diff options
Diffstat (limited to 'net/ipv4')
62 files changed, 2225 insertions, 1561 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 7c3a7d19124..9e95d7fb6d5 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -46,7 +46,7 @@ config IP_ADVANCED_ROUTER rp_filter on use: echo 1 > /proc/sys/net/ipv4/conf/<device>/rp_filter - and + or echo 1 > /proc/sys/net/ipv4/conf/all/rp_filter Note that some distributions enable it in startup scripts. @@ -84,7 +84,7 @@ config IP_FIB_TRIE An experimental study of compression methods for dynamic tries Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. - http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/ + <http://www.csc.kth.se/~snilsson/software/dyntrie2/> endchoice @@ -215,8 +215,15 @@ config NET_IPIP be inserted in and removed from the running kernel whenever you want). Most people won't need this and can say N. +config NET_IPGRE_DEMUX + tristate "IP: GRE demultiplexer" + help + This is helper module to demultiplex GRE packets on GRE version field criteria. + Required by ip_gre and pptp modules. + config NET_IPGRE tristate "IP: GRE tunnels over IP" + depends on (IPV6 || IPV6=n) && NET_IPGRE_DEMUX help Tunneling means encapsulating data of one protocol type within another protocol and sending it over a channel that understands the @@ -412,7 +419,7 @@ config INET_XFRM_MODE_BEET If unsure, say Y. config INET_LRO - bool "Large Receive Offload (ipv4/tcp)" + tristate "Large Receive Offload (ipv4/tcp)" default y ---help--- Support for Large Receive Offload (ipv4/tcp). @@ -555,7 +562,7 @@ config TCP_CONG_VENO distinguishing to circumvent the difficult judgment of the packet loss type. TCP Veno cuts down less congestion window in response to random loss packets. - See http://www.ntu.edu.sg/home5/ZHOU0022/papers/CPFu03a.pdf + See <http://ieeexplore.ieee.org/xpl/freeabs_all.jsp?arnumber=1177186> config TCP_CONG_YEAH tristate "YeAH TCP" diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index 80ff87ce43a..4978d22f9a7 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -20,6 +20,7 @@ obj-$(CONFIG_PROC_FS) += proc.o obj-$(CONFIG_IP_MULTIPLE_TABLES) += fib_rules.o obj-$(CONFIG_IP_MROUTE) += ipmr.o obj-$(CONFIG_NET_IPIP) += ipip.o +obj-$(CONFIG_NET_IPGRE_DEMUX) += gre.o obj-$(CONFIG_NET_IPGRE) += ip_gre.o obj-$(CONFIG_SYN_COOKIES) += syncookies.o obj-$(CONFIG_INET_AH) += ah4.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 6a1100c25a9..f581f77d109 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -227,18 +227,16 @@ EXPORT_SYMBOL(inet_ehash_secret); /* * inet_ehash_secret must be set exactly once - * Instead of using a dedicated spinlock, we (ab)use inetsw_lock */ void build_ehash_secret(void) { u32 rnd; + do { get_random_bytes(&rnd, sizeof(rnd)); } while (rnd == 0); - spin_lock_bh(&inetsw_lock); - if (!inet_ehash_secret) - inet_ehash_secret = rnd; - spin_unlock_bh(&inetsw_lock); + + cmpxchg(&inet_ehash_secret, 0, rnd); } EXPORT_SYMBOL(build_ehash_secret); diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 96c1955b3e2..d8e540c5b07 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -55,7 +55,7 @@ * Stuart Cheshire : Metricom and grat arp fixes * *** FOR 2.1 clean this up *** * Lawrence V. Stefani: (08/12/96) Added FDDI support. - * Alan Cox : Took the AP1000 nasty FDDI hack and + * Alan Cox : Took the AP1000 nasty FDDI hack and * folded into the mainstream FDDI code. * Ack spit, Linus how did you allow that * one in... @@ -120,14 +120,14 @@ EXPORT_SYMBOL(clip_tbl_hook); #endif #include <asm/system.h> -#include <asm/uaccess.h> +#include <linux/uaccess.h> #include <linux/netfilter_arp.h> /* * Interface to generic neighbour cache. */ -static u32 arp_hash(const void *pkey, const struct net_device *dev); +static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 rnd); static int arp_constructor(struct neighbour *neigh); static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb); static void arp_error_report(struct neighbour *neigh, struct sk_buff *skb); @@ -161,7 +161,7 @@ static const struct neigh_ops arp_direct_ops = { .queue_xmit = dev_queue_xmit, }; -const struct neigh_ops arp_broken_ops = { +static const struct neigh_ops arp_broken_ops = { .family = AF_INET, .solicit = arp_solicit, .error_report = arp_error_report, @@ -170,35 +170,34 @@ const struct neigh_ops arp_broken_ops = { .hh_output = dev_queue_xmit, .queue_xmit = dev_queue_xmit, }; -EXPORT_SYMBOL(arp_broken_ops); struct neigh_table arp_tbl = { - .family = AF_INET, - .entry_size = sizeof(struct neighbour) + 4, - .key_len = 4, - .hash = arp_hash, - .constructor = arp_constructor, - .proxy_redo = parp_redo, - .id = "arp_cache", - .parms = { - .tbl = &arp_tbl, - .base_reachable_time = 30 * HZ, - .retrans_time = 1 * HZ, - .gc_staletime = 60 * HZ, - .reachable_time = 30 * HZ, - .delay_probe_time = 5 * HZ, - .queue_len = 3, - .ucast_probes = 3, - .mcast_probes = 3, - .anycast_delay = 1 * HZ, - .proxy_delay = (8 * HZ) / 10, - .proxy_qlen = 64, - .locktime = 1 * HZ, + .family = AF_INET, + .entry_size = sizeof(struct neighbour) + 4, + .key_len = 4, + .hash = arp_hash, + .constructor = arp_constructor, + .proxy_redo = parp_redo, + .id = "arp_cache", + .parms = { + .tbl = &arp_tbl, + .base_reachable_time = 30 * HZ, + .retrans_time = 1 * HZ, + .gc_staletime = 60 * HZ, + .reachable_time = 30 * HZ, + .delay_probe_time = 5 * HZ, + .queue_len = 3, + .ucast_probes = 3, + .mcast_probes = 3, + .anycast_delay = 1 * HZ, + .proxy_delay = (8 * HZ) / 10, + .proxy_qlen = 64, + .locktime = 1 * HZ, }, - .gc_interval = 30 * HZ, - .gc_thresh1 = 128, - .gc_thresh2 = 512, - .gc_thresh3 = 1024, + .gc_interval = 30 * HZ, + .gc_thresh1 = 128, + .gc_thresh2 = 512, + .gc_thresh3 = 1024, }; EXPORT_SYMBOL(arp_tbl); @@ -226,14 +225,16 @@ int arp_mc_map(__be32 addr, u8 *haddr, struct net_device *dev, int dir) } -static u32 arp_hash(const void *pkey, const struct net_device *dev) +static u32 arp_hash(const void *pkey, + const struct net_device *dev, + __u32 hash_rnd) { - return jhash_2words(*(u32 *)pkey, dev->ifindex, arp_tbl.hash_rnd); + return jhash_2words(*(u32 *)pkey, dev->ifindex, hash_rnd); } static int arp_constructor(struct neighbour *neigh) { - __be32 addr = *(__be32*)neigh->primary_key; + __be32 addr = *(__be32 *)neigh->primary_key; struct net_device *dev = neigh->dev; struct in_device *in_dev; struct neigh_parms *parms; @@ -296,16 +297,19 @@ static int arp_constructor(struct neighbour *neigh) neigh->ops = &arp_broken_ops; neigh->output = neigh->ops->output; return 0; +#else + break; #endif - ;} + } #endif if (neigh->type == RTN_MULTICAST) { neigh->nud_state = NUD_NOARP; arp_mc_map(addr, neigh->ha, dev, 1); - } else if (dev->flags&(IFF_NOARP|IFF_LOOPBACK)) { + } else if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->dev_addr, dev->addr_len); - } else if (neigh->type == RTN_BROADCAST || dev->flags&IFF_POINTOPOINT) { + } else if (neigh->type == RTN_BROADCAST || + (dev->flags & IFF_POINTOPOINT)) { neigh->nud_state = NUD_NOARP; memcpy(neigh->ha, dev->broadcast, dev->addr_len); } @@ -315,7 +319,7 @@ static int arp_constructor(struct neighbour *neigh) else neigh->ops = &arp_generic_ops; - if (neigh->nud_state&NUD_VALID) + if (neigh->nud_state & NUD_VALID) neigh->output = neigh->ops->connected_output; else neigh->output = neigh->ops->output; @@ -334,7 +338,7 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) __be32 saddr = 0; u8 *dst_ha = NULL; struct net_device *dev = neigh->dev; - __be32 target = *(__be32*)neigh->primary_key; + __be32 target = *(__be32 *)neigh->primary_key; int probes = atomic_read(&neigh->probes); struct in_device *in_dev; @@ -347,7 +351,8 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) switch (IN_DEV_ARP_ANNOUNCE(in_dev)) { default: case 0: /* By default announce any local IP */ - if (skb && inet_addr_type(dev_net(dev), ip_hdr(skb)->saddr) == RTN_LOCAL) + if (skb && inet_addr_type(dev_net(dev), + ip_hdr(skb)->saddr) == RTN_LOCAL) saddr = ip_hdr(skb)->saddr; break; case 1: /* Restrict announcements of saddr in same subnet */ @@ -369,16 +374,21 @@ static void arp_solicit(struct neighbour *neigh, struct sk_buff *skb) if (!saddr) saddr = inet_select_addr(dev, target, RT_SCOPE_LINK); - if ((probes -= neigh->parms->ucast_probes) < 0) { - if (!(neigh->nud_state&NUD_VALID)) - printk(KERN_DEBUG "trying to ucast probe in NUD_INVALID\n"); + probes -= neigh->parms->ucast_probes; + if (probes < 0) { + if (!(neigh->nud_state & NUD_VALID)) + printk(KERN_DEBUG + "trying to ucast probe in NUD_INVALID\n"); dst_ha = neigh->ha; read_lock_bh(&neigh->lock); - } else if ((probes -= neigh->parms->app_probes) < 0) { + } else { + probes -= neigh->parms->app_probes; + if (probes < 0) { #ifdef CONFIG_ARPD - neigh_app_ns(neigh); + neigh_app_ns(neigh); #endif - return; + return; + } } arp_send(ARPOP_REQUEST, ETH_P_ARP, target, dev, saddr, @@ -451,7 +461,8 @@ static int arp_filter(__be32 sip, __be32 tip, struct net_device *dev) * is allowed to use this function, it is scheduled to be removed. --ANK */ -static int arp_set_predefined(int addr_hint, unsigned char * haddr, __be32 paddr, struct net_device * dev) +static int arp_set_predefined(int addr_hint, unsigned char *haddr, + __be32 paddr, struct net_device *dev) { switch (addr_hint) { case RTN_LOCAL: @@ -483,17 +494,16 @@ int arp_find(unsigned char *haddr, struct sk_buff *skb) paddr = skb_rtable(skb)->rt_gateway; - if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, paddr, dev)) + if (arp_set_predefined(inet_addr_type(dev_net(dev), paddr), haddr, + paddr, dev)) return 0; n = __neigh_lookup(&arp_tbl, &paddr, dev, 1); if (n) { n->used = jiffies; - if (n->nud_state&NUD_VALID || neigh_event_send(n, skb) == 0) { - read_lock_bh(&n->lock); - memcpy(haddr, n->ha, dev->addr_len); - read_unlock_bh(&n->lock); + if (n->nud_state & NUD_VALID || neigh_event_send(n, skb) == 0) { + neigh_ha_snapshot(haddr, n, dev); neigh_release(n); return 0; } @@ -515,13 +525,14 @@ int arp_bind_neighbour(struct dst_entry *dst) return -EINVAL; if (n == NULL) { __be32 nexthop = ((struct rtable *)dst)->rt_gateway; - if (dev->flags&(IFF_LOOPBACK|IFF_POINTOPOINT)) + if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) nexthop = 0; n = __neigh_lookup_errno( #if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) - dev->type == ARPHRD_ATM ? clip_tbl_hook : + dev->type == ARPHRD_ATM ? + clip_tbl_hook : #endif - &arp_tbl, &nexthop, dev); + &arp_tbl, &nexthop, dev); if (IS_ERR(n)) return PTR_ERR(n); dst->neighbour = n; @@ -543,8 +554,8 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, if (!IN_DEV_PROXY_ARP(in_dev)) return 0; - - if ((imi = IN_DEV_MEDIUM_ID(in_dev)) == 0) + imi = IN_DEV_MEDIUM_ID(in_dev); + if (imi == 0) return 1; if (imi == -1) return 0; @@ -555,7 +566,7 @@ static inline int arp_fwd_proxy(struct in_device *in_dev, if (out_dev) omi = IN_DEV_MEDIUM_ID(out_dev); - return (omi != imi && omi != -1); + return omi != imi && omi != -1; } /* @@ -685,7 +696,7 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp->ar_pln = 4; arp->ar_op = htons(type); - arp_ptr=(unsigned char *)(arp+1); + arp_ptr = (unsigned char *)(arp + 1); memcpy(arp_ptr, src_hw, dev->addr_len); arp_ptr += dev->addr_len; @@ -735,9 +746,8 @@ void arp_send(int type, int ptype, __be32 dest_ip, skb = arp_create(type, ptype, dest_ip, dev, src_ip, dest_hw, src_hw, target_hw); - if (skb == NULL) { + if (skb == NULL) return; - } arp_xmit(skb); } @@ -815,7 +825,7 @@ static int arp_process(struct sk_buff *skb) /* * Extract fields */ - arp_ptr= (unsigned char *)(arp+1); + arp_ptr = (unsigned char *)(arp + 1); sha = arp_ptr; arp_ptr += dev->addr_len; memcpy(&sip, arp_ptr, 4); @@ -869,16 +879,17 @@ static int arp_process(struct sk_buff *skb) addr_type = rt->rt_type; if (addr_type == RTN_LOCAL) { - int dont_send = 0; + int dont_send; - if (!dont_send) - dont_send |= arp_ignore(in_dev,sip,tip); + dont_send = arp_ignore(in_dev, sip, tip); if (!dont_send && IN_DEV_ARPFILTER(in_dev)) - dont_send |= arp_filter(sip,tip,dev); + dont_send |= arp_filter(sip, tip, dev); if (!dont_send) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) { - arp_send(ARPOP_REPLY,ETH_P_ARP,sip,dev,tip,sha,dev->dev_addr,sha); + arp_send(ARPOP_REPLY, ETH_P_ARP, sip, + dev, tip, sha, dev->dev_addr, + sha); neigh_release(n); } } @@ -887,8 +898,7 @@ static int arp_process(struct sk_buff *skb) if (addr_type == RTN_UNICAST && (arp_fwd_proxy(in_dev, dev, rt) || arp_fwd_pvlan(in_dev, dev, rt, sip, tip) || - pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) - { + pneigh_lookup(&arp_tbl, net, &tip, dev, 0))) { n = neigh_event_ns(&arp_tbl, sha, &sip, dev); if (n) neigh_release(n); @@ -896,9 +906,12 @@ static int arp_process(struct sk_buff *skb) if (NEIGH_CB(skb)->flags & LOCALLY_ENQUEUED || skb->pkt_type == PACKET_HOST || in_dev->arp_parms->proxy_delay == 0) { - arp_send(ARPOP_REPLY,ETH_P_ARP,sip,dev,tip,sha,dev->dev_addr,sha); + arp_send(ARPOP_REPLY, ETH_P_ARP, sip, + dev, tip, sha, dev->dev_addr, + sha); } else { - pneigh_enqueue(&arp_tbl, in_dev->arp_parms, skb); + pneigh_enqueue(&arp_tbl, + in_dev->arp_parms, skb); return 0; } goto out; @@ -939,7 +952,8 @@ static int arp_process(struct sk_buff *skb) if (arp->ar_op != htons(ARPOP_REPLY) || skb->pkt_type != PACKET_HOST) state = NUD_STALE; - neigh_update(n, sha, state, override ? NEIGH_UPDATE_F_OVERRIDE : 0); + neigh_update(n, sha, state, + override ? NEIGH_UPDATE_F_OVERRIDE : 0); neigh_release(n); } @@ -975,7 +989,8 @@ static int arp_rcv(struct sk_buff *skb, struct net_device *dev, arp->ar_pln != 4) goto freeskb; - if ((skb = skb_share_check(skb, GFP_ATOMIC)) == NULL) + skb = skb_share_check(skb, GFP_ATOMIC); + if (skb == NULL) goto out_of_mem; memset(NEIGH_CB(skb), 0, sizeof(struct neighbour_cb)); @@ -1019,7 +1034,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, return -EINVAL; if (!dev && (r->arp_flags & ATF_COM)) { dev = dev_getbyhwaddr(net, r->arp_ha.sa_family, - r->arp_ha.sa_data); + r->arp_ha.sa_data); if (!dev) return -ENODEV; } @@ -1033,7 +1048,7 @@ static int arp_req_set_public(struct net *net, struct arpreq *r, } static int arp_req_set(struct net *net, struct arpreq *r, - struct net_device * dev) + struct net_device *dev) { __be32 ip; struct neighbour *neigh; @@ -1046,10 +1061,11 @@ static int arp_req_set(struct net *net, struct arpreq *r, if (r->arp_flags & ATF_PERM) r->arp_flags |= ATF_COM; if (dev == NULL) { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip, - .tos = RTO_ONLINK } } }; - struct rtable * rt; - if ((err = ip_route_output_key(net, &rt, &fl)) != 0) + struct flowi fl = { .nl_u.ip4_u = { .daddr = ip, + .tos = RTO_ONLINK } }; + struct rtable *rt; + err = ip_route_output_key(net, &rt, &fl); + if (err != 0) return err; dev = rt->dst.dev; ip_rt_put(rt); @@ -1083,9 +1099,9 @@ static int arp_req_set(struct net *net, struct arpreq *r, unsigned state = NUD_STALE; if (r->arp_flags & ATF_PERM) state = NUD_PERMANENT; - err = neigh_update(neigh, (r->arp_flags&ATF_COM) ? + err = neigh_update(neigh, (r->arp_flags & ATF_COM) ? r->arp_ha.sa_data : NULL, state, - NEIGH_UPDATE_F_OVERRIDE| + NEIGH_UPDATE_F_OVERRIDE | NEIGH_UPDATE_F_ADMIN); neigh_release(neigh); } @@ -1094,12 +1110,12 @@ static int arp_req_set(struct net *net, struct arpreq *r, static unsigned arp_state_to_flags(struct neighbour *neigh) { - unsigned flags = 0; if (neigh->nud_state&NUD_PERMANENT) - flags = ATF_PERM|ATF_COM; + return ATF_PERM | ATF_COM; else if (neigh->nud_state&NUD_VALID) - flags = ATF_COM; - return flags; + return ATF_COM; + else + return 0; } /* @@ -1142,7 +1158,7 @@ static int arp_req_delete_public(struct net *net, struct arpreq *r, } static int arp_req_delete(struct net *net, struct arpreq *r, - struct net_device * dev) + struct net_device *dev) { int err; __be32 ip; @@ -1153,10 +1169,11 @@ static int arp_req_delete(struct net *net, struct arpreq *r, ip = ((struct sockaddr_in *)&r->arp_pa)->sin_addr.s_addr; if (dev == NULL) { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = ip, - .tos = RTO_ONLINK } } }; - struct rtable * rt; - if ((err = ip_route_output_key(net, &rt, &fl)) != 0) + struct flowi fl = { .nl_u.ip4_u = { .daddr = ip, + .tos = RTO_ONLINK } }; + struct rtable *rt; + err = ip_route_output_key(net, &rt, &fl); + if (err != 0) return err; dev = rt->dst.dev; ip_rt_put(rt); @@ -1166,7 +1183,7 @@ static int arp_req_delete(struct net *net, struct arpreq *r, err = -ENXIO; neigh = neigh_lookup(&arp_tbl, &ip, dev); if (neigh) { - if (neigh->nud_state&~NUD_NOARP) + if (neigh->nud_state & ~NUD_NOARP) err = neigh_update(neigh, NULL, NUD_FAILED, NEIGH_UPDATE_F_OVERRIDE| NEIGH_UPDATE_F_ADMIN); @@ -1186,24 +1203,24 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) struct net_device *dev = NULL; switch (cmd) { - case SIOCDARP: - case SIOCSARP: - if (!capable(CAP_NET_ADMIN)) - return -EPERM; - case SIOCGARP: - err = copy_from_user(&r, arg, sizeof(struct arpreq)); - if (err) - return -EFAULT; - break; - default: - return -EINVAL; + case SIOCDARP: + case SIOCSARP: + if (!capable(CAP_NET_ADMIN)) + return -EPERM; + case SIOCGARP: + err = copy_from_user(&r, arg, sizeof(struct arpreq)); + if (err) + return -EFAULT; + break; + default: + return -EINVAL; } if (r.arp_pa.sa_family != AF_INET) return -EPFNOSUPPORT; if (!(r.arp_flags & ATF_PUBL) && - (r.arp_flags & (ATF_NETMASK|ATF_DONTPUB))) + (r.arp_flags & (ATF_NETMASK | ATF_DONTPUB))) return -EINVAL; if (!(r.arp_flags & ATF_NETMASK)) ((struct sockaddr_in *)&r.arp_netmask)->sin_addr.s_addr = @@ -1211,7 +1228,8 @@ int arp_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); if (r.arp_dev[0]) { err = -ENODEV; - if ((dev = __dev_get_by_name(net, r.arp_dev)) == NULL) + dev = __dev_get_by_name(net, r.arp_dev); + if (dev == NULL) goto out; /* Mmmm... It is wrong... ARPHRD_NETROM==0 */ @@ -1243,7 +1261,8 @@ out: return err; } -static int arp_netdev_event(struct notifier_block *this, unsigned long event, void *ptr) +static int arp_netdev_event(struct notifier_block *this, unsigned long event, + void *ptr) { struct net_device *dev = ptr; @@ -1311,12 +1330,13 @@ static char *ax2asc2(ax25_address *a, char *buf) for (n = 0, s = buf; n < 6; n++) { c = (a->ax25_call[n] >> 1) & 0x7F; - if (c != ' ') *s++ = c; + if (c != ' ') + *s++ = c; } *s++ = '-'; - - if ((n = ((a->ax25_call[6] >> 1) & 0x0F)) > 9) { + n = (a->ax25_call[6] >> 1) & 0x0F; + if (n > 9) { *s++ = '1'; n -= 10; } @@ -1325,10 +1345,9 @@ static char *ax2asc2(ax25_address *a, char *buf) *s++ = '\0'; if (*buf == '\0' || *buf == '-') - return "*"; + return "*"; return buf; - } #endif /* CONFIG_AX25 */ @@ -1408,10 +1427,10 @@ static void *arp_seq_start(struct seq_file *seq, loff_t *pos) /* ------------------------------------------------------------------------ */ static const struct seq_operations arp_seq_ops = { - .start = arp_seq_start, - .next = neigh_seq_next, - .stop = neigh_seq_stop, - .show = arp_seq_show, + .start = arp_seq_start, + .next = neigh_seq_next, + .stop = neigh_seq_stop, + .show = arp_seq_show, }; static int arp_seq_open(struct inode *inode, struct file *file) diff --git a/net/ipv4/cipso_ipv4.c b/net/ipv4/cipso_ipv4.c index 3a92a76ae41..094e150c626 100644 --- a/net/ipv4/cipso_ipv4.c +++ b/net/ipv4/cipso_ipv4.c @@ -9,7 +9,7 @@ * * The CIPSO draft specification can be found in the kernel's Documentation * directory as well as the following URL: - * http://netlabel.sourceforge.net/files/draft-ietf-cipso-ipsecurity-01.txt + * http://tools.ietf.org/id/draft-ietf-cipso-ipsecurity-01.txt * The FIPS-188 specification can be found at the following URL: * http://www.itl.nist.gov/fipspubs/fip188.htm * diff --git a/net/ipv4/datagram.c b/net/ipv4/datagram.c index f0550941df7..174be6caa5c 100644 --- a/net/ipv4/datagram.c +++ b/net/ipv4/datagram.c @@ -62,14 +62,17 @@ int ip4_datagram_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len) } if (!inet->inet_saddr) inet->inet_saddr = rt->rt_src; /* Update source address */ - if (!inet->inet_rcv_saddr) + if (!inet->inet_rcv_saddr) { inet->inet_rcv_saddr = rt->rt_src; + if (sk->sk_prot->rehash) + sk->sk_prot->rehash(sk); + } inet->inet_daddr = rt->rt_dst; inet->inet_dport = usin->sin_port; sk->sk_state = TCP_ESTABLISHED; inet->inet_id = jiffies; sk_dst_set(sk, &rt->dst); - return(0); + return 0; } EXPORT_SYMBOL(ip4_datagram_connect); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index da14c49284f..dc94b0316b7 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -209,7 +209,7 @@ static void inetdev_destroy(struct in_device *in_dev) inet_free_ifa(ifa); } - dev->ip_ptr = NULL; + rcu_assign_pointer(dev->ip_ptr, NULL); devinet_sysctl_unregister(in_dev); neigh_parms_release(&arp_tbl, in_dev->arp_parms); @@ -403,6 +403,9 @@ static int inet_set_ifa(struct net_device *dev, struct in_ifaddr *ifa) return inet_insert_ifa(ifa); } +/* Caller must hold RCU or RTNL : + * We dont take a reference on found in_device + */ struct in_device *inetdev_by_index(struct net *net, int ifindex) { struct net_device *dev; @@ -411,7 +414,7 @@ struct in_device *inetdev_by_index(struct net *net, int ifindex) rcu_read_lock(); dev = dev_get_by_index_rcu(net, ifindex); if (dev) - in_dev = in_dev_get(dev); + in_dev = rcu_dereference_rtnl(dev->ip_ptr); rcu_read_unlock(); return in_dev; } @@ -453,8 +456,6 @@ static int inet_rtm_deladdr(struct sk_buff *skb, struct nlmsghdr *nlh, void *arg goto errout; } - __in_dev_put(in_dev); - for (ifap = &in_dev->ifa_list; (ifa = *ifap) != NULL; ifap = &ifa->ifa_next) { if (tb[IFA_LOCAL] && @@ -1059,7 +1060,7 @@ static int inetdev_event(struct notifier_block *this, unsigned long event, switch (event) { case NETDEV_REGISTER: printk(KERN_DEBUG "inetdev_event: bug\n"); - dev->ip_ptr = NULL; + rcu_assign_pointer(dev->ip_ptr, NULL); break; case NETDEV_UP: if (!inetdev_valid_mtu(dev->mtu)) diff --git a/net/ipv4/fib_frontend.c b/net/ipv4/fib_frontend.c index a4396891835..36e27c2107d 100644 --- a/net/ipv4/fib_frontend.c +++ b/net/ipv4/fib_frontend.c @@ -147,35 +147,43 @@ static void fib_flush(struct net *net) rt_cache_flush(net, -1); } -/* - * Find the first device with a given source address. +/** + * __ip_dev_find - find the first device with a given source address. + * @net: the net namespace + * @addr: the source address + * @devref: if true, take a reference on the found device + * + * If a caller uses devref=false, it should be protected by RCU, or RTNL */ - -struct net_device * ip_dev_find(struct net *net, __be32 addr) +struct net_device *__ip_dev_find(struct net *net, __be32 addr, bool devref) { - struct flowi fl = { .nl_u = { .ip4_u = { .daddr = addr } } }; - struct fib_result res; + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = addr + } + }, + .flags = FLOWI_FLAG_MATCH_ANY_IIF + }; + struct fib_result res = { 0 }; struct net_device *dev = NULL; - struct fib_table *local_table; - -#ifdef CONFIG_IP_MULTIPLE_TABLES - res.r = NULL; -#endif - local_table = fib_get_table(net, RT_TABLE_LOCAL); - if (!local_table || fib_table_lookup(local_table, &fl, &res)) + rcu_read_lock(); + if (fib_lookup(net, &fl, &res)) { + rcu_read_unlock(); return NULL; + } if (res.type != RTN_LOCAL) goto out; dev = FIB_RES_DEV(res); - if (dev) + if (dev && devref) dev_hold(dev); out: - fib_res_put(&res); + rcu_read_unlock(); return dev; } -EXPORT_SYMBOL(ip_dev_find); +EXPORT_SYMBOL(__ip_dev_find); /* * Find address type as if only "dev" was present in the system. If @@ -202,11 +210,12 @@ static inline unsigned __inet_dev_addr_type(struct net *net, local_table = fib_get_table(net, RT_TABLE_LOCAL); if (local_table) { ret = RTN_UNICAST; - if (!fib_table_lookup(local_table, &fl, &res)) { + rcu_read_lock(); + if (!fib_table_lookup(local_table, &fl, &res, FIB_LOOKUP_NOREF)) { if (!dev || dev == res.fi->fib_dev) ret = res.type; - fib_res_put(&res); } + rcu_read_unlock(); } return ret; } @@ -220,37 +229,41 @@ EXPORT_SYMBOL(inet_addr_type); unsigned int inet_dev_addr_type(struct net *net, const struct net_device *dev, __be32 addr) { - return __inet_dev_addr_type(net, dev, addr); + return __inet_dev_addr_type(net, dev, addr); } EXPORT_SYMBOL(inet_dev_addr_type); /* Given (packet source, input interface) and optional (dst, oif, tos): - - (main) check, that source is valid i.e. not broadcast or our local - address. - - figure out what "logical" interface this packet arrived - and calculate "specific destination" address. - - check, that packet arrived from expected physical interface. + * - (main) check, that source is valid i.e. not broadcast or our local + * address. + * - figure out what "logical" interface this packet arrived + * and calculate "specific destination" address. + * - check, that packet arrived from expected physical interface. + * called with rcu_read_lock() */ - int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, struct net_device *dev, __be32 *spec_dst, u32 *itag, u32 mark) { struct in_device *in_dev; - struct flowi fl = { .nl_u = { .ip4_u = - { .daddr = src, - .saddr = dst, - .tos = tos } }, - .mark = mark, - .iif = oif }; - + struct flowi fl = { + .nl_u = { + .ip4_u = { + .daddr = src, + .saddr = dst, + .tos = tos + } + }, + .mark = mark, + .iif = oif + }; struct fib_result res; int no_addr, rpf, accept_local; + bool dev_match; int ret; struct net *net; no_addr = rpf = accept_local = 0; - rcu_read_lock(); in_dev = __in_dev_get_rcu(dev); if (in_dev) { no_addr = in_dev->ifa_list == NULL; @@ -259,7 +272,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, if (mark && !IN_DEV_SRC_VMARK(in_dev)) fl.mark = 0; } - rcu_read_unlock(); if (in_dev == NULL) goto e_inval; @@ -269,21 +281,29 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, goto last_resort; if (res.type != RTN_UNICAST) { if (res.type != RTN_LOCAL || !accept_local) - goto e_inval_res; + goto e_inval; } *spec_dst = FIB_RES_PREFSRC(res); fib_combine_itag(itag, &res); + dev_match = false; + #ifdef CONFIG_IP_ROUTE_MULTIPATH - if (FIB_RES_DEV(res) == dev || res.fi->fib_nhs > 1) + for (ret = 0; ret < res.fi->fib_nhs; ret++) { + struct fib_nh *nh = &res.fi->fib_nh[ret]; + + if (nh->nh_dev == dev) { + dev_match = true; + break; + } + } #else if (FIB_RES_DEV(res) == dev) + dev_match = true; #endif - { + if (dev_match) { ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; - fib_res_put(&res); return ret; } - fib_res_put(&res); if (no_addr) goto last_resort; if (rpf == 1) @@ -296,7 +316,6 @@ int fib_validate_source(__be32 src, __be32 dst, u8 tos, int oif, *spec_dst = FIB_RES_PREFSRC(res); ret = FIB_RES_NH(res).nh_scope >= RT_SCOPE_HOST; } - fib_res_put(&res); } return ret; @@ -307,8 +326,6 @@ last_resort: *itag = 0; return 0; -e_inval_res: - fib_res_put(&res); e_inval: return -EINVAL; e_rpf: @@ -461,9 +478,9 @@ static int rtentry_to_fib_config(struct net *net, int cmd, struct rtentry *rt, } /* - * Handle IP routing ioctl calls. These are used to manipulate the routing tables + * Handle IP routing ioctl calls. + * These are used to manipulate the routing tables */ - int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) { struct fib_config cfg; @@ -507,7 +524,7 @@ int ip_rt_ioctl(struct net *net, unsigned int cmd, void __user *arg) return -EINVAL; } -const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { +const struct nla_policy rtm_ipv4_policy[RTA_MAX + 1] = { [RTA_DST] = { .type = NLA_U32 }, [RTA_SRC] = { .type = NLA_U32 }, [RTA_IIF] = { .type = NLA_U32 }, @@ -521,7 +538,7 @@ const struct nla_policy rtm_ipv4_policy[RTA_MAX+1] = { }; static int rtm_to_fib_config(struct net *net, struct sk_buff *skb, - struct nlmsghdr *nlh, struct fib_config *cfg) + struct nlmsghdr *nlh, struct fib_config *cfg) { struct nlattr *attr; int err, remaining; @@ -676,12 +693,11 @@ out: } /* Prepare and feed intra-kernel routing request. - Really, it should be netlink message, but :-( netlink - can be not configured, so that we feed it directly - to fib engine. It is legal, because all events occur - only when netlink is already locked. + * Really, it should be netlink message, but :-( netlink + * can be not configured, so that we feed it directly + * to fib engine. It is legal, because all events occur + * only when netlink is already locked. */ - static void fib_magic(int cmd, int type, __be32 dst, int dst_len, struct in_ifaddr *ifa) { struct net *net = dev_net(ifa->ifa_dev->dev); @@ -727,9 +743,9 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) struct in_ifaddr *prim = ifa; __be32 mask = ifa->ifa_mask; __be32 addr = ifa->ifa_local; - __be32 prefix = ifa->ifa_address&mask; + __be32 prefix = ifa->ifa_address & mask; - if (ifa->ifa_flags&IFA_F_SECONDARY) { + if (ifa->ifa_flags & IFA_F_SECONDARY) { prim = inet_ifa_byprefix(in_dev, prefix, mask); if (prim == NULL) { printk(KERN_WARNING "fib_add_ifaddr: bug: prim == NULL\n"); @@ -739,22 +755,24 @@ void fib_add_ifaddr(struct in_ifaddr *ifa) fib_magic(RTM_NEWROUTE, RTN_LOCAL, addr, 32, prim); - if (!(dev->flags&IFF_UP)) + if (!(dev->flags & IFF_UP)) return; /* Add broadcast address, if it is explicitly assigned. */ if (ifa->ifa_broadcast && ifa->ifa_broadcast != htonl(0xFFFFFFFF)) fib_magic(RTM_NEWROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); - if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags&IFA_F_SECONDARY) && + if (!ipv4_is_zeronet(prefix) && !(ifa->ifa_flags & IFA_F_SECONDARY) && (prefix != addr || ifa->ifa_prefixlen < 32)) { - fib_magic(RTM_NEWROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL : - RTN_UNICAST, prefix, ifa->ifa_prefixlen, prim); + fib_magic(RTM_NEWROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + prefix, ifa->ifa_prefixlen, prim); /* Add network specific broadcasts, when it takes a sense */ if (ifa->ifa_prefixlen < 31) { fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix, 32, prim); - fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix|~mask, 32, prim); + fib_magic(RTM_NEWROUTE, RTN_BROADCAST, prefix | ~mask, + 32, prim); } } } @@ -765,17 +783,18 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) struct net_device *dev = in_dev->dev; struct in_ifaddr *ifa1; struct in_ifaddr *prim = ifa; - __be32 brd = ifa->ifa_address|~ifa->ifa_mask; - __be32 any = ifa->ifa_address&ifa->ifa_mask; + __be32 brd = ifa->ifa_address | ~ifa->ifa_mask; + __be32 any = ifa->ifa_address & ifa->ifa_mask; #define LOCAL_OK 1 #define BRD_OK 2 #define BRD0_OK 4 #define BRD1_OK 8 unsigned ok = 0; - if (!(ifa->ifa_flags&IFA_F_SECONDARY)) - fib_magic(RTM_DELROUTE, dev->flags&IFF_LOOPBACK ? RTN_LOCAL : - RTN_UNICAST, any, ifa->ifa_prefixlen, prim); + if (!(ifa->ifa_flags & IFA_F_SECONDARY)) + fib_magic(RTM_DELROUTE, + dev->flags & IFF_LOOPBACK ? RTN_LOCAL : RTN_UNICAST, + any, ifa->ifa_prefixlen, prim); else { prim = inet_ifa_byprefix(in_dev, any, ifa->ifa_mask); if (prim == NULL) { @@ -785,9 +804,9 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) } /* Deletion is more complicated than add. - We should take care of not to delete too much :-) - - Scan address list to be sure that addresses are really gone. + * We should take care of not to delete too much :-) + * + * Scan address list to be sure that addresses are really gone. */ for (ifa1 = in_dev->ifa_list; ifa1; ifa1 = ifa1->ifa_next) { @@ -801,23 +820,23 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) ok |= BRD0_OK; } - if (!(ok&BRD_OK)) + if (!(ok & BRD_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, ifa->ifa_broadcast, 32, prim); - if (!(ok&BRD1_OK)) + if (!(ok & BRD1_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, brd, 32, prim); - if (!(ok&BRD0_OK)) + if (!(ok & BRD0_OK)) fib_magic(RTM_DELROUTE, RTN_BROADCAST, any, 32, prim); - if (!(ok&LOCAL_OK)) { + if (!