diff options
Diffstat (limited to 'net/ipv4')
66 files changed, 1656 insertions, 815 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index cbb505ba932..335ca7abbd4 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -163,8 +163,6 @@ config IP_PNP_RARP operating on your network. Read <file:Documentation/filesystems/nfs/nfsroot.txt> for details. -# not yet ready.. -# bool ' IP: ARP support' CONFIG_IP_PNP_ARP config NET_IPIP tristate "IP: tunneling" select INET_TUNNEL @@ -409,6 +407,10 @@ config INET_TCP_DIAG depends on INET_DIAG def_tristate INET_DIAG +config INET_UDP_DIAG + depends on INET_DIAG + def_tristate INET_DIAG && IPV6 + menuconfig TCP_CONG_ADVANCED bool "TCP: advanced congestion control" ---help--- diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index f2dc69cffb5..ff75d3bbcd6 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -34,6 +34,7 @@ obj-$(CONFIG_IP_PNP) += ipconfig.o obj-$(CONFIG_NETFILTER) += netfilter.o netfilter/ obj-$(CONFIG_INET_DIAG) += inet_diag.o obj-$(CONFIG_INET_TCP_DIAG) += tcp_diag.o +obj-$(CONFIG_INET_UDP_DIAG) += udp_diag.o obj-$(CONFIG_NET_TCPPROBE) += tcp_probe.o obj-$(CONFIG_TCP_CONG_BIC) += tcp_bic.o obj-$(CONFIG_TCP_CONG_CUBIC) += tcp_cubic.o @@ -47,6 +48,7 @@ obj-$(CONFIG_TCP_CONG_SCALABLE) += tcp_scalable.o obj-$(CONFIG_TCP_CONG_LP) += tcp_lp.o obj-$(CONFIG_TCP_CONG_YEAH) += tcp_yeah.o obj-$(CONFIG_TCP_CONG_ILLINOIS) += tcp_illinois.o +obj-$(CONFIG_CGROUP_MEM_RES_CTLR_KMEM) += tcp_memcontrol.o obj-$(CONFIG_NETLABEL) += cipso_ipv4.o obj-$(CONFIG_XFRM) += xfrm4_policy.o xfrm4_state.o xfrm4_input.o \ diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index 1b5096a9875..f7b5670744f 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1250,7 +1250,8 @@ out: return err; } -static struct sk_buff *inet_gso_segment(struct sk_buff *skb, u32 features) +static struct sk_buff *inet_gso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct iphdr *iph; @@ -1572,9 +1573,9 @@ static __net_init int ipv4_mib_init_net(struct net *net) sizeof(struct icmp_mib), __alignof__(struct icmp_mib)) < 0) goto err_icmp_mib; - if (snmp_mib_init((void __percpu **)net->mib.icmpmsg_statistics, - sizeof(struct icmpmsg_mib), - __alignof__(struct icmpmsg_mib)) < 0) + net->mib.icmpmsg_statistics = kzalloc(sizeof(struct icmpmsg_mib), + GFP_KERNEL); + if (!net->mib.icmpmsg_statistics) goto err_icmpmsg_mib; tcp_mib_init(net); @@ -1598,7 +1599,7 @@ err_tcp_mib: static __net_exit void ipv4_mib_exit_net(struct net *net) { - snmp_mib_free((void __percpu **)net->mib.icmpmsg_statistics); + kfree(net->mib.icmpmsg_statistics); snmp_mib_free((void __percpu **)net->mib.icmp_statistics); snmp_mib_free((void __percpu **)net->mib.udplite_statistics); snmp_mib_free((void __percpu **)net->mib.udp_statistics); @@ -1671,6 +1672,8 @@ static int __init inet_init(void) ip_static_sysctl_init(); #endif + tcp_prot.sysctl_mem = init_net.ipv4.sysctl_tcp_mem; + /* * Add all the base protocols. */ diff --git a/net/ipv4/ah4.c b/net/ipv4/ah4.c index c1f4154552f..36d14406261 100644 --- a/net/ipv4/ah4.c +++ b/net/ipv4/ah4.c @@ -136,8 +136,6 @@ static void ah_output_done(struct crypto_async_request *base, int err) memcpy(top_iph+1, iph+1, top_iph->ihl*4 - sizeof(struct iphdr)); } - err = ah->nexthdr; - kfree(AH_SKB_CB(skb)->tmp); xfrm_output_resume(skb, err); } @@ -264,12 +262,12 @@ static void ah_input_done(struct crypto_async_request *base, int err) if (err) goto out; + err = ah->nexthdr; + skb->network_header += ah_hlen; memcpy(skb_network_header(skb), work_iph, ihl); __skb_pull(skb, ah_hlen + ihl); skb_set_transport_header(skb, -ihl); - - err = ah->nexthdr; out: kfree(AH_SKB_CB(skb)->tmp); xfrm_input_resume(skb, err); @@ -371,8 +369,6 @@ static int ah_input(struct xfrm_state *x, struct sk_buff *skb) if (err == -EINPROGRESS) goto out; - if (err == -EBUSY) - err = NET_XMIT_DROP; goto out_free; } diff --git a/net/ipv4/arp.c b/net/ipv4/arp.c index 96a164aa136..59402be133f 100644 --- a/net/ipv4/arp.c +++ b/net/ipv4/arp.c @@ -112,11 +112,6 @@ #include <net/arp.h> #include <net/ax25.h> #include <net/netrom.h> -#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) -#include <net/atmclip.h> -struct neigh_table *clip_tbl_hook; -EXPORT_SYMBOL(clip_tbl_hook); -#endif #include <asm/system.h> #include <linux/uaccess.h> @@ -126,7 +121,7 @@ EXPORT_SYMBOL(clip_tbl_hook); /* * Interface to generic neighbour cache. */ -static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 rnd); +static u32 arp_hash(const void *pkey, const struct net_device *dev, __u32 *hash_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); @@ -164,7 +159,6 @@ static const struct neigh_ops 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, @@ -177,7 +171,7 @@ struct neigh_table arp_tbl = { .gc_staletime = 60 * HZ, .reachable_time = 30 * HZ, .delay_probe_time = 5 * HZ, - .queue_len = 3, + .queue_len_bytes = 64*1024, .ucast_probes = 3, .mcast_probes = 3, .anycast_delay = 1 * HZ, @@ -221,9 +215,9 @@ 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, - __u32 hash_rnd) + __u32 *hash_rnd) { - return arp_hashfn(*(u32 *)pkey, dev, hash_rnd); + return arp_hashfn(*(u32 *)pkey, dev, *hash_rnd); } static int arp_constructor(struct neighbour *neigh) @@ -283,9 +277,9 @@ static int arp_constructor(struct neighbour *neigh) default: break; case ARPHRD_ROSE: -#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: -#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE) +#if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: #endif neigh->ops = &arp_broken_ops; @@ -592,16 +586,18 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, struct sk_buff *skb; struct arphdr *arp; unsigned char *arp_ptr; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; /* * Allocate a buffer */ - skb = alloc_skb(arp_hdr_len(dev) + LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + skb = alloc_skb(arp_hdr_len(dev) + hlen + tlen, GFP_ATOMIC); if (skb == NULL) return NULL; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); arp = (struct arphdr *) skb_put(skb, arp_hdr_len(dev)); skb->dev = dev; @@ -633,13 +629,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, arp->ar_pro = htons(ETH_P_IP); break; -#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if IS_ENABLED(CONFIG_AX25) case ARPHRD_AX25: arp->ar_hrd = htons(ARPHRD_AX25); arp->ar_pro = htons(AX25_P_IP); break; -#if defined(CONFIG_NETROM) || defined(CONFIG_NETROM_MODULE) +#if IS_ENABLED(CONFIG_NETROM) case ARPHRD_NETROM: arp->ar_hrd = htons(ARPHRD_NETROM); arp->ar_pro = htons(AX25_P_IP); @@ -647,13 +643,13 @@ struct sk_buff *arp_create(int type, int ptype, __be32 dest_ip, #endif #endif -#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE) +#if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: arp->ar_hrd = htons(ARPHRD_ETHER); arp->ar_pro = htons(ETH_P_IP); break; #endif -#if defined(CONFIG_TR) || defined(CONFIG_TR_MODULE) +#if IS_ENABLED(CONFIG_TR) case ARPHRD_IEEE802_TR: arp->ar_hrd = htons(ARPHRD_IEEE802); arp->ar_pro = htons(ETH_P_IP); @@ -1040,7 +1036,7 @@ static int arp_req_set(struct net *net, struct arpreq *r, return -EINVAL; } switch (dev->type) { -#if defined(CONFIG_FDDI) || defined(CONFIG_FDDI_MODULE) +#if IS_ENABLED(CONFIG_FDDI) case ARPHRD_FDDI: /* * According to RFC 1390, FDDI devices should accept ARP @@ -1286,7 +1282,7 @@ void __init arp_init(void) } #ifdef CONFIG_PROC_FS -#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if IS_ENABLED(CONFIG_AX25) /* ------------------------------------------------------------------------ */ /* @@ -1334,7 +1330,7 @@ static void arp_format_neigh_entry(struct seq_file *seq, read_lock(&n->lock); /* Convert hardware address to XX:XX:XX:XX ... form. */ -#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if IS_ENABLED(CONFIG_AX25) if (hatype == ARPHRD_AX25 || hatype == ARPHRD_NETROM) ax2asc2((ax25_address *)n->ha, hbuffer); else { @@ -1347,7 +1343,7 @@ static void arp_format_neigh_entry(struct seq_file *seq, if (k != 0) --k; hbuffer[k] = 0; -#if defined(CONFIG_AX25) || defined(CONFIG_AX25_MODULE) +#if IS_ENABLED(CONFIG_AX25) } #endif sprintf(tbuf, "%pI4", n->primary_key); diff --git a/net/ipv4/devinet.c b/net/ipv4/devinet.c index c6b5092f29a..65f01dc4756 100644 --- a/net/ipv4/devinet.c +++ b/net/ipv4/devinet.c @@ -1490,7 +1490,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, void __user *buffer, size_t *lenp, loff_t *ppos) { + int old_value = *(int *)ctl->data; int ret = proc_dointvec(ctl, write, buffer, lenp, ppos); + int new_value = *(int *)ctl->data; if (write) { struct ipv4_devconf *cnf = ctl->extra1; @@ -1501,6 +1503,9 @@ static int devinet_conf_proc(ctl_table *ctl, int write, if (cnf == net->ipv4.devconf_dflt) devinet_copy_dflt_conf(net, i); + if (i == IPV4_DEVCONF_ACCEPT_LOCAL - 1) + if ((new_value == 0) && (old_value != 0)) + rt_cache_flush(net, 0); } return ret; diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 