diff options
author | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-03-25 03:53:42 -0300 |
---|---|---|
committer | André Fabian Silva Delgado <emulatorman@parabola.nu> | 2016-03-25 03:53:42 -0300 |
commit | 03dd4cb26d967f9588437b0fc9cc0e8353322bb7 (patch) | |
tree | fa581f6dc1c0596391690d1f67eceef3af8246dc /net/ipv6 | |
parent | d4e493caf788ef44982e131ff9c786546904d934 (diff) |
Linux-libre 4.5-gnu
Diffstat (limited to 'net/ipv6')
27 files changed, 1185 insertions, 268 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index 983bb9997..40c897515 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -69,6 +69,7 @@ config INET6_ESP select CRYPTO_CBC select CRYPTO_SHA1 select CRYPTO_DES + select CRYPTO_ECHAINIV ---help--- Support for IPsec ESP. @@ -94,6 +95,7 @@ config IPV6_MIP6 config IPV6_ILA tristate "IPv6: Identifier Locator Addressing (ILA)" + depends on NETFILTER select LWTUNNEL ---help--- Support for IPv6 Identifier Locator Addressing (ILA). diff --git a/net/ipv6/Makefile b/net/ipv6/Makefile index 2c900c7b7..2fbd90bf8 100644 --- a/net/ipv6/Makefile +++ b/net/ipv6/Makefile @@ -34,7 +34,7 @@ obj-$(CONFIG_INET6_XFRM_MODE_TUNNEL) += xfrm6_mode_tunnel.o obj-$(CONFIG_INET6_XFRM_MODE_ROUTEOPTIMIZATION) += xfrm6_mode_ro.o obj-$(CONFIG_INET6_XFRM_MODE_BEET) += xfrm6_mode_beet.o obj-$(CONFIG_IPV6_MIP6) += mip6.o -obj-$(CONFIG_IPV6_ILA) += ila.o +obj-$(CONFIG_IPV6_ILA) += ila/ obj-$(CONFIG_NETFILTER) += netfilter/ obj-$(CONFIG_IPV6_VTI) += ip6_vti.o diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index e8d3da081..bdd7eac43 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -70,7 +70,7 @@ #include <net/sock.h> #include <net/snmp.h> -#include <net/af_ieee802154.h> +#include <net/6lowpan.h> #include <net/firewire.h> #include <net/ipv6.h> #include <net/protocol.h> @@ -1772,12 +1772,13 @@ struct inet6_ifaddr *ipv6_get_ifaddr(struct net *net, const struct in6_addr *add static void addrconf_dad_stop(struct inet6_ifaddr *ifp, int dad_failed) { + if (dad_failed) + ifp->flags |= IFA_F_DADFAILED; + if (ifp->flags&IFA_F_PERMANENT) { spin_lock_bh(&ifp->lock); addrconf_del_dad_work(ifp); ifp->flags |= IFA_F_TENTATIVE; - if (dad_failed) - ifp->flags |= IFA_F_DADFAILED; spin_unlock_bh(&ifp->lock); if (dad_failed) ipv6_ifa_notify(0, ifp); @@ -1953,9 +1954,9 @@ static void addrconf_leave_anycast(struct inet6_ifaddr *ifp) static int addrconf_ifid_eui64(u8 *eui, struct net_device *dev) { - if (dev->addr_len != IEEE802154_ADDR_LEN) + if (dev->addr_len != EUI64_ADDR_LEN) return -1; - memcpy(eui, dev->dev_addr, 8); + memcpy(eui, dev->dev_addr, EUI64_ADDR_LEN); eui[0] ^= 2; return 0; } @@ -2047,7 +2048,6 @@ static int ipv6_generate_eui64(u8 *eui, struct net_device *dev) case ARPHRD_IPGRE: return addrconf_ifid_gre(eui, dev); case ARPHRD_6LOWPAN: - case ARPHRD_IEEE802154: return addrconf_ifid_eui64(eui, dev); case ARPHRD_IEEE1394: return addrconf_ifid_ieee1394(eui, dev); @@ -2320,6 +2320,12 @@ static void manage_tempaddrs(struct inet6_dev *idev, } } +static bool is_addr_mode_generate_stable(struct inet6_dev *idev) +{ + return idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY || + idev->addr_gen_mode == IN6_ADDR_GEN_MODE_RANDOM; +} + void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) { struct prefix_info *pinfo; @@ -2433,8 +2439,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) in6_dev->token.s6_addr + 8, 8); read_unlock_bh(&in6_dev->lock); tokenized = true; - } else if (in6_dev->addr_gen_mode == - IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + } else if (is_addr_mode_generate_stable(in6_dev) && !ipv6_generate_stable_address(&addr, 0, in6_dev)) { addr_flags |= IFA_F_STABLE_PRIVACY; @@ -3034,6 +3039,17 @@ retry: return 0; } +static void ipv6_gen_mode_random_init(struct inet6_dev *idev) +{ + struct ipv6_stable_secret *s = &idev->cnf.stable_secret; + + if (s->initialized) + return; + s = &idev->cnf.stable_secret; + get_random_bytes(&s->secret, sizeof(s->secret)); + s->initialized = true; +} + static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) { struct in6_addr addr; @@ -3044,13 +3060,18 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) ipv6_addr_set(&addr, htonl(0xFE800000), 0, 0, 0); - if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY) { + switch (idev->addr_gen_mode) { + case IN6_ADDR_GEN_MODE_RANDOM: + ipv6_gen_mode_random_init(idev); + /* fallthrough */ + case IN6_ADDR_GEN_MODE_STABLE_PRIVACY: if (!ipv6_generate_stable_address(&addr, 0, idev)) addrconf_add_linklocal(idev, &addr, IFA_F_STABLE_PRIVACY); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); - } else if (idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) { + break; + case IN6_ADDR_GEN_MODE_EUI64: /* addrconf_add_linklocal also adds a prefix_route and we * only need to care about prefix routes if ipv6_generate_eui64 * couldn't generate one. @@ -3059,6 +3080,11 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + break; + case IN6_ADDR_GEN_MODE_NONE: + default: + /* will not add any link local address */ + break; } } @@ -3072,10 +3098,10 @@ static void addrconf_dev_config(struct net_device *dev) (dev->type != ARPHRD_FDDI) && (dev->type != ARPHRD_ARCNET) && (dev->type != ARPHRD_INFINIBAND) && - (dev->type != ARPHRD_IEEE802154) && (dev->type != ARPHRD_IEEE1394) && (dev->type != ARPHRD_TUNNEL6) && - (dev->type != ARPHRD_6LOWPAN)) { + (dev->type != ARPHRD_6LOWPAN) && + (dev->type != ARPHRD_NONE)) { /* Alas, we support only Ethernet autoconfiguration. */ return; } @@ -3084,6 +3110,11 @@ static void addrconf_dev_config(struct net_device *dev) if (IS_ERR(idev)) return; + /* this device type has no EUI support */ + if (dev->type == ARPHRD_NONE && + idev->addr_gen_mode == IN6_ADDR_GEN_MODE_EUI64) + idev->addr_gen_mode = IN6_ADDR_GEN_MODE_RANDOM; + addrconf_addr_gen(idev, false); } @@ -3293,7 +3324,8 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, case NETDEV_PRE_TYPE_CHANGE: case NETDEV_POST_TYPE_CHANGE: - addrconf_type_change(dev, event); + if (idev) + addrconf_type_change(dev, event); break; } @@ -4930,7 +4962,8 @@ static int inet6_set_link_af(struct net_device *dev, const struct nlattr *nla) if (mode != IN6_ADDR_GEN_MODE_EUI64 && mode != IN6_ADDR_GEN_MODE_NONE && - mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY) + mode != IN6_ADDR_GEN_MODE_STABLE_PRIVACY && + mode != IN6_ADDR_GEN_MODE_RANDOM) return -EINVAL; if (mode == IN6_ADDR_GEN_MODE_STABLE_PRIVACY && @@ -5209,6 +5242,20 @@ int addrconf_sysctl_forward(struct ctl_table *ctl, int write, } static +int addrconf_sysctl_hop_limit(struct ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, loff_t *ppos) +{ + struct ctl_table lctl; + int min_hl = 1, max_hl = 255; + + lctl = *ctl; + lctl.extra1 = &min_hl; + lctl.extra2 = &max_hl; + + return proc_dointvec_minmax(&lctl, write, buffer, lenp, ppos); +} + +static int addrconf_sysctl_mtu(struct ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { @@ -5460,7 +5507,7 @@ static struct addrconf_sysctl_table .data = &ipv6_devconf.hop_limit, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .proc_handler = addrconf_sysctl_hop_limit, }, { .procname = "mtu", diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index 5c5d23e59..9508a20fb 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -257,7 +257,11 @@ int ipv6_find_hdr(const struct sk_buff *skb, unsigned int *offset, *fragoff = _frag_off; return hp->nexthdr; } - return -ENOENT; + if (!found) + return -ENOENT; + if (fragoff) + *fragoff = _frag_off; + break; } hdrlen = 8; } else if (nexthdr == NEXTHDR_AUTH) { diff --git a/net/ipv6/ila/Makefile b/net/ipv6/ila/Makefile new file mode 100644 index 000000000..4b32e5921 --- /dev/null +++ b/net/ipv6/ila/Makefile @@ -0,0 +1,7 @@ +# +# Makefile for ILA module +# + +obj-$(CONFIG_IPV6_ILA) += ila.o + +ila-objs := ila_common.o ila_lwt.o ila_xlat.o diff --git a/net/ipv6/ila/ila.h b/net/ipv6/ila/ila.h new file mode 100644 index 000000000..28542cb2b --- /dev/null +++ b/net/ipv6/ila/ila.h @@ -0,0 +1,48 @@ +/* + * Copyright (c) 2015 Tom Herbert <tom@herbertland.com> + * + * 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. + * + */ + +#ifndef __ILA_H +#define __ILA_H + +#include <linux/errno.