diff options
author | Patrick McHardy <kaber@trash.net> | 2011-01-14 14:12:37 +0100 |
---|---|---|
committer | Patrick McHardy <kaber@trash.net> | 2011-01-14 14:12:37 +0100 |
commit | 0134e89c7bcc9fde1da962c82a120691e185619f (patch) | |
tree | 3e03335cf001019a2687d161e956de4f73379984 /net/ipv4 | |
parent | c7066f70d9610df0b9406cc635fc09e86136e714 (diff) | |
parent | 6faee60a4e82075853a437831768cc9e2e563e4e (diff) | |
download | op-kernel-dev-0134e89c7bcc9fde1da962c82a120691e185619f.zip op-kernel-dev-0134e89c7bcc9fde1da962c82a120691e185619f.tar.gz |
Merge branch 'master' of git://1984.lsi.us.es/net-next-2.6
Conflicts:
net/ipv4/route.c
Signed-off-by: Patrick McHardy <kaber@trash.net>
Diffstat (limited to 'net/ipv4')
39 files changed, 875 insertions, 685 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index f581f77..f2b6110 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1148,21 +1148,13 @@ int inet_sk_rebuild_header(struct sock *sk) struct flowi fl = { .oif = sk->sk_bound_dev_if, .mark = sk->sk_mark, - .nl_u = { - .ip4_u = { - .daddr = daddr, - .saddr = inet->inet_saddr, - .tos = RT_CONN_FLAGS(sk), - }, - }, + .fl4_dst = daddr, + .fl4_src = inet->inet_saddr, + .fl4_tos = RT_CONN_FLAGS(sk), .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), - .uli_u = { - .ports = { - .sport = inet->inet_sport, - .dport = inet->inet_dport, - }, - }, + .fl_ip_sport = inet->inet_sport, + .fl_ip_dport = inet->inet_dport, }; security_sk_classify_flow(sk, &fl); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index d8e540c..a2fc7b9 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -433,8 +433,8 @@ static int arp_ignore(struct in_device *in_dev, __be32 sip, __be32 tip) static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = sip, - .saddr = tip } } }; + struct flowi fl = { .fl4_dst = sip, + .fl4_src = tip }; struct rtable *rt; int flag = 0; /*unsigned long now; */ @@ -883,7 +883,7 @@ static int arp_process(struct sk_buff *skb) dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) - dont_send |= arp_filter(sip, tip, dev); + dont_send = arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { @@ -1017,13 +1017,14 @@ static int arp_req_set_proxy(struct net *net, struct net_device *dev, int on) IPV4_DEVCONF_ALL(net, PROXY_ARP) = on; return 0; } - if (__in_dev_get_rtnl(dev)) { - IN_DEV_CONF_SET(__in_dev_get_rtnl(dev), PROXY_ARP, on); + if (__in_dev_get_rcu(dev)) { + IN_DEV_CONF_SET(__in_dev_get_rcu(dev), PROXY_ARP, on); return 0; } return -ENXIO; } +/* must be called with rcu_read_lock() */ static int arp_req_set_public(struct net *net, struct arpreq *r, struct net_device *dev) { @@ -1033,7 +1034,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, if (mask && mask != htonl(0xFFFFFFFF)) return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { - dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, + dev = dev_getbyhwaddr_rcu(net, r->arp_ha.sa_family, r->arp_ha.sa_data); if (!dev) return -ENODEV; @@ -1061,8 +1062,8 @@ static int arp_req_set(struct net *net, struct arpreq *r, if (r->arp_flags & ATF_PERM) r->arp_flags |= ATF_COM; if (dev == NULL) { - struct flowi fl = { .nl_u.ip4_u = { .daddr = ip, - .tos = RTO_ONLINK } }; + struct flowi fl = { .fl4_dst = ip, + .fl4_tos = RTO_ONLINK }; struct rtable *rt; err = ip_route_output_key(net, &rt, &fl); if (err != 0) @@ -1169,8 +1170,8 @@ static int arp_req_delete(struct net *net, struct arpreq *r, ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; if (dev == NULL) { - struct flowi fl = { .nl_u.ip4_u = { .daddr = ip, - .tos = RTO_ONLINK } }; + struct flowi fl = { .fl4_dst = ip, + .fl4_tos = RTO_ONLINK }; struct rtable *rt; err = ip_route_output_key(net, &rt, &fl); if (err != 0) @@ -1225,10 +1226,10 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) if (!(r.arp_flags & ATF_NETMASK)) ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = htonl(0xFFFFFFFFUL); - rtnl_lock(); + rcu_read_lock(); if (r.arp_dev[0]) { err = -ENODEV; - dev = __dev_get_by_name(net, r.arp_dev); + dev = dev_get_by_name_rcu(net, r.arp_dev); if (dev == NULL) goto out; @@ -1252,12 +1253,12 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) break; case SIOCGARP: err = arp_req_get(&r, dev); - if (!err && copy_to_user(arg, &r, sizeof(r))) - err = -EFAULT; break; } out: - rtnl_unlock(); + rcu_read_unlock(); + if (cmd == SIOCGARP && !err && copy_to_user(arg, &r, sizeof(r))) + err = -EFAULT; return err; } diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index dc94b03..748cb5b 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1256,6 +1256,87 @@ errout: rtnl_set_sk_err(net, RTNLGRP_IPV4_IFADDR, err); } +static size_t inet_get_link_af_size(const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rtnl(dev); + + if (!in_dev) + return 0; + + return nla_total_size(IPV4_DEVCONF_MAX * 4); /* IFLA_INET_CONF */ +} + +static int inet_fill_link_af(struct sk_buff *skb, const struct net_device *dev) +{ + struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct nlattr *nla; + int i; + + if (!in_dev) + return -ENODATA; + + nla = nla_reserve(skb, IFLA_INET_CONF, IPV4_DEVCONF_MAX * 4); + if (nla == NULL) + return -EMSGSIZE; + + for (i = 0; i < IPV4_DEVCONF_MAX; i++) + ((u32 *) nla_data(nla))[i] = in_dev->cnf.data[i]; + + return 0; +} + +static const struct nla_policy inet_af_policy[IFLA_INET_MAX+1] = { + [IFLA_INET_CONF] = { .type = NLA_NESTED }, +}; + +static int inet_validate_link_af(const struct net_device *dev, + const struct nlattr *nla) +{ + struct nlattr *a, *tb[IFLA_INET_MAX+1]; + int err, rem; + + if (dev && !__in_dev_get_rtnl(dev)) + return -EAFNOSUPPORT; + + err = nla_parse_nested(tb, IFLA_INET_MAX, nla, inet_af_policy); + if (err < 0) + return err; + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) { + int cfgid = nla_type(a); + + if (nla_len(a) < 4) + return -EINVAL; + + if (cfgid <= 0 || cfgid > IPV4_DEVCONF_MAX) + return -EINVAL; + } + } + + return 0; +} + +static int inet_set_link_af(struct net_device *dev, const struct nlattr *nla) +{ + struct in_device *in_dev = __in_dev_get_rtnl(dev); + struct nlattr *a, *tb[IFLA_INET_MAX+1]; + int rem; + + if (!in_dev) + return -EAFNOSUPPORT; + + if (nla_parse_nested(tb, IFLA_INET_MAX, nla, NULL) < 0) + BUG(); + + if (tb[IFLA_INET_CONF]) { + nla_for_each_nested(a, tb[IFLA_INET_CONF], rem) + ipv4_devconf_set(in_dev, nla_type(a), nla_get_u32(a)); + } + + return 0; +} + #ifdef CONFIG_SYSCTL static void devinet_copy_dflt_conf(struct net *net, int i) @@ -1349,9 +1430,9 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, return ret; } -int ipv4_doint_and_flush(ctl_table *ctl, int write, - void __user *buffer, - size_t *lenp, loff_t *ppos) +static int ipv4_doint_and_flush(ctl_table *ctl, int write, + void __user *buffer, + size_t *lenp, loff_t *ppos) { int *valp = ctl->data; int val = *valp; @@ -1619,6 +1700,14 @@ static __net_initdata struct pernet_operations devinet_ops = { .exit = devinet_exit_net, }; +static struct rtnl_af_ops inet_af_ops = { + .family = AF_INET, + .fill_link_af = inet_fill_link_af, + .get_link_af_size = inet_get_link_af_size, + .validate_link_af = inet_validate_link_af, + .set_link_af = inet_set_link_af, +}; + void __init devinet_init(void) { register_pernet_subsys(&devinet_ops); @@ -1626,6 +1715,8 @@ void __init devinet_init(void) register_gifconf(PF_INET, inet_gifconf); register_netdevice_notifier(&ip_netdev_notifier); + rtnl_af_register(&inet_af_ops); + rtnl_register(PF_INET, RTM_NEWADDR, inet_rtm_newaddr, NULL); rtnl_register(PF_INET, RTM_DELADDR, inet_rtm_deladdr, NULL); rtnl_register(PF_INET, RTM_GETADDR, NULL, inet_dump_ifaddr); diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 14ca1f1..e42a905 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -23,6 +23,8 @@ struct esp_skb_cb { #define ESP_SKB_CB(__skb) ((struct esp_skb_cb *)&((__skb)->cb[0])) +static u32 esp4_get_mtu(struct xfrm_state *x, int mtu); + /* * Allocate an AEAD request structure with extra space for SG and IV. * @@ -117,25 +119,35 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) int blksize; int clen; int alen; + int plen; + int tfclen; int nfrags; /* skb is pure payload to encrypt */ err = -ENOMEM; - /* Round to block size */ - clen = skb->len; - esp = x->data; aead = esp->aead; alen = crypto_aead_authsize(aead); + tfclen = 0; + if (x->tfcpad) { + struct xfrm_dst *dst = (struct xfrm_dst *)skb_dst(skb); + u32 padto; + + padto = min(x->tfcpad, esp4_get_mtu(x, dst->child_mtu_cached)); + if (skb->len < padto) + tfclen = padto - skb->len; + } blksize = ALIGN(crypto_aead_blocksize(aead), 4); - clen = ALIGN(clen + 2, blksize); + clen = ALIGN(skb->len + 2 + tfclen, blksize); if (esp->padlen) clen = ALIGN(clen, esp->padlen); + plen = clen - skb->len - tfclen; - if ((err = skb_cow_data(skb, clen - skb->len + alen, &trailer)) < 0) + err = skb_cow_data(skb, tfclen + plen + alen, &trailer); + if (err < 0) goto error; nfrags = err; @@ -150,13 +162,17 @@ static int esp_output(struct xfrm_state *x, struct sk_buff *skb) /* Fill padding... */ tail = skb_tail_pointer(trailer); + if (tfclen) { + memset(tail, 0, tfclen); + tail += tfclen; + } do { int i; - for (i=0; i<clen-skb->len - 2; i++) + for (i = 0; i < plen - 2; i++) tail[i] = i + 1; } while (0); - tail[clen - skb->len - 2] = (clen - skb->len) - 2; - tail[clen - skb->len - 1] = *skb_mac_header(skb); + tail[plen - 2] = plen - 2; + tail[plen - 1] = *skb_mac_header(skb); pskb_put(skb, trailer, clen - skb->len + alen); skb_push(skb, -skb_network_offset(skb)); diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index eb6f69a..1d2cdd4 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -158,18 +158,20 @@ static void fib_flush(struct net *net) struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = addr - } - }, - .flags = FLOWI_FLAG_MATCH_ANY_IIF + .fl4_dst = addr, }; struct fib_result res = { 0 }; struct net_device *dev = NULL; + struct fib_table *local_table; + +#ifdef CONFIG_IP_MULTIPLE_TABLES + res.r = NULL; +#endif rcu_read_lock(); - if (fib_lookup(net, &fl, &res)) { + local_table = fib_get_table(net, RT_TABLE_LOCAL); + if (!local_table || + fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) { rcu_read_unlock(); return NULL; } @@ -193,7 +195,7 @@ static inline unsigned __inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; + struct flowi fl = { .fl4_dst = addr }; struct fib_result res; unsigned ret = RTN_BROADCAST; struct fib_table *local_table; @@ -247,13 +249,9 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, { struct in_device *in_dev; struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = src, - .saddr = dst, - .tos = tos - } - }, + .fl4_dst = src, + .fl4_src = dst, + .fl4_tos = tos, .mark = mark, .iif = oif }; @@ -853,13 +851,9 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb) struct fib_result res; struct flowi fl = { .mark = frn->fl_mark, - .nl_u = { - .ip4_u = { - .daddr = frn->fl_addr, - .tos = frn->fl_tos, - .scope = frn->fl_scope - } - } + .fl4_dst = frn->fl_addr, + .fl4_tos = frn->fl_tos, + .fl4_scope = frn->fl_scope, }; #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -999,7 +993,11 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo rt_cache_flush(dev_net(dev), 0); break; case NETDEV_UNREGISTER_BATCH: - rt_cache_flush_batch(); + /* The batch unregister is only called on the first + * device in the list of devices being unregistered. + * Therefore we should not pass dev_net(dev) in here. + */ + rt_cache_flush_batch(NULL); break; } return NOTIFY_DONE; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index a72c62d..9aff11d7 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -563,12 +563,8 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, rcu_read_lock(); { struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = nh->nh_gw, - .scope = cfg->fc_scope + 1, - }, - }, + .fl4_dst = nh->nh_gw, + .fl4_scope = cfg->fc_scope + 1, .oif = nh->nh_oif, }; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 200eb53..0f28034 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -365,7 +365,7 @@ static struct tnode *tnode_alloc(size_t size) if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); else - return __vmalloc(size, GFP_KERNEL | __GFP_ZERO, PAGE_KERNEL); + return vzalloc(size); } static void __tnode_vfree(struct work_struct *arg) diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index c6e2aff..4aa1b7f 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -386,10 +386,9 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) daddr = icmp_param->replyopts.faddr; } { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = daddr, - .saddr = rt->rt_spec_dst, - .tos = RT_TOS(ip_hdr(skb)->tos) } }, + struct flowi fl = { .fl4_dst= daddr, + .fl4_src = rt->rt_spec_dst, + .fl4_tos = RT_TOS(ip_hdr(skb)->tos), .proto = IPPROTO_ICMP }; security_skb_classify_flow(skb, &fl); if (ip_route_output_key(net, &rt, &fl)) @@ -542,22 +541,13 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) { struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = icmp_param.replyopts.srr ? - icmp_param.replyopts.faddr : - iph->saddr, - .saddr = saddr, - .tos = RT_TOS(tos) - } - }, + .fl4_dst = icmp_param.replyopts.srr ? + icmp_param.replyopts.faddr : iph->saddr, + .fl4_src = saddr, + .fl4_tos = RT_TOS(tos), .proto = IPPROTO_ICMP, - .uli_u = { - .icmpt = { - .type = type, - .code = code - } - } + .fl_icmp_type = type, + .fl_icmp_code = code, }; int err; struct rtable *rt2; @@ -569,6 +559,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) /* No need to clone since we're just using its address. */ rt2 = rt; + if (!fl.nl_u.ip4_u.saddr) + fl.nl_u.ip4_u.saddr = rt->rt_src; + err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0); switch (err) { case 0: diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index 08d0d81..e0e77e2 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -149,21 +149,37 @@ static void ip_mc_clear_src(struct ip_mc_list *pmc); static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, int sfcount, __be32 *psfsrc, int delta); + +static void ip_mc_list_reclaim(struct rcu_head *head) +{ + kfree(container_of(head, struct ip_mc_list, rcu)); +} + static void ip_ma_put(struct ip_mc_list *im) { if (atomic_dec_and_test(&im->refcnt)) { in_dev_put(im->interface); - kfree(im); + call_rcu(&im->rcu, ip_mc_list_reclaim); } } +#define for_each_pmc_rcu(in_dev, pmc) \ + for (pmc = rcu_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rcu_dereference(pmc->next_rcu)) + +#define for_each_pmc_rtnl(in_dev, pmc) \ + for (pmc = rtnl_dereference(in_dev->mc_list); \ + pmc != NULL; \ + pmc = rtnl_dereference(pmc->next_rcu)) + #ifdef CONFIG_IP_MULTICAST /* * Timer management */ -static __inline__ void igmp_stop_timer(struct ip_mc_list *im) +static void igmp_stop_timer(struct ip_mc_list *im) { spin_lock_bh(&im->lock); if (del_timer(&im->timer)) @@ -284,6 +300,8 @@ igmp_scount(struct ip_mc_list *pmc, int type, int gdeleted, int sdeleted) return scount; } +#define igmp_skb_size(skb) (*(unsigned int *)((skb)->cb)) + static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) { struct sk_buff *skb; @@ -292,14 +310,20 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct igmpv3_report *pig; struct net *net = dev_net(dev); - skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); - if (skb == NULL) - return NULL; + while (1) { + skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), + GFP_ATOMIC | __GFP_NOWARN); + if (skb) + break; + size >>= 1; + if (size < 256) + return NULL; + } + igmp_skb_size(skb) = size; { struct flowi fl = { .oif = dev->ifindex, - .nl_u = { .ip4_u = { - .daddr = IGMPV3_ALL_MCR } }, + .fl4_dst = IGMPV3_ALL_MCR, .proto = IPPROTO_IGMP }; if (ip_route_output_key(net, &rt, &fl)) { kfree_skb(skb); @@ -384,7 +408,7 @@ static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, return skb; } -#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? (skb)->dev->mtu - (skb)->len : \ +#define AVAILABLE(skb) ((skb) ? ((skb)->dev ? igmp_skb_size(skb) - (skb)->len : \ skb_tailroom(skb)) : 0) static struct sk_buff *add_grec(struct sk_buff *skb, struct ip_mc_list *pmc, @@ -502,8 +526,8 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) int type; if (!pmc) { - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (pmc->multiaddr == IGMP_ALL_HOSTS) continue; spin_lock_bh(&pmc->lock); @@ -514,7 +538,7 @@ static int igmpv3_send_report(struct in_device *in_dev, struct ip_mc_list *pmc) skb = add_grec(skb, pmc, type, 0, 0); spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } else { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) @@ -556,7 +580,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) struct sk_buff *skb = NULL; int type, dtype; - read_lock(&in_dev->mc_list_lock); + rcu_read_lock(); spin_lock_bh(&in_dev->mc_tomb_lock); /* deleted MCA's */ @@ -593,7 +617,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) spin_unlock_bh(&in_dev->mc_tomb_lock); /* change recs */ - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rcu(in_dev, pmc) { spin_lock_bh(&pmc->lock); if (pmc->sfcount[MCAST_EXCLUDE]) { type = IGMPV3_BLOCK_OLD_SOURCES; @@ -616,7 +640,7 @@ static void igmpv3_send_cr(struct in_device *in_dev) } spin_unlock_bh(&pmc->lock); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); if (!skb) return; @@ -644,7 +668,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, { struct flowi fl = { .oif = dev->ifindex, - .nl_u = { .ip4_u = { .daddr = dst } }, + .fl4_dst = dst, .proto = IPPROTO_IGMP }; if (ip_route_output_key(net, &rt, &fl)) return -1; @@ -813,14 +837,14 @@ static void igmp_heard_report(struct in_device *in_dev, __be32 group) if (group == IGMP_ALL_HOSTS) return; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == group) { igmp_stop_timer(im); break; } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, @@ -906,8 +930,8 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, * - Use the igmp->igmp_code field as the maximum * delay possible */ - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im!=NULL; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { int changed; if (group && group != im->multiaddr) @@ -925,7 +949,7 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, if (changed) igmp_mod_timer(im, max_delay); } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } /* called in rcu_read_lock() section */ @@ -1110,8 +1134,8 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(pmc); } /* clear dead sources, too */ - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { struct ip_sf_list *psf, *psf_next; spin_lock_bh(&pmc->lock); @@ -1123,7 +1147,7 @@ static void igmpv3_clear_delrec(struct in_device *in_dev) kfree(psf); } } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); } #endif @@ -1209,7 +1233,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); - for (im=in_dev->mc_list; im; im=im->next) { + for_each_pmc_rtnl(in_dev, im) { if (im->multiaddr == addr) { im->users++; ip_mc_add_src(in_dev, &addr, MCAST_EXCLUDE, 0, NULL, 0); @@ -1217,7 +1241,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) } } - im = kmalloc(sizeof(*im), GFP_KERNEL); + im = kzalloc(sizeof(*im), GFP_KERNEL); if (!im) goto out; @@ -1227,26 +1251,18 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; - im->sfcount[MCAST_INCLUDE] = 0; im->sfcount[MCAST_EXCLUDE] = 1; - im->sources = NULL; - im->tomb = NULL; - im->crcount = 0; atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - im->tm_running = 0; setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); im->unsolicit_count = IGMP_Unsolicited_Report_Count; - im->reporter = 0; - im->gsquery = 0; #endif - im->loaded = 0; - write_lock_bh(&in_dev->mc_list_lock); - im->next = in_dev->mc_list; - in_dev->mc_list = im; + + im->next_rcu = in_dev->mc_list; in_dev->mc_count++; - write_unlock_bh(&in_dev->mc_list_lock); + rcu_assign_pointer(in_dev->mc_list, im); + #ifdef CONFIG_IP_MULTICAST igmpv3_del_delrec(in_dev, im->multiaddr); #endif @@ -1260,26 +1276,32 @@ EXPORT_SYMBOL(ip_mc_inc_group); /* * Resend IGMP JOIN report; used for bonding. + * Called with rcu_read_lock() */ -void ip_mc_rejoin_group(struct ip_mc_list *im) +void ip_mc_rejoin_groups(struct in_device *in_dev) { #ifdef CONFIG_IP_MULTICAST - struct in_device *in_dev = im->interface; + struct ip_mc_list *im; + int type; - if (im->multiaddr == IGMP_ALL_HOSTS) - return; + for_each_pmc_rcu(in_dev, im) { + if (im->multiaddr == IGMP_ALL_HOSTS) + continue; - /* a failover is happening and switches - * must be notified immediately */ - if (IGMP_V1_SEEN(in_dev)) - igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); - else if (IGMP_V2_SEEN(in_dev)) - igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); - else - igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); + /* a failover is happening and switches + * must be notified immediately + */ + if (IGMP_V1_SEEN(in_dev)) + type = IGMP_HOST_MEMBERSHIP_REPORT; + else if (IGMP_V2_SEEN(in_dev)) + type = IGMPV2_HOST_MEMBERSHIP_REPORT; + else + type = IGMPV3_HOST_MEMBERSHIP_REPORT; + igmp_send_report(in_dev, im, type); + } #endif } -EXPORT_SYMBOL(ip_mc_rejoin_group); +EXPORT_SYMBOL(ip_mc_rejoin_groups); /* * A socket has left a multicast group on device dev @@ -1287,17 +1309,18 @@ EXPORT_SYMBOL(ip_mc_rejoin_group); void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) { - struct ip_mc_list *i, **ip; + struct ip_mc_list *i; + struct ip_mc_list __rcu **ip; ASSERT_RTNL(); - for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { + for (ip = &in_dev->mc_list; + (i = rtnl_dereference(*ip)) != NULL; + ip = &i->next_rcu) { if (i->multiaddr == addr) { if (--i->users == 0) { - write_lock_bh(&in_dev->mc_list_lock); - *ip = i->next; + *ip = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); igmp_group_dropped(i); if (!in_dev->dead) @@ -1316,34 +1339,34 @@ EXPORT_SYMBOL(ip_mc_dec_group); void ip_mc_unmap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); } void ip_mc_remap(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i = in_dev->mc_list; i; i = i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* Device going down */ void ip_mc_down(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_dropped(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_dropped(pmc); #ifdef CONFIG_IP_MULTICAST in_dev->mr_ifc_count = 0; @@ -1374,7 +1397,6 @@ void ip_mc_init_dev(struct in_device *in_dev) in_dev->mr_qrv = IGMP_Unsolicited_Report_Count; #endif - rwlock_init(&in_dev->mc_list_lock); spin_lock_init(&in_dev->mc_tomb_lock); } @@ -1382,14 +1404,14 @@ void ip_mc_init_dev(struct in_device *in_dev) void ip_mc_up(struct in_device *in_dev) { - struct ip_mc_list *i; + struct ip_mc_list *pmc; ASSERT_RTNL(); ip_mc_inc_group(in_dev, IGMP_ALL_HOSTS); - for (i=in_dev->mc_list; i; i=i->next) - igmp_group_added(i); + for_each_pmc_rtnl(in_dev, pmc) + igmp_group_added(pmc); } /* @@ -1405,24 +1427,19 @@ void ip_mc_destroy_dev(struct in_device *in_dev) /* Deactivate timers */ ip_mc_down(in_dev); - write_lock_bh(&in_dev->mc_list_lock); - while ((i = in_dev->mc_list) != NULL) { - in_dev->mc_list = i->next; + while ((i = rtnl_dereference(in_dev->mc_list)) != NULL) { + in_dev->mc_list = i->next_rcu; in_dev->mc_count--; - write_unlock_bh(&in_dev->mc_list_lock); + igmp_group_dropped(i); ip_ma_put(i); - - write_lock_bh(&in_dev->mc_list_lock); } - write_unlock_bh(&in_dev->mc_list_lock); } /* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = imr->imr_multiaddr.s_addr } } }; + struct flowi fl = { .fl4_dst = imr->imr_multiaddr.s_addr }; struct rtable *rt; struct net_device *dev = NULL; struct in_device *idev = NULL; @@ -1513,18 +1530,18 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); #endif @@ -1685,18 +1702,18 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, if (!in_dev) return -ENODEV; - read_lock(&in_dev->mc_list_lock); - for (pmc=in_dev->mc_list; pmc; pmc=pmc->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, pmc) { if (*pmca == pmc->multiaddr) break; } if (!pmc) { /* MCA not found?? bug */ - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return -ESRCH; } spin_lock_bh(&pmc->lock); - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); #ifdef CONFIG_IP_MULTICAST sf_markstate(pmc); @@ -1793,7 +1810,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) err = -EADDRINUSE; ifindex = imr->imr_ifindex; - for (i = inet->mc_list; i; i = i->next) { + for_each_pmc_rtnl(inet, i) { if (i->multi.imr_multiaddr.s_addr == addr && i->multi.imr_ifindex == ifindex) goto done; @@ -1807,7 +1824,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) goto done; memcpy(&iml->multi, imr, sizeof(*imr)); - iml->next = inet->mc_list; + iml->next_rcu = inet->mc_list; iml->sflist = NULL; iml->sfmode = MCAST_EXCLUDE; rcu_assign_pointer(inet->mc_list, iml); @@ -1821,17 +1838,14 @@ EXPORT_SYMBOL(ip_mc_join_group); static void ip_sf_socklist_reclaim(struct rcu_head *rp) { - struct ip_sf_socklist *psf; - - psf = container_of(rp, struct ip_sf_socklist, rcu); + kfree(container_of(rp, struct ip_sf_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(psf); } static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, struct in_device *in_dev) { - struct ip_sf_socklist *psf = iml->sflist; + struct ip_sf_socklist *psf = rtnl_dereference(iml->sflist); int err; if (psf == NULL) { @@ -1851,11 +1865,8 @@ static int ip_mc_leave_src(struct sock *sk, struct ip_mc_socklist *iml, static void ip_mc_socklist_reclaim(struct rcu_head *rp) { - struct ip_mc_socklist *iml; - - iml = container_of(rp, struct