(ok & LOCAL_OK)) { fib_magic(RTM_DELROUTE, RTN_LOCAL, ifa->ifa_local, 32, prim); /* Check, that this local address finally disappeared. */ if (inet_addr_type(dev_net(dev), ifa->ifa_local) != RTN_LOCAL) { /* And the last, but not the least thing. - We must flush stray FIB entries. - - First of all, we scan fib_info list searching - for stray nexthop entries, then ignite fib_flush. - */ + * We must flush stray FIB entries. + * + * First of all, we scan fib_info list searching + * for stray nexthop entries, then ignite fib_flush. + */ if (fib_sync_down_addr(dev_net(dev), ifa->ifa_local)) fib_flush(dev_net(dev)); } @@ -828,14 +847,20 @@ static void fib_del_ifaddr(struct in_ifaddr *ifa) #undef BRD1_OK } -static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) +static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb) { struct fib_result res; - struct flowi fl = { .mark = frn->fl_mark, - .nl_u = { .ip4_u = { .daddr = frn->fl_addr, - .tos = frn->fl_tos, - .scope = frn->fl_scope } } }; + struct flowi fl = { + .mark = frn->fl_mark, + .nl_u = { + .ip4_u = { + .daddr = frn->fl_addr, + .tos = frn->fl_tos, + .scope = frn->fl_scope + } + } + }; #ifdef CONFIG_IP_MULTIPLE_TABLES res.r = NULL; @@ -846,15 +871,16 @@ static void nl_fib_lookup(struct fib_result_nl *frn, struct fib_table *tb ) local_bh_disable(); frn->tb_id = tb->tb_id; - frn->err = fib_table_lookup(tb, &fl, &res); + rcu_read_lock(); + frn->err = fib_table_lookup(tb, &fl, &res, FIB_LOOKUP_NOREF); if (!frn->err) { frn->prefixlen = res.prefixlen; frn->nh_sel = res.nh_sel; frn->type = res.type; frn->scope = res.scope; - fib_res_put(&res); } + rcu_read_unlock(); local_bh_enable(); } } @@ -883,8 +909,8 @@ static void nl_fib_input(struct sk_buff *skb) nl_fib_lookup(frn, tb); - pid = NETLINK_CB(skb).pid; /* pid of sending process */ - NETLINK_CB(skb).pid = 0; /* from kernel */ + pid = NETLINK_CB(skb).pid; /* pid of sending process */ + NETLINK_CB(skb).pid = 0; /* from kernel */ NETLINK_CB(skb).dst_group = 0; /* unicast */ netlink_unicast(net->ipv4.fibnl, skb, pid, MSG_DONTWAIT); } @@ -931,7 +957,7 @@ static int fib_inetaddr_event(struct notifier_block *this, unsigned long event, fib_del_ifaddr(ifa); if (ifa->ifa_dev->ifa_list == NULL) { /* Last address was deleted from this interface. - Disable IP. + * Disable IP. */ fib_disable_ip(dev, 1, 0); } else { @@ -990,16 +1016,15 @@ static struct notifier_block fib_netdev_notifier = { static int __net_init ip_fib_net_init(struct net *net) { int err; - unsigned int i; + size_t size = sizeof(struct hlist_head) * FIB_TABLE_HASHSZ; - net->ipv4.fib_table_hash = kzalloc( - sizeof(struct hlist_head)*FIB_TABLE_HASHSZ, GFP_KERNEL); + /* Avoid false sharing : Use at least a full cache line */ + size = max_t(size_t, size, L1_CACHE_BYTES); + + net->ipv4.fib_table_hash = kzalloc(size, GFP_KERNEL); if (net->ipv4.fib_table_hash == NULL) return -ENOMEM; - for (i = 0; i < FIB_TABLE_HASHSZ; i++) - INIT_HLIST_HEAD(&net->ipv4.fib_table_hash[i]); - err = fib4_rules_init(net); if (err < 0) goto fail; diff --git a/net/ipv4/fib_hash.c b/net/ipv4/fib_hash.c index 4ed7e0dea1b..b232375a0b7 100644 --- a/net/ipv4/fib_hash.c +++ b/net/ipv4/fib_hash.c @@ -54,36 +54,37 @@ struct fib_node { struct fib_alias fn_embedded_alias; }; -struct fn_zone { - struct fn_zone *fz_next; /* Next not empty zone */ - struct hlist_head *fz_hash; /* Hash table pointer */ - int fz_nent; /* Number of entries */ +#define EMBEDDED_HASH_SIZE (L1_CACHE_BYTES / sizeof(struct hlist_head)) - int fz_divisor; /* Hash divisor */ +struct fn_zone { + struct fn_zone __rcu *fz_next; /* Next not empty zone */ + struct hlist_head __rcu *fz_hash; /* Hash table pointer */ + seqlock_t fz_lock; u32 fz_hashmask; /* (fz_divisor - 1) */ -#define FZ_HASHMASK(fz) ((fz)->fz_hashmask) - int fz_order; /* Zone order */ - __be32 fz_mask; + u8 fz_order; /* Zone order (0..32) */ + u8 fz_revorder; /* 32 - fz_order */ + __be32 fz_mask; /* inet_make_mask(order) */ #define FZ_MASK(fz) ((fz)->fz_mask) -}; -/* NOTE. On fast computers evaluation of fz_hashmask and fz_mask - * can be cheaper than memory lookup, so that FZ_* macros are used. - */ + struct hlist_head fz_embedded_hash[EMBEDDED_HASH_SIZE]; + + int fz_nent; /* Number of entries */ + int fz_divisor; /* Hash size (mask+1) */ +}; struct fn_hash { - struct fn_zone *fn_zones[33]; - struct fn_zone *fn_zone_list; + struct fn_zone *fn_zones[33]; + struct fn_zone __rcu *fn_zone_list; }; static inline u32 fn_hash(__be32 key, struct fn_zone *fz) { - u32 h = ntohl(key)>>(32 - fz->fz_order); + u32 h = ntohl(key) >> fz->fz_revorder; h ^= (h>>20); h ^= (h>>10); h ^= (h>>5); - h &= FZ_HASHMASK(fz); + h &= fz->fz_hashmask; return h; } @@ -92,7 +93,6 @@ static inline __be32 fz_key(__be32 dst, struct fn_zone *fz) return dst & FZ_MASK(fz); } -static DEFINE_RWLOCK(fib_hash_lock); static unsigned int fib_hash_genid; #define FZ_MAX_DIVISOR ((PAGE_SIZE<<MAX_ORDER) / sizeof(struct hlist_head)) @@ -101,12 +101,11 @@ static struct hlist_head *fz_hash_alloc(int divisor) { unsigned long size = divisor * sizeof(struct hlist_head); - if (size <= PAGE_SIZE) { + if (size <= PAGE_SIZE) return kzalloc(size, GFP_KERNEL); - } else { - return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(size)); - } + + return (struct hlist_head *) + __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(size)); } /* The fib hash lock must be held when this is called. */ @@ -123,10 +122,11 @@ static inline void fn_rebuild_zone(struct fn_zone *fz, hlist_for_each_entry_safe(f, node, n, &old_ht[i], fn_hash) { struct hlist_head *new_head; - hlist_del(&f->fn_hash); + hlist_del_rcu(&f->fn_hash); - new_head = &fz->fz_hash[fn_hash(f->fn_key, fz)]; - hlist_add_head(&f->fn_hash, new_head); + new_head = rcu_dereference_protected(fz->fz_hash, 1) + + fn_hash(f->fn_key, fz); + hlist_add_head_rcu(&f->fn_hash, new_head); } } } @@ -147,14 +147,14 @@ static void fn_rehash_zone(struct fn_zone *fz) int old_divisor, new_divisor; u32 new_hashmask; - old_divisor = fz->fz_divisor; + new_divisor = old_divisor = fz->fz_divisor; switch (old_divisor) { - case 16: - new_divisor = 256; + case EMBEDDED_HASH_SIZE: + new_divisor *= EMBEDDED_HASH_SIZE; break; - case 256: - new_divisor = 1024; + case EMBEDDED_HASH_SIZE*EMBEDDED_HASH_SIZE: + new_divisor *= (EMBEDDED_HASH_SIZE/2); break; default: if ((old_divisor << 1) > FZ_MAX_DIVISOR) { @@ -175,31 +175,55 @@ static void fn_rehash_zone(struct fn_zone *fz) ht = fz_hash_alloc(new_divisor); if (ht) { - write_lock_bh(&fib_hash_lock); - old_ht = fz->fz_hash; - fz->fz_hash = ht; + struct fn_zone nfz; + + memcpy(&nfz, fz, sizeof(nfz)); + + write_seqlock_bh(&fz->fz_lock); + old_ht = rcu_dereference_protected(fz->fz_hash, 1); + RCU_INIT_POINTER(nfz.fz_hash, ht); + nfz.fz_hashmask = new_hashmask; + nfz.fz_divisor = new_divisor; + fn_rebuild_zone(&nfz, old_ht, old_divisor); + fib_hash_genid++; + rcu_assign_pointer(fz->fz_hash, ht); fz->fz_hashmask = new_hashmask; fz->fz_divisor = new_divisor; - fn_rebuild_zone(fz, old_ht, old_divisor); - fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); + write_sequnlock_bh(&fz->fz_lock); - fz_hash_free(old_ht, old_divisor); + if (old_ht != fz->fz_embedded_hash) { + synchronize_rcu(); + fz_hash_free(old_ht, old_divisor); + } } } -static inline void fn_free_node(struct fib_node * f) +static void fn_free_node_rcu(struct rcu_head *head) { + struct fib_node *f = container_of(head, struct fib_node, fn_embedded_alias.rcu); + kmem_cache_free(fn_hash_kmem, f); } +static inline void fn_free_node(struct fib_node *f) +{ + call_rcu(&f->fn_embedded_alias.rcu, fn_free_node_rcu); +} + +static void fn_free_alias_rcu(struct rcu_head *head) +{ + struct fib_alias *fa = container_of(head, struct fib_alias, rcu); + + kmem_cache_free(fn_alias_kmem, fa); +} + static inline void fn_free_alias(struct fib_alias *fa, struct fib_node *f) { fib_release_info(fa->fa_info); if (fa == &f->fn_embedded_alias) fa->fa_info = NULL; else - kmem_cache_free(fn_alias_kmem, fa); + call_rcu(&fa->rcu, fn_free_alias_rcu); } static struct fn_zone * @@ -210,68 +234,71 @@ fn_new_zone(struct fn_hash *table, int z) if (!fz) return NULL; - if (z) { - fz->fz_divisor = 16; - } else { - fz->fz_divisor = 1; - } - fz->fz_hashmask = (fz->fz_divisor - 1); - fz->fz_hash = fz_hash_alloc(fz->fz_divisor); - if (!fz->fz_hash) { - kfree(fz); - return NULL; - } + seqlock_init(&fz->fz_lock); + fz->fz_divisor = z ? EMBEDDED_HASH_SIZE : 1; + fz->fz_hashmask = fz->fz_divisor - 1; + RCU_INIT_POINTER(fz->fz_hash, fz->fz_embedded_hash); fz->fz_order = z; + fz->fz_revorder = 32 - z; fz->fz_mask = inet_make_mask(z); /* Find the first not empty zone with more specific mask */ - for (i=z+1; i<=32; i++) + for (i = z + 1; i <= 32; i++) if (table->fn_zones[i]) break; - write_lock_bh(&fib_hash_lock); - if (i>32) { + if (i > 32) { /* No more specific masks, we are the first. */ - fz->fz_next = table->fn_zone_list; - table->fn_zone_list = fz; + rcu_assign_pointer(fz->fz_next, + rtnl_dereference(table->fn_zone_list)); + rcu_assign_pointer(table->fn_zone_list, fz); } else { - fz->fz_next = table->fn_zones[i]->fz_next; - table->fn_zones[i]->fz_next = fz; + rcu_assign_pointer(fz->fz_next, + rtnl_dereference(table->fn_zones[i]->fz_next)); + rcu_assign_pointer(table->fn_zones[i]->fz_next, fz); } table->fn_zones[z] = fz; fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); return fz; } int fib_table_lookup(struct fib_table *tb, - const struct flowi *flp, struct fib_result *res) + const struct flowi *flp, struct fib_result *res, + int fib_flags) { int err; struct fn_zone *fz; 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) { + rcu_read_lock(); + for (fz = rcu_dereference(t->fn_zone_list); + fz != NULL; + fz = rcu_dereference(fz->fz_next)) { struct hlist_head *head; struct hlist_node *node; struct fib_node *f; - __be32 k = fz_key(flp->fl4_dst, fz); + __be32 k; + unsigned int seq; - head = &fz->fz_hash[fn_hash(k, fz)]; - hlist_for_each_entry(f, node, head, fn_hash) { - if (f->fn_key != k) - continue; + do { + seq = read_seqbegin(&fz->fz_lock); + k = fz_key(flp->fl4_dst, fz); + + head = rcu_dereference(fz->fz_hash) + fn_hash(k, fz); + hlist_for_each_entry_rcu(f, node, head, fn_hash) { + if (f->fn_key != k) + continue; - err = fib_semantic_match(&f->fn_alias, + err = fib_semantic_match(&f->fn_alias, flp, res, - fz->fz_order); - if (err <= 0) - goto out; - } + fz->fz_order, fib_flags); + if (err <= 0) + goto out; + } + } while (read_seqretry(&fz->fz_lock, seq)); } err = 1; out: - read_unlock(&fib_hash_lock); + rcu_read_unlock(); return err; } @@ -285,6 +312,7 @@ void fib_table_select_default(struct fib_table *tb, struct fib_info *last_resort; struct fn_hash *t = (struct fn_hash *)tb->tb_data; struct fn_zone *fz = t->fn_zones[0]; + struct hlist_head *head; if (fz == NULL) return; @@ -293,11 +321,12 @@ void fib_table_select_default(struct fib_table *tb, last_resort = NULL; order = -1; - read_lock(&fib_hash_lock); - hlist_for_each_entry(f, node, &fz->fz_hash[0], fn_hash) { + rcu_read_lock(); + head = rcu_dereference(fz->fz_hash); + hlist_for_each_entry_rcu(f, node, head, fn_hash) { struct fib_alias *fa; - list_for_each_entry(fa, &f->fn_alias, fa_list) { + list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) { struct fib_info *next_fi = fa->fa_info; if (fa->fa_scope != res->scope || @@ -309,7 +338,8 @@ void fib_table_select_default(struct fib_table *tb, if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; - fa->fa_state |= FA_S_ACCESSED; + + fib_alias_accessed(fa); if (fi == NULL) { if (next_fi != res->fi) @@ -341,25 +371,25 @@ void fib_table_select_default(struct fib_table *tb, fib_result_assign(res, last_resort); tb->tb_default = last_idx; out: - read_unlock(&fib_hash_lock); + rcu_read_unlock(); } /* Insert node F to FZ. */ static inline void fib_insert_node(struct fn_zone *fz, struct fib_node *f) { - struct hlist_head *head = &fz->fz_hash[fn_hash(f->fn_key, fz)]; + struct hlist_head *head = rtnl_dereference(fz->fz_hash) + fn_hash(f->fn_key, fz); - hlist_add_head(&f->fn_hash, head); + hlist_add_head_rcu(&f->fn_hash, head); } /* Return the node in FZ matching KEY. */ static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) { - struct hlist_head *head = &fz->fz_hash[fn_hash(key, fz)]; + struct hlist_head *head = rtnl_dereference(fz->fz_hash) + fn_hash(key, fz); struct hlist_node *node; struct fib_node *f; - hlist_for_each_entry(f, node, head, fn_hash) { + hlist_for_each_entry_rcu(f, node, head, fn_hash) { if (f->fn_key == key) return f; } @@ -367,6 +397,17 @@ static struct fib_node *fib_find_node(struct fn_zone *fz, __be32 key) return NULL; } + +static struct fib_alias *fib_fast_alloc(struct fib_node *f) +{ + struct fib_alias *fa = &f->fn_embedded_alias; + + if (fa->fa_info != NULL) + fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); + return fa; +} + +/* Caller must hold RTNL. */ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; @@ -451,7 +492,6 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) } if (cfg->fc_nlflags & NLM_F_REPLACE) { - struct fib_info *fi_drop; u8 state; fa = fa_first; @@ -460,21 +500,25 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) err = 0; goto out; } - write_lock_bh(&fib_hash_lock); - fi_drop = fa->fa_info; - fa->fa_info = fi; - fa->fa_type = cfg->fc_type; - fa->fa_scope = cfg->fc_scope; + err = -ENOBUFS; + new_fa = fib_fast_alloc(f); + if (new_fa == NULL) + goto out; + + new_fa->fa_tos = fa->fa_tos; + new_fa->fa_info = fi; + new_fa->fa_type = cfg->fc_type; + new_fa->fa_scope = cfg->fc_scope; state = fa->fa_state; - fa->fa_state &= ~FA_S_ACCESSED; + new_fa->fa_state = state & ~FA_S_ACCESSED; fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); + list_replace_rcu(&fa->fa_list, &new_fa->fa_list); - fib_release_info(fi_drop); + fn_free_alias(fa, f); if (state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); - rtmsg_fib(RTM_NEWROUTE, key, fa, cfg->fc_dst_len, tb->tb_id, - &cfg->fc_nlinfo, NLM_F_REPLACE); + rtmsg_fib(RTM_NEWROUTE, key, new_fa, cfg->fc_dst_len, + tb->tb_id, &cfg->fc_nlinfo, NLM_F_REPLACE); return 0; } @@ -506,12 +550,10 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) f = new_f; } - new_fa = &f->fn_embedded_alias; - if (new_fa->fa_info != NULL) { - new_fa = kmem_cache_alloc(fn_alias_kmem, GFP_KERNEL); - if (new_fa == NULL) - goto out; - } + new_fa = fib_fast_alloc(f); + if (new_fa == NULL) + goto out; + new_fa->fa_info = fi; new_fa->fa_tos = tos; new_fa->fa_type = cfg->fc_type; @@ -522,13 +564,11 @@ int fib_table_insert(struct fib_table *tb, struct fib_config *cfg) * Insert new entry to the list. */ - write_lock_bh(&fib_hash_lock); if (new_f) fib_insert_node(fz, new_f); - list_add_tail(&new_fa->fa_list, + list_add_tail_rcu(&new_fa->fa_list, (fa ? &fa->fa_list : &f->fn_alias)); fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); if (new_f) fz->fz_nent++; @@ -603,14 +643,12 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) tb->tb_id, &cfg->fc_nlinfo, 0); kill_fn = 0; - write_lock_bh(&fib_hash_lock); - list_del(&fa->fa_list); + list_del_rcu(&fa->fa_list); if (list_empty(&f->fn_alias)) { - hlist_del(&f->fn_hash); + hlist_del_rcu(&f->fn_hash); kill_fn = 1; } fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); if (fa->fa_state & FA_S_ACCESSED) rt_cache_flush(cfg->fc_nlinfo.nl_net, -1); @@ -627,7 +665,7 @@ int fib_table_delete(struct fib_table *tb, struct fib_config *cfg) static int fn_flush_list(struct fn_zone *fz, int idx) { - struct hlist_head *head = &fz->fz_hash[idx]; + struct hlist_head *head = rtnl_dereference(fz->fz_hash) + idx; struct hlist_node *node, *n; struct fib_node *f; int found = 0; @@ -641,14 +679,12 @@ static int fn_flush_list(struct fn_zone *fz, int idx) struct fib_info *fi = fa->fa_info; if (fi && (fi->fib_flags&RTNH_F_DEAD)) { - write_lock_bh(&fib_hash_lock); - list_del(&fa->fa_list); + list_del_rcu(&fa->fa_list); if (list_empty(&f->fn_alias)) { - hlist_del(&f->fn_hash); + hlist_del_rcu(&f->fn_hash); kill_f = 1; } fib_hash_genid++; - write_unlock_bh(&fib_hash_lock); fn_free_alias(fa, f); found++; @@ -662,13 +698,16 @@ static int fn_flush_list(struct fn_zone *fz, int idx) return found; } +/* caller must hold RTNL. */ int fib_table_flush(struct fib_table *tb) { struct fn_hash *table = (struct fn_hash *) tb->tb_data; struct fn_zone *fz; int found = 0; - for (fz = table->fn_zone_list; fz; fz = fz->fz_next) { + for (fz = rtnl_dereference(table->fn_zone_list); + fz != NULL; + fz = rtnl_dereference(fz->fz_next)) { int i; for (i = fz->fz_divisor - 1; i >= 0; i--) @@ -690,10 +729,10 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, s_i = cb->args[4]; i = 0; - hlist_for_each_entry(f, node, head, fn_hash) { + hlist_for_each_entry_rcu(f, node, head, fn_hash) { struct fib_alias *fa; - list_for_each_entry(fa, &f->fn_alias, fa_list) { + list_for_each_entry_rcu(fa, &f->fn_alias, fa_list) { if (i < s_i) goto next; @@ -711,7 +750,7 @@ fn_hash_dump_bucket(struct sk_buff *skb, struct netlink_callback *cb, cb->args[4] = i; return -1; } - next: +next: i++; } } @@ -725,14 +764,15 @@ fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, struct fn_zone *fz) { int h, s_h; + struct hlist_head *head = rcu_dereference(fz->fz_hash); - if (fz->fz_hash == NULL) + if (head == NULL) return skb->len; s_h = cb->args[3]; for (h = s_h; h < fz->fz_divisor; h++) { - if (hlist_empty(&fz->fz_hash[h])) + if (hlist_empty(head + h)) continue; - if (fn_hash_dump_bucket(skb, cb, tb, fz, &fz->fz_hash[h]) < 0) { + if (fn_hash_dump_bucket(skb, cb, tb, fz, head + h) < 0) { cb->args[3] = h; return -1; } @@ -746,23 +786,26 @@ fn_hash_dump_zone(struct sk_buff *skb, struct netlink_callback *cb, int fib_table_dump(struct fib_table *tb, struct sk_buff *skb, struct netlink_callback *cb) { - int m, s_m; + int m = 0, s_m; struct fn_zone *fz; struct fn_hash *table = (struct fn_hash *)tb->tb_data; s_m = cb->args[2]; - read_lock(&fib_hash_lock); - for (fz = table->fn_zone_list, m=0; fz; fz = fz->fz_next, m++) { - if (m < s_m) continue; + rcu_read_lock(); + for (fz = rcu_dereference(table->fn_zone_list); + fz != NULL; + fz = rcu_dereference(fz->fz_next), m++) { + if (m < s_m) + continue; if (fn_hash_dump_zone(skb, cb, tb, fz) < 0) { cb->args[2] = m; - read_unlock(&fib_hash_lock); + rcu_read_unlock(); return -1; } memset(&cb->args[3], 0, sizeof(cb->args) - 3*sizeof(cb->args[0])); } - read_unlock(&fib_hash_lock); + rcu_read_unlock(); cb->args[2] = m; return skb->len; } @@ -825,14 +868,15 @@ static struct fib_alias *fib_get_first(struct seq_file *seq) iter->genid = fib_hash_genid; iter->valid = 1; - for (iter->zone = table->fn_zone_list; iter->zone; - iter->zone = iter->zone->fz_next) { + for (iter->zone = rcu_dereference(table->fn_zone_list); + iter->zone != NULL; + iter->zone = rcu_dereference(iter->zone->fz_next)) { int maxslot; if (!iter->zone->fz_nent) continue; - iter->hash_head = iter->zone->fz_hash; + iter->hash_head = rcu_dereference(iter->zone->fz_hash); maxslot = iter->zone->fz_divisor; for (iter->bucket = 0; iter->bucket < maxslot; @@ -911,13 +955,13 @@ static struct fib_alias *fib_get_next(struct seq_file *seq) } } - iter->zone = iter->zone->fz_next; + iter->zone = rcu_dereference(iter->zone->fz_next); if (!iter->zone) goto out; iter->bucket = 0; - iter->hash_head = iter->zone->fz_hash; + iter->hash_head = rcu_dereference(iter->zone->fz_hash); hlist_for_each_entry(fn, node, iter->hash_head, fn_hash) { list_for_each_entry(fa, &fn->fn_alias, fa_list) { @@ -950,11 +994,11 @@ static struct fib_alias *fib_get_idx(struct seq_file *seq, loff_t pos) } static void *fib_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(fib_hash_lock) + __acquires(RCU) { void *v = NULL; - read_lock(&fib_hash_lock); + rcu_read_lock(); if (fib_get_table(seq_file_net(seq), RT_TABLE_MAIN)) v = *pos ? fib_get_idx(seq, *pos - 1) : SEQ_START_TOKEN; return v; @@ -967,15 +1011,16 @@ static void *fib_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void fib_seq_stop(struct seq_file *seq, void *v) - __releases(fib_hash_lock) + __releases(RCU) { - read_unlock(&fib_hash_lock); + rcu_read_unlock(); } static unsigned fib_flag_trans(int type, __be32 mask, struct fib_info *fi) { static const unsigned type2flags[RTN_MAX + 1] = { - [7] = RTF_REJECT, [8] = RTF_REJECT, + [7] = RTF_REJECT, + [8] = RTF_REJECT, }; unsigned flags = type2flags[type]; diff --git a/net/ipv4/fib_lookup.h b/net/ipv4/fib_lookup.h index 637b133973b..a29edf2219c 100644 --- a/net/ipv4/fib_lookup.h +++ b/net/ipv4/fib_lookup.h @@ -12,17 +12,22 @@ struct fib_alias { u8 fa_type; u8 fa_scope; u8 fa_state; -#ifdef CONFIG_IP_FIB_TRIE struct rcu_head rcu; -#endif }; #define FA_S_ACCESSED 0x01 +/* Dont write on fa_state unless needed, to keep it shared on all cpus */ +static inline void fib_alias_accessed(struct fib_alias *fa) +{ + if (!(fa->fa_state & FA_S_ACCESSED)) + fa->fa_state |= FA_S_ACCESSED; +} + /* Exported by fib_semantics.c */ extern int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, int prefixlen); + struct fib_result *res, int prefixlen, int fib_flags); extern void fib_release_info(struct fib_info *); extern struct fib_info *fib_create_info(struct fib_config *cfg); extern int fib_nh_match(struct fib_config *cfg, struct fib_info *fi); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 76daeb5ff56..7981a24f5c7 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -6,7 +6,7 @@ * IPv4 Forwarding Information Base: policy rules. * * Authors: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> - * Thomas Graf <tgraf@suug.ch> + * Thomas Graf <tgraf@suug.ch> * * This program is free software; you can redistribute it and/or * modify it under the terms of the GNU General Public License @@ -14,7 +14,7 @@ * 2 of the License, or (at your option) any later version. * * Fixes: - * Rani Assaf : local_rule cannot be deleted + * Rani Assaf : local_rule cannot be deleted * Marc Boucher : routing by fwmark */ @@ -32,8 +32,7 @@ #include <net/ip_fib.h> #include <net/fib_rules.h> -struct fib4_rule -{ +struct fib4_rule { struct fib_rule common; u8 dst_len; u8 src_len; @@ -58,6 +57,7 @@ int fib_lookup(struct net *net, struct flowi *flp, struct fib_result *res) { struct fib_lookup_arg arg = { .result = res, + .flags = FIB_LOOKUP_NOREF, }; int err; @@ -91,10 +91,11 @@ static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, goto errout; } - if ((tbl = fib_get_table(rule->fr_net, rule->table)) == NULL) + tbl = fib_get_table(rule->fr_net, rule->table); + if (!tbl) goto errout; - err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result); + err = fib_table_lookup(tbl, flp, (struct fib_result *) arg->result, arg->flags); if (err > 0) err = -EAGAIN; errout: diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index 20f09c5b31e..3e0da3ef611 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -60,21 +60,30 @@ static struct hlist_head fib_info_devhash[DEVINDEX_HASHSIZE]; static DEFINE_SPINLOCK(fib_multipath_lock); -#define for_nexthops(fi) { int nhsel; const struct fib_nh * nh; \ -for (nhsel=0, nh = (fi)->fib_nh; nhsel < (fi)->fib_nhs; nh++, nhsel++) - -#define change_nexthops(fi) { int nhsel; struct fib_nh *nexthop_nh; \ -for (nhsel=0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); nhsel < (fi)->fib_nhs; nexthop_nh++, nhsel++) +#define for_nexthops(fi) { \ + int nhsel; const struct fib_nh *nh; \ + for (nhsel = 0, nh = (fi)->fib_nh; \ + nhsel < (fi)->fib_nhs; \ + nh++, nhsel++) + +#define change_nexthops(fi) { \ + int nhsel; struct fib_nh *nexthop_nh; \ + for (nhsel = 0, nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ + nhsel < (fi)->fib_nhs; \ + nexthop_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; \ -for (nhsel=0; nhsel < 1; nhsel++) +#define for_nexthops(fi) { \ + int nhsel; const struct fib_nh *nh = (fi)->fib_nh; \ + for (nhsel = 0; nhsel < 1; nhsel++) -#define change_nexthops(fi) { int nhsel = 0; struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ -for (nhsel=0; nhsel < 1; nhsel++) +#define change_nexthops(fi) { \ + int nhsel; \ + struct fib_nh *nexthop_nh = (struct fib_nh *)((fi)->fib_nh); \ + for (nhsel = 0; nhsel < 1; nhsel++) #endif /* CONFIG_IP_ROUTE_MULTIPATH */ @@ -86,63 +95,70 @@ static const struct int error; u8 scope; } fib_props[RTN_MAX + 1] = { - { + [RTN_UNSPEC] = { .error = 0, .scope = RT_SCOPE_NOWHERE, - }, /* RTN_UNSPEC */ - { + }, + [RTN_UNICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_UNICAST */ - { + }, + [RTN_LOCAL] = { .error = 0, .scope = RT_SCOPE_HOST, - }, /* RTN_LOCAL */ - { + }, + [RTN_BROADCAST] = { .error = 0, .scope = RT_SCOPE_LINK, - }, /* RTN_BROADCAST */ - { + }, + [RTN_ANYCAST] = { .error = 0, .scope = RT_SCOPE_LINK, - }, /* RTN_ANYCAST */ - { + }, + [RTN_MULTICAST] = { .error = 0, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_MULTICAST */ - { + }, + [RTN_BLACKHOLE] = { .error = -EINVAL, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_BLACKHOLE */ - { + }, + [RTN_UNREACHABLE] = { .error = -EHOSTUNREACH, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_UNREACHABLE */ - { + }, + [RTN_PROHIBIT] = { .error = -EACCES, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_PROHIBIT */ - { + }, + [RTN_THROW] = { .error = -EAGAIN, .scope = RT_SCOPE_UNIVERSE, - }, /* RTN_THROW */ - { + }, + [RTN_NAT] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE, - }, /* RTN_NAT */ - { + }, + [RTN_XRESOLVE] = { .error = -EINVAL, .scope = RT_SCOPE_NOWHERE, - }, /* RTN_XRESOLVE */ + }, }; /* Release a nexthop info record */ +static void free_fib_info_rcu(struct rcu_head *head) +{ + struct fib_info *fi = container_of(head, struct fib_info, rcu); + + kfree(fi); +} + void free_fib_info(struct fib_info *fi) { if (fi->fib_dead == 0) { - printk(KERN_WARNING "Freeing alive fib_info %p\n", fi); + pr_warning("Freeing alive fib_info %p\n", fi); return; } change_nexthops(fi) { @@ -152,7 +168,7 @@ void free_fib_info(struct fib_info *fi) } endfor_nexthops(fi); fib_info_cnt--; release_net(fi->fib_net); - kfree(fi); + call_rcu(&fi->rcu, free_fib_info_rcu); } void fib_release_info(struct fib_info *fi) @@ -173,7 +189,7 @@ void fib_release_info(struct fib_info *fi) spin_unlock_bh(&fib_info_lock); } -static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) +static inline int nh_comp(const struct fib_info *fi, const struct fib_info *ofi) { const struct fib_nh *onh = ofi->fib_nh; @@ -187,7 +203,7 @@ static __inline__ int nh_comp(const struct fib_info *fi, const struct fib_info * #ifdef CONFIG_NET_CLS_ROUTE nh->nh_tclassid != onh->nh_tclassid || #endif - ((nh->nh_flags^onh->nh_flags)&~RTNH_F_DEAD)) + ((nh->nh_flags ^ onh->nh_flags) & ~RTNH_F_DEAD)) return -1; onh++; } endfor_nexthops(fi); @@ -238,7 +254,7 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) nfi->fib_priority == fi->fib_priority && memcmp(nfi->fib_metrics, fi->fib_metrics, sizeof(fi->fib_metrics)) == 0 && - ((nfi->fib_flags^fi->fib_flags)&~RTNH_F_DEAD) == 0 && + ((nfi->fib_flags ^ fi->fib_flags) & ~RTNH_F_DEAD) == 0 && (nfi->fib_nhs == 0 || nh_comp(fi, nfi) == 0)) return fi; } @@ -247,9 +263,8 @@ static struct fib_info *fib_find_info(const struct fib_info *nfi) } /* Check, that the gateway is already configured. - Used only by redirect accept routine. + * Used only by redirect accept routine. */ - int ip_fib_check_default(__be32 gw, struct net_device *dev) { struct hlist_head *head; @@ -264,7 +279,7 @@ int ip_fib_check_default(__be32 gw, struct net_device *dev) hlist_for_each_entry(nh, node, head, nh_hash) { if (nh->nh_dev == dev && nh->nh_gw == gw && - !(nh->nh_flags&RTNH_F_DEAD)) { + !(nh->nh_flags & RTNH_F_DEAD)) { spin_unlock(&fib_info_lock); return 0; } @@ -362,10 +377,10 @@ int fib_detect_death(struct fib_info *fi, int order, } if (state == NUD_REACHABLE) return 0; - if ((state&NUD_VALID) && order != dflt) + if ((state & NUD_VALID) && order != dflt) return 0; - if ((state&NUD_VALID) || - (*last_idx<0 && order > dflt)) { + if ((state & NUD_VALID) || + (*last_idx < 0 && order > dflt)) { *last_resort = fi; *last_idx = order; } @@ -476,75 +491,76 @@ int fib_nh_match(struct fib_config *cfg, struct fib_info *fi) /* - Picture - ------- - - Semantics of nexthop is very messy by historical reasons. - We have to take into account, that: - a) gateway can be actually local interface address, - so that gatewayed route is direct. - b) gateway must be on-link address, possibly - described not by an ifaddr, but also by a direct route. - c) If both gateway and interface are specified, they should not - contradict. - d) If we use tunnel routes, gateway could be not on-link. - - Attempt to reconcile all of these (alas, self-contradictory) conditions - results in pretty ugly and hairy code with obscure logic. - - I chose to generalized it instead, so that the size - of code does not increase practically, but it becomes - much more general. - Every prefix is assigned a "scope" value: "host" is local address, - "link" is direct route, - [ ... "site" ... "interior" ... ] - and "universe" is true gateway route with global meaning. - - Every prefix refers to a set of "nexthop"s (gw, oif), - where gw must have narrower scope. This recursion stops - when gw has LOCAL scope or if "nexthop" is declared ONLINK, - which means that gw is forced to be on link. - - Code is still hairy, but now it is apparently logically - consistent and very flexible. F.e. as by-product it allows - to co-exists in peace independent exterior and interior - routing processes. - - Normally it looks as following. - - {universe prefix} -> (gw, oif) [scope link] - | - |-> {link prefix} -> (gw, oif) [scope local] - | - |-> {local prefix} (terminal node) + * Picture + * ------- + * + * Semantics of nexthop is very messy by historical reasons. + * We have to take into account, that: + * a) gateway can be actually local interface address, + * so that gatewayed route is direct. + * b) gateway must be on-link address, possibly + * described not by an ifaddr, but also by a direct route. + * c) If both gateway and interface are specified, they should not + * contradict. + * d) If we use tunnel routes, gateway could be not on-link. + * + * Attempt to reconcile all of these (alas, self-contradictory) conditions + * results in pretty ugly and hairy code with obscure logic. + * + * I chose to generalized it instead, so that the size + * of code does not increase practically, but it becomes + * much more general. + * Every prefix is assigned a "scope" value: "host" is local address, + * "link" is direct route, + * [ ... "site" ... "interior" ... ] + * and "universe" is true gateway route with global meaning. + * + * Every prefix refers to a set of "nexthop"s (gw, oif), + * where gw must have narrower scope. This recursion stops + * when gw has LOCAL scope or if "nexthop" is declared ONLINK, + * which means that gw is forced to be on link. + * + * Code is still hairy, but now it is apparently logically + * consistent and very flexible. F.e. as by-product it allows + * to co-exists in peace independent exterior and interior + * routing processes. + * + * Normally it looks as following. + * + * {universe prefix} -> (gw, oif) [scope link] + * | + * |-> {link prefix} -> (gw, oif) [scope local] + * | + * |-> {local prefix} (terminal node) */ - static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, struct fib_nh *nh) { int err; struct net *net; + struct net_device *dev; net = cfg->fc_nlinfo.nl_net; if (nh->nh_gw) { struct fib_result res; - if (nh->nh_flags&RTNH_F_ONLINK) { - struct net_device *dev; + if (nh->nh_flags & RTNH_F_ONLINK) { if (cfg->fc_scope >= RT_SCOPE_LINK) return -EINVAL; if (inet_addr_type(net, nh->nh_gw) != RTN_UNICAST) return -EINVAL; - if ((dev = __dev_get_by_index(net, nh->nh_oif)) == NULL) + dev = __dev_get_by_index(net, nh->nh_oif); + if (!dev) return -ENODEV; - if (!(dev->flags&IFF_UP)) + if (!