diff options
Diffstat (limited to 'net/ipv6')
35 files changed, 1346 insertions, 730 deletions
diff --git a/net/ipv6/Kconfig b/net/ipv6/Kconfig index ead6c7a42f44..a578096152ab 100644 --- a/net/ipv6/Kconfig +++ b/net/ipv6/Kconfig @@ -170,6 +170,25 @@ config IPV6_SIT Saying M here will produce a module called sit. If unsure, say Y. +config IPV6_SIT_6RD + bool "IPv6: IPv6 Rapid Deployment (6RD) (EXPERIMENTAL)" + depends on IPV6_SIT && EXPERIMENTAL + default n + ---help--- + IPv6 Rapid Deployment (6rd; draft-ietf-softwire-ipv6-6rd) builds upon + mechanisms of 6to4 (RFC3056) to enable a service provider to rapidly + deploy IPv6 unicast service to IPv4 sites to which it provides + customer premise equipment. Like 6to4, it utilizes stateless IPv6 in + IPv4 encapsulation in order to transit IPv4-only network + infrastructure. Unlike 6to4, a 6rd service provider uses an IPv6 + prefix of its own in place of the fixed 6to4 prefix. + + With this option enabled, the SIT driver offers 6rd functionality by + providing additional ioctl API to configure the IPv6 Prefix for in + stead of static 2002::/16 for 6to4. + + If unsure, say N. + config IPV6_NDISC_NODETYPE bool diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index f918399c985c..de7a194a64ab 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -481,9 +481,8 @@ static void addrconf_forward_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { - rcu_read_lock(); + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.forwarding) ^ (!newf); @@ -491,9 +490,8 @@ static void addrconf_forward_change(struct net *net, __s32 newf) if (changed) dev_forward_change(idev); } - rcu_read_unlock(); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int addrconf_fixup_forwarding(struct ctl_table *table, int *p, int old) @@ -1137,10 +1135,9 @@ int ipv6_dev_get_saddr(struct net *net, struct net_device *dst_dev, hiscore->rule = -1; hiscore->ifa = NULL; - read_lock(&dev_base_lock); rcu_read_lock(); - for_each_netdev(net, dev) { + for_each_netdev_rcu(net, dev) { struct inet6_dev *idev; /* Candidate Source Address (section 4) @@ -1235,7 +1232,6 @@ try_nextdev: read_unlock_bh(&idev->lock); } rcu_read_unlock(); - read_unlock(&dev_base_lock); if (!hiscore->ifa) return -EADDRNOTAVAIL; @@ -3485,85 +3481,114 @@ enum addr_type_t ANYCAST_ADDR, }; +/* called with rcu_read_lock() */ +static int in6_dump_addrs(struct inet6_dev *idev, struct sk_buff *skb, + struct netlink_callback *cb, enum addr_type_t type, + int s_ip_idx, int *p_ip_idx) +{ + struct inet6_ifaddr *ifa; + struct ifmcaddr6 *ifmca; + struct ifacaddr6 *ifaca; + int err = 1; + int ip_idx = *p_ip_idx; + + read_lock_bh(&idev->lock); + switch (type) { + case UNICAST_ADDR: + /* unicast address incl. temp addr */ + for (ifa = idev->addr_list; ifa; + ifa = ifa->if_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifaddr(skb, ifa, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWADDR, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + case MULTICAST_ADDR: + /* multicast address */ + for (ifmca = idev->mc_list; ifmca; + ifmca = ifmca->next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifmcaddr(skb, ifmca, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_GETMULTICAST, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + case ANYCAST_ADDR: + /* anycast address */ + for (ifaca = idev->ac_list; ifaca; + ifaca = ifaca->aca_next, ip_idx++) { + if (ip_idx < s_ip_idx) + continue; + err = inet6_fill_ifacaddr(skb, ifaca, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_GETANYCAST, + NLM_F_MULTI); + if (err <= 0) + break; + } + break; + default: + break; + } + read_unlock_bh(&idev->lock); + *p_ip_idx = ip_idx; + return err; +} + static int inet6_dump_addr(struct sk_buff *skb, struct netlink_callback *cb, enum addr_type_t type) { + struct net *net = sock_net(skb->sk); + int h, s_h; int idx, ip_idx; int s_idx, s_ip_idx; - int err = 1; struct net_device *dev; - struct inet6_dev *idev = NULL; - struct inet6_ifaddr *ifa; - struct ifmcaddr6 *ifmca; - struct ifacaddr6 *ifaca; - struct net *net = sock_net(skb->sk); - - s_idx = cb->args[0]; - s_ip_idx = ip_idx = cb->args[1]; + struct inet6_dev *idev; + struct hlist_head *head; + struct hlist_node *node; - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if (idx > s_idx) - s_ip_idx = 0; - ip_idx = 0; - if ((idev = in6_dev_get(dev)) == NULL) - goto cont; - read_lock_bh(&idev->lock); - switch (type) { - case UNICAST_ADDR: - /* unicast address incl. temp addr */ - for (ifa = idev->addr_list; ifa; - ifa = ifa->if_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - err = inet6_fill_ifaddr(skb, ifa, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_NEWADDR, - NLM_F_MULTI); - } - break; - case MULTICAST_ADDR: - /* multicast address */ - for (ifmca = idev->mc_list; ifmca; - ifmca = ifmca->next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - err = inet6_fill_ifmcaddr(skb, ifmca, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_GETMULTICAST, - NLM_F_MULTI); - } - break; - case ANYCAST_ADDR: - /* anycast address */ - for (ifaca = idev->ac_list; ifaca; - ifaca = ifaca->aca_next, ip_idx++) { - if (ip_idx < s_ip_idx) - continue; - err = inet6_fill_ifacaddr(skb, ifaca, - NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, - RTM_GETANYCAST, - NLM_F_MULTI); - } - break; - default: - break; - } - read_unlock_bh(&idev->lock); - in6_dev_put(idev); + s_h = cb->args[0]; + s_idx = idx = cb->args[1]; + s_ip_idx = ip_idx = cb->args[2]; - if (err <= 0) - break; + rcu_read_lock(); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + if (idx > s_idx) + s_ip_idx = 0; + ip_idx = 0; + if ((idev = __in6_dev_get(dev)) == NULL) + goto cont; + + if (in6_dump_addrs(idev, skb, cb, type, + s_ip_idx, &ip_idx) <= 0) + goto done; cont: - idx++; + idx++; + } } - cb->args[0] = idx; - cb->args[1] = ip_idx; +done: + rcu_read_unlock(); + cb->args[0] = h; + cb->args[1] = idx; + cb->args[2] = ip_idx; + return skb->len; } @@ -3708,6 +3733,7 @@ static inline void ipv6_store_devconf(struct ipv6_devconf *cnf, #endif array[DEVCONF_DISABLE_IPV6] = cnf->disable_ipv6; array[DEVCONF_ACCEPT_DAD] = cnf->accept_dad; + array[DEVCONF_FORCE_TLLAO] = cnf->force_tllao; } static inline size_t inet6_if_nlmsg_size(void) @@ -3826,28 +3852,39 @@ nla_put_failure: static int inet6_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); - int idx, err; - int s_idx = cb->args[0]; + int h, s_h; + int idx = 0, s_idx; struct net_device *dev; struct inet6_dev *idev; + struct hlist_head *head; + struct hlist_node *node; - read_lock(&dev_base_lock); - idx = 0; - for_each_netdev(net, dev) { - if (idx < s_idx) - goto cont; - if ((idev = in6_dev_get(dev)) == NULL) - goto cont; - err = inet6_fill_ifinfo(skb, idev, NETLINK_CB(cb->skb).pid, - cb->nlh->nlmsg_seq, RTM_NEWLINK, NLM_F_MULTI); - in6_dev_put(idev); - if (err <= 0) - break; + s_h = cb->args[0]; + s_idx = cb->args[1]; + + rcu_read_lock(); + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { + idx = 0; + head = &net->dev_index_head[h]; + hlist_for_each_entry_rcu(dev, node, head, index_hlist) { + if (idx < s_idx) + goto cont; + idev = __in6_dev_get(dev); + if (!idev) + goto cont; + if (inet6_fill_ifinfo(skb, idev, + NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, + RTM_NEWLINK, NLM_F_MULTI) <= 0) + goto out; cont: - idx++; + idx++; + } } - read_unlock(&dev_base_lock); - cb->args[0] = idx; +out: + rcu_read_unlock(); + cb->args[1] = idx; + cb->args[0] = h; return skb->len; } @@ -4016,9 +4053,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) struct net_device *dev; struct inet6_dev *idev; - read_lock(&dev_base_lock); - for_each_netdev(net, dev) { - rcu_read_lock(); + rcu_read_lock(); + for_each_netdev_rcu(net, dev) { idev = __in6_dev_get(dev); if (idev) { int changed = (!idev->cnf.disable_ipv6) ^ (!newf); @@ -4026,9 +4062,8 @@ static void addrconf_disable_change(struct net *net, __s32 newf) if (changed) dev_disable_change(idev); } - rcu_read_unlock(); } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int addrconf_disable_ipv6(struct ctl_table *table, int *p, int old) @@ -4285,6 +4320,13 @@ static struct addrconf_sysctl_table .proc_handler = proc_dointvec, }, { + .procname = "force_tllao", + .data = &ipv6_devconf.force_tllao, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, + { /* sentinel */ } }, @@ -4385,7 +4427,7 @@ static int addrconf_init_net(struct net *net) all = &ipv6_devconf; dflt = &ipv6_devconf_dflt; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { all = kmemdup(all, sizeof(ipv6_devconf), GFP_KERNEL); if (all == NULL) goto err_alloc_all; @@ -4431,7 +4473,7 @@ static void addrconf_exit_net(struct net *net) __addrconf_sysctl_unregister(net->ipv6.devconf_dflt); __addrconf_sysctl_unregister(net->ipv6.devconf_all); #endif - if (net != &init_net) { + if (!net_eq(net, &init_net)) { kfree(net->ipv6.devconf_dflt); kfree(net->ipv6.devconf_all); } diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index e127a32f9540..12e69d364dd5 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -95,7 +95,8 @@ static __inline__ struct ipv6_pinfo *inet6_sk_generic(struct sock *sk) return (struct ipv6_pinfo *)(((u8 *)sk) + offset); } -static int inet6_create(struct net *net, struct socket *sock, int protocol) +static int inet6_create(struct net *net, struct socket *sock, int protocol, + int kern) { struct inet_sock *inet; struct ipv6_pinfo *np; @@ -158,7 +159,7 @@ lookup_protocol: } err = -EPERM; - if (answer->capability > 0 && !capable(answer->capability)) + if (sock->type == SOCK_RAW && !kern && !capable(CAP_NET_RAW)) goto out_rcu_unlock; sock->ops = answer->ops; @@ -185,7 +186,7 @@ lookup_protocol: inet->is_icsk = (INET_PROTOSW_ICSK & answer_flags) != 0; if (SOCK_RAW == sock->type) { - inet->num = protocol; + inet->inet_num = protocol; if (IPPROTO_RAW == protocol) inet->hdrincl = 1; } @@ -228,12 +229,12 @@ lookup_protocol: */ sk_refcnt_debug_inc(sk); - if (inet->num) { + if (inet->inet_num) { /* It assumes that any protocol which allows * the user to assign a number at socket * creation time automatically shares. */ - inet->sport = htons(inet->num); + inet->inet_sport = htons(inet->inet_num); sk->sk_prot->hash(sk); } if (sk->sk_prot->init) { @@ -281,7 +282,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) lock_sock(sk); /* Check these errors (active socket, double bind). */ - if (sk->sk_state != TCP_CLOSE || inet->num) { + if (sk->sk_state != TCP_CLOSE || inet->inet_num) { err = -EINVAL; goto out; } @@ -314,6 +315,7 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; + rcu_read_lock(); if (addr_type & IPV6_ADDR_LINKLOCAL) { if (addr_len >= sizeof(struct sockaddr_in6) && addr->sin6_scope_id) { @@ -326,12 +328,12 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) { err = -EINVAL; - goto out; + goto out_unlock; } - dev = dev_get_by_index(net, sk->sk_bound_dev_if); + dev = dev_get_by_index_rcu(net, sk->sk_bound_dev_if); if (!dev) { err = -ENODEV; - goto out; + goto out_unlock; } } @@ -342,19 +344,16 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) if (!(addr_type & IPV6_ADDR_MULTICAST)) { if (!ipv6_chk_addr(net, &addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); err = -EADDRNOTAVAIL; - goto out; + goto out_unlock; } } - if (dev) - dev_put(dev); + rcu_read_unlock(); } } - inet->rcv_saddr = v4addr; - inet->saddr = v4addr; + inet->inet_rcv_saddr = v4addr; + inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); @@ -375,12 +374,15 @@ int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) } if (snum) sk->sk_userlocks |= SOCK_BINDPORT_LOCK; - inet->sport = htons(inet->num); - inet->dport = 0; - inet->daddr = 0; + inet->inet_sport = htons(inet->inet_num); + inet->inet_dport = 0; + inet->inet_daddr = 0; out: release_sock(sk); return err; +out_unlock: + rcu_read_unlock(); + goto out; } EXPORT_SYMBOL(inet6_bind); @@ -441,12 +443,12 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, sin->sin6_flowinfo = 0; sin->sin6_scope_id = 0; if (peer) { - if (!inet->dport) + if (!inet->inet_dport) return -ENOTCONN; if (((1 << sk->sk_state) & (TCPF_CLOSE | TCPF_SYN_SENT)) && peer == 1) return -ENOTCONN; - sin->sin6_port = inet->dport; + sin->sin6_port = inet->inet_dport; ipv6_addr_copy(&sin->sin6_addr, &np->daddr); if (np->sndflow) sin->sin6_flowinfo = np->flow_label; @@ -456,7 +458,7 @@ int inet6_getname(struct socket *sock, struct sockaddr *uaddr, else ipv6_addr_copy(&sin->sin6_addr, &np->rcv_saddr); - sin->sin6_port = inet->sport; + sin->sin6_port = inet->inet_sport; } if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = sk->sk_bound_dev_if; @@ -552,7 +554,7 @@ const struct proto_ops inet6_dgram_ops = { #endif }; -static struct net_proto_family inet6_family_ops = { +static const struct net_proto_family inet6_family_ops = { .family = PF_INET6, .create = inet6_create, .owner = THIS_MODULE, @@ -654,8 +656,9 @@ int inet6_sk_rebuild_header(struct sock *sk) ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.fl6_flowlabel = np->flow_label; fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { diff --git a/net/ipv6/ah6.c b/net/ipv6/ah6.c index c1589e2f1dc9..c2f300c314be 100644 --- a/net/ipv6/ah6.c +++ b/net/ipv6/ah6.c @@ -24,18 +24,92 @@ * This file is derived from net/ipv4/ah.c. */ +#include <crypto/hash.h> #include <linux/module.h> #include <net/ip.h> #include <net/ah.h> #include <linux/crypto.h> #include <linux/pfkeyv2.h> -#include <linux/spinlock.h> #include <linux/string.h> +#include <linux/scatterlist.h> #include <net/icmp.h> #include <net/ipv6.h> #include <net/protocol.h> #include <net/xfrm.h> +#define IPV6HDR_BASELEN 8 + +struct tmp_ext { +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) + struct in6_addr saddr; +#endif + struct in6_addr daddr; + char hdrs[0]; +}; + +struct ah_skb_cb { + struct xfrm_skb_cb xfrm; + void *tmp; +}; + +#define AH_SKB_CB(__skb) ((struct ah_skb_cb *)&((__skb)->cb[0])) + +static void *ah_alloc_tmp(struct crypto_ahash *ahash, int nfrags, + unsigned int size) +{ + unsigned int len; + + len = size + crypto_ahash_digestsize(ahash) + + (crypto_ahash_alignmask(ahash) & + ~(crypto_tfm_ctx_alignment() - 1)); + + len = ALIGN(len, crypto_tfm_ctx_alignment()); + + len += sizeof(struct ahash_request) + crypto_ahash_reqsize(ahash); + len = ALIGN(len, __alignof__(struct scatterlist)); + + len += sizeof(struct scatterlist) * nfrags; + + return