46339ba7a2d..799fc790b3c 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -67,6 +67,7 @@ int fib_lookup(struct net *net, struct flowi4 *flp, struct fib_result *res) return err; } +EXPORT_SYMBOL_GPL(fib_lookup); static int fib4_rule_action(struct fib_rule *rule, struct flowi *flp, int flags, struct fib_lookup_arg *arg) diff --git a/net/ipv4/fib_trie.c b/net/ipv4/fib_trie.c index 37b671185c8..d04b13ae18f 100644 --- a/net/ipv4/fib_trie.c +++ b/net/ipv4/fib_trie.c @@ -1607,6 +1607,7 @@ found: rcu_read_unlock(); return ret; } +EXPORT_SYMBOL_GPL(fib_table_lookup); /* * Remove the leaf and return parent. diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c index c7472eff2d5..fa057d105be 100644 --- a/net/ipv4/igmp.c +++ b/net/ipv4/igmp.c @@ -304,9 +304,11 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) struct igmpv3_report *pig; struct net *net = dev_net(dev); struct flowi4 fl4; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; while (1) { - skb = alloc_skb(size + LL_ALLOCATED_SPACE(dev), + skb = alloc_skb(size + hlen + tlen, GFP_ATOMIC | __GFP_NOWARN); if (skb) break; @@ -327,7 +329,7 @@ static struct sk_buff *igmpv3_newpack(struct net_device *dev, int size) skb_dst_set(skb, &rt->dst); skb->dev = dev; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); pip = ip_hdr(skb); @@ -647,6 +649,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, __be32 group = pmc ? pmc->multiaddr : 0; struct flowi4 fl4; __be32 dst; + int hlen, tlen; if (type == IGMPV3_HOST_MEMBERSHIP_REPORT) return igmpv3_send_report(in_dev, pmc); @@ -661,7 +664,9 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, if (IS_ERR(rt)) return -1; - skb = alloc_skb(IGMP_SIZE+LL_ALLOCATED_SPACE(dev), GFP_ATOMIC); + hlen = LL_RESERVED_SPACE(dev); + tlen = dev->needed_tailroom; + skb = alloc_skb(IGMP_SIZE + hlen + tlen, GFP_ATOMIC); if (skb == NULL) { ip_rt_put(rt); return -1; @@ -669,7 +674,7 @@ static int igmp_send_report(struct in_device *in_dev, struct ip_mc_list *pmc, skb_dst_set(skb, &rt->dst); - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); skb_reset_network_header(skb); iph = ip_hdr(skb); @@ -1574,7 +1579,7 @@ out_unlock: * Add multicast single-source filter to the interface list */ static int ip_mc_add1_src(struct ip_mc_list *pmc, int sfmode, - __be32 *psfsrc, int delta) + __be32 *psfsrc) { struct ip_sf_list *psf, *psf_prev; @@ -1709,14 +1714,15 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode, pmc->sfcount[sfmode]++; err = 0; for (i=0; i<sfcount; i++) { - err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i], delta); + err = ip_mc_add1_src(pmc, sfmode, &psfsrc[i]); if (err) break; } if (err) { int j; - pmc->sfcount[sfmode]--; + if (!delta) + pmc->sfcount[sfmode]--; for (j=0; j<i; j++) (void) ip_mc_del1_src(pmc, sfmode, &psfsrc[j]); } else if (isexclude != (pmc->sfcount[MCAST_EXCLUDE] != 0)) { diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index c14d88ad348..2e4e24476c4 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -418,7 +418,7 @@ static inline u32 inet_synq_hash(const __be32 raddr, const __be16 rport, return jhash_2words((__force u32)raddr, (__force u32)rport, rnd) & (synq_hsize - 1); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #define AF_INET_FAMILY(fam) ((fam) == AF_INET) #else #define AF_INET_FAMILY(fam) 1 @@ -588,10 +588,19 @@ void inet_csk_reqsk_queue_prune(struct sock *parent, } EXPORT_SYMBOL_GPL(inet_csk_reqsk_queue_prune); -struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, - const gfp_t priority) +/** + * inet_csk_clone_lock - clone an inet socket, and lock its clone + * @sk: the socket to clone + * @req: request_sock + * @priority: for allocation (%GFP_KERNEL, %GFP_ATOMIC, etc) + * + * Caller must unlock socket even in error path (bh_unlock_sock(newsk)) + */ +struct sock *inet_csk_clone_lock(const struct sock *sk, + const struct request_sock *req, + const gfp_t priority) { - struct sock *newsk = sk_clone(sk, priority); + struct sock *newsk = sk_clone_lock(sk, priority); if (newsk != NULL) { struct inet_connection_sock *newicsk = inet_csk(newsk); @@ -615,7 +624,7 @@ struct sock *inet_csk_clone(struct sock *sk, const struct request_sock *req, } return newsk; } -EXPORT_SYMBOL_GPL(inet_csk_clone); +EXPORT_SYMBOL_GPL(inet_csk_clone_lock); /* * At this point, there should be no process reference to this diff --git a/net/ipv4/inet_diag.c b/net/ipv4/inet_diag.c index f5e2bdaef94..2240a8e8c44 100644 --- a/net/ipv4/inet_diag.c +++ b/net/ipv4/inet_diag.c @@ -33,6 +33,7 @@ #include <linux/stddef.h> #include <linux/inet_diag.h> +#include <linux/sock_diag.h> static const struct inet_diag_handler **inet_diag_table; @@ -45,24 +46,22 @@ struct inet_diag_entry { u16 userlocks; }; -static struct sock *idiagnl; - #define INET_DIAG_PUT(skb, attrtype, attrlen) \ RTA_DATA(__RTA_PUT(skb, attrtype, attrlen)) static DEFINE_MUTEX(inet_diag_table_mutex); -static const struct inet_diag_handler *inet_diag_lock_handler(int type) +static const struct inet_diag_handler *inet_diag_lock_handler(int proto) { - if (!inet_diag_table[type]) - request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK, - NETLINK_INET_DIAG, type); + if (!inet_diag_table[proto]) + request_module("net-pf-%d-proto-%d-type-%d-%d", PF_NETLINK, + NETLINK_SOCK_DIAG, AF_INET, proto); mutex_lock(&inet_diag_table_mutex); - if (!inet_diag_table[type]) + if (!inet_diag_table[proto]) return ERR_PTR(-ENOENT); - return inet_diag_table[type]; + return inet_diag_table[proto]; } static inline void inet_diag_unlock_handler( @@ -71,21 +70,21 @@ static inline void inet_diag_unlock_handler( mutex_unlock(&inet_diag_table_mutex); } -static int inet_csk_diag_fill(struct sock *sk, - struct sk_buff *skb, - int ext, u32 pid, u32 seq, u16 nlmsg_flags, +int inet_sk_diag_fill(struct sock *sk, struct inet_connection_sock *icsk, + struct sk_buff *skb, struct inet_diag_req *req, + u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { const struct inet_sock *inet = inet_sk(sk); - const struct inet_connection_sock *icsk = inet_csk(sk); struct inet_diag_msg *r; struct nlmsghdr *nlh; void *info = NULL; struct inet_diag_meminfo *minfo = NULL; unsigned char *b = skb_tail_pointer(skb); const struct inet_diag_handler *handler; + int ext = req->idiag_ext; - handler = inet_diag_table[unlh->nlmsg_type]; + handler = inet_diag_table[req->sdiag_protocol]; BUG_ON(handler == NULL); nlh = NLMSG_PUT(skb, pid, seq, unlh->nlmsg_type, sizeof(*r)); @@ -97,47 +96,55 @@ static int inet_csk_diag_fill(struct sock *sk, if (ext & (1 << (INET_DIAG_MEMINFO - 1))) minfo = INET_DIAG_PUT(skb, INET_DIAG_MEMINFO, sizeof(*minfo)); - if (ext & (1 << (INET_DIAG_INFO - 1))) - info = INET_DIAG_PUT(skb, INET_DIAG_INFO, - handler->idiag_info_size); - - if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) { - const size_t len = strlen(icsk->icsk_ca_ops->name); - - strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1), - icsk->icsk_ca_ops->name); - } - - if ((ext & (1 << (INET_DIAG_TOS - 1))) && (sk->sk_family != AF_INET6)) - RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); - r->idiag_family = sk->sk_family; r->idiag_state = sk->sk_state; r->idiag_timer = 0; r->idiag_retrans = 0; r->id.idiag_if = sk->sk_bound_dev_if; - r->id.idiag_cookie[0] = (u32)(unsigned long)sk; - r->id.idiag_cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1); + sock_diag_save_cookie(sk, r->id.idiag_cookie); r->id.idiag_sport = inet->inet_sport; r->id.idiag_dport = inet->inet_dport; r->id.idiag_src[0] = inet->inet_rcv_saddr; r->id.idiag_dst[0] = inet->inet_daddr; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) + /* IPv6 dual-stack sockets use inet->tos for IPv4 connections, + * hence this needs to be included regardless of socket family. + */ + if (ext & (1 << (INET_DIAG_TOS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TOS, inet->tos); + +#if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { const struct ipv6_pinfo *np = inet6_sk(sk); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &np->rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &np->daddr); - if (ext & (1 << (INET_DIAG_TOS - 1))) - RTA_PUT_U8(skb, INET_DIAG_TOS, np->tclass); + *(struct in6_addr *)r->id.idiag_src = np->rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = np->daddr; + if (ext & (1 << (INET_DIAG_TCLASS - 1))) + RTA_PUT_U8(skb, INET_DIAG_TCLASS, np->tclass); } #endif + r->idiag_uid = sock_i_uid(sk); + r->idiag_inode = sock_i_ino(sk); + + if (minfo) { + minfo->idiag_rmem = sk_rmem_alloc_get(sk); + minfo->idiag_wmem = sk->sk_wmem_queued; + minfo->idiag_fmem = sk->sk_forward_alloc; + minfo->idiag_tmem = sk_wmem_alloc_get(sk); + } + + if (ext & (1 << (INET_DIAG_SKMEMINFO - 1))) + if (sock_diag_put_meminfo(sk, skb, INET_DIAG_SKMEMINFO)) + goto rtattr_failure; + + if (icsk == NULL) { + r->idiag_rqueue = r->idiag_wqueue = 