diff options
Diffstat (limited to 'net/ipv4')
64 files changed, 2172 insertions, 1373 deletions
diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1aa2dc9e380e..743f5542d65a 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -94,6 +94,7 @@ #include <linux/igmp.h> #include <linux/inetdevice.h> #include <linux/netdevice.h> +#include <net/checksum.h> #include <net/ip.h> #include <net/protocol.h> #include <net/arp.h> @@ -245,7 +246,7 @@ static inline int inet_netns_ok(struct net *net, int protocol) int hash; struct net_protocol *ipprot; - if (net == &init_net) + if (net_eq(net, &init_net)) return 1; hash = protocol & (MAX_INET_PROTOS - 1); @@ -272,10 +273,9 @@ static int inet_create(struct net *net, struct socket *sock, int protocol) int try_loading_module = 0; int err; - if (sock->type != SOCK_RAW && - sock->type != SOCK_DGRAM && - !inet_ehash_secret) - build_ehash_secret(); + if (unlikely(!inet_ehash_secret)) + if (sock->type != SOCK_RAW && sock->type != SOCK_DGRAM) + build_ehash_secret(); sock->state = SS_UNCONNECTED; @@ -1070,11 +1070,8 @@ static int inet_sk_reselect_saddr(struct sock *sk) return 0; if (sysctl_ip_dynaddr > 1) { - printk(KERN_INFO "%s(): shifting inet->" - "saddr from " NIPQUAD_FMT " to " NIPQUAD_FMT "\n", - __func__, - NIPQUAD(old_saddr), - NIPQUAD(new_saddr)); + printk(KERN_INFO "%s(): shifting inet->saddr from %pI4 to %pI4\n", + __func__, &old_saddr, &new_saddr); } inet->saddr = inet->rcv_saddr = new_saddr; @@ -1245,6 +1242,100 @@ out: return segs; } +static struct sk_buff **inet_gro_receive(struct sk_buff **head, + struct sk_buff *skb) +{ + struct net_protocol *ops; + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct iphdr *iph; + int flush = 1; + int proto; + int id; + + if (unlikely(!pskb_may_pull(skb, sizeof(*iph)))) + goto out; + + iph = ip_hdr(skb); + proto = iph->protocol & (MAX_INET_PROTOS - 1); + + rcu_read_lock(); + ops = rcu_dereference(inet_protos[proto]); + if (!ops || !ops->gro_receive) + goto out_unlock; + + if (iph->version != 4 || iph->ihl != 5) + goto out_unlock; + + if (unlikely(ip_fast_csum((u8 *)iph, iph->ihl))) + goto out_unlock; + + flush = ntohs(iph->tot_len) != skb->len || + iph->frag_off != htons(IP_DF); + id = ntohs(iph->id); + + for (p = *head; p; p = p->next) { + struct iphdr *iph2; + + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + iph2 = ip_hdr(p); + + if (iph->protocol != iph2->protocol || + iph->tos != iph2->tos || + memcmp(&iph->saddr, &iph2->saddr, 8)) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + /* All fields must match except length and checksum. */ + NAPI_GRO_CB(p)->flush |= + memcmp(&iph->frag_off, &iph2->frag_off, 4) || + (u16)(ntohs(iph2->id) + NAPI_GRO_CB(p)->count) != id; + + NAPI_GRO_CB(p)->flush |= flush; + } + + NAPI_GRO_CB(skb)->flush |= flush; + __skb_pull(skb, sizeof(*iph)); + skb_reset_transport_header(skb); + + pp = ops->gro_receive(head, skb); + +out_unlock: + rcu_read_unlock(); + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +static int inet_gro_complete(struct sk_buff *skb) +{ + struct net_protocol *ops; + struct iphdr *iph = ip_hdr(skb); + int proto = iph->protocol & (MAX_INET_PROTOS - 1); + int err = -ENOSYS; + __be16 newlen = htons(skb->len - skb_network_offset(skb)); + + csum_replace2(&iph->check, iph->tot_len, newlen); + iph->tot_len = newlen; + + rcu_read_lock(); + ops = rcu_dereference(inet_protos[proto]); + if (WARN_ON(!ops || !ops->gro_complete)) + goto out_unlock; + + err = ops->gro_complete(skb); + +out_unlock: + rcu_read_unlock(); + + return err; +} + int inet_ctl_sock_create(struct sock **sk, unsigned short family, unsigned short type, unsigned char protocol, struct net *net) @@ -1311,6 +1402,7 @@ EXPORT_SYMBOL_GPL(snmp_mib_free); #ifdef CONFIG_IP_MULTICAST static struct net_protocol igmp_protocol = { .handler = igmp_rcv, + .netns_ok = 1, }; #endif @@ -1319,6 +1411,8 @@ static struct net_protocol tcp_protocol = { .err_handler = tcp_v4_err, .gso_send_check = tcp_v4_gso_send_check, .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, .no_policy = 1, .netns_ok = 1, }; @@ -1411,6 +1505,8 @@ static struct packet_type ip_packet_type = { .func = ip_rcv, .gso_send_check = inet_gso_send_check, .gso_segment = inet_gso_segment, + .gro_receive = inet_gro_receive, + .gro_complete = inet_gro_complete, }; static int __init inet_init(void) diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index 8219b7e0968d..e878e494296e 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -201,15 +201,16 @@ out: static void ah4_err(struct sk_buff *skb, u32 info) { - struct iphdr *iph = (struct iphdr*)skb->data; - struct ip_auth_hdr *ah = (struct ip_auth_hdr*)(skb->data+(iph->ihl<<2)); + struct net *net = dev_net(skb->dev); + struct iphdr *iph = (struct iphdr *)skb->data; + struct ip_auth_hdr *ah = (struct ip_auth_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, ah->spi, IPPROTO_AH, AF_INET); if (!x) return; printk(KERN_DEBUG "pmtu discovery on SA AH/%08x/%08x\n", @@ -293,9 +294,7 @@ static void ah_destroy(struct xfrm_state *x) return; kfree(ahp->work_icv); - ahp->work_icv = NULL; crypto_free_hash(ahp->tfm); - ahp->tfm = NULL; kfree(ahp); } @@ -316,6 +315,7 @@ static struct net_protocol ah4_protocol = { .handler = xfrm4_rcv, .err_handler = ah4_err, .no_policy = 1, + .netns_ok = 1, }; static int __init ah4_init(void) diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 1a9dd66511fc..29a74c01d8de 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -506,7 +506,7 @@ int arp_bind_neighbour(struct dst_entry *dst) if (dev == NULL) return -EINVAL; if (n == NULL) { - __be32 nexthop = ((struct rtable*)dst)->rt_gateway; + __be32 nexthop = ((struct rtable *)dst)->rt_gateway; if (dev->flags&(IFF_LOOPBACK|IFF_POINTOPOINT)) nexthop = 0; n = __neigh_lookup_errno( @@ -640,14 +640,14 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp_ptr=(unsigned char *)(arp+1); memcpy(arp_ptr, src_hw, dev->addr_len); - arp_ptr+=dev->addr_len; - memcpy(arp_ptr, &src_ip,4); - arp_ptr+=4; + arp_ptr += dev->addr_len; + memcpy(arp_ptr, &src_ip, 4); + arp_ptr += 4; if (target_hw != NULL) memcpy(arp_ptr, target_hw, dev->addr_len); else memset(arp_ptr, 0, dev->addr_len); - arp_ptr+=dev->addr_len; + arp_ptr += dev->addr_len; memcpy(arp_ptr, &dest_ip, 4); return skb; @@ -818,18 +818,18 @@ static int arp_process(struct sk_buff *skb) addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { - n = neigh_event_ns(&arp_tbl, sha, &sip, dev); - if (n) { - int dont_send = 0; - - if (!dont_send) - dont_send |= arp_ignore(in_dev,sip,tip); - if (!dont_send && IN_DEV_ARPFILTER(in_dev)) - dont_send |= arp_filter(sip,tip,dev); - if (!dont_send) - arp_send(ARPOP_REPLY,ETH_P_ARP,sip,dev,tip,sha,dev->dev_addr,sha); + int dont_send = 0; - neigh_release(n); + if (!dont_send) + dont_send |= arp_ignore(in_dev,sip,tip); + if (!dont_send && IN_DEV_ARPFILTER(in_dev)) + dont_send |= arp_filter(sip,tip,dev); + if (!dont_send) { + n = neigh_event_ns(&arp_tbl, sha, &sip, dev); + if (n) { + arp_send(ARPOP_REPLY,ETH_P_ARP,sip,dev,tip,sha,dev->dev_addr,sha); + neigh_release(n); + } } goto out; } else if (IN_DEV_FORWARD(in_dev)) { @@ -1308,7 +1308,7 @@ static void arp_format_neigh_entry(struct seq_file *seq, #if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) } #endif - sprintf(tbuf, NIPQUAD_FMT, NIPQUAD(*(u32*)n->primary_key)); + sprintf(tbuf, "%pI4", n->primary_key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", tbuf, hatype, arp_state_to_flags(n), hbuffer, dev->name); read_unlock(&n->lock); @@ -1321,7 +1321,7 @@ static void arp_format_pneigh_entry(struct seq_file *seq, int hatype = dev ? dev->type : 0; char tbuf[16]; - sprintf(tbuf, NIPQUAD_FMT, NIPQUAD(*(u32*)n->key)); + sprintf(tbuf, "%pI4", n->key); seq_printf(seq, "%-16s 0x%-10x0x%-10x%s * %s\n", tbuf, hatype, ATF_PUBL | ATF_PERM, "00:00:00:00:00:00", dev ? dev->name : "*"); diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 2e78f6bd9775..e52799047a5f 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -490,7 +490,6 @@ int cipso_v4_doi_add(struct cipso_v4_doi *doi_def) } atomic_set(&doi_def->refcount, 1); - INIT_RCU_HEAD(&doi_def->rcu); spin_lock(&cipso_v4_doi_list_lock); if (cipso_v4_doi_search(doi_def->doi) != NULL) diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index 56fce3ab6c55..309997edc8a5 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -112,13 +112,7 @@ static inline void devinet_sysctl_unregister(struct in_device *idev) static struct in_ifaddr *inet_alloc_ifa(void) { - struct in_ifaddr *ifa = kzalloc(sizeof(*ifa), GFP_KERNEL); - - if (ifa) { - INIT_RCU_HEAD(&ifa->rcu_head); - } - - return ifa; + return kzalloc(sizeof(struct in_ifaddr), GFP_KERNEL); } static void inet_rcu_free_ifa(struct rcu_head *head) @@ -161,7 +155,6 @@ static struct in_device *inetdev_init(struct net_device *dev) in_dev = kzalloc(sizeof(*in_dev), GFP_KERNEL); if (!in_dev) goto out; - INIT_RCU_HEAD(&in_dev->rcu_head); memcpy(&in_dev->cnf, dev_net(dev)->ipv4.devconf_dflt, sizeof(in_dev->cnf)); in_dev->cnf.sysctl = NULL; @@ -1108,7 +1101,7 @@ out: } static struct notifier_block ip_netdev_notifier = { - .notifier_call =inetdev_event, + .notifier_call = inetdev_event, }; static inline size_t inet_nlmsg_size(void) @@ -1195,7 +1188,7 @@ done: return skb->len; } -static void rtmsg_ifa(int event, struct in_ifaddr* ifa, struct nlmsghdr *nlh, +static void rtmsg_ifa(int event, struct in_ifaddr *ifa, struct nlmsghdr *nlh, u32 pid) { struct sk_buff *skb; @@ -1262,7 +1255,7 @@ static void inet_forward_change(struct net *net) } static int devinet_conf_proc(ctl_table *ctl, int write, - struct file* filp, void __user *buffer, + struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int ret = proc_dointvec(ctl, write, filp, buffer, lenp, ppos); @@ -1334,7 +1327,7 @@ static int devinet_conf_sysctl(ctl_table *table, } static int devinet_sysctl_forward(ctl_table *ctl, int write, - struct file* filp, void __user *buffer, + struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; @@ -1363,7 +1356,7 @@ static int devinet_sysctl_forward(ctl_table *ctl, int write, } int ipv4_doint_and_flush(ctl_table *ctl, int write, - struct file* filp, void __user *buffer, + struct file *filp, void __user *buffer, size_t *lenp, loff_t *ppos) { int *valp = ctl->data; diff --git a/net/ipv4/esp4.c b/net/ipv4/esp4.c index 21515d4c49eb..18bb383ea393 100644 --- a/net/ipv4/esp4.c +++ b/net/ipv4/esp4.c @@ -413,15 +413,16 @@ static u32 esp4_get_mtu(struct xfrm_state *x, int mtu) static void esp4_err(struct sk_buff *skb, u32 info) { - struct iphdr *iph = (struct iphdr*)skb->data; - struct ip_esp_hdr *esph = (struct ip_esp_hdr*)(skb->data+(iph->ihl<<2)); + struct net *net = dev_net(skb->dev); + struct iphdr *iph = (struct iphdr *)skb->data; + struct ip_esp_hdr *esph = (struct ip_esp_hdr *)(skb->data+(iph->ihl<<2)); struct xfrm_state *x; if (icmp_hdr(skb)->type != ICMP_DEST_UNREACH || icmp_hdr(skb)->code != ICMP_FRAG_NEEDED) return; - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); + x = xfrm_state_lookup(net, (xfrm_address_t *)&iph->daddr, esph->spi, IPPROTO_ESP, AF_INET); if (!x) return; NETDEBUG(KERN_DEBUG "pmtu discovery on SA ESP/%08x/%08x\n", @@ -618,6 +619,7 @@ static struct net_protocol esp4_protocol = { .handler = xfrm4_rcv, .err_handler = esp4_err, .no_policy = 1, + .netns_ok = 1, }; static int __init esp4_init(void) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index 65c1503f8cc8..741e4fa3e474 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -578,7 +578,7 @@ errout: return err; } -static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet_rtm_delroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct fib_config cfg; @@ -600,7 +600,7 @@ errout: return err; } -static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr* nlh, void *arg) +static int inet_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg) { struct net *net = sock_net(skb->sk); struct fib_config cfg; @@ -903,7 +903,7 @@ static void fib_disable_ip(struct net_device *dev, int force) static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, void *ptr) { - struct in_ifaddr *ifa = (struct in_ifaddr*)ptr; + struct in_ifaddr *ifa = (struct in_ifaddr *)ptr; struct net_device *dev = ifa->ifa_dev->dev; switch (event) { @@ -964,11 +964,11 @@ static int fib_netdev_event(struct notifier_block *this, unsigned long event, vo } static struct notifier_block fib_inetaddr_notifier = { - .notifier_call =fib_inetaddr_event, + .notifier_call = fib_inetaddr_event, }; static struct notifier_block fib_netdev_notifier = { - .notifier_call =fib_netdev_event, + .notifier_call = fib_netdev_event, }; static int __net_init ip_fib_net_init(struct net *net) diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index c8cac6c7f881..ded8c44fb848 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -247,7 +247,7 @@ fn_hash_lookup(struct fib_table *tb, const struct flowi *flp, struct fib_result { int err; struct fn_zone *fz; - struct fn_hash *t = (struct fn_hash*)tb->tb_data; + struct fn_hash *t = (struct fn_hash *)tb->tb_data; read_lock(&fib_hash_lock); for (fz = t->fn_zone_list; fz; fz = fz->fz_next) { @@ -283,7 +283,7 @@ fn_hash_select_default(struct fib_table *tb, const struct flowi *flp, struct fib struct fib_node *f; struct fib_info *fi = NULL; struct fib_info *last_resort; - struct fn_hash *t = (struct fn_hash*)tb->tb_data; + struct fn_hash *t = (struct fn_hash *)tb->tb_data; struct fn_zone *fz = t->fn_zones[0]; if (fz == NULL) @@ -548,7 +548,7 @@ out: static int fn_hash_delete(struct fib_table *tb, struct fib_config *cfg) { - struct fn_hash *table = (struct fn_hash*)tb->tb_data; + struct fn_hash *table = (struct fn_hash *)tb->tb_data; struct fib_node *f; struct fib_alias *fa, *fa_to_delete; struct fn_zone *fz; @@ -748,7 +748,7 @@ static int fn_hash_dump(struct fib_table *tb, struct sk_buff *skb, struct netlin { int m, s_m; struct fn_zone *fz; - struct fn_hash *table = (struct fn_hash*)tb->tb_data; + struct fn_hash *table = (struct fn_hash *)tb->tb_data; s_m = cb->args[2]; read_lock(&fib_hash_lock); @@ -845,10 +845,10 @@ static struct fib_alias *fib_get_first(struct seq_file *seq) struct hlist_node *node; struct fib_node *fn; - hlist_for_each_entry(fn,node,iter->hash_head,fn_hash) { + hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) { struct fib_alias *fa; - list_for_each_entry(fa,&fn->fn_alias,fa_list) { + list_for_each_entry(fa, &fn->fn_alias, fa_list) { iter->fn = fn; iter->fa = fa; goto out; diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index ded2ae34eab1..4817dea3bc73 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -63,16 +63,16 @@ static DEFINE_SPINLOCK(fib_multipath_lock); for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) #define change_nexthops(fi) { int nhsel; struct fib_nh * nh; \ -for (nhsel=0, nh = (struct fib_nh*)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++) +for (nhsel=0, nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nh++, nhsel++) #else /* CONFIG_IP_ROUTE_MULTIPATH */ /* Hope, that gcc will optimize it to get rid of dummy loop */ -#define for_nexthops(fi) { int nhsel=0; const struct fib_nh * nh = (fi)->fib_nh; \ +#define for_nexthops(fi) { int nhsel = 0; const struct fib_nh * nh = (fi)->fib_nh; \ for (nhsel=0; nhsel < 1; nhsel++) -#define change_nexthops(fi) { int nhsel=0; struct fib_nh * nh = (struct fib_nh*)((fi)->fib_nh); \ +#define change_nexthops(fi) { int nhsel = 0; struct fib_nh * nh = (struct fib_nh *)((fi)->fib_nh); \ for (nhsel=0; nhsel < 1; nhsel++) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -358,7 +358,7 @@ int fib_detect_death(struct fib_info *fi, int order, state = n->nud_state; neigh_release(n); } - if (state==NUD_REACHABLE) + if (state == NUD_REACHABLE) return 0; if ((state&NUD_VALID) && order != dflt) return 0; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 5cb72786a8af..ec0ae490f0b6 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -2399,8 +2399,8 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) __be32 prf = htonl(mask_pfx(tn->key, tn->pos)); seq_indent(seq, iter->depth-1); - seq_printf(seq, " +-- " NIPQUAD_FMT "/%d %d %d %d\n", - NIPQUAD(prf), tn->pos, tn->bits, tn->full_children, + seq_printf(seq, " +-- %pI4/%d %d %d %d\n", + &prf, tn->pos, tn->bits, tn->full_children, tn->empty_children); } else { @@ -2410,7 +2410,7 @@ static int fib_trie_seq_show(struct seq_file *seq, void *v) __be32 val = htonl(l->key); seq_indent(seq, iter->depth); - seq_printf(seq, " |-- " NIPQUAD_FMT "\n", NIPQUAD(val)); + seq_printf(seq, " |-- %pI4\n", &val); hlist_for_each_entry_rcu(li, node, &l->list, hlist) { struct fib_alias *fa; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 72b2de76f1cd..705b33b184a3 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -321,12 +321,12 @@ static int icmp_glue_bits(void *from, char *to, int offset, int len, int odd, } static void icmp_push_reply(struct icmp_bxm *icmp_param, - struct ipcm_cookie *ipc, struct rtable *rt) + struct ipcm_cookie *ipc, struct rtable **rt) { struct sock *sk; struct sk_buff *skb; - sk = icmp_sk(dev_net(rt->u.dst.dev)); + sk = icmp_sk(dev_net((*rt)->u.dst.dev)); if (ip_append_data(sk, icmp_glue_bits, icmp_param, icmp_param->data_len+icmp_param->head_len, icmp_param->head_len, @@ -392,7 +392,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) } if (icmpv4_xrlim_allow(net, rt, icmp_param->data.icmph.type, icmp_param->data.icmph.code)) - icmp_push_reply(icmp_param, &ipc, rt); + icmp_push_reply(icmp_param, &ipc, &rt); ip_rt_put(rt); out_unlock: icmp_xmit_unlock(sk); @@ -562,7 +562,7 @@ 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; - err = xfrm_lookup((struct dst_entry **)&rt, &fl, NULL, 0); + err = xfrm_lookup(net, (struct dst_entry **)&rt, &fl, NULL, 0); switch (err) { case 0: if (rt != rt2) @@ -601,7 +601,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) if (err) goto relookup_failed; - err = xfrm_lookup((struct dst_entry **)&rt2, &fl, NULL, + err = xfrm_lookup(net, (struct dst_entry **)&rt2, &fl, NULL, XFRM_LOOKUP_ICMP); switch (err) { case 0: @@ -635,7 +635,7 @@ route_done: icmp_param.data_len = room; icmp_param.head_len = sizeof(struct icmphdr); - icmp_push_reply(&icmp_param, &ipc, rt); + icmp_push_reply(&icmp_param, &ipc, &rt); ende: ip_rt_put(rt); out_unlock: @@ -683,10 +683,8 @@ static void icmp_unreach(struct sk_buff *skb) break; case ICMP_FRAG_NEEDED: if (ipv4_config.no_pmtu_disc) { - LIMIT_NETDEBUG(KERN_INFO "ICMP: " NIPQUAD_FMT ": " - "fragmentation needed " - "and DF set.\n", - NIPQUAD(iph->daddr)); + LIMIT_NETDEBUG(KERN_INFO "ICMP: %pI4: fragmentation needed and DF set.\n", + &iph->daddr); } else { info = ip_rt_frag_needed(net, iph, ntohs(icmph->un.frag.mtu), @@ -696,9 +694,8 @@ static void icmp_unreach(struct sk_buff *skb) } break; case ICMP_SR_FAILED: - LIMIT_NETDEBUG(KERN_INFO "ICMP: " NIPQUAD_FMT ": Source " - "Route Failed.\n", - NIPQUAD(iph->daddr)); + LIMIT_NETDEBUG(KERN_INFO "ICMP: %pI4: Source Route Failed.\n", + &iph->daddr); break; default: break; @@ -729,12 +726,12 @@ static void icmp_unreach(struct sk_buff *skb) if (!net->ipv4.sysctl_icmp_ignore_bogus_error_responses && inet_addr_type(net, iph->daddr) == RTN_BROADCAST) { if (net_ratelimit()) - printk(KERN_WARNING NIPQUAD_FMT " sent an invalid ICMP " + printk(KERN_WARNING "%pI4 sent an invalid ICMP " "type %u, code %u " - "error to a broadcast: " NIPQUAD_FMT " on %s\n", - NIPQUAD(ip_hdr(skb)->saddr), + "error to a broadcast: %pI4 on %s\n", + &ip_hdr(skb)->saddr, icmph->type, icmph->code, - NIPQUAD(iph->daddr), + &iph->daddr, skb->dev->name); goto out; } @@ -952,9 +949,8 @@ static void icmp_address_reply(struct sk_buff *skb) break; } if (!ifa && net_ratelimit()) { - printk(KERN_INFO "Wrong address mask " NIPQUAD_FMT " from " - "%s/" NIPQUAD_FMT "\n", - NIPQUAD(*mp), dev->name, NIPQUAD(rt->rt_src)); + printk(KERN_INFO "Wrong address mask %pI4 from %s/%pI4\n", + mp, dev->name, &rt->rt_src); } } rcu_read_unlock(); @@ -976,9 +972,10 @@ int icmp_rcv(struct sk_buff *skb) struct net *net = dev_net(rt->u.dst.dev); if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { + struct sec_path *sp = skb_sec_path(skb); int nh; - if (!(skb->sp && skb->sp->xvec[skb->sp->len - 1]->props.flags & + if (!(sp && sp->xvec[sp->len - 1]->props.flags & XFRM_STATE_ICMP)) goto drop; diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a0d86455c53e..9eb6219af615 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -167,7 +167,7 @@ static __inline__ void igmp_stop_timer(struct ip_mc_list *im) spin_lock_bh(&im->lock); if (del_timer(&im->timer)) atomic_dec(&im->refcnt); - im->tm_running=0; + im->tm_running = 0; im->reporter = 0; im->unsolicit_count = 0; spin_unlock_bh(&im->lock); @@ -176,9 +176,9 @@ static __inline__ void igmp_stop_timer(struct ip_mc_list *im) /* It must be called with locked im->lock */ static void igmp_start_timer(struct ip_mc_list *im, int max_delay) { - int tv=net_random() % max_delay; + int tv = net_random() % max_delay; - im->tm_running=1; + im->tm_running = 1; if (!mod_timer(&im->timer, jiffies+tv+2)) atomic_inc(&im->refcnt); } @@ -207,7 +207,7 @@ static void igmp_mod_timer(struct ip_mc_list *im, int max_delay) if (del_timer(&im->timer)) { if ((long)(im->timer.expires-jiffies) < max_delay) { add_timer(&im->timer); - im->tm_running=1; + im->tm_running = 1; spin_unlock_bh(&im->lock); return; } @@ -358,7 +358,7 @@ static int igmpv3_sendpack(struct sk_buff *skb) static int grec_size(struct ip_mc_list *pmc, int type, int gdel, int sdel) { - return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc,type,gdel,sdel); + return sizeof(struct igmpv3_grec) + 4*igmp_scount(pmc, type, gdel, sdel); } static struct sk_buff *add_grhead(struct sk_buff *skb, struct ip_mc_list *pmc, @@ -653,7 +653,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, return -1; } - skb=alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); if (skb == NULL) { ip_rt_put(rt); return -1; @@ -682,11 +682,11 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, ((u8*)&iph[1])[3] = 0; ih = (struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); - ih->type=type; - ih->code=0; - ih->csum=0; - ih->group=group; - ih->csum=ip_compute_csum((void *)ih, sizeof(struct igmphdr)); + ih->type = type; + ih->code = 0; + ih->csum = 0; + ih->group = group; + ih->csum = ip_compute_csum((void *)ih, sizeof(struct igmphdr)); return ip_local_out(skb); } @@ -728,7 +728,7 @@ static void igmp_timer_expire(unsigned long data) struct in_device *in_dev = im->interface; spin_lock(&im->lock); - im->tm_running=0; + im->tm_running = 0; if (im->unsolicit_count) { im->unsolicit_count--; @@ -997,7 +997,7 @@ static void ip_mc_filter_add(struct in_device *in_dev, __be32 addr) --ANK */ if (arp_mc_map(addr, buf, dev, 0) == 0) - dev_mc_add(dev,buf,dev->addr_len,0); + dev_mc_add(dev, buf, dev->addr_len, 0); } /* @@ -1010,7 +1010,7 @@ static void ip_mc_filter_del(struct in_device *in_dev, __be32 addr) struct net_device *dev = in_dev->dev; if (arp_mc_map(addr, buf, dev, 0) == 0) - dev_mc_delete(dev,buf,dev->addr_len,0); + dev_mc_delete(dev, buf, dev->addr_len, 0); } #ifdef CONFIG_IP_MULTICAST @@ -1210,10 +1210,10 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) if (!im) goto out; - im->users=1; - im->interface=in_dev; + im->users = 1; + im->interface = in_dev; in_dev_hold(in_dev); - im->multiaddr=addr; + im->multiaddr = addr; /* initial mode is (EX, empty) */ im->sfmode = MCAST_EXCLUDE; im->sfcount[MCAST_INCLUDE] = 0; @@ -1224,7 +1224,7 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) atomic_set(&im->refcnt, 1); spin_lock_init(&im->lock); #ifdef CONFIG_IP_MULTICAST - im->tm_running=0; + im->tm_running = 0; setup_timer(&im->timer, &igmp_timer_expire, (unsigned long)im); im->unsolicit_count = IGMP_Unsolicited_Report_Count; im->reporter = 0; @@ -1232,8 +1232,8 @@ void ip_mc_inc_group(struct in_device *in_dev, __be32 addr) #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 = in_dev->mc_list; + in_dev->mc_list = im; in_dev->mc_count++; write_unlock_bh(&in_dev->mc_list_lock); #ifdef CONFIG_IP_MULTICAST @@ -1279,7 +1279,7 @@ void ip_mc_dec_group(struct in_device *in_dev, __be32 addr) ASSERT_RTNL(); for (ip=&in_dev->mc_list; (i=*ip)!=NULL; ip=&i->next) { - if (i->multiaddr==addr) { + if (i->multiaddr == addr) { if (--i->users == 0) { write_lock_bh(&in_dev->mc_list_lock); *ip = i->next; @@ -1738,7 +1738,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) { int err; __be32 addr = imr->imr_multiaddr.s_addr; - struct ip_mc_socklist *iml=NULL, *i; + struct ip_mc_socklist *iml = NULL, *i; struct in_device *in_dev; struct inet_sock *inet = inet_sk(sk); struct net *net = sock_net(sk); @@ -1769,7 +1769,7 @@ int ip_mc_join_group(struct sock *sk , struct ip_mreqn *imr) err = -ENOBUFS; if (count >= sysctl_igmp_max_memberships) goto done; - iml = sock_kmalloc(sk,sizeof(*iml),GFP_KERNEL); + iml = sock_kmalloc(sk, sizeof(*iml), GFP_KERNEL); if (iml == NULL) goto done; @@ -2275,6 +2275,7 @@ int ip_check_mc(struct in_device *in_dev, __be32 mc_addr, __be32 src_addr, u16 p #if defined(CONFIG_PROC_FS) struct igmp_mc_iter_state { + struct seq_net_private p; struct net_device *dev; struct in_device *in_dev; }; @@ -2283,11 +2284,12 @@ struct igmp_mc_iter_state { static inline struct ip_mc_list *igmp_mc_get_first(struct seq_file *seq) { + struct net *net = seq_file_net(seq); struct ip_mc_list *im = NULL; struct igmp_mc_iter_state *state = igmp_mc_seq_private(seq); state->in_dev = NULL; - for_each_netdev(&init_net, state->dev) { + for_each_netdev(net, state->dev) { struct in_device *in_dev; in_dev = in_dev_get(state->dev); if (!in_dev) @@ -2408,7 +2410,7 @@ static const struct seq_operations igmp_mc_seq_ops = { static int igmp_mc_seq_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &igmp_mc_seq_ops, + return seq_open_net(inode, file, &igmp_mc_seq_ops, sizeof(struct igmp_mc_iter_state)); } @@ -2417,10 +2419,11 @@ static const struct file_operations igmp_mc_seq_fops = { .open = igmp_mc_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; struct igmp_mcf_iter_state { + struct seq_net_private p; struct net_device *dev; struct in_device *idev; struct ip_mc_list *im; @@ -2430,13 +2433,14 @@ struct igmp_mcf_iter_state { static inline struct ip_sf_list *igmp_mcf_get_first(struct seq_file *seq) { + struct net *net = seq_file_net(seq); struct ip_sf_list *psf = NULL; struct ip_mc_list *im = NULL; struct igmp_mcf_iter_state *state = igmp_mcf_seq_private(seq); state->idev = NULL; state->im = NULL; - for_each_netdev(&init_net, state->dev) { + for_each_netdev(net, state->dev) { struct in_device *idev; idev = in_dev_get(state->dev); if (unlikely(idev == NULL)) @@ -2567,7 +2571,7 @@ static const struct seq_operations igmp_mcf_seq_ops = { static int igmp_mcf_seq_open(struct inode *inode, struct file *file) { - return seq_open_private(file, &igmp_mcf_seq_ops, + return seq_open_net(inode, file, &igmp_mcf_seq_ops, sizeof(struct igmp_mcf_iter_state)); } @@ -2576,14 +2580,41 @@ static const struct file_operations igmp_mcf_seq_fops = { .open = igmp_mcf_seq_open, .read = seq_read, .llseek = seq_lseek, - .release = seq_release_private, + .release = seq_release_net, }; -int __init igmp_mc_proc_init(void) +static int igmp_net_init(struct net *net) { - proc_net_fops_create(&init_net, "igmp", S_IRUGO, &igmp_mc_seq_fops); - proc_net_fops_create(&init_net, "mcfilter", S_IRUGO, &igmp_mcf_seq_fops); + struct proc_dir_entry *pde; + + pde = proc_net_fops_create(net, "igmp", S_IRUGO, &igmp_mc_seq_fops); + if (!pde) + goto out_igmp; + pde = proc_net_fops_create(net, "mcfilter", S_IRUGO, &igmp_mcf_seq_fops); + if (!pde) + goto out_mcfilter; return 0; + +out_mcfilter: + proc_net_remove(net, "igmp"); +out_igmp: + return -ENOMEM; +} + +static void igmp_net_exit(struct net *net) +{ + proc_net_remove(net, "mcfilter"); + proc_net_remove(net, "igmp"); +} + +static struct pernet_operations igmp_net_ops = { + .init = igmp_net_init, + .exit = igmp_net_exit, +}; + +int __init igmp_mc_proc_init(void) +{ + return register_pernet_subsys(&igmp_net_ops); } #endif diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index bd1278a2d828..f26ab38680de 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -109,7 +109,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (tb->ib_net == net && tb->port == rover) + if (ib_net(tb) == net && tb->port == rover) goto next; break; next: @@ -137,7 +137,7 @@ int inet_csk_get_port(struct sock *sk, unsigned short snum) hashinfo->bhash_size)]; spin_lock(&head->lock); inet_bind_bucket_for_each(tb, node, &head->chain) - if (tb->ib_net == net && tb->port == snum) + if (ib_net(tb) == net && tb->port == snum) goto tb_found; } tb = NULL; @@ -323,7 +323,7 @@ void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long len) EXPORT_SYMBOL(inet_csk_reset_keepalive_timer); -struct dst_entry* inet_csk_route_req(struct sock *sk, +struct dst_entry *inet_csk_route_req(struct sock *sk, const struct request_sock *req) { struct rtable *rt; @@ -344,16 +344,17 @@ struct dst_entry* inet_csk_route_req(struct sock *sk, struct net *net = sock_net(sk); security_req_classify_flow(req, &fl); - if (ip_route_output_flow(net, &rt, &fl, sk, 0)) { - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); - return NULL; - } - if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) { - ip_rt_put(rt); - IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); - return NULL; - } + if (ip_route_output_flow(net, &rt, &fl, sk, 0)) + goto no_route; + if (opt && opt->is_strictroute && rt->rt_dst != rt->rt_gateway) + goto route_err; return &rt->u.dst; + +route_err: + ip_rt_put(rt); +no_route: + IP_INC_STATS_BH(net, IPSTATS_MIB_OUTNOROUTES); + return NULL; } EXPORT_SYMBOL_GPL(inet_csk_route_req); @@ -561,7 +562,7 @@ void inet_csk_destroy_sock(struct sock *sk) sk_refcnt_debug_release(sk); - atomic_dec(sk->sk_prot->orphan_count); + percpu_counter_dec(sk->sk_prot->orphan_count); sock_put(sk); } @@ -641,7 +642,7 @@ void inet_csk_listen_stop(struct sock *sk) sock_orphan(child); - atomic_inc(sk->sk_prot->orphan_count); + percpu_counter_inc(sk->sk_prot->orphan_count); inet_csk_destroy_sock(child); diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index 564230dabcb8..588a7796e3e3 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -718,13 +718,15 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) if (!