ip_mc_socklist, rcu); + kfree(container_of(rp, struct ip_mc_socklist, rcu)); /* sk_omem_alloc should have been decreased by the caller*/ - kfree(iml); } @@ -1866,7 +1877,8 @@ static void ip_mc_socklist_reclaim(struct rcu_head *rp) int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) { struct inet_sock *inet = inet_sk(sk); - struct ip_mc_socklist *iml, **imlp; + struct ip_mc_socklist *iml; + struct ip_mc_socklist __rcu **imlp; struct in_device *in_dev; struct net *net = sock_net(sk); __be32 group = imr->imr_multiaddr.s_addr; @@ -1876,7 +1888,9 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) rtnl_lock(); in_dev = ip_mc_find_dev(net, imr); ifindex = imr->imr_ifindex; - for (imlp = &inet->mc_list; (iml = *imlp) != NULL; imlp = &iml->next) { + for (imlp = &inet->mc_list; + (iml = rtnl_dereference(*imlp)) != NULL; + imlp = &iml->next_rcu) { if (iml->multi.imr_multiaddr.s_addr != group) continue; if (ifindex) { @@ -1888,7 +1902,7 @@ int ip_mc_leave_group(struct sock *sk, struct ip_mreqn *imr) (void) ip_mc_leave_src(sk, iml, in_dev); - rcu_assign_pointer(*imlp, iml->next); + *imlp = iml->next_rcu; if (in_dev) ip_mc_dec_group(in_dev, group); @@ -1934,7 +1948,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if ((pmc->multi.imr_multiaddr.s_addr == imr.imr_multiaddr.s_addr) && (pmc->multi.imr_ifindex == imr.imr_ifindex)) @@ -1958,7 +1972,7 @@ int ip_mc_source(int add, int omode, struct sock *sk, struct pmc->sfmode = omode; } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (!add) { if (!psl) goto done; /* err = -EADDRNOTAVAIL */ @@ -2077,7 +2091,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) goto done; } - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2107,7 +2121,7 @@ int ip_mc_msfilter(struct sock *sk, struct ip_msfilter *msf, int ifindex) (void) ip_mc_add_src(in_dev, &msf->imsf_multiaddr, msf->imsf_fmode, 0, NULL, 0); } - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); if (psl) { (void) ip_mc_del_src(in_dev, &msf->imsf_multiaddr, pmc->sfmode, psl->sl_count, psl->sl_addr, 0); @@ -2155,7 +2169,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, } err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == msf->imsf_multiaddr && pmc->multi.imr_ifindex == imr.imr_ifindex) break; @@ -2163,7 +2177,7 @@ int ip_mc_msfget(struct sock *sk, struct ip_msfilter *msf, if (!pmc) /* must have a prior join */ goto done; msf->imsf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); if (!psl) { len = 0; @@ -2208,7 +2222,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, err = -EADDRNOTAVAIL; - for (pmc=inet->mc_list; pmc; pmc=pmc->next) { + for_each_pmc_rtnl(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == addr && pmc->multi.imr_ifindex == gsf->gf_interface) break; @@ -2216,7 +2230,7 @@ int ip_mc_gsfget(struct sock *sk, struct group_filter *gsf, if (!pmc) /* must have a prior join */ goto done; gsf->gf_fmode = pmc->sfmode; - psl = pmc->sflist; + psl = rtnl_dereference(pmc->sflist); rtnl_unlock(); count = psl ? psl->sl_count : 0; copycount = count < gsf->gf_numsrc ? count : gsf->gf_numsrc; @@ -2257,7 +2271,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) goto out; rcu_read_lock(); - for (pmc=rcu_dereference(inet->mc_list); pmc; pmc=rcu_dereference(pmc->next)) { + for_each_pmc_rcu(inet, pmc) { if (pmc->multi.imr_multiaddr.s_addr == loc_addr && pmc->multi.imr_ifindex == dif) break; @@ -2265,7 +2279,7 @@ int ip_mc_sf_allow(struct sock *sk, __be32 loc_addr, __be32 rmt_addr, int dif) ret = inet->mc_all; if (!pmc) goto unlock; - psl = pmc->sflist; + psl = rcu_dereference(pmc->sflist); ret = (pmc->sfmode == MCAST_EXCLUDE); if (!psl) goto unlock; @@ -2300,16 +2314,14 @@ void ip_mc_drop_socket(struct sock *sk) return; rtnl_lock(); - while ((iml = inet->mc_list) != NULL) { + while ((iml = rtnl_dereference(inet->mc_list)) != NULL) { struct in_device *in_dev; - rcu_assign_pointer(inet->mc_list, iml->next); + inet->mc_list = iml->next_rcu; in_dev = inetdev_by_index(net, iml->multi.imr_ifindex); (void) ip_mc_leave_src(sk, iml, in_dev); - if (in_dev != NULL) { + if (in_dev != NULL) ip_mc_dec_group(in_dev, iml->multi.imr_multiaddr.s_addr); - in_dev_put(in_dev); - } /* decrease mem now to avoid the memleak warning */ atomic_sub(sizeof(*iml), &sk->sk_omem_alloc); call_rcu(&iml->rcu, ip_mc_socklist_reclaim); @@ -2323,8 +2335,8 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p struct ip_sf_list *psf; int rv = 0; - read_lock(&in_dev->mc_list_lock); - for (im=in_dev->mc_list; im; im=im->next) { + rcu_read_lock(); + for_each_pmc_rcu(in_dev, im) { if (im->multiaddr == mc_addr) break; } @@ -2345,7 +2357,7 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p } else rv = 1; /* unspecified source; tentatively allow */ } - read_unlock(&in_dev->mc_list_lock); + rcu_read_unlock(); return rv; } @@ -2371,13 +2383,11 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) in_dev = __in_dev_get_rcu(state->dev); if (!in_dev) continue; - read_lock(&in_dev->mc_list_lock); - im = in_dev->mc_list; + im = rcu_dereference(in_dev->mc_list); if (im) { state->in_dev = in_dev; break; } - read_unlock(&in_dev->mc_list_lock); } return im; } @@ -2385,11 +2395,9 @@ static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_list *im) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - im = im->next; - while (!im) { - if (likely(state->in_dev != NULL)) - read_unlock(&state->in_dev->mc_list_lock); + im = rcu_dereference(im->next_rcu); + while (!im) { state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->in_dev = NULL; @@ -2398,8 +2406,7 @@ static struct ip_mc_list *igmp_mc_get_next(struct seq_file *seq, struct ip_mc_li state->in_dev = __in_dev_get_rcu(state->dev); if (!state->in_dev) continue; - read_lock(&state->in_dev->mc_list_lock); - im = state->in_dev->mc_list; + im = rcu_dereference(state->in_dev->mc_list); } return im; } @@ -2435,10 +2442,8 @@ static void igmp_mc_seq_stop(struct seq_file *seq, void *v) __releases(rcu) { struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); - if (likely(state->in_dev != NULL)) { - read_unlock(&state->in_dev->mc_list_lock); - state->in_dev = NULL; - } + + state->in_dev = NULL; state->dev = NULL; rcu_read_unlock(); } @@ -2460,7 +2465,7 @@ static int igmp_mc_seq_show(struct seq_file *seq, void *v) querier = "NONE"; #endif - if (state->in_dev->mc_list == im) { + if (rcu_dereference(state->in_dev->mc_list) == im) { seq_printf(seq, "%d\t%-10s: %5d %7s\n", state->dev->ifindex, state->dev->name, state->in_dev->mc_count, querier); } @@ -2519,8 +2524,7 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) idev = __in_dev_get_rcu(state->dev); if (unlikely(idev == NULL)) continue; - read_lock(&idev->mc_list_lock); - im = idev->mc_list; + im = rcu_dereference(idev->mc_list); if (likely(im != NULL)) { spin_lock_bh(&im->lock); psf = im->sources; @@ -2531,7 +2535,6 @@ static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) } spin_unlock_bh(&im->lock); } - read_unlock(&idev->mc_list_lock); } return psf; } @@ -2545,9 +2548,6 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l spin_unlock_bh(&state->im->lock); state->im = state->im->next; while (!state->im) { - if (likely(state->idev != NULL)) - read_unlock(&state->idev->mc_list_lock); - state->dev = next_net_device_rcu(state->dev); if (!state->dev) { state->idev = NULL; @@ -2556,8 +2556,7 @@ static struct ip_sf_list *igmp_mcf_get_next(struct seq_file *seq, struct ip_sf_l state->idev = __in_dev_get_rcu(state->dev); if (!state->idev) continue; - read_lock(&state->idev->mc_list_lock); - state->im = state->idev->mc_list; + state->im = rcu_dereference(state->idev->mc_list); } if (!state->im) break; @@ -2603,10 +2602,7 @@ static void igmp_mcf_seq_stop(struct seq_file *seq, void *v) spin_unlock_bh(&state->im->lock); state->im = NULL; } - if (likely(state->idev != NULL)) { - read_unlock(&state->idev->mc_list_lock); - state->idev = NULL; - } + state->idev = NULL; state->dev = NULL; rcu_read_unlock(); } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 7174370..25e3181 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -55,7 +55,6 @@ EXPORT_SYMBOL(inet_get_local_port_range); int inet_csk_bind_conflict(const struct sock *sk, const struct inet_bind_bucket *tb) { - const __be32 sk_rcv_saddr = inet_rcv_saddr(sk); struct sock *sk2; struct hlist_node *node; int reuse = sk->sk_reuse; @@ -75,9 +74,9 @@ int inet_csk_bind_conflict(const struct sock *sk, sk->sk_bound_dev_if == sk2->sk_bound_dev_if)) { if (!reuse || !sk2->sk_reuse || sk2->sk_state == TCP_LISTEN) { - const __be32 sk2_rcv_saddr = inet_rcv_saddr(sk2); - if (!sk2_rcv_saddr || !sk_rcv_saddr || - sk2_rcv_saddr == sk_rcv_saddr) + const __be32 sk2_rcv_saddr = sk_rcv_saddr(sk2); + if (!sk2_rcv_saddr || !sk_rcv_saddr(sk) || + sk2_rcv_saddr == sk_rcv_saddr(sk)) break; } } @@ -358,17 +357,14 @@ struct dst_entry *inet_csk_route_req(struct sock *sk, struct ip_options *opt = inet_rsk(req)->opt; struct flowi fl = { .oif = sk->sk_bound_dev_if, .mark = sk->sk_mark, - .nl_u = { .ip4_u = - { .daddr = ((opt && opt->srr) ? - opt->faddr : - ireq->rmt_addr), - .saddr = ireq->loc_addr, - .tos = RT_CONN_FLAGS(sk) } }, + .fl4_dst = ((opt && opt->srr) ? + opt->faddr : ireq->rmt_addr), + .fl4_src = ireq->loc_addr, + .fl4_tos = RT_CONN_FLAGS(sk), .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), - .uli_u = { .ports = - { .sport = inet_sk(sk)->inet_sport, - .dport = ireq->rmt_port } } }; + .fl_ip_sport = inet_sk(sk)->inet_sport, + .fl_ip_dport = ireq->rmt_port }; struct net *net = sock_net(sk); security_req_classify_flow(req, &fl); diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 1b344f3..3c0369a 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -133,8 +133,7 @@ int __inet_inherit_port(struct sock *sk, struct sock *child) } } } - sk_add_bind_node(child, &tb->owners); - inet_csk(child)->icsk_bind_hash = tb; + inet_bind_hash(child, tb, port); spin_unlock(&head->lock); return 0; diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 9e94d7c..d9bc857 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -63,7 +63,7 @@ * refcnt: atomically against modifications on other CPU; * usually under some other lock to prevent node disappearing * dtime: unused node list lock - * v4daddr: unchangeable + * daddr: unchangeable * ip_id_count: atomic value (no lock needed) */ @@ -79,15 +79,24 @@ static const struct inet_peer peer_fake_node = { .avl_height = 0 }; -static struct { +struct inet_peer_base { struct inet_peer __rcu *root; spinlock_t lock; int total; -} peers = { +}; + +static struct inet_peer_base v4_peers = { + .root = peer_avl_empty_rcu, + .lock = __SPIN_LOCK_UNLOCKED(v4_peers.lock), + .total = 0, +}; + +static struct inet_peer_base v6_peers = { .root = peer_avl_empty_rcu, - .lock = __SPIN_LOCK_UNLOCKED(peers.lock), + .lock = __SPIN_LOCK_UNLOCKED(v6_peers.lock), .total = 0, }; + #define PEER_MAXDEPTH 40 /* sufficient for about 2^27 nodes */ /* Exported for sysctl_net_ipv4. */ @@ -152,28 +161,45 @@ static void unlink_from_unused(struct inet_peer *p) } } +static int addr_compare(const struct inetpeer_addr *a, + const struct inetpeer_addr *b) +{ + int i, n = (a->family == AF_INET ? 