kmalloc(len, GFP_ATOMIC); +} + +static inline struct tmp_ext *ah_tmp_ext(void *base) +{ + return base + IPV6HDR_BASELEN; +} + +static inline u8 *ah_tmp_auth(u8 *tmp, unsigned int offset) +{ + return tmp + offset; +} + +static inline u8 *ah_tmp_icv(struct crypto_ahash *ahash, void *tmp, + unsigned int offset) +{ + return PTR_ALIGN((u8 *)tmp + offset, crypto_ahash_alignmask(ahash) + 1); +} + +static inline struct ahash_request *ah_tmp_req(struct crypto_ahash *ahash, + u8 *icv) +{ + struct ahash_request *req; + + req = (void *)PTR_ALIGN(icv + crypto_ahash_digestsize(ahash), + crypto_tfm_ctx_alignment()); + + ahash_request_set_tfm(req, ahash); + + return req; +} + +static inline struct scatterlist *ah_req_sg(struct crypto_ahash *ahash, + struct ahash_request *req) +{ + return (void *)ALIGN((unsigned long)(req + 1) + + crypto_ahash_reqsize(ahash), + __alignof__(struct scatterlist)); +} + static int zero_out_mutable_opts(struct ipv6_opt_hdr *opthdr) { u8 *opt = (u8 *)opthdr; @@ -218,24 +292,85 @@ static int ipv6_clear_mutable_options(struct ipv6hdr *iph, int len, int dir) return 0; } +static void ah6_output_done(struct crypto_async_request *base, int err) +{ + int extlen; + u8 *iph_base; + u8 *icv; + struct sk_buff *skb = base->data; + struct xfrm_state *x = skb_dst(skb)->xfrm; + struct ah_data *ahp = x->data; + struct ipv6hdr *top_iph = ipv6_hdr(skb); + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + struct tmp_ext *iph_ext; + + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + iph_base = AH_SKB_CB(skb)->tmp; + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahp->ahash, iph_ext, extlen); + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { +#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) + memcpy(&top_iph->saddr, iph_ext, extlen); +#else + memcpy(&top_iph->daddr, iph_ext, extlen); +#endif + } + + err = ah->nexthdr; + + kfree(AH_SKB_CB(skb)->tmp); + xfrm_output_resume(skb, err); +} + static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) { int err; + int nfrags; int extlen; + u8 *iph_base; + u8 *icv; + u8 nexthdr; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ipv6hdr *top_iph; struct ip_auth_hdr *ah; struct ah_data *ahp; - u8 nexthdr; - char tmp_base[8]; - struct { -#if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - struct in6_addr saddr; -#endif - struct in6_addr daddr; - char hdrs[0]; - } *tmp_ext; + struct tmp_ext *iph_ext; + + ahp = x->data; + ahash = ahp->ahash; + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; skb_push(skb, -skb_network_offset(skb)); + extlen = skb_network_header_len(skb) - sizeof(struct ipv6hdr); + if (extlen) + extlen += sizeof(*iph_ext); + + err = -ENOMEM; + iph_base = ah_alloc_tmp(ahash, nfrags, IPV6HDR_BASELEN + extlen); + if (!iph_base) + goto out; + + iph_ext = ah_tmp_ext(iph_base); + icv = ah_tmp_icv(ahash, iph_ext, extlen); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + ah = ip_auth_hdr(skb); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + top_iph = ipv6_hdr(skb); top_iph->payload_len = htons(skb->len - sizeof(*top_iph)); @@ -245,31 +380,22 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) /* When there are no extension headers, we only need to save the first * 8 bytes of the base IP header. */ - memcpy(tmp_base, top_iph, sizeof(tmp_base)); + memcpy(iph_base, top_iph, IPV6HDR_BASELEN); - tmp_ext = NULL; - extlen = skb_transport_offset(skb) - sizeof(struct ipv6hdr); if (extlen) { - extlen += sizeof(*tmp_ext); - tmp_ext = kmalloc(extlen, GFP_ATOMIC); - if (!tmp_ext) { - err = -ENOMEM; - goto error; - } #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - memcpy(tmp_ext, &top_iph->saddr, extlen); + memcpy(iph_ext, &top_iph->saddr, extlen); #else - memcpy(tmp_ext, &top_iph->daddr, extlen); + memcpy(iph_ext, &top_iph->daddr, extlen); #endif err = ipv6_clear_mutable_options(top_iph, - extlen - sizeof(*tmp_ext) + + extlen - sizeof(*iph_ext) + sizeof(*top_iph), XFRM_POLICY_OUT); if (err) - goto error_free_iph; + goto out_free; } - ah = ip_auth_hdr(skb); ah->nexthdr = nexthdr; top_iph->priority = 0; @@ -278,36 +404,80 @@ static int ah6_output(struct xfrm_state *x, struct sk_buff *skb) top_iph->flow_lbl[2] = 0; top_iph->hop_limit = 0; - ahp = x->data; ah->hdrlen = (XFRM_ALIGN8(sizeof(*ah) + ahp->icv_trunc_len) >> 2) - 2; ah->reserved = 0; ah->spi = x->id.spi; ah->seq_no = htonl(XFRM_SKB_CB(skb)->seq.output); - spin_lock_bh(&x->lock); - err = ah_mac_digest(ahp, skb, ah->auth_data); - memcpy(ah->auth_data, ahp->work_icv, ahp->icv_trunc_len); - spin_unlock_bh(&x->lock); + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - if (err) - goto error_free_iph; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah6_output_done, skb); + + AH_SKB_CB(skb)->tmp = iph_base; - memcpy(top_iph, tmp_base, sizeof(tmp_base)); - if (tmp_ext) { + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; + } + + memcpy(ah->auth_data, icv, ahp->icv_trunc_len); + memcpy(top_iph, iph_base, IPV6HDR_BASELEN); + + if (extlen) { #if defined(CONFIG_IPV6_MIP6) || defined(CONFIG_IPV6_MIP6_MODULE) - memcpy(&top_iph->saddr, tmp_ext, extlen); + memcpy(&top_iph->saddr, iph_ext, extlen); #else - memcpy(&top_iph->daddr, tmp_ext, extlen); + memcpy(&top_iph->daddr, iph_ext, extlen); #endif -error_free_iph: - kfree(tmp_ext); } -error: +out_free: + kfree(iph_base); +out: return err; } +static void ah6_input_done(struct crypto_async_request *base, int err) +{ + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *skb = base->data; + struct xfrm_state *x = xfrm_input_state(skb); + struct ah_data *ahp = x->data; + struct ip_auth_hdr *ah = ip_auth_hdr(skb); + int hdr_len = skb_network_header_len(skb); + int ah_hlen = (ah->hdrlen + 2) << 2; + + work_iph = AH_SKB_CB(skb)->tmp; + auth_data = ah_tmp_auth(work_iph, hdr_len); + icv = ah_tmp_icv(ahp->ahash, auth_data, ahp->icv_trunc_len); + + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; + if (err) + goto out; + + skb->network_header += ah_hlen; + memcpy(skb_network_header(skb), work_iph, hdr_len); + __skb_pull(skb, ah_hlen + hdr_len); + skb_set_transport_header(skb, -hdr_len); + + err = ah->nexthdr; +out: + kfree(AH_SKB_CB(skb)->tmp); + xfrm_input_resume(skb, err); +} + + + static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) { /* @@ -325,14 +495,21 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) * There is offset of AH before IPv6 header after the process. */ + u8 *auth_data; + u8 *icv; + u8 *work_iph; + struct sk_buff *trailer; + struct crypto_ahash *ahash; + struct ahash_request *req; + struct scatterlist *sg; struct ip_auth_hdr *ah; struct ipv6hdr *ip6h; struct ah_data *ahp; - unsigned char *tmp_hdr = NULL; u16 hdr_len; u16 ah_hlen; int nexthdr; - int err = -EINVAL; + int nfrags; + int err = -ENOMEM; if (!pskb_may_pull(skb, sizeof(struct ip_auth_hdr))) goto out; @@ -345,9 +522,11 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) skb->ip_summed = CHECKSUM_NONE; - hdr_len = skb->data - skb_network_header(skb); + hdr_len = skb_network_header_len(skb); ah = (struct ip_auth_hdr *)skb->data; ahp = x->data; + ahash = ahp->ahash; + nexthdr = ah->nexthdr; ah_hlen = (ah->hdrlen + 2) << 2; @@ -358,48 +537,67 @@ static int ah6_input(struct xfrm_state *x, struct sk_buff *skb) if (!pskb_may_pull(skb, ah_hlen)) goto out; - tmp_hdr = kmemdup(skb_network_header(skb), hdr_len, GFP_ATOMIC); - if (!tmp_hdr) - goto out; ip6h = ipv6_hdr(skb); + + skb_push(skb, hdr_len); + + if ((err = skb_cow_data(skb, 0, &trailer)) < 0) + goto out; + nfrags = err; + + work_iph = ah_alloc_tmp(ahash, nfrags, hdr_len + ahp->icv_trunc_len); + if (!work_iph) + goto out; + + auth_data = ah_tmp_auth(work_iph, hdr_len); + icv = ah_tmp_icv(ahash, auth_data, ahp->icv_trunc_len); + req = ah_tmp_req(ahash, icv); + sg = ah_req_sg(ahash, req); + + memcpy(work_iph, ip6h, hdr_len); + memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); + memset(ah->auth_data, 0, ahp->icv_trunc_len); + if (ipv6_clear_mutable_options(ip6h, hdr_len, XFRM_POLICY_IN)) - goto free_out; + goto out_free; + ip6h->priority = 0; ip6h->flow_lbl[0] = 0; ip6h->flow_lbl[1] = 0; ip6h->flow_lbl[2] = 0; ip6h->hop_limit = 0; - spin_lock(&x->lock); - { - u8 auth_data[MAX_AH_AUTH_LEN]; + sg_init_table(sg, nfrags); + skb_to_sgvec(skb, sg, 0, skb->len); - memcpy(auth_data, ah->auth_data, ahp->icv_trunc_len); - memset(ah->auth_data, 0, ahp->icv_trunc_len); - skb_push(skb, hdr_len); - err = ah_mac_digest(ahp, skb, ah->auth_data); - if (err) - goto unlock; - if (memcmp(ahp->work_icv, auth_data, ahp->icv_trunc_len)) - err = -EBADMSG; + ahash_request_set_crypt(req, sg, icv, skb->len); + ahash_request_set_callback(req, 0, ah6_input_done, skb); + + AH_SKB_CB(skb)->tmp = work_iph; + + err = crypto_ahash_digest(req); + if (err) { + if (err == -EINPROGRESS) + goto out; + + if (err == -EBUSY) + err = NET_XMIT_DROP; + goto out_free; } -unlock: - spin_unlock(&x->lock); + err = memcmp(icv, auth_data, ahp->icv_trunc_len) ? -EBADMSG: 0; if (err) - goto free_out; + goto out_free; skb->network_header += ah_hlen; - memcpy(skb_network_header(skb), tmp_hdr, hdr_len); + memcpy(skb_network_header(skb), work_iph, hdr_len); skb->transport_header = skb->network_header; __skb_pull(skb, ah_hlen + hdr_len); - kfree(tmp_hdr); + err = nexthdr; - return nexthdr; - -free_out: - kfree(tmp_hdr); +out_free: + kfree(work_iph); out: return err; } @@ -430,7 +628,7 @@ static int ah6_init_state(struct xfrm_state *x) { struct ah_data *ahp = NULL; struct xfrm_algo_desc *aalg_desc; - struct crypto_hash *tfm; + struct crypto_ahash *ahash; if (!x->aalg) goto error; @@ -442,12 +640,12 @@ static int ah6_init_state(struct xfrm_state *x) if (ahp == NULL) return -ENOMEM; - tfm = crypto_alloc_hash(x->aalg->alg_name, 0, CRYPTO_ALG_ASYNC); - if (IS_ERR(tfm)) + ahash = crypto_alloc_ahash(x->aalg->alg_name, 0, 0); + if (IS_ERR(ahash)) goto error; - ahp->tfm = tfm; - if (crypto_hash_setkey(tfm, x->aalg->alg_key, + ahp->ahash = ahash; + if (crypto_ahash_setkey(ahash, x->aalg->alg_key, (x->aalg->alg_key_len + 7) / 8)) goto error; @@ -461,22 +659,18 @@ static int ah6_init_state(struct xfrm_state *x) BUG_ON(!aalg_desc); if (aalg_desc->uinfo.auth.icv_fullbits/8 != - crypto_hash_digestsize(tfm)) { + crypto_ahash_digestsize(ahash)) { printk(KERN_INFO "AH: %s digestsize %u != %hu\n", - x->aalg->alg_name, crypto_hash_digestsize(tfm), + x->aalg->alg_name, crypto_ahash_digestsize(ahash), aalg_desc->uinfo.auth.icv_fullbits/8); goto error; } ahp->icv_full_len = aalg_desc->uinfo.auth.icv_fullbits/8; - ahp->icv_trunc_len = aalg_desc->uinfo.auth.icv_truncbits/8; + ahp->icv_trunc_len = x->aalg->alg_trunc_len/8; BUG_ON(ahp->icv_trunc_len > MAX_AH_AUTH_LEN); - ahp->work_icv = kmalloc(ahp->icv_full_len, GFP_KERNEL); - if (!ahp->work_icv) - goto error; - x->props.header_len = XFRM_ALIGN8(sizeof(struct ip_auth_hdr) + ahp->icv_trunc_len); switch (x->props.mode) { @@ -495,8 +689,7 @@ static int ah6_init_state(struct xfrm_state *x) error: if (ahp) { - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } return -EINVAL; @@ -509,8 +702,7 @@ static void ah6_destroy(struct xfrm_state *x) if (!ahp) return; - kfree(ahp->work_icv); - crypto_free_hash(ahp->tfm); + crypto_free_ahash(ahp->ahash); kfree(ahp); } diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index 1ae58bec1de0..f1c74c8ef9de 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -404,13 +404,13 @@ int ipv6_chk_acast_addr(struct net *net, struct net_device *dev, if (dev) return ipv6_chk_acast_dev(dev, addr); - read_lock(&dev_base_lock); - for_each_netdev(net, dev) + rcu_read_lock(); + for_each_netdev_rcu(net, dev) if (ipv6_chk_acast_dev(dev, addr)) { found = 1; break; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); return found; } @@ -431,9 +431,9 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); state->idev = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -443,7 +443,6 @@ static inline struct ifacaddr6 *ac6_get_first(struct seq_file *seq) break; } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return im; } @@ -454,16 +453,15 @@ static struct ifacaddr6 *ac6_get_next(struct seq_file *seq, struct ifacaddr6 *im im = im->aca_next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -482,29 +480,30 @@ static struct ifacaddr6 *ac6_get_idx(struct seq_file *seq, loff_t pos) } static void *ac6_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return ac6_get_idx(seq, *pos); } static void *ac6_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifacaddr6 *im; - im = ac6_get_next(seq, v); + struct ifacaddr6 *im = ac6_get_next(seq, v); + ++*pos; return im; } static void ac6_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct ac6_iter_state *state = ac6_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); + state->idev = NULL; } - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int ac6_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv6/datagram.c b/net/ipv6/datagram.c index e2bdc6d83a43..e6f9cdf780fe 100644 --- a/net/ipv6/datagram.c +++ b/net/ipv6/datagram.c @@ -98,17 +98,15 @@ ipv4_connected: if (err) goto out; - ipv6_addr_set(&np->daddr, 0, 0, htonl(0x0000ffff), inet->daddr); + ipv6_addr_set_v4mapped(inet->inet_daddr, &np->daddr); - if (ipv6_addr_any(&np->saddr)) { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000ffff), - inet->saddr); - } + if (ipv6_addr_any(&np->saddr)) + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + + if (ipv6_addr_any(&np->rcv_saddr)) + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &np->rcv_saddr); - if (ipv6_addr_any(&np->rcv_saddr)) { - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000ffff), - inet->rcv_saddr); - } goto out; } @@ -136,7 +134,7 @@ ipv4_connected: ipv6_addr_copy(&np->daddr, daddr); np->flow_label = fl.fl6_flowlabel; - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; /* * Check for a route to destination an obtain the @@ -147,8 +145,9 @@ ipv4_connected: ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; if (!fl.oif && (addr_type&IPV6_ADDR_MULTICAST)) fl.oif = np->mcast_oif; @@ -190,7 +189,7 @@ ipv4_connected: if (ipv6_addr_any(&np->rcv_saddr)) { ipv6_addr_copy(&np->rcv_saddr, &fl.fl6_src); - inet->rcv_saddr = LOOPBACK4_IPV6; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; } ip6_dst_store(sk, dst, @@ -329,9 +328,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) if (ipv6_addr_type(&sin->sin6_addr) & IPV6_ADDR_LINKLOCAL) sin->sin6_scope_id = IP6CB(skb)->iif; } else { - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), - *(__be32 *)(nh + serr->addr_offset)); + ipv6_addr_set_v4mapped(*(__be32 *)(nh + serr->addr_offset), + &sin->sin6_addr); } } @@ -351,8 +349,8 @@ int ipv6_recv_error(struct sock *sk, struct msghdr *msg, int len) } else { struct inet_sock *inet = inet_sk(sk); - ipv6_addr_set(&sin->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin->sin6_addr); if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); } @@ -539,12 +537,17 @@ int datagram_send_ctl(struct net *net, addr_type = __ipv6_addr_type(&src_info->ipi6_addr); + rcu_read_lock(); if (fl->oif) { - dev = dev_get_by_index(net, fl->oif); - if (!dev) + dev = dev_get_by_index_rcu(net, fl->oif); + if (!dev) { + rcu_read_unlock(); return -ENODEV; - } else if (addr_type & IPV6_ADDR_LINKLOCAL) + } + } else if (addr_type & IPV6_ADDR_LINKLOCAL) { + rcu_read_unlock(); return -EINVAL; + } if (addr_type != IPV6_ADDR_ANY) { int strict = __ipv6_addr_src_scope(addr_type) <= IPV6_ADDR_SCOPE_LINKLOCAL; @@ -555,8 +558,7 @@ int datagram_send_ctl(struct net *net, ipv6_addr_copy(&fl->fl6_src, &src_info->ipi6_addr); } - if (dev) - dev_put(dev); + rcu_read_unlock(); if (err) goto exit_f; diff --git a/net/ipv6/esp6.c b/net/ipv6/esp6.c index af597c73ebe9..668a46b655e6 100644 --- a/net/ipv6/esp6.c +++ b/net/ipv6/esp6.c @@ -473,7 +473,7 @@ static int esp_init_authenc(struct xfrm_state *x) } err = crypto_aead_setauthsize( - aead, aalg_desc->uinfo.auth.icv_truncbits / 8); + aead, x->aalg->alg_trunc_len / 8); if (err) goto free_key; } diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index 00a7a5e4ac97..b7aa7c64cc4a 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -264,44 +264,36 @@ static struct fib_rules_ops fib6_rules_ops_template = { static int fib6_rules_net_init(struct net *net) { + struct fib_rules_ops *ops; int err = -ENOMEM; - net->ipv6.fib6_rules_ops = kmemdup(&fib6_rules_ops_template, - sizeof(*net->ipv6.fib6_rules_ops), - GFP_KERNEL); - if (!net->ipv6.fib6_rules_ops) - goto out; + ops = fib_rules_register(&fib6_rules_ops_template, net); + if (IS_ERR(ops)) + return PTR_ERR(ops); + net->ipv6.fib6_rules_ops = ops; - net->ipv6.fib6_rules_ops->fro_net = net; - INIT_LIST_HEAD(&net->ipv6.fib6_rules_ops->rules_list); err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0, - RT6_TABLE_LOCAL, FIB_RULE_PERMANENT); + RT6_TABLE_LOCAL, 0); if (err) goto out_fib6_rules_ops; err = fib_default_rule_add(net->ipv6.fib6_rules_ops, 0x7FFE, RT6_TABLE_MAIN, 0); if (err) - goto out_fib6_default_rule_add; + goto out_fib6_rules_ops; - err = fib_rules_register(net->ipv6.fib6_rules_ops); - if (err) - goto out_fib6_default_rule_add; out: return err; -out_fib6_default_rule_add: - fib_rules_cleanup_ops(net->ipv6.fib6_rules_ops); out_fib6_rules_ops: - kfree(net->ipv6.fib6_rules_ops); + fib_rules_unregister(ops); goto out; } static void fib6_rules_net_exit(struct net *net) { fib_rules_unregister(net->ipv6.fib6_rules_ops); - kfree(net->ipv6.fib6_rules_ops); } static struct pernet_operations fib6_rules_net_ops = { diff --git a/net/ipv6/inet6_connection_sock.c b/net/ipv6/inet6_connection_sock.c index cc4797dd8325..3516e6fe2e56 100644 --- a/net/ipv6/inet6_connection_sock.c +++ b/net/ipv6/inet6_connection_sock.c @@ -132,7 +132,7 @@ void inet6_csk_addr2sockaddr(struct sock *sk, struct sockaddr * uaddr) sin6->sin6_family = AF_INET6; ipv6_addr_copy(&sin6->sin6_addr, &np->daddr); - sin6->sin6_port = inet_sk(sk)->dport; + sin6->sin6_port = inet_sk(sk)->inet_dport; /* We do not store received flowlabel for TCP */ sin6->sin6_flowinfo = 0; sin6->sin6_scope_id = 0; @@ -168,8 +168,7 @@ struct dst_entry *__inet6_csk_dst_check(struct sock *sk, u32 cookie) if (dst) { struct rt6_info *rt = (struct rt6_info *)dst; if (rt->rt6i_flow_cache_genid != atomic_read(&flow_cache_genid)) { - sk->sk_dst_cache = NULL; - dst_release(dst); + __sk_dst_reset(sk); dst = NULL; } } @@ -194,8 +193,9 @@ int inet6_csk_xmit(struct sk_buff *skb, int ipfragok) fl.fl6_flowlabel = np->flow_label; IP6_ECN_flow_xmit(sk, fl.fl6_flowlabel); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_sport = inet->sport; - fl.fl_ip_dport = inet->dport; + fl.mark = sk->sk_mark; + fl.fl_ip_sport = inet->inet_sport; + fl.fl_ip_dport = inet->inet_dport; security_sk_classify_flow(sk, &fl); if (np->opt && np->opt->srcrt) { diff --git a/net/ipv6/inet6_hashtables.c b/net/ipv6/inet6_hashtables.c index 1bcc3431859e..c813e294ec0c 100644 --- a/net/ipv6/inet6_hashtables.c +++ b/net/ipv6/inet6_hashtables.c @@ -73,7 +73,7 @@ struct sock *__inet6_lookup_established(struct net *net, * have wildcards anyways. */ unsigned int hash = inet6_ehashfn(net, daddr, hnum, saddr, sport); - unsigned int slot = hash & (hashinfo->ehash_size - 1); + unsigned int slot = hash & hashinfo->ehash_mask; struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; @@ -125,7 +125,7 @@ static int inline compute_score(struct sock *sk, struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && inet_sk(sk)->num == hnum && + if (net_eq(sock_net(sk), net) && inet_sk(sk)->inet_num == hnum && sk->sk_family == PF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); @@ -214,15 +214,16 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, const struct in6_addr *daddr = &np->rcv_saddr; const struct in6_addr *saddr = &np->daddr; const int dif = sk->sk_bound_dev_if; - const __portpair ports = INET_COMBINED_PORTS(inet->dport, lport); + const __portpair ports = INET_COMBINED_PORTS(inet->inet_dport, lport); struct net *net = sock_net(sk); const unsigned int hash = inet6_ehashfn(net, daddr, lport, saddr, - inet->dport); + inet->inet_dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; + int twrefcnt = 0; spin_lock(lock); @@ -248,21 +249,25 @@ static int __inet6_check_established(struct inet_timewait_death_row *death_row, unique: /* Must record num and sport now. Otherwise we will see * in hash table socket with a funny identity. */ - inet->num = lport; - inet->sport = htons(lport); + inet->inet_num = lport; + inet->inet_sport = htons(lport); + sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); __sk_nulls_add_node_rcu(sk, &head->chain); - sk->sk_hash = hash; + if (tw) { + twrefcnt = inet_twsk_unhash(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 != NULL) { + if (twp) { *twp = tw; - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); - } else if (tw != NULL) { + } else if (tw) { /* Silly. Should hash-dance instead... */ inet_twsk_deschedule(tw, death_row); - NET_INC_STATS_BH(net, LINUX_MIB_TIMEWAITRECYCLED); inet_twsk_put(tw); } @@ -279,7 +284,7 @@ static inline u32 inet6_sk_port_offset(const struct sock *sk) const struct ipv6_pinfo *np = inet6_sk(sk); return secure_ipv6_port_ephemeral(np->rcv_saddr.s6_addr32, np->daddr.s6_addr32, - inet->dport); + inet->inet_dport); } int inet6_hash_connect(struct inet_timewait_death_row *death_row, diff --git a/net/ipv6/ip6_flowlabel.c b/net/ipv6/ip6_flowlabel.c index 7712578bdc66..6e7bffa2205e 100644 --- a/net/ipv6/ip6_flowlabel.c +++ b/net/ipv6/ip6_flowlabel.c @@ -67,7 +67,7 @@ static inline struct ip6_flowlabel *__fl_lookup(struct net *net, __be32 label) struct ip6_flowlabel *fl; for (fl=fl_ht[FL_HASH(label)]; fl; fl = fl->next) { - if (fl->label == label && fl->fl_net == net) + if (fl->label == label && net_eq(fl->fl_net, net)) return fl; } return NULL; @@ -163,7 +163,8 @@ static void ip6_fl_purge(struct net *net) struct ip6_flowlabel *fl, **flp; flp = &fl_ht[i]; while ((fl = *flp) != NULL) { - if (fl->fl_net == net && atomic_read(&fl->users) == 0) { + if (net_eq(fl->fl_net, net) && + atomic_read(&fl->users) == 0) { *flp = fl->next; fl_free(fl); atomic_dec(&fl_size); @@ -377,8 +378,8 @@ fl_create(struct net *net, struct in6_flowlabel_req *freq, char __user *optval, goto done; fl->share = freq->flr_share; addr_type = ipv6_addr_type(&freq->flr_dst); - if ((addr_type&IPV6_ADDR_MAPPED) - || addr_type == IPV6_ADDR_ANY) { + if ((addr_type & IPV6_ADDR_MAPPED) || + addr_type == IPV6_ADDR_ANY) { err = -EINVAL; goto done; } @@ -421,8 +422,8 @@ static int mem_check(struct sock *sk) if (room <= 0 || ((count >= FL_MAX_PER_SOCK || - (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) - && !capable(CAP_NET_ADMIN))) + (count > 0 && room < FL_MAX_SIZE/2) || room < FL_MAX_SIZE/4) && + !capable(CAP_NET_ADMIN))) return -ENOBUFS; return 0; @@ -630,7 +631,7 @@ static struct ip6_flowlabel *ip6fl_get_first(struct seq_file *seq) for (state->bucket = 0; state->bucket <= FL_HASH_MASK; ++state->bucket) { fl = fl_ht[state->bucket]; - while (fl && fl->fl_net != net) + while (fl && !net_eq(fl->fl_net, net)) fl = fl->next; if (fl) break; @@ -645,7 +646,7 @@ static struct ip6_flowlabel *ip6fl_get_next(struct seq_file *seq, struct ip6_flo fl = fl->next; try_again: - while (fl && fl->fl_net != net) + while (fl && !net_eq(fl->fl_net, net)) fl = fl->next; while (!fl) { diff --git a/net/ipv6/ip6_tunnel.c b/net/ipv6/ip6_tunnel.c index c595bbe1ed99..d453d07b0dfe 100644 --- a/net/ipv6/ip6_tunnel.c +++ b/net/ipv6/ip6_tunnel.c @@ -78,7 +78,7 @@ static void ip6_fb_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_init(struct net_device *dev); static void ip6_tnl_dev_setup(struct net_device *dev); -static int ip6_tnl_net_id; +static int ip6_tnl_net_id __read_mostly; struct ip6_tnl_net { /* the IPv6 tunnel fallback device */ struct net_device *fb_tnl_dev; @@ -88,8 +88,10 @@ struct ip6_tnl_net { struct ip6_tnl **tnls[2]; }; -/* lock for the tunnel lists */ -static DEFINE_RWLOCK(ip6_tnl_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ip6_tnl_lock); static inline struct dst_entry *ip6_tnl_dst_check(struct ip6_tnl *t) { @@ -130,6 +132,9 @@ static inline void ip6_tnl_dst_store(struct ip6_tnl *t, struct dst_entry *dst) * else %NULL **/ +#define for_each_ip6_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) + static struct ip6_tnl * ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) { @@ -138,13 +143,14 @@ ip6_tnl_lookup(struct net *net, struct in6_addr *remote, struct in6_addr *local) struct ip6_tnl *t; struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - for (t = ip6n->tnls_r_l[h0 ^ h1]; t; t = t->next) { + for_each_ip6_tunnel_rcu(ip6n->tnls_r_l[h0 ^ h1]) { if (ipv6_addr_equal(local, &t->parms.laddr) && ipv6_addr_equal(remote, &t->parms.raddr) && (t->dev->flags & IFF_UP)) return t; } - if ((t = ip6n->tnls_wc[0]) != NULL && (t->dev->flags & IFF_UP)) + t = rcu_dereference(ip6n->tnls_wc[0]); + if (t && (t->dev->flags & IFF_UP)) return t; return NULL; @@ -186,10 +192,10 @@ ip6_tnl_link(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) { struct ip6_tnl **tp = ip6_tnl_bucket(ip6n, &t->parms); + spin_lock_bh(&ip6_tnl_lock); t->next = *tp; - write_lock_bh(&ip6_tnl_lock); - *tp = t; - write_unlock_bh(&ip6_tnl_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ip6_tnl_lock); } /** @@ -204,9 +210,9 @@ ip6_tnl_unlink(struct ip6_tnl_net *ip6n, struct ip6_tnl *t) for (tp = ip6_tnl_bucket(ip6n, &t->parms); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ip6_tnl_lock); + spin_lock_bh(&ip6_tnl_lock); *tp = t->next; - write_unlock_bh(&ip6_tnl_lock); + spin_unlock_bh(&ip6_tnl_lock); break; } } @@ -313,9 +319,9 @@ ip6_tnl_dev_uninit(struct net_device *dev) struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); if (dev == ip6n->fb_tnl_dev) { - write_lock_bh(&ip6_tnl_lock); + spin_lock_bh(&ip6_tnl_lock); ip6n->tnls_wc[0] = NULL; - write_unlock_bh(&ip6_tnl_lock); + spin_unlock_bh(&ip6_tnl_lock); } else { ip6_tnl_unlink(ip6n, t); } @@ -409,7 +415,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, in trouble since we might need the source address for further processing of the error. */ - read_lock(&ip6_tnl_lock); + rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->daddr, &ipv6h->saddr)) == NULL) goto out; @@ -482,7 +488,7 @@ ip6_tnl_err(struct sk_buff *skb, __u8 ipproto, struct inet6_skb_parm *opt, *msg = rel_msg; out: - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return err; } @@ -652,6 +658,7 @@ static void ip6ip6_dscp_ecn_decapsulate(struct ip6_tnl *t, IP6_ECN_set_ce(ipv6_hdr(skb)); } +/* called with rcu_read_lock() */ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) { struct ip6_tnl_parm *p = &t->parms; @@ -662,15 +669,13 @@ static inline int ip6_tnl_rcv_ctl(struct ip6_tnl *t) struct net_device *ldev = NULL; if (p->link) - ldev = dev_get_by_index(net, p->link); + ldev = dev_get_by_index_rcu(net, p->link); if ((ipv6_addr_is_multicast(&p->laddr) || likely(ipv6_chk_addr(net, &p->laddr, ldev, 0))) && likely(!ipv6_chk_addr(net, &p->raddr, NULL, 0))) ret = 1; - if (ldev) - dev_put(ldev); } return ret; } @@ -693,23 +698,23 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, struct ip6_tnl *t; struct ipv6hdr *ipv6h = ipv6_hdr(skb); - read_lock(&ip6_tnl_lock); + rcu_read_lock(); if ((t = ip6_tnl_lookup(dev_net(skb->dev), &ipv6h->saddr, &ipv6h->daddr)) != NULL) { if (t->parms.proto != ipproto && t->parms.proto != 0) { - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } if (!xfrm6_policy_check(NULL, XFRM_POLICY_IN, skb)) { - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } if (!ip6_tnl_rcv_ctl(t)) { t->dev->stats.rx_dropped++; - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); goto discard; } secpath_reset(skb); @@ -727,10 +732,10 @@ static int ip6_tnl_rcv(struct sk_buff *skb, __u16 protocol, t->dev->stats.rx_packets++; t->dev->stats.rx_bytes += skb->len; netif_rx(skb); - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return 0; } - read_unlock(&ip6_tnl_lock); + rcu_read_unlock(); return 1; discard: @@ -798,8 +803,9 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) if (p->flags & IP6_TNL_F_CAP_XMIT) { struct net_device *ldev = NULL; + rcu_read_lock(); if (p->link) - ldev = dev_get_by_index(net, p->link); + ldev = dev_get_by_index_rcu(net, p->link); if (unlikely(!ipv6_chk_addr(net, &p->laddr, ldev, 0))) printk(KERN_WARNING @@ -813,8 +819,7 @@ static inline int ip6_tnl_xmit_ctl(struct ip6_tnl *t) p->name); else ret = 1; - if (ldev) - dev_put(ldev); + rcu_read_unlock(); } return ret; } @@ -1387,29 +1392,25 @@ static void ip6_tnl_destroy_tunnels(struct ip6_tnl_net *ip6n) { int h; struct ip6_tnl *t; + LIST_HEAD(list); for (h = 0; h < HASH_SIZE; h++) { - while ((t = ip6n->tnls_r_l[h]) != NULL) - unregister_netdevice(t->dev); + t = ip6n->tnls_r_l[h]; + while (t != NULL) { + unregister_netdevice_queue(t->dev, &list); + t = t->next; + } } t = ip6n->tnls_wc[0]; - unregister_netdevice(t->dev); + unregister_netdevice_queue(t->dev, &list); + unregister_netdevice_many(&list); } static int ip6_tnl_init_net(struct net *net) { + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); int err; - struct ip6_tnl_net *ip6n; - - err = -ENOMEM; - ip6n = kzalloc(sizeof(struct ip6_tnl_net), GFP_KERNEL); - if (ip6n == NULL) - goto err_alloc; - - err = net_assign_generic(net, ip6_tnl_net_id, ip6n); - if (err < 0) - goto err_assign; ip6n->tnls[0] = ip6n->tnls_wc; ip6n->tnls[1] = ip6n->tnls_r_l; @@ -1432,27 +1433,23 @@ static int ip6_tnl_init_net(struct net *net) err_register: free_netdev(ip6n->fb_tnl_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(ip6n); -err_alloc: return err; } static void ip6_tnl_exit_net(struct net *net) { - struct ip6_tnl_net *ip6n; + struct ip6_tnl_net *ip6n = net_generic(net, ip6_tnl_net_id); - ip6n = net_generic(net, ip6_tnl_net_id); rtnl_lock(); ip6_tnl_destroy_tunnels(ip6n); rtnl_unlock(); - kfree(ip6n); } static struct pernet_operations ip6_tnl_net_ops = { .init = ip6_tnl_init_net, .exit = ip6_tnl_exit_net, + .id = &ip6_tnl_net_id, + .size = sizeof(struct ip6_tnl_net), }; /** @@ -1477,7 +1474,7 @@ static int __init ip6_tunnel_init(void) goto unreg_ip4ip6; } - err = register_pernet_gen_device(&ip6_tnl_net_id, &ip6_tnl_net_ops); + err = register_pernet_device(&ip6_tnl_net_ops); if (err < 0) goto err_pernet; return 0; @@ -1501,7 +1498,7 @@ static void __exit ip6_tunnel_cleanup(void) if (xfrm6_tunnel_deregister(&ip6ip6_handler, AF_INET6)) printk(KERN_INFO "ip6_tunnel close: can't deregister ip6ip6\n"); - unregister_pernet_gen_device(ip6_tnl_net_id, &ip6_tnl_net_ops); + unregister_pernet_device(&ip6_tnl_net_ops); } module_init(ip6_tunnel_init); diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 716153941fc4..52e0f74fdfe0 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -477,7 +477,7 @@ failure: * Delete a VIF entry */ -static int mif6_delete(struct net *net, int vifi) +static int mif6_delete(struct net *net, int vifi, struct list_head *head) { struct mif_device *v; struct net_device *dev; @@ -519,7 +519,7 @@ static int mif6_delete(struct net *net, int vifi) in6_dev->cnf.mc_forwarding--; if (v->flags & MIFF_REGISTER) - unregister_netdevice(dev); + unregister_netdevice_queue(dev, head); dev_put(dev); return 0; @@ -976,6 +976,7 @@ static int ip6mr_device_event(struct notifier_block *this, struct net *net = dev_net(dev); struct mif_device *v; int ct; + LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -983,8 +984,10 @@ static int ip6mr_device_event(struct notifier_block *this, v = &net->ipv6.vif6_table[0]; for (ct = 0; ct < net->ipv6.maxvif; ct++, v++) { if (v->dev == dev) - mif6_delete(net, ct); + mif6_delete(net, ct, &list); } + unregister_netdevice_many(&list); + return NOTIFY_DONE; } @@ -1188,14 +1191,16 @@ static int ip6mr_mfc_add(struct net *net, struct mf6cctl *mfc, int mrtsock) static void mroute_clean_tables(struct net *net) { int i; + LIST_HEAD(list); /* * Shut down all active vif entries */ for (i = 0; i < net->ipv6.maxvif; i++) { if (!(net->ipv6.vif6_table[i].flags & VIFF_STATIC)) - mif6_delete(net, i); + mif6_delete(net, i, &list); } + unregister_netdevice_many(&list); /* * Wipe the cache @@ -1297,7 +1302,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns switch (optname) { case MRT6_INIT: if (sk->sk_type != SOCK_RAW || - inet_sk(sk)->num != IPPROTO_ICMPV6) + inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; if (optlen < sizeof(int)) return -EINVAL; @@ -1325,7 +1330,7 @@ int ip6_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, uns if (copy_from_user(&mifi, optval, sizeof(mifi_t))) return -EFAULT; rtnl_lock(); - ret = mif6_delete(net, mifi); + ret = mif6_delete(net, mifi, NULL); rtnl_unlock(); return ret; diff --git a/net/ipv6/ipv6_sockglue.c b/net/ipv6/ipv6_sockglue.c index 4f7aaf6996a3..430454ee5ead 100644 --- a/net/ipv6/ipv6_sockglue.c +++ b/net/ipv6/ipv6_sockglue.c @@ -64,7 +64,7 @@ int ip6_ra_control(struct sock *sk, int sel) struct ip6_ra_chain *ra, *new_ra, **rap; /* RA packet may be delivered ONLY to IPPROTO_RAW socket */ - if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_RAW) + if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num != IPPROTO_RAW) return -ENOPROTOOPT; new_ra = (sel>=0) ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; @@ -106,7 +106,7 @@ struct ipv6_txoptions *ipv6_update_options(struct sock *sk, if (inet_sk(sk)->is_icsk) { if (opt && !((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && - inet_sk(sk)->daddr != LOOPBACK4_IPV6) { + inet_sk(sk)->inet_daddr != LOOPBACK4_IPV6) { struct inet_connection_sock *icsk = inet_csk(sk); icsk->icsk_ext_hdr_len = opt->opt_flen + opt->opt_nflen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); @@ -234,7 +234,7 @@ static int do_ipv6_setsockopt(struct sock *sk, int level, int optname, case IPV6_V6ONLY: if (optlen < sizeof(int) || - inet_sk(sk)->num) + inet_sk(sk)->inet_num) goto e_inval; np->ipv6only = valbool; retv = 0; @@ -424,6 +424,7 @@ sticky_done: fl.fl6_flowlabel = 0; fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; if (optlen == 0) goto update; @@ -665,7 +666,7 @@ done: case IPV6_MTU_DISCOVER: if (optlen < sizeof(int)) goto e_inval; - if (val<0 || val>3) + if (val < IP_PMTUDISC_DONT || val > IP_PMTUDISC_PROBE) goto e_inval; np->pmtudisc = val; retv = 0; diff --git a/net/ipv6/mcast.c b/net/ipv6/mcast.c index f9fcf690bd5d..1f9c44442e65 100644 --- a/net/ipv6/mcast.c +++ b/net/ipv6/mcast.c @@ -2375,9 +2375,9 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) struct net *net = seq_file_net(seq); state->idev = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (!idev) continue; read_lock_bh(&idev->lock); @@ -2387,7 +2387,6 @@ static inline struct ifmcaddr6 *igmp6_mc_get_first(struct seq_file *seq) break; } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return im; } @@ -2398,16 +2397,15 @@ static struct ifmcaddr6 *igmp6_mc_get_next(struct seq_file *seq, struct ifmcaddr im = im->next; while (!im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; break; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -2426,31 +2424,31 @@ static struct ifmcaddr6 *igmp6_mc_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp6_mc_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return igmp6_mc_get_idx(seq, *pos); } static void *igmp6_mc_seq_next(struct seq_file *seq, void *v, loff_t *pos) { - struct ifmcaddr6 *im; - im = igmp6_mc_get_next(seq, v); + struct ifmcaddr6 *im = igmp6_mc_get_next(seq, v); + ++*pos; return im; } static void igmp6_mc_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct igmp6_mc_iter_state *state = igmp6_mc_seq_private(seq); + if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp6_mc_seq_show(struct seq_file *seq, void *v) @@ -2507,9 +2505,9 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) state->idev = NULL; state->im = NULL; - for_each_netdev(net, state->dev) { + for_each_netdev_rcu(net, state->dev) { struct inet6_dev *idev; - idev = in6_dev_get(state->dev); + idev = __in6_dev_get(state->dev); if (unlikely(idev == NULL)) continue; read_lock_bh(&idev->lock); @@ -2525,7 +2523,6 @@ static inline struct ip6_sf_list *igmp6_mcf_get_first(struct seq_file *seq) spin_unlock_bh(&im->mca_lock); } read_unlock_bh(&idev->lock); - in6_dev_put(idev); } return psf; } @@ -2539,16 +2536,15 @@ static struct ip6_sf_list *igmp6_mcf_get_next(struct seq_file *seq, struct ip6_s spin_unlock_bh(&state->im->mca_lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) { + if (likely(state->idev != NULL)) read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); - } - state->dev = next_net_device(state->dev); + + state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; goto out; } - state->idev = in6_dev_get(state->dev); + state->idev = __in6_dev_get(state->dev); if (!state->idev) continue; read_lock_bh(&state->idev->lock); @@ -2573,9 +2569,9 @@ static struct ip6_sf_list *igmp6_mcf_get_idx(struct seq_file *seq, loff_t pos) } static void *igmp6_mcf_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(dev_base_lock) + __acquires(RCU) { - read_lock(&dev_base_lock); + rcu_read_lock(); return *pos ? igmp6_mcf_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; } @@ -2591,7 +2587,7 @@ static void *igmp6_mcf_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) - __releases(dev_base_lock) + __releases(RCU) { struct igmp6_mcf_iter_state *state = igmp6_mcf_seq_private(seq); if (likely(state->im != NULL)) { @@ -2600,11 +2596,10 @@ static void igmp6_mcf_seq_stop(struct seq_file *seq, void *v) } if (likely(state->idev != NULL)) { read_unlock_bh(&state->idev->lock); - in6_dev_put(state->idev); state->idev = NULL; } state->dev = NULL; - read_unlock(&dev_base_lock); + rcu_read_unlock(); } static int igmp6_mcf_seq_show(struct seq_file *seq, void *v) diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 3d0520e455d8..c45852798092 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -598,6 +598,7 @@ static void ndisc_send_na(struct net_device *dev, struct neighbour *neigh, icmp6h.icmp6_solicited = solicited; icmp6h.icmp6_override = override; + inc_opt |= ifp->idev->cnf.force_tllao; __ndisc_send(dev, neigh, daddr, src_addr, &icmp6h, solicited_addr, inc_opt ? ND_OPT_TARGET_LL_ADDR : 0); diff --git a/net/ipv6/netfilter/ip6_queue.c b/net/ipv6/netfilter/ip6_queue.c index 14e52aa624c2..7854052be60b 100644 --- a/net/ipv6/netfilter/ip6_queue.c +++ b/net/ipv6/netfilter/ip6_queue.c @@ -498,10 +498,9 @@ ipq_rcv_nl_event(struct notifier_block *this, { struct netlink_notify *n = ptr; - if (event == NETLINK_URELEASE && - n->protocol == NETLINK_IP6_FW && n->pid) { + if (event == NETLINK_URELEASE && n->protocol == NETLINK_IP6_FW) { write_lock_bh(&queue_lock); - if ((n->net == &init_net) && (n->pid == peer_pid)) + if ((net_eq(n->net, &init_net)) && (n->pid == peer_pid)) __ipq_reset(); write_unlock_bh(&queue_lock); } @@ -623,7 +622,7 @@ cleanup_netlink_notifier: static void __exit ip6_queue_fini(void) { nf_unregister_queue_handlers(&nfqh); - synchronize_net(); + ipq_flush(NULL, 0); #ifdef CONFIG_SYSCTL diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index cc9f8ef303fd..480d7f8c9802 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -105,9 +105,9 @@ ip6_packet_match(const struct sk_buff *skb, #define FWINV(bool, invflg) ((bool) ^ !!(ip6info->invflags & (invflg))) if (FWINV(ipv6_masked_addr_cmp(&ipv6->saddr, &ip6info->smsk, - &ip6info->src), IP6T_INV_SRCIP) - || FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, - &ip6info->dst), IP6T_INV_DSTIP)) { + &ip6info->src), IP6T_INV_SRCIP) || + FWINV(ipv6_masked_addr_cmp(&ipv6->daddr, &ip6info->dmsk, + &ip6info->dst), IP6T_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); /* dprintf("SRC: %u. Mask: %u. Target: %u.%s\n", ip->saddr, @@ -277,11 +277,11 @@ get_chainname_rulenum(struct ip6t_entry *s, struct ip6t_entry *e, } else if (s == e) { (*rulenum)++; - if (s->target_offset == sizeof(struct ip6t_entry) - && strcmp(t->target.u.kernel.target->name, - IP6T_STANDARD_TARGET) == 0 - && t->verdict < 0 - && unconditional(&s->ipv6)) { + if (s->target_offset == sizeof(struct ip6t_entry) && + strcmp(t->target.u.kernel.target->name, + IP6T_STANDARD_TARGET) == 0 && + t->verdict < 0 && + unconditional(&s->ipv6)) { /* Tail of chains: STANDARD target (return/policy) */ *comment = *chainname == hookname ? comments[NF_IP6_TRACE_COMMENT_POLICY] @@ -418,8 +418,8 @@ ip6t_do_table(struct sk_buff *skb, back = get_entry(table_base, back->comefrom); continue; } - if (table_base + v != ip6t_next_entry(e) - && !(e->ipv6.flags & IP6T_F_GOTO)) { + if (table_base + v != ip6t_next_entry(e) && + !(e->ipv6.flags & IP6T_F_GOTO)) { /* Save old back ptr in next entry */ struct ip6t_entry *next = ip6t_next_entry(e); next->comefrom = (void *)back - table_base; @@ -505,11 +505,11 @@ mark_source_chains(struct xt_table_info *newinfo, e->comefrom |= ((1 << hook) | (1 << NF_INET_NUMHOOKS)); /* Unconditional return/END. */ - if ((e->target_offset == sizeof(struct ip6t_entry) - && (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0) - && t->verdict < 0 - && unconditional(&e->ipv6)) || visited) { + if ((e->target_offset == sizeof(struct ip6t_entry) && + (strcmp(t->target.u.user.name, + IP6T_STANDARD_TARGET) == 0) && + t->verdict < 0 && + unconditional(&e->ipv6)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, @@ -556,8 +556,8 @@ mark_source_chains(struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IP6T_STANDARD_TARGET) == 0 - && newpos >= 0) { + IP6T_STANDARD_TARGET) == 0 && + newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ip6t_entry)) { duprintf("mark_source_chains: " @@ -767,8 +767,8 @@ check_entry_size_and_hooks(struct ip6t_entry *e, { unsigned int h; - if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct ip6t_entry) >= limit) { duprintf("Bad offset %p\n", e); return -EINVAL; } @@ -1584,8 +1584,8 @@ check_compat_entry_size_and_hooks(struct compat_ip6t_entry *e, int ret, off, h; duprintf("check_compat_entry_size_and_hooks %p\n", e); - if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 - || (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { + if ((unsigned long)e % __alignof__(struct compat_ip6t_entry) != 0 || + (unsigned char *)e + sizeof(struct compat_ip6t_entry) >= limit) { duprintf("Bad offset %p, limit = %p\n", e, limit); return -EINVAL; } diff --git a/net/ipv6/netfilter/ip6t_LOG.c b/net/ipv6/netfilter/ip6t_LOG.c index 7018cac4fddc..b285fdf19050 100644 --- a/net/ipv6/netfilter/ip6t_LOG.c +++ b/net/ipv6/netfilter/ip6t_LOG.c @@ -249,8 +249,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 11 "URGP=65535 " */ printk("URGP=%u ", ntohs(th->urg_ptr)); - if ((logflags & IP6T_LOG_TCPOPT) - && th->doff * 4 > sizeof(struct tcphdr)) { + if ((logflags & IP6T_LOG_TCPOPT) && + th->doff * 4 > sizeof(struct tcphdr)) { u_int8_t _opt[60 - sizeof(struct tcphdr)]; const u_int8_t *op; unsigned int i; diff --git a/net/ipv6/netfilter/ip6t_REJECT.c b/net/ipv6/netfilter/ip6t_REJECT.c index 5a7f00cd15ce..8311ca31816a 100644 --- a/net/ipv6/netfilter/ip6t_REJECT.c +++ b/net/ipv6/netfilter/ip6t_REJECT.c @@ -223,8 +223,8 @@ static bool reject_tg6_check(const struct xt_tgchk_param *par) return false; } else if (rejinfo->with == IP6T_TCP_RESET) { /* Must specify that it's a TCP packet */ - if (e->ipv6.proto != IPPROTO_TCP - || (e->ipv6.invflags & XT_INV_PROTO)) { + if (e->ipv6.proto != IPPROTO_TCP || + (e->ipv6.invflags & XT_INV_PROTO)) { printk("ip6t_REJECT: TCP_RESET illegal for non-tcp\n"); return false; } diff --git a/net/ipv6/netfilter/ip6t_ah.c b/net/ipv6/netfilter/ip6t_ah.c index 3a82f24746b9..ac0b7c629d78 100644 --- a/net/ipv6/netfilter/ip6t_ah.c +++ b/net/ipv6/netfilter/ip6t_ah.c @@ -77,17 +77,14 @@ static bool ah_mt6(const struct sk_buff *skb, const struct xt_match_param *par) ahinfo->hdrres, ah->reserved, !