(r->idiag_states & (TCPF_LISTEN | TCPF_SYN_RECV))) goto skip_listen_ht; - inet_listen_lock(hashinfo); for (i = s_i; i < INET_LHTABLE_SIZE; i++) { struct sock *sk; - struct hlist_node *node; + struct hlist_nulls_node *node; + struct inet_listen_hashbucket *ilb; num = 0; - sk_for_each(sk, node, &hashinfo->listening_hash[i]) { + ilb = &hashinfo->listening_hash[i]; + spin_lock_bh(&ilb->lock); + sk_nulls_for_each(sk, node, &ilb->head) { struct inet_sock *inet = inet_sk(sk); if (num < s_num) { @@ -742,7 +744,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) goto syn_recv; if (inet_csk_diag_dump(sk, skb, cb) < 0) { - inet_listen_unlock(hashinfo); + spin_unlock_bh(&ilb->lock); goto done; } @@ -751,7 +753,7 @@ syn_recv: goto next_listen; if (inet_diag_dump_reqs(skb, sk, cb) < 0) { - inet_listen_unlock(hashinfo); + spin_unlock_bh(&ilb->lock); goto done; } @@ -760,12 +762,12 @@ next_listen: cb->args[4] = 0; ++num; } + spin_unlock_bh(&ilb->lock); s_num = 0; cb->args[3] = 0; cb->args[4] = 0; } - inet_listen_unlock(hashinfo); skip_listen_ht: cb->args[0] = 1; s_i = num = s_num = 0; @@ -776,20 +778,21 @@ skip_listen_ht: for (i = s_i; i < hashinfo->ehash_size; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; - rwlock_t *lock = inet_ehash_lockp(hashinfo, i); + spinlock_t *lock = inet_ehash_lockp(hashinfo, i); struct sock *sk; - struct hlist_node *node; + struct hlist_nulls_node *node; num = 0; - if (hlist_empty(&head->chain) && hlist_empty(&head->twchain)) + if (hlist_nulls_empty(&head->chain) && + hlist_nulls_empty(&head->twchain)) continue; if (i > s_i) s_num = 0; - read_lock_bh(lock); - sk_for_each(sk, node, &head->chain) { + spin_lock_bh(lock); + sk_nulls_for_each(sk, node, &head->chain) { struct inet_sock *inet = inet_sk(sk); if (num < s_num) @@ -803,7 +806,7 @@ skip_listen_ht: r->id.idiag_dport) goto next_normal; if (inet_csk_diag_dump(sk, skb, cb) < 0) { - read_unlock_bh(lock); + spin_unlock_bh(lock); goto done; } next_normal: @@ -825,14 +828,14 @@ next_normal: r->id.idiag_dport) goto next_dying; if (inet_twsk_diag_dump(tw, skb, cb) < 0) { - read_unlock_bh(lock); + spin_unlock_bh(lock); goto done; } next_dying: ++num; } } - read_unlock_bh(lock); + spin_unlock_bh(lock); } done: diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index 44981906fb91..6a1045da48d2 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -35,7 +35,7 @@ struct inet_bind_bucket *inet_bind_bucket_create(struct kmem_cache *cachep, struct inet_bind_bucket *tb = kmem_cache_alloc(cachep, GFP_ATOMIC); if (tb != NULL) { - tb->ib_net = hold_net(net); + write_pnet(&tb->ib_net, hold_net(net)); tb->port = snum; tb->fastreuse = 0; INIT_HLIST_HEAD(&tb->owners); @@ -51,7 +51,7 @@ void inet_bind_bucket_destroy(struct kmem_cache *cachep, struct inet_bind_bucket { if (hlist_empty(&tb->owners)) { __hlist_del(&tb->node); - release_net(tb->ib_net); + release_net(ib_net(tb)); kmem_cache_free(cachep, tb); } } @@ -110,33 +110,29 @@ void __inet_inherit_port(struct sock *sk, struct sock *child) EXPORT_SYMBOL_GPL(__inet_inherit_port); -/* - * This lock without WQ_FLAG_EXCLUSIVE is good on UP and it can be very bad on SMP. - * Look, when several writers sleep and reader wakes them up, all but one - * immediately hit write lock and grab all the cpus. Exclusive sleep solves - * this, _but_ remember, it adds useless work on UP machines (wake up each - * exclusive lock release). It should be ifdefed really. - */ -void inet_listen_wlock(struct inet_hashinfo *hashinfo) - __acquires(hashinfo->lhash_lock) +static inline int compute_score(struct sock *sk, struct net *net, + const unsigned short hnum, const __be32 daddr, + const int dif) { - write_lock(&hashinfo->lhash_lock); - - if (atomic_read(&hashinfo->lhash_users)) { - DEFINE_WAIT(wait); + int score = -1; + struct inet_sock *inet = inet_sk(sk); - for (;;) { - prepare_to_wait_exclusive(&hashinfo->lhash_wait, - &wait, TASK_UNINTERRUPTIBLE); - if (!atomic_read(&hashinfo->lhash_users)) - break; - write_unlock_bh(&hashinfo->lhash_lock); - schedule(); - write_lock_bh(&hashinfo->lhash_lock); + if (net_eq(sock_net(sk), net) && inet->num == hnum && + !ipv6_only_sock(sk)) { + __be32 rcv_saddr = inet->rcv_saddr; + score = sk->sk_family == PF_INET ? 1 : 0; + if (rcv_saddr) { + if (rcv_saddr != daddr) + return -1; + score += 2; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score += 2; } - - finish_wait(&hashinfo->lhash_wait, &wait); } + return score; } /* @@ -145,72 +141,48 @@ void inet_listen_wlock(struct inet_hashinfo *hashinfo) * remote address for the connection. So always assume those are both * wildcarded during the search since they can never be otherwise. */ -static struct sock *inet_lookup_listener_slow(struct net *net, - const struct hlist_head *head, - const __be32 daddr, - const unsigned short hnum, - const int dif) -{ - struct sock *result = NULL, *sk; - const struct hlist_node *node; - int hiscore = -1; - - sk_for_each(sk, node, head) { - const struct inet_sock *inet = inet_sk(sk); - - if (net_eq(sock_net(sk), net) && inet->num == hnum && - !ipv6_only_sock(sk)) { - const __be32 rcv_saddr = inet->rcv_saddr; - int score = sk->sk_family == PF_INET ? 1 : 0; - - if (rcv_saddr) { - if (rcv_saddr != daddr) - continue; - score += 2; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score += 2; - } - if (score == 5) - return sk; - if (score > hiscore) { - hiscore = score; - result = sk; - } - } - } - return result; -} -/* Optimize the common listener case. */ + struct sock *__inet_lookup_listener(struct net *net, struct inet_hashinfo *hashinfo, const __be32 daddr, const unsigned short hnum, const int dif) { - struct sock *sk = NULL; - const struct hlist_head *head; - - read_lock(&hashinfo->lhash_lock); - head = &hashinfo->listening_hash[inet_lhashfn(net, hnum)]; - if (!hlist_empty(head)) { - const struct inet_sock *inet = inet_sk((sk = __sk_head(head))); - - if (inet->num == hnum && !sk->sk_node.next && - (!inet->rcv_saddr || inet->rcv_saddr == daddr) && - (sk->sk_family == PF_INET || !ipv6_only_sock(sk)) && - !sk->sk_bound_dev_if && net_eq(sock_net(sk), net)) - goto sherry_cache; - sk = inet_lookup_listener_slow(net, head, daddr, hnum, dif); + struct sock *sk, *result; + struct hlist_nulls_node *node; + unsigned int hash = inet_lhashfn(net, hnum); + struct inet_listen_hashbucket *ilb = &hashinfo->listening_hash[hash]; + int score, hiscore; + + rcu_read_lock(); +begin: + result = NULL; + hiscore = -1; + sk_nulls_for_each_rcu(sk, node, &ilb->head) { + score = compute_score(sk, net, hnum, daddr, dif); + if (score > hiscore) { + result = sk; + hiscore = score; + } } - if (sk) { -sherry_cache: - sock_hold(sk); + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash + LISTENING_NULLS_BASE) + goto begin; + if (result) { + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score(result, net, hnum, daddr, + dif) < hiscore)) { + sock_put(result); + goto begin; + } } - read_unlock(&hashinfo->lhash_lock); - return sk; + rcu_read_unlock(); + return result; } EXPORT_SYMBOL_GPL(__inet_lookup_listener); @@ -223,35 +195,65 @@ struct sock * __inet_lookup_established(struct net *net, INET_ADDR_COOKIE(acookie, saddr, daddr) const __portpair ports = INET_COMBINED_PORTS(sport, hnum); struct sock *sk; - const struct hlist_node *node; + const struct hlist_nulls_node *node; /* Optimize here for direct hit, only listening connections can * have wildcards anyways. */ unsigned int hash = inet_ehashfn(net, daddr, hnum, saddr, sport); - struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hashinfo, hash); + unsigned int slot = hash & (hashinfo->ehash_size - 1); + struct inet_ehash_bucket *head = &hashinfo->ehash[slot]; - prefetch(head->chain.first); - read_lock(lock); - sk_for_each(sk, node, &head->chain) { + rcu_read_lock(); +begin: + sk_nulls_for_each_rcu(sk, node, &head->chain) { if (INET_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif)) - goto hit; /* You sunk my battleship! */ + saddr, daddr, ports, dif)) { + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) + goto begintw; + if (unlikely(!INET_MATCH(sk, net, hash, acookie, + saddr, daddr, ports, dif))) { + sock_put(sk); + goto begin; + } + goto out; + } } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begin; +begintw: /* Must check for a TIME_WAIT'er before going to listener hash. */ - sk_for_each(sk, node, &head->twchain) { + sk_nulls_for_each_rcu(sk, node, &head->twchain) { if (INET_TW_MATCH(sk, net, hash, acookie, - saddr, daddr, ports, dif)) - goto hit; + saddr, daddr, ports, dif)) { + if (unlikely(!atomic_inc_not_zero(&sk->sk_refcnt))) { + sk = NULL; + goto out; + } + if (unlikely(!INET_TW_MATCH(sk, net, hash, acookie, + saddr, daddr, ports, dif))) { + sock_put(sk); + goto begintw; + } + goto out; + } } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begintw; sk = NULL; out: - read_unlock(lock); + rcu_read_unlock(); return sk; -hit: - sock_hold(sk); - goto out; } EXPORT_SYMBOL_GPL(__inet_lookup_established); @@ -270,16 +272,15 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, struct net *net = sock_net(sk); unsigned int hash = inet_ehashfn(net, daddr, lport, saddr, inet->dport); struct inet_ehash_bucket *head = inet_ehash_bucket(hinfo, hash); - rwlock_t *lock = inet_ehash_lockp(hinfo, hash); + spinlock_t *lock = inet_ehash_lockp(hinfo, hash); struct sock *sk2; - const struct hlist_node *node; + const struct hlist_nulls_node *node; struct inet_timewait_sock *tw; - prefetch(head->chain.first); - write_lock(lock); + spin_lock(lock); /* Check TIME-WAIT sockets first. */ - sk_for_each(sk2, node, &head->twchain) { + sk_nulls_for_each(sk2, node, &head->twchain) { tw = inet_twsk(sk2); if (INET_TW_MATCH(sk2, net, hash, acookie, @@ -293,7 +294,7 @@ static int __inet_check_established(struct inet_timewait_death_row *death_row, tw = NULL; /* And established part... */ - sk_for_each(sk2, node, &head->chain) { + sk_nulls_for_each(sk2, node, &head->chain) { if (INET_MATCH(sk2, net, hash, acookie, saddr, daddr, ports, dif)) goto not_unique; @@ -306,9 +307,9 @@ unique: inet->sport = htons(lport); sk->sk_hash = hash; WARN_ON(!sk_unhashed(sk)); - __sk_add_node(sk, &head->chain); + __sk_nulls_add_node_rcu(sk, &head->chain); + spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); if (twp) { *twp = tw; @@ -324,7 +325,7 @@ unique: return 0; not_unique: - write_unlock(lock); + spin_unlock(lock); return -EADDRNOTAVAIL; } @@ -338,8 +339,8 @@ static inline u32 inet_sk_port_offset(const struct sock *sk) void __inet_hash_nolisten(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - struct hlist_head *list; - rwlock_t *lock; + struct hlist_nulls_head *list; + spinlock_t *lock; struct inet_ehash_bucket *head; WARN_ON(!sk_unhashed(sk)); @@ -349,18 +350,17 @@ void __inet_hash_nolisten(struct sock *sk) list = &head->chain; lock = inet_ehash_lockp(hashinfo, sk->sk_hash); - write_lock(lock); - __sk_add_node(sk, list); + spin_lock(lock); + __sk_nulls_add_node_rcu(sk, list); + spin_unlock(lock); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); } EXPORT_SYMBOL_GPL(__inet_hash_nolisten); static void __inet_hash(struct sock *sk) { struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; - struct hlist_head *list; - rwlock_t *lock; + struct inet_listen_hashbucket *ilb; if (sk->sk_state != TCP_LISTEN) { __inet_hash_nolisten(sk); @@ -368,14 +368,12 @@ static void __inet_hash(struct sock *sk) } WARN_ON(!sk_unhashed(sk)); - list = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - lock = &hashinfo->lhash_lock; + ilb = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)]; - inet_listen_wlock(hashinfo); - __sk_add_node(sk, list); + spin_lock(&ilb->lock); + __sk_nulls_add_node_rcu(sk, &ilb->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); - write_unlock(lock); - wake_up(&hashinfo->lhash_wait); + spin_unlock(&ilb->lock); } void inet_hash(struct sock *sk) @@ -390,27 +388,23 @@ EXPORT_SYMBOL_GPL(inet_hash); void inet_unhash(struct sock *sk) { - rwlock_t *lock; struct inet_hashinfo *hashinfo = sk->sk_prot->h.hashinfo; + spinlock_t *lock; + int done; if (sk_unhashed(sk)) - goto out; + return; - if (sk->sk_state == TCP_LISTEN) { - local_bh_disable(); - inet_listen_wlock(hashinfo); - lock = &hashinfo->lhash_lock; - } else { + if (sk->sk_state == TCP_LISTEN) + lock = &hashinfo->listening_hash[inet_sk_listen_hashfn(sk)].lock; + else lock = inet_ehash_lockp(hashinfo, sk->sk_hash); - write_lock_bh(lock); - } - if (__sk_del_node_init(sk)) + spin_lock_bh(lock); + done =__sk_nulls_del_node_init_rcu(sk); + if (done) sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - write_unlock_bh(lock); -out: - if (sk->sk_state == TCP_LISTEN) - wake_up(&hashinfo->lhash_wait); + spin_unlock_bh(lock); } EXPORT_SYMBOL_GPL(inet_unhash); @@ -449,7 +443,7 @@ int __inet_hash_connect(struct inet_timewait_death_row *death_row, * unique enough. */ inet_bind_bucket_for_each(tb, node, &head->chain) { - if (tb->ib_net == net && tb->port == port) { + if (ib_net(tb) == net && tb->port == port) { WARN_ON(hlist_empty(&tb->owners)); if (tb->fastreuse >= 0) goto next_port; @@ -524,3 +518,16 @@ int inet_hash_connect(struct inet_timewait_death_row *death_row, } EXPORT_SYMBOL_GPL(inet_hash_connect); + +void inet_hashinfo_init(struct inet_hashinfo *h) +{ + int i; + + for (i = 0; i < INET_LHTABLE_SIZE; i++) { + spin_lock_init(&h->listening_hash[i].lock); + INIT_HLIST_NULLS_HEAD(&h->listening_hash[i].head, + i + LISTENING_NULLS_BASE); + } +} + +EXPORT_SYMBOL_GPL(inet_hashinfo_init); diff --git a/net/ipv4/inet_lro.c b/net/ipv4/inet_lro.c index cfd034a2b96e..6a667dae315e 100644 --- a/net/ipv4/inet_lro.c +++ b/net/ipv4/inet_lro.c @@ -120,7 +120,7 @@ static void lro_update_tcp_ip_header(struct net_lro_desc *lro_desc) iph->check = ip_fast_csum((u8 *)lro_desc->iph, iph->ihl); tcph->check = 0; - tcp_hdr_csum = csum_partial((u8 *)tcph, TCP_HDR_LEN(tcph), 0); + tcp_hdr_csum = csum_partial(tcph, TCP_HDR_LEN(tcph), 0); lro_desc->data_csum = csum_add(lro_desc->data_csum, tcp_hdr_csum); tcph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, lro_desc->ip_tot_len - @@ -135,7 +135,7 @@ static __wsum lro_tcp_data_csum(struct iphdr *iph, struct tcphdr *tcph, int len) __wsum tcp_ps_hdr_csum; tcp_csum = ~csum_unfold(tcph->check); - tcp_hdr_csum = csum_partial((u8 *)tcph, TCP_HDR_LEN(tcph), tcp_csum); + tcp_hdr_csum = csum_partial(tcph, TCP_HDR_LEN(tcph), tcp_csum); tcp_ps_hdr_csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, len + TCP_HDR_LEN(tcph), diff --git a/net/ipv4/inet_timewait_sock.c b/net/ipv4/inet_timewait_sock.c index 1c5fd38f8824..8554d0ea1719 100644 --- a/net/ipv4/inet_timewait_sock.c +++ b/net/ipv4/inet_timewait_sock.c @@ -20,16 +20,16 @@ static void __inet_twsk_kill(struct inet_timewait_sock *tw, struct inet_bind_hashbucket *bhead; struct inet_bind_bucket *tb; /* Unlink from established hashes. */ - rwlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); + spinlock_t *lock = inet_ehash_lockp(hashinfo, tw->tw_hash); - write_lock(lock); - if (hlist_unhashed(&tw->tw_node)) { - write_unlock(lock); + spin_lock(lock); + if (hlist_nulls_unhashed(&tw->tw_node)) { + spin_unlock(lock); return; } - __hlist_del(&tw->tw_node); - sk_node_init(&tw->tw_node); - write_unlock(lock); + hlist_nulls_del_rcu(&tw->tw_node); + sk_nulls_node_init(&tw->tw_node); + spin_unlock(lock); /* Disassociate with bind bucket. */ bhead = &hashinfo->bhash[inet_bhashfn(twsk_net(tw), tw->tw_num, @@ -76,7 +76,7 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, const struct inet_sock *inet = inet_sk(sk); const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_ehash_bucket *ehead = inet_ehash_bucket(hashinfo, sk->sk_hash); - rwlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); + spinlock_t *lock = inet_ehash_lockp(hashinfo, sk->sk_hash); struct inet_bind_hashbucket *bhead; /* Step 1: Put TW into bind hash. Original socket stays there too. Note, that any socket with inet->num != 0 MUST be bound in @@ -90,17 +90,21 @@ void __inet_twsk_hashdance(struct inet_timewait_sock *tw, struct sock *sk, inet_twsk_add_bind_node(tw, &tw->tw_tb->owners); spin_unlock(&bhead->lock); - write_lock(lock); + spin_lock(lock); - /* Step 2: Remove SK from established hash. */ - if (__sk_del_node_init(sk)) - sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); - - /* Step 3: Hash TW into TIMEWAIT chain. */ - inet_twsk_add_node(tw, &ehead->twchain); + /* + * Step 2: Hash TW into TIMEWAIT chain. + * Should be done before removing sk from established chain + * because readers are lockless and search established first. + */ atomic_inc(&tw->tw_refcnt); + inet_twsk_add_node_rcu(tw, &ehead->twchain); - write_unlock(lock); + /* Step 3: Remove SK from established hash. */ + if (__sk_nulls_del_node_init_rcu(sk)) + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + + spin_unlock(lock); } EXPORT_SYMBOL_GPL(__inet_twsk_hashdance); @@ -416,17 +420,17 @@ void inet_twsk_purge(struct net *net, struct inet_hashinfo *hashinfo, { struct inet_timewait_sock *tw; struct sock *sk; - struct hlist_node *node; + struct hlist_nulls_node *node; int h; local_bh_disable(); for (h = 0; h < (hashinfo->ehash_size); h++) { struct inet_ehash_bucket *head = inet_ehash_bucket(hashinfo, h); - rwlock_t *lock = inet_ehash_lockp(hashinfo, h); + spinlock_t *lock = inet_ehash_lockp(hashinfo, h); restart: - write_lock(lock); - sk_for_each(sk, node, &head->twchain) { + spin_lock(lock); + sk_nulls_for_each(sk, node, &head->twchain) { tw = inet_twsk(sk); if (!net_eq(twsk_net(tw), net) || @@ -434,13 +438,13 @@ restart: continue; atomic_inc(&tw->tw_refcnt); - write_unlock(lock); + spin_unlock(lock); inet_twsk_deschedule(tw, twdr); inet_twsk_put(tw); goto restart; } - write_unlock(lock); + spin_unlock(lock); } local_bh_enable(); } diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index a456ceeac3f2..b1fbe18feb5a 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -144,7 +144,7 @@ static void unlink_from_unused(struct inet_peer *p) * _stack is known to be NULL or not at compile time, * so compiler will optimize the if (_stack) tests. */ -#define lookup(_daddr,_stack) \ +#define lookup(_daddr, _stack) \ ({ \ struct inet_peer *u, **v; \ if (_stack != NULL) { \ diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 450016b89a18..df3fe50bbf0d 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -106,7 +106,7 @@ int ip_forward(struct sk_buff *skb) * We now generate an ICMP HOST REDIRECT giving the route * we calculated. */ - if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb->sp) + if (rt->rt_flags&RTCF_DOREDIRECT && !opt->srr && !skb_sec_path(skb)) ip_rt_send_redirect(skb); skb->priority = rt_tos2priority(iph->tos); diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index e4f81f54befe..6659ac000eeb 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -56,7 +56,7 @@ struct ipfrag_skb_cb int offset; }; -#define FRAG_CB(skb) ((struct ipfrag_skb_cb*)((skb)->cb)) +#define FRAG_CB(skb) ((struct ipfrag_skb_cb *)((skb)->cb)) /* Describe an entry in the "incomplete datagrams" queue. */ struct ipq { @@ -559,9 +559,8 @@ out_nomem: goto out_fail; out_oversize: if (net_ratelimit()) - printk(KERN_INFO - "Oversized IP packet from " NIPQUAD_FMT ".\n", - NIPQUAD(qp->saddr)); + printk(KERN_INFO "Oversized IP packet from %pI4.\n", + &qp->saddr); out_fail: IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_REASMFAILS); return err; @@ -608,7 +607,7 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .data = &init_net.ipv4.frags.high_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_IPFRAG_LOW_THRESH, @@ -616,7 +615,7 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .data = &init_net.ipv4.frags.low_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_IPFRAG_TIME, @@ -624,8 +623,8 @@ static struct ctl_table ip4_frags_ns_ctl_table[] = { .data = &init_net.ipv4.frags.timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { } }; @@ -637,15 +636,15 @@ static struct ctl_table ip4_frags_ctl_table[] = { .data = &ip4_frags.secret_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .procname = "ipfrag_max_dist", .data = &sysctl_ipfrag_max_dist, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, + .proc_handler = proc_dointvec_minmax, .extra1 = &zero }, { } diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 85c487b8572b..0101521f366b 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -126,8 +126,6 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev); /* Fallback tunnel: no source, no destination, no key, no options */ -static int ipgre_fb_tunnel_init(struct net_device *dev); - #define HASH_SIZE 16 static int ipgre_net_id; @@ -371,7 +369,7 @@ static void ipgre_err(struct sk_buff *skb, u32 info) by themself??? */ - struct iphdr *iph = (struct iphdr*)skb->data; + struct iphdr *iph = (struct iphdr *)skb->data; __be16 *p = (__be16*)(skb->data+(iph->ihl<<2)); int grehlen = (iph->ihl<<2) + 4; const int type = icmp_hdr(skb)->type; @@ -632,7 +630,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (dev->header_ops && dev->type == ARPHRD_IPGRE) { gre_hlen = 0; - tiph = (struct iphdr*)skb->data; + tiph = (struct iphdr *)skb->data; } else { gre_hlen = tunnel->hlen; tiph = &tunnel->parms.iph; @@ -660,7 +658,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (neigh == NULL) goto tx_error; - addr6 = (struct in6_addr*)&neigh->primary_key; + addr6 = (struct in6_addr *)&neigh->primary_key; addr_type = ipv6_addr_type(addr6); if (addr_type == IPV6_ADDR_ANY) { @@ -726,7 +724,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } #ifdef CONFIG_IPV6 else if (skb->protocol == htons(ETH_P_IPV6)) { - struct rt6_info *rt6 = (struct rt6_info*)skb->dst; + struct rt6_info *rt6 = (struct rt6_info *)skb->dst; if (rt6 && mtu < dst_mtu(skb->dst) && mtu >= IPV6_MIN_MTU) { if ((tunnel->parms.iph.daddr && @@ -800,7 +798,7 @@ static int ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) iph->ttl = old_iph->ttl; #ifdef CONFIG_IPV6 else if (skb->protocol == htons(ETH_P_IPV6)) - iph->ttl = ((struct ipv6hdr*)old_iph)->hop_limit; + iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif else iph->ttl = dst_metric(&rt->u.dst, RTAX_HOPLIMIT); @@ -962,7 +960,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } } else { - unsigned nflags=0; + unsigned nflags = 0; t = netdev_priv(dev); @@ -1104,7 +1102,7 @@ static int ipgre_header(struct sk_buff *skb, struct net_device *dev, static int ipgre_header_parse(const struct sk_buff *skb, unsigned char *haddr) { - struct iphdr *iph = (struct iphdr*) skb_mac_header(skb); + struct iphdr *iph = (struct iphdr *) skb_mac_header(skb); memcpy(haddr, &iph->saddr, 4); return 4; } @@ -1142,6 +1140,7 @@ static int ipgre_open(struct net_device *dev) static int ipgre_close(struct net_device *dev) { struct ip_tunnel *t = netdev_priv(dev); + if (ipv4_is_multicast(t->parms.iph.daddr) && t->mlink) { struct in_device *in_dev; in_dev = inetdev_by_index(dev_net(dev), t->mlink); @@ -1155,14 +1154,22 @@ static int ipgre_close(struct net_device *dev) #endif +static const struct net_device_ops ipgre_netdev_ops = { + .ndo_init = ipgre_tunnel_init, + .ndo_uninit = ipgre_tunnel_uninit, +#ifdef CONFIG_NET_IPGRE_BROADCAST + .ndo_open = ipgre_open, + .ndo_stop = ipgre_close, +#endif + .ndo_start_xmit = ipgre_tunnel_xmit, + .ndo_do_ioctl = ipgre_tunnel_ioctl, + .ndo_change_mtu = ipgre_tunnel_change_mtu, +}; + static void ipgre_tunnel_setup(struct net_device *dev) { - dev->init = ipgre_tunnel_init; - dev->uninit = ipgre_tunnel_uninit; + dev->netdev_ops = &ipgre_netdev_ops; dev->destructor = free_netdev; - dev->hard_start_xmit = ipgre_tunnel_xmit; - dev->do_ioctl = ipgre_tunnel_ioctl; - dev->change_mtu = ipgre_tunnel_change_mtu; dev->type = ARPHRD_IPGRE; dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4; @@ -1194,8 +1201,6 @@ static int ipgre_tunnel_init(struct net_device *dev) return -EINVAL; dev->flags = IFF_BROADCAST; dev->header_ops = &ipgre_header_ops; - dev->open = ipgre_open; - dev->stop = ipgre_close; } #endif } else @@ -1204,7 +1209,7 @@ static int ipgre_tunnel_init(struct net_device *dev) return 0; } -static int ipgre_fb_tunnel_init(struct net_device *dev) +static void ipgre_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -1220,7 +1225,6 @@ static int ipgre_fb_tunnel_init(struct net_device *dev) dev_hold(dev); ign->tunnels_wc[0] = tunnel; - return 0; } @@ -1264,9 +1268,9 @@ static int ipgre_init_net(struct net *net) err = -ENOMEM; goto err_alloc_dev; } - - ign->fb_tunnel_dev->init = ipgre_fb_tunnel_init; dev_net_set(ign->fb_tunnel_dev, net); + + ipgre_fb_tunnel_init(ign->fb_tunnel_dev); ign->fb_tunnel_dev->rtnl_link_ops = &ipgre_link_ops; if ((err = register_netdev(ign->fb_tunnel_dev))) @@ -1397,16 +1401,22 @@ static int ipgre_tap_init(struct net_device *dev) return 0; } +static const struct net_device_ops ipgre_tap_netdev_ops = { + .ndo_init = ipgre_tap_init, + .ndo_uninit = ipgre_tunnel_uninit, + .ndo_start_xmit = ipgre_tunnel_xmit, + .ndo_set_mac_address = eth_mac_addr, + .ndo_validate_addr = eth_validate_addr, + .ndo_change_mtu = ipgre_tunnel_change_mtu, +}; + static void ipgre_tap_setup(struct net_device *dev) { ether_setup(dev); - dev->init = ipgre_tap_init; - dev->uninit = ipgre_tunnel_uninit; + dev->netdev_ops = &ipgre_netdev_ops; dev->destructor = free_netdev; - dev->hard_start_xmit = ipgre_tunnel_xmit; - dev->change_mtu = ipgre_tunnel_change_mtu; dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index cfb38ac9d698..1a58a6fa1dc0 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -302,10 +302,8 @@ static inline int ip_rcv_options(struct sk_buff *skb) if (!IN_DEV_SOURCE_ROUTE(in_dev)) { if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - printk(KERN_INFO "source route option " - NIPQUAD_FMT " -> " NIPQUAD_FMT "\n", - NIPQUAD(iph->saddr), - NIPQUAD(iph->daddr)); + printk(KERN_INFO "source route option %pI4 -> %pI4\n", + &iph->saddr, &iph->daddr); in_dev_put(in_dev); goto drop; } @@ -350,9 +348,9 @@ static int ip_rcv_finish(struct sk_buff *skb) struct ip_rt_acct *st = per_cpu_ptr(ip_rt_acct, smp_processor_id()); u32 idx = skb->dst->tclassid; st[idx&0xFF].o_packets++; - st[idx&0xFF].o_bytes+=skb->len; + st[idx&0xFF].o_bytes += skb->len; st[(idx>>16)&0xFF].i_packets++; - st[(idx>>16)&0xFF].i_bytes+=skb->len; + st[(idx>>16)&0xFF].i_bytes += skb->len; } #endif diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index d2a8f8bb78a6..8ebe86dd72af 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -430,7 +430,7 @@ static void ip_copy_metadata(struct sk_buff *to, struct sk_buff *from) * single device frame, and queue such a frame for sending. */ -int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff*)) +int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) { struct iphdr *iph; int raw = 0; @@ -720,7 +720,7 @@ static inline int ip_ufo_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int hh_len, int fragheaderlen, - int transhdrlen, int mtu,unsigned int flags) + int transhdrlen, int mtu, unsigned int flags) { struct sk_buff *skb; int err; @@ -741,7 +741,7 @@ static inline int ip_ufo_append_data(struct sock *sk, skb_reserve(skb, hh_len); /* create space for UDP/IP header */ - skb_put(skb,fragheaderlen + transhdrlen); + skb_put(skb, fragheaderlen + transhdrlen); /* initialize network header pointer */ skb_reset_network_header(skb); @@ -778,7 +778,7 @@ int ip_append_data(struct sock *sk, int getfrag(void *from, char *to, int offset, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, - struct ipcm_cookie *ipc, struct rtable *rt, + struct ipcm_cookie *ipc, struct rtable **rtp, unsigned int flags) { struct inet_sock *inet = inet_sk(sk); @@ -793,6 +793,7 @@ int ip_append_data(struct sock *sk, int offset = 0; unsigned int maxfraglen, fragheaderlen; int csummode = CHECKSUM_NONE; + struct rtable *rt; if (flags&MSG_PROBE) return 0; @@ -812,7 +813,11 @@ int ip_append_data(struct sock *sk, inet->cork.flags |= IPCORK_OPT; inet->cork.addr = ipc->addr; } - dst_hold(&rt->u.dst); + rt = *rtp; + /* + * We steal reference to this route, caller should not release it + */ + *rtp = NULL; inet->cork.fragsize = mtu = inet->pmtudisc == IP_PMTUDISC_PROBE ? rt->u.dst.dev->mtu : dst_mtu(rt->u.dst.path); @@ -1279,7 +1284,12 @@ int ip_push_pending_frames(struct sock *sk) skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; - skb->dst = dst_clone(&rt->u.dst); + /* + * Steal rt from cork.dst to avoid a pair of atomic_inc/atomic_dec + * on dst refcount + */ + inet->cork.dst = NULL; + skb->dst = &rt->u.dst; if (iph->protocol == IPPROTO_ICMP) icmp_out_count(net, ((struct icmphdr *) @@ -1391,7 +1401,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar sk->sk_protocol = ip_hdr(skb)->protocol; sk->sk_bound_dev_if = arg->bound_dev_if; ip_append_data(sk, ip_reply_glue_bits, arg->iov->iov_base, len, 0, - &ipc, rt, MSG_DONTWAIT); + &ipc, &rt, MSG_DONTWAIT); if ((skb = skb_peek(&sk->sk_write_queue)) != NULL) { if (arg->csumoffset >= 0) *((__sum16 *)skb_transport_header(skb) + diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 465abf0a9869..43c05854d752 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -48,6 +48,7 @@ #define IP_CMSG_RECVOPTS 8 #define IP_CMSG_RETOPTS 16 #define IP_CMSG_PASSSEC 32 +#define IP_CMSG_ORIGDSTADDR 64 /* * SOL_IP control messages. @@ -94,7 +95,7 @@ static void ip_cmsg_recv_opts(struct msghdr *msg, struct sk_buff *skb) static void ip_cmsg_recv_retopts(struct msghdr *msg, struct sk_buff *skb) { unsigned char optbuf[sizeof(struct ip_options) + 40]; - struct ip_options * opt = (struct ip_options*)optbuf; + struct ip_options * opt = (struct ip_options *)optbuf; if (IPCB(skb)->opt.optlen == 0) return; @@ -126,6 +127,27 @@ static void ip_cmsg_recv_security(struct msghdr *msg, struct sk_buff *skb) security_release_secctx(secdata, seclen); } +static void ip_cmsg_recv_dstaddr(struct msghdr *msg, struct sk_buff *skb) +{ + struct sockaddr_in sin; + struct iphdr *iph = ip_hdr(skb); + __be16 *ports = (__be16 *)skb_transport_header(skb); + + if (skb_transport_offset(skb) + 4 > skb->len) + return; + + /* All current transport protocols have the port numbers in the + * first four bytes of the transport header and this function is + * written with this assumption in mind. + */ + + sin.sin_family = AF_INET; + sin.sin_addr.s_addr = iph->daddr; + sin.sin_port = ports[1]; + memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); + + put_cmsg(msg, SOL_IP, IP_ORIGDSTADDR, sizeof(sin), &sin); +} void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) { @@ -160,6 +182,12 @@ void ip_cmsg_recv(struct msghdr *msg, struct sk_buff *skb) if (flags & 1) ip_cmsg_recv_security(msg, skb); + + if ((flags>>=1) == 0) + return; + if (flags & 1) + ip_cmsg_recv_dstaddr(msg, skb); + } int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) @@ -411,7 +439,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, int optlen) { struct inet_sock *inet = inet_sk(sk); - int val=0,err; + int val = 0, err; if (((1<<optname) & ((1<<IP_PKTINFO) | (1<<IP_RECVTTL) | (1<<IP_RECVOPTS) | (1<<IP_RECVTOS) | @@ -421,7 +449,8 @@ static int do_ip_setsockopt(struct sock *sk, int level, (1<<IP_ROUTER_ALERT) | (1<<IP_FREEBIND) | (1<<IP_PASSSEC) | (1<<IP_TRANSPARENT))) || optname == IP_MULTICAST_TTL || - optname == IP_MULTICAST_LOOP) { + optname == IP_MULTICAST_LOOP || + optname == IP_RECVORIGDSTADDR) { if (optlen >= sizeof(int)) { if (get_user(val, (int __user *) optval)) return -EFAULT; @@ -437,7 +466,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, /* If optlen==0, it is equivalent to val == 0 */ if (ip_mroute_opt(optname)) - return ip_mroute_setsockopt(sk,optname,optval,optlen); + return ip_mroute_setsockopt(sk, optname, optval, optlen); err = 0; lock_sock(sk); @@ -509,6 +538,12 @@ static int do_ip_setsockopt(struct sock *sk, int level, else inet->cmsg_flags &= ~IP_CMSG_PASSSEC; break; + case IP_RECVORIGDSTADDR: + if (val) + inet->cmsg_flags |= IP_CMSG_ORIGDSTADDR; + else + inet->cmsg_flags &= ~IP_CMSG_ORIGDSTADDR; + break; case IP_TOS: /* This sets both TOS and Precedence */ if (sk->sk_type == SOCK_STREAM) { val &= ~3; @@ -549,7 +584,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, goto e_inval; if (optlen<1) goto e_inval; - if (val==-1) + if (val == -1) val = 1; if (val < 0 || val > 255) goto e_inval; @@ -573,12 +608,12 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { - if (copy_from_user(&mreq,optval,sizeof(mreq))) + if (copy_from_user(&mreq, optval, sizeof(mreq))) break; } else { memset(&mreq, 0, sizeof(mreq)); if (optlen >= sizeof(struct in_addr) && - copy_from_user(&mreq.imr_address,optval,sizeof(struct in_addr))) + copy_from_user(&mreq.imr_address, optval, sizeof(struct in_addr))) break; } @@ -626,11 +661,11 @@ static int do_ip_setsockopt(struct sock *sk, int level, goto e_inval; err = -EFAULT; if (optlen >= sizeof(struct ip_mreqn)) { - if (copy_from_user(&mreq,optval,sizeof(mreq))) + if (copy_from_user(&mreq, optval, sizeof(mreq))) break; } else { memset(&mreq, 0, sizeof(mreq)); - if (copy_from_user(&mreq,optval,sizeof(struct ip_mreq))) + if (copy_from_user(&mreq, optval, sizeof(struct ip_mreq))) break; } @@ -808,7 +843,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, err = -ENOBUFS; break; } - gsf = kmalloc(optlen,GFP_KERNEL); + gsf = kmalloc(optlen, GFP_KERNEL); if (!gsf) { err = -ENOBUFS; break; @@ -828,7 +863,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, goto mc_msf_out; } msize = IP_MSFILTER_SIZE(gsf->gf_numsrc); - msf = kmalloc(msize,GFP_KERNEL); + msf = kmalloc(msize, GFP_KERNEL); if (!msf) { err = -ENOBUFS; goto mc_msf_out; @@ -971,9 +1006,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, return -EOPNOTSUPP; if (ip_mroute_opt(optname)) - return ip_mroute_getsockopt(sk,optname,optval,optlen); + return ip_mroute_getsockopt(sk, optname, optval, optlen); - if (get_user(len,optlen)) + if (get_user(len, optlen)) return -EFAULT; if (len < 0) return -EINVAL; @@ -984,7 +1019,7 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_OPTIONS: { unsigned char optbuf[sizeof(struct ip_options)+40]; - struct ip_options * opt = (struct ip_options*)optbuf; + struct ip_options * opt = (struct ip_options *)optbuf; opt->optlen = 0; if (inet->opt) memcpy(optbuf, inet->opt, @@ -1022,6 +1057,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_PASSSEC: val = (inet->cmsg_flags & IP_CMSG_PASSSEC) != 0; break; + case IP_RECVORIGDSTADDR: + val = (inet->cmsg_flags & IP_CMSG_ORIGDSTADDR) != 0; + break; case IP_TOS: val = inet->tos; break; @@ -1154,13 +1192,13 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, len = 1; if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval,&ucval,1)) + if (copy_to_user(optval, &ucval, 1)) return -EFAULT; } else { len = min_t(unsigned int, sizeof(int), len); if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval,&val,len)) + if (copy_to_user(optval, &val, len)) return -EFAULT; } return 0; @@ -1178,7 +1216,7 @@ int ip_getsockopt(struct sock *sk, int level, !ip_mroute_opt(optname)) { int len; - if (get_user(len,optlen)) + if (get_user(len, optlen)) return -EFAULT; lock_sock(sk); diff --git a/net/ipv4/ipcomp.c b/net/ipv4/ipcomp.c index 38ccb6dfb02e..3262ce06294c 100644 --- a/net/ipv4/ipcomp.c +++ b/net/ipv4/ipcomp.c @@ -35,12 +35,12 @@ static void ipcomp4_err(struct sk_buff *skb, u32 info) return; spi = htonl(ntohs(ipch->cpi)); - x = xfrm_state_lookup((xfrm_address_t *)&iph->daddr, + x = xfrm_state_lookup(&init_net, (xfrm_address_t *)&iph->daddr, spi, IPPROTO_COMP, AF_INET); if (!x) return; - NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/" NIPQUAD_FMT "\n", - spi, NIPQUAD(iph->daddr)); + NETDEBUG(KERN_DEBUG "pmtu discovery on SA IPCOMP/%08x/%pI4\n", + spi, &iph->daddr); xfrm_state_put(x); } @@ -49,7 +49,7 @@ static struct xfrm_state *ipcomp_tunnel_create(struct xfrm_state *x) { struct xfrm_state *t; - t = xfrm_state_alloc(); + t = xfrm_state_alloc(&init_net); if (t == NULL) goto out; @@ -85,7 +85,7 @@ static int ipcomp_tunnel_attach(struct xfrm_state *x) int err = 0; struct xfrm_state *t; - t = xfrm_state_lookup((xfrm_address_t *)&x->id.daddr.a4, + t = xfrm_state_lookup(&init_net, (xfrm_address_t *)&x->id.daddr.a4, x->props.saddr.a4, IPPROTO_IPIP, AF_INET); if (!t) { t = ipcomp_tunnel_create(x); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 42065fff46c4..42a0f3dd3fd6 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -374,7 +374,7 @@ static int __init ic_defaults(void) */ if (!ic_host_name_set) - sprintf(init_utsname()->nodename, NIPQUAD_FMT, NIPQUAD(ic_myaddr)); + sprintf(init_utsname()->nodename, "%pI4", &ic_myaddr); if (root_server_addr == NONE) root_server_addr = ic_servaddr; @@ -387,11 +387,11 @@ static int __init ic_defaults(void) else if (IN_CLASSC(ntohl(ic_myaddr))) ic_netmask = htonl(IN_CLASSC_NET); else { - printk(KERN_ERR "IP-Config: Unable to guess netmask for address " NIPQUAD_FMT "\n", - NIPQUAD(ic_myaddr)); + printk(KERN_ERR "IP-Config: Unable to guess netmask for address %pI4\n", + &ic_myaddr); return -1; } - printk("IP-Config: Guessing netmask " NIPQUAD_FMT "\n", NIPQUAD(ic_netmask)); + printk("IP-Config: Guessing netmask %pI4\n", &ic_netmask); } return 0; @@ -979,10 +979,8 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str ic_myaddr = b->your_ip; ic_servaddr = server_id; #ifdef IPCONFIG_DEBUG - printk("DHCP: Offered address " NIPQUAD_FMT, - NIPQUAD(ic_myaddr)); - printk(" by server " NIPQUAD_FMT "\n", - NIPQUAD(ic_servaddr)); + printk("DHCP: Offered address %pI4 by server %pI4\n", + &ic_myaddr, &ic_servaddr); #endif /* The DHCP indicated server address takes * precedence over the bootp header one if @@ -1177,11 +1175,11 @@ static int __init ic_dynamic(void) return -1; } - printk("IP-Config: Got %s answer from " NIPQUAD_FMT ", ", + printk("IP-Config: Got %s answer from %pI4, ", ((ic_got_reply & IC_RARP) ? "RARP" : (ic_proto_enabled & IC_USE_DHCP) ? "DHCP" : "BOOTP"), - NIPQUAD(ic_servaddr)); - printk("my address is " NIPQUAD_FMT "\n", NIPQUAD(ic_myaddr)); + &ic_servaddr); + printk("my address is %pI4\n", &ic_myaddr); return 0; } @@ -1206,14 +1204,12 @@ static int pnp_seq_show(struct seq_file *seq, void *v) "domain %s\n", ic_domain); for (i = 0; i < CONF_NAMESERVERS_MAX; i++) { if (ic_nameservers[i] != NONE) - seq_printf(seq, - "nameserver " NIPQUAD_FMT "\n", - NIPQUAD(ic_nameservers[i])); + seq_printf(seq, "nameserver %pI4\n", + &ic_nameservers[i]); } if (ic_servaddr != NONE) - seq_printf(seq, - "bootserver " NIPQUAD_FMT "\n", - NIPQUAD(ic_servaddr)); + seq_printf(seq, "bootserver %pI4\n", + &ic_servaddr); return 0; } @@ -1387,13 +1383,13 @@ static int __init ip_auto_config(void) */ printk("IP-Config: Complete:"); printk("\n device=%s", ic_dev->name); - printk(", addr=" NIPQUAD_FMT, NIPQUAD(ic_myaddr)); - printk(", mask=" NIPQUAD_FMT, NIPQUAD(ic_netmask)); - printk(", gw=" NIPQUAD_FMT, NIPQUAD(ic_gateway)); + printk(", addr=%pI4", &ic_myaddr); + printk(", mask=%pI4", &ic_netmask); + printk(", gw=%pI4", &ic_gateway); printk(",\n host=%s, domain=%s, nis-domain=%s", utsname()->nodename, ic_domain, utsname()->domainname); - printk(",\n bootserver=" NIPQUAD_FMT, NIPQUAD(ic_servaddr)); - printk(", rootserver=" NIPQUAD_FMT, NIPQUAD(root_server_addr)); + printk(",\n bootserver=%pI4", &ic_servaddr); + printk(", rootserver=%pI4", &root_server_addr); printk(", rootpath=%s", root_server_path); printk("\n"); #endif /* !SILENT */ diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 29609d29df76..5079dfbc6f38 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -130,8 +130,8 @@ struct ipip_net { struct net_device *fb_tunnel_dev; }; -static int ipip_fb_tunnel_init(struct net_device *dev); -static int ipip_tunnel_init(struct net_device *dev); +static void ipip_fb_tunnel_init(struct net_device *dev); +static void ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); static DEFINE_RWLOCK(ipip_lock); @@ -245,9 +245,10 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, } nt = netdev_priv(dev); - dev->init = ipip_tunnel_init; nt->parms = *parms; + ipip_tunnel_init(dev); + if (register_netdevice(dev) < 0) goto failed_free; @@ -281,7 +282,7 @@ static int ipip_err(struct sk_buff *skb, u32 info) 8 bytes of packet payload. It means, that precise relaying of ICMP in the real Internet is absolutely infeasible. */ - struct iphdr *iph = (struct iphdr*)skb->data; + struct iphdr *iph = (struct iphdr *)skb->data; const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct ip_tunnel *t; @@ -691,12 +692,17 @@ static int ipip_tunnel_change_mtu(struct net_device *dev, int new_mtu) return 0; } +static const struct net_device_ops ipip_netdev_ops = { + .ndo_uninit = ipip_tunnel_uninit, + .ndo_start_xmit = ipip_tunnel_xmit, + .ndo_do_ioctl = ipip_tunnel_ioctl, + .ndo_change_mtu = ipip_tunnel_change_mtu, + +}; + static void ipip_tunnel_setup(struct net_device *dev) { - dev->uninit = ipip_tunnel_uninit; - dev->hard_start_xmit = ipip_tunnel_xmit; - dev->do_ioctl = ipip_tunnel_ioctl; - dev->change_mtu = ipip_tunnel_change_mtu; + dev->netdev_ops = &ipip_netdev_ops; dev->destructor = free_netdev; dev->type = ARPHRD_TUNNEL; @@ -708,11 +714,9 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->features |= NETIF_F_NETNS_LOCAL; } -static int ipip_tunnel_init(struct net_device *dev) +static void ipip_tunnel_init(struct net_device *dev) { - struct ip_tunnel *tunnel; - - tunnel = netdev_priv(dev); + struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; strcpy(tunnel->parms.name, dev->name); @@ -721,11 +725,9 @@ static int ipip_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip_tunnel_bind_dev(dev); - - return 0; } -static int ipip_fb_tunnel_init(struct net_device *dev) +static void ipip_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -740,7 +742,6 @@ static int ipip_fb_tunnel_init(struct net_device *dev) dev_hold(dev); ipn->tunnels_wc[0] = tunnel; - return 0; } static struct xfrm_tunnel ipip_handler = { @@ -792,10 +793,10 @@ static int ipip_init_net(struct net *net) err = -ENOMEM; goto err_alloc_dev; } - - ipn->fb_tunnel_dev->init = ipip_fb_tunnel_init; dev_net_set(ipn->fb_tunnel_dev, net); + ipip_fb_tunnel_init(ipn->fb_tunnel_dev); + if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 25924b1eb2ef..14666449dc1c 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -124,8 +124,8 @@ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) dev = __dev_get_by_name(&init_net, "tunl0"); if (dev) { + const struct net_device_ops *ops = dev->netdev_ops; struct ifreq ifr; - mm_segment_t oldfs; struct ip_tunnel_parm p; memset(&p, 0, sizeof(p)); @@ -137,9 +137,13 @@ static void ipmr_del_tunnel(struct net_device *dev, struct vifctl *v) sprintf(p.name, "dvmrp%d", v->vifc_vifi); ifr.ifr_ifru.ifru_data = (__force void __user *)&p; - oldfs = get_fs(); set_fs(KERNEL_DS); - dev->do_ioctl(dev, &ifr, SIOCDELTUNNEL); - set_fs(oldfs); + if (ops->ndo_do_ioctl) { + mm_segment_t oldfs = get_fs(); + + set_fs(KERNEL_DS); + ops->ndo_do_ioctl(dev, &ifr, SIOCDELTUNNEL); + set_fs(oldfs); + } } } @@ -151,9 +155,9 @@ struct net_device *ipmr_new_tunnel(struct vifctl *v) dev = __dev_get_by_name(&init_net, "tunl0"); if (dev) { + const struct net_device_ops *ops = dev->netdev_ops; int err; struct ifreq ifr; - mm_segment_t oldfs; struct ip_tunnel_parm p; struct in_device *in_dev; @@ -166,9 +170,14 @@ struct net_device *ipmr_new_tunnel(struct vifctl *v) sprintf(p.name, "dvmrp%d", v->vifc_vifi); ifr.ifr_ifru.ifru_data = (__force void __user *)&p; - oldfs = get_fs(); set_fs(KERNEL_DS); - err = dev->do_ioctl(dev, &ifr, SIOCADDTUNNEL); - set_fs(oldfs); + if (ops->ndo_do_ioctl) { + mm_segment_t oldfs = get_fs(); + + set_fs(KERNEL_DS); + err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); + set_fs(oldfs); + } else + err = -EOPNOTSUPP; dev = NULL; @@ -213,12 +222,16 @@ static int reg_vif_xmit(struct sk_buff *skb, struct net_device *dev) return 0; } +static const struct net_device_ops reg_vif_netdev_ops = { + .ndo_start_xmit = reg_vif_xmit, +}; + static void reg_vif_setup(struct net_device *dev) { dev->type = ARPHRD_PIMREG; dev->mtu = ETH_DATA_LEN - sizeof(struct iphdr) - 8; dev->flags = IFF_NOARP; - dev->hard_start_xmit = reg_vif_xmit; + dev->netdev_ops = ®_vif_netdev_ops, dev->destructor = free_netdev; } @@ -331,7 +344,7 @@ static void ipmr_destroy_unres(struct mfc_cache *c) atomic_dec(&cache_resolve_queue_len); - while ((skb=skb_dequeue(&c->mfc_un.unres.unresolved))) { + while ((skb = skb_dequeue(&c->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); nlh->nlmsg_type = NLMSG_ERROR; @@ -477,13 +490,13 @@ static int vif_add(struct vifctl *vifc, int mrtsock) /* * Fill in the VIF structures */ - v->rate_limit=vifc->vifc_rate_limit; - v->local=vifc->vifc_lcl_addr.s_addr; - v->remote=vifc->vifc_rmt_addr.s_addr; - v->flags=vifc->vifc_flags; + v->rate_limit = vifc->vifc_rate_limit; + v->local = vifc->vifc_lcl_addr.s_addr; + v->remote = vifc->vifc_rmt_addr.s_addr; + v->flags = vifc->vifc_flags; if (!mrtsock) v->flags |= VIFF_STATIC; - v->threshold=vifc->vifc_threshold; + v->threshold = vifc->vifc_threshold; v->bytes_in = 0; v->bytes_out = 0; v->pkt_in = 0; @@ -494,7 +507,7 @@ static int vif_add(struct vifctl *vifc, int mrtsock) /* And finish update writing critical data */ write_lock_bh(&mrt_lock); - v->dev=dev; + v->dev = dev; #ifdef CONFIG_IP_PIMSM if (v->flags&VIFF_REGISTER) reg_vif_num = vifi; @@ -507,7 +520,7 @@ static int vif_add(struct vifctl *vifc, int mrtsock) static struct mfc_cache *ipmr_cache_find(__be32 origin, __be32 mcastgrp) { - int line=MFC_HASH(mcastgrp,origin); + int line = MFC_HASH(mcastgrp, origin); struct mfc_cache *c; for (c=mfc_cache_array[line]; c; c = c->next) { @@ -522,8 +535,8 @@ static struct mfc_cache *ipmr_cache_find(__be32 origin, __be32 mcastgrp) */ static struct mfc_cache *ipmr_cache_alloc(void) { - struct mfc_cache *c=kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); - if (c==NULL) + struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); + if (c == NULL) return NULL; c->mfc_un.res.minvif = MAXVIFS; return c; @@ -531,8 +544,8 @@ static struct mfc_cache *ipmr_cache_alloc(void) static struct mfc_cache *ipmr_cache_alloc_unres(void) { - struct mfc_cache *c=kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); - if (c==NULL) + struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_ATOMIC); + if (c == NULL) return NULL; skb_queue_head_init(&c->mfc_un.unres.unresolved); c->mfc_un.unres.expires = jiffies + 10*HZ; @@ -552,7 +565,7 @@ static void ipmr_cache_resolve(struct mfc_cache *uc, struct mfc_cache *c) * Play the pending entries through our router */ - while ((skb=__skb_dequeue(&uc->mfc_un.unres.unresolved))) { + while ((skb = __skb_dequeue(&uc->mfc_un.unres.unresolved))) { if (ip_hdr(skb)->version == 0) { struct nlmsghdr *nlh = (struct nlmsghdr *)skb_pull(skb, sizeof(struct iphdr)); @@ -637,7 +650,7 @@ static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert) * Add our header */ - igmp=(struct igmphdr *)skb_put(skb,sizeof(struct igmphdr)); + igmp=(struct igmphdr *)skb_put(skb, sizeof(struct igmphdr)); igmp->type = msg->im_msgtype = assert; igmp->code = 0; @@ -653,7 +666,7 @@ static int ipmr_cache_report(struct sk_buff *pkt, vifi_t vifi, int assert) /* * Deliver to mrouted */ - if ((ret=sock_queue_rcv_skb(mroute_socket,skb))<0) { + if ((ret = sock_queue_rcv_skb(mroute_socket, skb))<0) { if (net_ratelimit()) printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n"); kfree_skb(skb); @@ -685,7 +698,7 @@ ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb) * Create a new entry if allowable */ - if (atomic_read(&cache_resolve_queue_len)>=10 || + if (atomic_read(&cache_resolve_queue_len) >= 10 || (c=ipmr_cache_alloc_unres())==NULL) { spin_unlock_bh(&mfc_unres_lock); @@ -728,7 +741,7 @@ ipmr_cache_unresolved(vifi_t vifi, struct sk_buff *skb) kfree_skb(skb); err = -ENOBUFS; } else { - skb_queue_tail(&c->mfc_un.unres.unresolved,skb); + skb_queue_tail(&c->mfc_un.unres.unresolved, skb); err = 0; } @@ -745,7 +758,7 @@ static int ipmr_mfc_delete(struct mfcctl *mfc) int line; struct mfc_cache *c, **cp; - line=MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); + line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); for (cp=&mfc_cache_array[line]; (c=*cp) != NULL; cp = &c->next) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && @@ -766,7 +779,7 @@ static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock) int line; struct mfc_cache *uc, *c, **cp; - line=MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); + line = MFC_HASH(mfc->mfcc_mcastgrp.s_addr, mfc->mfcc_origin.s_addr); for (cp=&mfc_cache_array[line]; (c=*cp) != NULL; cp = &c->next) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && @@ -787,13 +800,13 @@ static int ipmr_mfc_add(struct mfcctl *mfc, int mrtsock) if (!ipv4_is_multicast(mfc->mfcc_mcastgrp.s_addr)) return -EINVAL; - c=ipmr_cache_alloc(); - if (c==NULL) + c = ipmr_cache_alloc(); + if (c == NULL) return -ENOMEM; - c->mfc_origin=mfc->mfcc_origin.s_addr; - c->mfc_mcastgrp=mfc->mfcc_mcastgrp.s_addr; - c->mfc_parent=mfc->mfcc_parent; + c->mfc_origin = mfc->mfcc_origin.s_addr; + c->mfc_mcastgrp = mfc->mfcc_mcastgrp.s_addr; + c->mfc_parent = mfc->mfcc_parent; ipmr_update_thresholds(c, mfc->mfcc_ttls); if (!mrtsock) c->mfc_flags |= MFC_STATIC; @@ -846,7 +859,7 @@ static void mroute_clean_tables(struct sock *sk) /* * Wipe the cache */ - for (i=0;i<MFC_LINES;i++) { + for (i=0; i<MFC_LINES; i++) { struct mfc_cache *c, **cp; cp = &mfc_cache_array[i]; @@ -887,7 +900,7 @@ static void mrtsock_destruct(struct sock *sk) IPV4_DEVCONF_ALL(sock_net(sk), MC_FORWARDING)--; write_lock_bh(&mrt_lock); - mroute_socket=NULL; + mroute_socket = NULL; write_unlock_bh(&mrt_lock); mroute_clean_tables(sk); @@ -902,7 +915,7 @@ static void mrtsock_destruct(struct sock *sk) * MOSPF/PIM router set up we can clean this up. */ -int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int optlen) +int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, int optlen) { int ret; struct vifctl vif; @@ -918,7 +931,7 @@ int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int opt if (sk->sk_type != SOCK_RAW || inet_sk(sk)->num != IPPROTO_IGMP) return -EOPNOTSUPP; - if (optlen!=sizeof(int)) + if (optlen != sizeof(int)) return -ENOPROTOOPT; rtnl_lock(); @@ -930,7 +943,7 @@ int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int opt ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { write_lock_bh(&mrt_lock); - mroute_socket=sk; + mroute_socket = sk; write_unlock_bh(&mrt_lock); IPV4_DEVCONF_ALL(sock_net(sk), MC_FORWARDING)++; @@ -938,19 +951,19 @@ int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int opt rtnl_unlock(); return ret; case MRT_DONE: - if (sk!=mroute_socket) + if (sk != mroute_socket) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: case MRT_DEL_VIF: - if (optlen!=sizeof(vif)) + if (optlen != sizeof(vif)) return -EINVAL; - if (copy_from_user(&vif,optval,sizeof(vif))) + if (copy_from_user(&vif, optval, sizeof(vif))) return -EFAULT; if (vif.vifc_vifi >= MAXVIFS) return -ENFILE; rtnl_lock(); - if (optname==MRT_ADD_VIF) { + if (optname == MRT_ADD_VIF) { ret = vif_add(&vif, sk==mroute_socket); } else { ret = vif_delete(vif.vifc_vifi, 0); @@ -964,12 +977,12 @@ int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int opt */ case MRT_ADD_MFC: case MRT_DEL_MFC: - if (optlen!=sizeof(mfc)) + if (optlen != sizeof(mfc)) return -EINVAL; - if (copy_from_user(&mfc,optval, sizeof(mfc))) + if (copy_from_user(&mfc, optval, sizeof(mfc))) return -EFAULT; rtnl_lock(); - if (optname==MRT_DEL_MFC) + if (optname == MRT_DEL_MFC) ret = ipmr_mfc_delete(&mfc); else ret = ipmr_mfc_add(&mfc, sk==mroute_socket); @@ -1028,12 +1041,12 @@ int ip_mroute_setsockopt(struct sock *sk,int optname,char __user *optval,int opt * Getsock opt support for the multicast routing system. */ -int ip_mroute_getsockopt(struct sock *sk,int optname,char __user *optval,int __user *optlen) +int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int __user *optlen) { int olr; int val; - if (optname!=MRT_VERSION && + if (optname != MRT_VERSION && #ifdef CONFIG_IP_PIMSM optname!=MRT_PIM && #endif @@ -1047,17 +1060,17 @@ int ip_mroute_getsockopt(struct sock *sk,int optname,char __user *optval,int __u if (olr < 0) return -EINVAL; - if (put_user(olr,optlen)) + if (put_user(olr, optlen)) return -EFAULT; - if (optname==MRT_VERSION) - val=0x0305; + if (optname == MRT_VERSION) + val = 0x0305; #ifdef CONFIG_IP_PIMSM - else if (optname==MRT_PIM) - val=mroute_do_pim; + else if (optname == MRT_PIM) + val = mroute_do_pim; #endif else - val=mroute_do_assert; - if (copy_to_user(optval,&val,olr)) + val = mroute_do_assert; + if (copy_to_user(optval, &val, olr)) return -EFAULT; return 0; } @@ -1075,27 +1088,27 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) switch (cmd) { case SIOCGETVIFCNT: - if (copy_from_user(&vr,arg,sizeof(vr))) + if (copy_from_user(&vr, arg, sizeof(vr))) return -EFAULT; - if (vr.vifi>=maxvif) + if (vr.vifi >= maxvif) return -EINVAL; read_lock(&mrt_lock); vif=&vif_table[vr.vifi]; if (VIF_EXISTS(vr.vifi)) { - vr.icount=vif->pkt_in; - vr.ocount=vif->pkt_out; - vr.ibytes=vif->bytes_in; - vr.obytes=vif->bytes_out; + vr.icount = vif->pkt_in; + vr.ocount = vif->pkt_out; + vr.ibytes = vif->bytes_in; + vr.obytes = vif->bytes_out; read_unlock(&mrt_lock); - if (copy_to_user(arg,&vr,sizeof(vr))) + if (copy_to_user(arg, &vr, sizeof(vr))) return -EFAULT; return 0; } read_unlock(&mrt_lock); return -EADDRNOTAVAIL; case SIOCGETSGCNT: - if (copy_from_user(&sr,arg,sizeof(sr))) + if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; read_lock(&mrt_lock); @@ -1106,7 +1119,7 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) sr.wrong_if = c->mfc_un.res.wrong_if; read_unlock(&mrt_lock); - if (copy_to_user(arg,&sr,sizeof(sr))) + if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } @@ -1130,15 +1143,15 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; v=&vif_table[0]; - for (ct=0;ct<maxvif;ct++,v++) { - if (v->dev==dev) + for (ct=0; ct<maxvif; ct++,v++) { + if (v->dev == dev) vif_delete(ct, 1); } return NOTIFY_DONE; } -static struct notifier_block ip_mr_notifier={ +static struct notifier_block ip_mr_notifier = { .notifier_call = ipmr_device_event, }; @@ -1204,7 +1217,7 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) #ifdef CONFIG_IP_PIMSM if (vif->flags & VIFF_REGISTER) { vif->pkt_out++; - vif->bytes_out+=skb->len; + vif->bytes_out += skb->len; vif->dev->stats.tx_bytes += skb->len; vif->dev->stats.tx_packets++; ipmr_cache_report(skb, vifi, IGMPMSG_WHOLEPKT); @@ -1254,7 +1267,7 @@ static void ipmr_queue_xmit(struct sk_buff *skb, struct mfc_cache *c, int vifi) } vif->pkt_out++; - vif->bytes_out+=skb->len; + vif->bytes_out += skb->len; dst_release(skb->dst); skb->dst = &rt->u.dst; @@ -1352,7 +1365,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local } vif_table[vif].pkt_in++; - vif_table[vif].bytes_in+=skb->len; + vif_table[vif].bytes_in += skb->len; /* * Forward the frame @@ -1364,7 +1377,7 @@ static int ip_mr_forward(struct sk_buff *skb, struct mfc_cache *cache, int local if (skb2) ipmr_queue_xmit(skb2, cache, psend); } - psend=ct; + psend = ct; } } if (psend != -1) { @@ -1428,7 +1441,7 @@ int ip_mr_input(struct sk_buff *skb) /* * No usable cache entry */ - if (cache==NULL) { + if (cache == NULL) { int vif; if (local) { @@ -1469,29 +1482,13 @@ dont_forward: return 0; } -#ifdef CONFIG_IP_PIMSM_V1 -/* - * Handle IGMP messages of PIMv1 - */ - -int pim_rcv_v1(struct sk_buff * skb) +#ifdef CONFIG_IP_PIMSM +static int __pim_rcv(struct sk_buff *skb, unsigned int pimlen) { - struct igmphdr *pim; - struct iphdr *encap; - struct net_device *reg_dev = NULL; - - if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) - goto drop; + struct net_device *reg_dev = NULL; + struct iphdr *encap; - pim = igmp_hdr(skb); - - if (!mroute_do_pim || - skb->len < sizeof(*pim) + sizeof(*encap) || - pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) - goto drop; - - encap = (struct iphdr *)(skb_transport_header(skb) + - sizeof(struct igmphdr)); + encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* Check that: a. packet is really destinted to a multicast group @@ -1500,8 +1497,8 @@ int pim_rcv_v1(struct sk_buff * skb) */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || - ntohs(encap->tot_len) + sizeof(*pim) > skb->len) - goto drop; + ntohs(encap->tot_len) + pimlen > skb->len) + return 1; read_lock(&mrt_lock); if (reg_vif_num >= 0) @@ -1511,7 +1508,7 @@ int pim_rcv_v1(struct sk_buff * skb) read_unlock(&mrt_lock); if (reg_dev == NULL) - goto drop; + return 1; skb->mac_header = skb->network_header; skb_pull(skb, (u8*)encap - skb->data); @@ -1527,9 +1524,33 @@ int pim_rcv_v1(struct sk_buff * skb) nf_reset(skb); netif_rx(skb); dev_put(reg_dev); + return 0; - drop: - kfree_skb(skb); +} +#endif + +#ifdef CONFIG_IP_PIMSM_V1 +/* + * Handle IGMP messages of PIMv1 + */ + +int pim_rcv_v1(struct sk_buff * skb) +{ + struct igmphdr *pim; + + if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) + goto drop; + + pim = igmp_hdr(skb); + + if (!mroute_do_pim || + pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) + goto drop; + + if (__pim_rcv(skb, sizeof(*pim))) { +drop: + kfree_skb(skb); + } return 0; } #endif @@ -1538,10 +1559,8 @@ int pim_rcv_v1(struct sk_buff * skb) static int pim_rcv(struct sk_buff * skb) { struct pimreghdr *pim; - struct iphdr *encap; - struct net_device *reg_dev = NULL; - if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) + if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(struct iphdr))) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); @@ -1551,41 +1570,10 @@ static int pim_rcv(struct sk_buff * skb) csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; - /* check if the inner packet is destined to mcast group */ - encap = (struct iphdr *)(skb_transport_header(skb) + - sizeof(struct pimreghdr)); - if (!ipv4_is_multicast(encap->daddr) || - encap->tot_len == 0 || - ntohs(encap->tot_len) + sizeof(*pim) > skb->len) - goto drop; - - read_lock(&mrt_lock); - if (reg_vif_num >= 0) - reg_dev = vif_table[reg_vif_num].dev; - if (reg_dev) - dev_hold(reg_dev); - read_unlock(&mrt_lock); - - if (reg_dev == NULL) - goto drop; - - skb->mac_header = skb->network_header; - skb_pull(skb, (u8*)encap - skb->data); - skb_reset_network_header(skb); - skb->dev = reg_dev; - skb->protocol = htons(ETH_P_IP); - skb->ip_summed = 0; - skb->pkt_type = PACKET_HOST; - dst_release(skb->dst); - reg_dev->stats.rx_bytes += skb->len; - reg_dev->stats.rx_packets++; - skb->dst = NULL; - nf_reset(skb); - netif_rx(skb); - dev_put(reg_dev); - return 0; - drop: - kfree_skb(skb); + if (__pim_rcv(skb, sizeof(*pim))) { +drop: + kfree_skb(skb); + } return 0; } #endif @@ -1602,13 +1590,13 @@ ipmr_fill_mroute(struct sk_buff *skb, struct mfc_cache *c, struct rtmsg *rtm) if (dev) RTA_PUT(skb, RTA_IIF, 4, &dev->ifindex); - mp_head = (struct rtattr*)skb_put(skb, RTA_LENGTH(0)); + mp_head = (struct rtattr *)skb_put(skb, RTA_LENGTH(0)); for (ct = c->mfc_un.res.minvif; ct < c->mfc_un.res.maxvif; ct++) { if (c->mfc_un.res.ttls[ct] < 255) { if (skb_tailroom(skb) < RTA_ALIGN(RTA_ALIGN(sizeof(*nhp)) + 4)) goto rtattr_failure; - nhp = (struct rtnexthop*)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); + nhp = (struct rtnexthop *)skb_put(skb, RTA_ALIGN(sizeof(*nhp))); nhp->rtnh_flags = 0; nhp->rtnh_hops = c->mfc_un.res.ttls[ct]; nhp->rtnh_ifindex = vif_table[ct].dev->ifindex; @@ -1634,7 +1622,7 @@ int ipmr_get_route(struct sk_buff *skb, struct rtmsg *rtm, int nowait) read_lock(&mrt_lock); cache = ipmr_cache_find(rt->rt_src, rt->rt_dst); - if (cache==NULL) { + if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; @@ -1866,15 +1854,16 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) const struct mfc_cache *mfc = v; const struct ipmr_mfc_iter *it = seq->private; - seq_printf(seq, "%08lX %08lX %-3d %8ld %8ld %8ld", + seq_printf(seq, "%08lX %08lX %-3hd", (unsigned long) mfc->mfc_mcastgrp, (unsigned long) mfc->mfc_origin, - mfc->mfc_parent, - mfc->mfc_un.res.pkt, - mfc->mfc_un.res.bytes, - mfc->mfc_un.res.wrong_if); + mfc->mfc_parent); if (it->cache != &mfc_unres_queue) { + seq_printf(seq, " %8lu %8lu %8lu", + mfc->mfc_un.res.pkt, + mfc->mfc_un.res.bytes, + mfc->mfc_un.res.wrong_if); for (n = mfc->mfc_un.res.minvif; n < mfc->mfc_un.res.maxvif; n++ ) { if (VIF_EXISTS(n) @@ -1883,6 +1872,11 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) " %2d:%-3d", n, mfc->mfc_un.res.ttls[n]); } + } else { + /* unresolved mfc_caches don't contain + * pkt, bytes and wrong_if values + */ + seq_printf(seq, " %8lu %8lu %8lu", 0ul, 0ul, 0ul); } seq_putc(seq, '\n'); } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 6efdb70b3eb2..fdf6811c31a2 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -66,7 +66,7 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) #ifdef CONFIG_XFRM if (!(IPCB(skb)->flags & IPSKB_XFRM_TRANSFORMED) && xfrm_decode_session(skb, &fl, AF_INET) == 0) - if (xfrm_lookup(&skb->dst, &fl, skb->sk, 0)) + if (xfrm_lookup(net, &skb->dst, &fl, skb->sk, 0)) return -1; #endif @@ -97,7 +97,7 @@ int ip_xfrm_me_harder(struct sk_buff *skb) dst = ((struct xfrm_dst *)dst)->route; dst_hold(dst); - if (xfrm_lookup(&dst, &fl, skb->sk, 0) < 0) + if (xfrm_lookup(dev_net(dst->dev), &dst, &fl, skb->sk, 0) < 0) return -1; dst_release(skb->dst); @@ -125,6 +125,7 @@ struct ip_rt_info { __be32 daddr; __be32 saddr; u_int8_t tos; + u_int32_t mark; }; static void nf_ip_saveroute(const struct sk_buff *skb, @@ -138,6 +139,7 @@ static void nf_ip_saveroute(const struct sk_buff *skb, rt_info->tos = iph->tos; rt_info->daddr = iph->daddr; rt_info->saddr = iph->saddr; + rt_info->mark = skb->mark; } } @@ -150,6 +152,7 @@ static int nf_ip_reroute(struct sk_buff *skb, const struct iphdr *iph = ip_hdr(skb); if (!(iph->tos == rt_info->tos + && skb->mark == rt_info->mark && iph->daddr == rt_info->daddr && iph->saddr == rt_info->saddr)) return ip_route_me_harder(skb, RTN_UNSPEC); diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index 8d70d29f1ccf..7ea88b61cb0d 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -142,15 +142,15 @@ static inline int arp_packet_match(const struct arphdr *arphdr, ARPT_INV_TGTIP)) { dprintf("Source or target IP address mismatch.\n"); - dprintf("SRC: %u.%u.%u.%u. Mask: %u.%u.%u.%u. Target: %u.%u.%u.%u.%s\n", - NIPQUAD(src_ipaddr), - NIPQUAD(arpinfo->smsk.s_addr), - NIPQUAD(arpinfo->src.s_addr), + dprintf("SRC: %pI4. Mask: %pI4. Target: %pI4.%s\n", + &src_ipaddr, + &arpinfo->smsk.s_addr, + &arpinfo->src.s_addr, arpinfo->invflags & ARPT_INV_SRCIP ? " (INV)" : ""); - dprintf("TGT: %u.%u.%u.%u Mask: %u.%u.%u.%u Target: %u.%u.%u.%u.%s\n", - NIPQUAD(tgt_ipaddr), - NIPQUAD(arpinfo->tmsk.s_addr), - NIPQUAD(arpinfo->tgt.s_addr), + dprintf("TGT: %pI4 Mask: %pI4 Target: %pI4.%s\n", + &tgt_ipaddr, + &arpinfo->tmsk.s_addr, + &arpinfo->tgt.s_addr, arpinfo->invflags & ARPT_INV_TGTIP ? " (INV)" : ""); return 0; } diff --git a/net/ipv4/netfilter/arptable_filter.c b/net/ipv4/netfilter/arptable_filter.c index bee3d117661a..e091187e864f 100644 --- a/net/ipv4/netfilter/arptable_filter.c +++ b/net/ipv4/netfilter/arptable_filter.c @@ -75,16 +75,6 @@ static unsigned int arpt_out_hook(unsigned int hook, dev_net(out)->ipv4.arptable_filter); } -static unsigned int arpt_forward_hook(unsigned int hook, - struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - int (*okfn)(struct sk_buff *)) -{ - return arpt_do_table(skb, hook, in, out, - dev_net(in)->ipv4.arptable_filter); -} - static struct nf_hook_ops arpt_ops[] __read_mostly = { { .hook = arpt_in_hook, @@ -101,7 +91,7 @@ static struct nf_hook_ops arpt_ops[] __read_mostly = { .priority = NF_IP_PRI_FILTER, }, { - .hook = arpt_forward_hook, + .hook = arpt_in_hook, .owner = THIS_MODULE, .pf = NFPROTO_ARP, .hooknum = NF_ARP_FORWARD, diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 213fb27debc1..ef8b6ca068b2 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -94,15 +94,11 @@ ip_packet_match(const struct iphdr *ip, IPT_INV_DSTIP)) { dprintf("Source or dest mismatch.\n"); - dprintf("SRC: %u.%u.%u.%u. Mask: %u.%u.%u.%u. Target: %u.%u.%u.%u.%s\n", - NIPQUAD(ip->saddr), - NIPQUAD(ipinfo->smsk.s_addr), - NIPQUAD(ipinfo->src.s_addr), + dprintf("SRC: %pI4. Mask: %pI4. Target: %pI4.%s\n", + &ip->saddr, &ipinfo->smsk.s_addr, &ipinfo->src.s_addr, ipinfo->invflags & IPT_INV_SRCIP ? " (INV)" : ""); - dprintf("DST: %u.%u.%u.%u Mask: %u.%u.%u.%u Target: %u.%u.%u.%u.%s\n", - NIPQUAD(ip->daddr), - NIPQUAD(ipinfo->dmsk.s_addr), - NIPQUAD(ipinfo->dst.s_addr), + dprintf("DST: %pI4 Mask: %pI4 Target: %pI4.%s\n", + &ip->daddr, &ipinfo->dmsk.s_addr, &ipinfo->dst.s_addr, ipinfo->invflags & IPT_INV_DSTIP ? " (INV)" : ""); return false; } diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 7ac1677419a9..2e4f98b85524 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -168,7 +168,7 @@ clusterip_config_init(const struct ipt_clusterip_tgt_info *i, __be32 ip, char buffer[16]; /* create proc dir entry */ - sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(ip)); + sprintf(buffer, "%pI4", &ip); c->pde = proc_create_data(buffer, S_IWUSR|S_IRUSR, clusterip_procdir, &clusterip_proc_fops, c); @@ -373,7 +373,7 @@ static bool clusterip_tg_check(const struct xt_tgchk_param *par) config = clusterip_config_find_get(e->ip.dst.s_addr, 1); if (!config) { if (!(cipinfo->flags & CLUSTERIP_FLAG_NEW)) { - printk(KERN_WARNING "CLUSTERIP: no config found for %u.%u.%u.%u, need 'new'\n", NIPQUAD(e->ip.dst.s_addr)); + printk(KERN_WARNING "CLUSTERIP: no config found for %pI4, need 'new'\n", &e->ip.dst.s_addr); return false; } else { struct net_device *dev; @@ -478,9 +478,8 @@ static void arp_print(struct arp_payload *payload) } hbuffer[--k]='\0'; - printk("src %u.%u.%u.%u@%s, dst %u.%u.%u.%u\n", - NIPQUAD(payload->src_ip), hbuffer, - NIPQUAD(payload->dst_ip)); + printk("src %pI4@%s, dst %pI4\n", + &payload->src_ip, hbuffer, &payload->dst_ip); } #endif diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index fc6ce04a3e35..27a78fbbd92b 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -54,8 +54,8 @@ static void dump_packet(const struct nf_loginfo *info, /* Important fields: * TOS, len, DF/MF, fragment offset, TTL, src, dst, options. */ /* Max length: 40 "SRC=255.255.255.255 DST=255.255.255.255 " */ - printk("SRC=%u.%u.%u.%u DST=%u.%u.%u.%u ", - NIPQUAD(ih->saddr), NIPQUAD(ih->daddr)); + printk("SRC=%pI4 DST=%pI4 ", + &ih->saddr, &ih->daddr); /* Max length: 46 "LEN=65535 TOS=0xFF PREC=0xFF TTL=255 ID=65535 " */ printk("LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", @@ -262,8 +262,7 @@ static void dump_packet(const struct nf_loginfo *info, break; case ICMP_REDIRECT: /* Max length: 24 "GATEWAY=255.255.255.255 " */ - printk("GATEWAY=%u.%u.%u.%u ", - NIPQUAD(ich->un.gateway)); + printk("GATEWAY=%pI4 ", &ich->un.gateway); /* Fall through */ case ICMP_DEST_UNREACH: case ICMP_SOURCE_QUENCH: @@ -340,8 +339,8 @@ static void dump_packet(const struct nf_loginfo *info, read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) printk("UID=%u GID=%u ", - skb->sk->sk_socket->file->f_uid, - skb->sk->sk_socket->file->f_gid); + skb->sk->sk_socket->file->f_cred->fsuid, + skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); } diff --git a/net/ipv4/netfilter/ipt_addrtype.c b/net/ipv4/netfilter/ipt_addrtype.c index 88762f02779d..3b216be3bc9f 100644 --- a/net/ipv4/netfilter/ipt_addrtype.c +++ b/net/ipv4/netfilter/ipt_addrtype.c @@ -23,24 +23,25 @@ MODULE_LICENSE("GPL"); MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Xtables: address type match for IPv4"); -static inline bool match_type(const struct net_device *dev, __be32 addr, - u_int16_t mask) +static inline bool match_type(struct net *net, const struct net_device *dev, + __be32 addr, u_int16_t mask) { - return !!(mask & (1 << inet_dev_addr_type(&init_net, dev, addr))); + return !!(mask & (1 << inet_dev_addr_type(net, dev, addr))); } static bool addrtype_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) { + struct net *net = dev_net(par->in ? par->in : par->out); const struct ipt_addrtype_info *info = par->matchinfo; const struct iphdr *iph = ip_hdr(skb); bool ret = true; if (info->source) - ret &= match_type(NULL, iph->saddr, info->source) ^ + ret &= match_type(net, NULL, iph->saddr, info->source) ^ info->invert_source; if (info->dest) - ret &= match_type(NULL, iph->daddr, info->dest) ^ + ret &= match_type(net, NULL, iph->daddr, info->dest) ^ info->invert_dest; return ret; @@ -49,6 +50,7 @@ addrtype_mt_v0(const struct sk_buff *skb, const struct xt_match_param *par) static bool addrtype_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) { + struct net *net = dev_net(par->in ? par->in : par->out); const struct ipt_addrtype_info_v1 *info = par->matchinfo; const struct iphdr *iph = ip_hdr(skb); const struct net_device *dev = NULL; @@ -60,10 +62,10 @@ addrtype_mt_v1(const struct sk_buff *skb, const struct xt_match_param *par) dev = par->out; if (info->source) - ret &= match_type(dev, iph->saddr, info->source) ^ + ret &= match_type(net, dev, iph->saddr, info->source) ^ (info->flags & IPT_ADDRTYPE_INVERT_SOURCE); if (ret && info->dest) - ret &= match_type(dev, iph->daddr, info->dest) ^ + ret &= match_type(net, dev, iph->daddr, info->dest) ^ !!(info->flags & IPT_ADDRTYPE_INVERT_DEST); return ret; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c index 4a7c35275396..b2141e11575e 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4.c @@ -60,9 +60,8 @@ static bool ipv4_invert_tuple(struct nf_conntrack_tuple *tuple, static int ipv4_print_tuple(struct seq_file *s, const struct nf_conntrack_tuple *tuple) { - return seq_printf(s, "src=%u.%u.%u.%u dst=%u.%u.%u.%u ", - NIPQUAD(tuple->src.u3.ip), - NIPQUAD(tuple->dst.u3.ip)); + return seq_printf(s, "src=%pI4 dst=%pI4 ", + &tuple->src.u3.ip, &tuple->dst.u3.ip); } static int ipv4_get_l4proto(const struct sk_buff *skb, unsigned int nhoff, @@ -198,7 +197,7 @@ static ctl_table ip_ct_sysctl_table[] = { .data = &nf_conntrack_max, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_NF_CONNTRACK_COUNT, @@ -206,7 +205,7 @@ static ctl_table ip_ct_sysctl_table[] = { .data = &init_net.ct.count, .maxlen = sizeof(int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_NF_CONNTRACK_BUCKETS, @@ -214,7 +213,7 @@ static ctl_table ip_ct_sysctl_table[] = { .data = &nf_conntrack_htable_size, .maxlen = sizeof(unsigned int), .mode = 0444, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_NF_CONNTRACK_CHECKSUM, @@ -222,7 +221,7 @@ static ctl_table ip_ct_sysctl_table[] = { .data = &init_net.ct.sysctl_checksum, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_NF_CONNTRACK_LOG_INVALID, @@ -230,8 +229,8 @@ static ctl_table ip_ct_sysctl_table[] = { .data = &init_net.ct.sysctl_log_invalid, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, + .strategy = sysctl_intvec, .extra1 = &log_invalid_proto_min, .extra2 = &log_invalid_proto_max, }, @@ -284,17 +283,17 @@ getorigdst(struct sock *sk, int optval, void __user *user, int *len) .tuple.dst.u3.ip; memset(sin.sin_zero, 0, sizeof(sin.sin_zero)); - pr_debug("SO_ORIGINAL_DST: %u.%u.%u.%u %u\n", - NIPQUAD(sin.sin_addr.s_addr), ntohs(sin.sin_port)); + pr_debug("SO_ORIGINAL_DST: %pI4 %u\n", + &sin.sin_addr.s_addr, ntohs(sin.sin_port)); nf_ct_put(ct); if (copy_to_user(user, &sin, sizeof(sin)) != 0) return -EFAULT; else return 0; } - pr_debug("SO_ORIGINAL_DST: Can't find %u.%u.%u.%u/%u-%u.%u.%u.%u/%u.\n", - NIPQUAD(tuple.src.u3.ip), ntohs(tuple.src.u.tcp.port), - NIPQUAD(tuple.dst.u3.ip), ntohs(tuple.dst.u.tcp.port)); + pr_debug("SO_ORIGINAL_DST: Can't find %pI4/%u-%pI4/%u.\n", + &tuple.src.u3.ip, ntohs(tuple.src.u.tcp.port), + &tuple.dst.u3.ip, ntohs(tuple.dst.u.tcp.port)); return -ENOENT; } diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 313ebf00ee36..6ba5c557690c 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -291,7 +291,7 @@ static void *ct_cpu_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) return SEQ_START_TOKEN; - for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) { + for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -306,7 +306,7 @@ static void *ct_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) struct net *net = seq_file_net(seq); int cpu; - for (cpu = *pos; cpu < NR_CPUS; ++cpu) { + for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; diff --git a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c index 4e8879220222..1fd3ef7718b6 100644 --- a/net/ipv4/netfilter/nf_conntrack_proto_icmp.c +++ b/net/ipv4/netfilter/nf_conntrack_proto_icmp.c @@ -272,7 +272,7 @@ static struct ctl_table icmp_sysctl_table[] = { .data = &nf_ct_icmp_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { .ctl_name = 0 @@ -285,7 +285,7 @@ static struct ctl_table icmp_compat_sysctl_table[] = { .data = &nf_ct_icmp_timeout, .maxlen = sizeof(unsigned int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, + .proc_handler = proc_dointvec_jiffies, }, { .ctl_name = 0 diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index ee47bf28c825..7e8e6fc75413 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -119,10 +119,9 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, (ntohl(addr.ip) & 0xff000000) == 0x7f000000) i = 0; - pr_debug("nf_nat_ras: set signal address " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(addr.ip), port, - NIPQUAD(ct->tuplehash[!dir].tuple.dst.u3.ip), + pr_debug("nf_nat_ras: set signal address %pI4:%hu->%pI4:%hu\n", + &addr.ip, port, + &ct->tuplehash[!dir].tuple.dst.u3.ip, info->sig_port[!dir]); return set_h225_addr(skb, data, 0, &taddr[i], &ct->tuplehash[!dir]. @@ -131,10 +130,9 @@ static int set_sig_addr(struct sk_buff *skb, struct nf_conn *ct, } else if (addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip && port == info->sig_port[dir]) { /* GK->GW */ - pr_debug("nf_nat_ras: set signal address " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(addr.ip), port, - NIPQUAD(ct->tuplehash[!dir].tuple.src.u3.ip), + pr_debug("nf_nat_ras: set signal address %pI4:%hu->%pI4:%hu\n", + &addr.ip, port, + &ct->tuplehash[!dir].tuple.src.u3.ip, info->sig_port[!dir]); return set_h225_addr(skb, data, 0, &taddr[i], &ct->tuplehash[!dir]. @@ -162,10 +160,9 @@ static int set_ras_addr(struct sk_buff *skb, struct nf_conn *ct, if (get_h225_addr(ct, *data, &taddr[i], &addr, &port) && addr.ip == ct->tuplehash[dir].tuple.src.u3.ip && port == ct->tuplehash[dir].tuple.src.u.udp.port) { - pr_debug("nf_nat_ras: set rasAddress " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(addr.ip), ntohs(port), - NIPQUAD(ct->tuplehash[!dir].tuple.dst.u3.ip), + pr_debug("nf_nat_ras: set rasAddress %pI4:%hu->%pI4:%hu\n", + &addr.ip, ntohs(port), + &ct->tuplehash[!dir].tuple.dst.u3.ip, ntohs(ct->tuplehash[!dir].tuple.dst.u.udp.port)); return set_h225_addr(skb, data, 0, &taddr[i], &ct->tuplehash[!dir].tuple.dst.u3, @@ -257,15 +254,15 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, } /* Success */ - pr_debug("nf_nat_h323: expect RTP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(rtp_exp->tuple.src.u3.ip), + pr_debug("nf_nat_h323: expect RTP %pI4:%hu->%pI4:%hu\n", + &rtp_exp->tuple.src.u3.ip, ntohs(rtp_exp->tuple.src.u.udp.port), - NIPQUAD(rtp_exp->tuple.dst.u3.ip), + &rtp_exp->tuple.dst.u3.ip, ntohs(rtp_exp->tuple.dst.u.udp.port)); - pr_debug("nf_nat_h323: expect RTCP %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(rtcp_exp->tuple.src.u3.ip), + pr_debug("nf_nat_h323: expect RTCP %pI4:%hu->%pI4:%hu\n", + &rtcp_exp->tuple.src.u3.ip, ntohs(rtcp_exp->tuple.src.u.udp.port), - NIPQUAD(rtcp_exp->tuple.dst.u3.ip), + &rtcp_exp->tuple.dst.u3.ip, ntohs(rtcp_exp->tuple.dst.u.udp.port)); return 0; @@ -307,10 +304,10 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, return -1; } - pr_debug("nf_nat_h323: expect T.120 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.u3.ip), + pr_debug("nf_nat_h323: expect T.120 %pI4:%hu->%pI4:%hu\n", + &exp->tuple.src.u3.ip, ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.u3.ip), + &exp->tuple.dst.u3.ip, ntohs(exp->tuple.dst.u.tcp.port)); return 0; @@ -361,10 +358,10 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, return -1; } - pr_debug("nf_nat_q931: expect H.245 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.u3.ip), + pr_debug("nf_nat_q931: expect H.245 %pI4:%hu->%pI4:%hu\n", + &exp->tuple.src.u3.ip, ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.u3.ip), + &exp->tuple.dst.u3.ip, ntohs(exp->tuple.dst.u.tcp.port)); return 0; @@ -455,10 +452,10 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, } /* Success */ - pr_debug("nf_nat_ras: expect Q.931 %u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.u3.ip), + pr_debug("nf_nat_ras: expect Q.931 %pI4:%hu->%pI4:%hu\n", + &exp->tuple.src.u3.ip, ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.u3.ip), + &exp->tuple.dst.u3.ip, ntohs(exp->tuple.dst.u.tcp.port)); return 0; @@ -524,11 +521,10 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, } /* Success */ - pr_debug("nf_nat_q931: expect Call Forwarding " - "%u.%u.%u.%u:%hu->%u.%u.%u.%u:%hu\n", - NIPQUAD(exp->tuple.src.u3.ip), + pr_debug("nf_nat_q931: expect Call Forwarding %pI4:%hu->%pI4:%hu\n", + &exp->tuple.src.u3.ip, ntohs(exp->tuple.src.u.tcp.port), - NIPQUAD(exp->tuple.dst.u3.ip), + &exp->tuple.dst.u3.ip, ntohs(exp->tuple.dst.u.tcp.port)); return 0; diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index fe6f9cef6c85..ea83a886b03e 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -55,8 +55,8 @@ static unsigned int help(struct sk_buff *skb, ip = ntohl(exp->master->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip); sprintf(buffer, "%u %u", ip, port); - pr_debug("nf_nat_irc: inserting '%s' == %u.%u.%u.%u, port %u\n", - buffer, NIPQUAD(ip), port); + pr_debug("nf_nat_irc: inserting '%s' == %pI4, port %u\n", + buffer, &ip, port); ret = nf_nat_mangle_tcp_packet(skb, exp->master, ctinfo, matchoff, matchlen, buffer, diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index bea54a685109..a7eb04719044 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -61,7 +61,7 @@ static struct static struct xt_table nat_table = { .name = "nat", .valid_hooks = NAT_VALID_HOOKS, - .lock = __RW_LOCK_UNLOCKED(__nat_table.lock), + .lock = __RW_LOCK_UNLOCKED(nat_table.lock), .me = THIS_MODULE, .af = AF_INET, }; @@ -86,25 +86,6 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_target_param *par) return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC); } -/* Before 2.6.11 we did implicit source NAT if required. Warn about change. */ -static void warn_if_extra_mangle(struct net *net, __be32 dstip, __be32 srcip) -{ - static int warned = 0; - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = dstip } } }; - struct rtable *rt; - - if (ip_route_output_key(net, &rt, &fl) != 0) - return; - - if (rt->rt_src != srcip && !warned) { - printk("NAT: no longer support implicit source local NAT\n"); - printk("NAT: packet src %u.%u.%u.%u -> dst %u.%u.%u.%u\n", - NIPQUAD(srcip), NIPQUAD(dstip)); - warned = 1; - } - ip_rt_put(rt); -} - static unsigned int ipt_dnat_target(struct sk_buff *skb, const struct xt_target_param *par) { @@ -120,11 +101,6 @@ ipt_dnat_target(struct sk_buff *skb, const struct xt_target_param *par) /* Connection must be valid and new. */ NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); - if (par->hooknum == NF_INET_LOCAL_OUT && - mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) - warn_if_extra_mangle(dev_net(par->out), ip_hdr(skb)->daddr, - mr->range[0].min_ip); - return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_DST); } @@ -166,8 +142,7 @@ alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) struct nf_nat_range range = { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } }; - pr_debug("Allocating NULL binding for %p (%u.%u.%u.%u)\n", - ct, NIPQUAD(ip)); + pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, &ip); return nf_nat_setup_info(ct, &range, HOOK2MANIP(hooknum)); } diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 14544320c545..07d61a57613c 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -74,8 +74,7 @@ static int map_addr(struct sk_buff *skb, if (newaddr == addr->ip && newport == port) return 1; - buflen = sprintf(buffer, "%u.%u.%u.%u:%u", - NIPQUAD(newaddr), ntohs(newport)); + buflen = sprintf(buffer, "%pI4:%u", &newaddr, ntohs(newport)); return mangle_packet(skb, dptr, datalen, matchoff, matchlen, buffer, buflen); @@ -152,8 +151,8 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, &addr) > 0 && addr.ip == ct->tuplehash[dir].tuple.src.u3.ip && addr.ip != ct->tuplehash[!dir].tuple.dst.u3.ip) { - __be32 ip = ct->tuplehash[!dir].tuple.dst.u3.ip; - buflen = sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(ip)); + buflen = sprintf(buffer, "%pI4", + &ct->tuplehash[!dir].tuple.dst.u3.ip); if (!mangle_packet(skb, dptr, datalen, poff, plen, buffer, buflen)) return NF_DROP; @@ -166,8 +165,8 @@ static unsigned int ip_nat_sip(struct sk_buff *skb, &addr) > 0 && addr.ip == ct->tuplehash[dir].tuple.dst.u3.ip && addr.ip != ct->tuplehash[!dir].tuple.src.u3.ip) { - __be32 ip = ct->tuplehash[!dir].tuple.src.u3.ip; - buflen = sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(ip)); + buflen = sprintf(buffer, "%pI4", + &ct->tuplehash[!dir].tuple.src.u3.ip); if (!mangle_packet(skb, dptr, datalen, poff, plen, buffer, buflen)) return NF_DROP; @@ -279,8 +278,7 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, if (exp->tuple.dst.u3.ip != exp->saved_ip || exp->tuple.dst.u.udp.port != exp->saved_proto.udp.port) { - buflen = sprintf(buffer, "%u.%u.%u.%u:%u", - NIPQUAD(newip), port); + buflen = sprintf(buffer, "%pI4:%u", &newip, port); if (!mangle_packet(skb, dptr, datalen, matchoff, matchlen, buffer, buflen)) goto err; @@ -345,7 +343,7 @@ static unsigned int ip_nat_sdp_addr(struct sk_buff *skb, const char **dptr, char buffer[sizeof("nnn.nnn.nnn.nnn")]; unsigned int buflen; - buflen = sprintf(buffer, NIPQUAD_FMT, NIPQUAD(addr->ip)); + buflen = sprintf(buffer, "%pI4", &addr->ip); if (mangle_sdp_packet(skb, dptr, dataoff, datalen, type, term, buffer, buflen)) return 0; @@ -380,7 +378,7 @@ static unsigned int ip_nat_sdp_session(struct sk_buff *skb, const char **dptr, unsigned int buflen; /* Mangle session description owner and contact addresses */ - buflen = sprintf(buffer, "%u.%u.%u.%u", NIPQUAD(addr->ip)); + buflen = sprintf(buffer, "%pI4", &addr->ip); if (mangle_sdp_packet(skb, dptr, dataoff, datalen, SDP_HDR_OWNER_IP4, SDP_HDR_MEDIA, buffer, buflen)) diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 8303e4b406c0..182f845de92f 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -930,8 +930,8 @@ static inline void mangle_address(unsigned char *begin, } if (debug) - printk(KERN_DEBUG "bsalg: mapped %u.%u.%u.%u to " - "%u.%u.%u.%u\n", NIPQUAD(old), NIPQUAD(*addr)); + printk(KERN_DEBUG "bsalg: mapped %pI4 to %pI4\n", + &old, addr); } } @@ -1267,9 +1267,8 @@ static int help(struct sk_buff *skb, unsigned int protoff, */ if (ntohs(udph->len) != skb->len - (iph->ihl << 2)) { if (net_ratelimit()) - printk(KERN_WARNING "SNMP: dropping malformed packet " - "src=%u.%u.%u.%u dst=%u.%u.%u.%u\n", - NIPQUAD(iph->saddr), NIPQUAD(iph->daddr)); + printk(KERN_WARNING "SNMP: dropping malformed packet src=%pI4 dst=%pI4\n", + &iph->saddr, &iph->daddr); return NF_DROP; } diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a631a1f110ca..eb62e58bff79 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -38,6 +38,7 @@ #include <net/tcp.h> #include <net/udp.h> #include <net/udplite.h> +#include <linux/bottom_half.h> #include <linux/inetdevice.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> @@ -50,12 +51,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) { struct net *net = seq->private; + int orphans, sockets; + + local_bh_disable(); + orphans = percpu_counter_sum_positive(&tcp_orphan_count), + sockets = percpu_counter_sum_positive(&tcp_sockets_allocated), + local_bh_enable(); socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", - sock_prot_inuse_get(net, &tcp_prot), - atomic_read(&tcp_orphan_count), - tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated), + 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", sock_prot_inuse_get(net, &udp_prot), @@ -234,6 +240,9 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPSpuriousRTOs", LINUX_MIB_TCPSPURIOUSRTOS), SNMP_MIB_ITEM("TCPMD5NotFound", LINUX_MIB_TCPMD5NOTFOUND), SNMP_MIB_ITEM("TCPMD5Unexpected", LINUX_MIB_TCPMD5UNEXPECTED), + SNMP_MIB_ITEM("TCPSackShifted", LINUX_MIB_SACKSHIFTED), + SNMP_MIB_ITEM("TCPSackMerged", LINUX_MIB_SACKMERGED), + SNMP_MIB_ITEM("TCPSackShiftFallback", LINUX_MIB_SACKSHIFTFALLBACK), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index cd975743bcd2..dff8bc4e0fac 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -247,7 +247,7 @@ static void raw_err(struct sock *sk, struct sk_buff *skb, u32 info) } if (inet->recverr) { - struct iphdr *iph = (struct iphdr*)skb->data; + struct iphdr *iph = (struct iphdr *)skb->data; u8 *payload = skb->data + (iph->ihl << 2); if (inet->hdrincl) @@ -465,7 +465,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, */ if (msg->msg_namelen) { - struct sockaddr_in *usin = (struct sockaddr_in*)msg->msg_name; + struct sockaddr_in *usin = (struct sockaddr_in *)msg->msg_name; err = -EINVAL; if (msg->msg_namelen < sizeof(*usin)) goto out; @@ -572,7 +572,7 @@ back_from_confirm: ipc.addr = rt->rt_dst; lock_sock(sk); err = ip_append_data(sk, ip_generic_getfrag, msg->msg_iov, len, 0, - &ipc, rt, msg->msg_flags); + &ipc, &rt, msg->msg_flags); if (err) ip_flush_pending_frames(sk); else if (!