1 : 4); + + for (i = 0; i < n; i++) { + if (a->a6[i] == b->a6[i]) + continue; + if (a->a6[i] < b->a6[i]) + return -1; + return 1; + } + + return 0; +} + /* * Called with local BH disabled and the pool lock held. */ -#define lookup(_daddr, _stack) \ +#define lookup(_daddr, _stack, _base) \ ({ \ struct inet_peer *u; \ struct inet_peer __rcu **v; \ \ stackptr = _stack; \ - *stackptr++ = &peers.root; \ - for (u = rcu_dereference_protected(peers.root, \ - lockdep_is_held(&peers.lock)); \ + *stackptr++ = &_base->root; \ + for (u = rcu_dereference_protected(_base->root, \ + lockdep_is_held(&_base->lock)); \ u != peer_avl_empty; ) { \ - if (_daddr == u->v4daddr) \ + int cmp = addr_compare(_daddr, &u->daddr); \ + if (cmp == 0) \ break; \ - if ((__force __u32)_daddr < (__force __u32)u->v4daddr) \ + if (cmp == -1) \ v = &u->avl_left; \ else \ v = &u->avl_right; \ *stackptr++ = v; \ u = rcu_dereference_protected(*v, \ - lockdep_is_held(&peers.lock)); \ + lockdep_is_held(&_base->lock)); \ } \ u; \ }) @@ -185,13 +211,15 @@ static void unlink_from_unused(struct inet_peer *p) * But every pointer we follow is guaranteed to be valid thanks to RCU. * We exit from this function if number of links exceeds PEER_MAXDEPTH */ -static struct inet_peer *lookup_rcu_bh(__be32 daddr) +static struct inet_peer *lookup_rcu_bh(const struct inetpeer_addr *daddr, + struct inet_peer_base *base) { - struct inet_peer *u = rcu_dereference_bh(peers.root); + struct inet_peer *u = rcu_dereference_bh(base->root); int count = 0; while (u != peer_avl_empty) { - if (daddr == u->v4daddr) { + int cmp = addr_compare(daddr, &u->daddr); + if (cmp == 0) { /* Before taking a reference, check if this entry was * deleted, unlink_from_pool() sets refcnt=-1 to make * distinction between an unused entry (refcnt=0) and @@ -201,7 +229,7 @@ static struct inet_peer *lookup_rcu_bh(__be32 daddr) u = NULL; return u; } - if ((__force __u32)daddr < (__force __u32)u->v4daddr) + if (cmp == -1) u = rcu_dereference_bh(u->avl_left); else u = rcu_dereference_bh(u->avl_right); @@ -212,19 +240,19 @@ static struct inet_peer *lookup_rcu_bh(__be32 daddr) } /* Called with local BH disabled and the pool lock held. */ -#define lookup_rightempty(start) \ +#define lookup_rightempty(start, base) \ ({ \ struct inet_peer *u; \ struct inet_peer __rcu **v; \ *stackptr++ = &start->avl_left; \ v = &start->avl_left; \ for (u = rcu_dereference_protected(*v, \ - lockdep_is_held(&peers.lock)); \ + lockdep_is_held(&base->lock)); \ u->avl_right != peer_avl_empty_rcu; ) { \ v = &u->avl_right; \ *stackptr++ = v; \ u = rcu_dereference_protected(*v, \ - lockdep_is_held(&peers.lock)); \ + lockdep_is_held(&base->lock)); \ } \ u; \ }) @@ -234,7 +262,8 @@ static struct inet_peer *lookup_rcu_bh(__be32 daddr) * Look into mm/map_avl.c for more detail description of the ideas. */ static void peer_avl_rebalance(struct inet_peer __rcu **stack[], - struct inet_peer __rcu ***stackend) + struct inet_peer __rcu ***stackend, + struct inet_peer_base *base) { struct inet_peer __rcu **nodep; struct inet_peer *node, *l, *r; @@ -243,20 +272,20 @@ static void peer_avl_rebalance(struct inet_peer __rcu **stack[], while (stackend > stack) { nodep = *--stackend; node = rcu_dereference_protected(*nodep, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); l = rcu_dereference_protected(node->avl_left, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); r = rcu_dereference_protected(node->avl_right, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); lh = node_height(l); rh = node_height(r); if (lh > rh + 1) { /* l: RH+2 */ struct inet_peer *ll, *lr, *lrl, *lrr; int lrh; ll = rcu_dereference_protected(l->avl_left, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); lr = rcu_dereference_protected(l->avl_right, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); lrh = node_height(lr); if (lrh <= node_height(ll)) { /* ll: RH+1 */ RCU_INIT_POINTER(node->avl_left, lr); /* lr: RH or RH+1 */ @@ -268,9 +297,9 @@ static void peer_avl_rebalance(struct inet_peer __rcu **stack[], RCU_INIT_POINTER(*nodep, l); } else { /* ll: RH, lr: RH+1 */ lrl = rcu_dereference_protected(lr->avl_left, - lockdep_is_held(&peers.lock)); /* lrl: RH or RH-1 */ + lockdep_is_held(&base->lock)); /* lrl: RH or RH-1 */ lrr = rcu_dereference_protected(lr->avl_right, - lockdep_is_held(&peers.lock)); /* lrr: RH or RH-1 */ + lockdep_is_held(&base->lock)); /* lrr: RH or RH-1 */ RCU_INIT_POINTER(node->avl_left, lrr); /* lrr: RH or RH-1 */ RCU_INIT_POINTER(node->avl_right, r); /* r: RH */ node->avl_height = rh + 1; /* node: RH+1 */ @@ -286,9 +315,9 @@ static void peer_avl_rebalance(struct inet_peer __rcu **stack[], struct inet_peer *rr, *rl, *rlr, *rll; int rlh; rr = rcu_dereference_protected(r->avl_right, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); rl = rcu_dereference_protected(r->avl_left, - lockdep_is_held(&peers.lock)); + lockdep_is_held(&base->lock)); rlh = node_height(rl); if (rlh <= node_height(rr)) { /* rr: LH+1 */ RCU_INIT_POINTER(node->avl_right, rl); /* rl: LH or LH+1 */ @@ -300,9 +329,9 @@ static void peer_avl_rebalance(struct inet_peer __rcu **stack[], RCU_INIT_POINTER(*nodep, r); } else { /* rr: RH, rl: RH+1 */ rlr = rcu_dereference_protected(rl->avl_right, - lockdep_is_held(&peers.lock)); /* rlr: LH or LH-1 */ + lockdep_is_held(&base->lock)); /* rlr: LH or LH-1 */ rll = rcu_dereference_protected(rl->avl_left, - lockdep_is_held(&peers.lock)); /* rll: LH or LH-1 */ + lockdep_is_held(&base->lock)); /* rll: LH or LH-1 */ RCU_INIT_POINTER(node->avl_right, rll); /* rll: LH or LH-1 */ RCU_INIT_POINTER(node->avl_left, l); /* l: LH */ node->avl_height = lh + 1; /* node: LH+1 */ @@ -321,14 +350,14 @@ static void peer_avl_rebalance(struct inet_peer __rcu **stack[], } /* Called with local BH disabled and the pool lock held. */ -#define link_to_pool(n) \ +#define link_to_pool(n, base) \ do { \ n->avl_height = 1; \ n->avl_left = peer_avl_empty_rcu; \ n->avl_right = peer_avl_empty_rcu; \ /* lockless readers can catch us now */ \ rcu_assign_pointer(**--stackptr, n); \ - peer_avl_rebalance(stack, stackptr); \ + peer_avl_rebalance(stack, stackptr, base); \ } while (0) static void inetpeer_free_rcu(struct rcu_head *head) @@ -337,13 +366,13 @@ static void inetpeer_free_rcu(struct rcu_head *head) } /* May be called with local BH enabled. */ -static void unlink_from_pool(struct inet_peer *p) +static void unlink_from_pool(struct inet_peer *p, struct inet_peer_base *base) { int do_free; do_free = 0; - spin_lock_bh(&peers.lock); + spin_lock_bh(&base->lock); /* Check the reference counter. It was artificially incremented by 1 * in cleanup() function to prevent sudden disappearing. If we can * atomically (because of lockless readers) take this last reference, @@ -353,7 +382,7 @@ static void unlink_from_pool(struct inet_peer *p) if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) { struct inet_peer __rcu **stack[PEER_MAXDEPTH]; struct inet_peer __rcu ***stackptr, ***delp; - if (lookup(p->v4daddr, stack) != p) + if (lookup(&p->daddr, stack, base) != p) BUG(); delp = stackptr - 1; /* *delp[0] == p */ if (p->avl_left == peer_avl_empty_rcu) { @@ -362,11 +391,11 @@ static void unlink_from_pool(struct inet_peer *p) } else { /* look for a node to insert instead of p */ struct inet_peer *t; - t = lookup_rightempty(p); + t = lookup_rightempty(p, base); BUG_ON(rcu_dereference_protected(*stackptr[-1], - lockdep_is_held(&peers.lock)) != t); + lockdep_is_held(&base->lock)) != t); **--stackptr = t->avl_left; - /* t is removed, t->v4daddr > x->v4daddr for any + /* t is removed, t->daddr > x->daddr for any * x in p->avl_left subtree. * Put t in the old place of p. */ RCU_INIT_POINTER(*delp[0], t); @@ -376,11 +405,11 @@ static void unlink_from_pool(struct inet_peer *p) BUG_ON(delp[1] != &p->avl_left); delp[1] = &t->avl_left; /* was &p->avl_left */ } - peer_avl_rebalance(stack, stackptr); - peers.total--; + peer_avl_rebalance(stack, stackptr, base); + base->total--; do_free = 1; } - spin_unlock_bh(&peers.lock); + spin_unlock_bh(&base->lock); if (do_free) call_rcu_bh(&p->rcu, inetpeer_free_rcu); @@ -395,6 +424,16 @@ static void unlink_from_pool(struct inet_peer *p) inet_putpeer(p); } +static struct inet_peer_base *family_to_base(int family) +{ + return (family == AF_INET ? &v4_peers : &v6_peers); +} + +static struct inet_peer_base *peer_to_base(struct inet_peer *p) +{ + return family_to_base(p->daddr.family); +} + /* May be called with local BH enabled. */ static int cleanup_once(unsigned long ttl) { @@ -428,21 +467,22 @@ static int cleanup_once(unsigned long ttl) * happen because of entry limits in route cache. */ return -1; - unlink_from_pool(p); + unlink_from_pool(p, peer_to_base(p)); return 0; } /* Called with or without local BH being disabled. */ -struct inet_peer *inet_getpeer(__be32 daddr, int create) +struct inet_peer *inet_getpeer(struct inetpeer_addr *daddr, int create) { - struct inet_peer *p; struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; + struct inet_peer_base *base = family_to_base(AF_INET); + struct inet_peer *p; /* Look up for the address quickly, lockless. * Because of a concurrent writer, we might not find an existing entry. */ rcu_read_lock_bh(); - p = lookup_rcu_bh(daddr); + p = lookup_rcu_bh(daddr, base); rcu_read_unlock_bh(); if (p) { @@ -456,50 +496,57 @@ struct inet_peer *inet_getpeer(__be32 daddr, int create) /* retry an exact lookup, taking the lock before. * At least, nodes should be hot in our cache. */ - spin_lock_bh(&peers.lock); - p = lookup(daddr, stack); + spin_lock_bh(&base->lock); + p = lookup(daddr, stack, base); if (p != peer_avl_empty) { atomic_inc(&p->refcnt); - spin_unlock_bh(&peers.lock); + spin_unlock_bh(&base->lock); /* Remove the entry from unused list if it was there. */ unlink_from_unused(p); return p; } p = create ? kmem_cache_alloc(peer_cachep, GFP_ATOMIC) : NULL; if (p) { - p->v4daddr = daddr; + p->daddr = *daddr; atomic_set(&p->refcnt, 1); atomic_set(&p->rid, 0); - atomic_set(&p->ip_id_count, secure_ip_id(daddr)); + atomic_set(&p->ip_id_count, secure_ip_id(daddr->a4)); p->tcp_ts_stamp = 0; INIT_LIST_HEAD(&p->unused); /* Link the node. */ - link_to_pool(p); - peers.total++; + link_to_pool(p, base); + base->total++; } - spin_unlock_bh(&peers.lock); + spin_unlock_bh(&base->lock); - if (peers.total >= inet_peer_threshold) + if (base->total >= inet_peer_threshold) /* Remove one less-recently-used entry. */ cleanup_once(0); return p; } +static int compute_total(void) +{ + return v4_peers.total + v6_peers.total; +} +EXPORT_SYMBOL_GPL(inet_getpeer); + /* Called with local BH disabled. */ static void peer_check_expire(unsigned long dummy) { unsigned long now = jiffies; - int ttl; + int ttl, total; - if (peers.total >= inet_peer_threshold) + total = compute_total(); + if (total >= inet_peer_threshold) ttl = inet_peer_minttl; else ttl = inet_peer_maxttl - (inet_peer_maxttl - inet_peer_minttl) / HZ * - peers.total / inet_peer_threshold * HZ; + total / inet_peer_threshold * HZ; while (!cleanup_once(ttl)) { if (jiffies != now) break; @@ -508,13 +555,14 @@ static void peer_check_expire(unsigned long dummy) /* Trigger the timer after inet_peer_gc_mintime .. inet_peer_gc_maxtime * interval depending on the total number of entries (more entries, * less interval). */ - if (peers.total >= inet_peer_threshold) + total = compute_total(); + if (total >= inet_peer_threshold) peer_periodic_timer.expires = jiffies + inet_peer_gc_mintime; else peer_periodic_timer.expires = jiffies + inet_peer_gc_maxtime - (inet_peer_gc_maxtime - inet_peer_gc_mintime) / HZ * - peers.total / inet_peer_threshold * HZ; + total / inet_peer_threshold * HZ; add_timer(&peer_periodic_timer); } @@ -530,3 +578,4 @@ void inet_putpeer(struct inet_peer *p) local_bh_enable(); } +EXPORT_SYMBOL_GPL(inet_putpeer); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index 1684408..a1151b8 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -45,6 +45,7 @@ #include <linux/udp.h> #include <linux/inet.h> #include <linux/netfilter_ipv4.h> +#include <net/inet_ecn.h> /* NOTE. Logic of IP defragmentation is parallel to corresponding IPv6 * code now. If you change something here, _PLEASE_ update ipv6/reassembly.c @@ -70,11 +71,28 @@ struct ipq { __be32 daddr; __be16 id; u8 protocol; + u8 ecn; /* RFC3168 support */ int iif; unsigned int rid; struct inet_peer *peer; }; +#define IPFRAG_ECN_CLEAR 0x01 /* one frag had INET_ECN_NOT_ECT */ +#define IPFRAG_ECN_SET_CE 0x04 /* one frag had INET_ECN_CE */ + +static inline u8 ip4_frag_ecn(u8 tos) +{ + tos = (tos & INET_ECN_MASK) + 1; + /* + * After the last operation we have (in binary): + * INET_ECN_NOT_ECT => 001 + * INET_ECN_ECT_1 => 010 + * INET_ECN_ECT_0 => 011 + * INET_ECN_CE => 100 + */ + return (tos & 2) ? 0 : tos; +} + static struct inet_frags ip4_frags; int ip_frag_nqueues(struct net *net) @@ -137,11 +155,12 @@ static void ip4_frag_init(struct inet_frag_queue *q, void *a) qp->protocol = arg->iph->protocol; qp->id = arg->iph->id; + qp->ecn = ip4_frag_ecn(arg->iph->tos); qp->saddr = arg->iph->saddr; qp->daddr = arg->iph->daddr; qp->user = arg->user; qp->peer = sysctl_ipfrag_max_dist ? - inet_getpeer(arg->iph->saddr, 1) : NULL; + inet_getpeer_v4(arg->iph->saddr, 1) : NULL; } static __inline__ void ip4_frag_free(struct inet_frag_queue *q) @@ -316,6 +335,7 @@ static int ip_frag_reinit(struct ipq *qp) qp->q.fragments = NULL; qp->q.fragments_tail = NULL; qp->iif = 0; + qp->ecn = 0; return 0; } @@ -328,6 +348,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) int flags, offset; int ihl, end; int err = -ENOENT; + u8 ecn; if (qp->q.last_in & INET_FRAG_COMPLETE) goto err; @@ -339,6 +360,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) goto err; } + ecn = ip4_frag_ecn(ip_hdr(skb)->tos); offset = ntohs(ip_hdr(skb)->frag_off); flags = offset & ~IP_OFFSET; offset &= IP_OFFSET; @@ -472,6 +494,7 @@ found: } qp->q.stamp = skb->tstamp; qp->q.meat += skb->len; + qp->ecn |= ecn; atomic_add(skb->truesize, &qp->q.net->mem); if (offset == 0) qp->q.last_in |= INET_FRAG_FIRST_IN; @@ -583,6 +606,17 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, iph = ip_hdr(head); iph->frag_off = 0; iph->tot_len = htons(len); + /* RFC3168 5.3 Fragmentation support + * If one fragment had INET_ECN_NOT_ECT, + * reassembled frame also has INET_ECN_NOT_ECT + * Elif one fragment had INET_ECN_CE + * reassembled frame also has INET_ECN_CE + */ + if (qp->ecn & IPFRAG_ECN_CLEAR) + iph->tos &= ~INET_ECN_MASK; + else if (qp->ecn & IPFRAG_ECN_SET_CE) + iph->tos |= INET_ECN_CE; + IP_INC_STATS_BH(net, IPSTATS_MIB_REASMOKS); qp->q.fragments = NULL; qp->q.fragments_tail = NULL; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index cab2057..eb68a0e 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -405,11 +405,11 @@ static struct ip_tunnel *ipgre_tunnel_locate(struct net *net, if (parms->name[0]) strlcpy(name, parms->name, IFNAMSIZ); else - sprintf(name, "gre%%d"); + strcpy(name, "gre%d"); dev = alloc_netdev(sizeof(*t), name, ipgre_tunnel_setup); if (!dev) - return NULL; + return NULL; dev_net_set(dev, net); @@ -772,16 +772,11 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev { struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { - .ip4_u = { - .