(ahinfo->hdrres && ah->reserved)); - return (ah != NULL) - && - spi_match(ahinfo->spis[0], ahinfo->spis[1], - ntohl(ah->spi), - !!(ahinfo->invflags & IP6T_AH_INV_SPI)) - && - (!ahinfo->hdrlen || - (ahinfo->hdrlen == hdrlen) ^ - !!(ahinfo->invflags & IP6T_AH_INV_LEN)) - && - !(ahinfo->hdrres && ah->reserved); + return (ah != NULL) && + spi_match(ahinfo->spis[0], ahinfo->spis[1], + ntohl(ah->spi), + !!(ahinfo->invflags & IP6T_AH_INV_SPI)) && + (!ahinfo->hdrlen || + (ahinfo->hdrlen == hdrlen) ^ + !!(ahinfo->invflags & IP6T_AH_INV_LEN)) && + !(ahinfo->hdrres && ah->reserved); } static bool ah_mt6_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6t_frag.c b/net/ipv6/netfilter/ip6t_frag.c index 673aa0a5084e..7b91c2598ed5 100644 --- a/net/ipv6/netfilter/ip6t_frag.c +++ b/net/ipv6/netfilter/ip6t_frag.c @@ -70,41 +70,36 @@ frag_mt6(const struct sk_buff *skb, const struct xt_match_param *par) pr_debug("res %02X %02X%04X %02X ", fraginfo->flags & IP6T_FRAG_RES, fh->reserved, ntohs(fh->frag_off) & 0x6, - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x06)))); pr_debug("first %02X %02X %02X ", fraginfo->flags & IP6T_FRAG_FST, ntohs(fh->frag_off) & ~0x7, - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7))); + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7))); pr_debug("mf %02X %02X %02X ", fraginfo->flags & IP6T_FRAG_MF, ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_MF) - && !((ntohs(fh->frag_off) & IP6_MF)))); + !((fraginfo->flags & IP6T_FRAG_MF) && + !((ntohs(fh->frag_off) & IP6_MF)))); pr_debug("last %02X %02X %02X\n", fraginfo->flags & IP6T_FRAG_NMF, ntohs(fh->frag_off) & IP6_MF, - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF))); - - return (fh != NULL) - && - id_match(fraginfo->ids[0], fraginfo->ids[1], - ntohl(fh->identification), - !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) - && - !((fraginfo->flags & IP6T_FRAG_RES) - && (fh->reserved || (ntohs(fh->frag_off) & 0x6))) - && - !((fraginfo->flags & IP6T_FRAG_FST) - && (ntohs(fh->frag_off) & ~0x7)) - && - !((fraginfo->flags & IP6T_FRAG_MF) - && !(ntohs(fh->frag_off) & IP6_MF)) - && - !((fraginfo->flags & IP6T_FRAG_NMF) - && (ntohs(fh->frag_off) & IP6_MF)); + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF))); + + return (fh != NULL) && + id_match(fraginfo->ids[0], fraginfo->ids[1], + ntohl(fh->identification), + !!(fraginfo->invflags & IP6T_FRAG_INV_IDS)) && + !((fraginfo->flags & IP6T_FRAG_RES) && + (fh->reserved || (ntohs(fh->frag_off) & 0x6))) && + !((fraginfo->flags & IP6T_FRAG_FST) && + (ntohs(fh->frag_off) & ~0x7)) && + !((fraginfo->flags & IP6T_FRAG_MF) && + !(ntohs(fh->frag_off) & IP6_MF)) && + !((fraginfo->flags & IP6T_FRAG_NMF) && + (ntohs(fh->frag_off) & IP6_MF)); } static bool frag_mt6_check(const struct xt_mtchk_param *par) diff --git a/net/ipv6/netfilter/ip6t_rt.c b/net/ipv6/netfilter/ip6t_rt.c index 356b8d6f6baa..b77307fc8743 100644 --- a/net/ipv6/netfilter/ip6t_rt.c +++ b/net/ipv6/netfilter/ip6t_rt.c @@ -92,16 +92,13 @@ static bool rt_mt6(const struct sk_buff *skb, const struct xt_match_param *par) !((rtinfo->flags & IP6T_RT_RES) && (((const struct rt0_hdr *)rh)->reserved))); - ret = (rh != NULL) - && + ret = (rh != NULL) && (segsleft_match(rtinfo->segsleft[0], rtinfo->segsleft[1], rh->segments_left, - !!(rtinfo->invflags & IP6T_RT_INV_SGS))) - && + !!(rtinfo->invflags & IP6T_RT_INV_SGS))) && (!(rtinfo->flags & IP6T_RT_LEN) || ((rtinfo->hdrlen == hdrlen) ^ - !!(rtinfo->invflags & IP6T_RT_INV_LEN))) - && + !!(rtinfo->invflags & IP6T_RT_INV_LEN))) && (!(rtinfo->flags & IP6T_RT_TYP) || ((rtinfo->rt_type == rh->type) ^ !!(rtinfo->invflags & IP6T_RT_INV_TYP))); diff --git a/net/ipv6/netfilter/ip6table_filter.c b/net/ipv6/netfilter/ip6table_filter.c index 6f4383ad86f9..ad378efd0eb8 100644 --- a/net/ipv6/netfilter/ip6table_filter.c +++ b/net/ipv6/netfilter/ip6table_filter.c @@ -79,8 +79,8 @@ ip6t_local_out_hook(unsigned int hook, { #if 0 /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) { if (net_ratelimit()) printk("ip6t_hook: happy cracking.\n"); return NF_ACCEPT; diff --git a/net/ipv6/netfilter/ip6table_mangle.c b/net/ipv6/netfilter/ip6table_mangle.c index 0ad91433ed61..a929c19d30e3 100644 --- a/net/ipv6/netfilter/ip6table_mangle.c +++ b/net/ipv6/netfilter/ip6table_mangle.c @@ -102,8 +102,8 @@ ip6t_local_out_hook(unsigned int hook, #if 0 /* root is playing with raw sockets. */ - if (skb->len < sizeof(struct iphdr) - || ip_hdrlen(skb) < sizeof(struct iphdr)) { + if (skb->len < sizeof(struct iphdr) || + ip_hdrlen(skb) < sizeof(struct iphdr)) { if (net_ratelimit()) printk("ip6t_hook: happy cracking.\n"); return NF_ACCEPT; @@ -122,11 +122,11 @@ ip6t_local_out_hook(unsigned int hook, ret = ip6t_do_table(skb, hook, in, out, dev_net(out)->ipv6.ip6table_mangle); - if (ret != NF_DROP && ret != NF_STOLEN - && (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) - || memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) - || skb->mark != mark - || ipv6_hdr(skb)->hop_limit != hop_limit)) + if (ret != NF_DROP && ret != NF_STOLEN && + (memcmp(&ipv6_hdr(skb)->saddr, &saddr, sizeof(saddr)) || + memcmp(&ipv6_hdr(skb)->daddr, &daddr, sizeof(daddr)) || + skb->mark != mark || + ipv6_hdr(skb)->hop_limit != hop_limit)) return ip6_route_me_harder(skb) == 0 ? ret : NF_DROP; return ret; diff --git a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c index 2acadc8c7883..c7b8bd1d7984 100644 --- a/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_conntrack_proto_icmpv6.c @@ -244,18 +244,18 @@ static const struct nla_policy icmpv6_nla_policy[CTA_PROTO_MAX+1] = { static int icmpv6_nlattr_to_tuple(struct nlattr *tb[], struct nf_conntrack_tuple *tuple) { - if (!tb[CTA_PROTO_ICMPV6_TYPE] - || !tb[CTA_PROTO_ICMPV6_CODE] - || !tb[CTA_PROTO_ICMPV6_ID]) + if (!tb[CTA_PROTO_ICMPV6_TYPE] || + !tb[CTA_PROTO_ICMPV6_CODE] || + !tb[CTA_PROTO_ICMPV6_ID]) return -EINVAL; tuple->dst.u.icmp.type = nla_get_u8(tb[CTA_PROTO_ICMPV6_TYPE]); tuple->dst.u.icmp.code = nla_get_u8(tb[CTA_PROTO_ICMPV6_CODE]); tuple->src.u.icmp.id = nla_get_be16(tb[CTA_PROTO_ICMPV6_ID]); - if (tuple->dst.u.icmp.type < 128 - || tuple->dst.u.icmp.type - 128 >= sizeof(invmap) - || !invmap[tuple->dst.u.icmp.type - 128]) + if (tuple->dst.u.icmp.type < 128 || + tuple->dst.u.icmp.type - 128 >= sizeof(invmap) || + !invmap[tuple->dst.u.icmp.type - 128]) return -EINVAL; return 0; diff --git a/net/ipv6/raw.c b/net/ipv6/raw.c index 4f24570b0869..926ce8eeffaf 100644 --- a/net/ipv6/raw.c +++ b/net/ipv6/raw.c @@ -72,7 +72,7 @@ static struct sock *__raw_v6_lookup(struct net *net, struct sock *sk, int is_multicast = ipv6_addr_is_multicast(loc_addr); sk_for_each_from(sk, node) - if (inet_sk(sk)->num == num) { + if (inet_sk(sk)->inet_num == num) { struct ipv6_pinfo *np = inet6_sk(sk); if (!net_eq(sock_net(sk), net)) @@ -249,7 +249,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Raw sockets are IPv6 only */ if (addr_type == IPV6_ADDR_MAPPED) - return(-EADDRNOTAVAIL); + return -EADDRNOTAVAIL; lock_sock(sk); @@ -257,6 +257,7 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) if (sk->sk_state != TCP_CLOSE) goto out; + rcu_read_lock(); /* Check if the address belongs to the host. */ if (addr_type != IPV6_ADDR_ANY) { struct net_device *dev = NULL; @@ -272,13 +273,13 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) /* Binding to link-local address requires an interface */ if (!sk->sk_bound_dev_if) - goto out; + goto out_unlock; - dev = dev_get_by_index(sock_net(sk), sk->sk_bound_dev_if); - if (!dev) { - err = -ENODEV; - goto out; - } + err = -ENODEV; + dev = dev_get_by_index_rcu(sock_net(sk), + sk->sk_bound_dev_if); + if (!dev) + goto out_unlock; } /* ipv4 addr of the socket is invalid. Only the @@ -289,20 +290,18 @@ static int rawv6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len) err = -EADDRNOTAVAIL; if (!ipv6_chk_addr(sock_net(sk), &addr->sin6_addr, dev, 0)) { - if (dev) - dev_put(dev); - goto out; + goto out_unlock; } } - if (dev) - dev_put(dev); } - inet->rcv_saddr = inet->saddr = v4addr; + inet->inet_rcv_saddr = inet->inet_saddr = v4addr; ipv6_addr_copy(&np->rcv_saddr, &addr->sin6_addr); if (!(addr_type & IPV6_ADDR_MULTICAST)) ipv6_addr_copy(&np->saddr, &addr->sin6_addr); err = 0; +out_unlock: + rcu_read_unlock(); out: release_sock(sk); return err; @@ -381,8 +380,7 @@ static inline int rawv6_rcv_skb(struct sock * sk, struct sk_buff * skb) } /* Charge it to the socket. */ - if (sock_queue_rcv_skb(sk,skb)<0) { - atomic_inc(&sk->sk_drops); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -416,14 +414,14 @@ int rawv6_rcv(struct sock *sk, struct sk_buff *skb) skb_network_header_len(skb)); if (!csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, - skb->len, inet->num, skb->csum)) + skb->len, inet->inet_num, skb->csum)) skb->ip_summed = CHECKSUM_UNNECESSARY; } if (!skb_csum_unnecessary(skb)) skb->csum = ~csum_unfold(csum_ipv6_magic(&ipv6_hdr(skb)->saddr, &ipv6_hdr(skb)->daddr, skb->len, - inet->num, 0)); + inet->inet_num, 0)); if (inet->hdrincl) { if (skb_checksum_complete(skb)) { @@ -497,7 +495,7 @@ static int rawv6_recvmsg(struct kiocb *iocb, struct sock *sk, sin6->sin6_scope_id = IP6CB(skb)->iif; } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); if (np->rxopt.all) datagram_recv_ctl(sk, msg, skb); @@ -518,7 +516,6 @@ csum_copy_err: as some normal condition. */ err = (flags&MSG_DONTWAIT) ? -EAGAIN : -EHOSTUNREACH; - atomic_inc(&sk->sk_drops); goto out; } @@ -766,8 +763,8 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, proto = ntohs(sin6->sin6_port); if (!proto) - proto = inet->num; - else if (proto != inet->num) + proto = inet->inet_num; + else if (proto != inet->inet_num) return(-EINVAL); if (proto > 255) @@ -800,7 +797,7 @@ static int rawv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - proto = inet->num; + proto = inet->inet_num; daddr = &np->daddr; fl.fl6_flowlabel = np->flow_label; } @@ -967,7 +964,7 @@ static int do_rawv6_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case IPV6_CHECKSUM: - if (inet_sk(sk)->num == IPPROTO_ICMPV6 && + if (inet_sk(sk)->inet_num == IPPROTO_ICMPV6 && level == IPPROTO_IPV6) { /* * RFC3542 tells that IPV6_CHECKSUM socket @@ -1007,7 +1004,7 @@ static int rawv6_setsockopt(struct sock *sk, int level, int optname, break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); @@ -1030,7 +1027,7 @@ static int compat_rawv6_setsockopt(struct sock *sk, int level, int optname, case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_seticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: @@ -1087,7 +1084,7 @@ static int rawv6_getsockopt(struct sock *sk, int level, int optname, break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); @@ -1110,7 +1107,7 @@ static int compat_rawv6_getsockopt(struct sock *sk, int level, int optname, case SOL_RAW: break; case SOL_ICMPV6: - if (inet_sk(sk)->num != IPPROTO_ICMPV6) + if (inet_sk(sk)->inet_num != IPPROTO_ICMPV6) return -EOPNOTSUPP; return rawv6_geticmpfilter(sk, level, optname, optval, optlen); case SOL_IPV6: @@ -1157,7 +1154,7 @@ static int rawv6_ioctl(struct sock *sk, int cmd, unsigned long arg) static void rawv6_close(struct sock *sk, long timeout) { - if (inet_sk(sk)->num == IPPROTO_RAW) + if (inet_sk(sk)->inet_num == IPPROTO_RAW) ip6_ra_control(sk, -1); ip6mr_sk_done(sk); sk_common_release(sk); @@ -1176,7 +1173,7 @@ static int rawv6_init_sk(struct sock *sk) { struct raw6_sock *rp = raw6_sk(sk); - switch (inet_sk(sk)->num) { + switch (inet_sk(sk)->inet_num) { case IPPROTO_ICMPV6: rp->checksum = 1; rp->offset = 2; @@ -1226,7 +1223,7 @@ static void raw6_sock_seq_show(struct seq_file *seq, struct sock *sp, int i) dest = &np->daddr; src = &np->rcv_saddr; destp = 0; - srcp = inet_sk(sp)->num; + srcp = inet_sk(sp)->inet_num; seq_printf(seq, "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", @@ -1338,7 +1335,6 @@ static struct inet_protosw rawv6_protosw = { .protocol = IPPROTO_IP, /* wild card */ .prot = &rawv6_prot, .ops = &inet6_sockraw_ops, - .capability = CAP_NET_RAW, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_REUSE, }; diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 2499e9712031..4d98549a6868 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -208,18 +208,17 @@ static void ip6_frag_expire(unsigned long data) fq_kill(fq); net = container_of(fq->q.net, struct net, ipv6.frags); - dev = dev_get_by_index(net, fq->iif); + rcu_read_lock(); + dev = dev_get_by_index_rcu(net, fq->iif); if (!dev) - goto out; + goto out_rcu_unlock; - rcu_read_lock(); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMTIMEOUT); IP6_INC_STATS_BH(net, __in6_dev_get(dev), IPSTATS_MIB_REASMFAILS); - rcu_read_unlock(); /* Don't send error if the first segment did not arrive. */ if (!