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/socket.h> +#include <linux/skbuff.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ip.h> +#include <net/protocol.h> +#include <uapi/linux/ila.h> + +struct ila_params { + __be64 locator; + __be64 locator_match; + __wsum csum_diff; +}; + +static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) +{ + __be32 diff[] = { + ~from[0], ~from[1], to[0], to[1], + }; + + return csum_partial(diff, sizeof(diff), 0); +} + +void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p); + +int ila_lwt_init(void); +void ila_lwt_fini(void); +int ila_xlat_init(void); +void ila_xlat_fini(void); + +#endif /* __ILA_H */ diff --git a/net/ipv6/ila/ila_common.c b/net/ipv6/ila/ila_common.c new file mode 100644 index 000000000..32dc9aab7 --- /dev/null +++ b/net/ipv6/ila/ila_common.c @@ -0,0 +1,103 @@ +#include <linux/errno.h> +#include <linux/ip.h> +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/socket.h> +#include <linux/types.h> +#include <net/checksum.h> +#include <net/ip.h> +#include <net/ip6_fib.h> +#include <net/lwtunnel.h> +#include <net/protocol.h> +#include <uapi/linux/ila.h> +#include "ila.h" + +static __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) +{ + if (*(__be64 *)&ip6h->daddr == p->locator_match) + return p->csum_diff; + else + return compute_csum_diff8((__be32 *)&ip6h->daddr, + (__be32 *)&p->locator); +} + +void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) +{ + __wsum diff; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + size_t nhoff = sizeof(struct ipv6hdr); + + /* First update checksum */ + switch (ip6h->nexthdr) { + case NEXTHDR_TCP: + if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) { + struct tcphdr *th = (struct tcphdr *) + (skb_network_header(skb) + nhoff); + + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&th->check, skb, + diff, true); + } + break; + case NEXTHDR_UDP: + if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) { + struct udphdr *uh = (struct udphdr *) + (skb_network_header(skb) + nhoff); + + if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&uh->check, skb, + diff, true); + if (!uh->check) + uh->check = CSUM_MANGLED_0; + } + } + break; + case NEXTHDR_ICMP: + if (likely(pskb_may_pull(skb, + nhoff + sizeof(struct icmp6hdr)))) { + struct icmp6hdr *ih = (struct icmp6hdr *) + (skb_network_header(skb) + nhoff); + + diff = get_csum_diff(ip6h, p); + inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, + diff, true); + } + break; + } + + /* Now change destination address */ + *(__be64 *)&ip6h->daddr = p->locator; +} + +static int __init ila_init(void) +{ + int ret; + + ret = ila_lwt_init(); + + if (ret) + goto fail_lwt; + + ret = ila_xlat_init(); + if (ret) + goto fail_xlat; + + return 0; +fail_xlat: + ila_lwt_fini(); +fail_lwt: + return ret; +} + +static void __exit ila_fini(void) +{ + ila_xlat_fini(); + ila_lwt_fini(); +} + +module_init(ila_init); +module_exit(ila_fini); +MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); +MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila.c b/net/ipv6/ila/ila_lwt.c index 1a6852e1a..2ae3c4fd8 100644 --- a/net/ipv6/ila.c +++ b/net/ipv6/ila/ila_lwt.c @@ -11,12 +11,7 @@ #include <net/lwtunnel.h> #include <net/protocol.h> #include <uapi/linux/ila.h> - -struct ila_params { - __be64 locator; - __be64 locator_match; - __wsum csum_diff; -}; +#include "ila.h" static inline struct ila_params *ila_params_lwtunnel( struct lwtunnel_state *lwstate) @@ -24,73 +19,6 @@ static inline struct ila_params *ila_params_lwtunnel( return (struct ila_params *)lwstate->data; } -static inline __wsum compute_csum_diff8(const __be32 *from, const __be32 *to) -{ - __be32 diff[] = { - ~from[0], ~from[1], to[0], to[1], - }; - - return csum_partial(diff, sizeof(diff), 0); -} - -static inline __wsum get_csum_diff(struct ipv6hdr *ip6h, struct ila_params *p) -{ - if (*(__be64 *)&ip6h->daddr == p->locator_match) - return p->csum_diff; - else - return compute_csum_diff8((__be32 *)&ip6h->daddr, - (__be32 *)&p->locator); -} - -static void update_ipv6_locator(struct sk_buff *skb, struct ila_params *p) -{ - __wsum diff; - struct ipv6hdr *ip6h = ipv6_hdr(skb); - size_t nhoff = sizeof(struct ipv6hdr); - - /* First update checksum */ - switch (ip6h->nexthdr) { - case NEXTHDR_TCP: - if (likely(pskb_may_pull(skb, nhoff + sizeof(struct tcphdr)))) { - struct tcphdr *th = (struct tcphdr *) - (skb_network_header(skb) + nhoff); - - diff = get_csum_diff(ip6h, p); - inet_proto_csum_replace_by_diff(&th->check, skb, - diff, true); - } - break; - case NEXTHDR_UDP: - if (likely(pskb_may_pull(skb, nhoff + sizeof(struct udphdr)))) { - struct udphdr *uh = (struct udphdr *) - (skb_network_header(skb) + nhoff); - - if (uh->check || skb->ip_summed == CHECKSUM_PARTIAL) { - diff = get_csum_diff(ip6h, p); - inet_proto_csum_replace_by_diff(&uh->check, skb, - diff, true); - if (!uh->check) - uh->check = CSUM_MANGLED_0; - } - } - break; - case NEXTHDR_ICMP: - if (likely(pskb_may_pull(skb, - nhoff + sizeof(struct icmp6hdr)))) { - struct icmp6hdr *ih = (struct icmp6hdr *) - (skb_network_header(skb) + nhoff); - - diff = get_csum_diff(ip6h, p); - inet_proto_csum_replace_by_diff(&ih->icmp6_cksum, skb, - diff, true); - } - break; - } - - /* Now change destination address */ - *(__be64 *)&ip6h->daddr = p->locator; -} - static int ila_output(struct net *net, struct sock *sk, struct sk_buff *skb) { struct dst_entry *dst = skb_dst(skb); @@ -213,17 +141,12 @@ static const struct lwtunnel_encap_ops ila_encap_ops = { .cmp_encap = ila_encap_cmp, }; -static int __init ila_init(void) +int ila_lwt_init(void) { return lwtunnel_encap_add_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); } -static void __exit ila_fini(void) +void ila_lwt_fini(void) { lwtunnel_encap_del_ops(&ila_encap_ops, LWTUNNEL_ENCAP_ILA); } - -module_init(ila_init); -module_exit(ila_fini); -MODULE_AUTHOR("Tom Herbert <tom@herbertland.com>"); -MODULE_LICENSE("GPL"); diff --git a/net/ipv6/ila/ila_xlat.c b/net/ipv6/ila/ila_xlat.c new file mode 100644 index 000000000..295ca29a2 --- /dev/null +++ b/net/ipv6/ila/ila_xlat.c @@ -0,0 +1,680 @@ +#include <linux/jhash.h> +#include <linux/netfilter.h> +#include <linux/rcupdate.h> +#include <linux/rhashtable.h> +#include <linux/vmalloc.h> +#include <net/genetlink.h> +#include <net/ila.h> +#include <net/netns/generic.h> +#include <uapi/linux/genetlink.h> +#include "ila.h" + +struct ila_xlat_params { + struct ila_params ip; + __be64 identifier; + int ifindex; + unsigned int dir; +}; + +struct ila_map { + struct ila_xlat_params p; + struct rhash_head node; + struct ila_map __rcu *next; + struct rcu_head rcu; +}; + +static unsigned int ila_net_id; + +struct ila_net { + struct rhashtable rhash_table; + spinlock_t *locks; /* Bucket locks for entry manipulation */ + unsigned int locks_mask; + bool hooks_registered; +}; + +#define LOCKS_PER_CPU 10 + +static int alloc_ila_locks(struct ila_net *ilan) +{ + unsigned int i, size; + unsigned int nr_pcpus = num_possible_cpus(); + + nr_pcpus = min_t(unsigned int, nr_pcpus, 32UL); + size = roundup_pow_of_two(nr_pcpus * LOCKS_PER_CPU); + + if (sizeof(spinlock_t) != 0) { +#ifdef CONFIG_NUMA + if (size * sizeof(spinlock_t) > PAGE_SIZE) + ilan->locks = vmalloc(size * sizeof(spinlock_t)); + else +#endif + ilan->locks = kmalloc_array(size, sizeof(spinlock_t), + GFP_KERNEL); + if (!ilan->locks) + return -ENOMEM; + for (i = 0; i < size; i++) + spin_lock_init(&ilan->locks[i]); + } + ilan->locks_mask = size - 1; + + return 0; +} + +static u32 hashrnd __read_mostly; +static __always_inline void __ila_hash_secret_init(void) +{ + net_get_random_once(&hashrnd, sizeof(hashrnd)); +} + +static inline u32 ila_identifier_hash(__be64 identifier) +{ + u32 *v = (u32 *)&identifier; + + return jhash_2words(v[0], v[1], hashrnd); +} + +static inline spinlock_t *ila_get_lock(struct ila_net *ilan, __be64 identifier) +{ + return &ilan->locks[ila_identifier_hash(identifier) & ilan->locks_mask]; +} + +static inline int ila_cmp_wildcards(struct ila_map *ila, __be64 loc, + int ifindex, unsigned int dir) +{ + return (ila->p.ip.locator_match && ila->p.ip.locator_match != loc) || + (ila->p.ifindex && ila->p.ifindex != ifindex) || + !(ila->p.dir & dir); +} + +static inline int ila_cmp_params(struct ila_map *ila, struct ila_xlat_params *p) +{ + return (ila->p.ip.locator_match != p->ip.locator_match) || + (ila->p.ifindex != p->ifindex) || + (ila->p.dir != p->dir); +} + +static int ila_cmpfn(struct rhashtable_compare_arg *arg, + const void *obj) +{ + const struct ila_map *ila = obj; + + return (ila->p.identifier != *(__be64 *)arg->key); +} + +static inline int ila_order(struct ila_map *ila) +{ + int score = 0; + + if (ila->p.ip.locator_match) + score += 1 << 0; + + if (ila->p.ifindex) + score += 1 << 1; + + return score; +} + +static const struct rhashtable_params rht_params = { + .nelem_hint = 1024, + .head_offset = offsetof(struct ila_map, node), + .key_offset = offsetof(struct ila_map, p.identifier), + .key_len = sizeof(u64), /* identifier */ + .max_size = 1048576, + .min_size = 256, + .automatic_shrinking = true, + .obj_cmpfn = ila_cmpfn, +}; + +static struct genl_family ila_nl_family = { + .id = GENL_ID_GENERATE, + .hdrsize = 0, + .name = ILA_GENL_NAME, + .version = ILA_GENL_VERSION, + .maxattr = ILA_ATTR_MAX, + .netnsok = true, + .parallel_ops = true, +}; + +static struct nla_policy ila_nl_policy[ILA_ATTR_MAX + 1] = { + [ILA_ATTR_IDENTIFIER] = { .type = NLA_U64, }, + [ILA_ATTR_LOCATOR] = { .type = NLA_U64, }, + [ILA_ATTR_LOCATOR_MATCH] = { .type = NLA_U64, }, + [ILA_ATTR_IFINDEX] = { .type = NLA_U32, }, + [ILA_ATTR_DIR] = { .type = NLA_U32, }, +}; + +static int parse_nl_config(struct genl_info *info, + struct ila_xlat_params *p) +{ + memset(p, 0, sizeof(*p)); + + if (info->attrs[ILA_ATTR_IDENTIFIER]) + p->identifier = (__force __be64)nla_get_u64( + info->attrs[ILA_ATTR_IDENTIFIER]); + + if (info->attrs[ILA_ATTR_LOCATOR]) + p->ip.locator = (__force __be64)nla_get_u64( + info->attrs[ILA_ATTR_LOCATOR]); + + if (info->attrs[ILA_ATTR_LOCATOR_MATCH]) + p->ip.locator_match = (__force __be64)nla_get_u64( + info->attrs[ILA_ATTR_LOCATOR_MATCH]); + + if (info->attrs[ILA_ATTR_IFINDEX]) + p->ifindex = nla_get_s32(info->attrs[ILA_ATTR_IFINDEX]); + + if (info->attrs[ILA_ATTR_DIR]) + p->dir = nla_get_u32(info->attrs[ILA_ATTR_DIR]); + + return 0; +} + +/* Must be called with rcu readlock */ +static inline struct ila_map *ila_lookup_wildcards(__be64 id, __be64 loc, + int ifindex, + unsigned int dir, + struct ila_net *ilan) +{ + struct ila_map *ila; + + ila = rhashtable_lookup_fast(&ilan->rhash_table, &id, rht_params); + while (ila) { + if (!ila_cmp_wildcards(ila, loc, ifindex, dir)) + return ila; + ila = rcu_access_pointer(ila->next); + } + + return NULL; +} + +/* Must be called with rcu readlock */ +static inline struct ila_map *ila_lookup_by_params(struct ila_xlat_params *p, + struct ila_net *ilan) +{ + struct ila_map *ila; + + ila = rhashtable_lookup_fast(&ilan->rhash_table, &p->identifier, + rht_params); + while (ila) { + if (!ila_cmp_params(ila, p)) + return ila; + ila = rcu_access_pointer(ila->next); + } + + return NULL; +} + +static inline void ila_release(struct ila_map *ila) +{ + kfree_rcu(ila, rcu); +} + +static void ila_free_cb(void *ptr, void *arg) +{ + struct ila_map *ila = (struct ila_map *)ptr, *next; + + /* Assume rcu_readlock held */ + while (ila) { + next = rcu_access_pointer(ila->next); + ila_release(ila); + ila = next; + } +} + +static int ila_xlat_addr(struct sk_buff *skb, int dir); + +static unsigned int +ila_nf_input(void *priv, + struct sk_buff *skb, + const struct nf_hook_state *state) +{ + ila_xlat_addr(skb, ILA_DIR_IN); + return NF_ACCEPT; +} + +static struct nf_hook_ops ila_nf_hook_ops[] __read_mostly = { + { + .hook = ila_nf_input, + .pf = NFPROTO_IPV6, + .hooknum = NF_INET_PRE_ROUTING, + .priority = -1, + }, +}; + +static int ila_add_mapping(struct net *net, struct ila_xlat_params *p) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + struct ila_map *ila, *head; + spinlock_t *lock = ila_get_lock(ilan, p->identifier); + int err = 0, order; + + if (!ilan->hooks_registered) { + /* We defer registering net hooks in the namespace until the + * first mapping is added. + */ + err = nf_register_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); + if (err) + return err; + + ilan->hooks_registered = true; + } + + ila = kzalloc(sizeof(*ila), GFP_KERNEL); + if (!ila) + return -ENOMEM; + + ila->p = *p; + + if (p->ip.locator_match) { + /* Precompute checksum difference for translation since we + * know both the old identifier and the new one. + */ + ila->p.ip.csum_diff = compute_csum_diff8( + (__be32 *)&p->ip.locator_match, + (__be32 *)&p->ip.locator); + } + + order = ila_order(ila); + + spin_lock(lock); + + head = rhashtable_lookup_fast(&ilan->rhash_table, &p->identifier, + rht_params); + if (!head) { + /* New entry for the rhash_table */ + err = rhashtable_lookup_insert_fast(&ilan->rhash_table, + &ila->node, rht_params); + } else { + struct ila_map *tila = head, *prev = NULL; + + do { + if (!ila_cmp_params(tila, p)) { + err = -EEXIST; + goto out; + } + + if (order > ila_order(tila)) + break; + + prev = tila; + tila = rcu_dereference_protected(tila->next, + lockdep_is_held(lock)); + } while (tila); + + if (prev) { + /* Insert in sub list of head */ + RCU_INIT_POINTER(ila->next, tila); + rcu_assign_pointer(prev->next, ila); + } else { + /* Make this ila new head */ + RCU_INIT_POINTER(ila->next, head); + err = rhashtable_replace_fast(&ilan->rhash_table, + &head->node, + &ila->node, rht_params); + if (err) + goto out; + } + } + +out: + spin_unlock(lock); + + if (err) + kfree(ila); + + return err; +} + +static int ila_del_mapping(struct net *net, struct ila_xlat_params *p) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + struct ila_map *ila, *head, *prev; + spinlock_t *lock = ila_get_lock(ilan, p->identifier); + int err = -ENOENT; + + spin_lock(lock); + + head = rhashtable_lookup_fast(&ilan->rhash_table, + &p->identifier, rht_params); + ila = head; + + prev = NULL; + + while (ila) { + if (ila_cmp_params(ila, p)) { + prev = ila; + ila = rcu_dereference_protected(ila->next, + lockdep_is_held(lock)); + continue; + } + + err = 0; + + if (prev) { + /* Not head, just delete from list */ + rcu_assign_pointer(prev->next, ila->next); + } else { + /* It is the head. If there is something in the + * sublist we need to make a new head. + */ + head = rcu_dereference_protected(ila->next, + lockdep_is_held(lock)); + if (head) { + /* Put first entry in the sublist into the + * table + */ + err = rhashtable_replace_fast( + &ilan->rhash_table, &ila->node, + &head->node, rht_params); + if (err) + goto out; + } else { + /* Entry no longer used */ + err = rhashtable_remove_fast(&ilan->rhash_table, + &ila->node, + rht_params); + } + } + + ila_release(ila); + + break; + } + +out: + spin_unlock(lock); + + return err; +} + +static int ila_nl_cmd_add_mapping(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_xlat_params p; + int err; + + err = parse_nl_config(info, &p); + if (err) + return err; + + return ila_add_mapping(net, &p); +} + +static int ila_nl_cmd_del_mapping(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_xlat_params p; + int err; + + err = parse_nl_config(info, &p); + if (err) + return err; + + ila_del_mapping(net, &p); + + return 0; +} + +static int ila_fill_info(struct ila_map *ila, struct sk_buff *msg) +{ + if (nla_put_u64(msg, ILA_ATTR_IDENTIFIER, + (__force u64)ila->p.identifier) || + nla_put_u64(msg, ILA_ATTR_LOCATOR, + (__force u64)ila->p.ip.locator) || + nla_put_u64(msg, ILA_ATTR_LOCATOR_MATCH, + (__force u64)ila->p.ip.locator_match) || + nla_put_s32(msg, ILA_ATTR_IFINDEX, ila->p.ifindex) || + nla_put_u32(msg, ILA_ATTR_DIR, ila->p.dir)) + return -1; + + return 0; +} + +static int ila_dump_info(struct ila_map *ila, + u32 portid, u32 seq, u32 flags, + struct sk_buff *skb, u8 cmd) +{ + void *hdr; + + hdr = genlmsg_put(skb, portid, seq, &ila_nl_family, flags, cmd); + if (!hdr) + return -ENOMEM; + + if (ila_fill_info(ila, skb) < 0) + goto nla_put_failure; + + genlmsg_end(skb, hdr); + return 0; + +nla_put_failure: + genlmsg_cancel(skb, hdr); + return -EMSGSIZE; +} + +static int ila_nl_cmd_get_mapping(struct sk_buff *skb, struct genl_info *info) +{ + struct net *net = genl_info_net(info); + struct ila_net *ilan = net_generic(net, ila_net_id); + struct sk_buff *msg; + struct ila_xlat_params p; + struct ila_map *ila; + int ret; + + ret = parse_nl_config(info, &p); + if (ret) + return ret; + + msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_KERNEL); + if (!msg) + return -ENOMEM; + + rcu_read_lock(); + + ila = ila_lookup_by_params(&p, ilan); + if (ila) { + ret = ila_dump_info(ila, + info->snd_portid, + info->snd_seq, 0, msg, + info->genlhdr->cmd); + } + + rcu_read_unlock(); + + if (ret < 0) + goto out_free; + + return genlmsg_reply(msg, info); + +out_free: + nlmsg_free(msg); + return ret; +} + +struct ila_dump_iter { + struct rhashtable_iter rhiter; +}; + +static int ila_nl_dump_start(struct netlink_callback *cb) +{ + struct net *net = sock_net(cb->skb->sk); + struct ila_net *ilan = net_generic(net, ila_net_id); + struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; + + return rhashtable_walk_init(&ilan->rhash_table, &iter->rhiter); +} + +static int ila_nl_dump_done(struct netlink_callback *cb) +{ + struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; + + rhashtable_walk_exit(&iter->rhiter); + + return 0; +} + +static int ila_nl_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct ila_dump_iter *iter = (struct ila_dump_iter *)cb->args; + struct rhashtable_iter *rhiter = &iter->rhiter; + struct ila_map *ila; + int ret; + + ret = rhashtable_walk_start(rhiter); + if (ret && ret != -EAGAIN) + goto done; + + for (;;) { + ila = rhashtable_walk_next(rhiter); + + if (IS_ERR(ila)) { + if (PTR_ERR(ila) == -EAGAIN) + continue; + ret = PTR_ERR(ila); + goto done; + } else if (!ila) { + break; + } + + while (ila) { + ret = ila_dump_info(ila, NETLINK_CB(cb->skb).portid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, + skb, ILA_CMD_GET); + if (ret) + goto done; + + ila = rcu_access_pointer(ila->next); + } + } + + ret = skb->len; + +done: + rhashtable_walk_stop(rhiter); + return ret; +} + +static const struct genl_ops ila_nl_ops[] = { + { + .cmd = ILA_CMD_ADD, + .doit = ila_nl_cmd_add_mapping, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_DEL, + .doit = ila_nl_cmd_del_mapping, + .policy = ila_nl_policy, + .flags = GENL_ADMIN_PERM, + }, + { + .cmd = ILA_CMD_GET, + .doit = ila_nl_cmd_get_mapping, + .start = ila_nl_dump_start, + .dumpit = ila_nl_dump, + .done = ila_nl_dump_done, + .policy = ila_nl_policy, + }, +}; + +#define ILA_HASH_TABLE_SIZE 1024 + +static __net_init int ila_init_net(struct net *net) +{ + int err; + struct ila_net *ilan = net_generic(net, ila_net_id); + + err = alloc_ila_locks(ilan); + if (err) + return err; + + rhashtable_init(&ilan->rhash_table, &rht_params); + + return 0; +} + +static __net_exit void ila_exit_net(struct net *net) +{ + struct ila_net *ilan = net_generic(net, ila_net_id); + + rhashtable_free_and_destroy(&ilan->rhash_table, ila_free_cb, NULL); + + kvfree(ilan->locks); + + if (ilan->hooks_registered) + nf_unregister_net_hooks(net, ila_nf_hook_ops, + ARRAY_SIZE(ila_nf_hook_ops)); +} + +static struct pernet_operations ila_net_ops = { + .init = ila_init_net, + .exit = ila_exit_net, + .id = &ila_net_id, + .size = sizeof(struct ila_net), +}; + +static int ila_xlat_addr(struct sk_buff *skb, int dir) +{ + struct ila_map *ila; + struct ipv6hdr *ip6h = ipv6_hdr(skb); + struct net *net = dev_net(skb->dev); + struct ila_net *ilan = net_generic(net, ila_net_id); + __be64 identifier, locator_match; + size_t nhoff; + + /* Assumes skb contains a valid IPv6 header that is pulled */ + + identifier = *(__be64 *)&ip6h->daddr.in6_u.u6_addr8[8]; + locator_match = *(__be64 *)&ip6h->daddr.in6_u.u6_addr8[0]; + nhoff = sizeof(struct ipv6hdr); + + rcu_read_lock(); + + ila = ila_lookup_wildcards(identifier, locator_match, + skb->dev->ifindex, dir, ilan); + if (ila) + update_ipv6_locator(skb, &ila->p.ip); + + rcu_read_unlock(); + + return 0; +} + +int ila_xlat_incoming(struct sk_buff *skb) +{ + return ila_xlat_addr(skb, ILA_DIR_IN); +} +EXPORT_SYMBOL(ila_xlat_incoming); + +int ila_xlat_outgoing(struct sk_buff *skb) +{ + return ila_xlat_addr(skb, ILA_DIR_OUT); +} +EXPORT_SYMBOL(ila_xlat_outgoing); + +int ila_xlat_init(void) +{ + int ret; + + ret = register_pernet_device(&ila_net_ops); + if (ret) + goto exit; + + ret = genl_register_family_with_ops(&ila_nl_family, + ila_nl_ops); + if (ret < 0) + goto unregister; + + return 0; + +unregister: + unregister_pernet_device(&ila_net_ops); +exit: + return ret; +} + +void ila_xlat_fini(void) +{ + genl_unregister_family(&ila_nl_family); + unregister_pernet_device(&ila_net_ops); +} diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index a7ca2cde2..36c3f0155 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -51,12 +51,12 @@ int inet6_csk_bind_conflict(const struct sock *sk, (sk2->sk_state != TCP_TIME_WAIT && !uid_eq(uid, sock_i_uid((struct sock *)sk2))))) { - if (ipv6_rcv_saddr_equal(sk, sk2)) + if (ipv6_rcv_saddr_equal(sk, sk2, true)) break; } if (!relax && reuse && sk2->sk_reuse && sk2->sk_state != TCP_LISTEN && - ipv6_rcv_saddr_equal(sk, sk2)) + ipv6_rcv_saddr_equal(sk, sk2, true)) break; } } diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index e5ea177d3..c0d4dc1c5 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -24,7 +24,6 @@ #include <linux/tcp.h> #include <linux/udp.h> #include <linux/if_arp.h> -#include <linux/mroute.h> #include <linux/init.h> #include <linux/in6.h> #include <linux/inetdevice.h> @@ -778,6 +777,8 @@ static inline int ip6gre_xmit_ipv4(struct sk_buff *skb, struct net_device *dev) __u32 mtu; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + if (!