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) - } - }, - .proto = IPPROTO_GRE - } -; + .fl4_dst = dst, + .fl4_src = tiph->saddr, + .fl4_tos = RT_TOS(tos), + .fl_gre_key = tunnel->parms.o_key + }; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { dev->stats.tx_carrier_errors++; goto tx_error; @@ -823,7 +818,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev !ipv4_is_multicast(tunnel->parms.iph.daddr)) || rt6->rt6i_dst.plen == 128) { rt6->rt6i_flags |= RTF_MODIFIED; - skb_dst(skb)->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(skb_dst(skb), RTAX_MTU, mtu); } } @@ -895,7 +890,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif else - iph->ttl = dst_metric(&rt->dst, RTAX_HOPLIMIT); + iph->ttl = ip4_dst_hoplimit(&rt->dst); } ((__be16 *)(iph + 1))[0] = tunnel->parms.o_flags; @@ -951,14 +946,11 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) if (iph->daddr) { struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { - .ip4_u = { - .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) - } - }, - .proto = IPPROTO_GRE + .fl4_dst = iph->daddr, + .fl4_src = iph->saddr, + .fl4_tos = RT_TOS(iph->tos), + .proto = IPPROTO_GRE, + .fl_gre_key = tunnel->parms.o_key }; struct rtable *rt; @@ -1216,14 +1208,11 @@ static int ipgre_open(struct net_device *dev) if (ipv4_is_multicast(t->parms.iph.daddr)) { struct flowi fl = { .oif = t->parms.link, - .nl_u = { - .ip4_u = { - .daddr = t->parms.iph.daddr, - .saddr = t->parms.iph.saddr, - .tos = RT_TOS(t->parms.iph.tos) - } - }, - .proto = IPPROTO_GRE + .fl4_dst = t->parms.iph.daddr, + .fl4_src = t->parms.iph.saddr, + .fl4_tos = RT_TOS(t->parms.iph.tos), + .proto = IPPROTO_GRE, + .fl_gre_key = t->parms.o_key }; struct rtable *rt; @@ -1775,3 +1764,4 @@ module_exit(ipgre_fini); MODULE_LICENSE("GPL"); MODULE_ALIAS_RTNL_LINK("gre"); MODULE_ALIAS_RTNL_LINK("gretap"); +MODULE_ALIAS("gre0"); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 439d2a3..04c7b3b 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -82,6 +82,7 @@ #include <linux/tcp.h> int sysctl_ip_default_ttl __read_mostly = IPDEFTTL; +EXPORT_SYMBOL(sysctl_ip_default_ttl); /* Generate a checksum for an outgoing IP datagram. */ __inline__ void ip_send_check(struct iphdr *iph) @@ -130,7 +131,7 @@ static inline int ip_select_ttl(struct inet_sock *inet, struct dst_entry *dst) int ttl = inet->uc_ttl; if (ttl < 0) - ttl = dst_metric(dst, RTAX_HOPLIMIT); + ttl = ip4_dst_hoplimit(dst); return ttl; } @@ -341,15 +342,13 @@ int ip_queue_xmit(struct sk_buff *skb) { struct flowi fl = { .oif = sk->sk_bound_dev_if, .mark = sk->sk_mark, - .nl_u = { .ip4_u = - { .daddr = daddr, - .saddr = inet->inet_saddr, - .tos = RT_CONN_FLAGS(sk) } }, + .fl4_dst = daddr, + .fl4_src = inet->inet_saddr, + .fl4_tos = RT_CONN_FLAGS(sk), .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), - .uli_u = { .ports = - { .sport = inet->inet_sport, - .dport = inet->inet_dport } } }; + .fl_ip_sport = inet->inet_sport, + .fl_ip_dport = inet->inet_dport }; /* If this fails, retransmit mechanism of transport layer will * keep trying until route appears or the connection times @@ -1404,14 +1403,11 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar { struct flowi fl = { .oif = arg->bound_dev_if, - .nl_u = { .ip4_u = - { .daddr = daddr, - .saddr = rt->rt_spec_dst, - .tos = RT_TOS(ip_hdr(skb)->tos) } }, - /* Not quite clean, but right. */ - .uli_u = { .ports = - { .sport = tcp_hdr(skb)->dest, - .dport = tcp_hdr(skb)->source } }, + .fl4_dst = daddr, + .fl4_src = rt->rt_spec_dst, + .fl4_tos = RT_TOS(ip_hdr(skb)->tos), + .fl_ip_sport = tcp_hdr(skb)->dest, + .fl_ip_dport = tcp_hdr(skb)->source, .proto = sk->sk_protocol, .flags = ip_reply_arg_flowi_flags(arg) }; security_skb_classify_flow(skb, &fl); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 3a6e1ec..2b09775 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -1191,13 +1191,13 @@ static int __init ic_dynamic(void) (ic_proto_enabled & IC_USE_DHCP) && ic_dhcp_msgtype != DHCPACK) { ic_got_reply = 0; - printk(","); + printk(KERN_CONT ","); continue; } #endif /* IPCONFIG_DHCP */ if (ic_got_reply) { - printk(" OK\n"); + printk(KERN_CONT " OK\n"); break; } @@ -1205,7 +1205,7 @@ static int __init ic_dynamic(void) continue; if (! --retries) { - printk(" timed out!\n"); + printk(KERN_CONT " timed out!\n"); break; } @@ -1215,7 +1215,7 @@ static int __init ic_dynamic(void) if (timeout > CONF_TIMEOUT_MAX) timeout = CONF_TIMEOUT_MAX; - printk("."); + printk(KERN_CONT "."); } #ifdef IPCONFIG_BOOTP @@ -1236,7 +1236,7 @@ static int __init ic_dynamic(void) ((ic_got_reply & IC_RARP) ? "RARP" : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), &ic_servaddr); - printk("my address is %pI4\n", &ic_myaddr); + printk(KERN_CONT "my address is %pI4\n", &ic_myaddr); return 0; } @@ -1468,19 +1468,19 @@ static int __init ip_auto_config(void) /* * Clue in the operator. */ - printk("IP-Config: Complete:"); - printk("\n device=%s", ic_dev->name); - printk(", addr=%pI4", &ic_myaddr); - printk(", mask=%pI4", &ic_netmask); - printk(", gw=%pI4", &ic_gateway); - printk(",\n host=%s, domain=%s, nis-domain=%s", + printk("IP-Config: Complete:\n"); + printk(" device=%s", ic_dev->name); + printk(KERN_CONT ", addr=%pI4", &ic_myaddr); + printk(KERN_CONT ", mask=%pI4", &ic_netmask); + printk(KERN_CONT ", gw=%pI4", &ic_gateway); + printk(KERN_CONT ",\n host=%s, domain=%s, nis-domain=%s", utsname()->nodename, ic_domain, utsname()->domainname); - printk(",\n bootserver=%pI4", &ic_servaddr); - printk(", rootserver=%pI4", &root_server_addr); - printk(", rootpath=%s", root_server_path); + printk(KERN_CONT ",\n bootserver=%pI4", &ic_servaddr); + printk(KERN_CONT ", rootserver=%pI4", &root_server_addr); + printk(KERN_CONT ", rootpath=%s", root_server_path); if (ic_dev_mtu) - printk(", mtu=%d", ic_dev_mtu); - printk("\n"); + printk(KERN_CONT ", mtu=%d", ic_dev_mtu); + printk(KERN_CONT "\n"); #endif /* !SILENT */ return 0; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index cd300aa..988f52f 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -463,13 +463,9 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { - .ip4_u = { - .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) - } - }, + .fl4_dst = dst, + .fl4_src= tiph->saddr, + .fl4_tos = RT_TOS(tos), .proto = IPPROTO_IPIP }; @@ -589,13 +585,9 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) if (iph->daddr) { struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { - .ip4_u = { - .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) - } - }, + .fl4_dst = iph->daddr, + .fl4_src = iph->saddr, + .fl4_tos = RT_TOS(iph->tos), .proto = IPPROTO_IPIP }; struct rtable *rt; @@ -921,3 +913,4 @@ static void __exit ipip_fini(void) module_init(ipip_init); module_exit(ipip_fini); MODULE_LICENSE("GPL"); +MODULE_ALIAS("tunl0"); diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index ef2b008..3f3a9af 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1537,13 +1537,9 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (vif->flags & VIFF_TUNNEL) { struct flowi fl = { .oif = vif->link, - .nl_u = { - .ip4_u = { - .daddr = vif->remote, - .saddr = vif->local, - .tos = RT_TOS(iph->tos) - } - }, + .fl4_dst = vif->remote, + .fl4_src = vif->local, + .fl4_tos = RT_TOS(iph->tos), .proto = IPPROTO_IPIP }; @@ -1553,12 +1549,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, } else { struct flowi fl = { .oif = vif->link, - .nl_u = { - .ip4_u = { - .daddr = iph->daddr, - .tos = RT_TOS(iph->tos) - } - }, + .fl4_dst = iph->daddr, + .fl4_tos = RT_TOS(iph->tos), .proto = IPPROTO_IPIP }; diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index d88a46c..994a1f2 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -31,10 +31,10 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) * packets with foreign saddr to appear on the NF_INET_LOCAL_OUT hook. */ if (addr_type == RTN_LOCAL) { - fl.nl_u.ip4_u.daddr = iph->daddr; + fl.fl4_dst = iph->daddr; if (type == RTN_LOCAL) - fl.nl_u.ip4_u.saddr = iph->saddr; - fl.nl_u.ip4_u.tos = RT_TOS(iph->tos); + fl.fl4_src = iph->saddr; + fl.fl4_tos = RT_TOS(iph->tos); fl.oif = skb->sk ? skb->sk->sk_bound_dev_if : 0; fl.mark = skb->mark; fl.flags = skb->sk ? inet_sk_flowi_flags(skb->sk) : 0; @@ -47,7 +47,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) } else { /* non-local src, find valid iif to satisfy * rp-filter when calling ip_route_input. */ - fl.nl_u.ip4_u.daddr = iph->saddr; + fl.fl4_dst = iph->saddr; if (ip_route_output_key(net, &rt, &fl) != 0) return -1; diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index 4811159..19eb59d 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -3,15 +3,15 @@ # # objects for l3 independent conntrack -nf_conntrack_ipv4-objs := nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o +nf_conntrack_ipv4-y := nf_conntrack_l3proto_ipv4.o nf_conntrack_proto_icmp.o ifeq ($(CONFIG_NF_CONNTRACK_PROC_COMPAT),y) ifeq ($(CONFIG_PROC_FS),y) nf_conntrack_ipv4-objs += nf_conntrack_l3proto_ipv4_compat.o endif endif -nf_nat-objs := nf_nat_core.o nf_nat_helper.o nf_nat_proto_unknown.o nf_nat_proto_common.o nf_nat_proto_tcp.o nf_nat_proto_udp.o nf_nat_proto_icmp.o -iptable_nat-objs := nf_nat_rule.o nf_nat_standalone.o +nf_nat-y := nf_nat_core.o nf_nat_helper.o nf_nat_proto_unknown.o nf_nat_proto_common.o nf_nat_proto_tcp.o nf_nat_proto_udp.o nf_nat_proto_icmp.o +iptable_nat-y := nf_nat_rule.o nf_nat_standalone.o # connection tracking obj-$(CONFIG_NF_CONNTRACK_IPV4) += nf_conntrack_ipv4.o diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 3fac340..47e5178 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -883,6 +883,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(NFPROTO_ARP, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1350,6 +1351,7 @@ static int translate_compat_table(const char *name, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(NFPROTO_ARP); + xt_compat_init_offsets(NFPROTO_ARP, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index a846d63..c5a75d7 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -1080,6 +1080,7 @@ static int compat_table_info(const struct xt_table_info *info, memcpy(newinfo, info, offsetof(struct xt_table_info, entries)); newinfo->initial_entries = 0; loc_cpu_entry = info->entries[raw_smp_processor_id()]; + xt_compat_init_offsets(AF_INET, info->number); xt_entry_foreach(iter, loc_cpu_entry, info->size) { ret = compat_calc_entry(iter, info, loc_cpu_entry, newinfo); if (ret != 0) @@ -1681,6 +1682,7 @@ translate_compat_table(struct net *net, duprintf("translate_compat_table: size %u\n", info->size); j = 0; xt_compat_lock(AF_INET); + xt_compat_init_offsets(AF_INET, number); /* Walk through entries, checking offsets. */ xt_entry_foreach(iter0, entry0, total_size) { ret = check_compat_entry_size_and_hooks(iter0, info, &size, diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index 43eec80..1ff79e5 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -116,7 +116,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; - niph->ttl = dst_metric(skb_dst(nskb), RTAX_HOPLIMIT); + niph->ttl = ip4_dst_hoplimit(skb_dst(nskb)); /* "Never happens" */ if (nskb->len > dst_mtu(skb_dst(nskb))) diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index ab9c05c..5585980 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -100,7 +100,7 @@ static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) ret = security_secid_to_secctx(ct->secmark, &secctx, &len); if (ret) - return ret; + return 0; ret = seq_printf(s, "secctx=%s ", secctx); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4ae1f20..b14ec7d 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -59,13 +59,13 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) local_bh_enable(); socket_seq_show(seq); - seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", + seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, tcp_death_row.tw_count, sockets, - atomic_read(&tcp_memory_allocated)); - seq_printf(seq, "UDP: inuse %d mem %d\n", + atomic_long_read(&tcp_memory_allocated)); + seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), - atomic_read(&udp_memory_allocated)); + atomic_long_read(&udp_memory_allocated)); seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", @@ -253,6 +253,7 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPMinTTLDrop", LINUX_MIB_TCPMINTTLDROP), SNMP_MIB_ITEM("TCPDeferAcceptDrop", LINUX_MIB_TCPDEFERACCEPTDROP), SNMP_MIB_ITEM("IPReversePathFilter", LINUX_MIB_IPRPFILTER), + SNMP_MIB_ITEM("TCPTimeWaitOverflow", LINUX_MIB_TCPTIMEWAITOVERFLOW), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 1f85ef2..a3d5ab7 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -549,10 +549,9 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, { struct flowi fl = { .oif = ipc.oif, .mark = sk->sk_mark, - .nl_u = { .ip4_u = - { .daddr = daddr, - .saddr = saddr, - .tos = tos } }, + .fl4_dst = daddr, + .fl4_src = saddr, + .fl4_tos = tos, .proto = inet->hdrincl ? IPPROTO_RAW : sk->sk_protocol, }; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index f70ae1b..3e5b7cc 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -139,6 +139,8 @@ static unsigned long expires_ljiffies; */ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); +static unsigned int ipv4_default_advmss(const struct dst_entry *dst); +static unsigned int ipv4_default_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -155,6 +157,8 @@ static struct dst_ops ipv4_dst_ops = { .protocol = cpu_to_be16(ETH_P_IP), .gc = rt_garbage_collect, .check = ipv4_dst_check, + .default_advmss = ipv4_default_advmss, + .default_mtu = ipv4_default_mtu, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, .negative_advice = ipv4_negative_advice, @@ -383,8 +387,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) (__force u32)r->rt_gateway, r->rt_flags, atomic_read(&r->dst.__refcnt), r->dst.__use, 0, (__force u32)r->rt_src, - (dst_metric(&r->dst, RTAX_ADVMSS) ? - (int)dst_metric(&r->dst, RTAX_ADVMSS) + 40 : 0), + dst_metric_advmss(&r->dst) + 40, dst_metric(&r->dst, RTAX_WINDOW), (int)((dst_metric(&r->dst, RTAX_RTT) >> 3) + dst_metric(&r->dst, RTAX_RTTVAR)), @@ -684,17 +687,17 @@ static inline bool rt_caching(const struct net *net) static inline bool compare_hash_inputs(const struct flowi *fl1, const struct flowi *fl2) { - return ((((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) | - ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) | + return ((((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) | + ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) | (fl1->iif ^ fl2->iif)) == 0); } static inline int compare_keys(struct flowi *fl1, struct flowi *fl2) { - return (((__force u32)fl1->nl_u.ip4_u.daddr ^ (__force u32)fl2->nl_u.ip4_u.daddr) | - ((__force u32)fl1->nl_u.ip4_u.saddr ^ (__force u32)fl2->nl_u.ip4_u.saddr) | + return (((__force u32)fl1->fl4_dst ^ (__force u32)fl2->fl4_dst) | + ((__force u32)fl1->fl4_src ^ (__force u32)fl2->fl4_src) | (fl1->mark ^ fl2->mark) | - (*(u16 *)&fl1->nl_u.ip4_u.tos ^ *(u16 *)&fl2->nl_u.ip4_u.tos) | + (*(u16 *)&fl1->fl4_tos ^ *(u16 *)&fl2->fl4_tos) | (fl1->oif ^ fl2->oif) | (fl1->iif ^ fl2->iif)) == 0; } @@ -714,13 +717,15 @@ static inline int rt_is_expired(struct rtable *rth) * Can be called by a softirq or a process. * In the later case, we want to be reschedule if necessary */ -static void rt_do_flush(int process_context) +static void rt_do_flush(struct net *net, int process_context) { unsigned int i; struct rtable *rth, *next; - struct rtable * tail; for (i = 0; i <= rt_hash_mask; i++) { + struct rtable __rcu **pprev; + struct rtable *list; + if (process_context && need_resched()) cond_resched(); rth = rcu_dereference_raw(rt_hash_table[i].chain); @@ -728,50 +733,32 @@ static void rt_do_flush(int process_context) continue; spin_lock_bh(rt_hash_lock_addr(i)); -#ifdef CONFIG_NET_NS - { - struct rtable __rcu **prev; - struct rtable *p; - rth = rcu_dereference_protected(rt_hash_table[i].chain, + list = NULL; + pprev = &rt_hash_table[i].chain; + rth = rcu_dereference_protected(*pprev, lockdep_is_held(rt_hash_lock_addr(i))); - /* defer releasing the head of the list after spin_unlock */ - for (tail = rth; tail; - tail = rcu_dereference_protected(tail->dst.rt_next, - lockdep_is_held(rt_hash_lock_addr(i)))) - if (!rt_is_expired(tail)) - break; - if (rth != tail) - rt_hash_table[i].chain = tail; - - /* call rt_free on entries after the tail requiring flush */ - prev = &rt_hash_table[i].chain; - for (p = rcu_dereference_protected(*prev, + while (rth) { + next = rcu_dereference_protected(rth->dst.rt_next, lockdep_is_held(rt_hash_lock_addr(i))); - p != NULL; - p = next) { - next = rcu_dereference_protected(p->dst.rt_next, - lockdep_is_held(rt_hash_lock_addr(i))); - if (!rt_is_expired(p)) { - prev = &p->dst.rt_next; + + if (!net || + net_eq(dev_net(rth->dst.dev), net)) { + rcu_assign_pointer(*pprev, next); + rcu_assign_pointer(rth->dst.rt_next, list); + list = rth; } else { - *prev = next; - rt_free(p); + pprev = &rth->dst.rt_next; } + rth = next; } - } -#else - rth = rcu_dereference_protected(rt_hash_table[i].chain, - lockdep_is_held(rt_hash_lock_addr(i))); - rcu_assign_pointer(rt_hash_table[i].chain, NULL); - tail = NULL; -#endif + spin_unlock_bh(rt_hash_lock_addr(i)); - for (; rth != tail; rth = next) { - next = rcu_dereference_protected(rth->dst.rt_next, 1); - rt_free(rth); + for (; list; list = next) { + next = rcu_dereference_protected(list->dst.rt_next, 1); + rt_free(list); } } } @@ -919,13 +906,13 @@ void rt_cache_flush(struct net *net, int delay) { rt_cache_invalidate(net); if (delay >= 0) - rt_do_flush(!in_softirq()); + rt_do_flush(net, !in_softirq()); } /* Flush previous cache invalidated entries from the cache */ -void rt_cache_flush_batch(void) +void rt_cache_flush_batch(struct net *net) { - rt_do_flush(!in_softirq()); + rt_do_flush(net, !in_softirq()); } static void rt_emergency_hash_rebuild(struct net *net) @@ -1289,7 +1276,7 @@ void rt_bind_peer(struct rtable *rt, int create) { struct inet_peer *peer; - peer = inet_getpeer(rt->rt_dst, create); + peer = inet_getpeer_v4(rt->rt_dst, create); if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) inet_putpeer(peer); @@ -1686,11 +1673,14 @@ unsigned short ip_rt_frag_needed(struct net *net, struct iphdr *iph, if (mtu < dst_mtu(&rth->dst)) { dst_confirm(&rth->dst); if (mtu < ip_rt_min_pmtu) { + u32 lock = dst_metric(&rth->dst, + RTAX_LOCK); mtu = ip_rt_min_pmtu; - rth->dst.metrics[RTAX_LOCK-1] |= - (1 << RTAX_MTU); + lock |= (1 << RTAX_MTU); + dst_metric_set(&rth->dst, RTAX_LOCK, + lock); } - rth->dst.metrics[RTAX_MTU-1] = mtu; + dst_metric_set(&rth->dst, RTAX_MTU, mtu); dst_set_expires(&rth->dst, ip_rt_mtu_expires); } @@ -1708,10 +1698,11 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) if (dst_mtu(dst) > mtu && mtu >= 68 && !(dst_metric_locked(dst, RTAX_MTU))) { if (mtu < ip_rt_min_pmtu) { + u32 lock = dst_metric(dst, RTAX_LOCK); mtu = ip_rt_min_pmtu; - dst->metrics[RTAX_LOCK-1] |= (1 << RTAX_MTU); + dst_metric_set(dst, RTAX_LOCK, lock | (1 << RTAX_MTU)); } - dst->metrics[RTAX_MTU-1] = mtu; + dst_metric_set(dst, RTAX_MTU, mtu); dst_set_expires(dst, ip_rt_mtu_expires); call_netevent_notifiers(NETEVENT_PMTU_UPDATE, dst); } @@ -1794,38 +1785,55 @@ static void set_class_tag(struct rtable *rt, u32 tag) } #endif +static unsigned int ipv4_default_advmss(const struct dst_entry *dst) +{ + unsigned int advmss = dst_metric_raw(dst, RTAX_ADVMSS); + + if (advmss == 0) { + advmss = max_t(unsigned int, dst->dev->mtu - 40, + ip_rt_min_advmss); + if (advmss > 65535 - 40) + advmss = 65535 - 40; + } + return advmss; +} + +static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +{ + unsigned int mtu = dst->dev->mtu; + + if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { + const struct rtable *rt = (const struct rtable *) dst; + + if (rt->rt_gateway != rt->rt_dst && mtu > 576) + mtu = 576; + } + + if (mtu > IP_MAX_MTU) + mtu = IP_MAX_MTU; + + return mtu; +} + static void rt_set_nexthop(struct rtable *rt, struct fib_result *res, u32 itag) { + struct dst_entry *dst = &rt->dst; struct fib_info *fi = res->fi; if (fi) { if (FIB_RES_GW(*res) && FIB_RES_NH(*res).nh_scope == RT_SCOPE_LINK) rt->rt_gateway = FIB_RES_GW(*res); - memcpy(rt->dst.metrics, fi->fib_metrics, - sizeof(rt->dst.metrics)); - if (fi->fib_mtu == 0) { - rt->dst.metrics[RTAX_MTU-1] = rt->dst.dev->mtu; - if (dst_metric_locked(&rt->dst, RTAX_MTU) && - rt->rt_gateway != rt->rt_dst && - rt->dst.dev->mtu > 576) - rt->dst.metrics[RTAX_MTU-1] = 576; - } + dst_import_metrics(dst, fi->fib_metrics); #ifdef CONFIG_IP_ROUTE_CLASSID - rt->dst.tclassid = FIB_RES_NH(*res).nh_tclassid; + dst->tclassid = FIB_RES_NH(*res).nh_tclassid; #endif - } else - rt->dst.metrics[RTAX_MTU-1]= rt->dst.dev->mtu; - - if (dst_metric(&rt->dst, RTAX_HOPLIMIT) == 0) - rt->dst.metrics[RTAX_HOPLIMIT-1] = sysctl_ip_default_ttl; - if (dst_mtu(&rt->dst) > IP_MAX_MTU) - rt->dst.metrics[RTAX_MTU-1] = IP_MAX_MTU; - if (dst_metric(&rt->dst, RTAX_ADVMSS) == 0) - rt->dst.metrics[RTAX_ADVMSS-1] = max_t(unsigned int, rt->dst.dev->mtu - 40, - ip_rt_min_advmss); - if (dst_metric(&rt->dst, RTAX_ADVMSS) > 65535 - 40) - rt->dst.metrics[RTAX_ADVMSS-1] = 65535 - 40; + } + + if (dst_mtu(dst) > IP_MAX_MTU) + dst_metric_set(dst, RTAX_MTU, IP_MAX_MTU); + if (dst_metric_raw(dst, RTAX_ADVMSS) > 65535 - 40) + dst_metric_set(dst, RTAX_ADVMSS, 65535 - 40); #ifdef CONFIG_IP_ROUTE_CLASSID #ifdef CONFIG_IP_MULTIPLE_TABLES @@ -2089,12 +2097,10 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, { struct fib_result res; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = daddr, - .saddr = saddr, - .tos = tos, - .scope = RT_SCOPE_UNIVERSE, - } }, + struct flowi fl = { .fl4_dst = daddr, + .fl4_src = saddr, + .fl4_tos = tos, + .fl4_scope = RT_SCOPE_UNIVERSE, .mark = skb->mark, .iif = dev->ifindex }; unsigned flags = 0; @@ -2480,14 +2486,11 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, const struct flowi *oldflp) { u32 tos = RT_FL_TOS(oldflp); - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = oldflp->fl4_dst, - .saddr = oldflp->fl4_src, - .tos = tos & IPTOS_RT_MASK, - .scope = ((tos & RTO_ONLINK) ? - RT_SCOPE_LINK : - RT_SCOPE_UNIVERSE), - } }, + struct flowi fl = { .fl4_dst = oldflp->fl4_dst, + .fl4_src = oldflp->fl4_src, + .fl4_tos = tos & IPTOS_RT_MASK, + .fl4_scope = ((tos & RTO_ONLINK) ? + RT_SCOPE_LINK : RT_SCOPE_UNIVERSE), .mark = oldflp->mark, .iif = net->loopback_dev->ifindex, .oif = oldflp->oif }; @@ -2559,9 +2562,10 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, goto out; /* RACE: Check return value of inet_select_addr instead. */ - if (rcu_dereference(dev_out->ip_ptr) == NULL) - goto out; /* Wrong error code */ - + if (!(dev_out->flags & IFF_UP) || !