0; + goto out; + } + #define EXPIRES_IN_MS(tmo) DIV_ROUND_UP((tmo - jiffies) * 1000, HZ) if (icsk->icsk_pending == ICSK_TIME_RETRANS) { @@ -158,14 +165,14 @@ static int inet_csk_diag_fill(struct sock *sk, } #undef EXPIRES_IN_MS - r->idiag_uid = sock_i_uid(sk); - r->idiag_inode = sock_i_ino(sk); + if (ext & (1 << (INET_DIAG_INFO - 1))) + info = INET_DIAG_PUT(skb, INET_DIAG_INFO, sizeof(struct tcp_info)); - if (minfo) { - minfo->idiag_rmem = sk_rmem_alloc_get(sk); - minfo->idiag_wmem = sk->sk_wmem_queued; - minfo->idiag_fmem = sk->sk_forward_alloc; - minfo->idiag_tmem = sk_wmem_alloc_get(sk); + if ((ext & (1 << (INET_DIAG_CONG - 1))) && icsk->icsk_ca_ops) { + const size_t len = strlen(icsk->icsk_ca_ops->name); + + strcpy(INET_DIAG_PUT(skb, INET_DIAG_CONG, len + 1), + icsk->icsk_ca_ops->name); } handler->idiag_get_info(sk, r, info); @@ -174,6 +181,7 @@ static int inet_csk_diag_fill(struct sock *sk, icsk->icsk_ca_ops && icsk->icsk_ca_ops->get_info) icsk->icsk_ca_ops->get_info(sk, ext, skb); +out: nlh->nlmsg_len = skb_tail_pointer(skb) - b; return skb->len; @@ -182,10 +190,20 @@ nlmsg_failure: nlmsg_trim(skb, b); return -EMSGSIZE; } +EXPORT_SYMBOL_GPL(inet_sk_diag_fill); + +static int inet_csk_diag_fill(struct sock *sk, + struct sk_buff *skb, struct inet_diag_req *req, + u32 pid, u32 seq, u16 nlmsg_flags, + const struct nlmsghdr *unlh) +{ + return inet_sk_diag_fill(sk, inet_csk(sk), + skb, req, pid, seq, nlmsg_flags, unlh); +} static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, - struct sk_buff *skb, int ext, u32 pid, - u32 seq, u16 nlmsg_flags, + struct sk_buff *skb, struct inet_diag_req *req, + u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { long tmo; @@ -206,8 +224,7 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_family = tw->tw_family; r->idiag_retrans = 0; r->id.idiag_if = tw->tw_bound_dev_if; - r->id.idiag_cookie[0] = (u32)(unsigned long)tw; - r->id.idiag_cookie[1] = (u32)(((unsigned long)tw >> 31) >> 1); + sock_diag_save_cookie(tw, r->id.idiag_cookie); r->id.idiag_sport = tw->tw_sport; r->id.idiag_dport = tw->tw_dport; r->id.idiag_src[0] = tw->tw_rcv_saddr; @@ -219,15 +236,13 @@ static int inet_twsk_diag_fill(struct inet_timewait_sock *tw, r->idiag_wqueue = 0; r->idiag_uid = 0; r->idiag_inode = 0; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { const struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &tw6->tw_v6_rcv_saddr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &tw6->tw_v6_daddr); + *(struct in6_addr *)r->id.idiag_src = tw6->tw_v6_rcv_saddr; + *(struct in6_addr *)r->id.idiag_dst = tw6->tw_v6_daddr; } #endif nlh->nlmsg_len = skb_tail_pointer(skb) - previous_tail; @@ -238,42 +253,31 @@ nlmsg_failure: } static int sk_diag_fill(struct sock *sk, struct sk_buff *skb, - int ext, u32 pid, u32 seq, u16 nlmsg_flags, + struct inet_diag_req *r, u32 pid, u32 seq, u16 nlmsg_flags, const struct nlmsghdr *unlh) { if (sk->sk_state == TCP_TIME_WAIT) return inet_twsk_diag_fill((struct inet_timewait_sock *)sk, - skb, ext, pid, seq, nlmsg_flags, + skb, r, pid, seq, nlmsg_flags, unlh); - return inet_csk_diag_fill(sk, skb, ext, pid, seq, nlmsg_flags, unlh); + return inet_csk_diag_fill(sk, skb, r, pid, seq, nlmsg_flags, unlh); } -static int inet_diag_get_exact(struct sk_buff *in_skb, - const struct nlmsghdr *nlh) +int inet_diag_dump_one_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *in_skb, + const struct nlmsghdr *nlh, struct inet_diag_req *req) { int err; struct sock *sk; - struct inet_diag_req *req = NLMSG_DATA(nlh); struct sk_buff *rep; - struct inet_hashinfo *hashinfo; - const struct inet_diag_handler *handler; - - handler = inet_diag_lock_handler(nlh->nlmsg_type); - if (IS_ERR(handler)) { - err = PTR_ERR(handler); - goto unlock; - } - hashinfo = handler->idiag_hashinfo; err = -EINVAL; - - if (req->idiag_family == AF_INET) { + if (req->sdiag_family == AF_INET) { sk = inet_lookup(&init_net, hashinfo, req->id.idiag_dst[0], req->id.idiag_dport, req->id.idiag_src[0], req->id.idiag_sport, req->id.idiag_if); } -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) - else if (req->idiag_family == AF_INET6) { +#if IS_ENABLED(CONFIG_IPV6) + else if (req->sdiag_family == AF_INET6) { sk = inet6_lookup(&init_net, hashinfo, (struct in6_addr *)req->id.idiag_dst, req->id.idiag_dport, @@ -283,29 +287,26 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, } #endif else { - goto unlock; + goto out_nosk; } err = -ENOENT; if (sk == NULL) - goto unlock; + goto out_nosk; - err = -ESTALE; - if ((req->id.idiag_cookie[0] != INET_DIAG_NOCOOKIE || - req->id.idiag_cookie[1] != INET_DIAG_NOCOOKIE) && - ((u32)(unsigned long)sk != req->id.idiag_cookie[0] || - (u32)((((unsigned long)sk) >> 31) >> 1) != req->id.idiag_cookie[1])) + err = sock_diag_check_cookie(sk, req->id.idiag_cookie); + if (err) goto out; err = -ENOMEM; rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) + sizeof(struct inet_diag_meminfo) + - handler->idiag_info_size + 64)), + sizeof(struct tcp_info) + 64)), GFP_KERNEL); if (!rep) goto out; - err = sk_diag_fill(sk, rep, req->idiag_ext, + err = sk_diag_fill(sk, rep, req, NETLINK_CB(in_skb).pid, nlh->nlmsg_seq, 0, nlh); if (err < 0) { @@ -313,7 +314,7 @@ static int inet_diag_get_exact(struct sk_buff *in_skb, kfree_skb(rep); goto out; } - err = netlink_unicast(idiagnl, rep, NETLINK_CB(in_skb).pid, + err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, MSG_DONTWAIT); if (err > 0) err = 0; @@ -325,8 +326,25 @@ out: else sock_put(sk); } -unlock: +out_nosk: + return err; +} +EXPORT_SYMBOL_GPL(inet_diag_dump_one_icsk); + +static int inet_diag_get_exact(struct sk_buff *in_skb, + const struct nlmsghdr *nlh, + struct inet_diag_req *req) +{ + const struct inet_diag_handler *handler; + int err; + + handler = inet_diag_lock_handler(req->sdiag_protocol); + if (IS_ERR(handler)) + err = PTR_ERR(handler); + else + err = handler->dump_one(in_skb, nlh, req); inet_diag_unlock_handler(handler); + return err; } @@ -357,9 +375,12 @@ static int bitstring_match(const __be32 *a1, const __be32 *a2, int bits) } -static int inet_diag_bc_run(const void *bc, int len, - const struct inet_diag_entry *entry) +static int inet_diag_bc_run(const struct nlattr *_bc, + const struct inet_diag_entry *entry) { + const void *bc = nla_data(_bc); + int len = nla_len(_bc); + while (len > 0) { int yes = 1; const struct inet_diag_bc_op *op = bc; @@ -433,6 +454,35 @@ static int inet_diag_bc_run(const void *bc, int len, return len == 0; } +int inet_diag_bc_sk(const struct nlattr *bc, struct sock *sk) +{ + struct inet_diag_entry entry; + struct inet_sock *inet = inet_sk(sk); + + if (bc == NULL) + return 1; + + entry.family = sk->sk_family; +#if IS_ENABLED(CONFIG_IPV6) + if (entry.family == AF_INET6) { + struct ipv6_pinfo *np = inet6_sk(sk); + + entry.saddr = np->rcv_saddr.s6_addr32; + entry.daddr = np->daddr.s6_addr32; + } else +#endif + { + entry.saddr = &inet->inet_rcv_saddr; + entry.daddr = &inet->inet_daddr; + } + entry.sport = inet->inet_num; + entry.dport = ntohs(inet->inet_dport); + entry.userlocks = sk->sk_userlocks; + + return inet_diag_bc_run(bc, &entry); +} +EXPORT_SYMBOL_GPL(inet_diag_bc_sk); + static int valid_cc(const void *bc, int len, int cc) { while (len >= 0) { @@ -489,57 +539,29 @@ static int inet_diag_bc_audit(const void *bytecode, int bytecode_len) static int inet_csk_diag_dump(struct sock *sk, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, + struct inet_diag_req *r, + const struct nlattr *bc) { - struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - - if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { - struct inet_diag_entry entry; - const struct nlattr *bc = nlmsg_find_attr(cb->nlh, - sizeof(*r), - INET_DIAG_REQ_BYTECODE); - struct inet_sock *inet = inet_sk(sk); - - entry.family = sk->sk_family; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) - if (entry.family == AF_INET6) { - struct ipv6_pinfo *np = inet6_sk(sk); - - entry.saddr = np->rcv_saddr.s6_addr32; - entry.daddr = np->daddr.s6_addr32; - } else -#endif - { - entry.saddr = &inet->inet_rcv_saddr; - entry.daddr = &inet->inet_daddr; - } - entry.sport = inet->inet_num; - entry.dport = ntohs(inet->inet_dport); - entry.userlocks = sk->sk_userlocks; + if (!inet_diag_bc_sk(bc, sk)) + return 0; - if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry)) - return 0; - } - - return inet_csk_diag_fill(sk, skb, r->idiag_ext, + return inet_csk_diag_fill(sk, skb, r, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, struct sk_buff *skb, - struct netlink_callback *cb) + struct netlink_callback *cb, + struct inet_diag_req *r, + const struct nlattr *bc) { - struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - - if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { + if (bc != NULL) { struct inet_diag_entry entry; - const struct nlattr *bc = nlmsg_find_attr(cb->nlh, - sizeof(*r), - INET_DIAG_REQ_BYTECODE); entry.family = tw->tw_family; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == AF_INET6) { struct inet6_timewait_sock *tw6 = inet6_twsk((struct sock *)tw); @@ -555,11 +577,11 @@ static int inet_twsk_diag_dump(struct inet_timewait_sock *tw, entry.dport = ntohs(tw->tw_dport); entry.userlocks = 0; - if (!inet_diag_bc_run(nla_data(bc), nla_len(bc), &entry)) + if (!inet_diag_bc_run(bc, &entry)) return 0; } - return inet_twsk_diag_fill(tw, skb, r->idiag_ext, + return inet_twsk_diag_fill(tw, skb, r, NETLINK_CB(cb->skb).pid, cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); } @@ -585,8 +607,7 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_retrans = req->retrans; r->id.idiag_if = sk->sk_bound_dev_if; - r->id.idiag_cookie[0] = (u32)(unsigned long)req; - r->id.idiag_cookie[1] = (u32)(((unsigned long)req >> 31) >> 1); + sock_diag_save_cookie(req, r->id.idiag_cookie); tmo = req->expires - jiffies; if (tmo < 0) @@ -601,12 +622,10 @@ static int inet_diag_fill_req(struct sk_buff *skb, struct sock *sk, r->idiag_wqueue = 0; r->idiag_uid = sock_i_uid(sk); r->idiag_inode = 0; -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (r->idiag_family == AF_INET6) { - ipv6_addr_copy((struct in6_addr *)r->id.idiag_src, - &inet6_rsk(req)->loc_addr); - ipv6_addr_copy((struct in6_addr *)r->id.idiag_dst, - &inet6_rsk(req)->rmt_addr); + *(struct in6_addr *)r->id.idiag_src = inet6_rsk(req)->loc_addr; + *(struct in6_addr *)r->id.idiag_dst = inet6_rsk(req)->rmt_addr; } #endif nlh->nlmsg_len = skb_tail_pointer(skb) - b; @@ -619,13 +638,13 @@ nlmsg_failure: } static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, - struct netlink_callback *cb) + struct netlink_callback *cb, + struct inet_diag_req *r, + const struct nlattr *bc) { struct inet_diag_entry entry; - struct inet_diag_req *r = NLMSG_DATA(cb->nlh); struct inet_connection_sock *icsk = inet_csk(sk); struct listen_sock *lopt; - const struct nlattr *bc = NULL; struct inet_sock *inet = inet_sk(sk); int j, s_j; int reqnum, s_reqnum; @@ -645,9 +664,7 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (!lopt || !lopt->qlen) goto out; - if (nlmsg_attrlen(cb->nlh, sizeof(*r))) { - bc = nlmsg_find_attr(cb->nlh, sizeof(*r), - INET_DIAG_REQ_BYTECODE); + if (bc != NULL) { entry.sport = inet->inet_num; entry.userlocks = sk->sk_userlocks; } @@ -667,21 +684,20 @@ static int inet_diag_dump_reqs(struct sk_buff *skb, struct sock *sk, if (bc) { entry.saddr = -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) (entry.family == AF_INET6) ? inet6_rsk(req)->loc_addr.s6_addr32 : #endif &ireq->loc_addr; entry.daddr = -#if defined(CONFIG_IPV6) || defined (CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) (entry.family == AF_INET6) ? inet6_rsk(req)->rmt_addr.s6_addr32 : #endif &ireq->rmt_addr; entry.dport = ntohs(ireq->rmt_port); - if (!inet_diag_bc_run(nla_data(bc), - nla_len(bc), &entry)) + if (!inet_diag_bc_run(bc, &entry)) continue; } @@ -704,19 +720,11 @@ out: return err; } -static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +void inet_diag_dump_icsk(struct inet_hashinfo *hashinfo, struct sk_buff *skb, + struct netlink_callback *cb, struct inet_diag_req *r, struct nlattr *bc) { int i, num; int s_i, s_num; - struct inet_diag_req *r = NLMSG_DATA(cb->nlh); - const struct inet_diag_handler *handler; - struct inet_hashinfo *hashinfo; - - handler = inet_diag_lock_handler(cb->nlh->nlmsg_type); - if (IS_ERR(handler)) - goto unlock; - - hashinfo = handler->idiag_hashinfo; s_i = cb->args[1]; s_num = num = cb->args[2]; @@ -741,6 +749,10 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) continue; } + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next_listen; + if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_listen; @@ -750,7 +762,7 @@ static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) cb->args[3] > 0) goto syn_recv; - if (inet_csk_diag_dump(sk, skb, cb) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -759,7 +771,7 @@ syn_recv: if (!(r->idiag_states & TCPF_SYN_RECV)) goto next_listen; - if (inet_diag_dump_reqs(skb, sk, cb) < 0) { + if (inet_diag_dump_reqs(skb, sk, cb, r, bc) < 0) { spin_unlock_bh(&ilb->lock); goto done; } @@ -781,7 +793,7 @@ skip_listen_ht: } if (!(r->idiag_states & ~(TCPF_LISTEN | TCPF_SYN_RECV))) - goto unlock; + goto out; for (i = s_i; i <= hashinfo->ehash_mask; i++) { struct inet_ehash_bucket *head = &hashinfo->ehash[i]; @@ -806,13 +818,16 @@ skip_listen_ht: goto next_normal; if (!(r->idiag_states & (1 << sk->sk_state))) goto next_normal; + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next_normal; if (r->id.idiag_sport != inet->inet_sport && r->id.idiag_sport) goto next_normal; if (r->id.idiag_dport != inet->inet_dport && r->id.idiag_dport) goto next_normal; - if (inet_csk_diag_dump(sk, skb, cb) < 0) { + if (inet_csk_diag_dump(sk, skb, cb, r, bc) < 0) { spin_unlock_bh(lock); goto done; } @@ -828,13 +843,16 @@ next_normal: if (num < s_num) goto next_dying; + if (r->sdiag_family != AF_UNSPEC && + tw->tw_family != r->sdiag_family) + goto next_dying; if (r->id.idiag_sport != tw->tw_sport && r->id.idiag_sport) goto next_dying; if (r->id.idiag_dport != tw->tw_dport && r->id.idiag_dport) goto next_dying; - if (inet_twsk_diag_dump(tw, skb, cb) < 0) { + if (inet_twsk_diag_dump(tw, skb, cb, r, bc) < 0) { spin_unlock_bh(lock); goto done; } @@ -848,15 +866,85 @@ next_dying: done: cb->args[1] = i; cb->args[2] = num; -unlock: +out: + ; +} +EXPORT_SYMBOL_GPL(inet_diag_dump_icsk); + +static int __inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct inet_diag_req *r, struct nlattr *bc) +{ + const struct inet_diag_handler *handler; + + handler = inet_diag_lock_handler(r->sdiag_protocol); + if (!IS_ERR(handler)) + handler->dump(skb, cb, r, bc); inet_diag_unlock_handler(handler); + return skb->len; } -static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) +static int inet_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) { + struct nlattr *bc = NULL; int hdrlen = sizeof(struct inet_diag_req); + if (nlmsg_attrlen(cb->nlh, hdrlen)) + bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); + + return __inet_diag_dump(skb, cb, (struct inet_diag_req *)NLMSG_DATA(cb->nlh), bc); +} + +static inline int inet_diag_type2proto(int type) +{ + switch (type) { + case TCPDIAG_GETSOCK: + return IPPROTO_TCP; + case DCCPDIAG_GETSOCK: + return IPPROTO_DCCP; + default: + return 0; + } +} + +static int inet_diag_dump_compat(struct sk_buff *skb, struct netlink_callback *cb) +{ + struct inet_diag_req_compat *rc = NLMSG_DATA(cb->nlh); + struct inet_diag_req req; + struct nlattr *bc = NULL; + int hdrlen = sizeof(struct inet_diag_req_compat); + + req.sdiag_family = AF_UNSPEC; /* compatibility */ + req.sdiag_protocol = inet_diag_type2proto(cb->nlh->nlmsg_type); + req.idiag_ext = rc->idiag_ext; + req.idiag_states = rc->idiag_states; + req.id = rc->id; + + if (nlmsg_attrlen(cb->nlh, hdrlen)) + bc = nlmsg_find_attr(cb->nlh, hdrlen, INET_DIAG_REQ_BYTECODE); + + return __inet_diag_dump(skb, cb, &req, bc); +} + +static int inet_diag_get_exact_compat(struct sk_buff *in_skb, + const struct nlmsghdr *nlh) +{ + struct inet_diag_req_compat *rc = NLMSG_DATA(nlh); + struct inet_diag_req req; + + req.sdiag_family = rc->idiag_family; + req.sdiag_protocol = inet_diag_type2proto(nlh->nlmsg_type); + req.idiag_ext = rc->idiag_ext; + req.idiag_states = rc->idiag_states; + req.id = rc->id; + + return inet_diag_get_exact(in_skb, nlh, &req); +} + +static int inet_diag_rcv_msg_compat(struct sk_buff *skb, struct nlmsghdr *nlh) +{ + int hdrlen = sizeof(struct inet_diag_req_compat); + if (nlh->nlmsg_type >= INET_DIAG_GETSOCK_MAX || nlmsg_len(nlh) < hdrlen) return -EINVAL; @@ -873,28 +961,54 @@ static int inet_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh) return -EINVAL; } - return netlink_dump_start(idiagnl, skb, nlh, - inet_diag_dump, NULL, 0); + return netlink_dump_start(sock_diag_nlsk, skb, nlh, + inet_diag_dump_compat, NULL, 0); } - return inet_diag_get_exact(skb, nlh); + return inet_diag_get_exact_compat(skb, nlh); } -static DEFINE_MUTEX(inet_diag_mutex); - -static void inet_diag_rcv(struct sk_buff *skb) +static int inet_diag_handler_dump(struct sk_buff *skb, struct nlmsghdr *h) { - mutex_lock(&inet_diag_mutex); - netlink_rcv_skb(skb, &inet_diag_rcv_msg); - mutex_unlock(&inet_diag_mutex); + int hdrlen = sizeof(struct inet_diag_req); + + if (nlmsg_len(h) < hdrlen) + return -EINVAL; + + if (h->nlmsg_flags & NLM_F_DUMP) { + if (nlmsg_attrlen(h, hdrlen)) { + struct nlattr *attr; + attr = nlmsg_find_attr(h, hdrlen, + INET_DIAG_REQ_BYTECODE); + if (attr == NULL || + nla_len(attr) < sizeof(struct inet_diag_bc_op) || + inet_diag_bc_audit(nla_data(attr), nla_len(attr))) + return -EINVAL; + } + + return netlink_dump_start(sock_diag_nlsk, skb, h, + inet_diag_dump, NULL, 