(dev->flags & IFF_UP)) return -ENETDOWN; nh->nh_dev = dev; dev_hold(dev); nh->nh_scope = RT_SCOPE_LINK; return 0; } + rcu_read_lock(); { struct flowi fl = { .nl_u = { @@ -559,50 +575,53 @@ static int fib_check_nh(struct fib_config *cfg, struct fib_info *fi, /* It is not necessary, but requires a bit of thinking */ if (fl.fl4_scope < RT_SCOPE_LINK) fl.fl4_scope = RT_SCOPE_LINK; - if ((err = fib_lookup(net, &fl, &res)) != 0) + err = fib_lookup(net, &fl, &res); + if (err) { + rcu_read_unlock(); return err; + } } err = -EINVAL; if (res.type != RTN_UNICAST && res.type != RTN_LOCAL) goto out; nh->nh_scope = res.scope; nh->nh_oif = FIB_RES_OIF(res); - if ((nh->nh_dev = FIB_RES_DEV(res)) == NULL) + nh->nh_dev = dev = FIB_RES_DEV(res); + if (!dev) goto out; - dev_hold(nh->nh_dev); - err = -ENETDOWN; - if (!(nh->nh_dev->flags & IFF_UP)) - goto out; - err = 0; -out: - fib_res_put(&res); - return err; + dev_hold(dev); + err = (dev->flags & IFF_UP) ? 0 : -ENETDOWN; } else { struct in_device *in_dev; - if (nh->nh_flags&(RTNH_F_PERVASIVE|RTNH_F_ONLINK)) + if (nh->nh_flags & (RTNH_F_PERVASIVE | RTNH_F_ONLINK)) return -EINVAL; + rcu_read_lock(); + err = -ENODEV; in_dev = inetdev_by_index(net, nh->nh_oif); if (in_dev == NULL) - return -ENODEV; - if (!(in_dev->dev->flags&IFF_UP)) { - in_dev_put(in_dev); - return -ENETDOWN; - } + goto out; + err = -ENETDOWN; + if (!(in_dev->dev->flags & IFF_UP)) + goto out; nh->nh_dev = in_dev->dev; dev_hold(nh->nh_dev); nh->nh_scope = RT_SCOPE_HOST; - in_dev_put(in_dev); + err = 0; } - return 0; +out: + rcu_read_unlock(); + return err; } static inline unsigned int fib_laddr_hashfn(__be32 val) { unsigned int mask = (fib_hash_size - 1); - return ((__force u32)val ^ ((__force u32)val >> 7) ^ ((__force u32)val >> 14)) & mask; + return ((__force u32)val ^ + ((__force u32)val >> 7) ^ + ((__force u32)val >> 14)) & mask; } static struct hlist_head *fib_hash_alloc(int bytes) @@ -611,7 +630,8 @@ static struct hlist_head *fib_hash_alloc(int bytes) return kzalloc(bytes, GFP_KERNEL); else return (struct hlist_head *) - __get_free_pages(GFP_KERNEL | __GFP_ZERO, get_order(bytes)); + __get_free_pages(GFP_KERNEL | __GFP_ZERO, + get_order(bytes)); } static void fib_hash_free(struct hlist_head *hash, int bytes) @@ -806,7 +826,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) goto failure; } else { change_nexthops(fi) { - if ((err = fib_check_nh(cfg, fi, nexthop_nh)) != 0) + err = fib_check_nh(cfg, fi, nexthop_nh); + if (err != 0) goto failure; } endfor_nexthops(fi) } @@ -819,7 +840,8 @@ struct fib_info *fib_create_info(struct fib_config *cfg) } link_it: - if ((ofi = fib_find_info(fi)) != NULL) { + ofi = fib_find_info(fi); + if (ofi) { fi->fib_dead = 1; free_fib_info(fi); ofi->fib_treeref++; @@ -864,7 +886,7 @@ failure: /* Note! fib_semantic_match intentionally uses RCU list functions. */ int fib_semantic_match(struct list_head *head, const struct flowi *flp, - struct fib_result *res, int prefixlen) + struct fib_result *res, int prefixlen, int fib_flags) { struct fib_alias *fa; int nh_sel = 0; @@ -879,7 +901,7 @@ int fib_semantic_match(struct list_head *head, const struct flowi *flp, if (fa->fa_scope < flp->fl4_scope) continue; - fa->fa_state |= FA_S_ACCESSED; + fib_alias_accessed(fa); err = fib_props[fa->fa_type].error; if (err == 0) { @@ -895,7 +917,7 @@ int fib_semantic_match(struct list_head *head, const struct flowi *flp, case RTN_ANYCAST: case RTN_MULTICAST: for_nexthops(fi) { - if (nh->nh_flags&RTNH_F_DEAD) + if (nh->nh_flags & RTNH_F_DEAD) continue; if (!flp->oif || flp->oif == nh->nh_oif) break; @@ -906,16 +928,15 @@ int fib_semantic_match(struct list_head *head, const struct flowi *flp, goto out_fill_res; } #else - if (nhsel < 1) { + if (nhsel < 1) goto out_fill_res; - } #endif endfor_nexthops(fi); continue; default: - printk(KERN_WARNING "fib_semantic_match bad type %#x\n", - fa->fa_type); + pr_warning("fib_semantic_match bad type %#x\n", + fa->fa_type); return -EINVAL; } } @@ -929,7 +950,8 @@ out_fill_res: res->type = fa->fa_type; res->scope = fa->fa_scope; res->fi = fa->fa_info; - atomic_inc(&res->fi->fib_clntref); + if (!(fib_flags & FIB_LOOKUP_NOREF)) + atomic_inc(&res->fi->fib_clntref); return 0; } @@ -1028,10 +1050,10 @@ nla_put_failure: } /* - Update FIB if: - - local address disappeared -> we must delete all the entries - referring to it. - - device went down -> we must shutdown all nexthops going via it. + * Update FIB if: + * - local address disappeared -> we must delete all the entries + * referring to it. + * - device went down -> we must shutdown all nexthops going via it. */ int fib_sync_down_addr(struct net *net, __be32 local) { @@ -1078,7 +1100,7 @@ int fib_sync_down_dev(struct net_device *dev, int force) prev_fi = fi; dead = 0; change_nexthops(fi) { - if (nexthop_nh->nh_flags&RTNH_F_DEAD) + if (nexthop_nh->nh_flags & RTNH_F_DEAD) dead++; else if (nexthop_nh->nh_dev == dev && nexthop_nh->nh_scope != scope) { @@ -1110,10 +1132,9 @@ int fib_sync_down_dev(struct net_device *dev, int force) #ifdef CONFIG_IP_ROUTE_MULTIPATH /* - Dead device goes up. We wake up dead nexthops. - It takes sense only on multipath routes. + * Dead device goes up. We wake up dead nexthops. + * It takes sense only on multipath routes. */ - int fib_sync_up(struct net_device *dev) { struct fib_info *prev_fi; @@ -1123,7 +1144,7 @@ int fib_sync_up(struct net_device *dev) struct fib_nh *nh; int ret; - if (!(dev->flags&IFF_UP)) + if (!(dev->flags & IFF_UP)) return 0; prev_fi = NULL; @@ -1142,12 +1163,12 @@ int fib_sync_up(struct net_device *dev) prev_fi = fi; alive = 0; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { + if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) { alive++; continue; } if (nexthop_nh->nh_dev == NULL || - !(nexthop_nh->nh_dev->flags&IFF_UP)) + !(nexthop_nh->nh_dev->flags & IFF_UP)) continue; if (nexthop_nh->nh_dev != dev || !__in_dev_get_rtnl(dev)) @@ -1169,10 +1190,9 @@ int fib_sync_up(struct net_device *dev) } /* - The algorithm is suboptimal, but it provides really - fair weighted route distribution. + * The algorithm is suboptimal, but it provides really + * fair weighted route distribution. */ - void fib_select_multipath(const struct flowi *flp, struct fib_result *res) { struct fib_info *fi = res->fi; @@ -1182,7 +1202,7 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) if (fi->fib_power <= 0) { int power = 0; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags&RTNH_F_DEAD)) { + if (!(nexthop_nh->nh_flags & RTNH_F_DEAD)) { power += nexthop_nh->nh_weight; nexthop_nh->nh_power = nexthop_nh->nh_weight; } @@ -1198,15 +1218,16 @@ void fib_select_multipath(const struct flowi *flp, struct fib_result *res) /* w should be random number [0..fi->fib_power-1], - it is pretty bad approximation. + * it is pretty bad approximation. */ w = jiffies % fi->fib_power; change_nexthops(fi) { - if (!(nexthop_nh->nh_flags&RTNH_F_DEAD) && + if (!(nexthop_nh->nh_flags & RTNH_F_DEAD) && nexthop_nh->nh_power) { - if ((w -= nexthop_nh->nh_power) <= 0) { + w -= nexthop_nh->nh_power; + if (w <= 0) { nexthop_nh->nh_power--; fi->fib_power--; res->nh_sel = nhsel; diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 79d057a939b..b1445089510 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -16,7 +16,7 @@ * * An experimental study of compression methods for dynamic tries * Stefan Nilsson and Matti Tikkanen. Algorithmica, 33(1):19-33, 2002. - * http://www.nada.kth.se/~snilsson/public/papers/dyntrie2/ + * http://www.csc.kth.se/~snilsson/software/dyntrie2/ * * * IP-address lookup using LC-tries. Stefan Nilsson and Gunnar Karlsson @@ -186,7 +186,7 @@ static inline struct tnode *node_parent_rcu(struct node *node) { struct tnode *ret = node_parent(node); - return rcu_dereference(ret); + return rcu_dereference_rtnl(ret); } /* Same as rcu_assign_pointer @@ -209,9 +209,7 @@ static inline struct node *tnode_get_child_rcu(struct tnode *tn, unsigned int i) { struct node *ret = tnode_get_child(tn, i); - return rcu_dereference_check(ret, - rcu_read_lock_held() || - lockdep_rtnl_is_held()); + return rcu_dereference_rtnl(ret); } static inline int tnode_child_length(const struct tnode *tn) @@ -457,8 +455,8 @@ static struct tnode *tnode_new(t_key key, int pos, int bits) tn->empty_children = 1<<bits; } - pr_debug("AT %p s=%u %lu\n", tn, (unsigned int) sizeof(struct tnode), - (unsigned long) (sizeof(struct node) << bits)); + pr_debug("AT %p s=%zu %zu\n", tn, sizeof(struct tnode), + sizeof(struct node) << bits); return tn; } @@ -607,11 +605,10 @@ static struct node *resize(struct trie *t, struct tnode *tn) /* Keep root node larger */ - if (!node_parent((struct node*) tn)) { + if (!node_parent((struct node *)tn)) { inflate_threshold_use = inflate_threshold_root; halve_threshold_use = halve_threshold_root; - } - else { + } else { inflate_threshold_use = inflate_threshold; halve_threshold_use = halve_threshold; } @@ -637,7 +634,7 @@ static struct node *resize(struct trie *t, struct tnode *tn) check_tnode(tn); /* Return if at least one inflate is run */ - if( max_work != MAX_WORK) + if (max_work != MAX_WORK) return (struct node *) tn; /* @@ -964,9 +961,7 @@ fib_find_node(struct trie *t, u32 key) struct node *n; pos = 0; - n = rcu_dereference_check(t->trie, - rcu_read_lock_held() || - lockdep_rtnl_is_held()); + n = rcu_dereference_rtnl(t->trie); while (n != NULL && NODE_TYPE(n) == T_TNODE) { tn = (struct tnode *) n; @@ -1347,7 +1342,7 @@ err: /* should be called with rcu_read_lock */ static int check_leaf(struct trie *t, struct leaf *l, t_key key, const struct flowi *flp, - struct fib_result *res) + struct fib_result *res, int fib_flags) { struct leaf_info *li; struct hlist_head *hhead = &l->list; @@ -1361,7 +1356,7 @@ static int check_leaf(struct trie *t, struct leaf *l, if (l->key != (key & ntohl(mask))) continue; - err = fib_semantic_match(&li->falh, flp, res, plen); + err = fib_semantic_match(&li->falh, flp, res, plen, fib_flags); #ifdef CONFIG_IP_FIB_TRIE_STATS if (err <= 0) @@ -1377,7 +1372,7 @@ static int check_leaf(struct trie *t, struct leaf *l, } int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, - struct fib_result *res) + struct fib_result *res, int fib_flags) { struct trie *t = (struct trie *) tb->tb_data; int ret; @@ -1389,8 +1384,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, t_key cindex = 0; int current_prefix_length = KEYLENGTH; struct tnode *cn; - t_key node_prefix, key_prefix, pref_mismatch; - int mp; + t_key pref_mismatch; rcu_read_lock(); @@ -1404,7 +1398,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, /* Just a leaf? */ if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res); + ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); goto found; } @@ -1429,7 +1423,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, } if (IS_LEAF(n)) { - ret = check_leaf(t, (struct leaf *)n, key, flp, res); + ret = check_leaf(t, (struct leaf *)n, key, flp, res, fib_flags); if (ret > 0) goto backtrace; goto found; @@ -1505,10 +1499,7 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, * matching prefix. */ - node_prefix = mask_pfx(cn->key, cn->pos); - key_prefix = mask_pfx(key, cn->pos); - pref_mismatch = key_prefix^node_prefix; - mp = 0; + pref_mismatch = mask_pfx(cn->key ^ key, cn->pos); /* * In short: If skipped bits in this node do not match @@ -1516,13 +1507,9 @@ int fib_table_lookup(struct fib_table *tb, const struct flowi *flp, * state.directly. */ if (pref_mismatch) { - while (!(pref_mismatch & (1<<(KEYLENGTH-1)))) { - mp++; - pref_mismatch = pref_mismatch << 1; - } - key_prefix = tkey_extract_bits(cn->key, mp, cn->pos-mp); + int mp = KEYLENGTH - fls(pref_mismatch); - if (key_prefix != 0) + if (tkey_extract_bits(cn->key, mp, cn->pos - mp) != 0) goto backtrace; if (current_prefix_length >= cn->pos) @@ -1746,14 +1733,14 @@ static struct leaf *leaf_walk_rcu(struct tnode *p, struct node *c) /* Node empty, walk back up to parent */ c = (struct node *) p; - } while ( (p = node_parent_rcu(c)) != NULL); + } while ((p = node_parent_rcu(c)) != NULL); return NULL; /* Root of trie */ } static struct leaf *trie_firstleaf(struct trie *t) { - struct tnode *n = (struct tnode *) rcu_dereference(t->trie); + struct tnode *n = (struct tnode *)rcu_dereference_rtnl(t->trie); if (!n) return NULL; @@ -1851,7 +1838,8 @@ void fib_table_select_default(struct fib_table *tb, if (!next_fi->fib_nh[0].nh_gw || next_fi->fib_nh[0].nh_scope != RT_SCOPE_LINK) continue; - fa->fa_state |= FA_S_ACCESSED; + + fib_alias_accessed(fa); if (fi == NULL) { if (next_fi != res->fi) @@ -2039,14 +2027,14 @@ struct fib_trie_iter { struct seq_net_private p; struct fib_table *tb; struct tnode *tnode; - unsigned index; - unsigned depth; + unsigned int index; + unsigned int depth; }; static struct node *fib_trie_get_next(struct fib_trie_iter *iter) { struct tnode *tn = iter->tnode; - unsigned cindex = iter->index; + unsigned int cindex = iter->index; struct tnode *p; /* A single entry routing table */ @@ -2155,7 +2143,7 @@ static void trie_collect_stats(struct trie *t, struct trie_stat *s) */ static void trie_show_stats(struct seq_file *seq, struct trie_stat *stat) { - unsigned i, max, pointers, bytes, avdepth; + unsigned int i, max, pointers, bytes, avdepth; if (stat->leaves) avdepth = stat->totdepth*100 / stat->leaves; @@ -2352,7 +2340,8 @@ static void fib_trie_seq_stop(struct seq_file *seq, void *v) static void seq_indent(struct seq_file *seq, int n) { - while (n-- > 0) seq_puts(seq, " "); + while (n-- > 0) + seq_puts(seq, " "); } static inline const char *rtn_scope(char *buf, size_t len, enum rt_scope_t s) @@ -2384,7 +2373,7 @@ static const char *const rtn_type_names[__RTN_MAX] = { [RTN_XRESOLVE] = "XRESOLVE", }; -static inline const char *rtn_type(char *buf, size_t len, unsigned t) +static inline const char *rtn_type(char *buf, size_t len, unsigned int t) { if (t < __RTN_MAX && rtn_type_names[t]) return rtn_type_names[t]; @@ -2540,13 +2529,12 @@ static void fib_route_seq_stop(struct seq_file *seq, void *v) rcu_read_unlock(); } -static unsigned fib_flag_trans(int type, __be32 mask, const struct fib_info *fi) +static unsigned int fib_flag_trans(int type, __be32 mask, const struct fib_info *fi) { - static unsigned type2flags[RTN_MAX + 1] = { - [7] = RTF_REJECT, [8] = RTF_REJECT, - }; - unsigned flags = type2flags[type]; + unsigned int flags = 0; + if (type == RTN_UNREACHABLE || type == RTN_PROHIBIT) + flags = RTF_REJECT; if (fi && fi->fib_nh->nh_gw) flags |= RTF_GATEWAY; if (mask == htonl(0xFFFFFFFF)) @@ -2558,7 +2546,7 @@ static unsigned fib_flag_trans(int type, __be32 mask, const struct fib_info *fi) /* * This outputs /proc/net/route. * The format of the file is not supposed to be changed - * and needs to be same as fib_hash output to avoid breaking + * and needs to be same as fib_hash output to avoid breaking * legacy utilities */ static int fib_route_seq_show(struct seq_file *seq, void *v) @@ -2583,7 +2571,7 @@ static int fib_route_seq_show(struct seq_file *seq, void *v) list_for_each_entry_rcu(fa, &li->falh, fa_list) { const struct fib_info *fi = fa->fa_info; - unsigned flags = fib_flag_trans(fa->fa_type, mask, fi); + unsigned int flags = fib_flag_trans(fa->fa_type, mask, fi); int len; if (fa->fa_type == RTN_BROADCAST diff --git a/net/ipv4/gre.c b/net/ipv4/gre.c new file mode 100644 index 00000000000..c6933f2ea31 --- /dev/null +++ b/net/ipv4/gre.c @@ -0,0 +1,152 @@ +/* + * GRE over IPv4 demultiplexer driver + * + * Authors: Dmitry Kozlov (xeb@mail.ru) + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + * + */ + +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/kmod.h> +#include <linux/skbuff.h> +#include <linux/in.h> +#include <linux/netdevice.h> +#include <linux/version.h> +#include <linux/spinlock.h> +#include <net/protocol.h> +#include <net/gre.h> + + +static const struct gre_protocol __rcu *gre_proto[GREPROTO_MAX] __read_mostly; +static DEFINE_SPINLOCK(gre_proto_lock); + +int gre_add_protocol(const struct gre_protocol *proto, u8 version) +{ + if (version >= GREPROTO_MAX) + goto err_out; + + spin_lock(&gre_proto_lock); + if (gre_proto[version]) + goto err_out_unlock; + + rcu_assign_pointer(gre_proto[version], proto); + spin_unlock(&gre_proto_lock); + return 0; + +err_out_unlock: + spin_unlock(&gre_proto_lock); +err_out: + return -1; +} +EXPORT_SYMBOL_GPL(gre_add_protocol); + +int gre_del_protocol(const struct gre_protocol *proto, u8 version) +{ + if (version >= GREPROTO_MAX) + goto err_out; + + spin_lock(&gre_proto_lock); + if (rcu_dereference_protected(gre_proto[version], + lockdep_is_held(&gre_proto_lock)) != proto) + goto err_out_unlock; + rcu_assign_pointer(gre_proto[version], NULL); + spin_unlock(&gre_proto_lock); + synchronize_rcu(); + return 0; + +err_out_unlock: + spin_unlock(&gre_proto_lock); +err_out: + return -1; +} +EXPORT_SYMBOL_GPL(gre_del_protocol); + +static int gre_rcv(struct sk_buff *skb) +{ + const struct gre_protocol *proto; + u8 ver; + int ret; + + if (!pskb_may_pull(skb, 12)) + goto drop; + + ver = skb->data[1]&0x7f; + if (ver >= GREPROTO_MAX) + goto drop; + + rcu_read_lock(); + proto = rcu_dereference(gre_proto[ver]); + if (!proto || !proto->handler) + goto drop_unlock; + ret = proto->handler(skb); + rcu_read_unlock(); + return ret; + +drop_unlock: + rcu_read_unlock(); +drop: + kfree_skb(skb); + return NET_RX_DROP; +} + +static void gre_err(struct sk_buff *skb, u32 info) +{ + const struct gre_protocol *proto; + u8 ver; + + if (!pskb_may_pull(skb, 12)) + goto drop; + + ver = skb->data[1]&0x7f; + if (ver >= GREPROTO_MAX) + goto drop; + + rcu_read_lock(); + proto = rcu_dereference(gre_proto[ver]); + if (!proto || !proto->err_handler) + goto drop_unlock; + proto->err_handler(skb, info); + rcu_read_unlock(); + return; + +drop_unlock: + rcu_read_unlock(); +drop: + kfree_skb(skb); +} + +static const struct net_protocol net_gre_protocol = { + .handler = gre_rcv, + .err_handler = gre_err, + .netns_ok = 1, +}; + +static int __init gre_init(void) +{ + pr_info("GRE over IPv4 demultiplexor driver"); + + if (inet_add_protocol(&net_gre_protocol, IPPROTO_GRE) < 0) { + pr_err("gre: can't add protocol\n"); + return -EAGAIN; + } + + return 0; +} + +static void __exit gre_exit(void) +{ + inet_del_protocol(&net_gre_protocol, IPPROTO_GRE); +} + +module_init(gre_init); +module_exit(gre_exit); + +MODULE_DESCRIPTION("GRE over IPv4 demultiplexer driver"); +MODULE_AUTHOR("D. Kozlov (xeb@mail.ru)"); +MODULE_LICENSE("GPL"); + diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index a0d847c7cba..96bc7f9475a 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -379,7 +379,7 @@ static void icmp_reply(struct icmp_bxm *icmp_param, struct sk_buff *skb) inet->tos = ip_hdr(skb)->tos; daddr = ipc.addr = rt->rt_src; ipc.opt = NULL; - ipc.shtx.flags = 0; + ipc.tx_flags = 0; if (icmp_param->replyopts.optlen) { ipc.opt = &icmp_param->replyopts; if (ipc.opt->srr) @@ -538,7 +538,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) inet_sk(sk)->tos = tos; ipc.addr = iph->saddr; ipc.opt = &icmp_param.replyopts; - ipc.shtx.flags = 0; + ipc.tx_flags = 0; { struct flowi fl = { diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index a1ad0e7180d..c8877c6c721 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -856,6 +856,18 @@ static void igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb, igmpv3_clear_delrec(in_dev); } else if (len < 12) { return; /* ignore bogus packet; freed by caller */ + } else if (IGMP_V1_SEEN(in_dev)) { + /* This is a v3 query with v1 queriers present */ + max_delay = IGMP_Query_Response_Interval; + group = 0; + } else if (IGMP_V2_SEEN(in_dev)) { + /* this is a v3 query with v2 queriers present; + * Interpretation of the max_delay code is problematic here. + * A real v2 host would use ih_code directly, while v3 has a + * different encoding. We use the v3 encoding as more likely + * to be intended in a v3 query. + */ + max_delay = IGMPV3_MRC(ih3->code)*(HZ/IGMP_TIMER_SCALE); } else { /* v3 */ if (!pskb_may_pull(skb, sizeof(struct igmpv3_query))) return; @@ -1257,14 +1269,14 @@ void ip_mc_rejoin_group(struct ip_mc_list *im) if (im->multiaddr == IGMP_ALL_HOSTS) return; - if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev)) { - igmp_mod_timer(im, IGMP_Initial_Report_Delay); - return; - } - /* else, v3 */ - im->crcount = in_dev->mr_qrv ? in_dev->mr_qrv : - IGMP_Unsolicited_Report_Count; - igmp_ifc_event(in_dev); + /* a failover is happening and switches + * must be notified immediately */ + if (IGMP_V1_SEEN(in_dev)) + igmp_send_report(in_dev, im, IGMP_HOST_MEMBERSHIP_REPORT); + else if (IGMP_V2_SEEN(in_dev)) + igmp_send_report(in_dev, im, IGMPV2_HOST_MEMBERSHIP_REPORT); + else + igmp_send_report(in_dev, im, IGMPV3_HOST_MEMBERSHIP_REPORT); #endif } EXPORT_SYMBOL(ip_mc_rejoin_group); @@ -1406,6 +1418,7 @@ void ip_mc_destroy_dev(struct in_device *in_dev) write_unlock_bh(&in_dev->mc_list_lock); } +/* RTNL is locked */ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) { struct flowi fl = { .nl_u = { .ip4_u = @@ -1416,15 +1429,12 @@ static struct in_device *ip_mc_find_dev(struct net *net, struct ip_mreqn *imr) if (imr->imr_ifindex) { idev = inetdev_by_index(net, imr->imr_ifindex); - if (idev) - __in_dev_put(idev); return idev; } if (imr->imr_address.s_addr) { - dev = ip_dev_find(net, imr->imr_address.s_addr); + dev = __ip_dev_find(net, imr->imr_address.s_addr, false); if (!dev) return NULL; - dev_put(dev); } if (!dev && !ip_route_output_key(net, &rt, &fl)) { diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index e5fa2ddce32..ba804266584 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -425,7 +425,7 @@ static int inet_diag_bc_run(const void *bc, int len, bc += op->no; } } - return (len == 0); + return len == 0; } static int valid_cc(const void *bc, int len, int cc) diff --git a/net/ipv4/inet_hashtables.c b/net/ipv4/inet_hashtables.c index fb7ad5a21ff..1b344f30b46 100644 --- a/net/ipv4/inet_hashtables.c +++ b/net/ipv4/inet_hashtables.c @@ -101,19 +101,43 @@ void inet_put_port(struct sock *sk) } EXPORT_SYMBOL(inet_put_port); -void __inet_inherit_port(struct sock *sk, struct sock *child) +int __inet_inherit_port(struct sock *sk, struct sock *child) { struct inet_hashinfo *table = sk->sk_prot->h.hashinfo; - const int bhash = inet_bhashfn(sock_net(sk), inet_sk(child)->inet_num, + unsigned short port = inet_sk(child)->inet_num; + const int bhash = inet_bhashfn(sock_net(sk), port, table->bhash_size); struct inet_bind_hashbucket *head = &table->bhash[bhash]; struct inet_bind_bucket *tb; spin_lock(&head->lock); tb = inet_csk(sk)->icsk_bind_hash; + if (tb->port != port) { + /* NOTE: using tproxy and redirecting skbs to a proxy + * on a different listener port breaks the assumption + * that the listener socket's icsk_bind_hash is the same + * as that of the child socket. We have to look up or + * create a new bind bucket for the child here. */ + struct hlist_node *node; + inet_bind_bucket_for_each(tb, node, &head->chain) { + if (net_eq(ib_net(tb), sock_net(sk)) && + tb->port == port) + break; + } + if (!node) { + tb = inet_bind_bucket_create(table->bind_bucket_cachep, + sock_net(sk), head, port); + if (!tb) { + spin_unlock(&head->lock); + return -ENOMEM; + } + } + } sk_add_bind_node(child, &tb->owners); inet_csk(child)->icsk_bind_hash = tb; spin_unlock(&head->lock); + + return 0; } EXPORT_SYMBOL_GPL(__inet_inherit_port); diff --git a/net/ipv4/inetpeer.c b/net/ipv4/inetpeer.c index 9ffa24b9a80..9e94d7cf4f8 100644 --- a/net/ipv4/inetpeer.c +++ b/net/ipv4/inetpeer.c @@ -72,18 +72,19 @@ static struct kmem_cache *peer_cachep __read_mostly; #define node_height(x) x->avl_height #define peer_avl_empty ((struct inet_peer *)&peer_fake_node) +#define peer_avl_empty_rcu ((struct inet_peer __rcu __force *)&peer_fake_node) static const struct inet_peer peer_fake_node = { - .avl_left = peer_avl_empty, - .avl_right = peer_avl_empty, + .avl_left = peer_avl_empty_rcu, + .avl_right = peer_avl_empty_rcu, .avl_height = 0 }; static struct { - struct inet_peer *root; + struct inet_peer __rcu *root; spinlock_t lock; int total; } peers = { - .root = peer_avl_empty, + .root = peer_avl_empty_rcu, .lock = __SPIN_LOCK_UNLOCKED(peers.lock), .total = 0, }; @@ -156,11 +157,14 @@ static void unlink_from_unused(struct inet_peer *p) */ #define lookup(_daddr, _stack) \ ({ \ - struct inet_peer *u, **v; \ + struct inet_peer *u; \ + struct inet_peer __rcu **v; \ \ stackptr = _stack; \ *stackptr++ = &peers.root; \ - for (u = peers.root; u != peer_avl_empty; ) { \ + for (u = rcu_dereference_protected(peers.root, \ + lockdep_is_held(&peers.lock)); \ + u != peer_avl_empty; ) { \ if (_daddr == u->v4daddr) \ break; \ if ((__force __u32)_daddr < (__force __u32)u->v4daddr) \ @@ -168,7 +172,8 @@ static void unlink_from_unused(struct inet_peer *p) else \ v = &u->avl_right; \ *stackptr++ = v; \ - u = *v; \ + u = rcu_dereference_protected(*v, \ + lockdep_is_held(&peers.lock)); \ } \ u; \ }) @@ -209,13 +214,17 @@ static struct inet_peer *lookup_rcu_bh(__be32 daddr) /* Called with local BH disabled and the pool lock held. */ #define lookup_rightempty(start) \ ({ \ - struct inet_peer *u, **v; \ + struct inet_peer *u; \ + struct inet_peer __rcu **v; \ *stackptr++ = &start->avl_left; \ v = &start->avl_left; \ - for (u = *v; u->avl_right != peer_avl_empty; ) { \ + for (u = rcu_dereference_protected(*v, \ + lockdep_is_held(&peers.lock)); \ + u->avl_right != peer_avl_empty_rcu; ) { \ v = &u->avl_right; \ *stackptr++ = v; \ - u = *v; \ + u = rcu_dereference_protected(*v, \ + lockdep_is_held(&peers.lock)); \ } \ u; \ }) @@ -224,74 +233,86 @@ static struct inet_peer *lookup_rcu_bh(__be32 daddr) * Variable names are the proof of operation correctness. * Look into mm/map_avl.c for more detail description of the ideas. */ -static void peer_avl_rebalance(struct inet_peer **stack[], - struct inet_peer ***stackend) +static void peer_avl_rebalance(struct inet_peer __rcu **stack[], + struct inet_peer __rcu ***stackend) { - struct inet_peer **nodep, *node, *l, *r; + struct inet_peer __rcu **nodep; + struct inet_peer *node, *l, *r; int lh, rh; while (stackend > stack) { nodep = *--stackend; - node = *nodep; - l = node->avl_left; - r = node->avl_right; + node = rcu_dereference_protected(*nodep, + lockdep_is_held(&peers.lock)); + l = rcu_dereference_protected(node->avl_left, + lockdep_is_held(&peers.lock)); + r = rcu_dereference_protected(node->avl_right, + lockdep_is_held(&peers.lock)); lh = node_height(l); rh = node_height(r); if (lh > rh + 1) { /* l: RH+2 */ struct inet_peer *ll, *lr, *lrl, *lrr; int lrh; - ll = l->avl_left; - lr = l->avl_right; + ll = rcu_dereference_protected(l->avl_left, + lockdep_is_held(&peers.lock)); + lr = rcu_dereference_protected(l->avl_right, + lockdep_is_held(&peers.lock)); lrh = node_height(lr); if (lrh <= node_height(ll)) { /* ll: RH+1 */ - node->avl_left = lr; /* lr: RH or RH+1 */ - node->avl_right = r; /* r: RH */ + RCU_INIT_POINTER(node->avl_left, lr); /* lr: RH or RH+1 */ + RCU_INIT_POINTER(node->avl_right, r); /* r: RH */ node->avl_height = lrh + 1; /* RH+1 or RH+2 */ - l->avl_left = ll; /* ll: RH+1 */ - l->avl_right = node; /* node: RH+1 or RH+2 */ + RCU_INIT_POINTER(l->avl_left, ll); /* ll: RH+1 */ + RCU_INIT_POINTER(l->avl_right, node); /* node: RH+1 or RH+2 */ l->avl_height = node->avl_height + 1; - *nodep = l; + RCU_INIT_POINTER(*nodep, l); } else { /* ll: RH, lr: RH+1 */ - lrl = lr->avl_left; /* lrl: RH or RH-1 */ - lrr = lr->avl_right; /* lrr: RH or RH-1 */ - node->avl_left = lrr; /* lrr: RH or RH-1 */ - node->avl_right = r; /* r: RH */ + lrl = rcu_dereference_protected(lr->avl_left, + lockdep_is_held(&peers.lock)); /* lrl: RH or RH-1 */ + lrr = rcu_dereference_protected(lr->avl_right, + lockdep_is_held(&peers.lock)); /* lrr: RH or RH-1 */ + RCU_INIT_POINTER(node->avl_left, lrr); /* lrr: RH or RH-1 */ + RCU_INIT_POINTER(node->avl_right, r); /* r: RH */ node->avl_height = rh + 1; /* node: RH+1 */ - l->avl_left = ll; /* ll: RH */ - l->avl_right = lrl; /* lrl: RH or RH-1 */ + RCU_INIT_POINTER(l->avl_left, ll); /* ll: RH */ + RCU_INIT_POINTER(l->avl_right, lrl); /* lrl: RH or RH-1 */ l->avl_height = rh + 1; /* l: RH+1 */ - lr->avl_left = l; /* l: RH+1 */ - lr->avl_right = node; /* node: RH+1 */ + RCU_INIT_POINTER(lr->avl_left, l); /* l: RH+1 */ + RCU_INIT_POINTER(lr->avl_right, node); /* node: RH+1 */ lr->avl_height = rh + 2; - *nodep = lr; + RCU_INIT_POINTER(*nodep, lr); } } else if (rh > lh + 1) { /* r: LH+2 */ struct inet_peer *rr, *rl, *rlr, *rll; int rlh; - rr = r->avl_right; - rl = r->avl_left; + rr = rcu_dereference_protected(r->avl_right, + lockdep_is_held(&peers.lock)); + rl = rcu_dereference_protected(r->avl_left, + lockdep_is_held(&peers.lock)); rlh = node_height(rl); if (rlh <= node_height(rr)) { /* rr: LH+1 */ - node->avl_right = rl; /* rl: LH or LH+1 */ - node->avl_left = l; /* l: LH */ + RCU_INIT_POINTER(node->avl_right, rl); /* rl: LH or LH+1 */ + RCU_INIT_POINTER(node->avl_left, l); /* l: LH */ node->avl_height = rlh + 1; /* LH+1 or LH+2 */ - r->avl_right = rr; /* rr: LH+1 */ - r->avl_left = node; /* node: LH+1 or LH+2 */ + RCU_INIT_POINTER(r->avl_right, rr); /* rr: LH+1 */ + RCU_INIT_POINTER(r->avl_left, node); /* node: LH+1 or LH+2 */ r->avl_height = node->avl_height + 1; - *nodep = r; + RCU_INIT_POINTER(*nodep, r); } else { /* rr: RH, rl: RH+1 */ - rlr = rl->avl_right; /* rlr: LH or LH-1 */ - rll = rl->avl_left; /* rll: LH or LH-1 */ - node->avl_right = rll; /* rll: LH or LH-1 */ - node->avl_left = l; /* l: LH */ + rlr = rcu_dereference_protected(rl->avl_right, + lockdep_is_held(&peers.lock)); /* rlr: LH or LH-1 */ + rll = rcu_dereference_protected(rl->avl_left, + lockdep_is_held(&peers.lock)); /* rll: LH or LH-1 */ + RCU_INIT_POINTER(node->avl_right, rll); /* rll: LH or LH-1 */ + RCU_INIT_POINTER(node->avl_left, l); /* l: LH */ node->avl_height = lh + 1; /* node: LH+1 */ - r->avl_right = rr; /* rr: LH */ - r->avl_left = rlr; /* rlr: LH or LH-1 */ + RCU_INIT_POINTER(r->avl_right, rr); /* rr: LH */ + RCU_INIT_POINTER(r->avl_left, rlr); /* rlr: LH or LH-1 */ r->avl_height = lh + 1; /* r: LH+1 */ - rl->avl_right = r; /* r: LH+1 */ - rl->avl_left = node; /* node: LH+1 */ + RCU_INIT_POINTER(rl->avl_right, r); /* r: LH+1 */ + RCU_INIT_POINTER(rl->avl_left, node); /* node: LH+1 */ rl->avl_height = lh + 2; - *nodep = rl; + RCU_INIT_POINTER(*nodep, rl); } } else { node->avl_height = (lh > rh ? lh : rh) + 1; @@ -303,10 +324,10 @@ static void peer_avl_rebalance(struct inet_peer **stack[], #define link_to_pool(n) \ do { \ n->avl_height = 1; \ - n->avl_left = peer_avl_empty; \ - n->avl_right = peer_avl_empty; \ - smp_wmb(); /* lockless readers can catch us now */ \ - **--stackptr = n; \ + n->avl_left = peer_avl_empty_rcu; \ + n->avl_right = peer_avl_empty_rcu; \ + /* lockless readers can catch us now */ \ + rcu_assign_pointer(**--stackptr, n); \ peer_avl_rebalance(stack, stackptr); \ } while (0) @@ -330,24 +351,25 @@ static void unlink_from_pool(struct inet_peer *p) * We use refcnt=-1 to alert lockless readers this entry is deleted. */ if (atomic_cmpxchg(&p->refcnt, 1, -1) == 1) { - struct inet_peer **stack[PEER_MAXDEPTH]; - struct inet_peer ***stackptr, ***delp; + struct inet_peer __rcu **stack[PEER_MAXDEPTH]; + struct inet_peer __rcu ***stackptr, ***delp; if (lookup(p->v4daddr, stack) != p) BUG(); delp = stackptr - 1; /* *delp[0] == p */ - if (p->avl_left == peer_avl_empty) { + if (p->avl_left == peer_avl_empty_rcu) { *delp[0] = p->avl_right; --stackptr; } else { /* look for a node to insert instead of p */ struct inet_peer *t; t = lookup_rightempty(p); - BUG_ON(*stackptr[-1] != t); + BUG_ON(rcu_dereference_protected(*stackptr[-1], + lockdep_is_held(&peers.lock)) != t); **--stackptr = t->avl_left; /* t is removed, t->v4daddr > x->v4daddr for any * x in p->avl_left subtree. * Put t in the old place of p. */ - *delp[0] = t; + RCU_INIT_POINTER(*delp[0], t); t->avl_left = p->avl_left; t->avl_right = p->avl_right; t->avl_height = p->avl_height; @@ -414,7 +436,7 @@ static int cleanup_once(unsigned long ttl) struct inet_peer *inet_getpeer(__be32 daddr, int create) { struct inet_peer *p; - struct inet_peer **stack[PEER_MAXDEPTH], ***stackptr; + struct inet_peer __rcu **stack[PEER_MAXDEPTH], ***stackptr; /* Look up for the address quickly, lockless. * Because of a concurrent writer, we might not find an existing entry. diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index b7c41654dde..168440834ad 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -116,11 +116,11 @@ static int ip4_frag_match(struct inet_frag_queue *q, void *a) struct ip4_create_arg *arg = a; qp = container_of(q, struct ipq, q); - return (qp->id == arg->iph->id && + return qp->id == arg->iph->id && qp->saddr == arg->iph->saddr && qp->daddr == arg->iph->daddr && qp->protocol == arg->iph->protocol && - qp->user == arg->user); + qp->user == arg->user; } /* Memory Tracking Functions. */ @@ -542,7 +542,7 @@ static int ip_frag_reasm(struct ipq *qp, struct sk_buff *prev, /* If the first fragment is fragmented itself, we split * it to two chunks: the first with data and paged part * and the second, holding only fragments. */ - if (skb_has_frags(head)) { + if (skb_has_frag_list(head)) { struct sk_buff *clone; int i, plen = 0; diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 945b20a5ad5..01087e035b7 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -44,8 +44,9 @@ #include <net/net_namespace.h> #include <net/netns/generic.h> #include <net/rtnetlink.h> +#include <net/gre.h> -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -63,13 +64,13 @@ We cannot track such dead loops during route installation, it is infeasible task. The most general solutions would be to keep skb->encapsulation counter (sort of local ttl), - and silently drop packet when it expires. It is the best + and silently drop packet when it expires. It is a good solution, but it supposes maintaing new variable in ALL skb, even if no tunneling is used. - Current solution: HARD_TX_LOCK lock breaks dead loops. - - + Current solution: xmit_recursion breaks dead loops. This is a percpu + counter, since when we enter the first ndo_xmit(), cpu migration is + forbidden. We force an exit if this counter reaches RECURSION_LIMIT 2. Networking dead loops would not kill routers, but would really kill network. IP hop limit plays role of "t->recursion" in this case, @@ -128,7 +129,7 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev); static int ipgre_net_id __read_mostly; struct ipgre_net { - struct ip_tunnel *tunnels[4][HASH_SIZE]; + struct ip_tunnel __rcu *tunnels[4][HASH_SIZE]; struct net_device *fb_tunnel_dev; }; @@ -158,13 +159,40 @@ struct ipgre_net { #define tunnels_l tunnels[1] #define tunnels_wc tunnels[0] /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ipgre_lock); #define for_each_ip_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ipgre_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + /* Given src, dst and key, find appropriate for input tunnel. */ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, @@ -173,8 +201,8 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, { struct net *net = dev_net(dev); int link = dev->ifindex; - unsigned h0 = HASH(remote); - unsigned h1 = HASH(key); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(key); struct ip_tunnel *t, *cand = NULL; struct ipgre_net *ign = net_generic(net, ipgre_net_id); int dev_type = (gre_proto == htons(ETH_P_TEB)) ? @@ -289,13 +317,13 @@ static struct ip_tunnel * ipgre_tunnel_lookup(struct net_device *dev, return NULL; } -static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign, +static struct ip_tunnel __rcu **__ipgre_bucket(struct ipgre_net *ign, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; __be32 key = parms->i_key; - unsigned h = HASH(key); + unsigned int h = HASH(key); int prio = 0; if (local) @@ -308,7 +336,7 @@ static struct ip_tunnel **__ipgre_bucket(struct ipgre_net *ign, return &ign->tunnels[prio][h]; } -static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign, +static inline struct ip_tunnel __rcu **ipgre_bucket(struct ipgre_net *ign, struct ip_tunnel *t) { return __ipgre_bucket(ign, &t->parms); @@ -316,23 +344,22 @@ static inline struct ip_tunnel **ipgre_bucket(struct ipgre_net *ign, static void ipgre_tunnel_link(struct ipgre_net *ign, struct ip_tunnel *t) { - struct ip_tunnel **tp = ipgre_bucket(ign, t); + struct ip_tunnel __rcu **tp = ipgre_bucket(ign, t); - spin_lock_bh(&ipgre_lock); - t->next = *tp; + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ipgre_lock); } static void ipgre_tunnel_unlink(struct ipgre_net *ign, struct ip_tunnel *t) { - struct ip_tunnel **tp; - - for (tp = ipgre_bucket(ign, t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ipgre_lock); - *tp = t->next; - spin_unlock_bh(&ipgre_lock); + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipgre_bucket(ign, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } @@ -346,10 +373,13 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net, __be32 local = parms->iph.saddr; __be32 key = parms->i_key; int link = parms->link; - struct ip_tunnel *t, **tp; + struct ip_tunnel *t; + struct ip_tunnel __rcu **tp; struct ipgre_net *ign = net_generic(net, ipgre_net_id); - for (tp = __ipgre_bucket(ign, parms); (t = *tp) != NULL; tp = &t->next) + for (tp = __ipgre_bucket(ign, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr && key == t->parms.i_key && @@ -360,7 +390,7 @@ static struct ip_tunnel *ipgre_tunnel_find(struct net *net, return t; } -static struct ip_tunnel * ipgre_tunnel_locate(struct net *net, +static struct ip_tunnel *ipgre_tunnel_locate(struct net *net, struct ip_tunnel_parm *parms, int create) { struct ip_tunnel *t, *nt; @@ -582,7 +612,7 @@ static int ipgre_rcv(struct sk_buff *skb) if ((tunnel = ipgre_tunnel_lookup(skb->dev, iph->saddr, iph->daddr, key, gre_proto))) { - struct net_device_stats *stats = &tunnel->dev->stats; + struct pcpu_tstats *tstats; secpath_reset(skb); @@ -606,22 +636,22 @@ static int ipgre_rcv(struct sk_buff *skb) /* Looped back packet, drop it! */ if (skb_rtable(skb)->fl.iif == 0) goto drop; - stats->multicast++; + tunnel->dev->stats.multicast++; skb->pkt_type = PACKET_BROADCAST; } #endif if (((flags&GRE_CSUM) && csum) || (!(flags&GRE_CSUM) && tunnel->parms.i_flags&GRE_CSUM)) { - stats->rx_crc_errors++; - stats->rx_errors++; + tunnel->dev->stats.rx_crc_errors++; + tunnel->dev->stats.rx_errors++; goto drop; } if (tunnel->parms.i_flags&GRE_SEQ) { if (!(flags&GRE_SEQ) || (tunnel->i_seqno && (s32)(seqno - tunnel->i_seqno) < 0)) { - stats->rx_fifo_errors++; - stats->rx_errors++; + tunnel->dev->stats.rx_fifo_errors++; + tunnel->dev->stats.rx_errors++; goto drop; } tunnel->i_seqno = seqno + 1; @@ -630,8 +660,8 @@ static int ipgre_rcv(struct sk_buff *skb) /* Warning: All skb pointers will be invalidated! */ if (tunnel->dev->type == ARPHRD_ETHER) { if (!pskb_may_pull(skb, ETH_HLEN)) { - stats->rx_length_errors++; - stats->rx_errors++; + tunnel->dev->stats.rx_length_errors++; + tunnel->dev->stats.rx_errors++; goto drop; } @@ -640,14 +670,19 @@ static int ipgre_rcv(struct sk_buff *skb) skb_postpull_rcsum(skb, eth_hdr(skb), ETH_HLEN); } - skb_tunnel_rx(skb, tunnel->dev); + tstats = this_cpu_ptr(tunnel->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, tunnel->dev); skb_reset_network_header(skb); ipgre_ecn_decapsulate(iph, skb); netif_rx(skb); + rcu_read_unlock(); - return(0); + return 0; } icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); @@ -655,20 +690,19 @@ drop: rcu_read_unlock(); drop_nolock: kfree_skb(skb); - return(0); + return 0; } static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct pcpu_tstats *tstats; struct iphdr *old_iph = ip_hdr(skb); struct iphdr *tiph; u8 tos; __be16 df; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ + struct net_device *tdev; /* Device to other host */ struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ int gre_hlen; @@ -690,7 +724,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev /* NBMA tunnel */ if (skb_dst(skb) == NULL) { - stats->tx_fifo_errors++; + dev->stats.tx_fifo_errors++; goto tx_error; } @@ -699,7 +733,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((dst = rt->rt_gateway) == 0) goto tx_error_icmp; } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct in6_addr *addr6; int addr_type; @@ -736,14 +770,20 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) } }, - .proto = IPPROTO_GRE }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = dst, + .saddr = tiph->saddr, + .tos = RT_TOS(tos) + } + }, + .proto = IPPROTO_GRE + } +; if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error; } } @@ -751,7 +791,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (tdev == dev) { ip_rt_put(rt); - stats->collisions++; + dev->stats.collisions++; goto tx_error; } @@ -774,7 +814,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } } -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); @@ -814,7 +854,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); - txq->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -850,7 +890,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if ((iph->ttl = tiph->ttl) == 0) { if (skb->protocol == htons(ETH_P_IP)) iph->ttl = old_iph->ttl; -#ifdef CONFIG_IPV6 +#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) else if (skb->protocol == htons(ETH_P_IPV6)) iph->ttl = ((struct ipv6hdr *)old_iph)->hop_limit; #endif @@ -881,15 +921,15 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev } nf_reset(skb); - - IPTUNNEL_XMIT(); + tstats = this_cpu_ptr(dev->tstats); + __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: - stats->tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -909,13 +949,19 @@ static int ipgre_tunnel_bind_dev(struct net_device *dev) /* Guess output device to choose reasonable mtu and needed_headroom */ if (iph->daddr) { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_GRE }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_GRE + }; struct rtable *rt; + if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { tdev = rt->dst.dev; ip_rt_put(rt); @@ -1012,7 +1058,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } } else { - unsigned nflags = 0; + unsigned int nflags = 0; t = netdev_priv(dev); @@ -1026,6 +1072,7 @@ ipgre_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) break; } ipgre_tunnel_unlink(ign, t); + synchronize_net(); t->parms.iph.saddr = p.iph.saddr; t->parms.iph.daddr = p.iph.daddr; t->parms.i_key = p.i_key; @@ -1125,7 +1172,7 @@ static int ipgre_tunnel_change_mtu(struct net_device *dev, int new_mtu) static int ipgre_header(struct sk_buff *skb, struct net_device *dev, unsigned short type, - const void *daddr, const void *saddr, unsigned len) + const void *daddr, const void *saddr, unsigned int len) { struct ip_tunnel *t = netdev_priv(dev); struct iphdr *iph = (struct iphdr *)skb_push(skb, t->hlen); @@ -1167,13 +1214,19 @@ static int ipgre_open(struct net_device *dev) struct ip_tunnel *t = netdev_priv(dev); if (ipv4_is_multicast(t->parms.iph.daddr)) { - struct flowi fl = { .oif = t->parms.link, - .nl_u = { .ip4_u = - { .daddr = t->parms.iph.daddr, - .saddr = t->parms.iph.saddr, - .tos = RT_TOS(t->parms.iph.tos) } }, - .proto = IPPROTO_GRE }; + struct flowi fl = { + .oif = t->parms.link, + .nl_u = { + .ip4_u = { + .daddr = t->parms.iph.daddr, + .saddr = t->parms.iph.saddr, + .tos = RT_TOS(t->parms.iph.tos) + } + }, + .proto = IPPROTO_GRE + }; struct rtable *rt; + if (ip_route_output_key(dev_net(dev), &rt, &fl)) return -EADDRNOTAVAIL; dev = rt->dst.dev; @@ -1193,10 +1246,8 @@ static int ipgre_close(struct net_device *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); - if (in_dev) { + if (in_dev) ip_mc_dec_group(in_dev, t->parms.iph.daddr); - in_dev_put(in_dev); - } } return 0; } @@ -1213,12 +1264,19 @@ static const struct net_device_ops ipgre_netdev_ops = { .ndo_start_xmit = ipgre_tunnel_xmit, .ndo_do_ioctl = ipgre_tunnel_ioctl, .ndo_change_mtu = ipgre_tunnel_change_mtu, + .ndo_get_stats = ipgre_get_stats, }; +static void ipgre_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ipgre_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipgre_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipgre_dev_free; dev->type = ARPHRD_IPGRE; dev->needed_headroom = LL_MAX_HEADER + sizeof(struct iphdr) + 4; @@ -1256,6 +1314,10 @@ static int ipgre_tunnel_init(struct net_device *dev) } else dev->header_ops = &ipgre_header_ops; + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } @@ -1274,14 +1336,13 @@ static void ipgre_fb_tunnel_init(struct net_device *dev) tunnel->hlen = sizeof(struct iphdr) + 4; dev_hold(dev); - ign->tunnels_wc[0] = tunnel; + rcu_assign_pointer(ign->tunnels_wc[0], tunnel); } -static const struct net_protocol ipgre_protocol = { - .handler = ipgre_rcv, - .err_handler = ipgre_err, - .netns_ok = 1, +static const struct gre_protocol ipgre_protocol = { + .handler = ipgre_rcv, + .err_handler = ipgre_err, }; static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) @@ -1291,11 +1352,13 @@ static void ipgre_destroy_tunnels(struct ipgre_net *ign, struct list_head *head) for (prio = 0; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = ign->tunnels[prio][h]; + struct ip_tunnel *t; + + t = rtnl_dereference(ign->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } @@ -1441,6 +1504,10 @@ static int ipgre_tap_init(struct net_device *dev) ipgre_tunnel_bind_dev(dev); + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + return 0; } @@ -1451,6 +1518,7 @@ static const struct net_device_ops ipgre_tap_netdev_ops = { .ndo_set_mac_address = eth_mac_addr, .ndo_validate_addr = eth_validate_addr, .ndo_change_mtu = ipgre_tunnel_change_mtu, + .ndo_get_stats = ipgre_get_stats, }; static void ipgre_tap_setup(struct net_device *dev) @@ -1459,7 +1527,7 @@ static void ipgre_tap_setup(struct net_device *dev) ether_setup(dev); dev->netdev_ops = &ipgre_tap_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipgre_dev_free; dev->iflink = 0; dev->features |= NETIF_F_NETNS_LOCAL; @@ -1487,6 +1555,10 @@ static int ipgre_newlink(struct net *src_net, struct net_device *dev, struct nla if (!tb[IFLA_MTU]) dev->mtu = mtu; + /* Can use a lockless transmit, unless we generate output sequences */ + if (!(nt->parms.o_flags & GRE_SEQ)) + dev->features |= NETIF_F_LLTX; + err = register_netdevice(dev); if (err) goto out; @@ -1522,7 +1594,7 @@ static int ipgre_changelink(struct net_device *dev, struct nlattr *tb[], t = nt; if (dev->type != ARPHRD_ETHER) { - unsigned nflags = 0; + unsigned int nflags = 0; if (ipv4_is_multicast(p.iph.daddr)) nflags = IFF_BROADCAST; @@ -1663,7 +1735,7 @@ static int __init ipgre_init(void) if (err < 0) return err; - err = inet_add_protocol(&ipgre_protocol, IPPROTO_GRE); + err = gre_add_protocol(&ipgre_protocol, GREPROTO_CISCO); if (err < 0) { printk(KERN_INFO "ipgre init: can't add protocol\n"); goto add_proto_failed; @@ -1683,7 +1755,7 @@ out: tap_ops_failed: rtnl_link_unregister(&ipgre_link_ops); rtnl_link_failed: - inet_del_protocol(&ipgre_protocol, IPPROTO_GRE); + gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO); add_proto_failed: unregister_pernet_device(&ipgre_net_ops); goto out; @@ -1693,7 +1765,7 @@ static void __exit ipgre_fini(void) { rtnl_link_unregister(&ipgre_tap_ops); rtnl_link_unregister(&ipgre_link_ops); - if (inet_del_protocol(&ipgre_protocol, IPPROTO_GRE) < 0) + if (gre_del_protocol(&ipgre_protocol, GREPROTO_CISCO) < 0) printk(KERN_INFO "ipgre close: can't remove protocol\n"); unregister_pernet_device(&ipgre_net_ops); } diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ba9836c488e..1906fa35860 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -466,7 +466,7 @@ error: } return -EINVAL; } - +EXPORT_SYMBOL(ip_options_compile); /* * Undo all the changes done by ip_options_compile(). @@ -646,3 +646,4 @@ int ip_options_rcv_srr(struct sk_buff *skb) } return 0; } +EXPORT_SYMBOL(ip_options_rcv_srr); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 04b69896df5..439d2a34ee4 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -487,10 +487,9 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) * LATER: this step can be merged to real generation of fragments, * we can switch to copy when see the first bad fragment. */ - if (skb_has_frags(skb)) { - struct sk_buff *frag; + if (skb_has_frag_list(skb)) { + struct sk_buff *frag, *frag2; int first_len = skb_pagelen(skb); - int truesizes = 0; if (first_len - hlen > mtu || ((first_len - hlen) & 7) || @@ -503,18 +502,18 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (frag->len > mtu || ((frag->len & 7) && frag->next) || skb_headroom(frag) < hlen) - goto slow_path; + goto slow_path_clean; /* Partially cloned skb? */ if (skb_shared(frag)) - goto slow_path; + goto slow_path_clean; BUG_ON(frag->sk); if (skb->sk) { frag->sk = skb->sk; frag->destructor = sock_wfree; } - truesizes += frag->truesize; + skb->truesize -= frag->truesize; } /* Everything is OK. Generate! */ @@ -524,7 +523,6 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) frag = skb_shinfo(skb)->frag_list; skb_frag_list_init(skb); skb->data_len = first_len - skb_headlen(skb); - skb->truesize -= truesizes; skb->len = first_len; iph->tot_len = htons(first_len); iph->frag_off = htons(IP_MF); @@ -576,6 +574,15 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) } IP_INC_STATS(dev_net(dev), IPSTATS_MIB_FRAGFAILS); return err; + +slow_path_clean: + skb_walk_frags(skb, frag2) { + if (frag2 == frag) + break; + frag2->sk = NULL; + frag2->destructor = NULL; + skb->truesize += frag2->truesize; + } } slow_path: @@ -837,10 +844,9 @@ int ip_append_data(struct sock *sk, inet->cork.length = 0; sk->sk_sndmsg_page = NULL; sk->sk_sndmsg_off = 0; - if ((exthdrlen = rt->dst.header_len) != 0) { - length += exthdrlen; - transhdrlen += exthdrlen; - } + exthdrlen = rt->dst.header_len; + length += exthdrlen; + transhdrlen += exthdrlen; } else { rt = (struct rtable *)inet->cork.dst; if (inet->cork.flags & IPCORK_OPT) @@ -927,16 +933,19 @@ alloc_new_skb: !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; else - alloclen = datalen + fragheaderlen; + alloclen = fraglen; /* The last fragment gets additional space at tail. * Note, with MSG_MORE we overallocate on fragments, * because we have no idea what fragment will be * the last. */ - if (datalen == length + fraggap) + if (datalen == length + fraggap) { alloclen += rt->dst.trailer_len; - + /* make sure mtu is not reached */ + if (datalen > mtu - fragheaderlen - rt->dst.trailer_len) + datalen -= ALIGN(rt->dst.trailer_len, 8); + } if (transhdrlen) { skb = sock_alloc_send_skb(sk, alloclen + hh_len + 15, @@ -953,7 +962,7 @@ alloc_new_skb: else /* only the initial fragment is time stamped */ - ipc->shtx.flags = 0; + ipc->tx_flags = 0; } if (skb == NULL) goto error; @@ -964,7 +973,7 @@ alloc_new_skb: skb->ip_summed = csummode; skb->csum = 0; skb_reserve(skb, hh_len); - *skb_tx(skb) = ipc->shtx; + skb_shinfo(skb)->tx_flags = ipc->tx_flags; /* * Find where to start putting bytes. @@ -1384,7 +1393,7 @@ void ip_send_reply(struct sock *sk, struct sk_buff *skb, struct ip_reply_arg *ar daddr = ipc.addr = rt->rt_src; ipc.opt = NULL; - ipc.shtx.flags = 0; + ipc.tx_flags = 0; if (replyopts.opt.optlen) { ipc.opt = &replyopts.opt; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 6c40a8c46e7..3948c86e59c 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -238,7 +238,7 @@ int ip_cmsg_send(struct net *net, struct msghdr *msg, struct ipcm_cookie *ipc) but receiver should be enough clever f.e. to forward mtrace requests, sent to multicast group to reach destination designated router. */ -struct ip_ra_chain *ip_ra_chain; +struct ip_ra_chain __rcu *ip_ra_chain; static DEFINE_SPINLOCK(ip_ra_lock); @@ -253,7 +253,8 @@ static void ip_ra_destroy_rcu(struct rcu_head *head) int ip_ra_control(struct sock *sk, unsigned char on, void (*destructor)(struct sock *)) { - struct ip_ra_chain *ra, *new_ra, **rap; + struct ip_ra_chain *ra, *new_ra; + struct ip_ra_chain __rcu **rap; if (sk->sk_type != SOCK_RAW || inet_sk(sk)->inet_num == IPPROTO_RAW) return -EINVAL; @@ -261,7 +262,10 @@ int ip_ra_control(struct sock *sk, unsigned char on, new_ra = on ? kmalloc(sizeof(*new_ra), GFP_KERNEL) : NULL; spin_lock_bh(&ip_ra_lock); - for (rap = &ip_ra_chain; (ra = *rap) != NULL; rap = &ra->next) { + for (rap = &ip_ra_chain; + (ra = rcu_dereference_protected(*rap, + lockdep_is_held(&ip_ra_lock))) != NULL; + rap = &ra->next) { if (ra->sk == sk) { if (on) { spin_unlock_bh(&ip_ra_lock); @@ -1129,6 +1133,9 @@ static int do_ip_getsockopt(struct sock *sk, int level, int optname, case IP_HDRINCL: val = inet->hdrincl; break; + case IP_NODEFRAG: + val = inet->nodefrag; + break; case IP_MTU_DISCOVER: val = inet->pmtudisc; break; diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index ec036731a70..cd300aaee78 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -122,31 +122,59 @@ static int ipip_net_id __read_mostly; struct ipip_net { - struct ip_tunnel *tunnels_r_l[HASH_SIZE]; - struct ip_tunnel *tunnels_r[HASH_SIZE]; - struct ip_tunnel *tunnels_l[HASH_SIZE]; - struct ip_tunnel *tunnels_wc[1]; - struct ip_tunnel **tunnels[4]; + struct ip_tunnel __rcu *tunnels_r_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_r[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_l[HASH_SIZE]; + struct ip_tunnel __rcu *tunnels_wc[1]; + struct ip_tunnel __rcu **tunnels[4]; struct net_device *fb_tunnel_dev; }; -static void ipip_tunnel_init(struct net_device *dev); +static int ipip_tunnel_init(struct net_device *dev); static void ipip_tunnel_setup(struct net_device *dev); +static void ipip_dev_free(struct net_device *dev); /* - * Locking : hash tables are protected by RCU and a spinlock + * Locking : hash tables are protected by RCU and RTNL */ -static DEFINE_SPINLOCK(ipip_lock); #define for_each_ip_tunnel_rcu(start) \ for (t = rcu_dereference(start); t; t = rcu_dereference(t->next)) +/* often modified stats are per cpu, other are shared (netdev->stats) */ +struct pcpu_tstats { + unsigned long rx_packets; + unsigned long rx_bytes; + unsigned long tx_packets; + unsigned long tx_bytes; +}; + +static struct net_device_stats *ipip_get_stats(struct net_device *dev) +{ + struct pcpu_tstats sum = { 0 }; + int i; + + for_each_possible_cpu(i) { + const struct pcpu_tstats *tstats = per_cpu_ptr(dev->tstats, i); + + sum.rx_packets += tstats->rx_packets; + sum.rx_bytes += tstats->rx_bytes; + sum.tx_packets += tstats->tx_packets; + sum.tx_bytes += tstats->tx_bytes; + } + dev->stats.rx_packets = sum.rx_packets; + dev->stats.rx_bytes = sum.rx_bytes; + dev->stats.tx_packets = sum.tx_packets; + dev->stats.tx_bytes = sum.tx_bytes; + return &dev->stats; +} + static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, __be32 remote, __be32 local) { - unsigned h0 = HASH(remote); - unsigned h1 = HASH(local); + unsigned int h0 = HASH(remote); + unsigned int h1 = HASH(local); struct ip_tunnel *t; struct ipip_net *ipn = net_generic(net, ipip_net_id); @@ -169,12 +197,12 @@ static struct ip_tunnel * ipip_tunnel_lookup(struct net *net, return NULL; } -static struct ip_tunnel **__ipip_bucket(struct ipip_net *ipn, +static struct ip_tunnel __rcu **__ipip_bucket(struct ipip_net *ipn, struct ip_tunnel_parm *parms) { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - unsigned h = 0; + unsigned int h = 0; int prio = 0; if (remote) { @@ -188,7 +216,7 @@ static struct ip_tunnel **__ipip_bucket(struct ipip_net *ipn, return &ipn->tunnels[prio][h]; } -static inline struct ip_tunnel **ipip_bucket(struct ipip_net *ipn, +static inline struct ip_tunnel __rcu **ipip_bucket(struct ipip_net *ipn, struct ip_tunnel *t) { return __ipip_bucket(ipn, &t->parms); @@ -196,13 +224,14 @@ static inline struct ip_tunnel **ipip_bucket(struct ipip_net *ipn, static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) { - struct ip_tunnel **tp; - - for (tp = ipip_bucket(ipn, t); *tp; tp = &(*tp)->next) { - if (t == *tp) { - spin_lock_bh(&ipip_lock); - *tp = t->next; - spin_unlock_bh(&ipip_lock); + struct ip_tunnel __rcu **tp; + struct ip_tunnel *iter; + + for (tp = ipip_bucket(ipn, t); + (iter = rtnl_dereference(*tp)) != NULL; + tp = &iter->next) { + if (t == iter) { + rcu_assign_pointer(*tp, t->next); break; } } @@ -210,12 +239,10 @@ static void ipip_tunnel_unlink(struct ipip_net *ipn, struct ip_tunnel *t) static void ipip_tunnel_link(struct ipip_net *ipn, struct ip_tunnel *t) { - struct ip_tunnel **tp = ipip_bucket(ipn, t); + struct ip_tunnel __rcu **tp = ipip_bucket(ipn, t); - spin_lock_bh(&ipip_lock); - t->next = *tp; + rcu_assign_pointer(t->next, rtnl_dereference(*tp)); rcu_assign_pointer(*tp, t); - spin_unlock_bh(&ipip_lock); } static struct ip_tunnel * ipip_tunnel_locate(struct net *net, @@ -223,12 +250,15 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, { __be32 remote = parms->iph.daddr; __be32 local = parms->iph.saddr; - struct ip_tunnel *t, **tp, *nt; + struct ip_tunnel *t, *nt; + struct ip_tunnel __rcu **tp; struct net_device *dev; char name[IFNAMSIZ]; struct ipip_net *ipn = net_generic(net, ipip_net_id); - for (tp = __ipip_bucket(ipn, parms); (t = *tp) != NULL; tp = &t->next) { + for (tp = __ipip_bucket(ipn, parms); + (t = rtnl_dereference(*tp)) != NULL; + tp = &t->next) { if (local == t->parms.iph.saddr && remote == t->parms.iph.daddr) return t; } @@ -238,7 +268,7 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, if (parms->name[0]) strlcpy(name, parms->name, IFNAMSIZ); else - sprintf(name, "tunl%%d"); + strcpy(name, "tunl%d"); dev = alloc_netdev(sizeof(*t), name, ipip_tunnel_setup); if (dev == NULL) @@ -254,7 +284,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, nt = netdev_priv(dev); nt->parms = *parms; - ipip_tunnel_init(dev); + if (ipip_tunnel_init(dev) < 0) + goto failed_free; if (register_netdevice(dev) < 0) goto failed_free; @@ -264,20 +295,19 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, return nt; failed_free: - free_netdev(dev); + ipip_dev_free(dev); return NULL; } +/* called with RTNL */ static void ipip_tunnel_uninit(struct net_device *dev) { struct net *net = dev_net(dev); struct ipip_net *ipn = net_generic(net, ipip_net_id); - if (dev == ipn->fb_tunnel_dev) { - spin_lock_bh(&ipip_lock); - ipn->tunnels_wc[0] = NULL; - spin_unlock_bh(&ipip_lock); - } else + if (dev == ipn->fb_tunnel_dev) + rcu_assign_pointer(ipn->tunnels_wc[0], NULL); + else ipip_tunnel_unlink(ipn, netdev_priv(dev)); dev_put(dev); } @@ -359,8 +389,10 @@ static int ipip_rcv(struct sk_buff *skb) const struct iphdr *iph = ip_hdr(skb); rcu_read_lock(); - if ((tunnel = ipip_tunnel_lookup(dev_net(skb->dev), - iph->saddr, iph->daddr)) != NULL) { + tunnel = ipip_tunnel_lookup(dev_net(skb->dev), iph->saddr, iph->daddr); + if (tunnel != NULL) { + struct pcpu_tstats *tstats; + if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) { rcu_read_unlock(); kfree_skb(skb); @@ -374,10 +406,16 @@ static int ipip_rcv(struct sk_buff *skb) skb->protocol = htons(ETH_P_IP); skb->pkt_type = PACKET_HOST; - skb_tunnel_rx(skb, tunnel->dev); + tstats = this_cpu_ptr(tunnel->dev->tstats); + tstats->rx_packets++; + tstats->rx_bytes += skb->len; + + __skb_tunnel_rx(skb, tunnel->dev); ipip_ecn_decapsulate(iph, skb); + netif_rx(skb); + rcu_read_unlock(); return 0; } @@ -394,13 +432,12 @@ static int ipip_rcv(struct sk_buff *skb) static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); - struct net_device_stats *stats = &dev->stats; - struct netdev_queue *txq = netdev_get_tx_queue(dev, 0); + struct pcpu_tstats *tstats; struct iphdr *tiph = &tunnel->parms.iph; u8 tos = tunnel->parms.iph.tos; __be16 df = tiph->frag_off; struct rtable *rt; /* Route to the other host */ - struct net_device *tdev; /* Device to other host */ + struct net_device *tdev; /* Device to other host */ struct iphdr *old_iph = ip_hdr(skb); struct iphdr *iph; /* Our new IP header */ unsigned int max_headroom; /* The extra header space needed */ @@ -410,13 +447,13 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (skb->protocol != htons(ETH_P_IP)) goto tx_error; - if (tos&1) + if (tos & 1) tos = old_iph->tos; if (!dst) { /* NBMA tunnel */ if ((rt = skb_rtable(skb)) == NULL) { - stats->tx_fifo_errors++; + dev->stats.tx_fifo_errors++; goto tx_error; } if ((dst = rt->rt_gateway) == 0) @@ -424,14 +461,20 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) } { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = dst, - .saddr = tiph->saddr, - .tos = RT_TOS(tos) } }, - .proto = IPPROTO_IPIP }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = dst, + .saddr = tiph->saddr, + .tos = RT_TOS(tos) + } + }, + .proto = IPPROTO_IPIP + }; + if (ip_route_output_key(dev_net(dev), &rt, &fl)) { - stats->tx_carrier_errors++; + dev->stats.tx_carrier_errors++; goto tx_error_icmp; } } @@ -439,7 +482,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) if (tdev == dev) { ip_rt_put(rt); - stats->collisions++; + dev->stats.collisions++; goto tx_error; } @@ -449,7 +492,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr); if (mtu < 68) { - stats->collisions++; + dev->stats.collisions++; ip_rt_put(rt); goto tx_error; } @@ -485,7 +528,7 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); if (!new_skb) { ip_rt_put(rt); - txq->tx_dropped++; + dev->stats.tx_dropped++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -522,14 +565,14 @@ static netdev_tx_t ipip_tunnel_xmit(struct sk_buff *skb, struct net_device *dev) iph->ttl = old_iph->ttl; nf_reset(skb); - - IPTUNNEL_XMIT(); + tstats = this_cpu_ptr(dev->tstats); + __IPTUNNEL_XMIT(tstats, &dev->stats); return NETDEV_TX_OK; tx_error_icmp: dst_link_failure(skb); tx_error: - stats->tx_errors++; + dev->stats.tx_errors++; dev_kfree_skb(skb); return NETDEV_TX_OK; } @@ -544,13 +587,19 @@ static void ipip_tunnel_bind_dev(struct net_device *dev) iph = &tunnel->parms.iph; if (iph->daddr) { - struct flowi fl = { .oif = tunnel->parms.link, - .