(t->parms.flags & IP6_TNL_F_IGN_ENCAP_LIMIT)) encap_limit = t->parms.encap_limit; @@ -1513,6 +1514,7 @@ static void ip6gre_tap_setup(struct net_device *dev) dev->destructor = ip6gre_dev_free; dev->features |= NETIF_F_NETNS_LOCAL; + dev->priv_flags &= ~IFF_TX_SKB_SHARING; } static int ip6gre_newlink(struct net *src_net, struct net_device *dev, diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 31144c486..a163102f1 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -1326,7 +1326,7 @@ emsgsize: headersize == sizeof(struct ipv6hdr) && length < mtu - headersize && !(flags & MSG_MORE) && - rt->dst.dev->features & NETIF_F_V6_CSUM) + rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; if (sk->sk_type == SOCK_DGRAM || sk->sk_type == SOCK_RAW) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index 137fca42a..6c5dfec7a 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -1180,6 +1180,8 @@ ip4ip6_tnl_xmit(struct sk_buff *skb, struct net_device *dev) u8 tproto; int err; + memset(&(IPCB(skb)->opt), 0, sizeof(IPCB(skb)->opt)); + tproto = ACCESS_ONCE(t->parms.proto); if (tproto != IPPROTO_IPIP && tproto != 0) return -1; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index 5ee56d0a8..d64ee7e83 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -1574,9 +1574,8 @@ static struct sk_buff *mld_newpack(struct inet6_dev *idev, unsigned int mtu) return NULL; skb->priority = TC_PRIO_CONTROL; - skb->reserved_tailroom = skb_end_offset(skb) - - min(mtu, skb_end_offset(skb)); skb_reserve(skb, hlen); + skb_tailroom_reserve(skb, mtu, tlen); if (__ipv6_get_lladdr(idev, &addr_buf, IFA_F_TENTATIVE)) { /* <draft-ietf-magma-mld-source-05.txt>: diff --git a/net/ipv6/netfilter/nf_conntrack_reasm.c b/net/ipv6/netfilter/nf_conntrack_reasm.c index bab4441ed..e4347aeb2 100644 --- a/net/ipv6/netfilter/nf_conntrack_reasm.c +++ b/net/ipv6/netfilter/nf_conntrack_reasm.c @@ -56,7 +56,6 @@ struct nf_ct_frag6_skb_cb { struct inet6_skb_parm h; int offset; - struct sk_buff *orig; }; #define NFCT_FRAG6_CB(skb) ((struct nf_ct_frag6_skb_cb *)((skb)->cb)) @@ -170,12 +169,6 @@ static unsigned int nf_hashfn(const struct inet_frag_queue *q) return nf_hash_frag(nq->id, &nq->saddr, &nq->daddr); } -static void nf_skb_free(struct sk_buff *skb) -{ - if (NFCT_FRAG6_CB(skb)->orig) - kfree_skb(NFCT_FRAG6_CB(skb)->orig); -} - static void nf_ct_frag6_expire(unsigned long data) { struct frag_queue *fq; @@ -369,17 +362,18 @@ err: /* * Check if this packet is complete. - * Returns NULL on failure by any reason, and pointer - * to current nexthdr field in reassembled frame. * * It is called with locked fq, and caller must check that * queue is eligible for reassembly i.e. it is not COMPLETE, * the last and the first frames arrived and all the bits are here. + * + * returns true if *prev skb has been transformed into the reassembled + * skb, false otherwise. */ -static struct sk_buff * -nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) +static bool +nf_ct_frag6_reasm(struct frag_queue *fq, struct sk_buff *prev, struct net_device *dev) { - struct sk_buff *fp, *op, *head = fq->q.fragments; + struct sk_buff *fp, *head = fq->q.fragments; int payload_len; u8 ecn; @@ -390,22 +384,21 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) ecn = ip_frag_ecn_table[fq->ecn]; if (unlikely(ecn == 0xff)) - goto out_fail; + return false; /* Unfragmented part is taken from the first segment. */ payload_len = ((head->data - skb_network_header(head)) - sizeof(struct ipv6hdr) + fq->q.len - sizeof(struct frag_hdr)); if (payload_len > IPV6_MAXPLEN) { - pr_debug("payload len is too large.\n"); - goto out_oversize; + net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", + payload_len); + return false; } /* Head of list must not be cloned. */ - if (skb_unclone(head, GFP_ATOMIC)) { - pr_debug("skb is cloned but can't expand head"); - goto out_oom; - } + if (skb_unclone(head, GFP_ATOMIC)) + return false; /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part @@ -416,7 +409,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone = alloc_skb(0, GFP_ATOMIC); if (clone == NULL) - goto out_oom; + return false; clone->next = head->next; head->next = clone; @@ -430,10 +423,41 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) clone->csum = 0; clone->ip_summed = head->ip_summed; - NFCT_FRAG6_CB(clone)->orig = NULL; add_frag_mem_limit(fq->q.net, clone->truesize); } + /* morph head into last received skb: prev. + * + * This allows callers of ipv6 conntrack defrag to continue + * to use the last skb(frag) passed into the reasm engine. + * The last skb frag 'silently' turns into the full reassembled skb. + * + * Since prev is also part of q->fragments we have to clone it first. + */ + if (head != prev) { + struct sk_buff *iter; + + fp = skb_clone(prev, GFP_ATOMIC); + if (!fp) + return false; + + fp->next = prev->next; + + iter = head; + while (iter) { + if (iter->next == prev) { + iter->next = fp; + break; + } + iter = iter->next; + } + + skb_morph(prev, head); + prev->next = head->next; + consume_skb(head); + head = prev; + } + /* We have to remove fragment header from datagram and to relocate * header in order to calculate ICV correctly. */ skb_network_header(head)[fq->nhoffset] = skb_transport_header(head)[0]; @@ -474,31 +498,7 @@ nf_ct_frag6_reasm(struct frag_queue *fq, struct net_device *dev) fq->q.fragments = NULL; fq->q.fragments_tail = NULL; - /* all original skbs are linked into the NFCT_FRAG6_CB(head).orig */ - fp = skb_shinfo(head)->frag_list; - if (fp && NFCT_FRAG6_CB(fp)->orig == NULL) - /* at above code, head skb is divided into two skbs. */ - fp = fp->next; - - op = NFCT_FRAG6_CB(head)->orig; - for (; fp; fp = fp->next) { - struct sk_buff *orig = NFCT_FRAG6_CB(fp)->orig; - - op->next = orig; - op = orig; - NFCT_FRAG6_CB(fp)->orig = NULL; - } - - return head; - -out_oversize: - net_dbg_ratelimited("nf_ct_frag6_reasm: payload len = %d\n", - payload_len); - goto out_fail; -out_oom: - net_dbg_ratelimited("nf_ct_frag6_reasm: no memory for reassembly\n"); -out_fail: - return NULL; + return true; } /* @@ -564,89 +564,61 @@ find_prev_fhdr(struct sk_buff *skb, u8 *prevhdrp, int *prevhoff, int *fhoff) return 0; } -struct sk_buff *nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) +int nf_ct_frag6_gather(struct net *net, struct sk_buff *skb, u32 user) { - struct sk_buff *clone; struct net_device *dev = skb->dev; + int fhoff, nhoff, ret; struct frag_hdr *fhdr; struct frag_queue *fq; struct ipv6hdr *hdr; - int fhoff, nhoff; u8 prevhdr; - struct sk_buff *ret_skb = NULL; /* Jumbo payload inhibits frag. header */ if (ipv6_hdr(skb)->payload_len == 0) { pr_debug("payload len = 0\n"); - return skb; + return -EINVAL; } if (find_prev_fhdr(skb, &prevhdr, &nhoff, &fhoff) < 0) - return skb; + return -EINVAL; - clone = skb_clone(skb, GFP_ATOMIC); - if (clone == NULL) { - pr_debug("Can't clone skb\n"); - return skb; - } + if (!pskb_may_pull(skb, fhoff + sizeof(*fhdr))) + return -ENOMEM; - NFCT_FRAG6_CB(clone)->orig = skb; - - if (!pskb_may_pull(clone, fhoff + sizeof(*fhdr))) { - pr_debug("message is too short.