0); + } + + return inet_diag_get_exact(skb, h, (struct inet_diag_req *)NLMSG_DATA(h)); } +static struct sock_diag_handler inet_diag_handler = { + .family = AF_INET, + .dump = inet_diag_handler_dump, +}; + +static struct sock_diag_handler inet6_diag_handler = { + .family = AF_INET6, + .dump = inet_diag_handler_dump, +}; + int inet_diag_register(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; int err = -EINVAL; - if (type >= INET_DIAG_GETSOCK_MAX) + if (type >= IPPROTO_MAX) goto out; mutex_lock(&inet_diag_table_mutex); @@ -913,7 +1027,7 @@ void inet_diag_unregister(const struct inet_diag_handler *h) { const __u16 type = h->idiag_type; - if (type >= INET_DIAG_GETSOCK_MAX) + if (type >= IPPROTO_MAX) return; mutex_lock(&inet_diag_table_mutex); @@ -924,7 +1038,7 @@ EXPORT_SYMBOL_GPL(inet_diag_unregister); static int __init inet_diag_init(void) { - const int inet_diag_table_size = (INET_DIAG_GETSOCK_MAX * + const int inet_diag_table_size = (IPPROTO_MAX * sizeof(struct inet_diag_handler *)); int err = -ENOMEM; @@ -932,25 +1046,35 @@ static int __init inet_diag_init(void) if (!inet_diag_table) goto out; - idiagnl = netlink_kernel_create(&init_net, NETLINK_INET_DIAG, 0, - inet_diag_rcv, NULL, THIS_MODULE); - if (idiagnl == NULL) - goto out_free_table; - err = 0; + err = sock_diag_register(&inet_diag_handler); + if (err) + goto out_free_nl; + + err = sock_diag_register(&inet6_diag_handler); + if (err) + goto out_free_inet; + + sock_diag_register_inet_compat(inet_diag_rcv_msg_compat); out: return err; -out_free_table: + +out_free_inet: + sock_diag_unregister(&inet_diag_handler); +out_free_nl: kfree(inet_diag_table); goto out; } static void __exit inet_diag_exit(void) { - netlink_kernel_release(idiagnl); + sock_diag_unregister(&inet6_diag_handler); + sock_diag_unregister(&inet_diag_handler); + sock_diag_unregister_inet_compat(inet_diag_rcv_msg_compat); kfree(inet_diag_table); } module_init(inet_diag_init); module_exit(inet_diag_exit); MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_INET_DIAG); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2 /* AF_INET */); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 10 /* AF_INET6 */); diff --git a/net/ipv4/ip_forward.c b/net/ipv4/ip_forward.c index 3b34d1c8627..29a07b6c716 100644 --- a/net/ipv4/ip_forward.c +++ b/net/ipv4/ip_forward.c @@ -84,7 +84,7 @@ int ip_forward(struct sk_buff *skb) rt = skb_rtable(skb); - if (opt->is_strictroute && ip_hdr(skb)->daddr != rt->rt_gateway) + if (opt->is_strictroute && opt->nexthop != rt->rt_gateway) goto sr_failed; if (unlikely(skb->len > dst_mtu(&rt->dst) && !skb_is_gso(skb) && diff --git a/net/ipv4/ip_fragment.c b/net/ipv4/ip_fragment.c index fdaabf2f2b6..1f23a57aa9e 100644 --- a/net/ipv4/ip_fragment.c +++ b/net/ipv4/ip_fragment.c @@ -392,7 +392,7 @@ static int ip_frag_queue(struct ipq *qp, struct sk_buff *skb) /* Is this the final fragment? */ if ((flags & IP_MF) == 0) { /* If we already have some bits beyond end - * or have different end, the segment is corrrupted. + * or have different end, the segment is corrupted. */ if (end < qp->q.len || ((qp->q.last_in & INET_FRAG_LAST_IN) && end != qp->q.len)) diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index d55110e9312..2b53a1f7abf 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -46,7 +46,7 @@ #include <net/rtnetlink.h> #include <net/gre.h> -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <net/ipv6.h> #include <net/ip6_fib.h> #include <net/ip6_route.h> @@ -171,7 +171,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipgre_get_stats(struct net_device *dev) { @@ -729,9 +729,9 @@ 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; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { - struct neighbour *neigh = dst_get_neighbour(skb_dst(skb)); + struct neighbour *neigh = dst_get_neighbour_noref(skb_dst(skb)); const struct in6_addr *addr6; int addr_type; @@ -799,7 +799,7 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev goto tx_error; } } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) { struct rt6_info *rt6 = (struct rt6_info *)skb_dst(skb); @@ -835,6 +835,8 @@ static netdev_tx_t ipgre_tunnel_xmit(struct sk_buff *skb, struct net_device *dev if (skb_headroom(skb) < max_headroom || skb_shared(skb)|| (skb_cloned(skb) && !skb_clone_writable(skb, 0))) { struct sk_buff *new_skb = skb_realloc_headroom(skb, max_headroom); + if (max_headroom > dev->needed_headroom) + dev->needed_headroom = max_headroom; if (!new_skb) { ip_rt_put(rt); dev->stats.tx_dropped++; @@ -873,7 +875,7 @@ 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; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) else if (skb->protocol == htons(ETH_P_IPV6)) iph->ttl = ((const struct ipv6hdr *)old_iph)->hop_limit; #endif diff --git a/net/ipv4/ip_options.c b/net/ipv4/ip_options.c index ec93335901d..1e60f767907 100644 --- a/net/ipv4/ip_options.c +++ b/net/ipv4/ip_options.c @@ -568,12 +568,13 @@ void ip_forward_options(struct sk_buff *skb) ) { if (srrptr + 3 > srrspace) break; - if (memcmp(&ip_hdr(skb)->daddr, &optptr[srrptr-1], 4) == 0) + if (memcmp(&opt->nexthop, &optptr[srrptr-1], 4) == 0) break; } if (srrptr + 3 <= srrspace) { opt->is_changed = 1; ip_rt_get_source(&optptr[srrptr-1], skb, rt); + ip_hdr(skb)->daddr = opt->nexthop; optptr[2] = srrptr+4; } else if (net_ratelimit()) printk(KERN_CRIT "ip_forward(): Argh! Destination lost!\n"); @@ -640,6 +641,7 @@ int ip_options_rcv_srr(struct sk_buff *skb) } if (srrptr <= srrspace) { opt->srr_is_hit = 1; + opt->nexthop = nexthop; opt->is_changed = 1; } return 0; diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 0bc95f3977d..ff302bde889 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -206,7 +206,7 @@ static inline int ip_finish_output2(struct sk_buff *skb) } rcu_read_lock(); - neigh = dst_get_neighbour(dst); + neigh = dst_get_neighbour_noref(dst); if (neigh) { int res = neigh_output(neigh, skb); @@ -319,6 +319,20 @@ int ip_output(struct sk_buff *skb) !(IPCB(skb)->flags & IPSKB_REROUTED)); } +/* + * copy saddr and daddr, possibly using 64bit load/stores + * Equivalent to : + * iph->saddr = fl4->saddr; + * iph->daddr = fl4->daddr; + */ +static void ip_copy_addrs(struct iphdr *iph, const struct flowi4 *fl4) +{ + BUILD_BUG_ON(offsetof(typeof(*fl4), daddr) != + offsetof(typeof(*fl4), saddr) + sizeof(fl4->saddr)); + memcpy(&iph->saddr, &fl4->saddr, + sizeof(fl4->saddr) + sizeof(fl4->daddr)); +} + int ip_queue_xmit(struct sk_buff *skb, struct flowi *fl) { struct sock *sk = skb->sk; @@ -381,8 +395,8 @@ packet_routed: iph->frag_off = 0; iph->ttl = ip_select_ttl(inet, &rt->dst); iph->protocol = sk->sk_protocol; - iph->saddr = fl4->saddr; - iph->daddr = fl4->daddr; + ip_copy_addrs(iph, fl4); + /* Transport layer set skb->h.foo itself. */ if (inet_opt && inet_opt->opt.optlen) { @@ -1337,8 +1351,7 @@ struct sk_buff *__ip_make_skb(struct sock *sk, ip_select_ident(iph, &rt->dst, sk); iph->ttl = ttl; iph->protocol = sk->sk_protocol; - iph->saddr = fl4->saddr; - iph->daddr = fl4->daddr; + ip_copy_addrs(iph, fl4); if (opt) { iph->ihl += opt->optlen>>2; diff --git a/net/ipv4/ip_sockglue.c b/net/ipv4/ip_sockglue.c index 09ff51bf16a..8aa87c19fa0 100644 --- a/net/ipv4/ip_sockglue.c +++ b/net/ipv4/ip_sockglue.c @@ -37,7 +37,7 @@ #include <net/route.h> #include <net/xfrm.h> #include <net/compat.h> -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) #include <net/transp_v6.h> #endif @@ -55,20 +55,13 @@ /* * SOL_IP control messages. */ +#define PKTINFO_SKB_CB(__skb) ((struct in_pktinfo *)((__skb)->cb)) static void ip_cmsg_recv_pktinfo(struct msghdr *msg, struct sk_buff *skb) { - struct in_pktinfo info; - struct rtable *rt = skb_rtable(skb); + struct in_pktinfo info = *PKTINFO_SKB_CB(skb); info.ipi_addr.s_addr = ip_hdr(skb)->daddr; - if (rt) { - info.ipi_ifindex = rt->rt_iif; - info.ipi_spec_dst.s_addr = rt->rt_spec_dst; - } else { - info.ipi_ifindex = 0; - info.ipi_spec_dst.s_addr = 0; - } put_cmsg(msg, SOL_IP, IP_PKTINFO, sizeof(info), &info); } @@ -515,7 +508,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, sock_owned_by_user(sk)); if (inet->is_icsk) { struct inet_connection_sock *icsk = inet_csk(sk); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (sk->sk_family == PF_INET || (!((1 << sk->sk_state) & (TCPF_LISTEN | TCPF_CLOSE)) && @@ -526,7 +519,7 @@ static int do_ip_setsockopt(struct sock *sk, int level, if (opt) icsk->icsk_ext_hdr_len += opt->opt.optlen; icsk->icsk_sync_mss(sk, icsk->icsk_pmtu_cookie); -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) } #endif } @@ -992,20 +985,28 @@ e_inval: } /** - * ip_queue_rcv_skb - Queue an skb into sock receive queue + * ipv4_pktinfo_prepare - transfert some info from rtable to skb * @sk: socket * @skb: buffer * - * Queues an skb into socket receive queue. If IP_CMSG_PKTINFO option - * is not set, we drop skb dst entry now, while dst cache line is hot. + * To support IP_CMSG_PKTINFO option, we store rt_iif and rt_spec_dst + * in skb->cb[] before dst drop. + * This way, receiver doesnt make cache line misses to read rtable. */ -int ip_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +void ipv4_pktinfo_prepare(struct sk_buff *skb) { - if (!