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .saddr = iph->saddr, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_IPIP }; + struct flowi fl = { + .oif = tunnel->parms.link, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .saddr = iph->saddr, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_IPIP + }; struct rtable *rt; + if (!ip_route_output_key(dev_net(dev), &rt, &fl)) { tdev = rt->dst.dev; ip_rt_put(rt); @@ -627,6 +676,7 @@ ipip_tunnel_ioctl (struct net_device *dev, struct ifreq *ifr, int cmd) } t = netdev_priv(dev); ipip_tunnel_unlink(ipn, t); + synchronize_net(); t->parms.iph.saddr = p.iph.saddr; t->parms.iph.daddr = p.iph.daddr; memcpy(dev->dev_addr, &p.iph.saddr, 4); @@ -696,13 +746,19 @@ static const struct net_device_ops ipip_netdev_ops = { .ndo_start_xmit = ipip_tunnel_xmit, .ndo_do_ioctl = ipip_tunnel_ioctl, .ndo_change_mtu = ipip_tunnel_change_mtu, - + .ndo_get_stats = ipip_get_stats, }; +static void ipip_dev_free(struct net_device *dev) +{ + free_percpu(dev->tstats); + free_netdev(dev); +} + static void ipip_tunnel_setup(struct net_device *dev) { dev->netdev_ops = &ipip_netdev_ops; - dev->destructor = free_netdev; + dev->destructor = ipip_dev_free; dev->type = ARPHRD_TUNNEL; dev->hard_header_len = LL_MAX_HEADER + sizeof(struct iphdr); @@ -711,10 +767,11 @@ static void ipip_tunnel_setup(struct net_device *dev) dev->iflink = 0; dev->addr_len = 4; dev->features |= NETIF_F_NETNS_LOCAL; + dev->features |= NETIF_F_LLTX; dev->priv_flags &= ~IFF_XMIT_DST_RELEASE; } -static void ipip_tunnel_init(struct net_device *dev) +static int ipip_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); @@ -725,9 +782,15 @@ static void ipip_tunnel_init(struct net_device *dev) memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); ipip_tunnel_bind_dev(dev); + + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + + return 0; } -static void __net_init ipip_fb_tunnel_init(struct net_device *dev) +static int __net_init ipip_fb_tunnel_init(struct net_device *dev) { struct ip_tunnel *tunnel = netdev_priv(dev); struct iphdr *iph = &tunnel->parms.iph; @@ -740,11 +803,16 @@ static void __net_init ipip_fb_tunnel_init(struct net_device *dev) iph->protocol = IPPROTO_IPIP; iph->ihl = 5; + dev->tstats = alloc_percpu(struct pcpu_tstats); + if (!dev->tstats) + return -ENOMEM; + dev_hold(dev); - ipn->tunnels_wc[0] = tunnel; + rcu_assign_pointer(ipn->tunnels_wc[0], tunnel); + return 0; } -static struct xfrm_tunnel ipip_handler = { +static struct xfrm_tunnel ipip_handler __read_mostly = { .handler = ipip_rcv, .err_handler = ipip_err, .priority = 1, @@ -760,11 +828,12 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) for (prio = 1; prio < 4; prio++) { int h; for (h = 0; h < HASH_SIZE; h++) { - struct ip_tunnel *t = ipn->tunnels[prio][h]; + struct ip_tunnel *t; + t = rtnl_dereference(ipn->tunnels[prio][h]); while (t != NULL) { unregister_netdevice_queue(t->dev, head); - t = t->next; + t = rtnl_dereference(t->next); } } } @@ -789,7 +858,9 @@ static int __net_init ipip_init_net(struct net *net) } dev_net_set(ipn->fb_tunnel_dev, net); - ipip_fb_tunnel_init(ipn->fb_tunnel_dev); + err = ipip_fb_tunnel_init(ipn->fb_tunnel_dev); + if (err) + goto err_reg_dev; if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; @@ -797,7 +868,7 @@ static int __net_init ipip_init_net(struct net *net) return 0; err_reg_dev: - free_netdev(ipn->fb_tunnel_dev); + ipip_dev_free(ipn->fb_tunnel_dev); err_alloc_dev: /* nothing */ return err; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 179fcab866f..86dd5691af4 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -75,7 +75,7 @@ struct mr_table { struct net *net; #endif u32 id; - struct sock *mroute_sk; + struct sock __rcu *mroute_sk; struct timer_list ipmr_expire_timer; struct list_head mfc_unres_queue; struct list_head mfc_cache_array[MFC_LINES]; @@ -98,7 +98,7 @@ struct ipmr_result { }; /* Big lock, protecting vif table, mrt cache and mroute socket state. - Note that the changes are semaphored via rtnl_lock. + * Note that the changes are semaphored via rtnl_lock. */ static DEFINE_RWLOCK(mrt_lock); @@ -113,11 +113,11 @@ static DEFINE_RWLOCK(mrt_lock); static DEFINE_SPINLOCK(mfc_unres_lock); /* We return to original Alan's scheme. Hash table of resolved - entries is changed only in process context and protected - with weak lock mrt_lock. Queue of unresolved entries is protected - with strong spinlock mfc_unres_lock. - - In this case data path is free of exclusive locks at all. + * entries is changed only in process context and protected + * with weak lock mrt_lock. Queue of unresolved entries is protected + * with strong spinlock mfc_unres_lock. + * + * In this case data path is free of exclusive locks at all. */ static struct kmem_cache *mrt_cachep __read_mostly; @@ -396,9 +396,9 @@ struct net_device *ipmr_new_tunnel(struct net *net, struct vifctl *v) set_fs(KERNEL_DS); err = ops->ndo_do_ioctl(dev, &ifr, SIOCADDTUNNEL); set_fs(oldfs); - } else + } else { err = -EOPNOTSUPP; - + } dev = NULL; if (err == 0 && @@ -495,7 +495,8 @@ static struct net_device *ipmr_reg_vif(struct net *net, struct mr_table *mrt) dev->iflink = 0; rcu_read_lock(); - if ((in_dev = __in_dev_get_rcu(dev)) == NULL) { + in_dev = __in_dev_get_rcu(dev); + if (!in_dev) { rcu_read_unlock(); goto failure; } @@ -552,9 +553,10 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, mrt->mroute_reg_vif_num = -1; #endif - if (vifi+1 == mrt->maxvif) { + if (vifi + 1 == mrt->maxvif) { int tmp; - for (tmp=vifi-1; tmp>=0; tmp--) { + + for (tmp = vifi - 1; tmp >= 0; tmp--) { if (VIF_EXISTS(mrt, tmp)) break; } @@ -565,25 +567,33 @@ static int vif_delete(struct mr_table *mrt, int vifi, int notify, dev_set_allmulti(dev, -1); - if ((in_dev = __in_dev_get_rtnl(dev)) != NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (in_dev) { IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)--; ip_rt_multicast_event(in_dev); } - if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER) && !notify) + if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER) && !notify) unregister_netdevice_queue(dev, head); dev_put(dev); return 0; } -static inline void ipmr_cache_free(struct mfc_cache *c) +static void ipmr_cache_free_rcu(struct rcu_head *head) { + struct mfc_cache *c = container_of(head, struct mfc_cache, rcu); + kmem_cache_free(mrt_cachep, c); } +static inline void ipmr_cache_free(struct mfc_cache *c) +{ + call_rcu(&c->rcu, ipmr_cache_free_rcu); +} + /* Destroy an unresolved cache entry, killing queued skbs - and reporting error to netlink readers. + * and reporting error to netlink readers. */ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) @@ -605,8 +615,9 @@ static void ipmr_destroy_unres(struct mr_table *mrt, struct mfc_cache *c) memset(&e->msg, 0, sizeof(e->msg)); rtnl_unicast(skb, net, NETLINK_CB(skb).pid); - } else + } else { kfree_skb(skb); + } } ipmr_cache_free(c); @@ -724,13 +735,13 @@ static int vif_add(struct net *net, struct mr_table *mrt, case 0: if (vifc->vifc_flags == VIFF_USE_IFINDEX) { dev = dev_get_by_index(net, vifc->vifc_lcl_ifindex); - if (dev && dev->ip_ptr == NULL) { + if (dev && __in_dev_get_rtnl(dev) == NULL) { dev_put(dev); return -EADDRNOTAVAIL; } - } else + } else { dev = ip_dev_find(net, vifc->vifc_lcl_addr.s_addr); - + } if (!dev) return -EADDRNOTAVAIL; err = dev_set_allmulti(dev, 1); @@ -743,16 +754,16 @@ static int vif_add(struct net *net, struct mr_table *mrt, return -EINVAL; } - if ((in_dev = __in_dev_get_rtnl(dev)) == NULL) { + in_dev = __in_dev_get_rtnl(dev); + if (!in_dev) { dev_put(dev); return -EADDRNOTAVAIL; } IPV4_DEVCONF(in_dev->cnf, MC_FORWARDING)++; ip_rt_multicast_event(in_dev); - /* - * Fill in the VIF structures - */ + /* 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; @@ -765,14 +776,14 @@ static int vif_add(struct net *net, struct mr_table *mrt, v->pkt_in = 0; v->pkt_out = 0; v->link = dev->ifindex; - if (v->flags&(VIFF_TUNNEL|VIFF_REGISTER)) + if (v->flags & (VIFF_TUNNEL | VIFF_REGISTER)) v->link = dev->iflink; /* And finish update writing critical data */ write_lock_bh(&mrt_lock); v->dev = dev; #ifdef CONFIG_IP_PIMSM - if (v->flags&VIFF_REGISTER) + if (v->flags & VIFF_REGISTER) mrt->mroute_reg_vif_num = vifi; #endif if (vifi+1 > mrt->maxvif) @@ -781,6 +792,7 @@ static int vif_add(struct net *net, struct mr_table *mrt, return 0; } +/* called with rcu_read_lock() */ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, __be32 origin, __be32 mcastgrp) @@ -788,7 +800,7 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, int line = MFC_HASH(mcastgrp, origin); struct mfc_cache *c; - list_for_each_entry(c, &mrt->mfc_cache_array[line], list) { + list_for_each_entry_rcu(c, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == origin && c->mfc_mcastgrp == mcastgrp) return c; } @@ -801,19 +813,20 @@ static struct mfc_cache *ipmr_cache_find(struct mr_table *mrt, static struct mfc_cache *ipmr_cache_alloc(void) { struct mfc_cache *c = kmem_cache_zalloc(mrt_cachep, GFP_KERNEL); - if (c == NULL) - return NULL; - c->mfc_un.res.minvif = MAXVIFS; + + if (c) + c->mfc_un.res.minvif = MAXVIFS; return c; } static struct mfc_cache *ipmr_cache_alloc_unres(void) { 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; + + if (c) { + skb_queue_head_init(&c->mfc_un.unres.unresolved); + c->mfc_un.unres.expires = jiffies + 10*HZ; + } return c; } @@ -827,17 +840,15 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, struct sk_buff *skb; struct nlmsgerr *e; - /* - * Play the pending entries through our router - */ + /* Play the pending entries through our router */ 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)); if (__ipmr_fill_mroute(mrt, skb, c, NLMSG_DATA(nlh)) > 0) { - nlh->nlmsg_len = (skb_tail_pointer(skb) - - (u8 *)nlh); + nlh->nlmsg_len = skb_tail_pointer(skb) - + (u8 *)nlh; } else { nlh->nlmsg_type = NLMSG_ERROR; nlh->nlmsg_len = NLMSG_LENGTH(sizeof(struct nlmsgerr)); @@ -848,8 +859,9 @@ static void ipmr_cache_resolve(struct net *net, struct mr_table *mrt, } rtnl_unicast(skb, net, NETLINK_CB(skb).pid); - } else + } else { ip_mr_forward(net, mrt, skb, c, 0); + } } } @@ -867,6 +879,7 @@ static int ipmr_cache_report(struct mr_table *mrt, const int ihl = ip_hdrlen(pkt); struct igmphdr *igmp; struct igmpmsg *msg; + struct sock *mroute_sk; int ret; #ifdef CONFIG_IP_PIMSM @@ -882,9 +895,9 @@ static int ipmr_cache_report(struct mr_table *mrt, #ifdef CONFIG_IP_PIMSM if (assert == IGMPMSG_WHOLEPKT) { /* Ugly, but we have no choice with this interface. - Duplicate old header, fix ihl, length etc. - And all this only to mangle msg->im_msgtype and - to set msg->im_mbz to "mbz" :-) + * Duplicate old header, fix ihl, length etc. + * And all this only to mangle msg->im_msgtype and + * to set msg->im_mbz to "mbz" :-) */ skb_push(skb, sizeof(struct iphdr)); skb_reset_network_header(skb); @@ -901,39 +914,38 @@ static int ipmr_cache_report(struct mr_table *mrt, #endif { - /* - * Copy the IP header - */ + /* Copy the IP header */ skb->network_header = skb->tail; skb_put(skb, ihl); skb_copy_to_linear_data(skb, pkt->data, ihl); - ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ + ip_hdr(skb)->protocol = 0; /* Flag to the kernel this is a route add */ msg = (struct igmpmsg *)skb_network_header(skb); msg->im_vif = vifi; skb_dst_set(skb, dst_clone(skb_dst(pkt))); - /* - * Add our header - */ + /* 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; - ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ + igmp->code = 0; + ip_hdr(skb)->tot_len = htons(skb->len); /* Fix the length */ skb->transport_header = skb->network_header; } - if (mrt->mroute_sk == NULL) { + rcu_read_lock(); + mroute_sk = rcu_dereference(mrt->mroute_sk); + if (mroute_sk == NULL) { + rcu_read_unlock(); kfree_skb(skb); return -EINVAL; } - /* - * Deliver to mrouted - */ - ret = sock_queue_rcv_skb(mrt->mroute_sk, skb); + /* Deliver to mrouted */ + + ret = sock_queue_rcv_skb(mroute_sk, skb); + rcu_read_unlock(); if (ret < 0) { if (net_ratelimit()) printk(KERN_WARNING "mroute: pending queue full, dropping entries.\n"); @@ -965,9 +977,7 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) } if (!found) { - /* - * Create a new entry if allowable - */ + /* Create a new entry if allowable */ if (atomic_read(&mrt->cache_resolve_queue_len) >= 10 || (c = ipmr_cache_alloc_unres()) == NULL) { @@ -977,16 +987,14 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) return -ENOBUFS; } - /* - * Fill in the new cache entry - */ + /* Fill in the new cache entry */ + c->mfc_parent = -1; c->mfc_origin = iph->saddr; c->mfc_mcastgrp = iph->daddr; - /* - * Reflect first query at mrouted. - */ + /* Reflect first query at mrouted. */ + err = ipmr_cache_report(mrt, skb, vifi, IGMPMSG_NOCACHE); if (err < 0) { /* If the report failed throw the cache entry @@ -1006,10 +1014,9 @@ ipmr_cache_unresolved(struct mr_table *mrt, vifi_t vifi, struct sk_buff *skb) mod_timer(&mrt->ipmr_expire_timer, c->mfc_un.unres.expires); } - /* - * See if we can append the packet - */ - if (c->mfc_un.unres.unresolved.qlen>3) { + /* See if we can append the packet */ + + if (c->mfc_un.unres.unresolved.qlen > 3) { kfree_skb(skb); err = -ENOBUFS; } else { @@ -1035,9 +1042,7 @@ static int ipmr_mfc_delete(struct mr_table *mrt, struct mfcctl *mfc) list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[line], list) { if (c->mfc_origin == mfc->mfcc_origin.s_addr && c->mfc_mcastgrp == mfc->mfcc_mcastgrp.s_addr) { - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); + list_del_rcu(&c->list); ipmr_cache_free(c); return 0; @@ -1090,9 +1095,7 @@ static int ipmr_mfc_add(struct net *net, struct mr_table *mrt, if (!mrtsock) c->mfc_flags |= MFC_STATIC; - write_lock_bh(&mrt_lock); - list_add(&c->list, &mrt->mfc_cache_array[line]); - write_unlock_bh(&mrt_lock); + list_add_rcu(&c->list, &mrt->mfc_cache_array[line]); /* * Check to see if we resolved a queued list. If so we @@ -1130,26 +1133,21 @@ static void mroute_clean_tables(struct mr_table *mrt) LIST_HEAD(list); struct mfc_cache *c, *next; - /* - * Shut down all active vif entries - */ + /* Shut down all active vif entries */ + for (i = 0; i < mrt->maxvif; i++) { - if (!(mrt->vif_table[i].flags&VIFF_STATIC)) + if (!(mrt->vif_table[i].flags & VIFF_STATIC)) vif_delete(mrt, i, 0, &list); } unregister_netdevice_many(&list); - /* - * Wipe the cache - */ + /* Wipe the cache */ + for (i = 0; i < MFC_LINES; i++) { list_for_each_entry_safe(c, next, &mrt->mfc_cache_array[i], list) { - if (c->mfc_flags&MFC_STATIC) + if (c->mfc_flags & MFC_STATIC) continue; - write_lock_bh(&mrt_lock); - list_del(&c->list); - write_unlock_bh(&mrt_lock); - + list_del_rcu(&c->list); ipmr_cache_free(c); } } @@ -1164,6 +1162,9 @@ static void mroute_clean_tables(struct mr_table *mrt) } } +/* called from ip_ra_control(), before an RCU grace period, + * we dont need to call synchronize_rcu() here + */ static void mrtsock_destruct(struct sock *sk) { struct net *net = sock_net(sk); @@ -1171,13 +1172,9 @@ static void mrtsock_destruct(struct sock *sk) rtnl_lock(); ipmr_for_each_table(mrt, net) { - if (sk == mrt->mroute_sk) { + if (sk == rtnl_dereference(mrt->mroute_sk)) { IPV4_DEVCONF_ALL(net, MC_FORWARDING)--; - - write_lock_bh(&mrt_lock); - mrt->mroute_sk = NULL; - write_unlock_bh(&mrt_lock); - + rcu_assign_pointer(mrt->mroute_sk, NULL); mroute_clean_tables(mrt); } } @@ -1204,7 +1201,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOENT; if (optname != MRT_INIT) { - if (sk != mrt->mroute_sk && !capable(CAP_NET_ADMIN)) + if (sk != rcu_dereference_raw(mrt->mroute_sk) && + !capable(CAP_NET_ADMIN)) return -EACCES; } @@ -1217,23 +1215,20 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENOPROTOOPT; rtnl_lock(); - if (mrt->mroute_sk) { + if (rtnl_dereference(mrt->mroute_sk)) { rtnl_unlock(); return -EADDRINUSE; } ret = ip_ra_control(sk, 1, mrtsock_destruct); if (ret == 0) { - write_lock_bh(&mrt_lock); - mrt->mroute_sk = sk; - write_unlock_bh(&mrt_lock); - + rcu_assign_pointer(mrt->mroute_sk, sk); IPV4_DEVCONF_ALL(net, MC_FORWARDING)++; } rtnl_unlock(); return ret; case MRT_DONE: - if (sk != mrt->mroute_sk) + if (sk != rcu_dereference_raw(mrt->mroute_sk)) return -EACCES; return ip_ra_control(sk, 0, NULL); case MRT_ADD_VIF: @@ -1246,7 +1241,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -ENFILE; rtnl_lock(); if (optname == MRT_ADD_VIF) { - ret = vif_add(net, mrt, &vif, sk == mrt->mroute_sk); + ret = vif_add(net, mrt, &vif, + sk == rtnl_dereference(mrt->mroute_sk)); } else { ret = vif_delete(mrt, vif.vifc_vifi, 0, NULL); } @@ -1267,7 +1263,8 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi if (optname == MRT_DEL_MFC) ret = ipmr_mfc_delete(mrt, &mfc); else - ret = ipmr_mfc_add(net, mrt, &mfc, sk == mrt->mroute_sk); + ret = ipmr_mfc_add(net, mrt, &mfc, + sk == rtnl_dereference(mrt->mroute_sk)); rtnl_unlock(); return ret; /* @@ -1276,7 +1273,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi case MRT_ASSERT: { int v; - if (get_user(v,(int __user *)optval)) + if (get_user(v, (int __user *)optval)) return -EFAULT; mrt->mroute_do_assert = (v) ? 1 : 0; return 0; @@ -1286,7 +1283,7 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi { int v; - if (get_user(v,(int __user *)optval)) + if (get_user(v, (int __user *)optval)) return -EFAULT; v = (v) ? 1 : 0; @@ -1309,14 +1306,16 @@ int ip_mroute_setsockopt(struct sock *sk, int optname, char __user *optval, unsi return -EINVAL; if (get_user(v, (u32 __user *)optval)) return -EFAULT; - if (sk == mrt->mroute_sk) - return -EBUSY; rtnl_lock(); ret = 0; - if (!ipmr_new_table(net, v)) - ret = -ENOMEM; - raw_sk(sk)->ipmr_table = v; + if (sk == rtnl_dereference(mrt->mroute_sk)) { + ret = -EBUSY; + } else { + if (!ipmr_new_table(net, v)) + ret = -ENOMEM; + raw_sk(sk)->ipmr_table = v; + } rtnl_unlock(); return ret; } @@ -1347,9 +1346,9 @@ int ip_mroute_getsockopt(struct sock *sk, int optname, char __user *optval, int if (optname != MRT_VERSION && #ifdef CONFIG_IP_PIMSM - optname!=MRT_PIM && + optname != MRT_PIM && #endif - optname!=MRT_ASSERT) + optname != MRT_ASSERT) return -ENOPROTOOPT; if (get_user(olr, optlen)) @@ -1416,19 +1415,19 @@ int ipmr_ioctl(struct sock *sk, int cmd, void __user *arg) if (copy_from_user(&sr, arg, sizeof(sr))) return -EFAULT; - read_lock(&mrt_lock); + rcu_read_lock(); c = ipmr_cache_find(mrt, sr.src.s_addr, sr.grp.s_addr); if (c) { sr.pktcnt = c->mfc_un.res.pkt; sr.bytecnt = c->mfc_un.res.bytes; sr.wrong_if = c->mfc_un.res.wrong_if; - read_unlock(&mrt_lock); + rcu_read_unlock(); if (copy_to_user(arg, &sr, sizeof(sr))) return -EFAULT; return 0; } - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EADDRNOTAVAIL; default: return -ENOIOCTLCMD; @@ -1465,7 +1464,7 @@ static struct notifier_block ip_mr_notifier = { }; /* - * Encapsulate a packet by attaching a valid IPIP header to it. + * Encapsulate a packet by attaching a valid IPIP header to it. * This avoids tunnel drivers and other mess and gives us the speed so * important for multicast video. */ @@ -1480,7 +1479,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) skb_reset_network_header(skb); iph = ip_hdr(skb); - iph->version = 4; + iph->version = 4; iph->tos = old_iph->tos; iph->ttl = old_iph->ttl; iph->frag_off = 0; @@ -1498,7 +1497,7 @@ static void ip_encap(struct sk_buff *skb, __be32 saddr, __be32 daddr) static inline int ipmr_forward_finish(struct sk_buff *skb) { - struct ip_options * opt = &(IPCB(skb)->opt); + struct ip_options *opt = &(IPCB(skb)->opt); IP_INC_STATS_BH(dev_net(skb_dst(skb)->dev), IPSTATS_MIB_OUTFORWDATAGRAMS); @@ -1535,22 +1534,34 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, } #endif - if (vif->flags&VIFF_TUNNEL) { - struct flowi fl = { .oif = vif->link, - .nl_u = { .ip4_u = - { .daddr = vif->remote, - .saddr = vif->local, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_IPIP }; + if (vif->flags & VIFF_TUNNEL) { + struct flowi fl = { + .oif = vif->link, + .nl_u = { + .ip4_u = { + .daddr = vif->remote, + .saddr = vif->local, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_IPIP + }; + if (ip_route_output_key(net, &rt, &fl)) goto out_free; encap = sizeof(struct iphdr); } else { - struct flowi fl = { .oif = vif->link, - .nl_u = { .ip4_u = - { .daddr = iph->daddr, - .tos = RT_TOS(iph->tos) } }, - .proto = IPPROTO_IPIP }; + struct flowi fl = { + .oif = vif->link, + .nl_u = { + .ip4_u = { + .daddr = iph->daddr, + .tos = RT_TOS(iph->tos) + } + }, + .proto = IPPROTO_IPIP + }; + if (ip_route_output_key(net, &rt, &fl)) goto out_free; } @@ -1559,8 +1570,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, if (skb->len+encap > dst_mtu(&rt->dst) && (ntohs(iph->frag_off) & IP_DF)) { /* Do not fragment multicasts. Alas, IPv4 does not - allow to send ICMP, so that packets will disappear - to blackhole. + * allow to send ICMP, so that packets will disappear + * to blackhole. */ IP_INC_STATS_BH(dev_net(dev), IPSTATS_MIB_FRAGFAILS); @@ -1583,7 +1594,8 @@ static void ipmr_queue_xmit(struct net *net, struct mr_table *mrt, ip_decrease_ttl(ip_hdr(skb)); /* FIXME: forward and output firewalls used to be called here. - * What do we do with netfilter? -- RR */ + * What do we do with netfilter? -- RR + */ if (vif->flags & VIFF_TUNNEL) { ip_encap(skb, vif->local, vif->remote); /* FIXME: extra output firewall step used to be here. --RR */ @@ -1644,15 +1656,15 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (skb_rtable(skb)->fl.iif == 0) { /* It is our own packet, looped back. - Very complicated situation... - - The best workaround until routing daemons will be - fixed is not to redistribute packet, if it was - send through wrong interface. It means, that - multicast applications WILL NOT work for - (S,G), which have default multicast route pointing - to wrong oif. In any case, it is not a good - idea to use multicasting applications on router. + * Very complicated situation... + * + * The best workaround until routing daemons will be + * fixed is not to redistribute packet, if it was + * send through wrong interface. It means, that + * multicast applications WILL NOT work for + * (S,G), which have default multicast route pointing + * to wrong oif. In any case, it is not a good + * idea to use multicasting applications on router. */ goto dont_forward; } @@ -1662,9 +1674,9 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (true_vifi >= 0 && mrt->mroute_do_assert && /* pimsm uses asserts, when switching from RPT to SPT, - so that we cannot check that packet arrived on an oif. - It is bad, but otherwise we would need to move pretty - large chunk of pimd to kernel. Ough... --ANK + * so that we cannot check that packet arrived on an oif. + * It is bad, but otherwise we would need to move pretty + * large chunk of pimd to kernel. Ough... --ANK */ (mrt->mroute_do_pim || cache->mfc_un.res.ttls[true_vifi] < 255) && @@ -1682,10 +1694,12 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, /* * Forward the frame */ - for (ct = cache->mfc_un.res.maxvif-1; ct >= cache->mfc_un.res.minvif; ct--) { + for (ct = cache->mfc_un.res.maxvif - 1; + ct >= cache->mfc_un.res.minvif; ct--) { if (ip_hdr(skb)->ttl > cache->mfc_un.res.ttls[ct]) { if (psend != -1) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) ipmr_queue_xmit(net, mrt, skb2, cache, psend); @@ -1696,6 +1710,7 @@ static int ip_mr_forward(struct net *net, struct mr_table *mrt, if (psend != -1) { if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); + if (skb2) ipmr_queue_xmit(net, mrt, skb2, cache, psend); } else { @@ -1713,6 +1728,7 @@ dont_forward: /* * Multicast packets for forwarding arrive here + * Called with rcu_read_lock(); */ int ip_mr_input(struct sk_buff *skb) @@ -1724,9 +1740,9 @@ int ip_mr_input(struct sk_buff *skb) int err; /* Packet is looped back after forward, it should not be - forwarded second time, but still can be delivered locally. + * forwarded second time, but still can be delivered locally. */ - if (IPCB(skb)->flags&IPSKB_FORWARDED) + if (IPCB(skb)->flags & IPSKB_FORWARDED) goto dont_forward; err = ipmr_fib_lookup(net, &skb_rtable(skb)->fl, &mrt); @@ -1736,28 +1752,28 @@ int ip_mr_input(struct sk_buff *skb) } if (!local) { - if (IPCB(skb)->opt.router_alert) { - if (ip_call_ra_chain(skb)) - return 0; - } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP){ - /* IGMPv1 (and broken IGMPv2 implementations sort of - Cisco IOS <= 11.2(8)) do not put router alert - option to IGMP packets destined to routable - groups. It is very bad, because it means - that we can forward NO IGMP messages. - */ - read_lock(&mrt_lock); - if (mrt->mroute_sk) { - nf_reset(skb); - raw_rcv(mrt->mroute_sk, skb); - read_unlock(&mrt_lock); - return 0; - } - read_unlock(&mrt_lock); + if (IPCB(skb)->opt.router_alert) { + if (ip_call_ra_chain(skb)) + return 0; + } else if (ip_hdr(skb)->protocol == IPPROTO_IGMP) { + /* IGMPv1 (and broken IGMPv2 implementations sort of + * Cisco IOS <= 11.2(8)) do not put router alert + * option to IGMP packets destined to routable + * groups. It is very bad, because it means + * that we can forward NO IGMP messages. + */ + struct sock *mroute_sk; + + mroute_sk = rcu_dereference(mrt->mroute_sk); + if (mroute_sk) { + nf_reset(skb); + raw_rcv(mroute_sk, skb); + return 0; + } } } - read_lock(&mrt_lock); + /* already under rcu_read_lock() */ cache = ipmr_cache_find(mrt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr); /* @@ -1769,13 +1785,12 @@ int ip_mr_input(struct sk_buff *skb) if (local) { struct sk_buff *skb2 = skb_clone(skb, GFP_ATOMIC); ip_local_deliver(skb); - if (skb2 == NULL) { - read_unlock(&mrt_lock); + if (skb2 == NULL) return -ENOBUFS; - } skb = skb2; } + read_lock(&mrt_lock); vif = ipmr_find_vif(mrt, skb->dev); if (vif >= 0) { int err2 = ipmr_cache_unresolved(mrt, vif, skb); @@ -1788,8 +1803,8 @@ int ip_mr_input(struct sk_buff *skb) return -ENODEV; } + read_lock(&mrt_lock); ip_mr_forward(net, mrt, skb, cache, local); - read_unlock(&mrt_lock); if (local) @@ -1805,6 +1820,7 @@ dont_forward: } #ifdef CONFIG_IP_PIMSM +/* called with rcu_read_lock() */ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, unsigned int pimlen) { @@ -1813,10 +1829,10 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, encap = (struct iphdr *)(skb_transport_header(skb) + pimlen); /* - Check that: - a. packet is really destinted to a multicast group - b. packet is not a NULL-REGISTER - c. packet is not truncated + * Check that: + * a. packet is really sent to a multicast group + * b. packet is not a NULL-REGISTER + * c. packet is not truncated */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || @@ -1826,26 +1842,23 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, read_lock(&mrt_lock); if (mrt->mroute_reg_vif_num >= 0) reg_dev = mrt->vif_table[mrt->mroute_reg_vif_num].dev; - if (reg_dev) - dev_hold(reg_dev); read_unlock(&mrt_lock); if (reg_dev == NULL) return 1; skb->mac_header = skb->network_header; - skb_pull(skb, (u8*)encap - skb->data); + skb_pull(skb, (u8 *)encap - skb->data); skb_reset_network_header(skb); skb->protocol = htons(ETH_P_IP); - skb->ip_summed = 0; + skb->ip_summed = CHECKSUM_NONE; skb->pkt_type = PACKET_HOST; skb_tunnel_rx(skb, reg_dev); netif_rx(skb); - dev_put(reg_dev); - return 0; + return NET_RX_SUCCESS; } #endif @@ -1854,7 +1867,7 @@ static int __pim_rcv(struct mr_table *mrt, struct sk_buff *skb, * Handle IGMP messages of PIMv1 */ -int pim_rcv_v1(struct sk_buff * skb) +int pim_rcv_v1(struct sk_buff *skb) { struct igmphdr *pim; struct net *net = dev_net(skb->dev); @@ -1881,7 +1894,7 @@ drop: #endif #ifdef CONFIG_IP_PIMSM_V2 -static int pim_rcv(struct sk_buff * skb) +static int pim_rcv(struct sk_buff *skb) { struct pimreghdr *pim; struct net *net = dev_net(skb->dev); @@ -1891,8 +1904,8 @@ static int pim_rcv(struct sk_buff * skb) goto drop; pim = (struct pimreghdr *)skb_transport_header(skb); - if (pim->type != ((PIM_VERSION<<4)|(PIM_REGISTER)) || - (pim->flags&PIM_NULL_REGISTER) || + if (pim->type != ((PIM_VERSION << 4) | (PIM_REGISTER)) || + (pim->flags & PIM_NULL_REGISTER) || (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && csum_fold(skb_checksum(skb, 0, skb->len, 0)))) goto drop; @@ -1958,28 +1971,33 @@ int ipmr_get_route(struct net *net, if (mrt == NULL) return -ENOENT; - read_lock(&mrt_lock); + rcu_read_lock(); cache = ipmr_cache_find(mrt, rt->rt_src, rt->rt_dst); if (cache == NULL) { struct sk_buff *skb2; struct iphdr *iph; struct net_device *dev; - int vif; + int vif = -1; if (nowait) { - read_unlock(&mrt_lock); + rcu_read_unlock(); return -EAGAIN; } dev = skb->dev; - if (dev == NULL || (vif = ipmr_find_vif(mrt, dev)) < 0) { + read_lock(&mrt_lock); + if (dev) + vif = ipmr_find_vif(mrt, dev); + if (vif < 0) { read_unlock(&mrt_lock); + rcu_read_unlock(); return -ENODEV; } skb2 = skb_clone(skb, GFP_ATOMIC); if (!skb2) { read_unlock(&mrt_lock); + rcu_read_unlock(); return -ENOMEM; } @@ -1992,13 +2010,16 @@ int ipmr_get_route(struct net *net, iph->version = 0; err = ipmr_cache_unresolved(mrt, vif, skb2); read_unlock(&mrt_lock); + rcu_read_unlock(); return err; } - if (!nowait && (rtm->rtm_flags&RTM_F_NOTIFY)) + read_lock(&mrt_lock); + if (!nowait && (rtm->rtm_flags & RTM_F_NOTIFY)) cache->mfc_flags |= MFC_NOTIFY; err = __ipmr_fill_mroute(mrt, skb, cache, rtm); read_unlock(&mrt_lock); + rcu_read_unlock(); return err; } @@ -2050,14 +2071,14 @@ static int ipmr_rtm_dumproute(struct sk_buff *skb, struct netlink_callback *cb) s_h = cb->args[1]; s_e = cb->args[2]; - read_lock(&mrt_lock); + rcu_read_lock(); ipmr_for_each_table(mrt, net) { if (t < s_t) goto next_table; if (t > s_t) s_h = 0; for (h = s_h; h < MFC_LINES; h++) { - list_for_each_entry(mfc, &mrt->mfc_cache_array[h], list) { + list_for_each_entry_rcu(mfc, &mrt->mfc_cache_array[h], list) { if (e < s_e) goto next_entry; if (ipmr_fill_mroute(mrt, skb, @@ -2075,7 +2096,7 @@ next_table: t++; } done: - read_unlock(&mrt_lock); + rcu_read_unlock(); cb->args[2] = e; cb->args[1] = h; @@ -2086,7 +2107,8 @@ done: #ifdef CONFIG_PROC_FS /* - * The /proc interfaces to multicast routing /proc/ip_mr_cache /proc/ip_mr_vif + * The /proc interfaces to multicast routing : + * /proc/net/ip_mr_cache & /proc/net/ip_mr_vif */ struct ipmr_vif_iter { struct seq_net_private p; @@ -2208,14 +2230,14 @@ static struct mfc_cache *ipmr_mfc_seq_idx(struct net *net, struct mr_table *mrt = it->mrt; struct mfc_cache *mfc; - read_lock(&mrt_lock); + rcu_read_lock(); for (it->ct = 0; it->ct < MFC_LINES; it->ct++) { it->cache = &mrt->mfc_cache_array[it->ct]; - list_for_each_entry(mfc, it->cache, list) + list_for_each_entry_rcu(mfc, it->cache, list) if (pos-- == 0) return mfc; } - read_unlock(&mrt_lock); + rcu_read_unlock(); spin_lock_bh(&mfc_unres_lock); it->cache = &mrt->mfc_unres_queue; @@ -2274,7 +2296,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) } /* exhausted cache_array, show unresolved */ - read_unlock(&mrt_lock); + rcu_read_unlock(); it->cache = &mrt->mfc_unres_queue; it->ct = 0; @@ -2282,7 +2304,7 @@ static void *ipmr_mfc_seq_next(struct seq_file *seq, void *v, loff_t *pos) if (!list_empty(it->cache)) return list_first_entry(it->cache, struct mfc_cache, list); - end_of_list: +end_of_list: spin_unlock_bh(&mfc_unres_lock); it->cache = NULL; @@ -2297,7 +2319,7 @@ static void ipmr_mfc_seq_stop(struct seq_file *seq, void *v) if (it->cache == &mrt->mfc_unres_queue) spin_unlock_bh(&mfc_unres_lock); else if (it->cache == &mrt->mfc_cache_array[it->ct]) - read_unlock(&mrt_lock); + rcu_read_unlock(); } static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) @@ -2323,7 +2345,7 @@ static int ipmr_mfc_seq_show(struct seq_file *seq, void *v) 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++ ) { + n < mfc->mfc_un.res.maxvif; n++) { if (VIF_EXISTS(mrt, n) && mfc->mfc_un.res.ttls[n] < 255) seq_printf(seq, @@ -2421,7 +2443,7 @@ int __init ip_mr_init(void) mrt_cachep = kmem_cache_create("ip_mrt_cache", sizeof(struct mfc_cache), - 0, SLAB_HWCACHE_ALIGN|SLAB_PANIC, + 0, SLAB_HWCACHE_ALIGN | SLAB_PANIC, NULL); if (!mrt_cachep) return -ENOMEM; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1833bdbf980..babd1a2bae5 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -147,7 +147,7 @@ config IP_NF_TARGET_ULOG which can only be viewed through syslog. The appropriate userspace logging daemon (ulogd) may be obtained from - <http://www.gnumonks.org/projects/ulogd/> + <http://www.netfilter.org/projects/ulogd/index.html> To compile it as a module, choose M here. If unsure, say N. @@ -324,10 +324,10 @@ config IP_NF_TARGET_ECN config IP_NF_TARGET_TTL tristate '"TTL" target support' - depends on NETFILTER_ADVANCED + depends on NETFILTER_ADVANCED && IP_NF_MANGLE select NETFILTER_XT_TARGET_HL ---help--- - This is a backwards-compat option for the user's convenience + This is a backwards-compatible option for the user's convenience (e.g. when running oldconfig). It selects CONFIG_NETFILTER_XT_TARGET_HL. diff --git a/net/ipv4/netfilter/arp_tables.c b/net/ipv4/netfilter/arp_tables.c index e8f4f9a57f1..3cad2591ace 100644 --- a/net/ipv4/netfilter/arp_tables.c +++ b/net/ipv4/netfilter/arp_tables.c @@ -72,7 +72,7 @@ static inline int arp_devaddr_compare(const struct arpt_devaddr_info *ap, for (i = 0; i < len; i++) ret |= (hdr_addr[i] ^ ap->addr[i]) & ap->mask[i]; - return (ret != 0); + return ret != 0; } /* @@ -228,7 +228,7 @@ arpt_error(struct sk_buff *skb, const struct xt_action_param *par) return NF_DROP; } -static inline const struct arpt_entry_target * +static inline const struct xt_entry_target * arpt_get_target_c(const struct arpt_entry *e) { return arpt_get_target((struct arpt_entry *)e); @@ -282,7 +282,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, arp = arp_hdr(skb); do { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; if (!arp_packet_match(arp, skb->dev, indev, outdev, &e->arp)) { e = arpt_next_entry(e); @@ -297,10 +297,10 @@ unsigned int arpt_do_table(struct sk_buff *skb, if (!t->u.kernel.target->target) { int v; - v = ((struct arpt_standard_target *)t)->verdict; + v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ - if (v != ARPT_RETURN) { + if (v != XT_RETURN) { verdict = (unsigned)(-v) - 1; break; } @@ -332,7 +332,7 @@ unsigned int arpt_do_table(struct sk_buff *skb, /* Target might have changed stuff. */ arp = arp_hdr(skb); - if (verdict == ARPT_CONTINUE) + if (verdict == XT_CONTINUE) e = arpt_next_entry(e); else /* Verdict */ @@ -377,7 +377,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - const struct arpt_standard_target *t + const struct xt_standard_target *t = (void *)arpt_get_target_c(e); int visited = e->comefrom & (1 << hook); @@ -392,13 +392,13 @@ static int mark_source_chains(const struct xt_table_info *newinfo, /* Unconditional return/END. */ if ((e->target_offset == sizeof(struct arpt_entry) && (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < 0 && unconditional(&e->arp)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -433,7 +433,7 @@ static int mark_source_chains(const struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - ARPT_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && newpos >= 0) { if (newpos > newinfo->size - sizeof(struct arpt_entry)) { @@ -464,14 +464,14 @@ static int mark_source_chains(const struct xt_table_info *newinfo, static inline int check_entry(const struct arpt_entry *e, const char *name) { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; if (!arp_checkentry(&e->arp)) { duprintf("arp_tables: arp check failed %p %s.