\n"); - goto ret_orig; - } - - skb_set_transport_header(clone, fhoff); - hdr = ipv6_hdr(clone); - fhdr = (struct frag_hdr *)skb_transport_header(clone); + skb_set_transport_header(skb, fhoff); + hdr = ipv6_hdr(skb); + fhdr = (struct frag_hdr *)skb_transport_header(skb); fq = fq_find(net, fhdr->identification, user, &hdr->saddr, &hdr->daddr, skb->dev ? skb->dev->ifindex : 0, ip6_frag_ecn(hdr)); if (fq == NULL) { pr_debug("Can't find and can't create new queue\n"); - goto ret_orig; + return -ENOMEM; } spin_lock_bh(&fq->q.lock); - if (nf_ct_frag6_queue(fq, clone, fhdr, nhoff) < 0) { - spin_unlock_bh(&fq->q.lock); - pr_debug("Can't insert skb to queue\n"); - inet_frag_put(&fq->q, &nf_frags); - goto ret_orig; + if (nf_ct_frag6_queue(fq, skb, fhdr, nhoff) < 0) { + ret = -EINVAL; + goto out_unlock; } + /* after queue has assumed skb ownership, only 0 or -EINPROGRESS + * must be returned. + */ + ret = -EINPROGRESS; if (fq->q.flags == (INET_FRAG_FIRST_IN | INET_FRAG_LAST_IN) && - fq->q.meat == fq->q.len) { - ret_skb = nf_ct_frag6_reasm(fq, dev); - if (ret_skb == NULL) - pr_debug("Can't reassemble fragmented packets\n"); - } - spin_unlock_bh(&fq->q.lock); + fq->q.meat == fq->q.len && + nf_ct_frag6_reasm(fq, skb, dev)) + ret = 0; +out_unlock: + spin_unlock_bh(&fq->q.lock); inet_frag_put(&fq->q, &nf_frags); - return ret_skb; - -ret_orig: - kfree_skb(clone); - return skb; + return ret; } EXPORT_SYMBOL_GPL(nf_ct_frag6_gather); -void nf_ct_frag6_consume_orig(struct sk_buff *skb) -{ - struct sk_buff *s, *s2; - - for (s = NFCT_FRAG6_CB(skb)->orig; s;) { - s2 = s->next; - s->next = NULL; - consume_skb(s); - s = s2; - } -} -EXPORT_SYMBOL_GPL(nf_ct_frag6_consume_orig); - static int nf_ct_net_init(struct net *net) { int res; @@ -681,7 +653,6 @@ int nf_ct_frag6_init(void) nf_frags.hashfn = nf_hashfn; nf_frags.constructor = ip6_frag_init; nf_frags.destructor = NULL; - nf_frags.skb_free = nf_skb_free; nf_frags.qsize = sizeof(struct frag_queue); nf_frags.match = ip6_frag_match; nf_frags.frag_expire = nf_ct_frag6_expire; diff --git a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c index 4fdbed5eb..f7aab5ab9 100644 --- a/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c +++ b/net/ipv6/netfilter/nf_defrag_ipv6_hooks.c @@ -55,7 +55,7 @@ static unsigned int ipv6_defrag(void *priv, struct sk_buff *skb, const struct nf_hook_state *state) { - struct sk_buff *reasm; + int err; #if IS_ENABLED(CONFIG_NF_CONNTRACK) /* Previously seen (loopback)? */ @@ -63,23 +63,13 @@ static unsigned int ipv6_defrag(void *priv, return NF_ACCEPT; #endif - reasm = nf_ct_frag6_gather(state->net, skb, - nf_ct6_defrag_user(state->hook, skb)); + err = nf_ct_frag6_gather(state->net, skb, + nf_ct6_defrag_user(state->hook, skb)); /* queued */ - if (reasm == NULL) + if (err == -EINPROGRESS) return NF_STOLEN; - /* error occurred or not fragmented */ - if (reasm == skb) - return NF_ACCEPT; - - nf_ct_frag6_consume_orig(reasm); - - NF_HOOK_THRESH(NFPROTO_IPV6, state->hook, state->net, state->sk, reasm, - state->in, state->out, - state->okfn, NF_IP6_PRI_CONNTRACK_DEFRAG + 1); - - return NF_STOLEN; + return NF_ACCEPT; } static struct nf_hook_ops ipv6_defrag_ops[] = { diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 238e70c3f..6ce309928 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -136,7 +136,8 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, if (skb->ip_summed != CHECKSUM_PARTIAL) { if (!(rt->rt6i_flags & RTF_LOCAL) && - (!skb->dev || skb->dev->features & NETIF_F_V6_CSUM)) { + (!skb->dev || skb->dev->features & + (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM))) { skb->ip_summed = CHECKSUM_PARTIAL; skb->csum_start = skb_headroom(skb) + skb_network_offset(skb) + diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 31ba7ca19..051b6a6bf 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -21,6 +21,10 @@ #include <net/ipv6.h> #include <net/netfilter/ipv6/nf_nat_masquerade.h> +#define MAX_WORK_COUNT 16 + +static atomic_t v6_worker_count; + unsigned int nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, const struct net_device *out) @@ -78,14 +82,78 @@ static struct notifier_block masq_dev_notifier = { .notifier_call = masq_device_event, }; +struct masq_dev_work { + struct work_struct work; + struct net *net; + int ifindex; +}; + +static void iterate_cleanup_work(struct work_struct *work) +{ + struct masq_dev_work *w; + long index; + + w = container_of(work, struct masq_dev_work, work); + + index = w->ifindex; + nf_ct_iterate_cleanup(w->net, device_cmp, (void *)index, 0, 0); + + put_net(w->net); + kfree(w); + atomic_dec(&v6_worker_count); + module_put(THIS_MODULE); +} + +/* ipv6 inet notifier is an atomic notifier, i.e. we cannot + * schedule. + * + * Unfortunately, nf_ct_iterate_cleanup can run for a long + * time if there are lots of conntracks and the system + * handles high softirq load, so it frequently calls cond_resched + * while iterating the conntrack table. + * + * So we defer nf_ct_iterate_cleanup walk to the system workqueue. + * + * As we can have 'a lot' of inet_events (depending on amount + * of ipv6 addresses being deleted), we also need to add an upper + * limit to the number of queued work items. + */ static int masq_inet_event(struct notifier_block *this, unsigned long event, void *ptr) { struct inet6_ifaddr *ifa = ptr; - struct netdev_notifier_info info; + const struct net_device *dev; + struct masq_dev_work *w; + struct net *net; + + if (event != NETDEV_DOWN || + atomic_read(&v6_worker_count) >= MAX_WORK_COUNT) + return NOTIFY_DONE; + + dev = ifa->idev->dev; + net = maybe_get_net(dev_net(dev)); + if (!net) + return NOTIFY_DONE; - netdev_notifier_info_init(&info, ifa->idev->dev); - return masq_device_event(this, event, &info); + if (!try_module_get(THIS_MODULE)) + goto err_module; + + w = kmalloc(sizeof(*w), GFP_ATOMIC); + if (w) { + atomic_inc(&v6_worker_count); + + INIT_WORK(&w->work, iterate_cleanup_work); + w->ifindex = dev->ifindex; + w->net = net; + schedule_work(&w->work); + + return NOTIFY_DONE; + } + + module_put(THIS_MODULE); + err_module: + put_net(net); + return NOTIFY_DONE; } static struct notifier_block masq_inet_notifier = { diff --git a/net/ipv6/netfilter/nf_reject_ipv6.c b/net/ipv6/netfilter/nf_reject_ipv6.c index e0f922b77..4709f657b 100644 --- a/net/ipv6/netfilter/nf_reject_ipv6.c +++ b/net/ipv6/netfilter/nf_reject_ipv6.c @@ -14,7 +14,6 @@ #include <net/netfilter/ipv6/nf_reject.h> #include <linux/netfilter_ipv6.h> #include <linux/netfilter_bridge.h> -#include <net/netfilter/ipv6/nf_reject.h> const struct tcphdr *nf_reject_ip6_tcphdr_get(struct sk_buff *oldskb, struct tcphdr *otcph, diff --git a/net/ipv6/netfilter/nf_tables_ipv6.c b/net/ipv6/netfilter/nf_tables_ipv6.c index 120ea9131..30b22f4df 100644 --- a/net/ipv6/netfilter/nf_tables_ipv6.c +++ b/net/ipv6/netfilter/nf_tables_ipv6.c @@ -77,7 +77,7 @@ err: static void nf_tables_ipv6_exit_net(struct net *net) { - nft_unregister_afinfo(net->nft.ipv6); + nft_unregister_afinfo(net, net->nft.ipv6); kfree(net->nft.ipv6); } diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 99140986e..fa59dd7a4 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -972,6 +972,11 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, return -EFAULT; switch (optname) { + case IPV6_HDRINCL: + if (sk->sk_type != SOCK_RAW) + return -EINVAL; + inet_sk(sk)->hdrincl = !!val; + return 0; case IPV6_CHECKSUM: if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { @@ -1016,7 +1021,8 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return ipv6_setsockopt(sk, level, optname, optval, optlen); @@ -1037,7 +1043,8 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return compat_ipv6_setsockopt(sk, level, optname, @@ -1057,6 +1064,9 @@ static int do_rawv6_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; switch (optname) { + case IPV6_HDRINCL: + val = inet_sk(sk)->hdrincl; + break; case IPV6_CHECKSUM: /* * We allow getsockopt() for IPPROTO_IPV6-level @@ -1094,7 +1104,8 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return ipv6_getsockopt(sk, level, optname, optval, optlen); @@ -1115,7 +1126,8 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: - if (optname == IPV6_CHECKSUM) + if (optname == IPV6_CHECKSUM || + optname == IPV6_HDRINCL) break; default: return compat_ipv6_getsockopt(sk, level, optname, diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 45f5ae51d..18f3498a6 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -755,7 +755,6 @@ int __init ipv6_frag_init(void) ip6_frags.hashfn = ip6_hashfn; ip6_frags.constructor = ip6_frag_init; ip6_frags.destructor = NULL; - ip6_frags.skb_free = NULL; ip6_frags.qsize = sizeof(struct frag_queue); ip6_frags.match = ip6_frag_match; ip6_frags.frag_expire = ip6_frag_expire; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 3f164d3aa..ed4466392 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -62,6 +62,7 @@ #include <net/lwtunnel.h> #include <net/ip_tunnels.h> #include <net/l3mdev.h> +#include <trace/events/fib6.h> #include <asm/uaccess.h> @@ -865,6 +866,9 @@ restart: } dst_use(&rt->dst, jiffies); read_unlock_bh(&table->tb6_lock); + + trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); + return rt; } @@ -1078,6 +1082,8 @@ redo_rt6_select: read_unlock_bh(&table->tb6_lock); rt6_dst_from_metrics_check(rt); + + trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && !(rt->rt6i_flags & RTF_GATEWAY))) { @@ -1101,6 +1107,8 @@ redo_rt6_select: uncached_rt = net->ipv6.ip6_null_entry; dst_hold(&uncached_rt->dst); + + trace_fib6_table_lookup(net, uncached_rt, table->tb6_id, fl6); return uncached_rt; } else { @@ -1125,6 +1133,7 @@ redo_rt6_select: dst_release(&rt->dst); } + trace_fib6_table_lookup(net, pcpu_rt, table->tb6_id, fl6); return pcpu_rt; } @@ -1473,6 +1482,7 @@ out: read_unlock_bh(&table->tb6_lock); + trace_fib6_table_lookup(net, rt, table->tb6_id, fl6); return rt; }; @@ -2698,6 +2708,7 @@ static const struct nla_policy rtm_ipv6_policy[RTA_MAX+1] = { [RTA_PREF] = { .type = NLA_U8 }, [RTA_ENCAP_TYPE] = { .type = NLA_U16 }, [RTA_ENCAP] = { .type = NLA_NESTED }, + [RTA_EXPIRES] = { .type = NLA_U32 }, }; static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, @@ -2798,6 +2809,15 @@ static int rtm_to_fib6_config(struct sk_buff *skb, struct nlmsghdr *nlh, if (tb[RTA_ENCAP_TYPE]) cfg->fc_encap_type = nla_get_u16(tb[RTA_ENCAP_TYPE]); + if (tb[RTA_EXPIRES]) { + unsigned long timeout = addrconf_timeout_fixup(nla_get_u32(tb[RTA_EXPIRES]), HZ); + + if (addrconf_finite_timeout(timeout)) { + cfg->fc_expires = jiffies_to_clock_t(timeout * HZ); + cfg->fc_flags |= RTF_EXPIRES; + } + } + err = 0; errout: return err; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index dcccae861..2066d1c25 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -201,14 +201,14 @@ static int ipip6_tunnel_create(struct net_device *dev) if ((__force u16)t->parms.i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; + dev->rtnl_link_ops = &sit_link_ops; + err = register_netdevice(dev); if (err < 0) goto out; ipip6_tunnel_clone_6rd(dev, sitn); - dev->rtnl_link_ops = &sit_link_ops; - dev_hold(dev); ipip6_tunnel_link(sitn, t); @@ -820,7 +820,6 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, const struct in6_addr *addr6; int addr_type; u8 ttl; - int err; u8 protocol = IPPROTO_IPV6; int t_hlen = tunnel->hlen + sizeof(struct iphdr); @@ -983,10 +982,8 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, skb_set_inner_ipproto(skb, IPPROTO_IPV6); - err = iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, - protocol, tos, ttl, df, - !net_eq(tunnel->net, dev_net(dev))); - iptunnel_xmit_stats(err, &dev->stats, dev->tstats); + iptunnel_xmit(NULL, rt, skb, fl4.saddr, fl4.daddr, protocol, tos, ttl, + df, !net_eq(tunnel->net, dev_net(dev))); return NETDEV_TX_OK; tx_error_icmp: diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index eaf7ac496..2906ef207 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -193,7 +193,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) ireq->pktopts = skb; } - ireq->ir_iif = sk->sk_bound_dev_if; + ireq->ir_iif = inet_request_bound_dev_if(sk, skb); /* So that link locals have meaning */ if (!sk->sk_bound_dev_if && ipv6_addr_type(&ireq->ir_v6_rmt_addr) & IPV6_ADDR_LINKLOCAL) @@ -224,7 +224,7 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) fl6.daddr = ireq->ir_v6_rmt_addr; final_p = fl6_update_dst(&fl6, rcu_dereference(np->opt), &final); fl6.saddr = ireq->ir_v6_loc_addr; - fl6.flowi6_oif = sk->sk_bound_dev_if; + fl6.flowi6_oif = ireq->ir_iif; fl6.flowi6_mark = ireq->ir_mark; fl6.fl6_dport = ireq->ir_rmt_port; fl6.fl6_sport = inet_sk(sk)->inet_sport; diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 7482504bd..62e167ec1 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -61,7 +61,6 @@ #include <net/timewait_sock.h> #include <net/inet_common.h> #include <net/secure_seq.h> -#include <net/tcp_memcontrol.h> #include <net/busy_poll.h> #include <net/secure_seq.h> @@ -873,7 +872,9 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) #ifdef CONFIG_TCP_MD5SIG hash_location = tcp_parse_md5sig_option(th); - if (!sk && hash_location) { + if (sk && sk_fullsock(sk)) { + key = tcp_v6_md5_do_lookup(sk, &ipv6h->saddr); + } else if (hash_location) { /* * active side is lost. Try to find listening socket through * source port, and then find md5 key through listening socket. @@ -896,8 +897,6 @@ static void tcp_v6_send_reset(const struct sock *sk, struct sk_buff *skb) genhash = tcp_v6_md5_hash_skb(newhash, key, NULL, skb); if (genhash || memcmp(hash_location, newhash, 16) != 0) goto release_sk1; - } else { - key = sk ? tcp_v6_md5_do_lookup(sk, &ipv6h->saddr) : NULL; } #endif @@ -1154,7 +1153,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * */ tcp_md5_do_add(newsk, (union tcp_md5_addr *)&newsk->sk_v6_daddr, AF_INET6, key->key, key->keylen, - sk_gfp_atomic(sk, GFP_ATOMIC)); + sk_gfp_mask(sk, GFP_ATOMIC)); } #endif @@ -1170,7 +1169,7 @@ static struct sock *tcp_v6_syn_recv_sock(const struct sock *sk, struct sk_buff * /* Clone pktoptions received with SYN, if we own the req */ if (ireq->pktopts) { newnp->pktoptions = skb_clone(ireq->pktopts, - sk_gfp_atomic(sk, GFP_ATOMIC)); + sk_gfp_mask(sk, GFP_ATOMIC)); consume_skb(ireq->pktopts); ireq->pktopts = NULL; if (newnp->pktoptions) @@ -1237,7 +1236,7 @@ static int tcp_v6_do_rcv(struct sock *sk, struct sk_buff *skb) --ANK (980728) */ if (np->rxopt.all) - opt_skb = skb_clone(skb, sk_gfp_atomic(sk, GFP_ATOMIC)); + opt_skb = skb_clone(skb, sk_gfp_mask(sk, GFP_ATOMIC)); if (sk->sk_state == TCP_ESTABLISHED) { /* Fast path */ struct dst_entry *dst = sk->sk_rx_dst; @@ -1543,7 +1542,9 @@ do_time_wait: break; case TCP_TW_RST: tcp_v6_restore_cb(skb); - goto no_tcp_socket; + tcp_v6_send_reset(sk, skb); + inet_twsk_deschedule_put(inet_twsk(sk)); + goto discard_it; case TCP_TW_SUCCESS: ; } @@ -1912,10 +1913,8 @@ struct proto tcpv6_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif -#ifdef CONFIG_MEMCG_KMEM - .proto_cgroup = tcp_proto_cgroup, -#endif .clear_sk = tcp_v6_clear_sk, + .diag_destroy = tcp_abort, }; static const struct inet6_protocol tcpv6_protocol = { diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index 9da3287a3..422dd014a 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -47,6 +47,7 @@ #include <net/xfrm.h> #include <net/inet6_hashtables.h> #include <net/busy_poll.h> +#include <net/sock_reuseport.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -76,7 +77,14 @@ static u32 udp6_ehashfn(const struct net *net, udp_ipv6_hash_secret + net_hash_mix(net)); } -int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) +/* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 + * only, and any IPv4 addresses if not IPv6 only + * match_wildcard == false: addresses must be exactly the same, i.e. + * IPV6_ADDR_ANY only equals to IPV6_ADDR_ANY, + * and 0.0.0.0 equals to 0.0.0.0 only + */ +int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2, + bool match_wildcard) { const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); int sk2_ipv6only = inet_v6_ipv6only(sk2); @@ -84,16 +92,24 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) int addr_type2 = sk2_rcv_saddr6 ? ipv6_addr_type(sk2_rcv_saddr6) : IPV6_ADDR_MAPPED; /* if both are mapped, treat as IPv4 */ - if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) - return (!sk2_ipv6only && - (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr || - sk->sk_rcv_saddr == sk2->sk_rcv_saddr)); + if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) { + if (!sk2_ipv6only) { + if (sk->sk_rcv_saddr == sk2->sk_rcv_saddr) + return 1; + if (!sk->sk_rcv_saddr || !sk2->sk_rcv_saddr) + return match_wildcard; + } + return 0; + } - if (addr_type2 == IPV6_ADDR_ANY && + if (addr_type == IPV6_ADDR_ANY && addr_type2 == IPV6_ADDR_ANY) + return 1; + + if (addr_type2 == IPV6_ADDR_ANY && match_wildcard && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) return 1; - if (addr_type == IPV6_ADDR_ANY && + if (addr_type == IPV6_ADDR_ANY && match_wildcard && !(ipv6_only_sock(sk) && addr_type2 == IPV6_ADDR_MAPPED)) return 1; @@ -235,11 +251,13 @@ static inline int compute_score2(struct sock *sk, struct net *net, static struct sock *udp6_lib_lookup2(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, unsigned int hnum, int dif, - struct udp_hslot *hslot2, unsigned int slot2) + struct udp_hslot *hslot2, unsigned int slot2, + struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; begin: @@ -255,6 +273,17 @@ begin: if (reuseport) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } + } matches = 1; } } else if (score == badness && reuseport) { @@ -273,6 +302,7 @@ begin: goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, @@ -287,7 +317,8 @@ begin: struct sock *__udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, - int dif, struct udp_table *udptable) + int dif, struct udp_table *udptable, + struct sk_buff *skb) { struct sock *sk, *result; struct hlist_nulls_node *node; @@ -295,6 +326,7 @@ struct sock *__udp6_lib_lookup(struct net *net, unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness, matches = 0, reuseport = 0; + bool select_ok = true; u32 hash = 0; rcu_read_lock(); @@ -307,7 +339,7 @@ struct sock *__udp6_lib_lookup(struct net *net, result = udp6_lib_lookup2(net, saddr, sport, daddr, hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); if (!result) { hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); slot2 = hash2 & udptable->mask; @@ -317,7 +349,7 @@ struct sock *__udp6_lib_lookup(struct net *net, result = udp6_lib_lookup2(net, saddr, sport, &in6addr_any, hnum, dif, - hslot2, slot2); + hslot2, slot2, skb); } rcu_read_unlock(); return result; @@ -334,6 +366,17 @@ begin: if (reuseport) { hash = udp6_ehashfn(net, daddr, hnum, saddr, sport); + if (select_ok) { + struct sock *sk2; + + sk2 = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + if (sk2) { + result = sk2; + select_ok = false; + goto found; + } + } matches = 1; } } else if (score == badness && reuseport) { @@ -352,6 +395,7 @@ begin: goto begin; if (result) { +found: if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score(result, net, hnum, saddr, sport, @@ -377,13 +421,13 @@ static struct sock *__udp6_lib_lookup_skb(struct sk_buff *skb, return sk; return __udp6_lib_lookup(dev_net(skb_dst(skb)->dev), &iph->saddr, sport, &iph->daddr, dport, inet6_iif(skb), - udptable); + udptable, skb); } struct sock *udp6_lib_lookup(struct net *net, const struct in6_addr *saddr, __be16 sport, const struct in6_addr *daddr, __be16 dport, int dif) { - return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); + return __udp6_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table, NULL); } EXPORT_SYMBOL_GPL(udp6_lib_lookup); @@ -402,6 +446,7 @@ int udpv6_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); + bool checksum_valid = false; int is_udp4; bool slow; @@ -433,11 +478,12 @@ try_again: */ if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + checksum_valid = !udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) + if (checksum_valid || skb_csum_unnecessary(skb)) err = skb_copy_datagram_msg(skb, sizeof(struct udphdr), msg, copied); else { @@ -547,8 +593,8 @@ void __udp6_lib_err(struct sk_buff *skb, struct inet6_skb_parm *opt, int err; struct net *net = dev_net(skb->dev); - sk = __udp6_lib_lookup(net, daddr, uh->dest, - saddr, uh->source, inet6_iif(skb), udptable); + sk = __udp6_lib_lookup(net, daddr, uh->dest, saddr, uh->source, + inet6_iif(skb), udptable, skb); if (!sk) { ICMP6_INC_STATS_BH(net, __in6_dev_get(skb->dev), ICMP6_MIB_INERRORS); @@ -916,11 +962,9 @@ int __udp6_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, ret = udpv6_queue_rcv_skb(sk, skb); sock_put(sk); - /* a return value > 0 means to resubmit the input, but - * it wants the return to be -protocol, or 0 - */ + /* a return value > 0 means to resubmit the input */ if (ret > 0) - return -ret; + return ret; return 0; } |