(inet_sk(sk)->cmsg_flags & IP_CMSG_PKTINFO)) - skb_dst_drop(skb); - return sock_queue_rcv_skb(sk, skb); + struct in_pktinfo *pktinfo = PKTINFO_SKB_CB(skb); + const struct rtable *rt = skb_rtable(skb); + + if (rt) { + pktinfo->ipi_ifindex = rt->rt_iif; + pktinfo->ipi_spec_dst.s_addr = rt->rt_spec_dst; + } else { + pktinfo->ipi_ifindex = 0; + pktinfo->ipi_spec_dst.s_addr = 0; + } + skb_dst_drop(skb); } -EXPORT_SYMBOL(ip_queue_rcv_skb); int ip_setsockopt(struct sock *sk, int level, int optname, char __user *optval, unsigned int optlen) diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 0da2afc97f3..7e4ec9fc2ce 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -253,6 +253,10 @@ static int __init ic_open_devs(void) } } + /* no point in waiting if we could not bring up at least one device */ + if (!ic_first_dev) + goto have_carrier; + /* wait for a carrier on at least one device */ start = jiffies; while (jiffies - start < msecs_to_jiffies(CONF_CARRIER_TIMEOUT)) { @@ -763,13 +767,15 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d struct sk_buff *skb; struct bootp_pkt *b; struct iphdr *h; + int hlen = LL_RESERVED_SPACE(dev); + int tlen = dev->needed_tailroom; /* Allocate packet */ - skb = alloc_skb(sizeof(struct bootp_pkt) + LL_ALLOCATED_SPACE(dev) + 15, + skb = alloc_skb(sizeof(struct bootp_pkt) + hlen + tlen + 15, GFP_KERNEL); if (!skb) return; - skb_reserve(skb, LL_RESERVED_SPACE(dev)); + skb_reserve(skb, hlen); b = (struct bootp_pkt *) skb_put(skb, sizeof(struct bootp_pkt)); memset(b, 0, sizeof(struct bootp_pkt)); @@ -822,8 +828,13 @@ static void __init ic_bootp_send_if(struct ic_device *d, unsigned long jiffies_d skb->dev = dev; skb->protocol = htons(ETH_P_IP); if (dev_hard_header(skb, dev, ntohs(skb->protocol), - dev->broadcast, dev->dev_addr, skb->len) < 0 || - dev_queue_xmit(skb) < 0) + dev->broadcast, dev->dev_addr, skb->len) < 0) { + kfree_skb(skb); + printk("E"); + return; + } + + if (dev_queue_xmit(skb) < 0) printk("E"); } diff --git a/net/ipv4/ipip.c b/net/ipv4/ipip.c index 065effd8349..413ed1ba7a5 100644 --- a/net/ipv4/ipip.c +++ b/net/ipv4/ipip.c @@ -148,7 +148,7 @@ struct pcpu_tstats { unsigned long rx_bytes; unsigned long tx_packets; unsigned long tx_bytes; -}; +} __attribute__((aligned(4*sizeof(unsigned long)))); static struct net_device_stats *ipip_get_stats(struct net_device *dev) { @@ -285,6 +285,8 @@ static struct ip_tunnel * ipip_tunnel_locate(struct net *net, if (register_netdevice(dev) < 0) goto failed_free; + strcpy(nt->parms.name, dev->name); + dev_hold(dev); ipip_tunnel_link(ipn, nt); return nt; @@ -759,7 +761,6 @@ static int ipip_tunnel_init(struct net_device *dev) struct ip_tunnel *tunnel = netdev_priv(dev); tunnel->dev = dev; - strcpy(tunnel->parms.name, dev->name); memcpy(dev->dev_addr, &tunnel->parms.iph.saddr, 4); memcpy(dev->broadcast, &tunnel->parms.iph.daddr, 4); @@ -825,6 +826,7 @@ static void ipip_destroy_tunnels(struct ipip_net *ipn, struct list_head *head) static int __net_init ipip_init_net(struct net *net) { struct ipip_net *ipn = net_generic(net, ipip_net_id); + struct ip_tunnel *t; int err; ipn->tunnels[0] = ipn->tunnels_wc; @@ -848,6 +850,9 @@ static int __net_init ipip_init_net(struct net *net) if ((err = register_netdev(ipn->fb_tunnel_dev))) goto err_reg_dev; + t = netdev_priv(ipn->fb_tunnel_dev); + + strcpy(t->parms.name, ipn->fb_tunnel_dev->name); return 0; err_reg_dev: diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 76a7f07b38b..8e54490ee3f 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -1520,7 +1520,6 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v struct mr_table *mrt; struct vif_device *v; int ct; - LIST_HEAD(list); if (event != NETDEV_UNREGISTER) return NOTIFY_DONE; @@ -1529,10 +1528,9 @@ static int ipmr_device_event(struct notifier_block *this, unsigned long event, v v = &mrt->vif_table[0]; for (ct = 0; ct < mrt->maxvif; ct++, v++) { if (v->dev == dev) - vif_delete(mrt, ct, 1, &list); + vif_delete(mrt, ct, 1, NULL); } } - unregister_netdevice_many(&list); return NOTIFY_DONE; } diff --git a/net/ipv4/netfilter.c b/net/ipv4/netfilter.c index 9899619ab9b..4f47e064e26 100644 --- a/net/ipv4/netfilter.c +++ b/net/ipv4/netfilter.c @@ -64,7 +64,8 @@ int ip_route_me_harder(struct sk_buff *skb, unsigned addr_type) /* Change in oif may mean change in hh_len. */ hh_len = skb_dst(skb)->dev->hard_header_len; if (skb_headroom(skb) < hh_len && - pskb_expand_head(skb, hh_len - skb_headroom(skb), 0, GFP_ATOMIC)) + pskb_expand_head(skb, HH_DATA_ALIGN(hh_len - skb_headroom(skb)), + 0, GFP_ATOMIC)) return -1; return 0; diff --git a/net/ipv4/netfilter/Kconfig b/net/ipv4/netfilter/Kconfig index 1dfc18a03fd..74dfc9e5211 100644 --- a/net/ipv4/netfilter/Kconfig +++ b/net/ipv4/netfilter/Kconfig @@ -27,7 +27,7 @@ config NF_CONNTRACK_IPV4 config NF_CONNTRACK_PROC_COMPAT bool "proc/sysctl compatibility with old connection tracking" - depends on NF_CONNTRACK_IPV4 + depends on NF_CONNTRACK_PROCFS && NF_CONNTRACK_IPV4 default y help This option enables /proc and sysctl compatibility with the old @@ -76,11 +76,21 @@ config IP_NF_MATCH_AH config IP_NF_MATCH_ECN tristate '"ecn" match support' depends on NETFILTER_ADVANCED - help - This option adds a `ECN' match, which allows you to match against - the IPv4 and TCP header ECN fields. + select NETFILTER_XT_MATCH_ECN + ---help--- + This is a backwards-compat option for the user's convenience + (e.g. when running oldconfig). It selects + CONFIG_NETFILTER_XT_MATCH_ECN. + +config IP_NF_MATCH_RPFILTER + tristate '"rpfilter" reverse path filter match support' + depends on NETFILTER_ADVANCED + ---help--- + This option allows you to match packets whose replies would + go out via the interface the packet came in. To compile it as a module, choose M here. If unsure, say N. + The module will be called ipt_rpfilter. config IP_NF_MATCH_TTL tristate '"ttl" match support' @@ -325,7 +335,6 @@ config IP_NF_TARGET_TTL # raw + specific targets config IP_NF_RAW tristate 'raw table support (required for NOTRACK/TRACE)' - depends on NETFILTER_ADVANCED help This option adds a `raw' table to iptables. This table is the very first in the netfilter framework and hooks in at the PREROUTING diff --git a/net/ipv4/netfilter/Makefile b/net/ipv4/netfilter/Makefile index dca2082ec68..213a462b739 100644 --- a/net/ipv4/netfilter/Makefile +++ b/net/ipv4/netfilter/Makefile @@ -49,7 +49,7 @@ obj-$(CONFIG_IP_NF_SECURITY) += iptable_security.o # matches obj-$(CONFIG_IP_NF_MATCH_AH) += ipt_ah.o -obj-$(CONFIG_IP_NF_MATCH_ECN) += ipt_ecn.o +obj-$(CONFIG_IP_NF_MATCH_RPFILTER) += ipt_rpfilter.o # targets obj-$(CONFIG_IP_NF_TARGET_CLUSTERIP) += ipt_CLUSTERIP.o diff --git a/net/ipv4/netfilter/ip_queue.c b/net/ipv4/netfilter/ip_queue.c index e59aabd0eae..a057fe64deb 100644 --- a/net/ipv4/netfilter/ip_queue.c +++ b/net/ipv4/netfilter/ip_queue.c @@ -404,6 +404,7 @@ __ipq_rcv_skb(struct sk_buff *skb) int status, type, pid, flags; unsigned int nlmsglen, skblen; struct nlmsghdr *nlh; + bool enable_timestamp = false; skblen = skb->len; if (skblen < sizeof(*nlh)) @@ -441,12 +442,13 @@ __ipq_rcv_skb(struct sk_buff *skb) RCV_SKB_FAIL(-EBUSY); } } else { - net_enable_timestamp(); + enable_timestamp = true; peer_pid = pid; } spin_unlock_bh(&queue_lock); - + if (enable_timestamp) + net_enable_timestamp(); status = ipq_receive_peer(NLMSG_DATA(nlh), type, nlmsglen - NLMSG_LENGTH(0)); if (status < 0) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index 9931152a78b..2f210c79dc8 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -30,9 +30,9 @@ MODULE_DESCRIPTION("Xtables: automatic-address SNAT"); /* FIXME: Multiple targets. --RR */ static int masquerade_tg_check(const struct xt_tgchk_param *par) { - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { + if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) { pr_debug("bad MAP_IPS.