\n", e, name); return -EINVAL; } - if (e->target_offset + sizeof(struct arpt_entry_target) > e->next_offset) + if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; t = arpt_get_target_c(e); @@ -483,7 +483,7 @@ static inline int check_entry(const struct arpt_entry *e, const char *name) static inline int check_target(struct arpt_entry *e, const char *name) { - struct arpt_entry_target *t = arpt_get_target(e); + struct xt_entry_target *t = arpt_get_target(e); int ret; struct xt_tgchk_param par = { .table = name, @@ -506,7 +506,7 @@ static inline int check_target(struct arpt_entry *e, const char *name) static inline int find_check_entry(struct arpt_entry *e, const char *name, unsigned int size) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; int ret; @@ -536,7 +536,7 @@ out: static bool check_underflow(const struct arpt_entry *e) { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(&e->arp)) @@ -544,7 +544,7 @@ static bool check_underflow(const struct arpt_entry *e) t = arpt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; - verdict = ((struct arpt_standard_target *)t)->verdict; + verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } @@ -566,7 +566,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, } if (e->next_offset - < sizeof(struct arpt_entry) + sizeof(struct arpt_entry_target)) { + < sizeof(struct arpt_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; @@ -598,7 +598,7 @@ static inline int check_entry_size_and_hooks(struct arpt_entry *e, static inline void cleanup_entry(struct arpt_entry *e) { struct xt_tgdtor_param par; - struct arpt_entry_target *t; + struct xt_entry_target *t; t = arpt_get_target(e); par.target = t->u.kernel.target; @@ -794,7 +794,7 @@ static int copy_entries_to_user(unsigned int total_size, /* FIXME: use iterator macros --RR */ /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ - const struct arpt_entry_target *t; + const struct xt_entry_target *t; e = (struct arpt_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -807,7 +807,7 @@ static int copy_entries_to_user(unsigned int total_size, t = arpt_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct arpt_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -844,7 +844,7 @@ static int compat_calc_entry(const struct arpt_entry *e, const struct xt_table_info *info, const void *base, struct xt_table_info *newinfo) { - const struct arpt_entry_target *t; + const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; @@ -895,7 +895,7 @@ static int compat_table_info(const struct xt_table_info *info, static int get_info(struct net *net, void __user *user, const int *len, int compat) { - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; @@ -908,7 +908,7 @@ static int get_info(struct net *net, void __user *user, if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; - name[ARPT_TABLE_MAXNAMELEN-1] = '\0'; + name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT if (compat) xt_compat_lock(NFPROTO_ARP); @@ -1204,7 +1204,7 @@ static int do_add_counters(struct net *net, const void __user *user, #ifdef CONFIG_COMPAT static inline void compat_release_entry(struct compat_arpt_entry *e) { - struct arpt_entry_target *t; + struct xt_entry_target *t; t = compat_arpt_get_target(e); module_put(t->u.kernel.target->me); @@ -1220,7 +1220,7 @@ check_compat_entry_size_and_hooks(struct compat_arpt_entry *e, const unsigned int *underflows, const char *name) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; int ret, off, h; @@ -1288,7 +1288,7 @@ compat_copy_entry_from_user(struct compat_arpt_entry *e, void **dstptr, unsigned int *size, const char *name, struct xt_table_info *newinfo, unsigned char *base) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; struct arpt_entry *de; unsigned int origsize; @@ -1474,7 +1474,7 @@ out_unlock: } struct compat_arpt_replace { - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; @@ -1567,7 +1567,7 @@ static int compat_copy_entry_to_user(struct arpt_entry *e, void __user **dstptr, struct xt_counters *counters, unsigned int i) { - struct arpt_entry_target *t; + struct xt_entry_target *t; struct compat_arpt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; @@ -1628,7 +1628,7 @@ static int compat_copy_entries_to_user(unsigned int total_size, } struct compat_arpt_get_entries { - char name[ARPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_arpt_entry entrytable[0]; }; @@ -1828,7 +1828,7 @@ void arpt_unregister_table(struct xt_table *table) /* The built-in targets: standard (NULL) and error. */ static struct xt_target arpt_builtin_tg[] __read_mostly = { { - .name = ARPT_STANDARD_TARGET, + .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_ARP, #ifdef CONFIG_COMPAT @@ -1838,9 +1838,9 @@ static struct xt_target arpt_builtin_tg[] __read_mostly = { #endif }, { - .name = ARPT_ERROR_TARGET, + .name = XT_ERROR_TARGET, .target = arpt_error, - .targetsize = ARPT_FUNCTION_MAXNAMELEN, + .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_ARP, }, }; diff --git a/net/ipv4/netfilter/arpt_mangle.c b/net/ipv4/netfilter/arpt_mangle.c index e1be7dd1171..b8ddcc480ed 100644 --- a/net/ipv4/netfilter/arpt_mangle.c +++ b/net/ipv4/netfilter/arpt_mangle.c @@ -63,7 +63,7 @@ static int checkentry(const struct xt_tgchk_param *par) return false; if (mangle->target != NF_DROP && mangle->target != NF_ACCEPT && - mangle->target != ARPT_CONTINUE) + mangle->target != XT_CONTINUE) return false; return true; } diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index d163f2e3b2e..d31b007a6d8 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -186,7 +186,7 @@ static inline bool unconditional(const struct ipt_ip *ip) } /* for const-correctness */ -static inline const struct ipt_entry_target * +static inline const struct xt_entry_target * ipt_get_target_c(const struct ipt_entry *e) { return ipt_get_target((struct ipt_entry *)e); @@ -230,9 +230,9 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, const char *hookname, const char **chainname, const char **comment, unsigned int *rulenum) { - const struct ipt_standard_target *t = (void *)ipt_get_target_c(s); + const struct xt_standard_target *t = (void *)ipt_get_target_c(s); - if (strcmp(t->target.u.kernel.target->name, IPT_ERROR_TARGET) == 0) { + if (strcmp(t->target.u.kernel.target->name, XT_ERROR_TARGET) == 0) { /* Head of user chain: ERROR target with chainname */ *chainname = t->target.data; (*rulenum) = 0; @@ -241,7 +241,7 @@ get_chainname_rulenum(const struct ipt_entry *s, const struct ipt_entry *e, if (s->target_offset == sizeof(struct ipt_entry) && strcmp(t->target.u.kernel.target->name, - IPT_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && t->verdict < 0 && unconditional(&s->ip)) { /* Tail of chains: STANDARD target (return/policy) */ @@ -346,7 +346,7 @@ ipt_do_table(struct sk_buff *skb, get_entry(table_base, private->underflow[hook])); do { - const struct ipt_entry_target *t; + const struct xt_entry_target *t; const struct xt_entry_match *ematch; IP_NF_ASSERT(e); @@ -380,10 +380,10 @@ ipt_do_table(struct sk_buff *skb, if (!t->u.kernel.target->target) { int v; - v = ((struct ipt_standard_target *)t)->verdict; + v = ((struct xt_standard_target *)t)->verdict; if (v < 0) { /* Pop from stack? */ - if (v != IPT_RETURN) { + if (v != XT_RETURN) { verdict = (unsigned)(-v) - 1; break; } @@ -421,7 +421,7 @@ ipt_do_table(struct sk_buff *skb, verdict = t->u.kernel.target->target(skb, &acpar); /* Target might have changed stuff. */ ip = ip_hdr(skb); - if (verdict == IPT_CONTINUE) + if (verdict == XT_CONTINUE) e = ipt_next_entry(e); else /* Verdict */ @@ -461,7 +461,7 @@ mark_source_chains(const struct xt_table_info *newinfo, e->counters.pcnt = pos; for (;;) { - const struct ipt_standard_target *t + const struct xt_standard_target *t = (void *)ipt_get_target_c(e); int visited = e->comefrom & (1 << hook); @@ -475,13 +475,13 @@ mark_source_chains(const struct xt_table_info *newinfo, /* Unconditional return/END. */ if ((e->target_offset == sizeof(struct ipt_entry) && (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < 0 && unconditional(&e->ip)) || visited) { unsigned int oldpos, size; if ((strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0) && + XT_STANDARD_TARGET) == 0) && t->verdict < -NF_MAX_VERDICT - 1) { duprintf("mark_source_chains: bad " "negative verdict (%i)\n", @@ -524,7 +524,7 @@ mark_source_chains(const struct xt_table_info *newinfo, int newpos = t->verdict; if (strcmp(t->target.u.user.name, - IPT_STANDARD_TARGET) == 0 && + XT_STANDARD_TARGET) == 0 && newpos >= 0) { if (newpos > newinfo->size - sizeof(struct ipt_entry)) { @@ -552,7 +552,7 @@ mark_source_chains(const struct xt_table_info *newinfo, return 1; } -static void cleanup_match(struct ipt_entry_match *m, struct net *net) +static void cleanup_match(struct xt_entry_match *m, struct net *net) { struct xt_mtdtor_param par; @@ -568,14 +568,14 @@ static void cleanup_match(struct ipt_entry_match *m, struct net *net) static int check_entry(const struct ipt_entry *e, const char *name) { - const struct ipt_entry_target *t; + const struct xt_entry_target *t; if (!ip_checkentry(&e->ip)) { duprintf("ip check failed %p %s.\n", e, par->match->name); return -EINVAL; } - if (e->target_offset + sizeof(struct ipt_entry_target) > + if (e->target_offset + sizeof(struct xt_entry_target) > e->next_offset) return -EINVAL; @@ -587,7 +587,7 @@ check_entry(const struct ipt_entry *e, const char *name) } static int -check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) +check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { const struct ipt_ip *ip = par->entryinfo; int ret; @@ -605,7 +605,7 @@ check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) } static int -find_check_match(struct ipt_entry_match *m, struct xt_mtchk_param *par) +find_check_match(struct xt_entry_match *m, struct xt_mtchk_param *par) { struct xt_match *match; int ret; @@ -630,7 +630,7 @@ err: static int check_target(struct ipt_entry *e, struct net *net, const char *name) { - struct ipt_entry_target *t = ipt_get_target(e); + struct xt_entry_target *t = ipt_get_target(e); struct xt_tgchk_param par = { .net = net, .table = name, @@ -656,7 +656,7 @@ static int find_check_entry(struct ipt_entry *e, struct net *net, const char *name, unsigned int size) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; int ret; unsigned int j; @@ -707,7 +707,7 @@ find_check_entry(struct ipt_entry *e, struct net *net, const char *name, static bool check_underflow(const struct ipt_entry *e) { - const struct ipt_entry_target *t; + const struct xt_entry_target *t; unsigned int verdict; if (!unconditional(&e->ip)) @@ -715,7 +715,7 @@ static bool check_underflow(const struct ipt_entry *e) t = ipt_get_target_c(e); if (strcmp(t->u.user.name, XT_STANDARD_TARGET) != 0) return false; - verdict = ((struct ipt_standard_target *)t)->verdict; + verdict = ((struct xt_standard_target *)t)->verdict; verdict = -verdict - 1; return verdict == NF_DROP || verdict == NF_ACCEPT; } @@ -738,7 +738,7 @@ check_entry_size_and_hooks(struct ipt_entry *e, } if (e->next_offset - < sizeof(struct ipt_entry) + sizeof(struct ipt_entry_target)) { + < sizeof(struct ipt_entry) + sizeof(struct xt_entry_target)) { duprintf("checking: element %p size %u\n", e, e->next_offset); return -EINVAL; @@ -771,7 +771,7 @@ static void cleanup_entry(struct ipt_entry *e, struct net *net) { struct xt_tgdtor_param par; - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -972,8 +972,8 @@ copy_entries_to_user(unsigned int total_size, /* ... then go back and fix counters and names */ for (off = 0, num = 0; off < total_size; off += e->next_offset, num++){ unsigned int i; - const struct ipt_entry_match *m; - const struct ipt_entry_target *t; + const struct xt_entry_match *m; + const struct xt_entry_target *t; e = (struct ipt_entry *)(loc_cpu_entry + off); if (copy_to_user(userptr + off @@ -990,7 +990,7 @@ copy_entries_to_user(unsigned int total_size, m = (void *)e + i; if (copy_to_user(userptr + off + i - + offsetof(struct ipt_entry_match, + + offsetof(struct xt_entry_match, u.user.name), m->u.kernel.match->name, strlen(m->u.kernel.match->name)+1) @@ -1002,7 +1002,7 @@ copy_entries_to_user(unsigned int total_size, t = ipt_get_target_c(e); if (copy_to_user(userptr + off + e->target_offset - + offsetof(struct ipt_entry_target, + + offsetof(struct xt_entry_target, u.user.name), t->u.kernel.target->name, strlen(t->u.kernel.target->name)+1) != 0) { @@ -1040,7 +1040,7 @@ static int compat_calc_entry(const struct ipt_entry *e, const void *base, struct xt_table_info *newinfo) { const struct xt_entry_match *ematch; - const struct ipt_entry_target *t; + const struct xt_entry_target *t; unsigned int entry_offset; int off, i, ret; @@ -1092,7 +1092,7 @@ static int compat_table_info(const struct xt_table_info *info, static int get_info(struct net *net, void __user *user, const int *len, int compat) { - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; struct xt_table *t; int ret; @@ -1105,7 +1105,7 @@ static int get_info(struct net *net, void __user *user, if (copy_from_user(name, user, sizeof(name)) != 0) return -EFAULT; - name[IPT_TABLE_MAXNAMELEN-1] = '\0'; + name[XT_TABLE_MAXNAMELEN-1] = '\0'; #ifdef CONFIG_COMPAT if (compat) xt_compat_lock(AF_INET); @@ -1400,14 +1400,14 @@ do_add_counters(struct net *net, const void __user *user, #ifdef CONFIG_COMPAT struct compat_ipt_replace { - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; u32 valid_hooks; u32 num_entries; u32 size; u32 hook_entry[NF_INET_NUMHOOKS]; u32 underflow[NF_INET_NUMHOOKS]; u32 num_counters; - compat_uptr_t counters; /* struct ipt_counters * */ + compat_uptr_t counters; /* struct xt_counters * */ struct compat_ipt_entry entries[0]; }; @@ -1416,7 +1416,7 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, unsigned int *size, struct xt_counters *counters, unsigned int i) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct compat_ipt_entry __user *ce; u_int16_t target_offset, next_offset; compat_uint_t origsize; @@ -1451,7 +1451,7 @@ compat_copy_entry_to_user(struct ipt_entry *e, void __user **dstptr, } static int -compat_find_calc_match(struct ipt_entry_match *m, +compat_find_calc_match(struct xt_entry_match *m, const char *name, const struct ipt_ip *ip, unsigned int hookmask, @@ -1473,7 +1473,7 @@ compat_find_calc_match(struct ipt_entry_match *m, static void compat_release_entry(struct compat_ipt_entry *e) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_entry_match *ematch; /* Cleanup all matches */ @@ -1494,7 +1494,7 @@ check_compat_entry_size_and_hooks(struct compat_ipt_entry *e, const char *name) { struct xt_entry_match *ematch; - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; unsigned int entry_offset; unsigned int j; @@ -1576,7 +1576,7 @@ compat_copy_entry_from_user(struct compat_ipt_entry *e, void **dstptr, unsigned int *size, const char *name, struct xt_table_info *newinfo, unsigned char *base) { - struct ipt_entry_target *t; + struct xt_entry_target *t; struct xt_target *target; struct ipt_entry *de; unsigned int origsize; @@ -1884,7 +1884,7 @@ compat_do_ipt_set_ctl(struct sock *sk, int cmd, void __user *user, } struct compat_ipt_get_entries { - char name[IPT_TABLE_MAXNAMELEN]; + char name[XT_TABLE_MAXNAMELEN]; compat_uint_t size; struct compat_ipt_entry entrytable[0]; }; @@ -2039,7 +2039,7 @@ do_ipt_get_ctl(struct sock *sk, int cmd, void __user *user, int *len) case IPT_SO_GET_REVISION_MATCH: case IPT_SO_GET_REVISION_TARGET: { - struct ipt_get_revision rev; + struct xt_get_revision rev; int target; if (*len != sizeof(rev)) { @@ -2176,7 +2176,7 @@ static int icmp_checkentry(const struct xt_mtchk_param *par) static struct xt_target ipt_builtin_tg[] __read_mostly = { { - .name = IPT_STANDARD_TARGET, + .name = XT_STANDARD_TARGET, .targetsize = sizeof(int), .family = NFPROTO_IPV4, #ifdef CONFIG_COMPAT @@ -2186,9 +2186,9 @@ static struct xt_target ipt_builtin_tg[] __read_mostly = { #endif }, { - .name = IPT_ERROR_TARGET, + .name = XT_ERROR_TARGET, .target = ipt_error, - .targetsize = IPT_FUNCTION_MAXNAMELEN, + .targetsize = XT_FUNCTION_MAXNAMELEN, .family = NFPROTO_IPV4, }, }; diff --git a/net/ipv4/netfilter/ipt_CLUSTERIP.c b/net/ipv4/netfilter/ipt_CLUSTERIP.c index 3a43cf36db8..1e26a489765 100644 --- a/net/ipv4/netfilter/ipt_CLUSTERIP.c +++ b/net/ipv4/netfilter/ipt_CLUSTERIP.c @@ -29,6 +29,7 @@ #include <net/netfilter/nf_conntrack.h> #include <net/net_namespace.h> #include <net/checksum.h> +#include <net/ip.h> #define CLUSTERIP_VERSION "0.8" @@ -231,24 +232,22 @@ clusterip_hashfn(const struct sk_buff *skb, { const struct iphdr *iph = ip_hdr(skb); unsigned long hashval; - u_int16_t sport, dport; - const u_int16_t *ports; - - switch (iph->protocol) { - case IPPROTO_TCP: - case IPPROTO_UDP: - case IPPROTO_UDPLITE: - case IPPROTO_SCTP: - case IPPROTO_DCCP: - case IPPROTO_ICMP: - ports = (const void *)iph+iph->ihl*4; - sport = ports[0]; - dport = ports[1]; - break; - default: + u_int16_t sport = 0, dport = 0; + int poff; + + poff = proto_ports_offset(iph->protocol); + if (poff >= 0) { + const u_int16_t *ports; + u16 _ports[2]; + + ports = skb_header_pointer(skb, iph->ihl * 4 + poff, 4, _ports); + if (ports) { + sport = ports[0]; + dport = ports[1]; + } + } else { if (net_ratelimit()) pr_info("unknown protocol %u\n", iph->protocol); - sport = dport = 0; } switch (config->hash_mode) { diff --git a/net/ipv4/netfilter/ipt_LOG.c b/net/ipv4/netfilter/ipt_LOG.c index 915fc17d7ce..72ffc8fda2e 100644 --- a/net/ipv4/netfilter/ipt_LOG.c +++ b/net/ipv4/netfilter/ipt_LOG.c @@ -24,16 +24,15 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter_ipv4/ipt_LOG.h> #include <net/netfilter/nf_log.h> +#include <net/netfilter/xt_log.h> MODULE_LICENSE("GPL"); MODULE_AUTHOR("Netfilter Core Team <coreteam@netfilter.org>"); MODULE_DESCRIPTION("Xtables: IPv4 packet logging to syslog"); -/* Use lock to serialize, so printks don't overlap */ -static DEFINE_SPINLOCK(log_lock); - /* One level of recursion won't kill us */ -static void dump_packet(const struct nf_loginfo *info, +static void dump_packet(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb, unsigned int iphoff) { @@ -48,32 +47,32 @@ static void dump_packet(const struct nf_loginfo *info, ih = skb_header_pointer(skb, iphoff, sizeof(_iph), &_iph); if (ih == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* 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=%pI4 DST=%pI4 ", + sb_add(m, "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 ", + sb_add(m, "LEN=%u TOS=0x%02X PREC=0x%02X TTL=%u ID=%u ", ntohs(ih->tot_len), ih->tos & IPTOS_TOS_MASK, ih->tos & IPTOS_PREC_MASK, ih->ttl, ntohs(ih->id)); /* Max length: 6 "CE DF MF " */ if (ntohs(ih->frag_off) & IP_CE) - printk("CE "); + sb_add(m, "CE "); if (ntohs(ih->frag_off) & IP_DF) - printk("DF "); + sb_add(m, "DF "); if (ntohs(ih->frag_off) & IP_MF) - printk("MF "); + sb_add(m, "MF "); /* Max length: 11 "FRAG:65535 " */ if (ntohs(ih->frag_off) & IP_OFFSET) - printk("FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); + sb_add(m, "FRAG:%u ", ntohs(ih->frag_off) & IP_OFFSET); if ((logflags & IPT_LOG_IPOPT) && ih->ihl * 4 > sizeof(struct iphdr)) { @@ -85,15 +84,15 @@ static void dump_packet(const struct nf_loginfo *info, op = skb_header_pointer(skb, iphoff+sizeof(_iph), optsize, _opt); if (op == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); + sb_add(m, "OPT ("); for (i = 0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); } switch (ih->protocol) { @@ -102,7 +101,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct tcphdr *th; /* Max length: 10 "PROTO=TCP " */ - printk("PROTO=TCP "); + sb_add(m, "PROTO=TCP "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -111,41 +110,41 @@ static void dump_packet(const struct nf_loginfo *info, th = skb_header_pointer(skb, iphoff + ih->ihl * 4, sizeof(_tcph), &_tcph); if (th == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u ", + sb_add(m, "SPT=%u DPT=%u ", ntohs(th->source), ntohs(th->dest)); /* Max length: 30 "SEQ=4294967295 ACK=4294967295 " */ if (logflags & IPT_LOG_TCPSEQ) - printk("SEQ=%u ACK=%u ", + sb_add(m, "SEQ=%u ACK=%u ", ntohl(th->seq), ntohl(th->ack_seq)); /* Max length: 13 "WINDOW=65535 " */ - printk("WINDOW=%u ", ntohs(th->window)); + sb_add(m, "WINDOW=%u ", ntohs(th->window)); /* Max length: 9 "RES=0x3F " */ - printk("RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); + sb_add(m, "RES=0x%02x ", (u8)(ntohl(tcp_flag_word(th) & TCP_RESERVED_BITS) >> 22)); /* Max length: 32 "CWR ECE URG ACK PSH RST SYN FIN " */ if (th->cwr) - printk("CWR "); + sb_add(m, "CWR "); if (th->ece) - printk("ECE "); + sb_add(m, "ECE "); if (th->urg) - printk("URG "); + sb_add(m, "URG "); if (th->ack) - printk("ACK "); + sb_add(m, "ACK "); if (th->psh) - printk("PSH "); + sb_add(m, "PSH "); if (th->rst) - printk("RST "); + sb_add(m, "RST "); if (th->syn) - printk("SYN "); + sb_add(m, "SYN "); if (th->fin) - printk("FIN "); + sb_add(m, "FIN "); /* Max length: 11 "URGP=65535 " */ - printk("URGP=%u ", ntohs(th->urg_ptr)); + sb_add(m, "URGP=%u ", ntohs(th->urg_ptr)); if ((logflags & IPT_LOG_TCPOPT) && th->doff * 4 > sizeof(struct tcphdr)) { @@ -158,15 +157,15 @@ static void dump_packet(const struct nf_loginfo *info, iphoff+ih->ihl*4+sizeof(_tcph), optsize, _opt); if (op == NULL) { - printk("TRUNCATED"); + sb_add(m, "TRUNCATED"); return; } /* Max length: 127 "OPT (" 15*4*2chars ") " */ - printk("OPT ("); + sb_add(m, "OPT ("); for (i = 0; i < optsize; i++) - printk("%02X", op[i]); - printk(") "); + sb_add(m, "%02X", op[i]); + sb_add(m, ") "); } break; } @@ -177,9 +176,9 @@ static void dump_packet(const struct nf_loginfo *info, if (ih->protocol == IPPROTO_UDP) /* Max length: 10 "PROTO=UDP " */ - printk("PROTO=UDP " ); + sb_add(m, "PROTO=UDP " ); else /* Max length: 14 "PROTO=UDPLITE " */ - printk("PROTO=UDPLITE "); + sb_add(m, "PROTO=UDPLITE "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -188,13 +187,13 @@ static void dump_packet(const struct nf_loginfo *info, uh = skb_header_pointer(skb, iphoff+ih->ihl*4, sizeof(_udph), &_udph); if (uh == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Max length: 20 "SPT=65535 DPT=65535 " */ - printk("SPT=%u DPT=%u LEN=%u ", + sb_add(m, "SPT=%u DPT=%u LEN=%u ", ntohs(uh->source), ntohs(uh->dest), ntohs(uh->len)); break; @@ -221,7 +220,7 @@ static void dump_packet(const struct nf_loginfo *info, [ICMP_ADDRESSREPLY] = 12 }; /* Max length: 11 "PROTO=ICMP " */ - printk("PROTO=ICMP "); + sb_add(m, "PROTO=ICMP "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -230,19 +229,19 @@ static void dump_packet(const struct nf_loginfo *info, ich = skb_header_pointer(skb, iphoff + ih->ihl * 4, sizeof(_icmph), &_icmph); if (ich == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Max length: 18 "TYPE=255 CODE=255 " */ - printk("TYPE=%u CODE=%u ", ich->type, ich->code); + sb_add(m, "TYPE=%u CODE=%u ", ich->type, ich->code); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ if (ich->type <= NR_ICMP_TYPES && required_len[ich->type] && skb->len-iphoff-ih->ihl*4 < required_len[ich->type]) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } @@ -251,35 +250,35 @@ static void dump_packet(const struct nf_loginfo *info, case ICMP_ECHOREPLY: case ICMP_ECHO: /* Max length: 19 "ID=65535 SEQ=65535 " */ - printk("ID=%u SEQ=%u ", + sb_add(m, "ID=%u SEQ=%u ", ntohs(ich->un.echo.id), ntohs(ich->un.echo.sequence)); break; case ICMP_PARAMETERPROB: /* Max length: 14 "PARAMETER=255 " */ - printk("PARAMETER=%u ", + sb_add(m, "PARAMETER=%u ", ntohl(ich->un.gateway) >> 24); break; case ICMP_REDIRECT: /* Max length: 24 "GATEWAY=255.255.255.255 " */ - printk("GATEWAY=%pI4 ", &ich->un.gateway); + sb_add(m, "GATEWAY=%pI4 ", &ich->un.gateway); /* Fall through */ case ICMP_DEST_UNREACH: case ICMP_SOURCE_QUENCH: case ICMP_TIME_EXCEEDED: /* Max length: 3+maxlen */ if (!iphoff) { /* Only recurse once. */ - printk("["); - dump_packet(info, skb, + sb_add(m, "["); + dump_packet(m, info, skb, iphoff + ih->ihl*4+sizeof(_icmph)); - printk("] "); + sb_add(m, "] "); } /* Max length: 10 "MTU=65535 " */ if (ich->type == ICMP_DEST_UNREACH && ich->code == ICMP_FRAG_NEEDED) - printk("MTU=%u ", ntohs(ich->un.frag.mtu)); + sb_add(m, "MTU=%u ", ntohs(ich->un.frag.mtu)); } break; } @@ -292,19 +291,19 @@ static void dump_packet(const struct nf_loginfo *info, break; /* Max length: 9 "PROTO=AH " */ - printk("PROTO=AH "); + sb_add(m, "PROTO=AH "); /* Max length: 25 "INCOMPLETE [65535 bytes] " */ ah = skb_header_pointer(skb, iphoff+ih->ihl*4, sizeof(_ahdr), &_ahdr); if (ah == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Length: 15 "SPI=0xF1234567 " */ - printk("SPI=0x%x ", ntohl(ah->spi)); + sb_add(m, "SPI=0x%x ", ntohl(ah->spi)); break; } case IPPROTO_ESP: { @@ -312,7 +311,7 @@ static void dump_packet(const struct nf_loginfo *info, const struct ip_esp_hdr *eh; /* Max length: 10 "PROTO=ESP " */ - printk("PROTO=ESP "); + sb_add(m, "PROTO=ESP "); if (ntohs(ih->frag_off) & IP_OFFSET) break; @@ -321,25 +320,25 @@ static void dump_packet(const struct nf_loginfo *info, eh = skb_header_pointer(skb, iphoff+ih->ihl*4, sizeof(_esph), &_esph); if (eh == NULL) { - printk("INCOMPLETE [%u bytes] ", + sb_add(m, "INCOMPLETE [%u bytes] ", skb->len - iphoff - ih->ihl*4); break; } /* Length: 15 "SPI=0xF1234567 " */ - printk("SPI=0x%x ", ntohl(eh->spi)); + sb_add(m, "SPI=0x%x ", ntohl(eh->spi)); break; } /* Max length: 10 "PROTO 255 " */ default: - printk("PROTO=%u ", ih->protocol); + sb_add(m, "PROTO=%u ", ih->protocol); } /* Max length: 15 "UID=4294967295 " */ if ((logflags & IPT_LOG_UID) && !iphoff && skb->sk) { read_lock_bh(&skb->sk->sk_callback_lock); if (skb->sk->sk_socket && skb->sk->sk_socket->file) - printk("UID=%u GID=%u ", + sb_add(m, "UID=%u GID=%u ", skb->sk->sk_socket->file->f_cred->fsuid, skb->sk->sk_socket->file->f_cred->fsgid); read_unlock_bh(&skb->sk->sk_callback_lock); @@ -347,7 +346,7 @@ static void dump_packet(const struct nf_loginfo *info, /* Max length: 16 "MARK=0xFFFFFFFF " */ if (!iphoff && skb->mark) - printk("MARK=0x%x ", skb->mark); + sb_add(m, "MARK=0x%x ", skb->mark); /* Proto Max log string length */ /* IP: 40+46+6+11+127 = 230 */ @@ -364,7 +363,8 @@ static void dump_packet(const struct nf_loginfo *info, /* maxlen = 230+ 91 + 230 + 252 = 803 */ } -static void dump_mac_header(const struct nf_loginfo *info, +static void dump_mac_header(struct sbuff *m, + const struct nf_loginfo *info, const struct sk_buff *skb) { struct net_device *dev = skb->dev; @@ -378,7 +378,7 @@ static void dump_mac_header(const struct nf_loginfo *info, switch (dev->type) { case ARPHRD_ETHER: - printk("MACSRC=%pM MACDST=%pM MACPROTO=%04x ", + sb_add(m, "MACSRC=%pM MACDST=%pM MACPROTO=%04x ", eth_hdr(skb)->h_source, eth_hdr(skb)->h_dest, ntohs(eth_hdr(skb)->h_proto)); return; @@ -387,17 +387,17 @@ static void dump_mac_header(const struct nf_loginfo *info, } fallback: - printk("MAC="); + sb_add(m, "MAC="); if (dev->hard_header_len && skb->mac_header != skb->network_header) { const unsigned char *p = skb_mac_header(skb); unsigned int i; - printk("%02x", *p++); + sb_add(m, "%02x", *p++); for (i = 1; i < dev->hard_header_len; i++, p++) - printk(":%02x", *p); + sb_add(m, ":%02x", *p); } - printk(" "); + sb_add(m, " "); } static struct nf_loginfo default_loginfo = { @@ -419,11 +419,12 @@ ipt_log_packet(u_int8_t pf, const struct nf_loginfo *loginfo, const char *prefix) { + struct sbuff *m = sb_open(); + if (!loginfo) loginfo = &default_loginfo; - spin_lock_bh(&log_lock); - printk("<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, + sb_add(m, "<%d>%sIN=%s OUT=%s ", loginfo->u.log.level, prefix, in ? in->name : "", out ? out->name : ""); @@ -434,20 +435,20 @@ ipt_log_packet(u_int8_t pf, physindev = skb->nf_bridge->physindev; if (physindev && in != physindev) - printk("PHYSIN=%s ", physindev->name); + sb_add(m, "PHYSIN=%s ", physindev->name); physoutdev = skb->nf_bridge->physoutdev; if (physoutdev && out != physoutdev) - printk("PHYSOUT=%s ", physoutdev->name); + sb_add(m, "PHYSOUT=%s ", physoutdev->name); } #endif /* MAC logging for input path only. */ if (in && !out) - dump_mac_header(loginfo, skb); + dump_mac_header(m, loginfo, skb); + + dump_packet(m, loginfo, skb, 0); - dump_packet(loginfo, skb, 0); - printk("\n"); - spin_unlock_bh(&log_lock); + sb_close(m); } static unsigned int diff --git a/net/ipv4/netfilter/ipt_REJECT.c b/net/ipv4/netfilter/ipt_REJECT.c index b254dafaf42..43eec80c0e7 100644 --- a/net/ipv4/netfilter/ipt_REJECT.c +++ b/net/ipv4/netfilter/ipt_REJECT.c @@ -112,6 +112,7 @@ static void send_reset(struct sk_buff *oldskb, int hook) /* ip_route_me_harder expects skb->dst to be set */ skb_dst_set_noref(nskb, skb_dst(oldskb)); + nskb->protocol = htons(ETH_P_IP); if (ip_route_me_harder(nskb, addr_type)) goto free_nskb; diff --git a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c index 244f7cb08d6..37f8adb68c7 100644 --- a/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c +++ b/net/ipv4/netfilter/nf_conntrack_l3proto_ipv4_compat.c @@ -11,6 +11,7 @@ #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <linux/percpu.h> +#include <linux/security.h> #include <net/net_namespace.h> #include <linux/netfilter.h> @@ -87,6 +88,29 @@ static void ct_seq_stop(struct seq_file *s, void *v) rcu_read_unlock(); } +#ifdef CONFIG_NF_CONNTRACK_SECMARK +static int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) +{ + int ret; + u32 len; + char *secctx; + + ret = security_secid_to_secctx(ct->secmark, &secctx, &len); + if (ret) + return ret; + + ret = seq_printf(s, "secctx=%s ", secctx); + + security_release_secctx(secctx, len); + return ret; +} +#else +static inline int ct_show_secctx(struct seq_file *s, const struct nf_conn *ct) +{ + return 0; +} +#endif + static int ct_seq_show(struct seq_file *s, void *v) { struct nf_conntrack_tuple_hash *hash = v; @@ -148,10 +172,8 @@ static int ct_seq_show(struct seq_file *s, void *v) goto release; #endif -#ifdef CONFIG_NF_CONNTRACK_SECMARK - if (seq_printf(s, "secmark=%u ", ct->secmark)) + if (ct_show_secctx(s, ct)) goto release; -#endif if (seq_printf(s, "use=%u\n", atomic_read(&ct->ct_general.use))) goto release; diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index eab8de32f20..f3a9b42b16c 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -66,9 +66,11 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, const struct net_device *out, int (*okfn)(struct sk_buff *)) { + struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(skb->sk); - if (inet && inet->nodefrag) + if (sk && (sk->sk_family == PF_INET) && + inet->nodefrag) return NF_ACCEPT; #if defined(CONFIG_NF_CONNTRACK) || defined(CONFIG_NF_CONNTRACK_MODULE) diff --git a/net/ipv4/netfilter/nf_nat_amanda.c b/net/ipv4/netfilter/nf_nat_amanda.c index c31b8766825..0f23b3f06df 100644 --- a/net/ipv4/netfilter/nf_nat_amanda.c +++ b/net/ipv4/netfilter/nf_nat_amanda.c @@ -44,9 +44,16 @@ static unsigned int help(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 8c8632d9b93..295c97431e4 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -38,7 +38,7 @@ static DEFINE_SPINLOCK(nf_nat_lock); static struct nf_conntrack_l3proto *l3proto __read_mostly; #define MAX_IP_NAT_PROTO 256 -static const struct nf_nat_protocol *nf_nat_protos[MAX_IP_NAT_PROTO] +static const struct nf_nat_protocol __rcu *nf_nat_protos[MAX_IP_NAT_PROTO] __read_mostly; static inline const struct nf_nat_protocol * @@ -47,7 +47,7 @@ __nf_nat_proto_find(u_int8_t protonum) return rcu_dereference(nf_nat_protos[protonum]); } -const struct nf_nat_protocol * +static const struct nf_nat_protocol * nf_nat_proto_find_get(u_int8_t protonum) { const struct nf_nat_protocol *p; @@ -60,14 +60,12 @@ nf_nat_proto_find_get(u_int8_t protonum) return p; } -EXPORT_SYMBOL_GPL(nf_nat_proto_find_get); -void +static void nf_nat_proto_put(const struct nf_nat_protocol *p) { module_put(p->me); } -EXPORT_SYMBOL_GPL(nf_nat_proto_put); /* We keep an extra hash for each conntrack, for fast searching. */ static inline unsigned int @@ -262,11 +260,17 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, proto = __nf_nat_proto_find(orig_tuple->dst.protonum); /* Only bother mapping if it's not already in range and unique */ - if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM) && - (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || - proto->in_range(tuple, maniptype, &range->min, &range->max)) && - !nf_nat_used_tuple(tuple, ct)) - goto out; + if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { + if (range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) { + if (proto->in_range(tuple, maniptype, &range->min, + &range->max) && + (range->min.all == range->max.all || + !nf_nat_used_tuple(tuple, ct))) + goto out; + } else if (!nf_nat_used_tuple(tuple, ct)) { + goto out; + } + } /* Last change: get protocol to try to obtain unique tuple. */ proto->unique_tuple(tuple, range, maniptype, ct); @@ -458,6 +462,18 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, return 0; } + if (manip == IP_NAT_MANIP_SRC) + statusbit = IPS_SRC_NAT; + else + statusbit = IPS_DST_NAT; + + /* Invert if this is reply dir. */ + if (dir == IP_CT_DIR_REPLY) + statusbit ^= IPS_NAT_MASK; + + if (!