(fq->q.last_in & INET_FRAG_FIRST_IN) || !fq->q.fragments) - goto out; + goto out_rcu_unlock; /* But use as source device on which LAST ARRIVED @@ -228,9 +227,9 @@ static void ip6_frag_expire(unsigned long data) */ fq->q.fragments->dev = dev; icmpv6_send(fq->q.fragments, ICMPV6_TIME_EXCEED, ICMPV6_EXC_FRAGTIME, 0, dev); +out_rcu_unlock: + rcu_read_unlock(); out: - if (dev) - dev_put(dev); spin_unlock(&fq->q.lock); fq_put(fq); } @@ -676,7 +675,7 @@ static int ip6_frags_ns_sysctl_register(struct net *net) struct ctl_table_header *hdr; table = ip6_frags_ns_ctl_table; - if (net != &init_net) { + if (!net_eq(net, &init_net)) { table = kmemdup(table, sizeof(ip6_frags_ns_ctl_table), GFP_KERNEL); if (table == NULL) goto err_alloc; @@ -694,7 +693,7 @@ static int ip6_frags_ns_sysctl_register(struct net *net) return 0; err_reg: - if (net != &init_net) + if (!net_eq(net, &init_net)) kfree(table); err_alloc: return -ENOMEM; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index 6aa202e26f97..db3b27303890 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -1471,9 +1471,10 @@ static struct rt6_info *ip6_route_redirect(struct in6_addr *dest, }, }, }, - .gateway = *gateway, }; + ipv6_addr_copy(&rdfl.gateway, gateway); + if (rt6_need_strict(dest)) flags |= RT6_LOOKUP_F_IFACE; diff --git a/net/ipv6/sit.c b/net/ipv6/sit.c index dbd19a78ca73..976e68244b99 100644 --- a/net/ipv6/sit.c +++ b/net/ipv6/sit.c @@ -66,7 +66,7 @@ static void ipip6_fb_tunnel_init(struct net_device *dev); static void ipip6_tunnel_init(struct net_device *dev); static void ipip6_tunnel_setup(struct net_device *dev); -static int sit_net_id; +static int sit_net_id __read_mostly; struct sit_net { struct ip_tunnel *tunnels_r_l[HASH_SIZE]; struct ip_tunnel *tunnels_r[HASH_SIZE]; @@ -77,8 +77,17 @@ struct sit_net { struct net_device *fb_tunnel_dev; }; -static DEFINE_RWLOCK(ipip6_lock); +/* + * Locking : hash tables are protected by RCU and a spinlock + */ +static DEFINE_SPINLOCK(ipip6_lock); + +#define for_each_ip_tunnel_rcu(start) \ + for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* + * Must be invoked with rcu_read_lock + */ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct net_device *dev, __be32 remote, __be32 local) { @@ -87,26 +96,26 @@ static struct ip_tunnel * ipip6_tunnel_lookup(struct net *net, struct ip_tunnel *t; struct sit_net *sitn = net_generic(net, sit_net_id); - for (t = sitn->tunnels_r_l[h0^h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_r_l[h0 ^ h1]) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for (t = sitn->tunnels_r[h0]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_r[h0]) { if (remote == t->parms.iph.daddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - for (t = sitn->tunnels_l[h1]; t; t = t->next) { + for_each_ip_tunnel_rcu(sitn->tunnels_l[h1]) { if (local == t->parms.iph.saddr && (!dev || !t->parms.link || dev->iflink == t->parms.link) && (t->dev->flags & IFF_UP)) return t; } - t = sitn->tunnels_wc[0]; + t = rcu_dereference(sitn->tunnels_wc[0]); if ((t != NULL) && (t->dev->flags & IFF_UP)) return t; return NULL; @@ -143,9 +152,9 @@ static void ipip6_tunnel_unlink(struct sit_net *sitn, struct ip_tunnel *t) for (tp = ipip6_bucket(sitn, t); *tp; tp = &(*tp)->next) { if (t == *tp) { - write_lock_bh(&ipip6_lock); + spin_lock_bh(&ipip6_lock); *tp = t->next; - write_unlock_bh(&ipip6_lock); + spin_unlock_bh(&ipip6_lock); break; } } @@ -155,10 +164,27 @@ static void ipip6_tunnel_link(struct sit_net *sitn, struct ip_tunnel *t) { struct ip_tunnel **tp = ipip6_bucket(sitn, t); + spin_lock_bh(&ipip6_lock); t->next = *tp; - write_lock_bh(&ipip6_lock); - *tp = t; - write_unlock_bh(&ipip6_lock); + rcu_assign_pointer(*tp, t); + spin_unlock_bh(&ipip6_lock); +} + +static void ipip6_tunnel_clone_6rd(struct net_device *dev, struct sit_net *sitn) +{ +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel *t = netdev_priv(dev); + + if (t->dev == sitn->fb_tunnel_dev) { + ipv6_addr_set(&t->ip6rd.prefix, htonl(0x20020000), 0, 0, 0); + t->ip6rd.relay_prefix = 0; + t->ip6rd.prefixlen = 16; + t->ip6rd.relay_prefixlen = 0; + } else { + struct ip_tunnel *t0 = netdev_priv(sitn->fb_tunnel_dev); + memcpy(&t->ip6rd, &t0->ip6rd, sizeof(t->ip6rd)); + } +#endif } static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, @@ -204,6 +230,7 @@ static struct ip_tunnel * ipip6_tunnel_locate(struct net *net, nt->parms = *parms; ipip6_tunnel_init(dev); + ipip6_tunnel_clone_6rd(dev, sitn); if (parms->i_flags & SIT_ISATAP) dev->priv_flags |= IFF_ISATAP; @@ -222,15 +249,22 @@ failed: return NULL; } +static DEFINE_SPINLOCK(ipip6_prl_lock); + +#define for_each_prl_rcu(start) \ + for (prl = rcu_dereference(start); \ + prl; \ + prl = rcu_dereference(prl->next)) + static struct ip_tunnel_prl_entry * __ipip6_tunnel_locate_prl(struct ip_tunnel *t, __be32 addr) { - struct ip_tunnel_prl_entry *p = (struct ip_tunnel_prl_entry *)NULL; + struct ip_tunnel_prl_entry *prl; - for (p = t->prl; p; p = p->next) - if (p->addr == addr) + for_each_prl_rcu(t->prl) + if (prl->addr == addr) break; - return p; + return prl; } @@ -255,7 +289,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, kcalloc(cmax, sizeof(*kp), GFP_KERNEL) : NULL; - read_lock(&ipip6_lock); + rcu_read_lock(); ca = t->prl_count < cmax ? t->prl_count : cmax; @@ -273,7 +307,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, } c = 0; - for (prl = t->prl; prl; prl = prl->next) { + for_each_prl_rcu(t->prl) { if (c >= cmax) break; if (kprl.addr != htonl(INADDR_ANY) && prl->addr != kprl.addr) @@ -285,7 +319,7 @@ static int ipip6_tunnel_get_prl(struct ip_tunnel *t, break; } out: - read_unlock(&ipip6_lock); + rcu_read_unlock(); len = sizeof(*kp) * c; ret = 0; @@ -306,12 +340,14 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) if (a->addr == htonl(INADDR_ANY)) return -EINVAL; - write_lock(&ipip6_lock); + spin_lock(&ipip6_prl_lock); for (p = t->prl; p; p = p->next) { if (p->addr == a->addr) { - if (chg) - goto update; + if (chg) { + p->flags = a->flags; + goto out; + } err = -EEXIST; goto out; } @@ -328,46 +364,63 @@ ipip6_tunnel_add_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a, int chg) goto out; } + INIT_RCU_HEAD(&p->rcu_head); p->next = t->prl; - t->prl = p; - t->prl_count++; -update: p->addr = a->addr; p->flags = a->flags; + t->prl_count++; + rcu_assign_pointer(t->prl, p); out: - write_unlock(&ipip6_lock); + spin_unlock(&ipip6_prl_lock); return err; } +static void prl_entry_destroy_rcu(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_tunnel_prl_entry, rcu_head)); +} + +static void prl_list_destroy_rcu(struct rcu_head *head) +{ + struct ip_tunnel_prl_entry *p, *n; + + p = container_of(head, struct ip_tunnel_prl_entry, rcu_head); + do { + n = p->next; + kfree(p); + p = n; + } while (p); +} + static int ipip6_tunnel_del_prl(struct ip_tunnel *t, struct ip_tunnel_prl *a) { struct ip_tunnel_prl_entry *x, **p; int err = 0; - write_lock(&ipip6_lock); + spin_lock(&ipip6_prl_lock); if (a && a->addr != htonl(INADDR_ANY)) { for (p = &t->prl; *p; p = &(*p)->next) { if ((*p)->addr == a->addr) { x = *p; *p = x->next; - kfree(x); + call_rcu(&x->rcu_head, prl_entry_destroy_rcu); t->prl_count--; goto out; } } err = -ENXIO; } else { - while (t->prl) { + if (t->prl) { + t->prl_count = 0; x = t->prl; - t->prl = t->prl->next; - kfree(x); - t->prl_count--; + call_rcu(&x->rcu_head, prl_list_destroy_rcu); + t->prl = NULL; } } out: - write_unlock(&ipip6_lock); + spin_unlock(&ipip6_prl_lock); return err; } @@ -377,7 +430,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) struct ip_tunnel_prl_entry *p; int ok = 1; - read_lock(&ipip6_lock); + rcu_read_lock(); p = __ipip6_tunnel_locate_prl(t, iph->saddr); if (p) { if (p->flags & PRL_DEFAULT) @@ -393,7 +446,7 @@ isatap_chksrc(struct sk_buff *skb, struct iphdr *iph, struct ip_tunnel *t) else ok = 0; } - read_unlock(&ipip6_lock); + rcu_read_unlock(); return ok; } @@ -403,9 +456,9 @@ static void ipip6_tunnel_uninit(struct net_device *dev) struct sit_net *sitn = net_generic(net, sit_net_id); if (dev == sitn->fb_tunnel_dev) { - write_lock_bh(&ipip6_lock); + spin_lock_bh(&ipip6_lock); sitn->tunnels_wc[0] = NULL; - write_unlock_bh(&ipip6_lock); + spin_unlock_bh(&ipip6_lock); dev_put(dev); } else { ipip6_tunnel_unlink(sitn, netdev_priv(dev)); @@ -458,7 +511,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) err = -ENOENT; - read_lock(&ipip6_lock); + rcu_read_lock(); t = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->daddr, @@ -476,7 +529,7 @@ static int ipip6_err(struct sk_buff *skb, u32 info) t->err_count = 1; t->err_time = jiffies; out: - read_unlock(&ipip6_lock); + rcu_read_unlock(); return err; } @@ -496,7 +549,7 @@ static int ipip6_rcv(struct sk_buff *skb) iph = ip_hdr(skb); - read_lock(&ipip6_lock); + rcu_read_lock(); tunnel = ipip6_tunnel_lookup(dev_net(skb->dev), skb->dev, iph->saddr, iph->daddr); if (tunnel != NULL) { @@ -510,7 +563,7 @@ static int ipip6_rcv(struct sk_buff *skb) if ((tunnel->dev->priv_flags & IFF_ISATAP) && !isatap_chksrc(skb, iph, tunnel)) { tunnel->dev->stats.rx_errors++; - read_unlock(&ipip6_lock); + rcu_read_unlock(); kfree_skb(skb); return 0; } @@ -521,28 +574,52 @@ static int ipip6_rcv(struct sk_buff *skb) nf_reset(skb); ipip6_ecn_decapsulate(iph, skb); netif_rx(skb); - read_unlock(&ipip6_lock); + rcu_read_unlock(); return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); - read_unlock(&ipip6_lock); + rcu_read_unlock(); out: kfree_skb(skb); return 0; } -/* Returns the embedded IPv4 address if the IPv6 address - comes from 6to4 (RFC 3056) addr space */ - -static inline __be32 try_6to4(struct in6_addr *v6dst) +/* + * Returns the embedded IPv4 address if the IPv6 address + * comes from 6rd / 6to4 (RFC 3056) addr space. + */ +static inline +__be32 try_6rd(struct in6_addr *v6dst, struct ip_tunnel *tunnel) { __be32 dst = 0; +#ifdef CONFIG_IPV6_SIT_6RD + if (ipv6_prefix_equal(v6dst, &tunnel->ip6rd.prefix, + tunnel->ip6rd.prefixlen)) { + unsigned pbw0, pbi0; + int pbi1; + u32 d; + + pbw0 = tunnel->ip6rd.prefixlen >> 5; + pbi0 = tunnel->ip6rd.prefixlen & 0x1f; + + d = (ntohl(v6dst->s6_addr32[pbw0]) << pbi0) >> + tunnel->ip6rd.relay_prefixlen; + + pbi1 = pbi0 - tunnel->ip6rd.relay_prefixlen; + if (pbi1 > 0) + d |= ntohl(v6dst->s6_addr32[pbw0 + 1]) >> + (32 - pbi1); + + dst = tunnel->ip6rd.relay_prefix | htonl(d); + } +#else if (v6dst->s6_addr16[0] == htons(0x2002)) { /* 6to4 v6 addr has 16 bits prefix, 32 v4addr, 16 SLA, ... */ memcpy(&dst, &v6dst->s6_addr16[1], 4); } +#endif return dst; } @@ -555,10 +632,12 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &tunnel->dev->stats; + struct net_device_stats *stats = &dev->stats; + struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); struct iphdr *tiph = &tunnel->parms.iph; struct ipv6hdr *iph6 = ipv6_hdr(skb); u8 tos = tunnel->parms.iph.tos; + __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ @@ -595,7 +674,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, } if (!dst) - dst = try_6to4(&iph6->daddr); + dst = try_6rd(&iph6->daddr, tunnel); if (!dst) { struct neighbour *neigh = NULL; @@ -648,25 +727,28 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, goto tx_error; } - if (tiph->frag_off) + if (df) { mtu = dst_mtu(&rt->u.dst) - sizeof(struct iphdr); - else - mtu = skb_dst(skb) ? dst_mtu(skb_dst(skb)) : dev->mtu; - if (mtu < 68) { - stats->collisions++; - ip_rt_put(rt); - goto tx_error; - } - if (mtu < IPV6_MIN_MTU) - mtu = IPV6_MIN_MTU; - if (tunnel->parms.iph.daddr && skb_dst(skb)) - skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + if (mtu < 68) { + stats->collisions++; + ip_rt_put(rt); + goto tx_error; + } - if (skb->len > mtu) { - icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); - ip_rt_put(rt); - goto tx_error; + if (mtu < IPV6_MIN_MTU) { + mtu = IPV6_MIN_MTU; + df = 0; + } + + if (tunnel->parms.iph.daddr && skb_dst(skb)) + skb_dst(skb)->ops->update_pmtu(skb_dst(skb), mtu); + + if (skb->len > mtu) { + icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu, dev); + ip_rt_put(rt); + goto tx_error; + } } if (tunnel->err_count > 0) { @@ -688,7 +770,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - stats->tx_dropped++; + txq->tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -714,11 +796,7 @@ static netdev_tx_t ipip6_tunnel_xmit(struct sk_buff *skb, iph = ip_hdr(skb); iph->version = 4; iph->ihl = sizeof(struct iphdr)>>2; - if (mtu > IPV6_MIN_MTU) - iph->frag_off = tiph->frag_off; - else - iph->frag_off = 0; - + iph->frag_off = df; iph->protocol = IPPROTO_IPV6; iph->tos = INET_ECN_encapsulate(tos, ipv6_get_dsfield(iph6)); iph->daddr = rt->rt_dst; @@ -785,9 +863,15 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) struct ip_tunnel *t; struct net *net = dev_net(dev); struct sit_net *sitn = net_generic(net, sit_net_id); +#ifdef CONFIG_IPV6_SIT_6RD + struct ip_tunnel_6rd ip6rd; +#endif switch (cmd) { case SIOCGETTUNNEL: +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCGET6RD: +#endif t = NULL; if (dev == sitn->fb_tunnel_dev) { if (copy_from_user(&p, ifr->ifr_ifru.ifru_data, sizeof(p))) { @@ -798,9 +882,25 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) } if (t == NULL) t = netdev_priv(dev); - memcpy(&p, &t->parms, sizeof(p)); - if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, sizeof(p))) - err = -EFAULT; + + err = -EFAULT; + if (cmd == SIOCGETTUNNEL) { + memcpy(&p, &t->parms, sizeof(p)); + if (copy_to_user(ifr->ifr_ifru.ifru_data, &p, + sizeof(p))) + goto done; +#ifdef CONFIG_IPV6_SIT_6RD + } else { + ipv6_addr_copy(&ip6rd.prefix, &t->ip6rd.prefix); + ip6rd.relay_prefix = t->ip6rd.relay_prefix; + ip6rd.prefixlen = t->ip6rd.prefixlen; + ip6rd.relay_prefixlen = t->ip6rd.relay_prefixlen; + if (copy_to_user(ifr->ifr_ifru.ifru_data, &ip6rd, + sizeof(ip6rd))) + goto done; +#endif + } + err = 0; break; case SIOCADDTUNNEL: @@ -921,6 +1021,54 @@ ipip6_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) netdev_state_change(dev); break; +#ifdef CONFIG_IPV6_SIT_6RD + case SIOCADD6RD: + case SIOCCHG6RD: + case SIOCDEL6RD: + err = -EPERM; + if (!capable(CAP_NET_ADMIN)) + goto done; + + err = -EFAULT; + if (copy_from_user(&ip6rd, ifr->ifr_ifru.ifru_data, + sizeof(ip6rd))) + goto done; + + t = netdev_priv(dev); + + if (cmd != SIOCDEL6RD) { + struct in6_addr prefix; + __be32 relay_prefix; + + err = -EINVAL; + if (ip6rd.relay_prefixlen > 32 || + ip6rd.prefixlen + (32 - ip6rd.relay_prefixlen) > 64) + goto done; + + ipv6_addr_prefix(&prefix, &ip6rd.prefix, + ip6rd.prefixlen); + if (!ipv6_addr_equal(&prefix, &ip6rd.prefix)) + goto done; + if (ip6rd.relay_prefixlen) + relay_prefix = ip6rd.relay_prefix & + htonl(0xffffffffUL << + (32 - ip6rd.relay_prefixlen)); + else + relay_prefix = 0; + if (relay_prefix != ip6rd.relay_prefix) + goto done; + + ipv6_addr_copy(&t->ip6rd.prefix, &prefix); + t->ip6rd.relay_prefix = relay_prefix; + t->ip6rd.prefixlen = ip6rd.prefixlen; + t->ip6rd.relay_prefixlen = ip6rd.relay_prefixlen; + } else + ipip6_tunnel_clone_6rd(dev, sitn); + + err = 0; + break; +#endif + default: err = -EINVAL; } @@ -997,33 +1145,27 @@ static struct xfrm_tunnel sit_handler = { .priority = 1, }; -static void sit_destroy_tunnels(struct sit_net *sitn) +static void sit_destroy_tunnels(struct sit_net *sitn, struct list_head *head) { int prio; for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t; - while ((t = sitn->tunnels[prio][h]) != NULL) - unregister_netdevice(t->dev); + struct