\n"); return -EINVAL; } @@ -49,8 +49,8 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; - struct nf_nat_range newrange; - const struct nf_nat_multi_range_compat *mr; + struct nf_nat_ipv4_range newrange; + const struct nf_nat_ipv4_multi_range_compat *mr; const struct rtable *rt; __be32 newsrc; @@ -79,13 +79,13 @@ masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) nat->masq_index = par->out->ifindex; /* Transfer from original range. */ - newrange = ((struct nf_nat_range) - { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS, + newrange = ((struct nf_nat_ipv4_range) + { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS, newsrc, newsrc, mr->range[0].min, mr->range[0].max }); /* Hand modified range to generic setup. */ - return nf_nat_setup_info(ct, &newrange, IP_NAT_MANIP_SRC); + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_SRC); } static int @@ -139,7 +139,7 @@ static struct xt_target masquerade_tg_reg __read_mostly = { .name = "MASQUERADE", .family = NFPROTO_IPV4, .target = masquerade_tg, - .targetsize = sizeof(struct nf_nat_multi_range_compat), + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = 1 << NF_INET_POST_ROUTING, .checkentry = masquerade_tg_check, diff --git a/net/ipv4/netfilter/ipt_NETMAP.c b/net/ipv4/netfilter/ipt_NETMAP.c index 6cdb298f103..b5bfbbabf70 100644 --- a/net/ipv4/netfilter/ipt_NETMAP.c +++ b/net/ipv4/netfilter/ipt_NETMAP.c @@ -24,9 +24,9 @@ MODULE_DESCRIPTION("Xtables: 1:1 NAT mapping of IPv4 subnets"); static int netmap_tg_check(const struct xt_tgchk_param *par) { - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - if (!(mr->range[0].flags & IP_NAT_RANGE_MAP_IPS)) { + if (!(mr->range[0].flags & NF_NAT_RANGE_MAP_IPS)) { pr_debug("bad MAP_IPS.\n"); return -EINVAL; } @@ -43,8 +43,8 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be32 new_ip, netmask; - const struct nf_nat_multi_range_compat *mr = par->targinfo; - struct nf_nat_range newrange; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_ipv4_range newrange; NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || par->hooknum == NF_INET_POST_ROUTING || @@ -61,8 +61,8 @@ netmap_tg(struct sk_buff *skb, const struct xt_action_param *par) new_ip = ip_hdr(skb)->saddr & ~netmask; new_ip |= mr->range[0].min_ip & netmask; - newrange = ((struct nf_nat_range) - { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS, + newrange = ((struct nf_nat_ipv4_range) + { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS, new_ip, new_ip, mr->range[0].min, mr->range[0].max }); @@ -74,7 +74,7 @@ static struct xt_target netmap_tg_reg __read_mostly = { .name = "NETMAP", .family = NFPROTO_IPV4, .target = netmap_tg, - .targetsize = sizeof(struct nf_nat_multi_range_compat), + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_POST_ROUTING) | diff --git a/net/ipv4/netfilter/ipt_REDIRECT.c b/net/ipv4/netfilter/ipt_REDIRECT.c index 18a0656505a..7c0103a5203 100644 --- a/net/ipv4/netfilter/ipt_REDIRECT.c +++ b/net/ipv4/netfilter/ipt_REDIRECT.c @@ -28,9 +28,9 @@ MODULE_DESCRIPTION("Xtables: Connection redirection to localhost"); /* FIXME: Take multiple ranges --RR */ static int redirect_tg_check(const struct xt_tgchk_param *par) { - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - if (mr->range[0].flags & IP_NAT_RANGE_MAP_IPS) { + if (mr->range[0].flags & NF_NAT_RANGE_MAP_IPS) { pr_debug("bad MAP_IPS.\n"); return -EINVAL; } @@ -47,8 +47,8 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be32 newdst; - const struct nf_nat_multi_range_compat *mr = par->targinfo; - struct nf_nat_range newrange; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; + struct nf_nat_ipv4_range newrange; NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || par->hooknum == NF_INET_LOCAL_OUT); @@ -76,20 +76,20 @@ redirect_tg(struct sk_buff *skb, const struct xt_action_param *par) } /* Transfer from original range. */ - newrange = ((struct nf_nat_range) - { mr->range[0].flags | IP_NAT_RANGE_MAP_IPS, + newrange = ((struct nf_nat_ipv4_range) + { mr->range[0].flags | NF_NAT_RANGE_MAP_IPS, newdst, newdst, mr->range[0].min, mr->range[0].max }); /* Hand modified range to generic setup. */ - return nf_nat_setup_info(ct, &newrange, IP_NAT_MANIP_DST); + return nf_nat_setup_info(ct, &newrange, NF_NAT_MANIP_DST); } static struct xt_target redirect_tg_reg __read_mostly = { .name = "REDIRECT", .family = NFPROTO_IPV4, .target = redirect_tg, - .targetsize = sizeof(struct nf_nat_multi_range_compat), + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT), .checkentry = redirect_tg_check, diff --git a/net/ipv4/netfilter/ipt_ULOG.c b/net/ipv4/netfilter/ipt_ULOG.c index b5508151e54..ba5756d2016 100644 --- a/net/ipv4/netfilter/ipt_ULOG.c +++ b/net/ipv4/netfilter/ipt_ULOG.c @@ -65,7 +65,7 @@ static unsigned int flushtimeout = 10; module_param(flushtimeout, uint, 0600); MODULE_PARM_DESC(flushtimeout, "buffer flush timeout (hundredths of a second)"); -static int nflog = 1; +static bool nflog = true; module_param(nflog, bool, 0400); MODULE_PARM_DESC(nflog, "register as internal netfilter logging module"); diff --git a/net/ipv4/netfilter/ipt_ecn.c b/net/ipv4/netfilter/ipt_ecn.c deleted file mode 100644 index 2b57e52c746..00000000000 --- a/net/ipv4/netfilter/ipt_ecn.c +++ /dev/null @@ -1,127 +0,0 @@ -/* IP tables module for matching the value of the IPv4 and TCP ECN bits - * - * (C) 2002 by Harald Welte <laforge@gnumonks.org> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - */ -#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt -#include <linux/in.h> -#include <linux/ip.h> -#include <net/ip.h> -#include <linux/module.h> -#include <linux/skbuff.h> -#include <linux/tcp.h> - -#include <linux/netfilter/x_tables.h> -#include <linux/netfilter_ipv4/ip_tables.h> -#include <linux/netfilter_ipv4/ipt_ecn.h> - -MODULE_AUTHOR("Harald Welte <laforge@netfilter.org>"); -MODULE_DESCRIPTION("Xtables: Explicit Congestion Notification (ECN) flag match for IPv4"); -MODULE_LICENSE("GPL"); - -static inline bool match_ip(const struct sk_buff *skb, - const struct ipt_ecn_info *einfo) -{ - return ((ip_hdr(skb)->tos & IPT_ECN_IP_MASK) == einfo->ip_ect) ^ - !!(einfo->invert & IPT_ECN_OP_MATCH_IP); -} - -static inline bool match_tcp(const struct sk_buff *skb, - const struct ipt_ecn_info *einfo, - bool *hotdrop) -{ - struct tcphdr _tcph; - const struct tcphdr *th; - - /* In practice, TCP match does this, so can't fail. But let's - * be good citizens. - */ - th = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(_tcph), &_tcph); - if (th == NULL) { - *hotdrop = false; - return false; - } - - if (einfo->operation & IPT_ECN_OP_MATCH_ECE) { - if (einfo->invert & IPT_ECN_OP_MATCH_ECE) { - if (th->ece == 1) - return false; - } else { - if (th->ece == 0) - return false; - } - } - - if (einfo->operation & IPT_ECN_OP_MATCH_CWR) { - if (einfo->invert & IPT_ECN_OP_MATCH_CWR) { - if (th->cwr == 1) - return false; - } else { - if (th->cwr == 0) - return false; - } - } - - return true; -} - -static bool ecn_mt(const struct sk_buff *skb, struct xt_action_param *par) -{ - const struct ipt_ecn_info *info = par->matchinfo; - - if (info->operation & IPT_ECN_OP_MATCH_IP) - if (!match_ip(skb, info)) - return false; - - if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR)) { - if (!match_tcp(skb, info, &par->hotdrop)) - return false; - } - - return true; -} - -static int ecn_mt_check(const struct xt_mtchk_param *par) -{ - const struct ipt_ecn_info *info = par->matchinfo; - const struct ipt_ip *ip = par->entryinfo; - - if (info->operation & IPT_ECN_OP_MATCH_MASK) - return -EINVAL; - - if (info->invert & IPT_ECN_OP_MATCH_MASK) - return -EINVAL; - - if (info->operation & (IPT_ECN_OP_MATCH_ECE|IPT_ECN_OP_MATCH_CWR) && - (ip->proto != IPPROTO_TCP || ip->invflags & IPT_INV_PROTO)) { - pr_info("cannot match TCP bits in rule for non-tcp packets\n"); - return -EINVAL; - } - - return 0; -} - -static struct xt_match ecn_mt_reg __read_mostly = { - .name = "ecn", - .family = NFPROTO_IPV4, - .match = ecn_mt, - .matchsize = sizeof(struct ipt_ecn_info), - .checkentry = ecn_mt_check, - .me = THIS_MODULE, -}; - -static int __init ecn_mt_init(void) -{ - return xt_register_match(&ecn_mt_reg); -} - -static void __exit ecn_mt_exit(void) -{ - xt_unregister_match(&ecn_mt_reg); -} - -module_init(ecn_mt_init); -module_exit(ecn_mt_exit); diff --git a/net/ipv4/netfilter/ipt_rpfilter.c b/net/ipv4/netfilter/ipt_rpfilter.c new file mode 100644 index 00000000000..31371be8174 --- /dev/null +++ b/net/ipv4/netfilter/ipt_rpfilter.c @@ -0,0 +1,141 @@ +/* + * Copyright (c) 2011 Florian Westphal <fw@strlen.de> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * based on fib_frontend.c; Author: Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru> + */ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include <linux/ip.h> +#include <net/ip.h> +#include <net/ip_fib.h> +#include <net/route.h> + +#include <linux/netfilter/xt_rpfilter.h> +#include <linux/netfilter/x_tables.h> + +MODULE_LICENSE("GPL"); +MODULE_AUTHOR("Florian Westphal <fw@strlen.de>"); +MODULE_DESCRIPTION("iptables: ipv4 reverse path filter match"); + +/* don't try to find route from mcast/bcast/zeronet */ +static __be32 rpfilter_get_saddr(__be32 addr) +{ + if (ipv4_is_multicast(addr) || ipv4_is_lbcast(addr) || + ipv4_is_zeronet(addr)) + return 0; + return addr; +} + +static bool rpfilter_lookup_reverse(struct flowi4 *fl4, + const struct net_device *dev, u8 flags) +{ + struct fib_result res; + bool dev_match; + struct net *net = dev_net(dev); + int ret __maybe_unused; + + if (fib_lookup(net, fl4, &res)) + return false; + + if (res.type != RTN_UNICAST) { + if (res.type != RTN_LOCAL || !