(ct->status & statusbit)) + return 1; + pr_debug("icmp_reply_translation: translating error %p manip %u " "dir %s\n", skb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); @@ -492,20 +508,9 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, /* Change outer to look the reply to an incoming packet * (proto 0 means don't invert per-proto part). */ - if (manip == IP_NAT_MANIP_SRC) - statusbit = IPS_SRC_NAT; - else - statusbit = IPS_DST_NAT; - - /* Invert if this is reply dir. */ - if (dir == IP_CT_DIR_REPLY) - statusbit ^= IPS_NAT_MASK; - - if (ct->status & statusbit) { - nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); - if (!manip_pkt(0, skb, 0, &target, manip)) - return 0; - } + nf_ct_invert_tuplepr(&target, &ct->tuplehash[!dir].tuple); + if (!manip_pkt(0, skb, 0, &target, manip)) + return 0; return 1; } diff --git a/net/ipv4/netfilter/nf_nat_ftp.c b/net/ipv4/netfilter/nf_nat_ftp.c index 86e0e84ff0a..dc73abb3fe2 100644 --- a/net/ipv4/netfilter/nf_nat_ftp.c +++ b/net/ipv4/netfilter/nf_nat_ftp.c @@ -79,9 +79,16 @@ static unsigned int nf_nat_ftp(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index 5045196d853..790f3160e01 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -222,13 +222,24 @@ static int nat_rtp_rtcp(struct sk_buff *skb, struct nf_conn *ct, /* Try to get a pair of ports. */ for (nated_port = ntohs(rtp_exp->tuple.dst.u.udp.port); nated_port != 0; nated_port += 2) { + int ret; + rtp_exp->tuple.dst.u.udp.port = htons(nated_port); - if (nf_ct_expect_related(rtp_exp) == 0) { + ret = nf_ct_expect_related(rtp_exp); + if (ret == 0) { rtcp_exp->tuple.dst.u.udp.port = htons(nated_port + 1); - if (nf_ct_expect_related(rtcp_exp) == 0) + ret = nf_ct_expect_related(rtcp_exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + nated_port = 0; break; - nf_ct_unexpect_related(rtp_exp); + } + } else if (ret != -EBUSY) { + nated_port = 0; + break; } } @@ -284,9 +295,16 @@ static int nat_t120(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nated_port = 0; break; + } } if (nated_port == 0) { /* No port available */ @@ -334,9 +352,16 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) break; + else if (ret != -EBUSY) { + nated_port = 0; + break; + } } if (nated_port == 0) { /* No port available */ @@ -418,9 +443,16 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (; nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + nated_port = 0; break; + } } if (nated_port == 0) { /* No port available */ @@ -500,9 +532,16 @@ static int nat_callforwarding(struct sk_buff *skb, struct nf_conn *ct, /* Try to get same port: if not, try to change it. */ for (nated_port = ntohs(port); nated_port != 0; nated_port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(nated_port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) break; + else if (ret != -EBUSY) { + nated_port = 0; + break; + } } if (nated_port == 0) { /* No port available */ diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index 4a0c6b548ee..31427fb57aa 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -153,6 +153,35 @@ void nf_nat_set_seq_adjust(struct nf_conn *ct, enum ip_conntrack_info ctinfo, } EXPORT_SYMBOL_GPL(nf_nat_set_seq_adjust); +static void nf_nat_csum(struct sk_buff *skb, struct iphdr *iph, void *data, + int datalen, __sum16 *check, int oldlen) +{ + struct rtable *rt = skb_rtable(skb); + + if (skb->ip_summed != CHECKSUM_PARTIAL) { + if (!(rt->rt_flags & RTCF_LOCAL) && + skb->dev->features & NETIF_F_V4_CSUM) { + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_headroom(skb) + + skb_network_offset(skb) + + iph->ihl * 4; + skb->csum_offset = (void *)check - data; + *check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, iph->protocol, 0); + } else { + *check = 0; + *check = csum_tcpudp_magic(iph->saddr, iph->daddr, + datalen, iph->protocol, + csum_partial(data, datalen, + 0)); + if (iph->protocol == IPPROTO_UDP && !*check) + *check = CSUM_MANGLED_0; + } + } else + inet_proto_csum_replace2(check, skb, + htons(oldlen), htons(datalen), 1); +} + /* Generic function for mangling variable-length address changes inside * NATed TCP connections (like the PORT XXX,XXX,XXX,XXX,XXX,XXX * command in FTP). @@ -169,7 +198,6 @@ int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len, bool adjust) { - struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct tcphdr *tcph; int oldlen, datalen; @@ -192,26 +220,7 @@ int __nf_nat_mangle_tcp_packet(struct sk_buff *skb, match_offset, match_len, rep_buffer, rep_len); datalen = skb->len - iph->ihl*4; - if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(rt->rt_flags & RTCF_LOCAL) && - skb->dev->features & NETIF_F_V4_CSUM) { - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + - skb_network_offset(skb) + - iph->ihl * 4; - skb->csum_offset = offsetof(struct tcphdr, check); - tcph->check = ~tcp_v4_check(datalen, - iph->saddr, iph->daddr, 0); - } else { - tcph->check = 0; - tcph->check = tcp_v4_check(datalen, - iph->saddr, iph->daddr, - csum_partial(tcph, - datalen, 0)); - } - } else - inet_proto_csum_replace2(&tcph->check, skb, - htons(oldlen), htons(datalen), 1); + nf_nat_csum(skb, iph, tcph, datalen, &tcph->check, oldlen); if (adjust && rep_len != match_len) nf_nat_set_seq_adjust(ct, ctinfo, tcph->seq, @@ -240,7 +249,6 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, const char *rep_buffer, unsigned int rep_len) { - struct rtable *rt = skb_rtable(skb); struct iphdr *iph; struct udphdr *udph; int datalen, oldlen; @@ -274,29 +282,7 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, if (!udph->check && skb->ip_summed != CHECKSUM_PARTIAL) return 1; - if (skb->ip_summed != CHECKSUM_PARTIAL) { - if (!(rt->rt_flags & RTCF_LOCAL) && - skb->dev->features & NETIF_F_V4_CSUM) { - skb->ip_summed = CHECKSUM_PARTIAL; - skb->csum_start = skb_headroom(skb) + - skb_network_offset(skb) + - iph->ihl * 4; - skb->csum_offset = offsetof(struct udphdr, check); - udph->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - datalen, IPPROTO_UDP, - 0); - } else { - udph->check = 0; - udph->check = csum_tcpudp_magic(iph->saddr, iph->daddr, - datalen, IPPROTO_UDP, - csum_partial(udph, - datalen, 0)); - if (!udph->check) - udph->check = CSUM_MANGLED_0; - } - } else - inet_proto_csum_replace2(&udph->check, skb, - htons(oldlen), htons(datalen), 1); + nf_nat_csum(skb, iph, udph, datalen, &udph->check, oldlen); return 1; } diff --git a/net/ipv4/netfilter/nf_nat_irc.c b/net/ipv4/netfilter/nf_nat_irc.c index ea83a886b03..535e1a80235 100644 --- a/net/ipv4/netfilter/nf_nat_irc.c +++ b/net/ipv4/netfilter/nf_nat_irc.c @@ -45,9 +45,16 @@ static unsigned int help(struct sk_buff *skb, /* Try to get same port: if not, try to change it. */ for (port = ntohs(exp->saved_proto.tcp.port); port != 0; port++) { + int ret; + exp->tuple.dst.u.tcp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index ebbd319f62f..21c30426480 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -106,16 +106,15 @@ alloc_null_binding(struct nf_conn *ct, unsigned int hooknum) { /* Force range to this IP; let proto decide mapping for per-proto parts (hence not IP_NAT_RANGE_PROTO_SPECIFIED). - Use reply in case it's already been mangled (eg local packet). */ - __be32 ip - = (HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC - ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip - : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); - struct nf_nat_range range - = { IP_NAT_RANGE_MAP_IPS, ip, ip, { 0 }, { 0 } }; - - pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, &ip); + struct nf_nat_range range; + + range.flags = 0; + pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, + HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ? + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip : + &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.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 11b538deaae..e40cf7816fd 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -307,9 +307,16 @@ static unsigned int ip_nat_sip_expect(struct sk_buff *skb, unsigned int dataoff, exp->expectfn = ip_nat_sip_expected; for (; port != 0; port++) { + int ret; + exp->tuple.dst.u.udp.port = htons(port); - if (nf_ct_expect_related(exp) == 0) + ret = nf_ct_expect_related(exp); + if (ret == 0) + break; + else if (ret != -EBUSY) { + port = 0; break; + } } if (port == 0) @@ -480,13 +487,25 @@ static unsigned int ip_nat_sdp_media(struct sk_buff *skb, unsigned int dataoff, /* Try to get same pair of ports: if not, try to change them. */ for (port = ntohs(rtp_exp->tuple.dst.u.udp.port); port != 0; port += 2) { + int ret; + rtp_exp->tuple.dst.u.udp.port = htons(port); - if (nf_ct_expect_related(rtp_exp) != 0) + ret = nf_ct_expect_related(rtp_exp); + if (ret == -EBUSY) continue; + else if (ret < 0) { + port = 0; + break; + } rtcp_exp->tuple.dst.u.udp.port = htons(port + 1); - if (nf_ct_expect_related(rtcp_exp) == 0) + ret = nf_ct_expect_related(rtcp_exp); + if (ret == 0) break; - nf_ct_unexpect_related(rtp_exp); + else if (ret != -EBUSY) { + nf_ct_unexpect_related(rtp_exp); + port = 0; + break; + } } if (port == 0) diff --git a/net/ipv4/netfilter/nf_nat_snmp_basic.c b/net/ipv4/netfilter/nf_nat_snmp_basic.c index 1679e2c0963..ee5f419d0a5 100644 --- a/net/ipv4/netfilter/nf_nat_snmp_basic.c +++ b/net/ipv4/netfilter/nf_nat_snmp_basic.c @@ -893,13 +893,15 @@ static void fast_csum(__sum16 *csum, unsigned char s[4]; if (offset & 1) { - s[0] = s[2] = 0; + s[0] = ~0; s[1] = ~*optr; + s[2] = 0; s[3] = *nptr; } else { - s[1] = s[3] = 0; s[0] = ~*optr; + s[1] = ~0; s[2] = *nptr; + s[3] = 0; } *csum = csum_fold(csum_partial(s, 4, ~csum_unfold(*csum))); diff --git a/net/ipv4/protocol.c b/net/ipv4/protocol.c index f2d29735140..9ae5c01cd0b 100644 --- a/net/ipv4/protocol.c +++ b/net/ipv4/protocol.c @@ -28,8 +28,7 @@ #include <linux/spinlock.h> #include <net/protocol.h> -const struct net_protocol *inet_protos[MAX_INET_PROTOS] ____cacheline_aligned_in_smp; -static DEFINE_SPINLOCK(inet_proto_lock); +const struct net_protocol __rcu *inet_protos[MAX_INET_PROTOS] __read_mostly; /* * Add a protocol handler to the hash tables @@ -37,20 +36,10 @@ static DEFINE_SPINLOCK(inet_proto_lock); int inet_add_protocol(const struct net_protocol *prot, unsigned char protocol) { - int hash, ret; + int hash = protocol & (MAX_INET_PROTOS - 1); - hash = protocol & (MAX_INET_PROTOS - 1); - - spin_lock_bh(&inet_proto_lock); - if (inet_protos[hash]) { - ret = -1; - } else { - inet_protos[hash] = prot; - ret = 0; - } - spin_unlock_bh(&inet_proto_lock); - - return ret; + return !cmpxchg((const struct net_protocol **)&inet_protos[hash], + NULL, prot) ? 0 : -1; } EXPORT_SYMBOL(inet_add_protocol); @@ -60,18 +49,10 @@ EXPORT_SYMBOL(inet_add_protocol); int inet_del_protocol(const struct net_protocol *prot, unsigned char protocol) { - int hash, ret; - - hash = protocol & (MAX_INET_PROTOS - 1); + int ret, hash = protocol & (MAX_INET_PROTOS - 1); - spin_lock_bh(&inet_proto_lock); - if (inet_protos[hash] == prot) { - inet_protos[hash] = NULL; - ret = 0; - } else { - ret = -1; - } - spin_unlock_bh(&inet_proto_lock); + ret = (cmpxchg((const struct net_protocol **)&inet_protos[hash], + prot, NULL) == prot) ? 0 : -1; synchronize_net(); diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 009a7b2aa1e..1f85ef28989 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -505,7 +505,7 @@ static int raw_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.addr = inet->inet_saddr; ipc.opt = NULL; - ipc.shtx.flags = 0; + ipc.tx_flags = 0; ipc.oif = sk->sk_bound_dev_if; if (msg->msg_controllen) { diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 3f56b6e6c6a..987bf9adb31 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -159,7 +159,6 @@ static struct dst_ops ipv4_dst_ops = { .link_failure = ipv4_link_failure, .update_pmtu = ip_rt_update_pmtu, .local_out = __ip_local_out, - .entries = ATOMIC_INIT(0), }; #define ECN_OR_COST(class) TC_PRIO_##class @@ -199,7 +198,7 @@ const __u8 ip_tos2prio[16] = { */ struct rt_hash_bucket { - struct rtable *chain; + struct rtable __rcu *chain; }; #if defined(CONFIG_SMP) || defined(CONFIG_DEBUG_SPINLOCK) || \ @@ -281,7 +280,7 @@ static struct rtable *rt_cache_get_first(struct seq_file *seq) struct rtable *r = NULL; for (st->bucket = rt_hash_mask; st->bucket >= 0; --st->bucket) { - if (!rt_hash_table[st->bucket].chain) + if (!rcu_dereference_raw(rt_hash_table[st->bucket].chain)) continue; rcu_read_lock_bh(); r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); @@ -301,17 +300,17 @@ static struct rtable *__rt_cache_get_next(struct seq_file *seq, { struct rt_cache_iter_state *st = seq->private; - r = r->dst.rt_next; + r = rcu_dereference_bh(r->dst.rt_next); while (!r) { rcu_read_unlock_bh(); do { if (--st->bucket < 0) return NULL; - } while (!rt_hash_table[st->bucket].chain); + } while (!rcu_dereference_raw(rt_hash_table[st->bucket].chain)); rcu_read_lock_bh(); - r = rt_hash_table[st->bucket].chain; + r = rcu_dereference_bh(rt_hash_table[st->bucket].chain); } - return rcu_dereference_bh(r); + return r; } static struct rtable *rt_cache_get_next(struct seq_file *seq, @@ -466,7 +465,7 @@ static int rt_cpu_seq_show(struct seq_file *seq, void *v) seq_printf(seq,"%08x %08x %08x %08x %08x %08x %08x %08x " " %08x %08x %08x %08x %08x %08x %08x %08x %08x \n", - atomic_read(&ipv4_dst_ops.entries), + dst_entries_get_slow(&ipv4_dst_ops), st->in_hit, st->in_slow_tot, st->in_slow_mc, @@ -722,19 +721,23 @@ static void rt_do_flush(int process_context) for (i = 0; i <= rt_hash_mask; i++) { if (process_context && need_resched()) cond_resched(); - rth = rt_hash_table[i].chain; + rth = rcu_dereference_raw(rt_hash_table[i].chain); if (!rth) continue; spin_lock_bh(rt_hash_lock_addr(i)); #ifdef CONFIG_NET_NS { - struct rtable ** prev, * p; + struct rtable __rcu **prev; + struct rtable *p; - rth = rt_hash_table[i].chain; + rth = rcu_dereference_protected(rt_hash_table[i].chain, + lockdep_is_held(rt_hash_lock_addr(i))); /* defer releasing the head of the list after spin_unlock */ - for (tail = rth; tail; tail = tail->dst.rt_next) + for (tail = rth; tail; + tail = rcu_dereference_protected(tail->dst.rt_next, + lockdep_is_held(rt_hash_lock_addr(i)))) if (!rt_is_expired(tail)) break; if (rth != tail) @@ -742,8 +745,12 @@ static void rt_do_flush(int process_context) /* call rt_free on entries after the tail requiring flush */ prev = &rt_hash_table[i].chain; - for (p = *prev; p; p = next) { - next = p->dst.rt_next; + for (p = rcu_dereference_protected(*prev, + lockdep_is_held(rt_hash_lock_addr(i))); + p != NULL; + p = next) { + next = rcu_dereference_protected(p->dst.rt_next, + lockdep_is_held(rt_hash_lock_addr(i))); if (!rt_is_expired(p)) { prev = &p->dst.rt_next; } else { @@ -753,14 +760,15 @@ static void rt_do_flush(int process_context) } } #else - rth = rt_hash_table[i].chain; - rt_hash_table[i].chain = NULL; + rth = rcu_dereference_protected(rt_hash_table[i].chain, + lockdep_is_held(rt_hash_lock_addr(i))); + rcu_assign_pointer(rt_hash_table[i].chain, NULL); tail = NULL; #endif spin_unlock_bh(rt_hash_lock_addr(i)); for (; rth != tail; rth = next) { - next = rth->dst.rt_next; + next = rcu_dereference_protected(rth->dst.rt_next, 1); rt_free(rth); } } @@ -791,7 +799,7 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) while (aux != rth) { if (compare_hash_inputs(&aux->fl, &rth->fl)) return 0; - aux = aux->dst.rt_next; + aux = rcu_dereference_protected(aux->dst.rt_next, 1); } return ONE; } @@ -800,7 +808,8 @@ static void rt_check_expire(void) { static unsigned int rover; unsigned int i = rover, goal; - struct rtable *rth, **rthp; + struct rtable *rth; + struct rtable __rcu **rthp; unsigned long samples = 0; unsigned long sum = 0, sum2 = 0; unsigned long delta; @@ -826,11 +835,12 @@ static void rt_check_expire(void) samples++; - if (*rthp == NULL) + if (rcu_dereference_raw(*rthp) == NULL) continue; length = 0; spin_lock_bh(rt_hash_lock_addr(i)); - while ((rth = *rthp) != NULL) { + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(i)))) != NULL) { prefetch(rth->dst.rt_next); if (rt_is_expired(rth)) { *rthp = rth->dst.rt_next; @@ -942,9 +952,11 @@ static int rt_garbage_collect(struct dst_ops *ops) static unsigned long last_gc; static int rover; static int equilibrium; - struct rtable *rth, **rthp; + struct rtable *rth; + struct rtable __rcu **rthp; unsigned long now = jiffies; int goal; + int entries = dst_entries_get_fast(&ipv4_dst_ops); /* * Garbage collection is pretty expensive, @@ -954,28 +966,28 @@ static int rt_garbage_collect(struct dst_ops *ops) RT_CACHE_STAT_INC(gc_total); if (now - last_gc < ip_rt_gc_min_interval && - atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) { + entries < ip_rt_max_size) { RT_CACHE_STAT_INC(gc_ignored); goto out; } + entries = dst_entries_get_slow(&ipv4_dst_ops); /* Calculate number of entries, which we want to expire now. */ - goal = atomic_read(&ipv4_dst_ops.entries) - - (ip_rt_gc_elasticity << rt_hash_log); + goal = entries - (ip_rt_gc_elasticity << rt_hash_log); if (goal <= 0) { if (equilibrium < ipv4_dst_ops.gc_thresh) equilibrium = ipv4_dst_ops.gc_thresh; - goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium; + goal = entries - equilibrium; if (goal > 0) { equilibrium += min_t(unsigned int, goal >> 1, rt_hash_mask + 1); - goal = atomic_read(&ipv4_dst_ops.entries) - equilibrium; + goal = entries - equilibrium; } } else { /* We are in dangerous area. Try to reduce cache really * aggressively. */ goal = max_t(unsigned int, goal >> 1, rt_hash_mask + 1); - equilibrium = atomic_read(&ipv4_dst_ops.entries) - goal; + equilibrium = entries - goal; } if (now - last_gc >= ip_rt_gc_min_interval) @@ -995,7 +1007,8 @@ static int rt_garbage_collect(struct dst_ops *ops) k = (k + 1) & rt_hash_mask; rthp = &rt_hash_table[k].chain; spin_lock_bh(rt_hash_lock_addr(k)); - while ((rth = *rthp) != NULL) { + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(k)))) != NULL) { if (!rt_is_expired(rth) && !rt_may_expire(rth, tmo, expire)) { tmo >>= 1; @@ -1032,14 +1045,16 @@ static int rt_garbage_collect(struct dst_ops *ops) expire >>= 1; #if RT_CACHE_DEBUG >= 2 printk(KERN_DEBUG "expire>> %u %d %d %d\n", expire, - atomic_read(&ipv4_dst_ops.entries), goal, i); + dst_entries_get_fast(&ipv4_dst_ops), goal, i); #endif - if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) + if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) goto out; } while (!in_softirq() && time_before_eq(jiffies, now)); - if (atomic_read(&ipv4_dst_ops.entries) < ip_rt_max_size) + if (dst_entries_get_fast(&ipv4_dst_ops) < ip_rt_max_size) + goto out; + if (dst_entries_get_slow(&ipv4_dst_ops) < ip_rt_max_size) goto out; if (net_ratelimit()) printk(KERN_WARNING "dst cache overflow\n"); @@ -1049,11 +1064,12 @@ static int rt_garbage_collect(struct dst_ops *ops) work_done: expire += ip_rt_gc_min_interval; if (expire > ip_rt_gc_timeout || - atomic_read(&ipv4_dst_ops.entries) < ipv4_dst_ops.gc_thresh) + dst_entries_get_fast(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh || + dst_entries_get_slow(&ipv4_dst_ops) < ipv4_dst_ops.gc_thresh) expire = ip_rt_gc_timeout; #if RT_CACHE_DEBUG >= 2 printk(KERN_DEBUG "expire++ %u %d %d %d\n", expire, - atomic_read(&ipv4_dst_ops.entries), goal, rover); + dst_entries_get_fast(&ipv4_dst_ops), goal, rover); #endif out: return 0; } @@ -1068,7 +1084,7 @@ static int slow_chain_length(const struct rtable *head) while (rth) { length += has_noalias(head, rth); - rth = rth->dst.rt_next; + rth = rcu_dereference_protected(rth->dst.rt_next, 1); } return length >> FRACT_BITS; } @@ -1076,9 +1092,9 @@ static int slow_chain_length(const struct rtable *head) static int rt_intern_hash(unsigned hash, struct rtable *rt, struct rtable **rp, struct sk_buff *skb, int ifindex) { - struct rtable *rth, **rthp; + struct rtable *rth, *cand; + struct rtable __rcu **rthp, **candp; unsigned long now; - struct rtable *cand, **candp; u32 min_score; int chain_length; int attempts = !in_softirq(); @@ -1102,30 +1118,31 @@ restart: * Note that we do rt_free on this new route entry, so that * once its refcount hits zero, we are still able to reap it * (Thanks Alexey) - * Note also the rt_free uses call_rcu. We don't actually - * need rcu protection here, this is just our path to get - * on the route gc list. + * Note: To avoid expensive rcu stuff for this uncached dst, + * we set DST_NOCACHE so that dst_release() can free dst without + * waiting a grace period. */ + rt->dst.flags |= DST_NOCACHE; if (rt->rt_type == RTN_UNICAST || rt->fl.iif == 0) { int err = arp_bind_neighbour(&rt->dst); if (err) { if (net_ratelimit()) printk(KERN_WARNING "Neighbour table failure & not caching routes.\n"); - rt_drop(rt); + ip_rt_put(rt); return err; } } - rt_free(rt); goto skip_hashing; } rthp = &rt_hash_table[hash].chain; spin_lock_bh(rt_hash_lock_addr(hash)); - while ((rth = *rthp) != NULL) { + while ((rth = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) { if (rt_is_expired(rth)) { *rthp = rth->dst.rt_next; rt_free(rth); @@ -1231,7 +1248,7 @@ restart: } if (net_ratelimit()) - printk(KERN_WARNING "Neighbour table overflow.\n"); + printk(KERN_WARNING "ipv4: Neighbour table overflow.\n"); rt_drop(rt); return -ENOBUFS; } @@ -1268,18 +1285,11 @@ skip_hashing: void rt_bind_peer(struct rtable *rt, int create) { - static DEFINE_SPINLOCK(rt_peer_lock); struct inet_peer *peer; peer = inet_getpeer(rt->rt_dst, create); - spin_lock_bh(&rt_peer_lock); - if (rt->peer == NULL) { - rt->peer = peer; - peer = NULL; - } - spin_unlock_bh(&rt_peer_lock); - if (peer) + if (peer && cmpxchg(&rt->peer, NULL, peer) != NULL) inet_putpeer(peer); } @@ -1328,12 +1338,14 @@ EXPORT_SYMBOL(__ip_select_ident); static void rt_del(unsigned hash, struct rtable *rt) { - struct rtable **rthp, *aux; + struct rtable __rcu **rthp; + struct rtable *aux; rthp = &rt_hash_table[hash].chain; spin_lock_bh(rt_hash_lock_addr(hash)); ip_rt_put(rt); - while ((aux = *rthp) != NULL) { + while ((aux = rcu_dereference_protected(*rthp, + lockdep_is_held(rt_hash_lock_addr(hash)))) != NULL) { if (aux == rt || rt_is_expired(aux)) { *rthp = aux->dst.rt_next; rt_free(aux); @@ -1350,7 +1362,8 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, { int i, k; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rth, **rthp; + struct rtable *rth; + struct rtable __rcu **rthp; __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; struct netevent_redirect netevent; @@ -1383,7 +1396,7 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, unsigned hash = rt_hash(daddr, skeys[i], ikeys[k], rt_genid(net)); - rthp=&rt_hash_table[hash].chain; + rthp = &rt_hash_table[hash].chain; while ((rth = rcu_dereference(*rthp)) != NULL) { struct rtable *rt; @@ -1779,12 +1792,15 @@ void ip_rt_get_source(u8 *addr, struct rtable *rt) if (rt->fl.iif == 0) src = rt->rt_src; - else if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) { - src = FIB_RES_PREFSRC(res); - fib_res_put(&res); - } else - src = inet_select_addr(rt->dst.dev, rt->rt_gateway, + else { + rcu_read_lock(); + if (fib_lookup(dev_net(rt->dst.dev), &rt->fl, &res) == 0) + src = FIB_RES_PREFSRC(res); + else + src = inet_select_addr(rt->dst.dev, rt->rt_gateway, RT_SCOPE_UNIVERSE); + rcu_read_unlock(); + } memcpy(addr, &src, 4); } @@ -2087,6 +2103,7 @@ static int ip_mkroute_input(struct sk_buff *skb, * Such approach solves two big problems: * 1. Not simplex devices are handled properly. * 2. IP spoofing attempts are filtered with 100% of guarantee. + * called with rcu_read_lock() */ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, @@ -2108,7 +2125,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, unsigned hash; __be32 spec_dst; int err = -EINVAL; - int free_res = 0; struct net * net = dev_net(dev); /* IP on this device is disabled. */ @@ -2124,7 +2140,7 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, ipv4_is_loopback(saddr)) goto martian_source; - if (daddr == htonl(0xFFFFFFFF) || (saddr == 0 && daddr == 0)) + if (ipv4_is_lbcast(daddr) || (saddr == 0 && daddr == 0)) goto brd_input; /* Accept zero addresses only to limited broadcast; @@ -2133,19 +2149,18 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (ipv4_is_zeronet(saddr)) goto martian_source; - if (ipv4_is_lbcast(daddr) || ipv4_is_zeronet(daddr) || - ipv4_is_loopback(daddr)) + if (ipv4_is_zeronet(daddr) || ipv4_is_loopback(daddr)) goto martian_destination; /* * Now we are ready to route packet. */ - if ((err = fib_lookup(net, &fl, &res)) != 0) { + err = fib_lookup(net, &fl, &res); + if (err != 0) { if (!IN_DEV_FORWARD(in_dev)) goto e_hostunreach; goto no_route; } - free_res = 1; RT_CACHE_STAT_INC(in_slow_tot); @@ -2154,8 +2169,8 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, if (res.type == RTN_LOCAL) { err = fib_validate_source(saddr, daddr, tos, - net->loopback_dev->ifindex, - dev, &spec_dst, &itag, skb->mark); + net->loopback_dev->ifindex, + dev, &spec_dst, &itag, skb->mark); if (err < 0) goto martian_source_keep_err; if (err) @@ -2170,9 +2185,6 @@ static int ip_route_input_slow(struct sk_buff *skb, __be32 daddr, __be32 saddr, goto martian_destination; err = ip_mkroute_input(skb, &res, &fl, in_dev, daddr, saddr, tos); -done: - if (free_res) - fib_res_put(&res); out: return err; brd_input: @@ -2232,7 +2244,7 @@ local_input: rth->rt_type = res.type; hash = rt_hash(daddr, saddr, fl.iif, rt_genid(net)); err = rt_intern_hash(hash, rth, NULL, skb, fl.iif); - goto done; + goto out; no_route: RT_CACHE_STAT_INC(in_no_route); @@ -2255,21 +2267,21 @@ martian_destination: e_hostunreach: err = -EHOSTUNREACH; - goto done; + goto out; e_inval: err = -EINVAL; - goto done; + goto out; e_nobufs: err = -ENOBUFS; - goto done; + goto out; martian_source: err = -EINVAL; martian_source_keep_err: ip_handle_martian_source(dev, in_dev, skb, daddr, saddr); - goto done; + goto out; } int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, @@ -2355,6 +2367,7 @@ skip_cache: } EXPORT_SYMBOL(ip_route_input_common); +/* called with rcu_read_lock() */ static int __mkroute_output(struct rtable **result, struct fib_result *res, const struct flowi *fl, @@ -2365,53 +2378,47 @@ static int __mkroute_output(struct rtable **result, struct rtable *rth; struct in_device *in_dev; u32 tos = RT_FL_TOS(oldflp); - int err = 0; - if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags&IFF_LOOPBACK)) + if (ipv4_is_loopback(fl->fl4_src) && !(dev_out->flags & IFF_LOOPBACK)) return -EINVAL; - if (fl->fl4_dst == htonl(0xFFFFFFFF)) + if (ipv4_is_lbcast(fl->fl4_dst)) res->type = RTN_BROADCAST; else if (ipv4_is_multicast(fl->fl4_dst)) res->type = RTN_MULTICAST; - else if (ipv4_is_lbcast(fl->fl4_dst) || ipv4_is_zeronet(fl->fl4_dst)) + else if (ipv4_is_zeronet(fl->fl4_dst)) return -EINVAL; if (dev_out->flags & IFF_LOOPBACK) flags |= RTCF_LOCAL; - /* get work reference to inet device */ - in_dev = in_dev_get(dev_out); + in_dev = __in_dev_get_rcu(dev_out); if (!in_dev) return -EINVAL; if (res->type == RTN_BROADCAST) { flags |= RTCF_BROADCAST | RTCF_LOCAL; - if (res->fi) { - fib_info_put(res->fi); - res->fi = NULL; - } + res->fi = NULL; } else if (res->type == RTN_MULTICAST) { - flags |= RTCF_MULTICAST|RTCF_LOCAL; + flags |= RTCF_MULTICAST | RTCF_LOCAL; if (!ip_check_mc(in_dev, oldflp->fl4_dst, oldflp->fl4_src, oldflp->proto)) flags &= ~RTCF_LOCAL; /* If multicast route do not exist use - default one, but do not gateway in this case. - Yes, it is hack. + * default one, but do not gateway in this case. + * Yes, it is hack. */ - if (res->fi && res->prefixlen < 4) { - fib_info_put(res->fi); + if (res->fi && res->prefixlen < 4) res->fi = NULL; - } } rth = dst_alloc(&ipv4_dst_ops); - if (!rth) { - err = -ENOBUFS; - goto cleanup; - } + if (!rth) + return -ENOBUFS; + + in_dev_hold(in_dev); + rth->idev = in_dev; atomic_set(&rth->dst.