ip_tunnel *t = sitn->tunnels[prio][h]; + + while (t != NULL) { + unregister_netdevice_queue(t->dev, head); + t = t->next; + } } } } static int sit_init_net(struct net *net) { + struct sit_net *sitn = net_generic(net, sit_net_id); int err; - struct sit_net *sitn; - - err = -ENOMEM; - sitn = kzalloc(sizeof(struct sit_net), GFP_KERNEL); - if (sitn == NULL) - goto err_alloc; - - err = net_assign_generic(net, sit_net_id, sitn); - if (err < 0) - goto err_assign; sitn->tunnels[0] = sitn->tunnels_wc; sitn->tunnels[1] = sitn->tunnels_l; @@ -1039,6 +1181,7 @@ static int sit_init_net(struct net *net) dev_net_set(sitn->fb_tunnel_dev, net); ipip6_fb_tunnel_init(sitn->fb_tunnel_dev); + ipip6_tunnel_clone_6rd(sitn->fb_tunnel_dev, sitn); if ((err = register_netdev(sitn->fb_tunnel_dev))) goto err_reg_dev; @@ -1049,35 +1192,34 @@ err_reg_dev: dev_put(sitn->fb_tunnel_dev); free_netdev(sitn->fb_tunnel_dev); err_alloc_dev: - /* nothing */ -err_assign: - kfree(sitn); -err_alloc: return err; } static void sit_exit_net(struct net *net) { - struct sit_net *sitn; + struct sit_net *sitn = net_generic(net, sit_net_id); + LIST_HEAD(list); - sitn = net_generic(net, sit_net_id); rtnl_lock(); - sit_destroy_tunnels(sitn); - unregister_netdevice(sitn->fb_tunnel_dev); + sit_destroy_tunnels(sitn, &list); + unregister_netdevice_queue(sitn->fb_tunnel_dev, &list); + unregister_netdevice_many(&list); rtnl_unlock(); - kfree(sitn); } static struct pernet_operations sit_net_ops = { .init = sit_init_net, .exit = sit_exit_net, + .id = &sit_net_id, + .size = sizeof(struct sit_net), }; static void __exit sit_cleanup(void) { xfrm4_tunnel_deregister(&sit_handler, AF_INET6); - unregister_pernet_gen_device(sit_net_id, &sit_net_ops); + unregister_pernet_device(&sit_net_ops); + rcu_barrier(); /* Wait for completion of call_rcu()'s */ } static int __init sit_init(void) @@ -1091,7 +1233,7 @@ static int __init sit_init(void) return -EAGAIN; } - err = register_pernet_gen_device(&sit_net_id, &sit_net_ops); + err = register_pernet_device(&sit_net_ops); if (err < 0) xfrm4_tunnel_deregister(&sit_handler, AF_INET6); diff --git a/net/ipv6/syncookies.c b/net/ipv6/syncookies.c index 6b6ae913b5d4..5b9af508b8f2 100644 --- a/net/ipv6/syncookies.c +++ b/net/ipv6/syncookies.c @@ -159,6 +159,8 @@ static inline int cookie_check(struct sk_buff *skb, __u32 cookie) struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) { + struct tcp_options_received tcp_opt; + u8 *hash_location; struct inet_request_sock *ireq; struct inet6_request_sock *ireq6; struct tcp_request_sock *treq; @@ -171,7 +173,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) int mss; struct dst_entry *dst; __u8 rcv_wscale; - struct tcp_options_received tcp_opt; if (!sysctl_tcp_syncookies || !th->ack) goto out; @@ -184,13 +185,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SYNCOOKIESRECV); - /* check for timestamp cookie support */ - memset(&tcp_opt, 0, sizeof(tcp_opt)); - tcp_parse_options(skb, &tcp_opt, 0); - - if (tcp_opt.saw_tstamp) - cookie_check_timestamp(&tcp_opt); - ret = NULL; req = inet6_reqsk_alloc(&tcp6_request_sock_ops); if (!req) @@ -224,12 +218,6 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) req->expires = 0UL; req->retrans = 0; ireq->ecn_ok = 0; - ireq->snd_wscale = tcp_opt.snd_wscale; - ireq->rcv_wscale = tcp_opt.rcv_wscale; - ireq->sack_ok = tcp_opt.sack_ok; - ireq->wscale_ok = tcp_opt.wscale_ok; - ireq->tstamp_ok = tcp_opt.saw_tstamp; - req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; treq->rcv_isn = ntohl(th->seq) - 1; treq->snt_isn = cookie; @@ -252,8 +240,9 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) } ipv6_addr_copy(&fl.fl6_src, &ireq6->loc_addr); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; - fl.fl_ip_sport = inet_sk(sk)->sport; + fl.fl_ip_sport = inet_sk(sk)->inet_sport; security_req_classify_flow(req, &fl); if (ip6_dst_lookup(sk, &dst, &fl)) goto out_free; @@ -264,6 +253,21 @@ struct sock *cookie_v6_check(struct sock *sk, struct sk_buff *skb) goto out_free; } + /* check for timestamp cookie support */ + memset(&tcp_opt, 0, sizeof(tcp_opt)); + tcp_parse_options(skb, &tcp_opt, &hash_location, 0, dst); + + if (tcp_opt.saw_tstamp) + cookie_check_timestamp(&tcp_opt); + + req->ts_recent = tcp_opt.saw_tstamp ? tcp_opt.rcv_tsval : 0; + + ireq->snd_wscale = tcp_opt.snd_wscale; + ireq->rcv_wscale = tcp_opt.rcv_wscale; + ireq->sack_ok = tcp_opt.sack_ok; + ireq->wscale_ok = tcp_opt.wscale_ok; + ireq->tstamp_ok = tcp_opt.saw_tstamp; + req->window_clamp = tp->window_clamp ? :dst_metric(dst, RTAX_WINDOW); tcp_select_initial_window(tcp_full_space(sk), req->mss, &req->rcv_wnd, &req->window_clamp, diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 21d100b68b19..aadd7cef73b3 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -226,10 +226,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, #endif goto failure; } else { - ipv6_addr_set(&np->saddr, 0, 0, htonl(0x0000FFFF), - inet->saddr); - ipv6_addr_set(&np->rcv_saddr, 0, 0, htonl(0x0000FFFF), - inet->rcv_saddr); + ipv6_addr_set_v4mapped(inet->inet_saddr, &np->saddr); + ipv6_addr_set_v4mapped(inet->inet_rcv_saddr, + &np->rcv_saddr); } return err; @@ -243,8 +242,9 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, ipv6_addr_copy(&fl.fl6_src, (saddr ? saddr : &np->saddr)); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = usin->sin6_port; - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; if (np->opt && np->opt->srcrt) { struct rt0_hdr *rt0 = (struct rt0_hdr *)np->opt->srcrt; @@ -276,7 +276,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, /* set the source address */ ipv6_addr_copy(&np->saddr, saddr); - inet->rcv_saddr = LOOPBACK4_IPV6; + inet->inet_rcv_saddr = LOOPBACK4_IPV6; sk->sk_gso_type = SKB_GSO_TCPV6; __ip6_dst_store(sk, dst, NULL, NULL); @@ -288,7 +288,7 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, tp->rx_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); - inet->dport = usin->sin6_port; + inet->inet_dport = usin->sin6_port; tcp_set_state(sk, TCP_SYN_SENT); err = inet6_hash_connect(&tcp_death_row, sk); @@ -298,8 +298,8 @@ static int tcp_v6_connect(struct sock *sk, struct sockaddr *uaddr, if (!tp->write_seq) tp->write_seq = secure_tcpv6_sequence_number(np->saddr.s6_addr32, np->daddr.s6_addr32, - inet->sport, - inet->dport); + inet->inet_sport, + inet->inet_dport); err = tcp_connect(sk); if (err) @@ -311,7 +311,7 @@ late_failure: tcp_set_state(sk, TCP_CLOSE); __sk_dst_reset(sk); failure: - inet->dport = 0; + inet->inet_dport = 0; sk->sk_route_caps = 0; return err; } @@ -383,8 +383,9 @@ static void tcp_v6_err(struct sk_buff *skb, struct inet6_skb_parm *opt, ipv6_addr_copy(&fl.fl6_dst, &np->daddr); ipv6_addr_copy(&fl.fl6_src, &np->saddr); fl.oif = sk->sk_bound_dev_if; - fl.fl_ip_dport = inet->dport; - fl.fl_ip_sport = inet->sport; + fl.mark = sk->sk_mark; + fl.fl_ip_dport = inet->inet_dport; + fl.fl_ip_sport = inet->inet_sport; security_skb_classify_flow(skb, &fl); if ((err = ip6_dst_lookup(sk, &dst, &fl))) { @@ -460,7 +461,8 @@ out: } -static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) +static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req, + struct request_values *rvp) { struct inet6_request_sock *treq = inet6_rsk(req); struct ipv6_pinfo *np = inet6_sk(sk); @@ -477,6 +479,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.fl6_flowlabel = 0; fl.oif = treq->iif; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, &fl); @@ -497,7 +500,7 @@ static int tcp_v6_send_synack(struct sock *sk, struct request_sock *req) if ((err = xfrm_lookup(sock_net(sk), &dst, &fl, sk, 0)) < 0) goto done; - skb = tcp_make_synack(sk, dst, req); + skb = tcp_make_synack(sk, dst, req, rvp); if (skb) { struct tcphdr *th = tcp_hdr(skb); @@ -1159,11 +1162,14 @@ static struct sock *tcp_v6_hnd_req(struct sock *sk,struct sk_buff *skb) */ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) { + struct tcp_extend_values tmp_ext; + struct tcp_options_received tmp_opt; + u8 *hash_location; + struct request_sock *req; struct inet6_request_sock *treq; struct ipv6_pinfo *np = inet6_sk(sk); - struct tcp_options_received tmp_opt; struct tcp_sock *tp = tcp_sk(sk); - struct request_sock *req = NULL; + struct dst_entry *dst = __sk_dst_get(sk); __u32 isn = TCP_SKB_CB(skb)->when; #ifdef CONFIG_SYN_COOKIES int want_cookie = 0; @@ -1202,8 +1208,52 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) tcp_clear_options(&tmp_opt); tmp_opt.mss_clamp = IPV6_MIN_MTU - sizeof(struct tcphdr) - sizeof(struct ipv6hdr); tmp_opt.user_mss = tp->rx_opt.user_mss; + tcp_parse_options(skb, &tmp_opt, &hash_location, 0, dst); + + if (tmp_opt.cookie_plus > 0 && + tmp_opt.saw_tstamp && + !tp->rx_opt.cookie_out_never && + (sysctl_tcp_cookie_size > 0 || + (tp->cookie_values != NULL && + tp->cookie_values->cookie_desired > 0))) { + u8 *c; + u32 *d; + u32 *mess = &tmp_ext.cookie_bakery[COOKIE_DIGEST_WORDS]; + int l = tmp_opt.cookie_plus - TCPOLEN_COOKIE_BASE; + + if (tcp_cookie_generator(&tmp_ext.cookie_bakery[0]) != 0) + goto drop_and_free; + + /* Secret recipe starts with IP addresses */ + d = &ipv6_hdr(skb)->daddr.s6_addr32[0]; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + d = &ipv6_hdr(skb)->saddr.s6_addr32[0]; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + *mess++ ^= *d++; + + /* plus variable length Initiator Cookie */ + c = (u8 *)mess; + while (l-- > 0) + *c++ ^= *hash_location++; - tcp_parse_options(skb, &tmp_opt, 0); +#ifdef CONFIG_SYN_COOKIES + want_cookie = 0; /* not our kind of cookie */ +#endif + tmp_ext.cookie_out_never = 0; /* false */ + tmp_ext.cookie_plus = tmp_opt.cookie_plus; + } else if (!tp->rx_opt.cookie_in_always) { + /* redundant indications, but ensure initialization. */ + tmp_ext.cookie_out_never = 1; /* true */ + tmp_ext.cookie_plus = 0; + } else { + goto drop_and_free; + } + tmp_ext.cookie_in_always = tp->rx_opt.cookie_in_always; if (want_cookie && !tmp_opt.saw_tstamp) tcp_clear_options(&tmp_opt); @@ -1236,23 +1286,21 @@ static int tcp_v6_conn_request(struct sock *sk, struct sk_buff *skb) isn = tcp_v6_init_sequence(skb); } - tcp_rsk(req)->snt_isn = isn; security_inet_conn_request(sk, skb, req); - if (tcp_v6_send_synack(sk, req)) - goto drop; + if (tcp_v6_send_synack(sk, req, + (struct request_values *)&tmp_ext) || + want_cookie) + goto drop_and_free; - if (!want_cookie) { - inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); - return 0; - } + inet6_csk_reqsk_queue_hash_add(sk, req, TCP_TIMEOUT_INIT); + return 0; +drop_and_free: + reqsk_free(req); drop: - if (req) - reqsk_free(req); - return 0; /* don't send reset */ } @@ -1290,11 +1338,9 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, memcpy(newnp, np, sizeof(struct ipv6_pinfo)); - ipv6_addr_set(&newnp->daddr, 0, 0, htonl(0x0000FFFF), - newinet->daddr); + ipv6_addr_set_v4mapped(newinet->inet_daddr, &newnp->daddr); - ipv6_addr_set(&newnp->saddr, 0, 0, htonl(0x0000FFFF), - newinet->saddr); + ipv6_addr_set_v4mapped(newinet->inet_saddr, &newnp->saddr); ipv6_addr_copy(&newnp->rcv_saddr, &newnp->saddr); @@ -1345,6 +1391,7 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } ipv6_addr_copy(&fl.fl6_src, &treq->loc_addr); fl.oif = sk->sk_bound_dev_if; + fl.mark = sk->sk_mark; fl.fl_ip_dport = inet_rsk(req)->rmt_port; fl.fl_ip_sport = inet_rsk(req)->loc_port; security_req_classify_flow(req, &fl); @@ -1431,7 +1478,8 @@ static struct sock * tcp_v6_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newtp->advmss = dst_metric(dst, RTAX_ADVMSS); tcp_initialize_rcv_mss(newsk); - newinet->daddr = newinet->saddr = newinet->rcv_saddr = LOOPBACK4_IPV6; + newinet->inet_daddr = newinet->inet_saddr = LOOPBACK4_IPV6; + newinet->inet_rcv_saddr = LOOPBACK4_IPV6; #ifdef CONFIG_TCP_MD5SIG /* Copy over the MD5 key from the original socket */ @@ -1848,7 +1896,7 @@ static int tcp_v6_init_sock(struct sock *sk) */ tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_clamp = ~0; - tp->mss_cache = 536; + tp->mss_cache = TCP_MSS_DEFAULT; tp->reordering = sysctl_tcp_reordering; @@ -1864,6 +1912,19 @@ static int tcp_v6_init_sock(struct sock *sk) tp->af_specific = &tcp_sock_ipv6_specific; #endif + /* TCP Cookie Transactions */ + if (sysctl_tcp_cookie_size > 0) { + /* Default, cookies without s_data_payload. */ + tp->cookie_values = + kzalloc(sizeof(*tp->cookie_values), + sk->sk_allocation); + if (tp->cookie_values != NULL) + kref_init(&tp->cookie_values->kref); + } + /* Presumed zeroed, in order of appearance: + * cookie_in_always, cookie_out_never, + * s_data_constant, s_data_in, s_data_out + */ sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; @@ -1931,8 +1992,8 @@ static void get_tcp6_sock(struct seq_file *seq, struct sock *sp, int i) dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); if (icsk->icsk_pending == ICSK_TIME_RETRANS) { timer_active = 1; @@ -2109,7 +2170,6 @@ static struct inet_protosw tcpv6_protosw = { .protocol = IPPROTO_TCP, .prot = &tcpv6_prot, .ops = &inet6_stream_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT | INET_PROTOSW_ICSK, @@ -2124,12 +2184,17 @@ static int tcpv6_net_init(struct net *net) static void tcpv6_net_exit(struct net *net) { inet_ctl_sock_destroy(net->ipv6.tcp_sk); - inet_twsk_purge(net, &tcp_hashinfo, &tcp_death_row, AF_INET6); +} + +static void tcpv6_net_exit_batch(struct list_head *net_exit_list) +{ + inet_twsk_purge(&tcp_hashinfo, &tcp_death_row, AF_INET6); } static struct pernet_operations tcpv6_net_ops = { - .init = tcpv6_net_init, - .exit = tcpv6_net_exit, + .init = tcpv6_net_init, + .exit = tcpv6_net_exit, + .exit_batch = tcpv6_net_exit_batch, }; int __init tcpv6_init(void) diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index cf538ed5ef6a..69ebdbe78c47 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -53,7 +53,7 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) { const struct in6_addr *sk_rcv_saddr6 = &inet6_sk(sk)->rcv_saddr; const struct in6_addr *sk2_rcv_saddr6 = inet6_rcv_saddr(sk2); - __be32 sk_rcv_saddr = inet_sk(sk)->rcv_saddr; + __be32 sk1_rcv_saddr = inet_sk(sk)->inet_rcv_saddr; __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); int sk_ipv6only = ipv6_only_sock(sk); int sk2_ipv6only = inet_v6_ipv6only(sk2); @@ -63,8 +63,8 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) /* if both are mapped, treat as IPv4 */ if (addr_type == IPV6_ADDR_MAPPED && addr_type2 == IPV6_ADDR_MAPPED) return (!sk2_ipv6only && - (!sk_rcv_saddr || !sk2_rcv_saddr || - sk_rcv_saddr == sk2_rcv_saddr)); + (!sk1_rcv_saddr || !sk2_rcv_saddr || + sk1_rcv_saddr == sk2_rcv_saddr)); if (addr_type2 == IPV6_ADDR_ANY && !