(msg->msg_flags & MSG_MORE)) @@ -851,7 +851,7 @@ struct proto raw_prot = { static struct sock *raw_get_first(struct seq_file *seq) { struct sock *sk; - struct raw_iter_state* state = raw_seq_private(seq); + struct raw_iter_state *state = raw_seq_private(seq); for (state->bucket = 0; state->bucket < RAW_HTABLE_SIZE; ++state->bucket) { @@ -868,7 +868,7 @@ found: static struct sock *raw_get_next(struct seq_file *seq, struct sock *sk) { - struct raw_iter_state* state = raw_seq_private(seq); + struct raw_iter_state *state = raw_seq_private(seq); do { sk = sk_next(sk); diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 2ea6dcc3e2cc..97f71153584f 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -129,6 +129,7 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int ip_rt_secret_interval __read_mostly = 10 * 60 * HZ; +static int rt_chain_length_max __read_mostly = 20; static void rt_worker_func(struct work_struct *work); static DECLARE_DELAYED_WORK(expires_work, rt_worker_func); @@ -145,6 +146,7 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu); static int rt_garbage_collect(struct dst_ops *ops); +static void rt_emergency_hash_rebuild(struct net *net); static struct dst_ops ipv4_dst_ops = { @@ -158,7 +160,6 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .local_out = __ip_local_out, - .entry_size = sizeof(struct rtable), .entries = ATOMIC_INIT(0), }; @@ -201,6 +202,7 @@ const __u8 ip_tos2prio[16] = { struct rt_hash_bucket { struct rtable *chain; }; + #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \ defined(CONFIG_PROVE_LOCKING) /* @@ -427,7 +429,7 @@ static void *rt_cpu_seq_start(struct seq_file *seq, loff_t *pos) if (*pos == 0) return SEQ_START_TOKEN; - for (cpu = *pos-1; cpu < NR_CPUS; ++cpu) { + for (cpu = *pos-1; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -440,7 +442,7 @@ static void *rt_cpu_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int cpu; - for (cpu = *pos; cpu < NR_CPUS; ++cpu) { + for (cpu = *pos; cpu < nr_cpu_ids; ++cpu) { if (!cpu_possible(cpu)) continue; *pos = cpu+1; @@ -674,6 +676,20 @@ static inline u32 rt_score(struct rtable *rt) return score; } +static inline bool rt_caching(const struct net *net) +{ + return net->ipv4.current_rt_cache_rebuild_count <= + net->ipv4.sysctl_rt_cache_rebuild_count; +} + +static inline bool compare_hash_inputs(const struct flowi *fl1, + const struct flowi *fl2) +{ + return (__force u32)(((fl1->nl_u.ip4_u.daddr ^ fl2->nl_u.ip4_u.daddr) | + (fl1->nl_u.ip4_u.saddr ^ fl2->nl_u.ip4_u.saddr) | + (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 ^ fl2->nl_u.ip4_u.daddr) | @@ -753,11 +769,24 @@ static void rt_do_flush(int process_context) } } +/* + * While freeing expired entries, we compute average chain length + * and standard deviation, using fixed-point arithmetic. + * This to have an estimation of rt_chain_length_max + * rt_chain_length_max = max(elasticity, AVG + 4*SD) + * We use 3 bits for frational part, and 29 (or 61) for magnitude. + */ + +#define FRACT_BITS 3 +#define ONE (1UL << FRACT_BITS) + static void rt_check_expire(void) { static unsigned int rover; unsigned int i = rover, goal; struct rtable *rth, **rthp; + unsigned long length = 0, samples = 0; + unsigned long sum = 0, sum2 = 0; u64 mult; mult = ((u64)ip_rt_gc_interval) << rt_hash_log; @@ -766,6 +795,7 @@ static void rt_check_expire(void) goal = (unsigned int)mult; if (goal > rt_hash_mask) goal = rt_hash_mask + 1; + length = 0; for (; goal > 0; goal--) { unsigned long tmo = ip_rt_gc_timeout; @@ -775,6 +805,8 @@ static void rt_check_expire(void) if (need_resched()) cond_resched(); + samples++; + if (*rthp == NULL) continue; spin_lock_bh(rt_hash_lock_addr(i)); @@ -789,11 +821,29 @@ static void rt_check_expire(void) if (time_before_eq(jiffies, rth->u.dst.expires)) { tmo >>= 1; rthp = &rth->u.dst.rt_next; + /* + * Only bump our length if the hash + * inputs on entries n and n+1 are not + * the same, we only count entries on + * a chain with equal hash inputs once + * so that entries for different QOS + * levels, and other non-hash input + * attributes don't unfairly skew + * the length computation + */ + if ((*rthp == NULL) || + !compare_hash_inputs(&(*rthp)->fl, + &rth->fl)) + length += ONE; continue; } } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) { tmo >>= 1; rthp = &rth->u.dst.rt_next; + if ((*rthp == NULL) || + !compare_hash_inputs(&(*rthp)->fl, + &rth->fl)) + length += ONE; continue; } @@ -802,6 +852,15 @@ static void rt_check_expire(void) rt_free(rth); } spin_unlock_bh(rt_hash_lock_addr(i)); + sum += length; + sum2 += length*length; + } + if (samples) { + unsigned long avg = sum / samples; + unsigned long sd = int_sqrt(sum2 / samples - avg*avg); + rt_chain_length_max = max_t(unsigned long, + ip_rt_gc_elasticity, + (avg + 4*sd) >> FRACT_BITS); } rover = i; } @@ -851,6 +910,26 @@ static void rt_secret_rebuild(unsigned long __net) mod_timer(&net->ipv4.rt_secret_timer, jiffies + ip_rt_secret_interval); } +static void rt_secret_rebuild_oneshot(struct net *net) +{ + del_timer_sync(&net->ipv4.rt_secret_timer); + rt_cache_invalidate(net); + if (ip_rt_secret_interval) { + net->ipv4.rt_secret_timer.expires += ip_rt_secret_interval; + add_timer(&net->ipv4.rt_secret_timer); + } +} + +static void rt_emergency_hash_rebuild(struct net *net) +{ + if (net_ratelimit()) { + printk(KERN_WARNING "Route hash chain too long!\n"); + printk(KERN_WARNING "Adjust your secret_interval!\n"); + } + + rt_secret_rebuild_oneshot(net); +} + /* Short description of GC goals. @@ -989,6 +1068,7 @@ out: return 0; static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp) { struct rtable *rth, **rthp; + struct rtable *rthi; unsigned long now; struct rtable *cand, **candp; u32 min_score; @@ -1002,7 +1082,13 @@ restart: candp = NULL; now = jiffies; + if (!rt_caching(dev_net(rt->u.dst.dev))) { + rt_drop(rt); + return 0; + } + rthp = &rt_hash_table[hash].chain; + rthi = NULL; spin_lock_bh(rt_hash_lock_addr(hash)); while ((rth = *rthp) != NULL) { @@ -1048,6 +1134,17 @@ restart: chain_length++; rthp = &rth->u.dst.rt_next; + + /* + * check to see if the next entry in the chain + * contains the same hash input values as rt. If it does + * This is where we will insert into the list, instead of + * at the head. This groups entries that differ by aspects not + * relvant to the hash function together, which we use to adjust + * our chain length + */ + if (*rthp && compare_hash_inputs(&(*rthp)->fl, &rt->fl)) + rthi = rth; } if (cand) { @@ -1061,6 +1158,16 @@ restart: *candp = cand->u.dst.rt_next; rt_free(cand); } + } else { + if (chain_length > rt_chain_length_max) { + struct net *net = dev_net(rt->u.dst.dev); + int num = ++net->ipv4.current_rt_cache_rebuild_count; + if (!rt_caching(dev_net(rt->u.dst.dev))) { + printk(KERN_WARNING "%s: %d rebuilds is over limit, route caching disabled\n", + rt->u.dst.dev->name, num); + } + rt_emergency_hash_rebuild(dev_net(rt->u.dst.dev)); + } } /* Try to bind route to arp only if it is output @@ -1098,14 +1205,17 @@ restart: } } - rt->u.dst.rt_next = rt_hash_table[hash].chain; + if (rthi) + rt->u.dst.rt_next = rthi->u.dst.rt_next; + else + rt->u.dst.rt_next = rt_hash_table[hash].chain; + #if RT_CACHE_DEBUG >= 2 if (rt->u.dst.rt_next) { struct rtable *trt; - printk(KERN_DEBUG "rt_cache @%02x: " NIPQUAD_FMT, hash, - NIPQUAD(rt->rt_dst)); + printk(KERN_DEBUG "rt_cache @%02x: %pI4", hash, &rt->rt_dst); for (trt = rt->u.dst.rt_next; trt; trt = trt->u.dst.rt_next) - printk(" . " NIPQUAD_FMT, NIPQUAD(trt->rt_dst)); + printk(" . %pI4", &trt->rt_dst); printk("\n"); } #endif @@ -1114,7 +1224,11 @@ restart: * previous writes to rt are comitted to memory * before making rt visible to other CPUS. */ - rcu_assign_pointer(rt_hash_table[hash].chain, rt); + if (rthi) + rcu_assign_pointer(rthi->u.dst.rt_next, rt); + else + rcu_assign_pointer(rt_hash_table[hash].chain, rt); + spin_unlock_bh(rt_hash_lock_addr(hash)); *rp = rt; return 0; @@ -1217,6 +1331,9 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, || ipv4_is_zeronet(new_gw)) goto reject_redirect; + if (!rt_caching(net)) + goto reject_redirect; + if (!IN_DEV_SHARED_MEDIA(in_dev)) { if (!inet_addr_onlink(in_dev, new_gw, old_gw)) goto reject_redirect; @@ -1267,7 +1384,6 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, /* Copy all the information. */ *rt = *rth; - INIT_RCU_HEAD(&rt->u.dst.rcu_head); rt->u.dst.__use = 1; atomic_set(&rt->u.dst.__refcnt, 1); rt->u.dst.child = NULL; @@ -1280,7 +1396,9 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, rt->u.dst.path = &rt->u.dst; rt->u.dst.neighbour = NULL; rt->u.dst.hh = NULL; +#ifdef CONFIG_XFRM rt->u.dst.xfrm = NULL; +#endif rt->rt_genid = rt_genid(net); rt->rt_flags |= RTCF_REDIRECTED; @@ -1324,11 +1442,10 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, reject_redirect: #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - printk(KERN_INFO "Redirect from " NIPQUAD_FMT " on %s about " - NIPQUAD_FMT " ignored.\n" - " Advised path = " NIPQUAD_FMT " -> " NIPQUAD_FMT "\n", - NIPQUAD(old_gw), dev->name, NIPQUAD(new_gw), - NIPQUAD(saddr), NIPQUAD(daddr)); + printk(KERN_INFO "Redirect from %pI4 on %s about %pI4 ignored.\n" + " Advised path = %pI4 -> %pI4\n", + &old_gw, dev->name, &new_gw, + &saddr, &daddr); #endif in_dev_put(in_dev); } @@ -1348,9 +1465,8 @@ static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst) rt->fl.oif, rt_genid(dev_net(dst->dev))); #if RT_CACHE_DEBUG >= 1 - printk(KERN_DEBUG "ipv4_negative_advice: redirect to " - NIPQUAD_FMT "/%02x dropped\n", - NIPQUAD(rt->rt_dst), rt->fl.fl4_tos); + printk(KERN_DEBUG "ipv4_negative_advice: redirect to %pI4/%02x dropped\n", + &rt->rt_dst, rt->fl.fl4_tos); #endif rt_del(hash, rt); ret = NULL; @@ -1414,10 +1530,9 @@ void ip_rt_send_redirect(struct sk_buff *skb) if (IN_DEV_LOG_MARTIANS(in_dev) && rt->u.dst.rate_tokens == ip_rt_redirect_number && net_ratelimit()) - printk(KERN_WARNING "host " NIPQUAD_FMT "/if%d ignores " - "redirects for " NIPQUAD_FMT " to " NIPQUAD_FMT ".\n", - NIPQUAD(rt->rt_src), rt->rt_iif, - NIPQUAD(rt->rt_dst), NIPQUAD(rt->rt_gateway)); + printk(KERN_WARNING "host %pI4/if%d ignores redirects for %pI4 to %pI4.\n", + &rt->rt_src, rt->rt_iif, + &rt->rt_dst, &rt->rt_gateway); #endif } out: @@ -1610,8 +1725,8 @@ static void ipv4_link_failure(struct sk_buff *skb) static int ip_rt_bug(struct sk_buff *skb) { - printk(KERN_DEBUG "ip_rt_bug: " NIPQUAD_FMT " -> " NIPQUAD_FMT ", %s\n", - NIPQUAD(ip_hdr(skb)->saddr), NIPQUAD(ip_hdr(skb)->daddr), + printk(KERN_DEBUG "ip_rt_bug: %pI4 -> %pI4, %s\n", + &ip_hdr(skb)->saddr, &ip_hdr(skb)->daddr, skb->dev ? skb->dev->name : "?"); kfree_skb(skb); return 0; @@ -1788,9 +1903,8 @@ static void ip_handle_martian_source(struct net_device *dev, * RFC1812 recommendation, if source is martian, * the only hint is MAC header. */ - printk(KERN_WARNING "martian source " NIPQUAD_FMT " from " - NIPQUAD_FMT", on dev %s\n", - NIPQUAD(daddr), NIPQUAD(saddr), dev->name); + printk(KERN_WARNING "martian source %pI4 from %pI4, on dev %s\n", + &daddr, &saddr, dev->name); if (dev->hard_header_len && skb_mac_header_was_set(skb)) { int i; const unsigned char *p = skb_mac_header(skb); @@ -2099,9 +2213,8 @@ martian_destination: RT_CACHE_STAT_INC(in_martian_dst); #ifdef CONFIG_IP_ROUTE_VERBOSE if (IN_DEV_LOG_MARTIANS(in_dev) && net_ratelimit()) - printk(KERN_WARNING "martian destination " NIPQUAD_FMT " from " - NIPQUAD_FMT ", dev %s\n", - NIPQUAD(daddr), NIPQUAD(saddr), dev->name); + printk(KERN_WARNING "martian destination %pI4 from %pI4, dev %s\n", + &daddr, &saddr, dev->name); #endif e_hostunreach: @@ -2130,6 +2243,10 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, struct net *net; net = dev_net(dev); + + if (!rt_caching(net)) + goto skip_cache; + tos &= IPTOS_RT_MASK; hash = rt_hash(daddr, saddr, iif, rt_genid(net)); @@ -2154,6 +2271,7 @@ int ip_route_input(struct sk_buff *skb, __be32 daddr, __be32 saddr, } rcu_read_unlock(); +skip_cache: /* Multicast recognition logic is moved from route cache to here. The problem was that too many Ethernet cards have broken/missing hardware multicast filters :-( As result the host on multicasting @@ -2539,6 +2657,9 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, unsigned hash; struct rtable *rth; + if (!rt_caching(net)) + goto slow_output; + hash = rt_hash(flp->fl4_dst, flp->fl4_src, flp->oif, rt_genid(net)); rcu_read_lock_bh(); @@ -2563,6 +2684,7 @@ int __ip_route_output_key(struct net *net, struct rtable **rp, } rcu_read_unlock_bh(); +slow_output: return ip_route_output_slow(net, rp, flp); } @@ -2578,7 +2700,6 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .destroy = ipv4_dst_destroy, .check = ipv4_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, - .entry_size = sizeof(struct rtable), .entries = ATOMIC_INIT(0), }; @@ -2640,7 +2761,7 @@ int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp, flp->fl4_src = (*rp)->rt_src; if (!flp->fl4_dst) flp->fl4_dst = (*rp)->rt_dst; - err = __xfrm_lookup((struct dst_entry **)rp, flp, sk, + err = __xfrm_lookup(net, (struct dst_entry **)rp, flp, sk, flags ? XFRM_LOOKUP_WAIT : 0); if (err == -EREMOTE) err = ipv4_dst_blackhole(net, rp, flp); @@ -2995,7 +3116,7 @@ static ctl_table ipv4_route_table[] = { .data = &ipv4_dst_ops.gc_thresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_MAX_SIZE, @@ -3003,7 +3124,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_max_size, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { /* Deprecated. Use gc_min_interval_ms */ @@ -3013,8 +3134,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV4_ROUTE_GC_MIN_INTERVAL_MS, @@ -3022,8 +3143,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_gc_min_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies, + .proc_handler = proc_dointvec_ms_jiffies, + .strategy = sysctl_ms_jiffies, }, { .ctl_name = NET_IPV4_ROUTE_GC_TIMEOUT, @@ -3031,8 +3152,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_gc_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV4_ROUTE_GC_INTERVAL, @@ -3040,8 +3161,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_gc_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV4_ROUTE_REDIRECT_LOAD, @@ -3049,7 +3170,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_redirect_load, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_REDIRECT_NUMBER, @@ -3057,7 +3178,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_redirect_number, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_REDIRECT_SILENCE, @@ -3065,7 +3186,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_redirect_silence, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_ERROR_COST, @@ -3073,7 +3194,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_error_cost, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_ERROR_BURST, @@ -3081,7 +3202,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_error_burst, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_GC_ELASTICITY, @@ -3089,7 +3210,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_gc_elasticity, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_MTU_EXPIRES, @@ -3097,8 +3218,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_mtu_expires, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies, + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies, }, { .ctl_name = NET_IPV4_ROUTE_MIN_PMTU, @@ -3106,7 +3227,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_min_pmtu, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_MIN_ADVMSS, @@ -3114,7 +3235,7 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_min_advmss, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_ROUTE_SECRET_INTERVAL, @@ -3122,8 +3243,8 @@ static ctl_table ipv4_route_table[] = { .data = &ip_rt_secret_interval, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &ipv4_sysctl_rt_secret_interval, - .strategy = &ipv4_sysctl_rt_secret_interval_strategy, + .proc_handler = ipv4_sysctl_rt_secret_interval, + .strategy = ipv4_sysctl_rt_secret_interval_strategy, }, { .ctl_name = 0 } }; @@ -3151,8 +3272,8 @@ static struct ctl_table ipv4_route_flush_table[] = { .procname = "flush", .maxlen = sizeof(int), .mode = 0200, - .proc_handler = &ipv4_sysctl_rtcache_flush, - .strategy = &ipv4_sysctl_rtcache_flush_strategy, + .proc_handler = ipv4_sysctl_rtcache_flush, + .strategy = ipv4_sysctl_rtcache_flush_strategy, }, { .ctl_name = 0 }, }; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 1bb10df8ce7d..4710d219f06a 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -195,7 +195,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_timestamps, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_WINDOW_SCALING, @@ -203,7 +203,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_window_scaling, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_SACK, @@ -211,7 +211,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_sack, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_RETRANS_COLLAPSE, @@ -219,7 +219,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_retrans_collapse, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_DEFAULT_TTL, @@ -227,8 +227,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_ip_default_ttl, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &ipv4_doint_and_flush, - .strategy = &ipv4_doint_and_flush_strategy, + .proc_handler = ipv4_doint_and_flush, + .strategy = ipv4_doint_and_flush_strategy, .extra2 = &init_net, }, { @@ -237,7 +237,7 @@ static struct ctl_table ipv4_table[] = { .data = &ipv4_config.no_pmtu_disc, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_NONLOCAL_BIND, @@ -245,7 +245,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_ip_nonlocal_bind, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_SYN_RETRIES, @@ -253,7 +253,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_syn_retries, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_SYNACK_RETRIES, @@ -261,7 +261,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_synack_retries, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_MAX_ORPHANS, @@ -269,7 +269,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_max_orphans, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_MAX_TW_BUCKETS, @@ -277,7 +277,7 @@ static struct ctl_table ipv4_table[] = { .data = &tcp_death_row.sysctl_max_tw_buckets, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_DYNADDR, @@ -285,7 +285,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_ip_dynaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_KEEPALIVE_TIME, @@ -293,8 +293,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_keepalive_time, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .ctl_name = NET_IPV4_TCP_KEEPALIVE_PROBES, @@ -302,7 +302,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_keepalive_probes, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_KEEPALIVE_INTVL, @@ -310,8 +310,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_keepalive_intvl, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .ctl_name = NET_IPV4_TCP_RETRIES1, @@ -319,8 +319,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_retries1, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, + .strategy = sysctl_intvec, .extra2 = &tcp_retr1_max }, { @@ -329,7 +329,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_retries2, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_TCP_FIN_TIMEOUT, @@ -337,8 +337,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_fin_timeout, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, #ifdef CONFIG_SYN_COOKIES { @@ -347,7 +347,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_syncookies, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #endif { @@ -356,7 +356,7 @@ static struct ctl_table ipv4_table[] = { .data = &tcp_death_row.sysctl_tw_recycle, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_ABORT_ON_OVERFLOW, @@ -364,7 +364,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_abort_on_overflow, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_STDURG, @@ -372,7 +372,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_stdurg, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_RFC1337, @@ -380,7 +380,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_rfc1337, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_MAX_SYN_BACKLOG, @@ -388,7 +388,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_max_syn_backlog, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_LOCAL_PORT_RANGE, @@ -396,8 +396,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_local_ports.range, .maxlen = sizeof(sysctl_local_ports.range), .mode = 0644, - .proc_handler = &ipv4_local_port_range, - .strategy = &ipv4_sysctl_local_port_range, + .proc_handler = ipv4_local_port_range, + .strategy = ipv4_sysctl_local_port_range, }, #ifdef CONFIG_IP_MULTICAST { @@ -406,7 +406,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_igmp_max_memberships, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #endif @@ -416,7 +416,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_igmp_max_msf, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_INET_PEER_THRESHOLD, @@ -424,7 +424,7 @@ static struct ctl_table ipv4_table[] = { .data = &inet_peer_threshold, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_INET_PEER_MINTTL, @@ -432,8 +432,8 @@ static struct ctl_table ipv4_table[] = { .data = &inet_peer_minttl, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .ctl_name = NET_IPV4_INET_PEER_MAXTTL, @@ -441,8 +441,8 @@ static struct ctl_table ipv4_table[] = { .data = &inet_peer_maxttl, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .ctl_name = NET_IPV4_INET_PEER_GC_MINTIME, @@ -450,8 +450,8 @@ static struct ctl_table ipv4_table[] = { .data = &inet_peer_gc_mintime, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .ctl_name = NET_IPV4_INET_PEER_GC_MAXTIME, @@ -459,8 +459,8 @@ static struct ctl_table ipv4_table[] = { .data = &inet_peer_gc_maxtime, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_jiffies, - .strategy = &sysctl_jiffies + .proc_handler = proc_dointvec_jiffies, + .strategy = sysctl_jiffies }, { .ctl_name = NET_TCP_ORPHAN_RETRIES, @@ -468,7 +468,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_orphan_retries, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_FACK, @@ -476,7 +476,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_fack, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_REORDERING, @@ -484,7 +484,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_reordering, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_ECN, @@ -492,7 +492,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_ecn, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_DSACK, @@ -500,7 +500,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_dsack, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_MEM, @@ -508,7 +508,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_mem, .maxlen = sizeof(sysctl_tcp_mem), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_WMEM, @@ -516,7 +516,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_RMEM, @@ -524,7 +524,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_rmem, .maxlen = sizeof(sysctl_tcp_rmem), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_APP_WIN, @@ -532,7 +532,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_app_win, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_ADV_WIN_SCALE, @@ -540,7 +540,7 @@ 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 }, { .ctl_name = NET_TCP_TW_REUSE, @@ -548,7 +548,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_tw_reuse, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_FRTO, @@ -556,7 +556,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_frto, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_FRTO_RESPONSE, @@ -564,7 +564,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_frto_response, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_LOW_LATENCY, @@ -572,7 +572,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_low_latency, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_TCP_NO_METRICS_SAVE, @@ -580,7 +580,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_nometrics_save, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_TCP_MODERATE_RCVBUF, @@ -588,7 +588,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_moderate_rcvbuf, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_TCP_TSO_WIN_DIVISOR, @@ -596,15 +596,15 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_tso_win_divisor, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_TCP_CONG_CONTROL, .procname = "tcp_congestion_control", .mode = 0644, .maxlen = TCP_CA_NAME_MAX, - .proc_handler = &proc_tcp_congestion_control, - .strategy = &sysctl_tcp_congestion_control, + .proc_handler = proc_tcp_congestion_control, + .strategy = sysctl_tcp_congestion_control, }, { .ctl_name = NET_TCP_ABC, @@ -612,7 +612,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_abc, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_TCP_MTU_PROBING, @@ -620,7 +620,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_mtu_probing, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_TCP_BASE_MSS, @@ -628,7 +628,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_base_mss, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_IPV4_TCP_WORKAROUND_SIGNED_WINDOWS, @@ -636,7 +636,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_workaround_signed_windows, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #ifdef CONFIG_NET_DMA { @@ -645,7 +645,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_dma_copybreak, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #endif { @@ -654,7 +654,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_slow_start_after_idle, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, #ifdef CONFIG_NETLABEL { @@ -663,7 +663,7 @@ static struct ctl_table ipv4_table[] = { .data = &cipso_v4_cache_enabled, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_CIPSOV4_CACHE_BUCKET_SIZE, @@ -671,7 +671,7 @@ static struct ctl_table ipv4_table[] = { .data = &cipso_v4_cache_bucketsize, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_CIPSOV4_RBM_OPTFMT, @@ -679,7 +679,7 @@ static struct ctl_table ipv4_table[] = { .data = &cipso_v4_rbm_optfmt, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = NET_CIPSOV4_RBM_STRICTVALID, @@ -687,22 +687,22 @@ static struct ctl_table ipv4_table[] = { .data = &cipso_v4_rbm_strictvalid, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, #endif /* CONFIG_NETLABEL */ { .procname = "tcp_available_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0444, - .proc_handler = &proc_tcp_available_congestion_control, + .proc_handler = proc_tcp_available_congestion_control, }, { .ctl_name = NET_TCP_ALLOWED_CONG_CONTROL, .procname = "tcp_allowed_congestion_control", .maxlen = TCP_CA_BUF_MAX, .mode = 0644, - .proc_handler = &proc_allowed_congestion_control, - .strategy = &strategy_allowed_congestion_control, + .proc_handler = proc_allowed_congestion_control, + .strategy = strategy_allowed_congestion_control, }, { .ctl_name = NET_TCP_MAX_SSTHRESH, @@ -710,7 +710,7 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_tcp_max_ssthresh, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec, + .proc_handler = proc_dointvec, }, { .ctl_name = CTL_UNNUMBERED, @@ -718,8 +718,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_udp_mem, .maxlen = sizeof(sysctl_udp_mem), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, + .strategy = sysctl_intvec, .extra1 = &zero }, { @@ -728,8 +728,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_udp_rmem_min, .maxlen = sizeof(sysctl_udp_rmem_min), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, + .strategy = sysctl_intvec, .extra1 = &zero }, { @@ -738,8 +738,8 @@ static struct ctl_table ipv4_table[] = { .data = &sysctl_udp_wmem_min, .maxlen = sizeof(sysctl_udp_wmem_min), .mode = 0644, - .proc_handler = &proc_dointvec_minmax, - .strategy = &sysctl_intvec, + .proc_handler = proc_dointvec_minmax, + .strategy = sysctl_intvec, .extra1 = &zero }, { .ctl_name = 0 } @@ -752,7 +752,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_echo_ignore_all, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_ICMP_ECHO_IGNORE_BROADCASTS, @@ -760,7 +760,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_echo_ignore_broadcasts, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_ICMP_IGNORE_BOGUS_ERROR_RESPONSES, @@ -768,7 +768,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_ignore_bogus_error_responses, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_ICMP_ERRORS_USE_INBOUND_IFADDR, @@ -776,7 +776,7 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_errors_use_inbound_ifaddr, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec }, { .ctl_name = NET_IPV4_ICMP_RATELIMIT, @@ -784,8 +784,8 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_ratelimit, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec_ms_jiffies, - .strategy = &sysctl_ms_jiffies + .proc_handler = proc_dointvec_ms_jiffies, + .strategy = sysctl_ms_jiffies }, { .ctl_name = NET_IPV4_ICMP_RATEMASK, @@ -793,7 +793,15 @@ static struct ctl_table ipv4_net_table[] = { .data = &init_net.ipv4.sysctl_icmp_ratemask, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = &proc_dointvec + .proc_handler = proc_dointvec + }, + { + .ctl_name = CTL_UNNUMBERED, + .procname = "rt_cache_rebuild_count", + .data = &init_net.ipv4.sysctl_rt_cache_rebuild_count, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec }, { } }; @@ -827,8 +835,12 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) &net->ipv4.sysctl_icmp_ratelimit; table[5].data = &net->ipv4.sysctl_icmp_ratemask; + table[6].data = + &net->ipv4.sysctl_rt_cache_rebuild_count; } + net->ipv4.sysctl_rt_cache_rebuild_count = 4; + net->ipv4.ipv4_hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); if (net->ipv4.ipv4_hdr == NULL) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c5aca0bb116a..f28acf11fc67 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -277,8 +277,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; -atomic_t tcp_orphan_count = ATOMIC_INIT(0); - +struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); int sysctl_tcp_mem[3] __read_mostly; @@ -290,9 +289,12 @@ EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); atomic_t tcp_memory_allocated; /* Current allocated memory. */ -atomic_t tcp_sockets_allocated; /* Current number of TCP sockets. */ - EXPORT_SYMBOL(tcp_memory_allocated); + +/* + * Current number of TCP sockets. + */ +struct percpu_counter tcp_sockets_allocated; EXPORT_SYMBOL(tcp_sockets_allocated); /* @@ -1680,7 +1682,7 @@ void tcp_set_state(struct sock *sk, int state) inet_put_port(sk); /* fall through */ default: - if (oldstate==TCP_ESTABLISHED) + if (oldstate == TCP_ESTABLISHED) TCP_DEC_STATS(sock_net(sk), TCP_MIB_CURRESTAB); } @@ -1690,7 +1692,7 @@ void tcp_set_state(struct sock *sk, int state) sk->sk_state = state; #ifdef STATE_TRACE - SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n",sk, statename[oldstate],statename[state]); + SOCK_DEBUG(sk, "TCP sk=%p, State %s -> %s\n", sk, statename[oldstate], statename[state]); #endif } EXPORT_SYMBOL_GPL(tcp_set_state); @@ -1834,7 +1836,6 @@ adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); - atomic_inc(sk->sk_prot->orphan_count); /* It is the last release_sock in its life. It will remove backlog. */ release_sock(sk); @@ -1847,6 +1848,8 @@ adjudge_to_death: bh_lock_sock(sk); WARN_ON(sock_owned_by_user(sk)); + percpu_counter_inc(sk->sk_prot->orphan_count); + /* Have we already been destroyed by a softirq or backlog? */ if (state != TCP_CLOSE && sk->sk_state == TCP_CLOSE) goto out; @@ -1885,9 +1888,11 @@ adjudge_to_death: } } if (sk->sk_state != TCP_CLOSE) { + int orphan_count = percpu_counter_read_positive( + sk->sk_prot->orphan_count); + sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, - atomic_read(sk->sk_prot->orphan_count))) { + if (tcp_too_many_orphans(sk, orphan_count)) { if (net_ratelimit()) printk(KERN_INFO "TCP: too many of orphaned " "sockets\n"); @@ -2461,6 +2466,106 @@ out: } EXPORT_SYMBOL(tcp_tso_segment); +struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct tcphdr *th; + struct tcphdr *th2; + unsigned int thlen; + unsigned int flags; + unsigned int total; + unsigned int mss = 1; + int flush = 1; + + if (!pskb_may_pull(skb, sizeof(*th))) + goto out; + + th = tcp_hdr(skb); + thlen = th->doff * 4; + if (thlen < sizeof(*th)) + goto out; + + if (!pskb_may_pull(skb, thlen)) + goto out; + + th = tcp_hdr(skb); + __skb_pull(skb, thlen); + + flags = tcp_flag_word(th); + + for (; (p = *head); head = &p->next) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + th2 = tcp_hdr(p); + + if (th->source != th2->source || th->dest != th2->dest) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + goto found; + } + + goto out_check_final; + +found: + flush = NAPI_GRO_CB(p)->flush; + flush |= flags & TCP_FLAG_CWR; + flush |= (flags ^ tcp_flag_word(th2)) & + ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH); + flush |= th->ack_seq != th2->ack_seq || th->window != th2->window; + flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th)); + + total = p->len; + mss = total; + if (skb_shinfo(p)->frag_list) + mss = skb_shinfo(p)->frag_list->len; + + flush |= skb->len > mss || skb->len <= 0; + flush |= ntohl(th2->seq) + total != ntohl(th->seq); + + if (flush || skb_gro_receive(head, skb)) { + mss = 1; + goto out_check_final; + } + + p = *head; + th2 = tcp_hdr(p); + tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); + +out_check_final: + flush = skb->len < mss; + flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | + TCP_FLAG_SYN | TCP_FLAG_FIN); + + if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) + pp = head; + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +int tcp_gro_complete(struct sk_buff *skb) +{ + struct tcphdr *th = tcp_hdr(skb); + + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + + skb_shinfo(skb)->gso_size = skb_shinfo(skb)->frag_list->len; + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + if (th->cwr) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + + return 0; +} + #ifdef CONFIG_TCP_MD5SIG static unsigned long tcp_md5sig_users; static struct tcp_md5sig_pool **tcp_md5sig_pool; @@ -2650,7 +2755,7 @@ EXPORT_SYMBOL(tcp_md5_hash_key); void tcp_done(struct sock *sk) { - if(sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) + if (sk->sk_state == TCP_SYN_SENT || sk->sk_state == TCP_SYN_RECV) TCP_INC_STATS_BH(sock_net(sk), TCP_MIB_ATTEMPTFAILS); tcp_set_state(sk, TCP_CLOSE); @@ -2685,6 +2790,8 @@ void __init tcp_init(void) BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); + percpu_counter_init(&tcp_sockets_allocated, 0); + percpu_counter_init(&tcp_orphan_count, 0); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, @@ -2707,8 +2814,8 @@ void __init tcp_init(void) thash_entries ? 0 : 512 * 1024); tcp_hashinfo.ehash_size = 1 << tcp_hashinfo.ehash_size; for (i = 0; i < tcp_hashinfo.ehash_size; i++) { - INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].chain); - INIT_HLIST_HEAD(&tcp_hashinfo.ehash[i].twchain); + INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].chain, i); + INIT_HLIST_NULLS_HEAD(&tcp_hashinfo.ehash[i].twchain, i); } if (inet_ehash_locks_alloc(&tcp_hashinfo)) panic("TCP: failed to alloc ehash_locks"); diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 4a1221e5e8ee..ee467ec40c4f 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -1,13 +1,23 @@ /* - * TCP CUBIC: Binary Increase Congestion control for TCP v2.2 + * TCP CUBIC: Binary Increase Congestion control for TCP v2.3 * Home page: * http://netsrv.csc.ncsu.edu/twiki/bin/view/Main/BIC * This is from the implementation of CUBIC TCP in - * Injong Rhee, Lisong Xu. - * "CUBIC: A New TCP-Friendly High-Speed TCP Variant - * in PFLDnet 2005 + * Sangtae Ha, Injong Rhee and Lisong Xu, + * "CUBIC: A New TCP-Friendly High-Speed TCP Variant" + * in ACM SIGOPS Operating System Review, July 2008. * Available from: - * http://netsrv.csc.ncsu.edu/export/cubic-paper.pdf + * http://netsrv.csc.ncsu.edu/export/cubic_a_new_tcp_2008.pdf + * + * CUBIC integrates a new slow start algorithm, called HyStart. + * The details of HyStart are presented in + * Sangtae Ha and Injong Rhee, + * "Taming the Elephants: New TCP Slow Start", NCSU TechReport 2008. + * Available from: + * http://netsrv.csc.ncsu.edu/export/hystart_techreport_2008.pdf + * + * All testing results are available from: + * http://netsrv.csc.ncsu.edu/wiki/index.php/TCP_Testing * * Unless CUBIC is enabled and congestion window is large * this behaves the same as the original Reno. @@ -23,12 +33,26 @@ */ #define BICTCP_HZ 10 /* BIC HZ 2^10 = 1024 */ +/* Two methods of hybrid slow start */ +#define HYSTART_ACK_TRAIN 0x1 +#define HYSTART_DELAY 0x2 + +/* Number of delay samples for detecting the increase of delay */ +#define HYSTART_MIN_SAMPLES 8 +#define HYSTART_DELAY_MIN (2U<<3) +#define HYSTART_DELAY_MAX (16U<<3) +#define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) + static int fast_convergence __read_mostly = 1; static int beta __read_mostly = 717; /* = 717/1024 (BICTCP_BETA_SCALE) */ static int initial_ssthresh __read_mostly; static int bic_scale __read_mostly = 41; static int tcp_friendliness __read_mostly = 1; +static int hystart __read_mostly = 1; +static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; +static int hystart_low_window __read_mostly = 16; + static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; static u64 cube_factor __read_mostly; @@ -44,6 +68,13 @@ module_param(bic_scale, int, 0444); MODULE_PARM_DESC(bic_scale, "scale (scaled by 1024) value for bic function (bic_scale/1024)"); module_param(tcp_friendliness, int, 0644); MODULE_PARM_DESC(tcp_friendliness, "turn on/off tcp friendliness"); +module_param(hystart, int, 0644); +MODULE_PARM_DESC(hystart, "turn on/off hybrid slow start algorithm"); +module_param(hystart_detect, int, 0644); +MODULE_PARM_DESC(hystart_detect, "hyrbrid slow start detection mechanisms" + " 1: packet-train 2: delay 3: both packet-train and delay"); +module_param(hystart_low_window, int, 0644); +MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); /* BIC TCP Parameters */ struct bictcp { @@ -59,7 +90,13 @@ struct bictcp { u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ #define ACK_RATIO_SHIFT 4 - u32 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ + u16 delayed_ack; /* estimate the ratio of Packets/ACKs << 4 */ + u8 sample_cnt; /* number of samples to decide curr_rtt */ + u8 found; /* the exit point is found? */ + u32 round_start; /* beginning of each round */ + u32 end_seq; /* end_seq of the round */ + u32 last_jiffies; /* last time when the ACK spacing is close */ + u32 curr_rtt; /* the minimum rtt of current round */ }; static inline void bictcp_reset(struct bictcp *ca) @@ -76,12 +113,28 @@ static inline void bictcp_reset(struct bictcp *ca) ca->delayed_ack = 2 << ACK_RATIO_SHIFT; ca->ack_cnt = 0; ca->tcp_cwnd = 0; + ca->found = 0; +} + +static inline void bictcp_hystart_reset(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + ca->round_start = ca->last_jiffies = jiffies; + ca->end_seq = tp->snd_nxt; + ca->curr_rtt = 0; + ca->sample_cnt = 0; } static void bictcp_init(struct sock *sk) { bictcp_reset(inet_csk_ca(sk)); - if (initial_ssthresh) + + if (hystart) + bictcp_hystart_reset(sk); + + if (!hystart && initial_ssthresh) tcp_sk(sk)->snd_ssthresh = initial_ssthresh; } @@ -235,9 +288,11 @@ static void bictcp_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) if (!tcp_is_cwnd_limited(sk, in_flight)) return; - if (tp->snd_cwnd <= tp->snd_ssthresh) + if (tp->snd_cwnd <= tp->snd_ssthresh) { + if (hystart && after(ack, ca->end_seq)) + bictcp_hystart_reset(sk); tcp_slow_start(tp); - else { + } else { bictcp_update(ca, tp->snd_cwnd); /* In dangerous area, increase slowly. @@ -281,8 +336,45 @@ static u32 bictcp_undo_cwnd(struct sock *sk) static void bictcp_state(struct sock *sk, u8 new_state) { - if (new_state == TCP_CA_Loss) + if (new_state == TCP_CA_Loss) { bictcp_reset(inet_csk_ca(sk)); + bictcp_hystart_reset(sk); + } +} + +static void hystart_update(struct sock *sk, u32 delay) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct bictcp *ca = inet_csk_ca(sk); + + if (!(ca->found & hystart_detect)) { + u32 curr_jiffies = jiffies; + + /* first detection parameter - ack-train detection */ + if (curr_jiffies - ca->last_jiffies <= msecs_to_jiffies(2)) { + ca->last_jiffies = curr_jiffies; + if (curr_jiffies - ca->round_start >= ca->delay_min>>4) + ca->found |= HYSTART_ACK_TRAIN; + } + + /* obtain the minimum delay of more than sampling packets */ + if (ca->sample_cnt < HYSTART_MIN_SAMPLES) { + if (ca->curr_rtt == 0 || ca->curr_rtt > delay) + ca->curr_rtt = delay; + + ca->sample_cnt++; + } else { + if (ca->curr_rtt > ca->delay_min + + HYSTART_DELAY_THRESH(ca->delay_min>>4)) + ca->found |= HYSTART_DELAY; + } + /* + * Either one of two conditions are met, + * we exit from slow start immediately. + */ + if (ca->found & hystart_detect) + tp->snd_ssthresh = tp->snd_cwnd; + } } /* Track delayed acknowledgment ratio using sliding window @@ -291,6 +383,7 @@ static void bictcp_state(struct sock *sk, u8 new_state) static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) { const struct inet_connection_sock *icsk = inet_csk(sk); + const struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); u32 delay; @@ -314,6 +407,11 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) /* first time call or link delay decreases */ if (ca->delay_min == 0 || ca->delay_min > delay) ca->delay_min = delay; + + /* hystart triggers when cwnd is larger than some threshold */ + if (hystart && tp->snd_cwnd <= tp->snd_ssthresh && + tp->snd_cwnd >= hystart_low_window) + hystart_update(sk, delay); } static struct tcp_congestion_ops cubictcp = { @@ -372,4 +470,4 @@ module_exit(cubictcp_unregister); MODULE_AUTHOR("Sangtae Ha, Stephen Hemminger"); MODULE_LICENSE("GPL"); MODULE_DESCRIPTION("CUBIC TCP"); -MODULE_VERSION("2.2"); +MODULE_VERSION("2.3"); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 838d491dfda7..fcbcd4ff6c5f 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -34,7 +34,7 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, tcp_get_info(sk, info); } -static struct inet_diag_handler tcp_diag_handler = { +static const struct inet_diag_handler tcp_diag_handler = { .idiag_hashinfo = &tcp_hashinfo, .idiag_get_info = tcp_diag_get_info, .idiag_type = TCPDIAG_GETSOCK, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index d77c0d29e239..99b7ecbe8893 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -701,13 +701,10 @@ static inline void tcp_set_rto(struct sock *sk) * all the algo is pure shit and should be replaced * with correct one. It is exactly, which we pretend to do. */ -} -/* NOTE: clamping at TCP_RTO_MIN is not required, current algo - * guarantees that rto is higher. - */ -static inline void tcp_bound_rto(struct sock *sk) -{ + /* NOTE: clamping at TCP_RTO_MIN is not required, current algo + * guarantees that rto is higher. + */ if (inet_csk(sk)->icsk_rto > TCP_RTO_MAX) inet_csk(sk)->icsk_rto = TCP_RTO_MAX; } @@ -928,7 +925,6 @@ static void tcp_init_metrics(struct sock *sk) tp->mdev_max = tp->rttvar = max(tp->mdev, tcp_rto_min(sk)); } tcp_set_rto(sk); - tcp_bound_rto(sk); if (inet_csk(sk)->icsk_rto < TCP_TIMEOUT_INIT && !tp->rx_opt.saw_tstamp) goto reset; tp->snd_cwnd = tcp_init_cwnd(tp, dst); @@ -1002,7 +998,8 @@ static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) } } -void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) +static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, + struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); @@ -1236,31 +1233,58 @@ static int tcp_check_dsack(struct sock *sk, struct sk_buff *ack_skb, return dup_sack; } +struct tcp_sacktag_state { + int reord; + int fack_count; + int flag; +}; + /* Check if skb is fully within the SACK block. In presence of GSO skbs, * the incoming SACK may not exactly match but we can find smaller MSS * aligned portion of it that matches. Therefore we might need to fragment * which may fail and creates some hassle (caller must handle error case * returns). + * + * FIXME: this could be merged to shift decision code */ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, u32 start_seq, u32 end_seq) { int in_sack, err; unsigned int pkt_len; + unsigned int mss; in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && !before(end_seq, TCP_SKB_CB(skb)->end_seq); if (tcp_skb_pcount(skb) > 1 && !in_sack && after(TCP_SKB_CB(skb)->end_seq, start_seq)) { - + mss = tcp_skb_mss(skb); in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq); - if (!in_sack) + if (!in_sack) { pkt_len = start_seq - TCP_SKB_CB(skb)->seq; - else + if (pkt_len < mss) + pkt_len = mss; + } else { pkt_len = end_seq - TCP_SKB_CB(skb)->seq; - err = tcp_fragment(sk, skb, pkt_len, skb_shinfo(skb)->gso_size); + if (pkt_len < mss) + return -EINVAL; + } + + /* Round if necessary so that SACKs cover only full MSSes + * and/or the remaining small portion (if present) + */ + if (pkt_len > mss) { + unsigned int new_len = (pkt_len / mss) * mss; + if (!in_sack && new_len < pkt_len) { + new_len += mss; + if (new_len > skb->len) + return 0; + } + pkt_len = new_len; + } + err = tcp_fragment(sk, skb, pkt_len, mss); if (err < 0) return err; } @@ -1268,24 +1292,25 @@ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, return in_sack; } -static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, - int *reord, int dup_sack, int fack_count) +static u8 tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, + struct tcp_sacktag_state *state, + int dup_sack, int pcount) { struct tcp_sock *tp = tcp_sk(sk); u8 sacked = TCP_SKB_CB(skb)->sacked; - int flag = 0; + int fack_count = state->fack_count; /* Account D-SACK for retransmitted packet. */ if (dup_sack && (sacked & TCPCB_RETRANS)) { if (after(TCP_SKB_CB(skb)->end_seq, tp->undo_marker)) tp->undo_retrans--; if (sacked & TCPCB_SACKED_ACKED) - *reord = min(fack_count, *reord); + state->reord = min(fack_count, state->reord); } /* Nothing to do; acked frame is about to be dropped (was ACKed). */ if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) - return flag; + return sacked; if (!(sacked & TCPCB_SACKED_ACKED)) { if (sacked & TCPCB_SACKED_RETRANS) { @@ -1294,10 +1319,9 @@ static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, * that retransmission is still in flight. */ if (sacked & TCPCB_LOST) { - TCP_SKB_CB(skb)->sacked &= - ~(TCPCB_LOST|TCPCB_SACKED_RETRANS); - tp->lost_out -= tcp_skb_pcount(skb); - tp->retrans_out -= tcp_skb_pcount(skb); + sacked &= ~(TCPCB_LOST|TCPCB_SACKED_RETRANS); + tp->lost_out -= pcount; + tp->retrans_out -= pcount; } } else { if (!(sacked & TCPCB_RETRANS)) { @@ -1306,56 +1330,280 @@ static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, */ if (before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) - *reord = min(fack_count, *reord); + state->reord = min(fack_count, + state->reord); /* SACK enhanced F-RTO (RFC4138; Appendix B) */ if (!after(TCP_SKB_CB(skb)->end_seq, tp->frto_highmark)) - flag |= FLAG_ONLY_ORIG_SACKED; + state->flag |= FLAG_ONLY_ORIG_SACKED; } if (sacked & TCPCB_LOST) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_LOST; - tp->lost_out -= tcp_skb_pcount(skb); + sacked &= ~TCPCB_LOST; + tp->lost_out -= pcount; } } - TCP_SKB_CB(skb)->sacked |= TCPCB_SACKED_ACKED; - flag |= FLAG_DATA_SACKED; - tp->sacked_out += tcp_skb_pcount(skb); + sacked |= TCPCB_SACKED_ACKED; + state->flag |= FLAG_DATA_SACKED; + tp->sacked_out += pcount; - fack_count += tcp_skb_pcount(skb); + fack_count += pcount; /* Lost marker hint past SACKed? Tweak RFC3517 cnt */ if (!tcp_is_fack(tp) && (tp->lost_skb_hint != NULL) && before(TCP_SKB_CB(skb)->seq, TCP_SKB_CB(tp->lost_skb_hint)->seq)) - tp->lost_cnt_hint += tcp_skb_pcount(skb); + tp->lost_cnt_hint += pcount; if (fack_count > tp->fackets_out) tp->fackets_out = fack_count; - - if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) - tcp_advance_highest_sack(sk, skb); } /* D-SACK. We can detect redundant retransmission in S|R and plain R * frames and clear it. undo_retrans is decreased above, L|R frames * are accounted above as well. */ - if (dup_sack && (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS)) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); + if (dup_sack && (sacked & TCPCB_SACKED_RETRANS)) { + sacked &= ~TCPCB_SACKED_RETRANS; + tp->retrans_out -= pcount; } - return flag; + return sacked; +} + +static int tcp_shifted_skb(struct sock *sk, struct sk_buff *skb, + struct tcp_sacktag_state *state, + unsigned int pcount, int shifted, int mss) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *prev = tcp_write_queue_prev(sk, skb); + + BUG_ON(!pcount); + + /* Tweak before seqno plays */ + if (!tcp_is_fack(tp) && tcp_is_sack(tp) && tp->lost_skb_hint && + !before(TCP_SKB_CB(tp->lost_skb_hint)->seq, TCP_SKB_CB(skb)->seq)) + tp->lost_cnt_hint += pcount; + + TCP_SKB_CB(prev)->end_seq += shifted; + TCP_SKB_CB(skb)->seq += shifted; + + skb_shinfo(prev)->gso_segs += pcount; + BUG_ON(skb_shinfo(skb)->gso_segs < pcount); + skb_shinfo(skb)->gso_segs -= pcount; + + /* When we're adding to gso_segs == 1, gso_size will be zero, + * in theory this shouldn't be necessary but as long as DSACK + * code can come after this skb later on it's better to keep + * setting gso_size to something. + */ + if (!skb_shinfo(prev)->gso_size) { + skb_shinfo(prev)->gso_size = mss; + skb_shinfo(prev)->gso_type = sk->sk_gso_type; + } + + /* CHECKME: To clear or not to clear? Mimics normal skb currently */ + if (skb_shinfo(skb)->gso_segs <= 1) { + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; + } + + /* We discard results */ + tcp_sacktag_one(skb, sk, state, 0, pcount); + + /* Difference in this won't matter, both ACKed by the same cumul. ACK */ + TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); + + if (skb->len > 0) { + BUG_ON(!tcp_skb_pcount(skb)); + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTED); + return 0; + } + + /* Whole SKB was eaten :-) */ + + if (skb == tp->retransmit_skb_hint) + tp->retransmit_skb_hint = prev; + if (skb == tp->scoreboard_skb_hint) + tp->scoreboard_skb_hint = prev; + if (skb == tp->lost_skb_hint) { + tp->lost_skb_hint = prev; + tp->lost_cnt_hint -= tcp_skb_pcount(prev); + } + + TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags; + if (skb == tcp_highest_sack(sk)) + tcp_advance_highest_sack(sk, skb); + + tcp_unlink_write_queue(skb, sk); + sk_wmem_free_skb(sk, skb); + + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKMERGED); + + return 1; +} + +/* I wish gso_size would have a bit more sane initialization than + * something-or-zero which complicates things + */ +static int tcp_skb_seglen(struct sk_buff *skb) +{ + return tcp_skb_pcount(skb) == 1 ? skb->len : tcp_skb_mss(skb); +} + +/* Shifting pages past head area doesn't work */ +static int skb_can_shift(struct sk_buff *skb) +{ + return !skb_headlen(skb) && skb_is_nonlinear(skb); +} + +/* Try collapsing SACK blocks spanning across multiple skbs to a single + * skb. + */ +static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, + struct tcp_sacktag_state *state, + u32 start_seq, u32 end_seq, + int dup_sack) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *prev; + int mss; + int pcount = 0; + int len; + int in_sack; + + if (!sk_can_gso(sk)) + goto fallback; + + /* Normally R but no L won't result in plain S */ + if (!dup_sack && + (TCP_SKB_CB(skb)->sacked & (TCPCB_LOST|TCPCB_SACKED_RETRANS)) == TCPCB_SACKED_RETRANS) + goto fallback; + if (!skb_can_shift(skb)) + goto fallback; + /* This frame is about to be dropped (was ACKed). */ + if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) + goto fallback; + + /* Can only happen with delayed DSACK + discard craziness */ + if (unlikely(skb == tcp_write_queue_head(sk))) + goto fallback; + prev = tcp_write_queue_prev(sk, skb); + + if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) + goto fallback; + + in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && + !before(end_seq, TCP_SKB_CB(skb)->end_seq); + + if (in_sack) { + len = skb->len; + pcount = tcp_skb_pcount(skb); + mss = tcp_skb_seglen(skb); + + /* TODO: Fix DSACKs to not fragment already SACKed and we can + * drop this restriction as unnecessary + */ + if (mss != tcp_skb_seglen(prev)) + goto fallback; + } else { + if (!after(TCP_SKB_CB(skb)->end_seq, start_seq)) + goto noop; + /* CHECKME: This is non-MSS split case only?, this will + * cause skipped skbs due to advancing loop btw, original + * has that feature too + */ + if (tcp_skb_pcount(skb) <= 1) + goto noop; + + in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq); + if (!in_sack) { + /* TODO: head merge to next could be attempted here + * if (!after(TCP_SKB_CB(skb)->end_seq, end_seq)), + * though it might not be worth of the additional hassle + * + * ...we can probably just fallback to what was done + * previously. We could try merging non-SACKed ones + * as well but it probably isn't going to buy off + * because later SACKs might again split them, and + * it would make skb timestamp tracking considerably + * harder problem. + */ + goto fallback; + } + + len = end_seq - TCP_SKB_CB(skb)->seq; + BUG_ON(len < 0); + BUG_ON(len > skb->len); + + /* MSS boundaries should be honoured or else pcount will + * severely break even though it makes things bit trickier. + * Optimize common case to avoid most of the divides + */ + mss = tcp_skb_mss(skb); + + /* TODO: Fix DSACKs to not fragment already SACKed and we can + * drop this restriction as unnecessary + */ + if (mss != tcp_skb_seglen(prev)) + goto fallback; + + if (len == mss) { + pcount = 1; + } else if (len < mss) { + goto noop; + } else { + pcount = len / mss; + len = pcount * mss; + } + } + + if (!skb_shift(prev, skb, len)) + goto fallback; + if (!tcp_shifted_skb(sk, skb, state, pcount, len, mss)) + goto out; + + /* Hole filled allows collapsing with the next as well, this is very + * useful when hole on every nth skb pattern happens + */ + if (prev == tcp_write_queue_tail(sk)) + goto out; + skb = tcp_write_queue_next(sk, prev); + + if (!skb_can_shift(skb) || + (skb == tcp_send_head(sk)) || + ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) || + (mss != tcp_skb_seglen(skb))) + goto out; + + len = skb->len; + if (skb_shift(prev, skb, len)) { + pcount += tcp_skb_pcount(skb); + tcp_shifted_skb(sk, skb, state, tcp_skb_pcount(skb), len, mss); + } + +out: + state->fack_count += pcount; + return prev; + +noop: + return skb; + +fallback: + NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_SACKSHIFTFALLBACK); + return NULL; } static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, + struct tcp_sacktag_state *state, u32 start_seq, u32 end_seq, - int dup_sack_in, int *fack_count, - int *reord, int *flag) + int dup_sack_in) { + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *tmp; + tcp_for_write_queue_from(skb, sk) { int in_sack = 0; int dup_sack = dup_sack_in; @@ -1376,17 +1624,42 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, dup_sack = 1; } - if (in_sack <= 0) - in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, - end_seq); + /* skb reference here is a bit tricky to get right, since + * shifting can eat and free both this skb and the next, + * so not even _safe variant of the loop is enough. + */ + if (in_sack <= 0) { + tmp = tcp_shift_skb_data(sk, skb, state, + start_seq, end_seq, dup_sack); + if (tmp != NULL) { + if (tmp != skb) { + skb = tmp; + continue; + } + + in_sack = 0; + } else { + in_sack = tcp_match_skb_to_sack(sk, skb, + start_seq, + end_seq); + } + } + if (unlikely(in_sack < 0)) break; - if (in_sack) - *flag |= tcp_sacktag_one(skb, sk, reord, dup_sack, - *fack_count); + if (in_sack) { + TCP_SKB_CB(skb)->sacked = tcp_sacktag_one(skb, sk, + state, + dup_sack, + tcp_skb_pcount(skb)); + + if (!before(TCP_SKB_CB(skb)->seq, + tcp_highest_sack_seq(tp))) + tcp_advance_highest_sack(sk, skb); + } - *fack_count += tcp_skb_pcount(skb); + state->fack_count += tcp_skb_pcount(skb); } return skb; } @@ -1395,16 +1668,17 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, * a normal way */ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, - u32 skip_to_seq, int *fack_count) + struct tcp_sacktag_state *state, + u32 skip_to_seq) { tcp_for_write_queue_from(skb, sk) { if (skb == tcp_send_head(sk)) break; - if (!before(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) + if (after(TCP_SKB_CB(skb)->end_seq, skip_to_seq)) break; - *fack_count += tcp_skb_pcount(skb); + state->fack_count += tcp_skb_pcount(skb); } return skb; } @@ -1412,18 +1686,17 @@ static struct sk_buff *tcp_sacktag_skip(struct sk_buff *skb, struct sock *sk, static struct sk_buff *tcp_maybe_skipping_dsack(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, - u32 skip_to_seq, - int *fack_count, int *reord, - int *flag) + struct tcp_sacktag_state *state, + u32 skip_to_seq) { if (next_dup == NULL) return skb; if (before(next_dup->start_seq, skip_to_seq)) { - skb = tcp_sacktag_skip(skb, sk, next_dup->start_seq, fack_count); - skb = tcp_sacktag_walk(skb, sk, NULL, - next_dup->start_seq, next_dup->end_seq, - 1, fack_count, reord, flag); + skb = tcp_sacktag_skip(skb, sk, state, next_dup->start_seq); + skb = tcp_sacktag_walk(skb, sk, NULL, state, + next_dup->start_seq, next_dup->end_seq, + 1); } return skb; @@ -1445,16 +1718,17 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, struct tcp_sack_block_wire *sp_wire = (struct tcp_sack_block_wire *)(ptr+2); struct tcp_sack_block sp[TCP_NUM_SACKS]; struct tcp_sack_block *cache; + struct tcp_sacktag_state state; struct sk_buff *skb; int num_sacks = min(TCP_NUM_SACKS, (ptr[1] - TCPOLEN_SACK_BASE) >> 3); int used_sacks; - int reord = tp->packets_out; - int flag = 0; int found_dup_sack = 0; - int fack_count; int i, j; int first_sack_index; + state.flag = 0; + state.reord = tp->packets_out; + if (!tp->sacked_out) { if (WARN_ON(tp->fackets_out)) tp->fackets_out = 0; @@ -1464,7 +1738,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, found_dup_sack = tcp_check_dsack(sk, ack_skb, sp_wire, num_sacks, prior_snd_una); if (found_dup_sack) - flag |= FLAG_DSACKING_ACK; + state.flag |= FLAG_DSACKING_ACK; /* Eliminate too old ACKs, but take into * account more or less fresh ones, they can @@ -1533,7 +1807,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, } skb = tcp_write_queue_head(sk); - fack_count = 0; + state.fack_count = 0; i = 0; if (!tp->sacked_out) { @@ -1558,7 +1832,7 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, /* Event "B" in the comment above. */ if (after(end_seq, tp->high_seq)) - flag |= FLAG_DATA_LOST; + state.flag |= FLAG_DATA_LOST; /* Skip too early cached blocks */ while (tcp_sack_cache_ok(tp, cache) && @@ -1571,13 +1845,13 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, /* Head todo? */ if (before(start_seq, cache->start_seq)) { - skb = tcp_sacktag_skip(skb, sk, start_seq, - &fack_count); + skb = tcp_sacktag_skip(skb, sk, &state, + start_seq); skb = tcp_sacktag_walk(skb, sk, next_dup, + &state, start_seq, cache->start_seq, - dup_sack, &fack_count, - &reord, &flag); + dup_sack); } /* Rest of the block already fully processed? */ @@ -1585,9 +1859,8 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, goto advance_sp; skb = tcp_maybe_skipping_dsack(skb, sk, next_dup, - cache->end_seq, - &fack_count, &reord, - &flag); + &state, + cache->end_seq); /* ...tail remains todo... */ if (tcp_highest_sack_seq(tp) == cache->end_seq) { @@ -1595,13 +1868,12 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, skb = tcp_highest_sack(sk); if (skb == NULL) break; - fack_count = tp->fackets_out; + state.fack_count = tp->fackets_out; cache++; goto walk; } - skb = tcp_sacktag_skip(skb, sk, cache->end_seq, - &fack_count); + skb = tcp_sacktag_skip(skb, sk, &state, cache->end_seq); /* Check overlap against next cached too (past this one already) */ cache++; continue; @@ -1611,20 +1883,20 @@ tcp_sacktag_write_queue(struct sock *sk, struct sk_buff *ack_skb, skb = tcp_highest_sack(sk); if (skb == NULL) break; - fack_count = tp->fackets_out; + state.fack_count = tp->fackets_out; } - skb = tcp_sacktag_skip(skb, sk, start_seq, &fack_count); + skb = tcp_sacktag_skip(skb, sk, &state, start_seq); walk: - skb = tcp_sacktag_walk(skb, sk, next_dup, start_seq, end_seq, - dup_sack, &fack_count, &reord, &flag); + skb = tcp_sacktag_walk(skb, sk, next_dup, &state, + start_seq, end_seq, dup_sack); advance_sp: /* SACK enhanced FRTO (RFC4138, Appendix B): Clearing correct * due to in-order walk */ if (after(end_seq, tp->frto_highmark)) - flag &= ~FLAG_ONLY_ORIG_SACKED; + state.flag &= ~FLAG_ONLY_ORIG_SACKED; i++; } @@ -1641,10 +1913,10 @@ advance_sp: tcp_verify_left_out(tp); - if ((reord < tp->fackets_out) && + if ((state.reord < tp->fackets_out) && ((icsk->icsk_ca_state != TCP_CA_Loss) || tp->undo_marker) && (!tp->frto_highmark || after(tp->snd_una, tp->frto_highmark))) - tcp_update_reordering(sk, tp->fackets_out - reord, 0); + tcp_update_reordering(sk, tp->fackets_out - state.reord, 0); out: @@ -1654,13 +1926,13 @@ out: WARN_ON((int)tp->retrans_out < 0); WARN_ON((int)tcp_packets_in_flight(tp) < 0); #endif - return flag; + return state.flag; } /* Limits sacked_out so that sum with lost_out isn't ever larger than * packets_out. Returns zero if sacked_out adjustement wasn't necessary. */ -int tcp_limit_reno_sacked(struct tcp_sock *tp) +static int tcp_limit_reno_sacked(struct tcp_sock *tp) { u32 holes; @@ -2336,9 +2608,9 @@ static void DBGUNDO(struct sock *sk, const char *msg) struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { - printk(KERN_DEBUG "Undo %s " NIPQUAD_FMT "/%u c%u l%u ss%u/%u p%u\n", + printk(KERN_DEBUG "Undo %s %pI4/%u c%u l%u ss%u/%u p%u\n", msg, - NIPQUAD(inet->daddr), ntohs(inet->dport), + &inet->daddr, ntohs(inet->dport), tp->snd_cwnd, tcp_left_out(tp), tp->snd_ssthresh, tp->prior_ssthresh, tp->packets_out); @@ -2346,9 +2618,9 @@ static void DBGUNDO(struct sock *sk, const char *msg) #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - printk(KERN_DEBUG "Undo %s " NIP6_FMT "/%u c%u l%u ss%u/%u p%u\n", + printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", msg, - NIP6(np->daddr), ntohs(inet->dport), + &np->daddr, ntohs(inet->dport), tp->snd_cwnd, tcp_left_out(tp), tp->snd_ssthresh, tp->prior_ssthresh, tp->packets_out); @@ -2559,6 +2831,56 @@ static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb) tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } +/* Do a simple retransmit without using the backoff mechanisms in + * tcp_timer. This is used for path mtu discovery. + * The socket is already locked here. + */ +void tcp_simple_retransmit(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + unsigned int mss = tcp_current_mss(sk, 0); + u32 prior_lost = tp->lost_out; + + tcp_for_write_queue(skb, sk) { + if (skb == tcp_send_head(sk)) + break; + if (tcp_skb_seglen(skb) > mss && + !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { + TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; + tp->retrans_out -= tcp_skb_pcount(skb); + } + tcp_skb_mark_lost_uncond_verify(tp, skb); + } + } + + tcp_clear_retrans_hints_partial(tp); + + if (prior_lost == tp->lost_out) + return; + + if (tcp_is_reno(tp)) + tcp_limit_reno_sacked(tp); + + tcp_verify_left_out(tp); + + /* Don't muck with the congestion window here. + * Reason is that we do not increase amount of _data_ + * in network, but units changed and effective + * cwnd/ssthresh really reduced now. + */ + if (icsk->icsk_ca_state != TCP_CA_Loss) { + tp->high_seq = tp->snd_nxt; + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->prior_ssthresh = 0; + tp->undo_marker = 0; + tcp_set_ca_state(sk, TCP_CA_Loss); + } + tcp_xmit_retransmit_queue(sk); +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and @@ -2730,6 +3052,13 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) tcp_xmit_retransmit_queue(sk); } +static void tcp_valid_rtt_meas(struct sock *sk, u32 seq_rtt) +{ + tcp_rtt_estimator(sk, seq_rtt); + tcp_set_rto(sk); + inet_csk(sk)->icsk_backoff = 0; +} + /* Read draft-ietf-tcplw-high-performance before mucking * with this code. (Supersedes RFC1323) */ @@ -2751,11 +3080,8 @@ static void tcp_ack_saw_tstamp(struct sock *sk, int flag) * in window is lost... Voila. --ANK (010210) */ struct tcp_sock *tp = tcp_sk(sk); - const __u32 seq_rtt = tcp_time_stamp - tp->rx_opt.rcv_tsecr; - tcp_rtt_estimator(sk, seq_rtt); - tcp_set_rto(sk); - inet_csk(sk)->icsk_backoff = 0; - tcp_bound_rto(sk); + + tcp_valid_rtt_meas(sk, tcp_time_stamp - tp->rx_opt.rcv_tsecr); } static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag) @@ -2772,10 +3098,7 @@ static void tcp_ack_no_tstamp(struct sock *sk, u32 seq_rtt, int flag) if (flag & FLAG_RETRANS_DATA_ACKED) return; - tcp_rtt_estimator(sk, seq_rtt); - tcp_set_rto(sk); - inet_csk(sk)->icsk_backoff = 0; - tcp_bound_rto(sk); + tcp_valid_rtt_meas(sk, seq_rtt); } static inline void tcp_ack_update_rtt(struct sock *sk, const int flag, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 5c8fa7f1e327..9d839fa9331e 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -51,6 +51,7 @@ */ +#include <linux/bottom_half.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> @@ -97,11 +98,7 @@ struct tcp_md5sig_key *tcp_v4_md5_do_lookup(struct sock *sk, __be32 addr) } #endif -struct inet_hashinfo __cacheline_aligned tcp_hashinfo = { - .lhash_lock = __RW_LOCK_UNLOCKED(tcp_hashinfo.lhash_lock), - .lhash_users = ATOMIC_INIT(0), - .lhash_wait = __WAIT_QUEUE_HEAD_INITIALIZER(tcp_hashinfo.lhash_wait), -}; +struct inet_hashinfo tcp_hashinfo; static inline __u32 tcp_v4_init_sequence(struct sk_buff *skb) { @@ -492,7 +489,7 @@ void tcp_v4_send_check(struct sock *sk, int len, struct sk_buff *skb) skb->csum_offset = offsetof(struct tcphdr, check); } else { th->check = tcp_v4_check(len, inet->saddr, inet->daddr, - csum_partial((char *)th, + csum_partial(th, th->doff << 2, skb->csum)); } @@ -726,7 +723,7 @@ static int __tcp_v4_send_synack(struct sock *sk, struct request_sock *req, th->check = tcp_v4_check(skb->len, ireq->loc_addr, ireq->rmt_addr, - csum_partial((char *)th, skb->len, + csum_partial(th, skb->len, skb->csum)); err = ip_build_and_send_pkt(skb, sk, ireq->loc_addr, @@ -1139,10 +1136,9 @@ static int tcp_v4_inbound_md5_hash(struct sock *sk, struct sk_buff *skb) if (genhash || memcmp(hash_location, newhash, 16) != 0) { if (net_ratelimit()) { - printk(KERN_INFO "MD5 Hash failed for " - "(" NIPQUAD_FMT ", %d)->(" NIPQUAD_FMT ", %d)%s\n", - NIPQUAD(iph->saddr), ntohs(th->source), - NIPQUAD(iph->daddr), ntohs(th->dest), + printk(KERN_INFO "MD5 Hash failed for (%pI4, %d)->(%pI4, %d)%s\n", + &iph->saddr, ntohs(th->source), + &iph->daddr, ntohs(th->dest), genhash ? " tcp_v4_calc_md5_hash failed" : ""); } return 1; @@ -1297,10 +1293,8 @@ int tcp_v4_conn_request(struct sock *sk, struct sk_buff *skb) * to destinations, already remembered * to the moment of synflood. */ - LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open " - "request from " NIPQUAD_FMT "/%u\n", - NIPQUAD(saddr), - ntohs(tcp_hdr(skb)->source)); + LIMIT_NETDEBUG(KERN_DEBUG "TCP: drop open request from %pI4/%u\n", + &saddr, ntohs(tcp_hdr(skb)->source)); goto drop_and_release; } @@ -1804,7 +1798,9 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - atomic_inc(&tcp_sockets_allocated); + local_bh_disable(); + percpu_counter_inc(&tcp_sockets_allocated); + local_bh_enable(); return 0; } @@ -1852,7 +1848,7 @@ void tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } - atomic_dec(&tcp_sockets_allocated); + percpu_counter_dec(&tcp_sockets_allocated); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -1860,32 +1856,35 @@ EXPORT_SYMBOL(tcp_v4_destroy_sock); #ifdef CONFIG_PROC_FS /* Proc filesystem TCP sock list dumping. */ -static inline struct inet_timewait_sock *tw_head(struct hlist_head *head) +static inline struct inet_timewait_sock *tw_head(struct hlist_nulls_head *head) { - return hlist_empty(head) ? NULL : + return hlist_nulls_empty(head) ? NULL : list_entry(head->first, struct inet_timewait_sock, tw_node); } static inline struct inet_timewait_sock *tw_next(struct inet_timewait_sock *tw) { - return tw->tw_node.next ? - hlist_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL; + return !is_a_nulls(tw->tw_node.next) ? + hlist_nulls_entry(tw->tw_node.next, typeof(*tw), tw_node) : NULL; } static void *listening_get_next(struct seq_file *seq, void *cur) { struct inet_connection_sock *icsk; - struct hlist_node *node; + struct hlist_nulls_node *node; struct sock *sk = cur; - struct tcp_iter_state* st = seq->private; + struct inet_listen_hashbucket *ilb; + struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); if (!sk) { st->bucket = 0; - sk = sk_head(&tcp_hashinfo.listening_hash[0]); + ilb = &tcp_hashinfo.listening_hash[0]; + spin_lock_bh(&ilb->lock); + sk = sk_nulls_head(&ilb->head); goto get_sk; } - + ilb = &tcp_hashinfo.listening_hash[st->bucket]; ++st->num; if (st->state == TCP_SEQ_STATE_OPENREQ) { @@ -1918,7 +1917,7 @@ get_req: sk = sk_next(sk); } get_sk: - sk_for_each_from(sk, node) { + sk_nulls_for_each_from(sk, node) { if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) { cur = sk; goto out; @@ -1935,8 +1934,11 @@ start_req: } read_unlock_bh(&icsk->icsk_accept_queue.syn_wait_lock); } + spin_unlock_bh(&ilb->lock); if (++st->bucket < INET_LHTABLE_SIZE) { - sk = sk_head(&tcp_hashinfo.listening_hash[st->bucket]); + ilb = &tcp_hashinfo.listening_hash[st->bucket]; + spin_lock_bh(&ilb->lock); + sk = sk_nulls_head(&ilb->head); goto get_sk; } cur = NULL; @@ -1957,28 +1959,28 @@ static void *listening_get_idx(struct seq_file *seq, loff_t *pos) static inline int empty_bucket(struct tcp_iter_state *st) { - return hlist_empty(&tcp_hashinfo.ehash[st->bucket].chain) && - hlist_empty(&tcp_hashinfo.ehash[st->bucket].twchain); + return hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].chain) && + hlist_nulls_empty(&tcp_hashinfo.ehash[st->bucket].twchain); } static void *established_get_first(struct seq_file *seq) { - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); void *rc = NULL; for (st->bucket = 0; st->bucket < tcp_hashinfo.ehash_size; ++st->bucket) { struct sock *sk; - struct hlist_node *node; + struct hlist_nulls_node *node; struct inet_timewait_sock *tw; - rwlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); + spinlock_t *lock = inet_ehash_lockp(&tcp_hashinfo, st->bucket); /* Lockless fast path for the common case of empty buckets */ if (empty_bucket(st)) continue; - read_lock_bh(lock); - sk_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { + spin_lock_bh(lock); + sk_nulls_for_each(sk, node, &tcp_hashinfo.ehash[st->bucket].chain) { if (sk->sk_family != st->family || !net_eq(sock_net(sk), net)) { continue; @@ -1996,7 +1998,7 @@ static void *established_get_first(struct seq_file *seq) rc = tw; goto out; } - read_unlock_bh(lock); + spin_unlock_bh(lock); st->state = TCP_SEQ_STATE_ESTABLISHED; } out: @@ -2007,8 +2009,8 @@ static void *established_get_next(struct seq_file *seq, void *cur) { struct sock *sk = cur; struct inet_timewait_sock *tw; - struct hlist_node *node; - struct tcp_iter_state* st = seq->private; + struct hlist_nulls_node *node; + struct tcp_iter_state *st = seq->private; struct net *net = seq_file_net(seq); ++st->num; @@ -2024,7 +2026,7 @@ get_tw: cur = tw; goto out; } - read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); st->state = TCP_SEQ_STATE_ESTABLISHED; /* Look for next non empty bucket */ @@ -2034,12 +2036,12 @@ get_tw: if (st->bucket >= tcp_hashinfo.ehash_size) return NULL; - read_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); - sk = sk_head(&tcp_hashinfo.ehash[st->bucket].chain); + spin_lock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + sk = sk_nulls_head(&tcp_hashinfo.ehash[st->bucket].chain); } else - sk = sk_next(sk); + sk = sk_nulls_next(sk); - sk_for_each_from(sk, node) { + sk_nulls_for_each_from(sk, node) { if (sk->sk_family == st->family && net_eq(sock_net(sk), net)) goto found; } @@ -2067,14 +2069,12 @@ static void *established_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_get_idx(struct seq_file *seq, loff_t pos) { void *rc; - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; - inet_listen_lock(&tcp_hashinfo); st->state = TCP_SEQ_STATE_LISTENING; rc = listening_get_idx(seq, &pos); if (!rc) { - inet_listen_unlock(&tcp_hashinfo); st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_idx(seq, pos); } @@ -2084,7 +2084,7 @@ static void *tcp_get_idx(struct seq_file *seq, loff_t pos) static void *tcp_seq_start(struct seq_file *seq, loff_t *pos) { - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; st->state = TCP_SEQ_STATE_LISTENING; st->num = 0; return *pos ? tcp_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; @@ -2093,7 +2093,7 @@ static void *tcp_seq_start(struct seq_file *seq, loff_t *pos) static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { void *rc = NULL; - struct tcp_iter_state* st; + struct tcp_iter_state *st; if (v == SEQ_START_TOKEN) { rc = tcp_get_idx(seq, 0); @@ -2106,7 +2106,6 @@ static void *tcp_seq_next(struct seq_file *seq, void *v, loff_t *pos) case TCP_SEQ_STATE_LISTENING: rc = listening_get_next(seq, v); if (!rc) { - inet_listen_unlock(&tcp_hashinfo); st->state = TCP_SEQ_STATE_ESTABLISHED; rc = established_get_first(seq); } @@ -2123,7 +2122,7 @@ out: static void tcp_seq_stop(struct seq_file *seq, void *v) { - struct tcp_iter_state* st = seq->private; + struct tcp_iter_state *st = seq->private; switch (st->state) { case TCP_SEQ_STATE_OPENREQ: @@ -2133,12 +2132,12 @@ static void tcp_seq_stop(struct seq_file *seq, void *v) } case TCP_SEQ_STATE_LISTENING: if (v != SEQ_START_TOKEN) - inet_listen_unlock(&tcp_hashinfo); + spin_unlock_bh(&tcp_hashinfo.listening_hash[st->bucket].lock); break; case TCP_SEQ_STATE_TIME_WAIT: case TCP_SEQ_STATE_ESTABLISHED: if (v) - read_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); + spin_unlock_bh(inet_ehash_lockp(&tcp_hashinfo, st->bucket)); break; } } @@ -2284,7 +2283,7 @@ static void get_timewait4_sock(struct inet_timewait_sock *tw, static int tcp4_seq_show(struct seq_file *seq, void *v) { - struct tcp_iter_state* st; + struct tcp_iter_state *st; int len; if (v == SEQ_START_TOKEN) { @@ -2350,6 +2349,41 @@ void tcp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ +struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (!tcp_v4_check(skb->len, iph->saddr, iph->daddr, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + + /* fall through */ + case CHECKSUM_NONE: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + return tcp_gro_receive(head, skb); +} +EXPORT_SYMBOL(tcp4_gro_receive); + +int tcp4_gro_complete(struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), + iph->saddr, iph->daddr, 0); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + + return tcp_gro_complete(skb); +} +EXPORT_SYMBOL(tcp4_gro_complete); + struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, @@ -2378,6 +2412,7 @@ struct proto tcp_prot = { .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, .obj_size = sizeof(struct tcp_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, .twsk_prot = &tcp_timewait_sock_ops, .rsk_prot = &tcp_request_sock_ops, .h.hashinfo = &tcp_hashinfo, @@ -2407,6 +2442,7 @@ static struct pernet_operations __net_initdata tcp_sk_ops = { void __init tcp_v4_init(void) { + inet_hashinfo_init(&tcp_hashinfo); if (register_pernet_device(&tcp_sk_ops)) panic("Failed to create the TCP control socket.\n"); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 779f2e9d0689..f67effbb102b 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -491,7 +491,7 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, * as a request_sock. */ -struct sock *tcp_check_req(struct sock *sk,struct sk_buff *skb, +struct sock *tcp_check_req(struct sock *sk, struct sk_buff *skb, struct request_sock *req, struct request_sock **prev) { diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 85b07eba1879..557fe16cbfb0 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -42,7 +42,7 @@ /* People can turn this off for buggy TCP's found in printers etc. */ int sysctl_tcp_retrans_collapse __read_mostly = 1; -/* People can turn this on to work with those rare, broken TCPs that +/* People can turn this on to work with those rare, broken TCPs that * interpret the window field as a signed quantity. */ int sysctl_tcp_workaround_signed_windows __read_mostly = 0; @@ -484,7 +484,7 @@ static unsigned tcp_syn_options(struct sock *sk, struct sk_buff *skb, } if (likely(sysctl_tcp_window_scaling)) { opts->ws = tp->rx_opt.rcv_wscale; - if(likely(opts->ws)) + if (likely(opts->ws)) size += TCPOLEN_WSCALE_ALIGNED; } if (likely(sysctl_tcp_sack)) { @@ -526,7 +526,7 @@ static unsigned tcp_synack_options(struct sock *sk, if (likely(ireq->wscale_ok)) { opts->ws = ireq->rcv_wscale; - if(likely(opts->ws)) + if (likely(opts->ws)) size += TCPOLEN_WSCALE_ALIGNED; } if (likely(doing_ts)) { @@ -663,10 +663,14 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, th->urg_ptr = 0; /* The urg_mode check is necessary during a below snd_una win probe */ - if (unlikely(tcp_urg_mode(tp) && - between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF))) { - th->urg_ptr = htons(tp->snd_up - tcb->seq); - th->urg = 1; + if (unlikely(tcp_urg_mode(tp))) { + if (between(tp->snd_up, tcb->seq + 1, tcb->seq + 0xFFFF)) { + th->urg_ptr = htons(tp->snd_up - tcb->seq); + th->urg = 1; + } else if (after(tcb->seq + 0xFFFF, tp->snd_nxt)) { + th->urg_ptr = 0xFFFF; + th->urg = 1; + } } tcp_options_write((__be32 *)(th + 1), tp, &opts, &md5_hash_location); @@ -722,8 +726,7 @@ static void tcp_queue_skb(struct sock *sk, struct sk_buff *skb) static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now) { - if (skb->len <= mss_now || !sk_can_gso(sk) || - tcp_urg_mode(tcp_sk(sk))) { + if (skb->len <= mss_now || !sk_can_gso(sk)) { /* Avoid the costly divide in the normal * non-TSO case. */ @@ -1029,10 +1032,6 @@ unsigned int tcp_sync_mss(struct sock *sk, u32 pmtu) /* Compute the current effective MSS, taking SACKs and IP options, * and even PMTU discovery events into account. - * - * LARGESEND note: !tcp_urg_mode is overkill, only frames up to snd_up - * cannot be large. However, taking into account rare use of URG, this - * is not a big flaw. */ unsigned int tcp_current_mss(struct sock *sk, int large_allowed) { @@ -1047,7 +1046,7 @@ unsigned int tcp_current_mss(struct sock *sk, int large_allowed) mss_now = tp->mss_cache; - if (large_allowed && sk_can_gso(sk) && !tcp_urg_mode(tp)) + if (large_allowed && sk_can_gso(sk)) doing_tso = 1; if (dst) { @@ -1164,9 +1163,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, { int tso_segs = tcp_skb_pcount(skb); - if (!tso_segs || - (tso_segs > 1 && (tcp_skb_mss(skb) != mss_now || - tcp_urg_mode(tcp_sk(sk))))) { + if (!tso_segs || (tso_segs > 1 && tcp_skb_mss(skb) != mss_now)) { tcp_set_skb_tso_segs(sk, skb, mss_now); tso_segs = tcp_skb_pcount(skb); } @@ -1175,7 +1172,7 @@ static int tcp_init_tso_segs(struct sock *sk, struct sk_buff *skb, static inline int tcp_minshall_check(const struct tcp_sock *tp) { - return after(tp->snd_sml,tp->snd_una) && + return after(tp->snd_sml, tp->snd_una) && !after(tp->snd_sml, tp->snd_nxt); } @@ -1341,7 +1338,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) /* Defer for less than two clock ticks. */ if (tp->tso_deferred && - ((jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1) + (((u32)jiffies << 1) >> 1) - (tp->tso_deferred >> 1) > 1) goto send_now; in_flight = tcp_packets_in_flight(tp); @@ -1519,10 +1516,15 @@ static int tcp_mtu_probe(struct sock *sk) * send_head. This happens as incoming acks open up the remote * window for us. * + * LARGESEND note: !tcp_urg_mode is overkill, only frames between + * snd_up-64k-mss .. snd_up cannot be large. However, taking into + * account rare use of URG, this is not a big flaw. + * * Returns 1, if no segments are in flight and we have queued segments, but * cannot send anything now because of SWS or another problem. */ -static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) +static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, + int push_one, gfp_t gfp) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -1530,20 +1532,16 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) int cwnd_quota; int result; - /* If we are closed, the bytes will have to remain here. - * In time closedown will finish, we empty the write queue and all - * will be happy. - */ - if (unlikely(sk->sk_state == TCP_CLOSE)) - return 0; - sent_pkts = 0; - /* Do MTU probing. */ - if ((result = tcp_mtu_probe(sk)) == 0) { - return 0; - } else if (result > 0) { - sent_pkts = 1; + if (!push_one) { + /* Do MTU probing. */ + result = tcp_mtu_probe(sk); + if (!result) { + return 0; + } else if (result > 0) { + sent_pkts = 1; + } } while ((skb = tcp_send_head(sk))) { @@ -1565,12 +1563,12 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) nonagle : TCP_NAGLE_PUSH)))) break; } else { - if (tcp_tso_should_defer(sk, skb)) + if (!push_one && tcp_tso_should_defer(sk, skb)) break; } limit = mss_now; - if (tso_segs > 1) + if (tso_segs > 1 && !tcp_urg_mode(tp)) limit = tcp_mss_split_point(sk, skb, mss_now, cwnd_quota); @@ -1580,7 +1578,7 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) TCP_SKB_CB(skb)->when = tcp_time_stamp; - if (unlikely(tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC))) + if (unlikely(tcp_transmit_skb(sk, skb, 1, gfp))) break; /* Advance the send_head. This one is sent out. @@ -1590,6 +1588,9 @@ static int tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle) tcp_minshall_update(tp, mss_now, skb); sent_pkts++; + + if (push_one) + break; } if (likely(sent_pkts)) { @@ -1608,10 +1609,18 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, { struct sk_buff *skb = tcp_send_head(sk); - if (skb) { - if (tcp_write_xmit(sk, cur_mss, nonagle)) - tcp_check_probe_timer(sk); - } + if (!skb) + return; + + /* If we are closed, the bytes will have to remain here. + * In time closedown will finish, we empty the write queue and + * all will be happy. + */ + if (unlikely(sk->sk_state == TCP_CLOSE)) + return; + + if (tcp_write_xmit(sk, cur_mss, nonagle, 0, GFP_ATOMIC)) + tcp_check_probe_timer(sk); } /* Send _single_ skb sitting at the send head. This function requires @@ -1620,36 +1629,10 @@ void __tcp_push_pending_frames(struct sock *sk, unsigned int cur_mss, void tcp_push_one(struct sock *sk, unsigned int mss_now) { struct sk_buff *skb = tcp_send_head(sk); - unsigned int tso_segs, cwnd_quota; BUG_ON(!skb || skb->len < mss_now); - tso_segs = tcp_init_tso_segs(sk, skb, mss_now); - cwnd_quota = tcp_snd_test(sk, skb, mss_now, TCP_NAGLE_PUSH); - - if (likely(cwnd_quota)) { - unsigned int limit; - - BUG_ON(!tso_segs); - - limit = mss_now; - if (tso_segs > 1) - limit = tcp_mss_split_point(sk, skb, mss_now, - cwnd_quota); - - if (skb->len > limit && - unlikely(tso_fragment(sk, skb, limit, mss_now))) - return; - - /* Send it out now. */ - TCP_SKB_CB(skb)->when = tcp_time_stamp; - - if (likely(!tcp_transmit_skb(sk, skb, 1, sk->sk_allocation))) { - tcp_event_new_data_sent(sk, skb); - tcp_cwnd_validate(sk); - return; - } - } + tcp_write_xmit(sk, mss_now, TCP_NAGLE_PUSH, 1, sk->sk_allocation); } /* This function returns the amount that we can raise the @@ -1769,46 +1752,22 @@ u32 __tcp_select_window(struct sock *sk) return window; } -/* Attempt to collapse two adjacent SKB's during retransmission. */ -static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, - int mss_now) +/* Collapses two adjacent SKB's during retransmission. */ +static void tcp_collapse_retrans(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *next_skb = tcp_write_queue_next(sk, skb); int skb_size, next_skb_size; u16 flags; - /* The first test we must make is that neither of these two - * SKB's are still referenced by someone else. - */ - if (skb_cloned(skb) || skb_cloned(next_skb)) - return; - skb_size = skb->len; next_skb_size = next_skb->len; flags = TCP_SKB_CB(skb)->flags; - /* Also punt if next skb has been SACK'd. */ - if (TCP_SKB_CB(next_skb)->sacked & TCPCB_SACKED_ACKED) - return; - - /* Next skb is out of window. */ - if (after(TCP_SKB_CB(next_skb)->end_seq, tcp_wnd_end(tp))) - return; - - /* Punt if not enough space exists in the first SKB for - * the data in the second, or the total combined payload - * would exceed the MSS. - */ - if ((next_skb_size > skb_tailroom(skb)) || - ((skb_size + next_skb_size) > mss_now)) - return; - BUG_ON(tcp_skb_pcount(skb) != 1 || tcp_skb_pcount(next_skb) != 1); tcp_highest_sack_combine(sk, next_skb, skb); - /* Ok. We will be able to collapse the packet. */ tcp_unlink_write_queue(next_skb, sk); skb_copy_from_linear_data(next_skb, skb_put(skb, next_skb_size), @@ -1850,54 +1809,60 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *skb, sk_wmem_free_skb(sk, next_skb); } -/* Do a simple retransmit without using the backoff mechanisms in - * tcp_timer. This is used for path mtu discovery. - * The socket is already locked here. - */ -void tcp_simple_retransmit(struct sock *sk) +static int tcp_can_collapse(struct sock *sk, struct sk_buff *skb) +{ + if (tcp_skb_pcount(skb) > 1) + return 0; + /* TODO: SACK collapsing could be used to remove this condition */ + if (skb_shinfo(skb)->nr_frags != 0) + return 0; + if (skb_cloned(skb)) + return 0; + if (skb == tcp_send_head(sk)) + return 0; + /* Some heurestics for collapsing over SACK'd could be invented */ + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED) + return 0; + + return 1; +} + +static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, + int space) { - const struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - unsigned int mss = tcp_current_mss(sk, 0); - u32 prior_lost = tp->lost_out; + struct sk_buff *skb = to, *tmp; + int first = 1; - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) + if (!sysctl_tcp_retrans_collapse) + return; + if (TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) + return; + + tcp_for_write_queue_from_safe(skb, tmp, sk) { + if (!tcp_can_collapse(sk, skb)) break; - if (skb->len > mss && - !