__refcnt, 1); rth->dst.flags= DST_HOST; @@ -2432,7 +2439,6 @@ static int __mkroute_output(struct rtable **result, cache entry */ rth->dst.dev = dev_out; dev_hold(dev_out); - rth->idev = in_dev_get(dev_out); rth->rt_gateway = fl->fl4_dst; rth->rt_spec_dst= fl->fl4_src; @@ -2467,15 +2473,11 @@ static int __mkroute_output(struct rtable **result, rt_set_nexthop(rth, res, 0); rth->rt_flags = flags; - *result = rth; - cleanup: - /* release work reference to inet device */ - in_dev_put(in_dev); - - return err; + return 0; } +/* called with rcu_read_lock() */ static int ip_mkroute_output(struct rtable **rp, struct fib_result *res, const struct flowi *fl, @@ -2497,6 +2499,7 @@ static int ip_mkroute_output(struct rtable **rp, /* * Major route resolver routine. + * called with rcu_read_lock(); */ static int ip_route_output_slow(struct net *net, struct rtable **rp, @@ -2515,9 +2518,8 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, .iif = net->loopback_dev->ifindex, .oif = oldflp->oif }; struct fib_result res; - unsigned flags = 0; + unsigned int flags = 0; struct net_device *dev_out = NULL; - int free_res = 0; int err; @@ -2543,9 +2545,9 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (oldflp->oif == 0 && (ipv4_is_multicast(oldflp->fl4_dst) || - oldflp->fl4_dst == htonl(0xFFFFFFFF))) { + ipv4_is_lbcast(oldflp->fl4_dst))) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - dev_out = ip_dev_find(net, oldflp->fl4_src); + dev_out = __ip_dev_find(net, oldflp->fl4_src, false); if (dev_out == NULL) goto out; @@ -2570,29 +2572,24 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (!(oldflp->flags & FLOWI_FLAG_ANYSRC)) { /* It is equivalent to inet_addr_type(saddr) == RTN_LOCAL */ - dev_out = ip_dev_find(net, oldflp->fl4_src); - if (dev_out == NULL) + if (!__ip_dev_find(net, oldflp->fl4_src, false)) goto out; - dev_put(dev_out); - dev_out = NULL; } } if (oldflp->oif) { - dev_out = dev_get_by_index(net, oldflp->oif); + dev_out = dev_get_by_index_rcu(net, oldflp->oif); err = -ENODEV; if (dev_out == NULL) goto out; /* RACE: Check return value of inet_select_addr instead. */ - if (__in_dev_get_rtnl(dev_out) == NULL) { - dev_put(dev_out); + if (rcu_dereference(dev_out->ip_ptr) == NULL) goto out; /* Wrong error code */ - } if (ipv4_is_local_multicast(oldflp->fl4_dst) || - oldflp->fl4_dst == htonl(0xFFFFFFFF)) { + ipv4_is_lbcast(oldflp->fl4_dst)) { if (!fl.fl4_src) fl.fl4_src = inet_select_addr(dev_out, 0, RT_SCOPE_LINK); @@ -2612,10 +2609,7 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, fl.fl4_dst = fl.fl4_src; if (!fl.fl4_dst) fl.fl4_dst = fl.fl4_src = htonl(INADDR_LOOPBACK); - if (dev_out) - dev_put(dev_out); dev_out = net->loopback_dev; - dev_hold(dev_out); fl.oif = net->loopback_dev->ifindex; res.type = RTN_LOCAL; flags |= RTCF_LOCAL; @@ -2649,23 +2643,15 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, res.type = RTN_UNICAST; goto make_route; } - if (dev_out) - dev_put(dev_out); err = -ENETUNREACH; goto out; } - free_res = 1; if (res.type == RTN_LOCAL) { if (!fl.fl4_src) fl.fl4_src = fl.fl4_dst; - if (dev_out) - dev_put(dev_out); dev_out = net->loopback_dev; - dev_hold(dev_out); fl.oif = dev_out->ifindex; - if (res.fi) - fib_info_put(res.fi); res.fi = NULL; flags |= RTCF_LOCAL; goto make_route; @@ -2682,28 +2668,21 @@ static int ip_route_output_slow(struct net *net, struct rtable **rp, if (!fl.fl4_src) fl.fl4_src = FIB_RES_PREFSRC(res); - if (dev_out) - dev_put(dev_out); dev_out = FIB_RES_DEV(res); - dev_hold(dev_out); fl.oif = dev_out->ifindex; make_route: err = ip_mkroute_output(rp, &res, &fl, oldflp, dev_out, flags); - - if (free_res) - fib_res_put(&res); - if (dev_out) - dev_put(dev_out); out: return err; } int __ip_route_output_key(struct net *net, struct rtable **rp, const struct flowi *flp) { - unsigned hash; + unsigned int hash; + int res; struct rtable *rth; if (!rt_caching(net)) @@ -2734,10 +2713,18 @@ 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); + rcu_read_lock(); + res = ip_route_output_slow(net, rp, flp); + rcu_read_unlock(); + return res; } EXPORT_SYMBOL_GPL(__ip_route_output_key); +static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 cookie) +{ + return NULL; +} + static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) { } @@ -2746,9 +2733,8 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .family = AF_INET, .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, - .check = ipv4_dst_check, + .check = ipv4_blackhole_dst_check, .update_pmtu = ipv4_rt_blackhole_update_pmtu, - .entries = ATOMIC_INIT(0), }; @@ -2793,7 +2779,7 @@ static int ipv4_dst_blackhole(struct net *net, struct rtable **rp, struct flowi dst_release(&(*rp)->dst); *rp = rt; - return (rt ? 0 : -ENOMEM); + return rt ? 0 : -ENOMEM; } int ip_route_output_flow(struct net *net, struct rtable **rp, struct flowi *flp, @@ -3318,6 +3304,12 @@ int __init ip_rt_init(void) ipv4_dst_blackhole_ops.kmem_cachep = ipv4_dst_ops.kmem_cachep; + if (dst_entries_init(&ipv4_dst_ops) < 0) + panic("IP: failed to allocate ipv4_dst_ops counter\n"); + + if (dst_entries_init(&ipv4_dst_blackhole_ops) < 0) + panic("IP: failed to allocate ipv4_dst_blackhole_ops counter\n"); + rt_hash_table = (struct rt_hash_bucket *) alloc_large_system_hash("IP route cache", sizeof(struct rt_hash_bucket), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 3fb1428e526..1664a0590bb 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -386,8 +386,6 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) */ mask = 0; - if (sk->sk_err) - mask = POLLERR; /* * POLLHUP is certainly not done right. But poll() doesn't @@ -457,6 +455,11 @@ unsigned int tcp_poll(struct file *file, struct socket *sock, poll_table *wait) if (tp->urg_data & TCP_URG_VALID) mask |= POLLPRI; } + /* This barrier is coupled with smp_wmb() in tcp_reset() */ + smp_rmb(); + if (sk->sk_err) + mask |= POLLERR; + return mask; } EXPORT_SYMBOL(tcp_poll); @@ -940,7 +943,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, sg = sk->sk_route_caps & NETIF_F_SG; while (--iovlen >= 0) { - int seglen = iov->iov_len; + size_t seglen = iov->iov_len; unsigned char __user *from = iov->iov_base; iov++; @@ -2389,7 +2392,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, err = tp->af_specific->md5_parse(sk, optval, optlen); break; #endif - + case TCP_USER_TIMEOUT: + /* Cap the max timeout in ms TCP will retry/retrans + * before giving up and aborting (ETIMEDOUT) a connection. + */ + icsk->icsk_user_timeout = msecs_to_jiffies(val); + break; default: err = -ENOPROTOOPT; break; @@ -2608,6 +2616,10 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_THIN_DUPACK: val = tp->thin_dupack; break; + + case TCP_USER_TIMEOUT: + val = jiffies_to_msecs(icsk->icsk_user_timeout); + break; default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_illinois.c b/net/ipv4/tcp_illinois.c index 1eba160b72d..00ca688d896 100644 --- a/net/ipv4/tcp_illinois.c +++ b/net/ipv4/tcp_illinois.c @@ -6,7 +6,7 @@ * The algorithm is described in: * "TCP-Illinois: A Loss and Delay-Based Congestion Control Algorithm * for High-Speed Networks" - * http://www.ews.uiuc.edu/~shaoliu/papersandslides/liubassri06perf.pdf + * http://www.ifp.illinois.edu/~srikant/Papers/liubassri06perf.pdf * * Implemented from description in paper and ns-2 simulation. * Copyright (C) 2007 Stephen Hemminger <shemminger@linux-foundation.org> diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e663b78a2ef..3357f69e353 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -182,7 +182,7 @@ static void tcp_incr_quickack(struct sock *sk) icsk->icsk_ack.quick = min(quickacks, TCP_MAX_QUICKACKS); } -void tcp_enter_quickack_mode(struct sock *sk) +static void tcp_enter_quickack_mode(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); tcp_incr_quickack(sk); @@ -428,10 +428,10 @@ EXPORT_SYMBOL(tcp_initialize_rcv_mss); * * The algorithm for RTT estimation w/o timestamps is based on * Dynamic Right-Sizing (DRS) by Wu Feng and Mike Fisk of LANL. - * <http://www.lanl.gov/radiant/website/pubs/drs/lacsi2001.ps> + * <http://public.lanl.gov/radiant/pubs.html#DRS> * * More detail on this code can be found at - * <http://www.psc.edu/~jheffner/senior_thesis.ps>, + * <http://staff.psc.edu/jheffner/>, * though this reference is out of date. A new paper * is pending. */ @@ -805,25 +805,12 @@ void tcp_update_metrics(struct sock *sk) } } -/* Numbers are taken from RFC3390. - * - * John Heffner states: - * - * The RFC specifies a window of no more than 4380 bytes - * unless 2*MSS > 4380. Reading the pseudocode in the RFC - * is a bit misleading because they use a clamp at 4380 bytes - * rather than use a multiplier in the relevant range. - */ __u32 tcp_init_cwnd(struct tcp_sock *tp, struct dst_entry *dst) { __u32 cwnd = (dst ? dst_metric(dst, RTAX_INITCWND) : 0); - if (!cwnd) { - if (tp->mss_cache > 1460) - cwnd = 2; - else - cwnd = (tp->mss_cache > 1095) ? 3 : 4; - } + if (!cwnd) + cwnd = rfc3390_bytes_to_packets(tp->mss_cache); return min_t(__u32, cwnd, tp->snd_cwnd_clamp); } @@ -2314,7 +2301,7 @@ static inline int tcp_dupack_heuristics(struct tcp_sock *tp) static inline int tcp_skb_timedout(struct sock *sk, struct sk_buff *skb) { - return (tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto); + return tcp_time_stamp - TCP_SKB_CB(skb)->when > inet_csk(sk)->icsk_rto; } static inline int tcp_head_timedout(struct sock *sk) @@ -2508,7 +2495,7 @@ static void tcp_timeout_skbs(struct sock *sk) /* Mark head of queue up as lost. With RFC3517 SACK, the packets is * is against sacked "cnt", otherwise it's against facked "cnt" */ -static void tcp_mark_head_lost(struct sock *sk, int packets) +static void tcp_mark_head_lost(struct sock *sk, int packets, int mark_head) { struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; @@ -2516,13 +2503,13 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) int err; unsigned int mss; - if (packets == 0) - return; - WARN_ON(packets > tp->packets_out); if (tp->lost_skb_hint) { skb = tp->lost_skb_hint; cnt = tp->lost_cnt_hint; + /* Head already handled? */ + if (mark_head && skb != tcp_write_queue_head(sk)) + return; } else { skb = tcp_write_queue_head(sk); cnt = 0; @@ -2545,7 +2532,8 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) cnt += tcp_skb_pcount(skb); if (cnt > packets) { - if (tcp_is_sack(tp) || (oldcnt >= packets)) + if ((tcp_is_sack(tp) && !tcp_is_fack(tp)) || + (oldcnt >= packets)) break; mss = skb_shinfo(skb)->gso_size; @@ -2556,6 +2544,9 @@ static void tcp_mark_head_lost(struct sock *sk, int packets) } tcp_skb_mark_lost(tp, skb); + + if (mark_head) + break; } tcp_verify_left_out(tp); } @@ -2567,17 +2558,18 @@ static void tcp_update_scoreboard(struct sock *sk, int fast_rexmit) struct tcp_sock *tp = tcp_sk(sk); if (tcp_is_reno(tp)) { - tcp_mark_head_lost(sk, 1); + tcp_mark_head_lost(sk, 1, 1); } else if (tcp_is_fack(tp)) { int lost = tp->fackets_out - tp->reordering; if (lost <= 0) lost = 1; - tcp_mark_head_lost(sk, lost); + tcp_mark_head_lost(sk, lost, 0); } else { int sacked_upto = tp->sacked_out - tp->reordering; - if (sacked_upto < fast_rexmit) - sacked_upto = fast_rexmit; - tcp_mark_head_lost(sk, sacked_upto); + if (sacked_upto >= 0) + tcp_mark_head_lost(sk, sacked_upto, 0); + else if (fast_rexmit) + tcp_mark_head_lost(sk, 1, 1); } tcp_timeout_skbs(sk); @@ -2886,7 +2878,7 @@ static void tcp_mtup_probe_success(struct sock *sk) icsk->icsk_mtup.probe_size; tp->snd_cwnd_cnt = 0; tp->snd_cwnd_stamp = tcp_time_stamp; - tp->rcv_ssthresh = tcp_current_ssthresh(sk); + tp->snd_ssthresh = tcp_current_ssthresh(sk); icsk->icsk_mtup.search_low = icsk->icsk_mtup.probe_size; icsk->icsk_mtup.probe_size = 0; @@ -2983,7 +2975,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, int flag) before(tp->snd_una, tp->high_seq) && icsk->icsk_ca_state != TCP_CA_Open && tp->fackets_out > tp->reordering) { - tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering); + tcp_mark_head_lost(sk, tp->fackets_out - tp->reordering, 0); NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_TCPLOSS); } @@ -3411,8 +3403,8 @@ static void tcp_ack_probe(struct sock *sk) static inline int tcp_ack_is_dubious(const struct sock *sk, const int flag) { - return (!(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) || - inet_csk(sk)->icsk_ca_state != TCP_CA_Open); + return !(flag & FLAG_NOT_DUP) || (flag & FLAG_CA_ALERT) || + inet_csk(sk)->icsk_ca_state != TCP_CA_Open; } static inline int tcp_may_raise_cwnd(const struct sock *sk, const int flag) @@ -3429,9 +3421,9 @@ static inline int tcp_may_update_window(const struct tcp_sock *tp, const u32 ack, const u32 ack_seq, const u32 nwin) { - return (after(ack, tp->snd_una) || + return after(ack, tp->snd_una) || after(ack_seq, tp->snd_wl1) || - (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd)); + (ack_seq == tp->snd_wl1 && nwin > tp->snd_wnd); } /* Update our send window. @@ -4048,6 +4040,8 @@ static void tcp_reset(struct sock *sk) default: sk->sk_err = ECONNRESET; } + /* This barrier is coupled with smp_rmb() in tcp_poll() */ + smp_wmb(); if (!sock_flag(sk, SOCK_DEAD)) sk->sk_error_report(sk); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 020766292bb..8f8527d4168 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1422,7 +1422,7 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, newsk = tcp_create_openreq_child(sk, req, skb); if (!newsk) - goto exit; + goto exit_nonewsk; newsk->sk_gso_type = SKB_GSO_TCPV4; sk_setup_caps(newsk, dst); @@ -1469,16 +1469,20 @@ struct sock *tcp_v4_syn_recv_sock(struct sock *sk, struct sk_buff *skb, } #endif + if (__inet_inherit_port(sk, newsk) < 0) { + sock_put(newsk); + goto exit; + } __inet_hash_nolisten(newsk, NULL); - __inet_inherit_port(sk, newsk); return newsk; exit_overflow: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENOVERFLOWS); +exit_nonewsk: + dst_release(dst); exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); - dst_release(dst); return NULL; } EXPORT_SYMBOL(tcp_v4_syn_recv_sock); @@ -2571,7 +2575,6 @@ struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) return tcp_gro_receive(head, skb); } -EXPORT_SYMBOL(tcp4_gro_receive); int tcp4_gro_complete(struct sk_buff *skb) { @@ -2584,7 +2587,6 @@ int tcp4_gro_complete(struct sk_buff *skb) return tcp_gro_complete(skb); } -EXPORT_SYMBOL(tcp4_gro_complete); struct proto tcp_prot = { .name = "TCP", diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index f25b56cb85c..43cf901d765 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -55,7 +55,7 @@ static __inline__ int tcp_in_window(u32 seq, u32 end_seq, u32 s_win, u32 e_win) return 1; if (after(end_seq, s_win) && before(seq, e_win)) return 1; - return (seq == e_win && seq == end_seq); + return seq == e_win && seq == end_seq; } /* diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index de3bd845858..05b1ecf3676 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -224,16 +224,10 @@ void tcp_select_initial_window(int __space, __u32 mss, } } - /* Set initial window to value enough for senders, - * following RFC2414. Senders, not following this RFC, - * will be satisfied with 2. - */ + /* Set initial window to value enough for senders, following RFC5681. */ if (mss > (1 << *rcv_wscale)) { - int init_cwnd = 4; - if (mss > 1460 * 3) - init_cwnd = 2; - else if (mss > 1460) - init_cwnd = 3; + int init_cwnd = rfc3390_bytes_to_packets(mss); + /* when initializing use the value from init_rcv_wnd * rather than the default from above */ @@ -1376,9 +1370,9 @@ static inline int tcp_nagle_check(const struct tcp_sock *tp, const struct sk_buff *skb, unsigned mss_now, int nonagle) { - return (skb->len < mss_now && + return skb->len < mss_now && ((nonagle & TCP_NAGLE_CORK) || - (!nonagle && tp->packets_out && tcp_minshall_check(tp)))); + (!nonagle && tp->packets_out && tcp_minshall_check(tp))); } /* Return non-zero if the Nagle test allows this packet to be @@ -1449,10 +1443,10 @@ int tcp_may_send_now(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb = tcp_send_head(sk); - return (skb && + return skb && tcp_snd_test(sk, skb, tcp_current_mss(sk), (tcp_skb_is_last(sk, skb) ? - tp->nonagle : TCP_NAGLE_PUSH))); + tp->nonagle : TCP_NAGLE_PUSH)); } /* Trim TSO SKB to LEN bytes, put the remaining data into a new packet @@ -2429,6 +2423,12 @@ struct sk_buff *tcp_make_synack(struct sock *sk, struct dst_entry *dst, __u8 rcv_wscale; /* Set this up on the first call only */ req->window_clamp = tp->window_clamp ? : dst_metric(dst, RTAX_WINDOW); + + /* limit the window selection if the user enforce a smaller rx buffer */ + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (req->window_clamp > tcp_full_space(sk) || req->window_clamp == 0)) + req->window_clamp = tcp_full_space(sk); + /* tcp_full_space because it is guaranteed to be the first packet */ tcp_select_initial_window(tcp_full_space(sk), mss - (ireq->tstamp_ok ? TCPOLEN_TSTAMP_ALIGNED : 0), @@ -2555,6 +2555,11 @@ static void tcp_connect_init(struct sock *sk) tcp_initialize_rcv_mss(sk); + /* limit the window selection if the user enforce a smaller rx buffer */ + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK && + (tp->window_clamp > tcp_full_space(sk) || tp->window_clamp == 0)) + tp->window_clamp = tcp_full_space(sk); + tcp_select_initial_window(tcp_full_space(sk), tp->advmss - (tp->rx_opt.ts_recent_stamp ? tp->tcp_header_len - sizeof(struct tcphdr) : 0), &tp->rcv_wnd, diff --git a/net/ipv4/tcp_probe.c b/net/ipv4/tcp_probe.c index f8efada580e..6211e211417 100644 --- a/net/ipv4/tcp_probe.c +++ b/net/ipv4/tcp_probe.c @@ -214,6 +214,7 @@ static const struct file_operations tcpprobe_fops = { .owner = THIS_MODULE, .open = tcpprobe_open, .read = tcpprobe_read, + .llseek = noop_llseek, }; static __init int tcpprobe_init(void) diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index c35b469e851..74a6aa00365 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -135,13 +135,16 @@ static void tcp_mtu_probing(struct inet_connection_sock *icsk, struct sock *sk) /* This function calculates a "timeout" which is equivalent to the timeout of a * TCP connection after "boundary" unsuccessful, exponentially backed-off - * retransmissions with an initial RTO of TCP_RTO_MIN. + * retransmissions with an initial RTO of TCP_RTO_MIN or TCP_TIMEOUT_INIT if + * syn_set flag is set. */ static bool retransmits_timed_out(struct sock *sk, - unsigned int boundary) + unsigned int boundary, + unsigned int timeout, + bool syn_set) { - unsigned int timeout, linear_backoff_thresh; - unsigned int start_ts; + unsigned int linear_backoff_thresh, start_ts; + unsigned int rto_base = syn_set ? TCP_TIMEOUT_INIT : TCP_RTO_MIN; if (!inet_csk(sk)->icsk_retransmits) return false; @@ -151,14 +154,15 @@ static bool retransmits_timed_out(struct sock *sk, else start_ts = tcp_sk(sk)->retrans_stamp; - linear_backoff_thresh = ilog2(TCP_RTO_MAX/TCP_RTO_MIN); - - if (boundary <= linear_backoff_thresh) - timeout = ((2 << boundary) - 1) * TCP_RTO_MIN; - else - timeout = ((2 << linear_backoff_thresh) - 1) * TCP_RTO_MIN + - (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + if (likely(timeout == 0)) { + linear_backoff_thresh = ilog2(TCP_RTO_MAX/rto_base); + if (boundary <= linear_backoff_thresh) + timeout = ((2 << boundary) - 1) * rto_base; + else + timeout = ((2 << linear_backoff_thresh) - 1) * rto_base + + (boundary - linear_backoff_thresh) * TCP_RTO_MAX; + } return (tcp_time_stamp - start_ts) >= timeout; } @@ -167,14 +171,15 @@ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; - bool do_reset; + bool do_reset, syn_set = 0; if ((1 << sk->sk_state) & (TCPF_SYN_SENT | TCPF_SYN_RECV)) { if (icsk->icsk_retransmits) dst_negative_advice(sk); retry_until = icsk->icsk_syn_retries ? : sysctl_tcp_syn_retries; + syn_set = 1; } else { - if (retransmits_timed_out(sk, sysctl_tcp_retries1)) { + if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { /* Black hole detection */ tcp_mtu_probing(icsk, sk); @@ -187,14 +192,15 @@ static int tcp_write_timeout(struct sock *sk) retry_until = tcp_orphan_retries(sk, alive); do_reset = alive || - !retransmits_timed_out(sk, retry_until); + !retransmits_timed_out(sk, retry_until, 0, 0); if (tcp_out_of_resources(sk, do_reset)) return 1; } } - if (retransmits_timed_out(sk, retry_until)) { + if (retransmits_timed_out(sk, retry_until, + syn_set ? 0 : icsk->icsk_user_timeout, syn_set)) { /* Has it gone just too far? */ tcp_write_err(sk); return 1; @@ -361,18 +367,19 @@ void tcp_retransmit_timer(struct sock *sk) if (icsk->icsk_retransmits == 0) { int mib_idx; - if (icsk->icsk_ca_state == TCP_CA_Disorder) { - if (tcp_is_sack(tp)) - mib_idx = LINUX_MIB_TCPSACKFAILURES; - else - mib_idx = LINUX_MIB_TCPRENOFAILURES; - } else if (icsk->icsk_ca_state == TCP_CA_Recovery) { + if (icsk->icsk_ca_state == TCP_CA_Recovery) { if (tcp_is_sack(tp)) mib_idx = LINUX_MIB_TCPSACKRECOVERYFAIL; else mib_idx = LINUX_MIB_TCPRENORECOVERYFAIL; } else if (icsk->icsk_ca_state == TCP_CA_Loss) { mib_idx = LINUX_MIB_TCPLOSSFAILURES; + } else if ((icsk->icsk_ca_state == TCP_CA_Disorder) || + tp->sacked_out) { + if (tcp_is_sack(tp)) + mib_idx = LINUX_MIB_TCPSACKFAILURES; + else + mib_idx = LINUX_MIB_TCPRENOFAILURES; } else { mib_idx = LINUX_MIB_TCPTIMEOUTS; } @@ -436,7 +443,7 @@ out_reset_timer: icsk->icsk_rto = min(icsk->icsk_rto << 1, TCP_RTO_MAX); } inet_csk_reset_xmit_timer(sk, ICSK_TIME_RETRANS, icsk->icsk_rto, TCP_RTO_MAX); - if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1)) + if (retransmits_timed_out(sk, sysctl_tcp_retries1 + 1, 0, 0)) __sk_dst_reset(sk); out:; @@ -556,7 +563,14 @@ static void tcp_keepalive_timer (unsigned long data) elapsed = keepalive_time_elapsed(tp); if (elapsed >= keepalive_time_when(tp)) { - if (icsk->icsk_probes_out >= keepalive_probes(tp)) { + /* If the TCP_USER_TIMEOUT option is enabled, use that + * to determine when to timeout instead. + */ + if ((icsk->icsk_user_timeout != 0 && + elapsed >= icsk->icsk_user_timeout && + icsk->icsk_probes_out > 0) || + (icsk->icsk_user_timeout == 0 && + icsk->icsk_probes_out >= keepalive_probes(tp))) { tcp_send_active_reset(sk, GFP_ATOMIC); tcp_write_err(sk); goto out; diff --git a/net/ipv4/tcp_veno.c b/net/ipv4/tcp_veno.c index b612acf7618..38bc0b52d74 100644 --- a/net/ipv4/tcp_veno.c +++ b/net/ipv4/tcp_veno.c @@ -6,7 +6,7 @@ * "TCP Veno: TCP Enhancement for Transmission over Wireless Access Networks." * IEEE Journal on Selected Areas in Communication, * Feb. 2003. - * See http://www.ntu.edu.sg/home5/ZHOU0022/papers/CPFu03a.pdf + * See http://www.ie.cuhk.edu.hk/fileadmin/staff_upload/soung/Journal/J3.pdf */ #include <linux/mm.h> diff --git a/net/ipv4/tcp_westwood.c b/net/ipv4/tcp_westwood.c index 20151d6a624..a534dda5456 100644 --- a/net/ipv4/tcp_westwood.c +++ b/net/ipv4/tcp_westwood.c @@ -80,7 +80,7 @@ static void tcp_westwood_init(struct sock *sk) */ static inline u32 westwood_do_filter(u32 a, u32 b) { - return (((7 * a) + b) >> 3); + return ((7 * a) + b) >> 3; } static void westwood_filter(struct westwood *w, u32 delta) diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index 59186ca7808..ac3b3ee4b07 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -14,32 +14,37 @@ #include <net/protocol.h> #include <net/xfrm.h> -static struct xfrm_tunnel *tunnel4_handlers; -static struct xfrm_tunnel *tunnel64_handlers; +static struct xfrm_tunnel __rcu *tunnel4_handlers __read_mostly; +static struct xfrm_tunnel __rcu *tunnel64_handlers __read_mostly; static DEFINE_MUTEX(tunnel4_mutex); -static inline struct xfrm_tunnel **fam_handlers(unsigned short family) +static inline struct xfrm_tunnel __rcu **fam_handlers(unsigned short family) { return (family == AF_INET) ? &tunnel4_handlers : &tunnel64_handlers; } int xfrm4_tunnel_register(struct xfrm_tunnel *handler, unsigned short family) { - struct xfrm_tunnel **pprev; + struct xfrm_tunnel __rcu **pprev; + struct xfrm_tunnel *t; + int ret = -EEXIST; int priority = handler->priority; mutex_lock(&tunnel4_mutex); - for (pprev = fam_handlers(family); *pprev; pprev = &(*pprev)->next) { - if ((*pprev)->priority > priority) + for (pprev = fam_handlers(family); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&tunnel4_mutex))) != NULL; + pprev = &t->next) { + if (t->priority > priority) break; - if ((*pprev)->priority == priority) + if (t->priority == priority) goto err; } handler->next = *pprev; - *pprev = handler; + rcu_assign_pointer(*pprev, handler); ret = 0; @@ -52,13 +57,17 @@ EXPORT_SYMBOL(xfrm4_tunnel_register); int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family) { - struct xfrm_tunnel **pprev; + struct xfrm_tunnel __rcu **pprev; + struct xfrm_tunnel *t; int ret = -ENOENT; mutex_lock(&tunnel4_mutex); - for (pprev = fam_handlers(family); *pprev; pprev = &(*pprev)->next) { - if (*pprev == handler) { + for (pprev = fam_handlers(family); + (t = rcu_dereference_protected(*pprev, + lockdep_is_held(&tunnel4_mutex))) != NULL; + pprev = &t->next) { + if (t == handler) { *pprev = handler->next; ret = 0; break; @@ -73,6 +82,11 @@ int xfrm4_tunnel_deregister(struct xfrm_tunnel *handler, unsigned short family) } EXPORT_SYMBOL(xfrm4_tunnel_deregister); +#define for_each_tunnel_rcu(head, handler) \ + for (handler = rcu_dereference(head); \ + handler != NULL; \ + handler = rcu_dereference(handler->next)) \ + static int tunnel4_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; @@ -80,7 +94,7 @@ static int tunnel4_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct iphdr))) goto drop; - for (handler = tunnel4_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel4_handlers, handler) if (!handler->handler(skb)) return 0; @@ -99,7 +113,7 @@ static int tunnel64_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, sizeof(struct ipv6hdr))) goto drop; - for (handler = tunnel64_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel64_handlers, handler) if (!handler->handler(skb)) return 0; @@ -115,7 +129,7 @@ static void tunnel4_err(struct sk_buff *skb, u32 info) { struct xfrm_tunnel *handler; - for (handler = tunnel4_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel4_handlers, handler) if (!handler->err_handler(skb, info)) break; } @@ -125,7 +139,7 @@ static void tunnel64_err(struct sk_buff *skb, u32 info) { struct xfrm_tunnel *handler; - for (handler = tunnel64_handlers; handler; handler = handler->next) + for_each_tunnel_rcu(tunnel64_handlers, handler) if (!handler->err_handler(skb, info)) break; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 32e0bef60d0..28cb2d733a3 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -797,7 +797,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, return -EOPNOTSUPP; ipc.opt = NULL; - ipc.shtx.flags = 0; + ipc.tx_flags = 0; if (up->pending) { /* @@ -845,7 +845,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; - err = sock_tx_timestamp(msg, sk, &ipc.shtx); + err = sock_tx_timestamp(sk, &ipc.tx_flags); if (err) return err; if (msg->msg_controllen) { @@ -1260,6 +1260,49 @@ void udp_lib_unhash(struct sock *sk) } EXPORT_SYMBOL(udp_lib_unhash); +/* + * inet_rcv_saddr was changed, we must rehash secondary hash + */ +void udp_lib_rehash(struct sock *sk, u16 newhash) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2, *nhslot2; + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + nhslot2 = udp_hashslot2(udptable, newhash); + udp_sk(sk)->udp_portaddr_hash = newhash; + if (hslot2 != nhslot2) { + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + /* we must lock primary chain too */ + spin_lock_bh(&hslot->lock); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + + spin_unlock_bh(&hslot->lock); + } + } +} +EXPORT_SYMBOL(udp_lib_rehash); + +static void udp_v4_rehash(struct sock *sk) +{ + u16 new_hash = udp4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + udp_lib_rehash(sk, new_hash); +} + static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; @@ -1370,7 +1413,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) } } - if (sk->sk_filter) { + if (rcu_dereference_raw(sk->sk_filter)) { if (udp_lib_checksum_complete(skb)) goto drop; } @@ -1843,6 +1886,7 @@ struct proto udp_prot = { .backlog_rcv = __udp_queue_rcv_skb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 869078d4eeb..4464f3bff6a 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -61,7 +61,7 @@ static int xfrm4_get_saddr(struct net *net, static int xfrm4_get_tos(struct flowi *fl) { - return fl->fl4_tos; + return IPTOS_RT_MASK & fl->fl4_tos; /* Strip ECN bits */ } static int xfrm4_init_path(struct xfrm_dst *path, struct dst_entry *dst, @@ -174,7 +174,7 @@ static inline int xfrm4_garbage_collect(struct dst_ops *ops) struct net *net = container_of(ops, struct net, xfrm.xfrm4_dst_ops); xfrm4_policy_afinfo.garbage_collect(net); - return (atomic_read(&ops->entries) > ops->gc_thresh * 2); + return (dst_entries_get_slow(ops) > ops->gc_thresh * 2); } static void xfrm4_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -232,7 +232,6 @@ static struct dst_ops xfrm4_dst_ops = { .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, .gc_thresh = 1024, - .entries = ATOMIC_INIT(0), }; static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { @@ -288,6 +287,7 @@ void __init xfrm4_init(int rt_max_size) * and start cleaning when were 1/2 full */ xfrm4_dst_ops.gc_thresh = rt_max_size/2; + dst_entries_init(&xfrm4_dst_ops); xfrm4_state_init(); xfrm4_policy_init(); diff --git a/net/ipv4/xfrm4_state.c b/net/ipv4/xfrm4_state.c index 1ef1366a0a0..47947624ecc 100644 --- a/net/ipv4/xfrm4_state.c +++ b/net/ipv4/xfrm4_state.c @@ -21,21 +21,25 @@ static int xfrm4_init_flags(struct xfrm_state *x) } static void -__xfrm4_init_tempsel(struct xfrm_state *x, struct flowi *fl, - struct xfrm_tmpl *tmpl, - xfrm_address_t *daddr, xfrm_address_t *saddr) +__xfrm4_init_tempsel(struct xfrm_selector *sel, struct flowi *fl) +{ + sel->daddr.a4 = fl->fl4_dst; + sel->saddr.a4 = fl->fl4_src; + sel->dport = xfrm_flowi_dport(fl); + sel->dport_mask = htons(0xffff); + sel->sport = xfrm_flowi_sport(fl); + sel->sport_mask = htons(0xffff); + sel->family = AF_INET; + sel->prefixlen_d = 32; + sel->prefixlen_s = 32; + sel->proto = fl->proto; + sel->ifindex = fl->oif; +} + +static void +xfrm4_init_temprop(struct xfrm_state *x, struct xfrm_tmpl *tmpl, + xfrm_address_t *daddr, xfrm_address_t *saddr) { - x->sel.daddr.a4 = fl->fl4_dst; - x->sel.saddr.a4 = fl->fl4_src; - x->sel.dport = xfrm_flowi_dport(fl); - x->sel.dport_mask = htons(0xffff); - x->sel.sport = xfrm_flowi_sport(fl); - x->sel.sport_mask = htons(0xffff); - x->sel.family = AF_INET; - x->sel.prefixlen_d = 32; - x->sel.prefixlen_s = 32; - x->sel.proto = fl->proto; - x->sel.ifindex = fl->oif; x->id = tmpl->id; if (x->id.daddr.a4 == 0) x->id.daddr.a4 = daddr->a4; @@ -70,6 +74,7 @@ static struct xfrm_state_afinfo xfrm4_state_afinfo = { .owner = THIS_MODULE, .init_flags = xfrm4_init_flags, .init_tempsel = __xfrm4_init_tempsel, + .init_temprop = xfrm4_init_temprop, .output = xfrm4_output, .extract_input = xfrm4_extract_input, .extract_output = xfrm4_extract_output, diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 41f5982d208..82806455e85 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -58,14 +58,14 @@ static int xfrm_tunnel_err(struct sk_buff *skb, u32 info) return -ENOENT; } -static struct xfrm_tunnel xfrm_tunnel_handler = { +static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = { .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, .priority = 2, }; #if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) -static struct xfrm_tunnel xfrm64_tunnel_handler = { +static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = { .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, .priority = 2, |