = req->rsk_ops->family; switch (daddr.family) { case AF_INET: - saddr.addr.a4 = inet_rsk(req)->ir_loc_addr; - daddr.addr.a4 = inet_rsk(req)->ir_rmt_addr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, inet_rsk(req)->ir_loc_addr); + inetpeer_set_addr_v4(&daddr, inet_rsk(req)->ir_rmt_addr); + hash = ipv4_addr_hash(inet_rsk(req)->ir_rmt_addr); break; #if IS_ENABLED(CONFIG_IPV6) case AF_INET6: - saddr.addr.in6 = inet_rsk(req)->ir_v6_loc_addr; - daddr.addr.in6 = inet_rsk(req)->ir_v6_rmt_addr; + inetpeer_set_addr_v6(&saddr, &inet_rsk(req)->ir_v6_loc_addr); + inetpeer_set_addr_v6(&daddr, &inet_rsk(req)->ir_v6_rmt_addr); hash = ipv6_addr_hash(&inet_rsk(req)->ir_v6_rmt_addr); break; #endif @@ -285,25 +281,19 @@ static struct tcp_metrics_block *__tcp_get_metrics_tw(struct inet_timewait_sock struct net *net; if (tw->tw_family == AF_INET) { - saddr.family = AF_INET; - saddr.addr.a4 = tw->tw_rcv_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = tw->tw_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); + inetpeer_set_addr_v4(&daddr, tw->tw_daddr); + hash = ipv4_addr_hash(tw->tw_daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (tw->tw_family == AF_INET6) { if (ipv6_addr_v4mapped(&tw->tw_v6_daddr)) { - saddr.family = AF_INET; - saddr.addr.a4 = tw->tw_rcv_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = tw->tw_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, tw->tw_rcv_saddr); + inetpeer_set_addr_v4(&daddr, tw->tw_daddr); + hash = ipv4_addr_hash(tw->tw_daddr); } else { - saddr.family = AF_INET6; - saddr.addr.in6 = tw->tw_v6_rcv_saddr; - daddr.family = AF_INET6; - daddr.addr.in6 = tw->tw_v6_daddr; + inetpeer_set_addr_v6(&saddr, &tw->tw_v6_rcv_saddr); + inetpeer_set_addr_v6(&daddr, &tw->tw_v6_daddr); hash = ipv6_addr_hash(&tw->tw_v6_daddr); } } @@ -335,25 +325,19 @@ static struct tcp_metrics_block *tcp_get_metrics(struct sock *sk, struct net *net; if (sk->sk_family == AF_INET) { - saddr.family = AF_INET; - saddr.addr.a4 = inet_sk(sk)->inet_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = inet_sk(sk)->inet_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr); + inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr); + hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr); } #if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { if (ipv6_addr_v4mapped(&sk->sk_v6_daddr)) { - saddr.family = AF_INET; - saddr.addr.a4 = inet_sk(sk)->inet_saddr; - daddr.family = AF_INET; - daddr.addr.a4 = inet_sk(sk)->inet_daddr; - hash = (__force unsigned int) daddr.addr.a4; + inetpeer_set_addr_v4(&saddr, inet_sk(sk)->inet_saddr); + inetpeer_set_addr_v4(&daddr, inet_sk(sk)->inet_daddr); + hash = ipv4_addr_hash(inet_sk(sk)->inet_daddr); } else { - saddr.family = AF_INET6; - saddr.addr.in6 = sk->sk_v6_rcv_saddr; - daddr.family = AF_INET6; - daddr.addr.in6 = sk->sk_v6_daddr; + inetpeer_set_addr_v6(&saddr, &sk->sk_v6_rcv_saddr); + inetpeer_set_addr_v6(&daddr, &sk->sk_v6_daddr); hash = ipv6_addr_hash(&sk->sk_v6_daddr); } } @@ -461,7 +445,7 @@ void tcp_update_metrics(struct sock *sk) tcp_metric_set(tm, TCP_METRIC_CWND, tp->snd_cwnd); } - } else if (tp->snd_cwnd > tp->snd_ssthresh && + } else if (!tcp_in_slow_start(tp) && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ if (!tcp_metric_locked(tm, TCP_METRIC_SSTHRESH)) @@ -796,18 +780,18 @@ static int tcp_metrics_fill_info(struct sk_buff *msg, switch (tm->tcpm_daddr.family) { case AF_INET: if (nla_put_in_addr(msg, TCP_METRICS_ATTR_ADDR_IPV4, - tm->tcpm_daddr.addr.a4) < 0) + inetpeer_get_addr_v4(&tm->tcpm_daddr)) < 0) goto nla_put_failure; if (nla_put_in_addr(msg, TCP_METRICS_ATTR_SADDR_IPV4, - tm->tcpm_saddr.addr.a4) < 0) + inetpeer_get_addr_v4(&tm->tcpm_saddr)) < 0) goto nla_put_failure; break; case AF_INET6: if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_ADDR_IPV6, - &tm->tcpm_daddr.addr.in6) < 0) + inetpeer_get_addr_v6(&tm->tcpm_daddr)) < 0) goto nla_put_failure; if (nla_put_in6_addr(msg, TCP_METRICS_ATTR_SADDR_IPV6, - &tm->tcpm_saddr.addr.in6) < 0) + inetpeer_get_addr_v6(&tm->tcpm_saddr)) < 0) goto nla_put_failure; break; default: @@ -956,20 +940,21 @@ static int __parse_nl_addr(struct genl_info *info, struct inetpeer_addr *addr, a = info->attrs[v4]; if (a) { - addr->family = AF_INET; - addr->addr.a4 = nla_get_in_addr(a); + inetpeer_set_addr_v4(addr, nla_get_in_addr(a)); if (hash) - *hash = (__force unsigned int) addr->addr.a4; + *hash = ipv4_addr_hash(inetpeer_get_addr_v4(addr)); return 0; } a = info->attrs[v6]; if (a) { + struct in6_addr in6; + if (nla_len(a) != sizeof(struct in6_addr)) return -EINVAL; - addr->family = AF_INET6; - addr->addr.in6 = nla_get_in6_addr(a); + in6 = nla_get_in6_addr(a); + inetpeer_set_addr_v6(addr, &in6); if (hash) - *hash = ipv6_addr_hash(&addr->addr.in6); + *hash = ipv6_addr_hash(inetpeer_get_addr_v6(addr)); return 0; } return optional ? 1 : -EAFNOSUPPORT; diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 4bc00cb79e60..6d8795b066ac 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -147,8 +147,7 @@ tcp_timewait_state_process(struct inet_timewait_sock *tw, struct sk_buff *skb, if (!th->fin || TCP_SKB_CB(skb)->end_seq != tcptw->tw_rcv_nxt + 1) { kill_with_rst: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_RST; } @@ -198,8 +197,7 @@ kill_with_rst: */ if (sysctl_tcp_rfc1337 == 0) { kill: - inet_twsk_deschedule(tw); - inet_twsk_put(tw); + inet_twsk_deschedule_put(tw); return TCP_TW_SUCCESS; } } diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index b1c218df2c85..1188e4fcf23b 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -137,12 +137,12 @@ static __u16 tcp_advertise_mss(struct sock *sk) } /* RFC2861. Reset CWND after idle period longer RTO to "restart window". - * This is the first part of cwnd validation mechanism. */ -static void tcp_cwnd_restart(struct sock *sk, const struct dst_entry *dst) + * This is the first part of cwnd validation mechanism. + */ +void tcp_cwnd_restart(struct sock *sk, s32 delta) { struct tcp_sock *tp = tcp_sk(sk); - s32 delta = tcp_time_stamp - tp->lsndtime; - u32 restart_cwnd = tcp_init_cwnd(tp, dst); + u32 restart_cwnd = tcp_init_cwnd(tp, __sk_dst_get(sk)); u32 cwnd = tp->snd_cwnd; tcp_ca_event(sk, CA_EVENT_CWND_RESTART); @@ -163,20 +163,14 @@ static void tcp_event_data_sent(struct tcp_sock *tp, { struct inet_connection_sock *icsk = inet_csk(sk); const u32 now = tcp_time_stamp; - const struct dst_entry *dst = __sk_dst_get(sk); - - if (sysctl_tcp_slow_start_after_idle && - (!tp->packets_out && (s32)(now - tp->lsndtime) > icsk->icsk_rto)) - tcp_cwnd_restart(sk, __sk_dst_get(sk)); tp->lsndtime = now; /* If it is a reply for ato after last received * packet, enter pingpong mode. */ - if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato && - (!dst || !dst_metric(dst, RTAX_QUICKACK))) - icsk->icsk_ack.pingpong = 1; + if ((u32)(now - icsk->icsk_ack.lrcvtime) < icsk->icsk_ack.ato) + icsk->icsk_ack.pingpong = 1; } /* Account for an ACK we sent. */ @@ -1776,7 +1770,7 @@ static bool tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb, if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto send_now; - if (!((1 << icsk->icsk_ca_state) & (TCPF_CA_Open | TCPF_CA_CWR))) + if (icsk->icsk_ca_state >= TCP_CA_Recovery) goto send_now; /* Avoid bursty behavior by allowing defer @@ -2151,7 +2145,7 @@ repair: tcp_cwnd_validate(sk, is_cwnd_limited); return false; } - return (push_one == 2) || (!tp->packets_out && tcp_send_head(sk)); + return !tp->packets_out && tcp_send_head(sk); } bool tcp_schedule_loss_probe(struct sock *sk) @@ -2228,7 +2222,7 @@ static bool skb_still_in_host_queue(const struct sock *sk, return false; } -/* When probe timeout (PTO) fires, send a new segment if one exists, else +/* When probe timeout (PTO) fires, try send a new segment if possible, else * retransmit the last segment. */ void tcp_send_loss_probe(struct sock *sk) @@ -2237,11 +2231,19 @@ void tcp_send_loss_probe(struct sock *sk) struct sk_buff *skb; int pcount; int mss = tcp_current_mss(sk); - int err = -1; - if (tcp_send_head(sk)) { - err = tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); - goto rearm_timer; + skb = tcp_send_head(sk); + if (skb) { + if (tcp_snd_wnd_test(tp, skb, mss)) { + pcount = tp->packets_out; + tcp_write_xmit(sk, mss, TCP_NAGLE_OFF, 2, GFP_ATOMIC); + if (tp->packets_out > pcount) + goto probe_sent; + goto rearm_timer; + } + skb = tcp_write_queue_prev(sk, skb); + } else { + skb = tcp_write_queue_tail(sk); } /* At most one outstanding TLP retransmission. */ @@ -2249,7 +2251,6 @@ void tcp_send_loss_probe(struct sock *sk) goto rearm_timer; /* Retransmit last segment. */ - skb = tcp_write_queue_tail(sk); if (WARN_ON(!skb)) goto rearm_timer; @@ -2264,26 +2265,24 @@ void tcp_send_loss_probe(struct sock *sk) if (unlikely(tcp_fragment(sk, skb, (pcount - 1) * mss, mss, GFP_ATOMIC))) goto rearm_timer; - skb = tcp_write_queue_tail(sk); + skb = tcp_write_queue_next(sk, skb); } if (WARN_ON(!skb || !tcp_skb_pcount(skb))) goto rearm_timer; - err = __tcp_retransmit_skb(sk, skb); + if (__tcp_retransmit_skb(sk, skb)) + goto rearm_timer; /* Record snd_nxt for loss detection. */ - if (likely(!err)) - tp->tlp_high_seq = tp->snd_nxt; + tp->tlp_high_seq = tp->snd_nxt; +probe_sent: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSSPROBES); + /* Reset s.t. tcp_rearm_rto will restart timer from now */ + inet_csk(sk)->icsk_pending = 0; rearm_timer: - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - inet_csk(sk)->icsk_rto, - TCP_RTO_MAX); - - if (likely(!err)) - NET_INC_STATS_BH(sock_net(sk), - LINUX_MIB_TCPLOSSPROBES); + tcp_rearm_rto(sk); } /* Push out any pending frames which were held back due to diff --git a/net/ipv4/tcp_scalable.c b/net/ipv4/tcp_scalable.c index 333bcb2415ff..bf5ea9e9bbc1 100644 --- a/net/ipv4/tcp_scalable.c +++ b/net/ipv4/tcp_scalable.c @@ -22,7 +22,7 @@ static void tcp_scalable_cong_avoid(struct sock *sk, u32 ack, u32 acked) if (!tcp_is_cwnd_limited(sk)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); else tcp_cong_avoid_ai(tp, min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT), diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 5b752f58a900..7149ebc820c7 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -649,4 +649,3 @@ void tcp_init_xmit_timers(struct sock *sk) inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); } -EXPORT_SYMBOL(tcp_init_xmit_timers); diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index a6cea1d5e20d..13951c4087d4 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -225,7 +225,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) */ diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT; - if (diff > gamma && tp->snd_cwnd <= tp->snd_ssthresh) { + if (diff > gamma && tcp_in_slow_start(tp)) { /* Going too fast. Time to slow down * and switch to congestion avoidance. */ @@ -240,7 +240,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1); tp->snd_ssthresh = tcp_vegas_ssthresh(tp); - } else if (tp->snd_cwnd <= tp->snd_ssthresh) { + } else if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { @@ -281,7 +281,7 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 acked) vegas->minRTT = 0x7fffffff; } /* Use normal slow start */ - else if (tp->snd_cwnd <= tp->snd_ssthresh) + else if (tcp_in_slow_start(tp)) tcp_slow_start(tp, acked); } diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index 112151eeee45..0d094b995cd9 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -150,7 +150,7 @@ static void tcp_veno_cong_avoid(struct sock *sk, u32 ack, u32 acked) veno->diff = (tp->snd_cwnd << V_PARAM_SHIFT) - target_cwnd; - if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (tcp_in_slow_start(tp)) { /* Slow start. */ tcp_slow_start(tp, acked); } else { diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1b8c5ba7d5f7..c0a15e7f359f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1013,11 +1013,31 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) if (!rt) { struct net *net = sock_net(sk); + __u8 flow_flags = inet_sk_flowi_flags(sk); fl4 = &fl4_stack; + + /* unconnected socket. If output device is enslaved to a VRF + * device lookup source address from VRF table. This mimics + * behavior of ip_route_connect{_init}. + */ + if (netif_index_is_vrf(net, ipc.oif)) { + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, sk->sk_protocol, + (flow_flags | FLOWI_FLAG_VRFSRC), + faddr, saddr, dport, + inet->inet_sport); + + rt = ip_route_output_flow(net, fl4, sk); + if (!IS_ERR(rt)) { + saddr = fl4->saddr; + ip_rt_put(rt); + } + } + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, RT_SCOPE_UNIVERSE, sk->sk_protocol, - inet_sk_flowi_flags(sk), + flow_flags, faddr, saddr, dport, inet->inet_sport); security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); diff --git a/net/ipv4/udp_tunnel.c b/net/ipv4/udp_tunnel.c index 933ea903f7b8..aba428626b52 100644 --- a/net/ipv4/udp_tunnel.c +++ b/net/ipv4/udp_tunnel.c @@ -4,9 +4,10 @@ #include <linux/udp.h> #include <linux/types.h> #include <linux/kernel.h> +#include <net/dst_metadata.h> +#include <net/net_namespace.h> #include <net/udp.h> #include <net/udp_tunnel.h> -#include <net/net_namespace.h> int udp_sock_create4(struct net *net, struct udp_port_cfg *cfg, struct socket **sockp) @@ -103,4 +104,26 @@ void udp_tunnel_sock_release(struct socket *sock) } EXPORT_SYMBOL_GPL(udp_tunnel_sock_release); +struct metadata_dst *udp_tun_rx_dst(struct sk_buff *skb, unsigned short family, + __be16 flags, __be64 tunnel_id, int md_size) +{ + struct metadata_dst *tun_dst; + struct ip_tunnel_info *info; + + if (family == AF_INET) + tun_dst = ip_tun_rx_dst(skb, flags, tunnel_id, md_size); + else + tun_dst = ipv6_tun_rx_dst(skb, flags, tunnel_id, md_size); + if (!tun_dst) + return NULL; + + info = &tun_dst->u.tun_info; + info->key.tp_src = udp_hdr(skb)->source; + info->key.tp_dst = udp_hdr(skb)->dest; + if (udp_hdr(skb)->check) + info->key.tun_flags |= TUNNEL_CSUM; + return tun_dst; +} +EXPORT_SYMBOL_GPL(udp_tun_rx_dst); + MODULE_LICENSE("GPL"); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index bff69746e05f..bb919b28619f 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -15,11 +15,12 @@ #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> +#include <net/vrf.h> static struct xfrm_policy_afinfo xfrm4_policy_afinfo; static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, - int tos, + int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { @@ -28,6 +29,7 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, memset(fl4, 0, sizeof(*fl4)); fl4->daddr = daddr->a4; fl4->flowi4_tos = tos; + fl4->flowi4_oif = oif; if (saddr) fl4->saddr = saddr->a4; @@ -38,22 +40,22 @@ static struct dst_entry *__xfrm4_dst_lookup(struct net *net, struct flowi4 *fl4, return ERR_CAST(rt); } -static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, +static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, int oif, const xfrm_address_t *saddr, const xfrm_address_t *daddr) { struct flowi4 fl4; - return __xfrm4_dst_lookup(net, &fl4, tos, saddr, daddr); + return __xfrm4_dst_lookup(net, &fl4, tos, oif, saddr, daddr); } -static int xfrm4_get_saddr(struct net *net, +static int xfrm4_get_saddr(struct net *net, int oif, xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; struct flowi4 fl4; - dst = __xfrm4_dst_lookup(net, &fl4, 0, NULL, daddr); + dst = __xfrm4_dst_lookup(net, &fl4, 0, oif, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -106,8 +108,10 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) struct flowi4 *fl4 = &fl->u.ip4; int oif = 0; - if (skb_dst(skb)) - oif = skb_dst(skb)->dev->ifindex; + if (skb_dst(skb)) { + oif = vrf_master_ifindex(skb_dst(skb)->dev) ? + : skb_dst(skb)->dev->ifindex; + } memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; |