__in_dev_get_rcu(dev_out)) { + err = -ENETUNREACH; + goto out; + } if (ipv4_is_local_multicast(oldflp->fl4_dst) || ipv4_is_lbcast(oldflp->fl4_dst)) { if (!fl.fl4_src) @@ -2622,8 +2626,12 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, } if (res.type == RTN_LOCAL) { - if (!fl.fl4_src) - fl.fl4_src = fl.fl4_dst; + if (!fl.fl4_src) { + if (res.fi->fib_prefsrc) + fl.fl4_src = res.fi->fib_prefsrc; + else + fl.fl4_src = fl.fl4_dst; + } dev_out = net->loopback_dev; fl.oif = dev_out->ifindex; res.fi = NULL; @@ -2725,7 +2733,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi new->__use = 1; new->input = dst_discard; new->output = dst_discard; - memcpy(new->metrics, ort->dst.metrics, RTAX_MAX*sizeof(u32)); + dst_copy_metrics(new, &ort->dst); new->dev = ort->dst.dev; if (new->dev) @@ -2832,7 +2840,7 @@ static int rt_fill_info(struct net *net, if (rt->rt_dst != rt->rt_gateway) NLA_PUT_BE32(skb, RTA_GATEWAY, rt->rt_gateway); - if (rtnetlink_put_metrics(skb, rt->dst.metrics) < 0) + if (rtnetlink_put_metrics(skb, dst_metrics_ptr(&rt->dst)) < 0) goto nla_put_failure; if (rt->fl.mark) @@ -2944,13 +2952,9 @@ static int inet_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr* nlh, void err = -rt->dst.error; } else { struct flowi fl = { - .nl_u = { - .ip4_u = { - .daddr = dst, - .saddr = src, - .tos = rtm->rtm_tos, - }, - }, + .fl4_dst = dst, + .fl4_src = src, + .fl4_tos = rtm->rtm_tos, .oif = tb[RTA_OIF] ? nla_get_u32(tb[RTA_OIF]) : 0, .mark = mark, }; diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 650cace..4751920 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -346,17 +346,14 @@ struct sock *cookie_v4_check(struct sock *sk, struct sk_buff *skb, */ { struct flowi fl = { .mark = sk->sk_mark, - .nl_u = { .ip4_u = - { .daddr = ((opt && opt->srr) ? - opt->faddr : - ireq->rmt_addr), - .saddr = ireq->loc_addr, - .tos = RT_CONN_FLAGS(sk) } }, + .fl4_dst = ((opt && opt->srr) ? + opt->faddr : ireq->rmt_addr), + .fl4_src = ireq->loc_addr, + .fl4_tos = RT_CONN_FLAGS(sk), .proto = IPPROTO_TCP, .flags = inet_sk_flowi_flags(sk), - .uli_u = { .ports = - { .sport = th->dest, - .dport = th->source } } }; + .fl_ip_sport = th->dest, + .fl_ip_dport = th->source }; security_req_classify_flow(req, &fl); if (ip_route_output_key(sock_net(sk), &rt, &fl)) { reqsk_free(req); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index d96c1da..1a45665 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -26,6 +26,10 @@ static int zero; static int tcp_retr1_max = 255; static int ip_local_port_range_min[] = { 1, 1 }; static int ip_local_port_range_max[] = { 65535, 65535 }; +static int tcp_adv_win_scale_min = -31; +static int tcp_adv_win_scale_max = 31; +static int ip_ttl_min = 1; +static int ip_ttl_max = 255; /* Update system visible IP port range */ static void set_local_port_range(int range[2]) @@ -153,8 +157,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_ip_default_ttl, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = ipv4_doint_and_flush, - .extra2 = &init_net, + .proc_handler = proc_dointvec_minmax, + .extra1 = &ip_ttl_min, + .extra2 = &ip_ttl_max, }, { .procname = "ip_no_pmtu_disc", @@ -398,7 +403,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_mem, .maxlen = sizeof(sysctl_tcp_mem), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_doulongvec_minmax }, { .procname = "tcp_wmem", @@ -426,7 +431,9 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_adv_win_scale, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .proc_handler = proc_dointvec_minmax, + .extra1 = &tcp_adv_win_scale_min, + .extra2 = &tcp_adv_win_scale_max, }, { .procname = "tcp_tw_reuse", @@ -602,8 +609,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, - .proc_handler = proc_dointvec_minmax, - .extra1 = &zero + .proc_handler = proc_doulongvec_minmax, }, { .procname = "udp_rmem_min", diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 5f738c5..6c11eec 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,7 +282,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); -int sysctl_tcp_mem[3] __read_mostly; +long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; @@ -290,7 +290,7 @@ EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); -atomic_t tcp_memory_allocated; /* Current allocated memory. */ +atomic_long_t tcp_memory_allocated; /* Current allocated memory. */ EXPORT_SYMBOL(tcp_memory_allocated); /* @@ -2244,7 +2244,7 @@ static int do_tcp_setsockopt(struct sock *sk, int level, /* Values greater than interface MTU won't take effect. However * at the point when this call is done we typically don't yet * know which interface is going to be used */ - if (val < 8 || val > MAX_TCP_WINDOW) { + if (val < TCP_MIN_MSS || val > MAX_TCP_WINDOW) { err = -EINVAL; break; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3357f69..2549b29 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -259,8 +259,11 @@ static void tcp_fixup_sndbuf(struct sock *sk) int sndmem = tcp_sk(sk)->rx_opt.mss_clamp + MAX_TCP_HEADER + 16 + sizeof(struct sk_buff); - if (sk->sk_sndbuf < 3 * sndmem) - sk->sk_sndbuf = min(3 * sndmem, sysctl_tcp_wmem[2]); + if (sk->sk_sndbuf < 3 * sndmem) { + sk->sk_sndbuf = 3 * sndmem; + if (sk->sk_sndbuf > sysctl_tcp_wmem[2]) + sk->sk_sndbuf = sysctl_tcp_wmem[2]; + } } /* 2. Tuning advertised window (window_clamp, rcv_ssthresh) @@ -396,7 +399,7 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && !tcp_memory_pressure && - atomic_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { + atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } @@ -731,7 +734,7 @@ void tcp_update_metrics(struct sock *sk) * Reset our results. */ if (!(dst_metric_locked(dst, RTAX_RTT))) - dst->metrics[RTAX_RTT - 1] = 0; + dst_metric_set(dst, RTAX_RTT, 0); return; } @@ -773,34 +776,38 @@ void tcp_update_metrics(struct sock *sk) if (dst_metric(dst, RTAX_SSTHRESH) && !dst_metric_locked(dst, RTAX_SSTHRESH) && (tp->snd_cwnd >> 1) > dst_metric(dst, RTAX_SSTHRESH)) - dst->metrics[RTAX_SSTHRESH-1] = tp->snd_cwnd >> 1; + dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_cwnd >> 1); if (!dst_metric_locked(dst, RTAX_CWND) && tp->snd_cwnd > dst_metric(dst, RTAX_CWND)) - dst->metrics[RTAX_CWND - 1] = tp->snd_cwnd; + dst_metric_set(dst, RTAX_CWND, tp->snd_cwnd); } else if (tp->snd_cwnd > tp->snd_ssthresh && icsk->icsk_ca_state == TCP_CA_Open) { /* Cong. avoidance phase, cwnd is reliable. */ if (!dst_metric_locked(dst, RTAX_SSTHRESH)) - dst->metrics[RTAX_SSTHRESH-1] = - max(tp->snd_cwnd >> 1, tp->snd_ssthresh); + dst_metric_set(dst, RTAX_SSTHRESH, + max(tp->snd_cwnd >> 1, tp->snd_ssthresh)); if (!dst_metric_locked(dst, RTAX_CWND)) - dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_cwnd) >> 1; + dst_metric_set(dst, RTAX_CWND, + (dst_metric(dst, RTAX_CWND) + + tp->snd_cwnd) >> 1); } else { /* Else slow start did not finish, cwnd is non-sense, ssthresh may be also invalid. */ if (!dst_metric_locked(dst, RTAX_CWND)) - dst->metrics[RTAX_CWND-1] = (dst_metric(dst, RTAX_CWND) + tp->snd_ssthresh) >> 1; + dst_metric_set(dst, RTAX_CWND, + (dst_metric(dst, RTAX_CWND) + + tp->snd_ssthresh) >> 1); if (dst_metric(dst, RTAX_SSTHRESH) && !dst_metric_locked(dst, RTAX_SSTHRESH) && tp->snd_ssthresh > dst_metric(dst, RTAX_SSTHRESH)) - dst->metrics[RTAX_SSTHRESH-1] = tp->snd_ssthresh; + dst_metric_set(dst, RTAX_SSTHRESH, tp->snd_ssthresh); } if (!dst_metric_locked(dst, RTAX_REORDERING)) { if (dst_metric(dst, RTAX_REORDERING) < tp->reordering && tp->reordering != sysctl_tcp_reordering) - dst->metrics[RTAX_REORDERING-1] = tp->reordering; + dst_metric_set(dst, RTAX_REORDERING, tp->reordering); } } } @@ -909,25 +916,20 @@ static void tcp_init_metrics(struct sock *sk) tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); } tcp_set_rto(sk); - if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) - goto reset; - -cwnd: - tp->snd_cwnd = tcp_init_cwnd(tp, dst); - tp->snd_cwnd_stamp = tcp_time_stamp; - return; - + if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) { reset: - /* Play conservative. If timestamps are not - * supported, TCP will fail to recalculate correct - * rtt, if initial rto is too small. FORGET ALL AND RESET! - */ - if (!tp->rx_opt.saw_tstamp && tp->srtt) { - tp->srtt = 0; - tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT; - inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; + /* Play conservative. If timestamps are not + * supported, TCP will fail to recalculate correct + * rtt, if initial rto is too small. FORGET ALL AND RESET! + */ + if (!tp->rx_opt.saw_tstamp && tp->srtt) { + tp->srtt = 0; + tp->mdev = tp->mdev_max = tp->rttvar = TCP_TIMEOUT_INIT; + inet_csk(sk)->icsk_rto = TCP_TIMEOUT_INIT; + } } - goto cwnd; + tp->snd_cwnd = tcp_init_cwnd(tp, dst); + tp->snd_cwnd_stamp = tcp_time_stamp; } static void tcp_update_reordering(struct sock *sk, const int metric, @@ -4861,7 +4863,7 @@ static int tcp_should_expand_sndbuf(struct sock *sk) return 0; /* If we are under soft global TCP memory pressure, do not expand. */ - if (atomic_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) return 0; /* If we filled the congestion window, do not expand. */ diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 8f8527d..856f684 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -415,6 +415,9 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) !icsk->icsk_backoff) break; + if (sock_owned_by_user(sk)) + break; + icsk->icsk_backoff--; inet_csk(sk)->icsk_rto = __tcp_set_rto(tp) << icsk->icsk_backoff; @@ -429,11 +432,6 @@ void tcp_v4_err(struct sk_buff *icmp_skb, u32 info) if (remaining) { inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, remaining, TCP_RTO_MAX); - } else if (sock_owned_by_user(sk)) { - /* RTO revert clocked out retransmission, - * but socket is locked. Will defer. */ - inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, - HZ/20, TCP_RTO_MAX); } else { /* RTO revert clocked out retransmission. * Will retransmit now */ @@ -1212,12 +1210,6 @@ static const struct tcp_request_sock_ops tcp_request_sock_ipv4_ops = { }; #endif -static struct timewait_sock_ops tcp_timewait_sock_ops = { - .twsk_obj_size = sizeof(struct tcp_timewait_sock), - .twsk_unique = tcp_twsk_unique, - .twsk_destructor= tcp_twsk_destructor, -}; - int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) { struct tcp_extend_values tmp_ext; @@ -1349,7 +1341,7 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) tcp_death_row.sysctl_tw_recycle && (dst = inet_csk_route_req(sk, req)) != NULL && (peer = rt_get_peer((struct rtable *)dst)) != NULL && - peer->v4daddr == saddr) { + peer->daddr.a4 == saddr) { inet_peer_refcheck(peer); if ((u32)get_seconds() - peer->tcp_ts_stamp < TCP_PAWS_MSL && (s32)(peer->tcp_ts - req->ts_recent) > @@ -1444,7 +1436,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, tcp_mtup_init(newsk); tcp_sync_mss(newsk, dst_mtu(dst)); - newtp->advmss = dst_metric(dst, RTAX_ADVMSS); + newtp->advmss = dst_metric_advmss(dst); if (tcp_sk(sk)->rx_opt.user_mss && tcp_sk(sk)->rx_opt.user_mss < newtp->advmss) newtp->advmss = tcp_sk(sk)->rx_opt.user_mss; @@ -1765,64 +1757,40 @@ do_time_wait: goto discard_it; } -/* VJ's idea. Save last timestamp seen from this destination - * and hold it at least for normal timewait interval to use for duplicate - * segment detection in subsequent connections, before they enter synchronized - * state. - */ - -int tcp_v4_remember_stamp(struct sock *sk) +struct inet_peer *tcp_v4_get_peer(struct sock *sk, bool *release_it) { + struct rtable *rt = (struct rtable *) __sk_dst_get(sk); struct inet_sock *inet = inet_sk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct rtable *rt = (struct rtable *)__sk_dst_get(sk); - struct inet_peer *peer = NULL; - int release_it = 0; + struct inet_peer *peer; if (!rt || rt->rt_dst != inet->inet_daddr) { - peer = inet_getpeer(inet->inet_daddr, 1); - release_it = 1; + peer = inet_getpeer_v4(inet->inet_daddr, 1); + *release_it = true; } else { if (!rt->peer) rt_bind_peer(rt, 1); peer = rt->peer; + *release_it = false; } - if (peer) { - if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || - ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && - peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { - peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; - peer->tcp_ts = tp->rx_opt.ts_recent; - } - if (release_it) - inet_putpeer(peer); - return 1; - } - - return 0; + return peer; } -EXPORT_SYMBOL(tcp_v4_remember_stamp); +EXPORT_SYMBOL(tcp_v4_get_peer); -int tcp_v4_tw_remember_stamp(struct inet_timewait_sock *tw) +void *tcp_v4_tw_get_peer(struct sock *sk) { - struct inet_peer *peer = inet_getpeer(tw->tw_daddr, 1); - - if (peer) { - const struct tcp_timewait_sock *tcptw = tcp_twsk((struct sock *)tw); - - if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || - ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && - peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { - peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; - peer->tcp_ts = tcptw->tw_ts_recent; - } - inet_putpeer(peer); - return 1; - } + struct inet_timewait_sock *tw = inet_twsk(sk); - return 0; + return inet_getpeer_v4(tw->tw_daddr, 1); } +EXPORT_SYMBOL(tcp_v4_tw_get_peer); + +static struct timewait_sock_ops tcp_timewait_sock_ops = { + .twsk_obj_size = sizeof(struct tcp_timewait_sock), + .twsk_unique = tcp_twsk_unique, + .twsk_destructor= tcp_twsk_destructor, + .twsk_getpeer = tcp_v4_tw_get_peer, +}; const struct inet_connection_sock_af_ops ipv4_specific = { .queue_xmit = ip_queue_xmit, @@ -1830,7 +1798,7 @@ const struct inet_connection_sock_af_ops ipv4_specific = { .rebuild_header = inet_sk_rebuild_header, .conn_request = tcp_v4_conn_request, .syn_recv_sock = tcp_v4_syn_recv_sock, - .remember_stamp = tcp_v4_remember_stamp, + .get_peer = tcp_v4_get_peer, .net_header_len = sizeof(struct iphdr), .setsockopt = ip_setsockopt, .getsockopt = ip_getsockopt, @@ -2032,7 +2000,7 @@ static void *listening_get_next(struct seq_file *seq, void *cur) get_req: req = icsk->icsk_accept_queue.listen_opt->syn_table[st->sbucket]; } - sk = sk_next(st->syn_wait_sk); + sk = sk_nulls_next(st->syn_wait_sk); st->state = TCP_SEQ_STATE_LISTENING; read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } else { @@ -2041,11 +2009,13 @@ get_req: if (reqsk_queue_len(&icsk->icsk_accept_queue)) goto start_req; read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); - sk = sk_next(sk); + sk = sk_nulls_next(sk); } get_sk: sk_nulls_for_each_from(sk, node) { - if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) { + if (!net_eq(sock_net(sk), net)) + continue; + if (sk->sk_family == st->family) { cur = sk; goto out; } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 43cf901..80b1f80 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -49,6 +49,56 @@ struct inet_timewait_death_row tcp_death_row = { }; EXPORT_SYMBOL_GPL(tcp_death_row); +/* VJ's idea. Save last timestamp seen from this destination + * and hold it at least for normal timewait interval to use for duplicate + * segment detection in subsequent connections, before they enter synchronized + * state. + */ + +static int tcp_remember_stamp(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct inet_peer *peer; + bool release_it; + + peer = icsk->icsk_af_ops->get_peer(sk, &release_it); + if (peer) { + if ((s32)(peer->tcp_ts - tp->rx_opt.ts_recent) <= 0 || + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tp->rx_opt.ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tp->rx_opt.ts_recent_stamp; + peer->tcp_ts = tp->rx_opt.ts_recent; + } + if (release_it) + inet_putpeer(peer); + return 1; + } + + return 0; +} + +static int tcp_tw_remember_stamp(struct inet_timewait_sock *tw) +{ + struct sock *sk = (struct sock *) tw; + struct inet_peer *peer; + + peer = twsk_getpeer(sk); + if (peer) { + const struct tcp_timewait_sock *tcptw = tcp_twsk(sk); + + if ((s32)(peer->tcp_ts - tcptw->tw_ts_recent) <= 0 || + ((u32)get_seconds() - peer->tcp_ts_stamp > TCP_PAWS_MSL && + peer->tcp_ts_stamp <= (u32)tcptw->tw_ts_recent_stamp)) { + peer->tcp_ts_stamp = (u32)tcptw->tw_ts_recent_stamp; + peer->tcp_ts = tcptw->tw_ts_recent; + } + inet_putpeer(peer); + return 1; + } + return 0; +} + static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) { if (seq == s_win) @@ -149,14 +199,9 @@ kill_with_rst: tcptw->tw_ts_recent = tmp_opt.rcv_tsval; } - /* I am shamed, but failed to make it more elegant. - * Yes, it is direct reference to IP, which is impossible - * to generalize to IPv6. Taking into account that IPv6 - * do not understand recycling in any case, it not - * a big problem in practice. --ANK */ - if (tw->tw_family == AF_INET && - tcp_death_row.sysctl_tw_recycle && tcptw->tw_ts_recent_stamp && - tcp_v4_tw_remember_stamp(tw)) + if (tcp_death_row.sysctl_tw_recycle && + tcptw->tw_ts_recent_stamp && + tcp_tw_remember_stamp(tw)) inet_twsk_schedule(tw, &tcp_death_row, tw->tw_timeout, TCP_TIMEWAIT_LEN); else @@ -274,7 +319,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) int recycle_ok = 0; if (tcp_death_row.sysctl_tw_recycle && tp->rx_opt.ts_recent_stamp) - recycle_ok = icsk->icsk_af_ops->remember_stamp(sk); + recycle_ok = tcp_remember_stamp(sk); if (tcp_death_row.tw_count < tcp_death_row.sysctl_max_tw_buckets) tw = inet_twsk_alloc(sk, state); @@ -347,7 +392,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) * socket up. We've got bigger problems than * non-graceful socket closings. */ - LIMIT_NETDEBUG(KERN_INFO "TCP: time wait bucket table overflow\n"); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPTIMEWAITOVERFLOW); } tcp_update_metrics(sk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 05b1ecf..dc7c096 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -55,7 +55,7 @@ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; int sysctl_tcp_tso_win_divisor __read_mostly = 3; int sysctl_tcp_mtu_probing __read_mostly = 0; -int sysctl_tcp_base_mss __read_mostly = 512; +int sysctl_tcp_base_mss __read_mostly = TCP_BASE_MSS; /* By default, RFC2861 behavior. */ int sysctl_tcp_slow_start_after_idle __read_mostly = 1; @@ -119,9 +119,13 @@ static __u16 tcp_advertise_mss(struct sock *sk) struct dst_entry *dst = __sk_dst_get(sk); int mss = tp->advmss; - if (dst && dst_metric(dst, RTAX_ADVMSS) < mss) { - mss = dst_metric(dst, RTAX_ADVMSS); - tp->advmss = mss; + if (dst) { + unsigned int metric = dst_metric_advmss(dst); + + if (metric < mss) { + mss = metric; + tp->advmss = mss; + } } return (__u16)mss; @@ -224,18 +228,22 @@ void tcp_select_initial_window(int __space, __u32 mss, } } - /* Set initial window to value enough for senders, following RFC5681. */ + /* Set initial window to a value enough for senders starting with + * initial congestion window of TCP_DEFAULT_INIT_RCVWND. Place + * a limit on the initial window when mss is larger than 1460. + */ if (mss > (1 << *rcv_wscale)) { - int init_cwnd = rfc3390_bytes_to_packets(mss); - + int init_cwnd = TCP_DEFAULT_INIT_RCVWND; + if (mss > 1460) + init_cwnd = + max_t(u32, (1460 * TCP_DEFAULT_INIT_RCVWND) / mss, 2); /* when initializing use the value from init_rcv_wnd * rather than the default from above */ - if (init_rcv_wnd && - (*rcv_wnd > init_rcv_wnd * mss)) - *rcv_wnd = init_rcv_wnd * mss; - else if (*rcv_wnd > init_cwnd * mss) - *rcv_wnd = init_cwnd * mss; + if (init_rcv_wnd) + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); + else + *rcv_wnd = min(*rcv_wnd, init_cwnd * mss); } /* Set the clamp no higher than max representable value */ @@ -386,27 +394,30 @@ struct tcp_out_options { */ static u8 tcp_cookie_size_check(u8 desired) { - if (desired > 0) { + int cookie_size; + + if (desired > 0) /* previously specified */ return desired; - } - if (sysctl_tcp_cookie_size <= 0) { + + cookie_size = ACCESS_ONCE(sysctl_tcp_cookie_size); + if (cookie_size <= 0) /* no default specified */ return 0; - } - if (sysctl_tcp_cookie_size <= TCP_COOKIE_MIN) { + + if (cookie_size <= TCP_COOKIE_MIN) /* value too small, specify minimum */ return TCP_COOKIE_MIN; - } - if (sysctl_tcp_cookie_size >= TCP_COOKIE_MAX) { + + if (cookie_size >= TCP_COOKIE_MAX) /* value too large, specify maximum */ return TCP_COOKIE_MAX; - } - if (0x1 & sysctl_tcp_cookie_size) { + + if (cookie_size & 1) /* 8-bit multiple, illegal, fix it */ - return (u8)(sysctl_tcp_cookie_size + 0x1); - } - return (u8)sysctl_tcp_cookie_size; + cookie_size++; + + return (u8)cookie_size; } /* Write previously computed TCP options to the packet. @@ -822,8 +833,11 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, &md5); tcp_header_size = tcp_options_size + sizeof(struct tcphdr); - if (tcp_packets_in_flight(tp) == 0) + if (tcp_packets_in_flight(tp) == 0) { tcp_ca_event(sk, CA_EVENT_TX_START); + skb->ooo_okay = 1; + } else + skb->ooo_okay = 0; skb_push(skb, tcp_header_size); skb_reset_transport_header(skb); @@ -1513,6 +1527,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) struct tcp_sock *tp = tcp_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); u32 send_win, cong_win, limit, in_flight; + int win_divisor; if (TCP_SKB_CB(skb)->flags & TCPHDR_FIN) goto send_now; @@ -1544,13 +1559,14 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) if ((skb != tcp_write_queue_tail(sk)) && (limit >= skb->len)) goto send_now; - if (sysctl_tcp_tso_win_divisor) { + win_divisor = ACCESS_ONCE(sysctl_tcp_tso_win_divisor); + if (win_divisor) { u32 chunk = min(tp->snd_wnd, tp->snd_cwnd * tp->mss_cache); /* If at least some fraction of a window is available, * just use it. */ - chunk /= sysctl_tcp_tso_win_divisor; + chunk /= win_divisor; if (limit >= chunk) goto send_now; } else { @@ -2415,7 +2431,7 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, skb_dst_set(skb, dst_clone(dst)); - mss = dst_metric(dst, RTAX_ADVMSS); + mss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < mss) mss = tp->rx_opt.user_mss; @@ -2549,7 +2565,7 @@ static void tcp_connect_init(struct sock *sk) if (!tp->window_clamp) tp->window_clamp = dst_metric(dst, RTAX_WINDOW); - tp->advmss = dst_metric(dst, RTAX_ADVMSS); + tp->advmss = dst_metric_advmss(dst); if (tp->rx_opt.user_mss && tp->rx_opt.user_mss < tp->advmss) tp->advmss = tp->rx_opt.user_mss; @@ -2592,6 +2608,7 @@ int tcp_connect(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *buff; + int err; tcp_connect_init(sk); @@ -2614,7 +2631,9 @@ int tcp_connect(struct sock *sk) sk->sk_wmem_queued += buff->truesize; sk_mem_charge(sk, buff->truesize); tp->packets_out += tcp_skb_pcount(buff); - tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + err = tcp_transmit_skb(sk, buff, 1, sk->sk_allocation); + if (err == -ECONNREFUSED) + return err; /* We change tp->snd_nxt after the tcp_transmit_skb() call * in order to make this packet get counted in tcpOutSegs. diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 6211e21..85ee7eb 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -154,7 +154,7 @@ static int tcpprobe_sprint(char *tbuf, int n) struct timespec tv = ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start)); - return snprintf(tbuf, n, + return scnprintf(tbuf, n, "%lu.%09lu %pI4:%u %pI4:%u %d %#x %#x %u %u %u %u\n", (unsigned long) tv.tv_sec, (unsigned long) tv.tv_nsec, @@ -174,7 +174,7 @@ static ssize_t tcpprobe_read(struct file *file, char __user *buf, return -EINVAL; while (cnt < len) { - char tbuf[128]; + char tbuf[164]; int width; /* Wait for data in buffer */ diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 28cb2d7..8157b17 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -110,7 +110,7 @@ struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); -int sysctl_udp_mem[3] __read_mostly; +long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); int sysctl_udp_rmem_min __read_mostly; @@ -119,7 +119,7 @@ EXPORT_SYMBOL(sysctl_udp_rmem_min); int sysctl_udp_wmem_min __read_mostly; EXPORT_SYMBOL(sysctl_udp_wmem_min); -atomic_t udp_memory_allocated; +atomic_long_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); #define MAX_UDP_PORTS 65536 @@ -430,7 +430,7 @@ begin: if (result) { exact_match: - if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score2(result, net, saddr, sport, daddr, hnum, dif) < badness)) { @@ -500,7 +500,7 @@ begin: goto begin; if (result) { - if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) result = NULL; else if (unlikely(compute_score(result, net, saddr, hnum, sport, daddr, dport, dif) < badness)) { @@ -890,15 +890,13 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (rt == NULL) { struct flowi fl = { .oif = ipc.oif, .mark = sk->sk_mark, - .nl_u = { .ip4_u = - { .daddr = faddr, - .saddr = saddr, - .tos = tos } }, + .fl4_dst = faddr, + .fl4_src = saddr, + .fl4_tos = tos, .proto = sk->sk_protocol, .flags = inet_sk_flowi_flags(sk), - .uli_u = { .ports = - { .sport = inet->inet_sport, - .dport = dport } } }; + .fl_ip_sport = inet->inet_sport, + .fl_ip_dport = dport }; struct net *net = sock_net(sk); security_sk_classify_flow(sk, &fl); @@ -1899,6 +1897,7 @@ struct proto udp_prot = { .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; EXPORT_SYMBOL(udp_prot); @@ -2228,7 +2227,7 @@ struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, int features) /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ - offset = skb->csum_start - skb_headroom(skb); + offset = skb_checksum_start_offset(skb); csum = skb_checksum(skb, offset, skb->len - offset, 0); offset += skb->csum_offset; *(__sum16 *)(skb->data + offset) = csum_fold(csum); diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index ab76aa9..aee9963 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -57,6 +57,7 @@ struct proto udplite_prot = { .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif + .clear_sk = sk_prot_clear_portaddr_nulls, }; EXPORT_SYMBOL(udplite_prot); diff --git a/net/ipv4/xfrm4_mode_tunnel.c b/net/ipv4/xfrm4_mode_tunnel.c index 6f368413..534972e 100644 --- a/net/ipv4/xfrm4_mode_tunnel.c +++ b/net/ipv4/xfrm4_mode_tunnel.c @@ -56,7 +56,7 @@ static int xfrm4_mode_tunnel_output(struct xfrm_state *x, struct sk_buff *skb) 0 : (XFRM_MODE_SKB_CB(skb)->frag_off & htons(IP_DF)); ip_select_ident(top_iph, dst->child, NULL); - top_iph->ttl = dst_metric(dst->child, RTAX_HOPLIMIT); + top_iph->ttl = ip4_dst_hoplimit(dst->child); top_iph->saddr = x->props.saddr.a4; top_iph->daddr = x->id.daddr.a4; diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index dd1fd8c..b057d40 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -11,6 +11,7 @@ #include <linux/err.h> #include <linux/kernel.h> #include <linux/inetdevice.h> +#include <linux/if_tunnel.h> #include <net/dst.h> #include <net/xfrm.h> #include <net/ip.h> @@ -22,12 +23,8 @@ static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, xfrm_address_t *daddr) { struct flowi fl = { - .nl_u = { - .ip4_u = { - .tos = tos, - .daddr = daddr->a4, - }, - }, + .fl4_dst = daddr->a4, + .fl4_tos = tos, }; struct dst_entry *dst; struct rtable *rt; @@ -154,6 +151,20 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) fl->fl_ipsec_spi = htonl(ntohs(ipcomp_hdr[1])); } break; + + case IPPROTO_GRE: + if (pskb_may_pull(skb, xprth + 12 - skb->data)) { + __be16 *greflags = (__be16 *)xprth; + __be32 *gre_hdr = (__be32 *)xprth; + + if (greflags[0] & GRE_KEY) { + if (greflags[0] & GRE_CSUM) + gre_hdr++; + fl->fl_gre_key = gre_hdr[1]; + } + } + break; + default: fl->fl_ipsec_spi = 0; break; |