(sk2_ipv6only && addr_type == IPV6_ADDR_MAPPED)) @@ -81,9 +81,33 @@ int ipv6_rcv_saddr_equal(const struct sock *sk, const struct sock *sk2) return 0; } +static unsigned int udp6_portaddr_hash(struct net *net, + const struct in6_addr *addr6, + unsigned int port) +{ + unsigned int hash, mix = net_hash_mix(net); + + if (ipv6_addr_any(addr6)) + hash = jhash_1word(0, mix); + else if (ipv6_addr_v4mapped(addr6)) + hash = jhash_1word(addr6->s6_addr32[3], mix); + else + hash = jhash2(addr6->s6_addr32, 4, mix); + + return hash ^ port; +} + + int udp_v6_get_port(struct sock *sk, unsigned short snum) { - return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal); + unsigned int hash2_nulladdr = + udp6_portaddr_hash(sock_net(sk), &in6addr_any, snum); + unsigned int hash2_partial = + udp6_portaddr_hash(sock_net(sk), &inet6_sk(sk)->rcv_saddr, 0); + + /* precompute partial secondary hash */ + udp_sk(sk)->udp_portaddr_hash = hash2_partial; + return udp_lib_get_port(sk, snum, ipv6_rcv_saddr_equal, hash2_nulladdr); } static inline int compute_score(struct sock *sk, struct net *net, @@ -94,14 +118,14 @@ static inline int compute_score(struct sock *sk, struct net *net, { int score = -1; - if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && sk->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet_sock *inet = inet_sk(sk); score = 0; - if (inet->dport) { - if (inet->dport != sport) + if (inet->inet_dport) { + if (inet->inet_dport != sport) return -1; score++; } @@ -124,6 +148,86 @@ static inline int compute_score(struct sock *sk, struct net *net, return score; } +#define SCORE2_MAX (1 + 1 + 1) +static inline int compute_score2(struct sock *sk, struct net *net, + const struct in6_addr *saddr, __be16 sport, + const struct in6_addr *daddr, unsigned short hnum, + int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && + sk->sk_family == PF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + struct inet_sock *inet = inet_sk(sk); + + if (!ipv6_addr_equal(&np->rcv_saddr, daddr)) + return -1; + score = 0; + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score++; + } + if (!ipv6_addr_any(&np->daddr)) { + if (!ipv6_addr_equal(&np->daddr, saddr)) + return -1; + score++; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score++; + } + } + return score; +} + + +/* called with read_rcu_lock() */ +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 sock *sk, *result; + struct hlist_nulls_node *node; + int score, badness; + +begin: + result = NULL; + badness = -1; + udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + score = compute_score2(sk, net, saddr, sport, + daddr, hnum, dif); + if (score > badness) { + result = sk; + badness = score; + if (score == SCORE2_MAX) + goto exact_match; + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot2) + goto begin; + + if (result) { +exact_match: + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score2(result, net, saddr, sport, + daddr, hnum, dif) < badness)) { + sock_put(result); + goto begin; + } + } + return result; +} + static struct sock *__udp6_lib_lookup(struct net *net, struct in6_addr *saddr, __be16 sport, struct in6_addr *daddr, __be16 dport, @@ -132,11 +236,35 @@ static struct sock *__udp6_lib_lookup(struct net *net, struct sock *sk, *result; struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - unsigned int hash = udp_hashfn(net, hnum); - struct udp_hslot *hslot = &udptable->hash[hash]; + unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; int score, badness; rcu_read_lock(); + if (hslot->count > 10) { + hash2 = udp6_portaddr_hash(net, daddr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp6_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, + hslot2, slot2); + if (!result) { + hash2 = udp6_portaddr_hash(net, &in6addr_any, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp6_lib_lookup2(net, &in6addr_any, sport, + daddr, hnum, dif, + hslot2, slot2); + } + rcu_read_unlock(); + return result; + } begin: result = NULL; badness = -1; @@ -152,7 +280,7 @@ begin: * not the expected one, we must restart lookup. * We probably met an item that was moved to another chain. */ - if (get_nulls_value(node) != hash) + if (get_nulls_value(node) != slot) goto begin; if (result) { @@ -252,7 +380,7 @@ try_again: UDP_MIB_INDATAGRAMS, is_udplite); } - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ if (msg->msg_name) { @@ -265,8 +393,8 @@ try_again: sin6->sin6_scope_id = 0; if (is_udp4) - ipv6_addr_set(&sin6->sin6_addr, 0, 0, - htonl(0xffff), ip_hdr(skb)->saddr); + ipv6_addr_set_v4mapped(ip_hdr(skb)->saddr, + &sin6->sin6_addr); else { ipv6_addr_copy(&sin6->sin6_addr, &ipv6_hdr(skb)->saddr); @@ -383,18 +511,18 @@ int udpv6_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; } - if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { + if ((rc = sock_queue_rcv_skb(sk, skb)) < 0) { /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) { + if (rc == -ENOMEM) UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - } - goto drop; + goto drop_no_sk_drops_inc; } return 0; drop: + atomic_inc(&sk->sk_drops); +drop_no_sk_drops_inc: UDP6_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); kfree_skb(skb); return -1; @@ -415,10 +543,11 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, if (!net_eq(sock_net(s), net)) continue; - if (s->sk_hash == num && s->sk_family == PF_INET6) { + if (udp_sk(s)->udp_port_hash == num && + s->sk_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(s); - if (inet->dport) { - if (inet->dport != rmt_port) + if (inet->inet_dport) { + if (inet->inet_dport != rmt_port) continue; } if (!ipv6_addr_any(&np->daddr) && @@ -440,6 +569,33 @@ static struct sock *udp_v6_mcast_next(struct net *net, struct sock *sk, return NULL; } +static void flush_stack(struct sock **stack, unsigned int count, + struct sk_buff *skb, unsigned int final) +{ + unsigned int i; + struct sock *sk; + struct sk_buff *skb1; + + for (i = 0; i < count; i++) { + skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); + + sk = stack[i]; + if (skb1) { + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) + udpv6_queue_rcv_skb(sk, skb1); + else + sk_add_backlog(sk, skb1); + bh_unlock_sock(sk); + } else { + atomic_inc(&sk->sk_drops); + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_RCVBUFERRORS, IS_UDPLITE(sk)); + UDP6_INC_STATS_BH(sock_net(sk), + UDP_MIB_INERRORS, IS_UDPLITE(sk)); + } + } +} /* * Note: called only from the BH handler context, * so we don't need to lock the hashes. @@ -448,41 +604,43 @@ static int __udp6_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct in6_addr *saddr, struct in6_addr *daddr, struct udp_table *udptable) { - struct sock *sk, *sk2; + struct sock *sk, *stack[256 / sizeof(struct sock *)]; const struct udphdr *uh = udp_hdr(skb); - struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; + unsigned int i, count = 0; spin_lock(&hslot->lock); sk = sk_nulls_head(&hslot->head); dif = inet6_iif(skb); sk = udp_v6_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - if (!sk) { - kfree_skb(skb); - goto out; - } - - sk2 = sk; - while ((sk2 = udp_v6_mcast_next(net, sk_nulls_next(sk2), uh->dest, daddr, - uh->source, saddr, dif))) { - struct sk_buff *buff = skb_clone(skb, GFP_ATOMIC); - if (buff) { - bh_lock_sock(sk2); - if (!sock_owned_by_user(sk2)) - udpv6_queue_rcv_skb(sk2, buff); - else - sk_add_backlog(sk2, buff); - bh_unlock_sock(sk2); + while (sk) { + stack[count++] = sk; + sk = udp_v6_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, + uh->source, saddr, dif); + if (unlikely(count == ARRAY_SIZE(stack))) { + if (!sk) + break; + flush_stack(stack, count, skb, ~0); + count = 0; } } - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) - udpv6_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); -out: + /* + * before releasing the lock, we must take reference on sockets + */ + for (i = 0; i < count; i++) + sock_hold(stack[i]); + spin_unlock(&hslot->lock); + + if (count) { + flush_stack(stack, count, skb, count - 1); + + for (i = 0; i < count; i++) + sock_put(stack[i]); + } else { + kfree_skb(skb); + } return 0; } @@ -792,7 +950,7 @@ int udpv6_sendmsg(struct kiocb *iocb, struct sock *sk, if (ipv6_addr_v4mapped(daddr)) { struct sockaddr_in sin; sin.sin_family = AF_INET; - sin.sin_port = sin6 ? sin6->sin6_port : inet->dport; + sin.sin_port = sin6 ? sin6->sin6_port : inet->inet_dport; sin.sin_addr.s_addr = daddr->s6_addr32[3]; msg->msg_name = &sin; msg->msg_namelen = sizeof(sin); @@ -865,7 +1023,7 @@ do_udp_sendmsg: if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - fl.fl_ip_dport = inet->dport; + fl.fl_ip_dport = inet->inet_dport; daddr = &np->daddr; fl.fl6_flowlabel = np->flow_label; connected = 1; @@ -877,6 +1035,8 @@ do_udp_sendmsg: if (!fl.oif) fl.oif = np->sticky_pktinfo.ipi6_ifindex; + fl.mark = sk->sk_mark; + if (msg->msg_controllen) { opt = &opt_space; memset(opt, 0, sizeof(struct ipv6_txoptions)); @@ -909,7 +1069,7 @@ do_udp_sendmsg: fl.fl6_dst.s6_addr[15] = 0x1; /* :: means loopback (BSD'ism) */ if (ipv6_addr_any(&fl.fl6_src) && !ipv6_addr_any(&np->saddr)) ipv6_addr_copy(&fl.fl6_src, &np->saddr); - fl.fl_ip_sport = inet->sport; + fl.fl_ip_sport = inet->inet_sport; /* merge ip6_build_xmit from ip6_output */ if (opt && opt->srcrt) { @@ -1190,10 +1350,10 @@ static void udp6_sock_seq_show(struct seq_file *seq, struct sock *sp, int bucket dest = &np->daddr; src = &np->rcv_saddr; - destp = ntohs(inet->dport); - srcp = ntohs(inet->sport); + destp = ntohs(inet->inet_dport); + srcp = ntohs(inet->inet_sport); seq_printf(seq, - "%4d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " + "%5d: %08X%08X%08X%08X:%04X %08X%08X%08X%08X:%04X " "%02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p %d\n", bucket, src->s6_addr32[0], src->s6_addr32[1], @@ -1282,7 +1442,6 @@ static struct inet_protosw udpv6_protosw = { .protocol = IPPROTO_UDP, .prot = &udpv6_prot, .ops = &inet6_dgram_ops, - .capability =-1, .no_check = UDP_CSUM_DEFAULT, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/udplite.c b/net/ipv6/udplite.c index d737a27ee010..6ea6938919e6 100644 --- a/net/ipv6/udplite.c +++ b/net/ipv6/udplite.c @@ -62,7 +62,6 @@ static struct inet_protosw udplite6_protosw = { .protocol = IPPROTO_UDPLITE, .prot = &udplitev6_prot, .ops = &inet6_dgram_ops, - .capability = -1, .no_check = 0, .flags = INET_PROTOSW_PERMANENT, }; diff --git a/net/ipv6/xfrm6_tunnel.c b/net/ipv6/xfrm6_tunnel.c index 81a95c00e503..438831d33593 100644 --- a/net/ipv6/xfrm6_tunnel.c +++ b/net/ipv6/xfrm6_tunnel.c @@ -23,7 +23,7 @@ */ #include <linux/module.h> #include <linux/xfrm.h> -#include <linux/list.h> +#include <linux/rculist.h> #include <net/ip.h> #include <net/xfrm.h> #include <net/ipv6.h> @@ -36,14 +36,15 @@ * per xfrm_address_t. */ struct xfrm6_tunnel_spi { - struct hlist_node list_byaddr; - struct hlist_node list_byspi; - xfrm_address_t addr; - u32 spi; - atomic_t refcnt; + struct hlist_node list_byaddr; + struct hlist_node list_byspi; + xfrm_address_t addr; + u32 spi; + atomic_t refcnt; + struct rcu_head rcu_head; }; -static DEFINE_RWLOCK(xfrm6_tunnel_spi_lock); +static DEFINE_SPINLOCK(xfrm6_tunnel_spi_lock); static u32 xfrm6_tunnel_spi; @@ -107,6 +108,7 @@ static void xfrm6_tunnel_spi_fini(void) if (!hlist_empty(&xfrm6_tunnel_spi_byspi[i])) return; } + rcu_barrier(); kmem_cache_destroy(xfrm6_tunnel_spi_kmem); xfrm6_tunnel_spi_kmem = NULL; } @@ -116,7 +118,7 @@ static struct xfrm6_tunnel_spi *__xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) struct xfrm6_tunnel_spi *x6spi; struct hlist_node *pos; - hlist_for_each_entry(x6spi, pos, + hlist_for_each_entry_rcu(x6spi, pos, &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], list_byaddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) @@ -131,10 +133,10 @@ __be32 xfrm6_tunnel_spi_lookup(xfrm_address_t *saddr) struct xfrm6_tunnel_spi *x6spi; u32 spi; - read_lock_bh(&xfrm6_tunnel_spi_lock); + rcu_read_lock_bh(); x6spi = __xfrm6_tunnel_spi_lookup(saddr); spi = x6spi ? x6spi->spi : 0; - read_unlock_bh(&xfrm6_tunnel_spi_lock); + rcu_read_unlock_bh(); return htonl(spi); } @@ -185,14 +187,15 @@ alloc_spi: if (!x6spi) goto out; + INIT_RCU_HEAD(&x6spi->rcu_head); memcpy(&x6spi->addr, saddr, sizeof(x6spi->addr)); x6spi->spi = spi; atomic_set(&x6spi->refcnt, 1); - hlist_add_head(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]); + hlist_add_head_rcu(&x6spi->list_byspi, &xfrm6_tunnel_spi_byspi[index]); index = xfrm6_tunnel_spi_hash_byaddr(saddr); - hlist_add_head(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]); + hlist_add_head_rcu(&x6spi->list_byaddr, &xfrm6_tunnel_spi_byaddr[index]); out: return spi; } @@ -202,26 +205,32 @@ __be32 xfrm6_tunnel_alloc_spi(xfrm_address_t *saddr) struct xfrm6_tunnel_spi *x6spi; u32 spi; - write_lock_bh(&xfrm6_tunnel_spi_lock); + spin_lock_bh(&xfrm6_tunnel_spi_lock); x6spi = __xfrm6_tunnel_spi_lookup(saddr); if (x6spi) { atomic_inc(&x6spi->refcnt); spi = x6spi->spi; } else spi = __xfrm6_tunnel_alloc_spi(saddr); - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); return htonl(spi); } EXPORT_SYMBOL(xfrm6_tunnel_alloc_spi); +static void x6spi_destroy_rcu(struct rcu_head *head) +{ + kmem_cache_free(xfrm6_tunnel_spi_kmem, + container_of(head, struct xfrm6_tunnel_spi, rcu_head)); +} + void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) { struct xfrm6_tunnel_spi *x6spi; struct hlist_node *pos, *n; - write_lock_bh(&xfrm6_tunnel_spi_lock); + spin_lock_bh(&xfrm6_tunnel_spi_lock); hlist_for_each_entry_safe(x6spi, pos, n, &xfrm6_tunnel_spi_byaddr[xfrm6_tunnel_spi_hash_byaddr(saddr)], @@ -229,14 +238,14 @@ void xfrm6_tunnel_free_spi(xfrm_address_t *saddr) { if (memcmp(&x6spi->addr, saddr, sizeof(x6spi->addr)) == 0) { if (atomic_dec_and_test(&x6spi->refcnt)) { - hlist_del(&x6spi->list_byaddr); - hlist_del(&x6spi->list_byspi); - kmem_cache_free(xfrm6_tunnel_spi_kmem, x6spi); + hlist_del_rcu(&x6spi->list_byaddr); + hlist_del_rcu(&x6spi->list_byspi); + call_rcu(&x6spi->rcu_head, x6spi_destroy_rcu); break; } } } - write_unlock_bh(&xfrm6_tunnel_spi_lock); + spin_unlock_bh(&xfrm6_tunnel_spi_lock); } EXPORT_SYMBOL(xfrm6_tunnel_free_spi); |