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - } - tcp_skb_mark_lost_uncond_verify(tp, skb); - } - } - tcp_clear_retrans_hints_partial(tp); + space -= skb->len; - if (prior_lost == tp->lost_out) - return; + if (first) { + first = 0; + continue; + } - if (tcp_is_reno(tp)) - tcp_limit_reno_sacked(tp); + if (space < 0) + break; + /* Punt if not enough space exists in the first SKB for + * the data in the second + */ + if (skb->len > skb_tailroom(to)) + break; - tcp_verify_left_out(tp); + if (after(TCP_SKB_CB(skb)->end_seq, tcp_wnd_end(tp))) + break; - /* Don't muck with the congestion window here. - * Reason is that we do not increase amount of _data_ - * in network, but units changed and effective - * cwnd/ssthresh really reduced now. - */ - if (icsk->icsk_ca_state != TCP_CA_Loss) { - tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->prior_ssthresh = 0; - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Loss); + tcp_collapse_retrans(sk, to); } - tcp_xmit_retransmit_queue(sk); } /* This retransmits one SKB. Policy decisions and retransmit queue @@ -1949,17 +1914,7 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) return -ENOMEM; /* We'll try again later. */ } - /* Collapse two adjacent packets if worthwhile and we can. */ - if (!(TCP_SKB_CB(skb)->flags & TCPCB_FLAG_SYN) && - (skb->len < (cur_mss >> 1)) && - (!tcp_skb_is_last(sk, skb)) && - (tcp_write_queue_next(sk, skb) != tcp_send_head(sk)) && - (skb_shinfo(skb)->nr_frags == 0 && - skb_shinfo(tcp_write_queue_next(sk, skb))->nr_frags == 0) && - (tcp_skb_pcount(skb) == 1 && - tcp_skb_pcount(tcp_write_queue_next(sk, skb)) == 1) && - (sysctl_tcp_retrans_collapse != 0)) - tcp_retrans_try_collapse(sk, skb, cur_mss); + tcp_retrans_try_collapse(sk, skb, cur_mss); /* Some Solaris stacks overoptimize and ignore the FIN on a * retransmit when old data is attached. So strip it off diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index 7ddc30f0744f..25524d4e372a 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -153,12 +153,11 @@ static int tcpprobe_sprint(char *tbuf, int n) = ktime_to_timespec(ktime_sub(p->tstamp, tcp_probe.start)); return snprintf(tbuf, n, - "%lu.%09lu " NIPQUAD_FMT ":%u " NIPQUAD_FMT ":%u" - " %d %#x %#x %u %u %u %u\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, - NIPQUAD(p->saddr), ntohs(p->sport), - NIPQUAD(p->daddr), ntohs(p->dport), + &p->saddr, ntohs(p->sport), + &p->daddr, ntohs(p->dport), p->length, p->snd_nxt, p->snd_una, p->snd_cwnd, p->ssthresh, p->snd_wnd, p->srtt); } diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 6b6dff1164b9..0170e914f1b0 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -65,7 +65,7 @@ static void tcp_write_err(struct sock *sk) static int tcp_out_of_resources(struct sock *sk, int do_reset) { struct tcp_sock *tp = tcp_sk(sk); - int orphans = atomic_read(&tcp_orphan_count); + int orphans = percpu_counter_read_positive(&tcp_orphan_count); /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ @@ -171,7 +171,7 @@ static int tcp_write_timeout(struct sock *sk) static void tcp_delack_timer(unsigned long data) { - struct sock *sk = (struct sock*)data; + struct sock *sk = (struct sock *)data; struct tcp_sock *tp = tcp_sk(sk); struct inet_connection_sock *icsk = inet_csk(sk); @@ -299,15 +299,15 @@ static void tcp_retransmit_timer(struct sock *sk) #ifdef TCP_DEBUG struct inet_sock *inet = inet_sk(sk); if (sk->sk_family == AF_INET) { - LIMIT_NETDEBUG(KERN_DEBUG "TCP: Treason uncloaked! Peer " NIPQUAD_FMT ":%u/%u shrinks window %u:%u. Repaired.\n", - NIPQUAD(inet->daddr), ntohs(inet->dport), + LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI4:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", + &inet->daddr, ntohs(inet->dport), inet->num, tp->snd_una, tp->snd_nxt); } #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); - LIMIT_NETDEBUG(KERN_DEBUG "TCP: Treason uncloaked! Peer " NIP6_FMT ":%u/%u shrinks window %u:%u. Repaired.\n", - NIP6(np->daddr), ntohs(inet->dport), + LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", + &np->daddr, ntohs(inet->dport), inet->num, tp->snd_una, tp->snd_nxt); } #endif @@ -396,7 +396,7 @@ out:; static void tcp_write_timer(unsigned long data) { - struct sock *sk = (struct sock*)data; + struct sock *sk = (struct sock *)data; struct inet_connection_sock *icsk = inet_csk(sk); int event; diff --git a/net/ipv4/tcp_vegas.c b/net/ipv4/tcp_vegas.c index 14504dada116..a453aac91bd3 100644 --- a/net/ipv4/tcp_vegas.c +++ b/net/ipv4/tcp_vegas.c @@ -40,18 +40,14 @@ #include "tcp_vegas.h" -/* Default values of the Vegas variables, in fixed-point representation - * with V_PARAM_SHIFT bits to the right of the binary point. - */ -#define V_PARAM_SHIFT 1 -static int alpha = 2<<V_PARAM_SHIFT; -static int beta = 4<<V_PARAM_SHIFT; -static int gamma = 1<<V_PARAM_SHIFT; +static int alpha = 2; +static int beta = 4; +static int gamma = 1; module_param(alpha, int, 0644); -MODULE_PARM_DESC(alpha, "lower bound of packets in network (scale by 2)"); +MODULE_PARM_DESC(alpha, "lower bound of packets in network"); module_param(beta, int, 0644); -MODULE_PARM_DESC(beta, "upper bound of packets in network (scale by 2)"); +MODULE_PARM_DESC(beta, "upper bound of packets in network"); module_param(gamma, int, 0644); MODULE_PARM_DESC(gamma, "limit on increase (scale by 2)"); @@ -172,49 +168,13 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) return; } - /* The key players are v_beg_snd_una and v_beg_snd_nxt. - * - * These are so named because they represent the approximate values - * of snd_una and snd_nxt at the beginning of the current RTT. More - * precisely, they represent the amount of data sent during the RTT. - * At the end of the RTT, when we receive an ACK for v_beg_snd_nxt, - * we will calculate that (v_beg_snd_nxt - v_beg_snd_una) outstanding - * bytes of data have been ACKed during the course of the RTT, giving - * an "actual" rate of: - * - * (v_beg_snd_nxt - v_beg_snd_una) / (rtt duration) - * - * Unfortunately, v_beg_snd_una is not exactly equal to snd_una, - * because delayed ACKs can cover more than one segment, so they - * don't line up nicely with the boundaries of RTTs. - * - * Another unfortunate fact of life is that delayed ACKs delay the - * advance of the left edge of our send window, so that the number - * of bytes we send in an RTT is often less than our cwnd will allow. - * So we keep track of our cwnd separately, in v_beg_snd_cwnd. - */ - if (after(ack, vegas->beg_snd_nxt)) { /* Do the Vegas once-per-RTT cwnd adjustment. */ - u32 old_wnd, old_snd_cwnd; - - - /* Here old_wnd is essentially the window of data that was - * sent during the previous RTT, and has all - * been acknowledged in the course of the RTT that ended - * with the ACK we just received. Likewise, old_snd_cwnd - * is the cwnd during the previous RTT. - */ - old_wnd = (vegas->beg_snd_nxt - vegas->beg_snd_una) / - tp->mss_cache; - old_snd_cwnd = vegas->beg_snd_cwnd; /* Save the extent of the current window so we can use this * at the end of the next RTT. */ - vegas->beg_snd_una = vegas->beg_snd_nxt; vegas->beg_snd_nxt = tp->snd_nxt; - vegas->beg_snd_cwnd = tp->snd_cwnd; /* We do the Vegas calculations only if we got enough RTT * samples that we can be reasonably sure that we got @@ -252,22 +212,14 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) * * This is: * (actual rate in segments) * baseRTT - * We keep it as a fixed point number with - * V_PARAM_SHIFT bits to the right of the binary point. */ - target_cwnd = ((u64)old_wnd * vegas->baseRTT); - target_cwnd <<= V_PARAM_SHIFT; - do_div(target_cwnd, rtt); + target_cwnd = tp->snd_cwnd * vegas->baseRTT / rtt; /* Calculate the difference between the window we had, * and the window we would like to have. This quantity * is the "Diff" from the Arizona Vegas papers. - * - * Again, this is a fixed point number with - * V_PARAM_SHIFT bits to the right of the binary - * point. */ - diff = (old_wnd << V_PARAM_SHIFT) - target_cwnd; + diff = tp->snd_cwnd * (rtt-vegas->baseRTT) / vegas->baseRTT; if (diff > gamma && tp->snd_ssthresh > 2 ) { /* Going too fast. Time to slow down @@ -282,16 +234,13 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) * truncation robs us of full link * utilization. */ - tp->snd_cwnd = min(tp->snd_cwnd, - ((u32)target_cwnd >> - V_PARAM_SHIFT)+1); + tp->snd_cwnd = min(tp->snd_cwnd, (u32)target_cwnd+1); } else if (tp->snd_cwnd <= tp->snd_ssthresh) { /* Slow start. */ tcp_slow_start(tp); } else { /* Congestion avoidance. */ - u32 next_snd_cwnd; /* Figure out where we would like cwnd * to be. @@ -300,32 +249,25 @@ static void tcp_vegas_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) /* The old window was too fast, so * we slow down. */ - next_snd_cwnd = old_snd_cwnd - 1; + tp->snd_cwnd--; } else if (diff < alpha) { /* We don't have enough extra packets * in the network, so speed up. */ - next_snd_cwnd = old_snd_cwnd + 1; + tp->snd_cwnd++; } else { /* Sending just as fast as we * should be. */ - next_snd_cwnd = old_snd_cwnd; } - - /* Adjust cwnd upward or downward, toward the - * desired value. - */ - if (next_snd_cwnd > tp->snd_cwnd) - tp->snd_cwnd++; - else if (next_snd_cwnd < tp->snd_cwnd) - tp->snd_cwnd--; } if (tp->snd_cwnd < 2) tp->snd_cwnd = 2; else if (tp->snd_cwnd > tp->snd_cwnd_clamp) tp->snd_cwnd = tp->snd_cwnd_clamp; + + tp->snd_ssthresh = tcp_current_ssthresh(sk); } /* Wipe the slate clean for the next RTT. */ diff --git a/net/ipv4/tcp_yeah.c b/net/ipv4/tcp_yeah.c index e03b10183a8b..9ec843a9bbb2 100644 --- a/net/ipv4/tcp_yeah.c +++ b/net/ipv4/tcp_yeah.c @@ -83,7 +83,7 @@ static void tcp_yeah_cong_avoid(struct sock *sk, u32 ack, u32 in_flight) else if (!yeah->doing_reno_now) { /* Scalable */ - tp->snd_cwnd_cnt+=yeah->pkts_acked; + tp->snd_cwnd_cnt += yeah->pkts_acked; if (tp->snd_cwnd_cnt > min(tp->snd_cwnd, TCP_SCALABLE_AI_CNT)){ if (tp->snd_cwnd < tp->snd_cwnd_clamp) tp->snd_cwnd++; @@ -224,7 +224,7 @@ static u32 tcp_yeah_ssthresh(struct sock *sk) { reduction = max( reduction, tp->snd_cwnd >> TCP_YEAH_DELTA); } else - reduction = max(tp->snd_cwnd>>1,2U); + reduction = max(tp->snd_cwnd>>1, 2U); yeah->fast_count = 0; yeah->reno_count = max(yeah->reno_count>>1, 2U); diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 98c1fd09be88..cf5ab0581eba 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -81,6 +81,8 @@ #include <asm/uaccess.h> #include <asm/ioctls.h> #include <linux/bootmem.h> +#include <linux/highmem.h> +#include <linux/swap.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> @@ -104,12 +106,8 @@ #include <net/xfrm.h> #include "udp_impl.h" -/* - * Snmp MIB for the UDP layer - */ - -struct hlist_head udp_hash[UDP_HTABLE_SIZE]; -DEFINE_RWLOCK(udp_hash_lock); +struct udp_table udp_table; +EXPORT_SYMBOL(udp_table); int sysctl_udp_mem[3] __read_mostly; int sysctl_udp_rmem_min __read_mostly; @@ -123,15 +121,15 @@ atomic_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); static int udp_lib_lport_inuse(struct net *net, __u16 num, - const struct hlist_head udptable[], + const struct udp_hslot *hslot, struct sock *sk, int (*saddr_comp)(const struct sock *sk1, const struct sock *sk2)) { struct sock *sk2; - struct hlist_node *node; + struct hlist_nulls_node *node; - sk_for_each(sk2, node, &udptable[udp_hashfn(net, num)]) + sk_nulls_for_each(sk2, node, &hslot->head) if (net_eq(sock_net(sk2), net) && sk2 != sk && sk2->sk_hash == num && @@ -154,12 +152,11 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*saddr_comp)(const struct sock *sk1, const struct sock *sk2 ) ) { - struct hlist_head *udptable = sk->sk_prot->h.udp_hash; + struct udp_hslot *hslot; + struct udp_table *udptable = sk->sk_prot->h.udp_table; int error = 1; struct net *net = sock_net(sk); - write_lock_bh(&udp_hash_lock); - if (!snum) { int low, high, remaining; unsigned rand; @@ -171,26 +168,34 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, rand = net_random(); snum = first = rand % remaining + low; rand |= 1; - while (udp_lib_lport_inuse(net, snum, udptable, sk, - saddr_comp)) { + for (;;) { + hslot = &udptable->hash[udp_hashfn(net, snum)]; + spin_lock_bh(&hslot->lock); + if (!udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp)) + break; + spin_unlock_bh(&hslot->lock); do { snum = snum + rand; } while (snum < low || snum > high); if (snum == first) goto fail; } - } else if (udp_lib_lport_inuse(net, snum, udptable, sk, saddr_comp)) - goto fail; - + } else { + hslot = &udptable->hash[udp_hashfn(net, snum)]; + spin_lock_bh(&hslot->lock); + if (udp_lib_lport_inuse(net, snum, hslot, sk, saddr_comp)) + goto fail_unlock; + } inet_sk(sk)->num = snum; sk->sk_hash = snum; if (sk_unhashed(sk)) { - sk_add_node(sk, &udptable[udp_hashfn(net, snum)]); + sk_nulls_add_node_rcu(sk, &hslot->head); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); } error = 0; +fail_unlock: + spin_unlock_bh(&hslot->lock); fail: - write_unlock_bh(&udp_hash_lock); return error; } @@ -208,63 +213,91 @@ int udp_v4_get_port(struct sock *sk, unsigned short snum) return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal); } +static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, + unsigned short hnum, + __be16 sport, __be32 daddr, __be16 dport, int dif) +{ + int score = -1; + + if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && + !ipv6_only_sock(sk)) { + struct inet_sock *inet = inet_sk(sk); + + score = (sk->sk_family == PF_INET ? 1 : 0); + if (inet->rcv_saddr) { + if (inet->rcv_saddr != daddr) + return -1; + score += 2; + } + if (inet->daddr) { + if (inet->daddr != saddr) + return -1; + score += 2; + } + if (inet->dport) { + if (inet->dport != sport) + return -1; + score += 2; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score += 2; + } + } + return score; +} + /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, - int dif, struct hlist_head udptable[]) + int dif, struct udp_table *udptable) { - struct sock *sk, *result = NULL; - struct hlist_node *node; + struct sock *sk, *result; + struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - int badness = -1; - - read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udptable[udp_hashfn(net, hnum)]) { - struct inet_sock *inet = inet_sk(sk); - - if (net_eq(sock_net(sk), net) && sk->sk_hash == hnum && - !ipv6_only_sock(sk)) { - int score = (sk->sk_family == PF_INET ? 1 : 0); - if (inet->rcv_saddr) { - if (inet->rcv_saddr != daddr) - continue; - score+=2; - } - if (inet->daddr) { - if (inet->daddr != saddr) - continue; - score+=2; - } - if (inet->dport) { - if (inet->dport != sport) - continue; - score+=2; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score+=2; - } - if (score == 9) { - result = sk; - break; - } else if (score > badness) { - result = sk; - badness = score; - } + unsigned int hash = udp_hashfn(net, hnum); + struct udp_hslot *hslot = &udptable->hash[hash]; + int score, badness; + + rcu_read_lock(); +begin: + result = NULL; + badness = -1; + sk_nulls_for_each_rcu(sk, node, &hslot->head) { + score = compute_score(sk, net, saddr, hnum, sport, + daddr, dport, dif); + if (score > badness) { + result = sk; + badness = score; } } - if (result) - sock_hold(result); - read_unlock(&udp_hash_lock); + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != hash) + goto begin; + + if (result) { + if (unlikely(!atomic_inc_not_zero(&result->sk_refcnt))) + result = NULL; + else if (unlikely(compute_score(result, net, saddr, hnum, sport, + daddr, dport, dif) < badness)) { + sock_put(result); + goto begin; + } + } + rcu_read_unlock(); return result; } static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, - struct hlist_head udptable[]) + struct udp_table *udptable) { struct sock *sk; const struct iphdr *iph = ip_hdr(skb); @@ -280,7 +313,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif) { - return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, udp_hash); + return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); } EXPORT_SYMBOL_GPL(udp4_lib_lookup); @@ -289,11 +322,11 @@ static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, __be16 rmt_port, __be32 rmt_addr, int dif) { - struct hlist_node *node; + struct hlist_nulls_node *node; struct sock *s = sk; unsigned short hnum = ntohs(loc_port); - sk_for_each_from(s, node) { + sk_nulls_for_each_from(s, node) { struct inet_sock *inet = inet_sk(s); if (!net_eq(sock_net(s), net) || @@ -324,7 +357,7 @@ found: * to find the appropriate port. */ -void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) +void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; struct iphdr *iph = (struct iphdr*)skb->data; @@ -393,7 +426,7 @@ out: void udp_err(struct sk_buff *skb, u32 info) { - __udp4_lib_err(skb, info, udp_hash); + __udp4_lib_err(skb, info, &udp_table); } /* @@ -686,7 +719,7 @@ do_append_data: up->len += ulen; getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; err = ip_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), &ipc, rt, + sizeof(struct udphdr), &ipc, &rt, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_flush_pending_frames(sk); @@ -935,6 +968,23 @@ int udp_disconnect(struct sock *sk, int flags) return 0; } +void udp_lib_unhash(struct sock *sk) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + unsigned int hash = udp_hashfn(sock_net(sk), sk->sk_hash); + struct udp_hslot *hslot = &udptable->hash[hash]; + + spin_lock_bh(&hslot->lock); + if (sk_nulls_del_node_init_rcu(sk)) { + inet_sk(sk)->num = 0; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + } + spin_unlock_bh(&hslot->lock); + } +} +EXPORT_SYMBOL(udp_lib_unhash); + static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int is_udplite = IS_UDPLITE(sk); @@ -1073,13 +1123,14 @@ drop: static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udphdr *uh, __be32 saddr, __be32 daddr, - struct hlist_head udptable[]) + struct udp_table *udptable) { struct sock *sk; + struct udp_hslot *hslot = &udptable->hash[udp_hashfn(net, ntohs(uh->dest))]; int dif; - read_lock(&udp_hash_lock); - sk = sk_head(&udptable[udp_hashfn(net, ntohs(uh->dest))]); + spin_lock(&hslot->lock); + sk = sk_nulls_head(&hslot->head); dif = skb->dev->ifindex; sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); if (sk) { @@ -1088,7 +1139,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, do { struct sk_buff *skb1 = skb; - sknext = udp_v4_mcast_next(net, sk_next(sk), uh->dest, + sknext = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest, daddr, uh->source, saddr, dif); if (sknext) @@ -1105,7 +1156,7 @@ static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, } while (sknext); } else kfree_skb(skb); - read_unlock(&udp_hash_lock); + spin_unlock(&hslot->lock); return 0; } @@ -1151,7 +1202,7 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, * All we need to do is get the socket, and then do a checksum. */ -int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], +int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { struct sock *sk; @@ -1219,13 +1270,13 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], return 0; short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From " NIPQUAD_FMT ":%u %d/%d to " NIPQUAD_FMT ":%u\n", + LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", proto == IPPROTO_UDPLITE ? "-Lite" : "", - NIPQUAD(saddr), + &saddr, ntohs(uh->source), ulen, skb->len, - NIPQUAD(daddr), + &daddr, ntohs(uh->dest)); goto drop; @@ -1234,11 +1285,11 @@ csum_error: * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From " NIPQUAD_FMT ":%u to " NIPQUAD_FMT ":%u ulen %d\n", + LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", proto == IPPROTO_UDPLITE ? "-Lite" : "", - NIPQUAD(saddr), + &saddr, ntohs(uh->source), - NIPQUAD(daddr), + &daddr, ntohs(uh->dest), ulen); drop: @@ -1249,7 +1300,7 @@ drop: int udp_rcv(struct sk_buff *skb) { - return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP); + return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); } void udp_destroy_sock(struct sock *sk) @@ -1491,7 +1542,8 @@ struct proto udp_prot = { .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp_sock), - .h.udp_hash = udp_hash, + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, @@ -1501,20 +1553,23 @@ struct proto udp_prot = { /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS -static struct sock *udp_get_first(struct seq_file *seq) +static struct sock *udp_get_first(struct seq_file *seq, int start) { struct sock *sk; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); - for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { - struct hlist_node *node; - sk_for_each(sk, node, state->hashtable + state->bucket) { + for (state->bucket = start; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { + struct hlist_nulls_node *node; + struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + spin_lock_bh(&hslot->lock); + sk_nulls_for_each(sk, node, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; if (sk->sk_family == state->family) goto found; } + spin_unlock_bh(&hslot->lock); } sk = NULL; found: @@ -1527,21 +1582,19 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) struct net *net = seq_file_net(seq); do { - sk = sk_next(sk); -try_again: - ; + sk = sk_nulls_next(sk); } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); - if (!sk && ++state->bucket < UDP_HTABLE_SIZE) { - sk = sk_head(state->hashtable + state->bucket); - goto try_again; + if (!sk) { + spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); + return udp_get_first(seq, state->bucket + 1); } return sk; } static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) { - struct sock *sk = udp_get_first(seq); + struct sock *sk = udp_get_first(seq, 0); if (sk) while (pos && (sk = udp_get_next(seq, sk)) != NULL) @@ -1550,9 +1603,7 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) } static void *udp_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(udp_hash_lock) { - read_lock(&udp_hash_lock); return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1570,9 +1621,11 @@ static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void udp_seq_stop(struct seq_file *seq, void *v) - __releases(udp_hash_lock) { - read_unlock(&udp_hash_lock); + struct udp_iter_state *state = seq->private; + + if (state->bucket < UDP_HTABLE_SIZE) + spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); } static int udp_seq_open(struct inode *inode, struct file *file) @@ -1588,7 +1641,7 @@ static int udp_seq_open(struct inode *inode, struct file *file) s = ((struct seq_file *)file->private_data)->private; s->family = afinfo->family; - s->hashtable = afinfo->hashtable; + s->udp_table = afinfo->udp_table; return err; } @@ -1660,7 +1713,7 @@ int udp4_seq_show(struct seq_file *seq, void *v) static struct udp_seq_afinfo udp4_seq_afinfo = { .name = "udp", .family = AF_INET, - .hashtable = udp_hash, + .udp_table = &udp_table, .seq_fops = { .owner = THIS_MODULE, }, @@ -1695,16 +1748,28 @@ void udp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ +void __init udp_table_init(struct udp_table *table) +{ + int i; + + for (i = 0; i < UDP_HTABLE_SIZE; i++) { + INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); + spin_lock_init(&table->hash[i].lock); + } +} + void __init udp_init(void) { - unsigned long limit; + unsigned long nr_pages, limit; + udp_table_init(&udp_table); /* Set the pressure threshold up by the same strategy of TCP. It is a * fraction of global memory that is up to 1/2 at 256 MB, decreasing * toward zero with the amount of memory, with a floor of 128 pages. */ - limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_all_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + nr_pages = totalram_pages - totalhigh_pages; + limit = min(nr_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); + limit = (limit * (nr_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; @@ -1715,8 +1780,6 @@ void __init udp_init(void) } EXPORT_SYMBOL(udp_disconnect); -EXPORT_SYMBOL(udp_hash); -EXPORT_SYMBOL(udp_hash_lock); EXPORT_SYMBOL(udp_ioctl); EXPORT_SYMBOL(udp_prot); EXPORT_SYMBOL(udp_sendmsg); diff --git a/net/ipv4/udp_impl.h b/net/ipv4/udp_impl.h index 2e9bad2fa1bc..9f4a6165f722 100644 --- a/net/ipv4/udp_impl.h +++ b/net/ipv4/udp_impl.h @@ -5,8 +5,8 @@ #include <net/protocol.h> #include <net/inet_common.h> -extern int __udp4_lib_rcv(struct sk_buff *, struct hlist_head [], int ); -extern void __udp4_lib_err(struct sk_buff *, u32, struct hlist_head []); +extern int __udp4_lib_rcv(struct sk_buff *, struct udp_table *, int ); +extern void __udp4_lib_err(struct sk_buff *, u32, struct udp_table *); extern int udp_v4_get_port(struct sock *sk, unsigned short snum); diff --git a/net/ipv4/udplite.c b/net/ipv4/udplite.c index 3c807964da96..c784891cb7e5 100644 --- a/net/ipv4/udplite.c +++ b/net/ipv4/udplite.c @@ -12,16 +12,17 @@ */ #include "udp_impl.h" -struct hlist_head udplite_hash[UDP_HTABLE_SIZE]; +struct udp_table udplite_table; +EXPORT_SYMBOL(udplite_table); static int udplite_rcv(struct sk_buff *skb) { - return __udp4_lib_rcv(skb, udplite_hash, IPPROTO_UDPLITE); + return __udp4_lib_rcv(skb, &udplite_table, IPPROTO_UDPLITE); } static void udplite_err(struct sk_buff *skb, u32 info) { - __udp4_lib_err(skb, info, udplite_hash); + __udp4_lib_err(skb, info, &udplite_table); } static struct net_protocol udplite_protocol = { @@ -50,7 +51,8 @@ struct proto udplite_prot = { .unhash = udp_lib_unhash, .get_port = udp_v4_get_port, .obj_size = sizeof(struct udp_sock), - .h.udp_hash = udplite_hash, + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udplite_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, @@ -71,7 +73,7 @@ static struct inet_protosw udplite4_protosw = { static struct udp_seq_afinfo udplite4_seq_afinfo = { .name = "udplite", .family = AF_INET, - .hashtable = udplite_hash, + .udp_table = &udplite_table, .seq_fops = { .owner = THIS_MODULE, }, @@ -108,6 +110,7 @@ static inline int udplite4_proc_init(void) void __init udplite4_register(void) { + udp_table_init(&udplite_table); if (proto_register(&udplite_prot, 1)) goto out_register_err; @@ -126,5 +129,4 @@ out_register_err: printk(KERN_CRIT "%s: Cannot add UDP-Lite protocol.\n", __func__); } -EXPORT_SYMBOL(udplite_hash); EXPORT_SYMBOL(udplite_prot); diff --git a/net/ipv4/xfrm4_input.c b/net/ipv4/xfrm4_input.c index 390dcb1354a5..4ec2162a437e 100644 --- a/net/ipv4/xfrm4_input.c +++ b/net/ipv4/xfrm4_input.c @@ -78,7 +78,6 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) struct udphdr *uh; struct iphdr *iph; int iphlen, len; - int ret; __u8 *udpdata; __be32 *udpdata32; @@ -152,8 +151,7 @@ int xfrm4_udp_encap_rcv(struct sock *sk, struct sk_buff *skb) skb_reset_transport_header(skb); /* process ESP */ - ret = xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, encap_type); - return ret; + return xfrm4_rcv_encap(skb, IPPROTO_ESP, 0, encap_type); drop: kfree_skb(skb); diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index c63de0a72aba..2ad24ba31f9d 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -18,7 +18,8 @@ static struct dst_ops xfrm4_dst_ops; static struct xfrm_policy_afinfo xfrm4_policy_afinfo; -static struct dst_entry *xfrm4_dst_lookup(int tos, xfrm_address_t *saddr, +static struct dst_entry *xfrm4_dst_lookup(struct net *net, int tos, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct flowi fl = { @@ -36,19 +37,20 @@ static struct dst_entry *xfrm4_dst_lookup(int tos, xfrm_address_t *saddr, if (saddr) fl.fl4_src = saddr->a4; - err = __ip_route_output_key(&init_net, &rt, &fl); + err = __ip_route_output_key(net, &rt, &fl); dst = &rt->u.dst; if (err) dst = ERR_PTR(err); return dst; } -static int xfrm4_get_saddr(xfrm_address_t *saddr, xfrm_address_t *daddr) +static int xfrm4_get_saddr(struct net *net, + xfrm_address_t *saddr, xfrm_address_t *daddr) { struct dst_entry *dst; struct rtable *rt; - dst = xfrm4_dst_lookup(0, NULL, daddr); + dst = xfrm4_dst_lookup(net, 0, NULL, daddr); if (IS_ERR(dst)) return -EHOSTUNREACH; @@ -65,7 +67,7 @@ __xfrm4_find_bundle(struct flowi *fl, struct xfrm_policy *policy) read_lock_bh(&policy->lock); for (dst = policy->bundles; dst; dst = dst->next) { - struct xfrm_dst *xdst = (struct xfrm_dst*)dst; + struct xfrm_dst *xdst = (struct xfrm_dst *)dst; if (xdst->u.rt.fl.oif == fl->oif && /*XXX*/ xdst->u.rt.fl.fl4_dst == fl->fl4_dst && xdst->u.rt.fl.fl4_src == fl->fl4_src && @@ -187,7 +189,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) static inline int xfrm4_garbage_collect(struct dst_ops *ops) { - xfrm4_policy_afinfo.garbage_collect(); + xfrm4_policy_afinfo.garbage_collect(&init_net); return (atomic_read(&xfrm4_dst_ops.entries) > xfrm4_dst_ops.gc_thresh*2); } @@ -246,7 +248,6 @@ static struct dst_ops xfrm4_dst_ops = { .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 1024, - .entry_size = sizeof(struct xfrm_dst), .entries = ATOMIC_INIT(0), }; diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 55dc6beab9aa..1ef1366a0a03 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -13,8 +13,6 @@ #include <linux/ipsec.h> #include <linux/netfilter_ipv4.h> -static struct xfrm_state_afinfo xfrm4_state_afinfo; - static int xfrm4_init_flags(struct xfrm_state *x) { if (ipv4_config.no_pmtu_disc) |