(flags & XT_RPFILTER_ACCEPT_LOCAL)) + return false; + } + dev_match = false; +#ifdef CONFIG_IP_ROUTE_MULTIPATH + 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 || flags & XT_RPFILTER_LOOSE) + return FIB_RES_NH(res).nh_scope <= RT_SCOPE_HOST; + return dev_match; +} + +static bool rpfilter_mt(const struct sk_buff *skb, struct xt_action_param *par) +{ + const struct xt_rpfilter_info *info; + const struct iphdr *iph; + struct flowi4 flow; + bool invert; + + info = par->matchinfo; + invert = info->flags & XT_RPFILTER_INVERT; + + if (par->in->flags & IFF_LOOPBACK) + return true ^ invert; + + iph = ip_hdr(skb); + if (ipv4_is_multicast(iph->daddr)) { + if (ipv4_is_zeronet(iph->saddr)) + return ipv4_is_local_multicast(iph->daddr) ^ invert; + flow.flowi4_iif = 0; + } else { + flow.flowi4_iif = dev_net(par->in)->loopback_dev->ifindex; + } + + flow.daddr = iph->saddr; + flow.saddr = rpfilter_get_saddr(iph->daddr); + flow.flowi4_oif = 0; + flow.flowi4_mark = info->flags & XT_RPFILTER_VALID_MARK ? skb->mark : 0; + flow.flowi4_tos = RT_TOS(iph->tos); + flow.flowi4_scope = RT_SCOPE_UNIVERSE; + + return rpfilter_lookup_reverse(&flow, par->in, info->flags) ^ invert; +} + +static int rpfilter_check(const struct xt_mtchk_param *par) +{ + const struct xt_rpfilter_info *info = par->matchinfo; + unsigned int options = ~XT_RPFILTER_OPTION_MASK; + if (info->flags & options) { + pr_info("unknown options encountered"); + return -EINVAL; + } + + if (strcmp(par->table, "mangle") != 0 && + strcmp(par->table, "raw") != 0) { + pr_info("match only valid in the \'raw\' " + "or \'mangle\' tables, not \'%s\'.\n", par->table); + return -EINVAL; + } + + return 0; +} + +static struct xt_match rpfilter_mt_reg __read_mostly = { + .name = "rpfilter", + .family = NFPROTO_IPV4, + .checkentry = rpfilter_check, + .match = rpfilter_mt, + .matchsize = sizeof(struct xt_rpfilter_info), + .hooks = (1 << NF_INET_PRE_ROUTING), + .me = THIS_MODULE +}; + +static int __init rpfilter_mt_init(void) +{ + return xt_register_match(&rpfilter_mt_reg); +} + +static void __exit rpfilter_mt_exit(void) +{ + xt_unregister_match(&rpfilter_mt_reg); +} + +module_init(rpfilter_mt_init); +module_exit(rpfilter_mt_exit); diff --git a/net/ipv4/netfilter/iptable_filter.c b/net/ipv4/netfilter/iptable_filter.c index c37641e819f..0e58f09e59f 100644 --- a/net/ipv4/netfilter/iptable_filter.c +++ b/net/ipv4/netfilter/iptable_filter.c @@ -52,7 +52,7 @@ iptable_filter_hook(unsigned int hook, struct sk_buff *skb, static struct nf_hook_ops *filter_ops __read_mostly; /* Default to forward because I got too much mail already. */ -static int forward = NF_ACCEPT; +static bool forward = NF_ACCEPT; module_param(forward, bool, 0000); static int __net_init iptable_filter_net_init(struct net *net) diff --git a/net/ipv4/netfilter/nf_nat_core.c b/net/ipv4/netfilter/nf_nat_core.c index 447bc5cfdc6..a708933dc23 100644 --- a/net/ipv4/netfilter/nf_nat_core.c +++ b/net/ipv4/netfilter/nf_nat_core.c @@ -30,7 +30,6 @@ #include <net/netfilter/nf_nat_helper.h> #include <net/netfilter/nf_conntrack_helper.h> #include <net/netfilter/nf_conntrack_l3proto.h> -#include <net/netfilter/nf_conntrack_l4proto.h> #include <net/netfilter/nf_conntrack_zones.h> static DEFINE_SPINLOCK(nf_nat_lock); @@ -57,7 +56,7 @@ hash_by_src(const struct net *net, u16 zone, /* Original src, to ensure we map it consistently if poss. */ hash = jhash_3words((__force u32)tuple->src.u3.ip, (__force u32)tuple->src.u.all ^ zone, - tuple->dst.protonum, 0); + tuple->dst.protonum, nf_conntrack_hash_rnd); return ((u64)hash * net->ipv4.nat_htable_size) >> 32; } @@ -82,14 +81,14 @@ EXPORT_SYMBOL(nf_nat_used_tuple); * that meet the constraints of range. */ static int in_range(const struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range) + const struct nf_nat_ipv4_range *range) { const struct nf_nat_protocol *proto; int ret = 0; /* If we are supposed to map IPs, then we must be in the range specified, otherwise let this drag us onto a new src IP. */ - if (range->flags & IP_NAT_RANGE_MAP_IPS) { + if (range->flags & NF_NAT_RANGE_MAP_IPS) { if (ntohl(tuple->src.u3.ip) < ntohl(range->min_ip) || ntohl(tuple->src.u3.ip) > ntohl(range->max_ip)) return 0; @@ -97,8 +96,8 @@ in_range(const struct nf_conntrack_tuple *tuple, rcu_read_lock(); proto = __nf_nat_proto_find(tuple->dst.protonum); - if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) || - proto->in_range(tuple, IP_NAT_MANIP_SRC, + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) || + proto->in_range(tuple, NF_NAT_MANIP_SRC, &range->min, &range->max)) ret = 1; rcu_read_unlock(); @@ -123,7 +122,7 @@ static int find_appropriate_src(struct net *net, u16 zone, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *result, - const struct nf_nat_range *range) + const struct nf_nat_ipv4_range *range) { unsigned int h = hash_by_src(net, zone, tuple); const struct nf_conn_nat *nat; @@ -157,7 +156,7 @@ find_appropriate_src(struct net *net, u16 zone, */ static void find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, const struct nf_conn *ct, enum nf_nat_manip_type maniptype) { @@ -166,10 +165,10 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, u_int32_t minip, maxip, j; /* No IP mapping? Do nothing. */ - if (!(range->flags & IP_NAT_RANGE_MAP_IPS)) + if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) return; - if (maniptype == IP_NAT_MANIP_SRC) + if (maniptype == NF_NAT_MANIP_SRC) var_ipp = &tuple->src.u3.ip; else var_ipp = &tuple->dst.u3.ip; @@ -189,7 +188,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, minip = ntohl(range->min_ip); maxip = ntohl(range->max_ip); j = jhash_2words((__force u32)tuple->src.u3.ip, - range->flags & IP_NAT_RANGE_PERSISTENT ? + range->flags & NF_NAT_RANGE_PERSISTENT ? 0 : (__force u32)tuple->dst.u3.ip ^ zone, 0); j = ((u64)j * (maxip - minip + 1)) >> 32; *var_ipp = htonl(minip + j); @@ -204,7 +203,7 @@ find_best_ips_proto(u16 zone, struct nf_conntrack_tuple *tuple, static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, struct nf_conn *ct, enum nf_nat_manip_type maniptype) { @@ -219,8 +218,8 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, This is only required for source (ie. NAT/masq) mappings. So far, we don't do local source mappings, so multiple manips not an issue. */ - if (maniptype == IP_NAT_MANIP_SRC && - !(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) { + if (maniptype == NF_NAT_MANIP_SRC && + !(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { /* try the original tuple first */ if (in_range(orig_tuple, range)) { if (!nf_nat_used_tuple(orig_tuple, ct)) { @@ -247,8 +246,8 @@ 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)) { - if (range->flags & IP_NAT_RANGE_PROTO_SPECIFIED) { + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) { + if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { if (proto->in_range(tuple, maniptype, &range->min, &range->max) && (range->min.all == range->max.all || @@ -267,7 +266,7 @@ out: unsigned int nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype) { struct net *net = nf_ct_net(ct); @@ -284,8 +283,8 @@ nf_nat_setup_info(struct nf_conn *ct, } } - NF_CT_ASSERT(maniptype == IP_NAT_MANIP_SRC || - maniptype == IP_NAT_MANIP_DST); + NF_CT_ASSERT(maniptype == NF_NAT_MANIP_SRC || + maniptype == NF_NAT_MANIP_DST); BUG_ON(nf_nat_initialized(ct, maniptype)); /* What we've got will look like inverse of reply. Normally @@ -306,19 +305,19 @@ nf_nat_setup_info(struct nf_conn *ct, nf_conntrack_alter_reply(ct, &reply); /* Non-atomic: we own this at the moment. */ - if (maniptype == IP_NAT_MANIP_SRC) + if (maniptype == NF_NAT_MANIP_SRC) ct->status |= IPS_SRC_NAT; else ct->status |= IPS_DST_NAT; } - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { unsigned int srchash; srchash = hash_by_src(net, nf_ct_zone(ct), &ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple); spin_lock_bh(&nf_nat_lock); - /* nf_conntrack_alter_reply might re-allocate exntension aera */ + /* nf_conntrack_alter_reply might re-allocate extension area */ nat = nfct_nat(ct); nat->ct = ct; hlist_add_head_rcu(&nat->bysource, @@ -327,7 +326,7 @@ nf_nat_setup_info(struct nf_conn *ct, } /* It's done. */ - if (maniptype == IP_NAT_MANIP_DST) + if (maniptype == NF_NAT_MANIP_DST) ct->status |= IPS_DST_NAT_DONE; else ct->status |= IPS_SRC_NAT_DONE; @@ -361,7 +360,7 @@ manip_pkt(u_int16_t proto, iph = (void *)skb->data + iphdroff; - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { csum_replace4(&iph->check, iph->saddr, target->src.u3.ip); iph->saddr = target->src.u3.ip; } else { @@ -381,7 +380,7 @@ unsigned int nf_nat_packet(struct nf_conn *ct, unsigned long statusbit; enum nf_nat_manip_type mtype = HOOK2MANIP(hooknum); - if (mtype == IP_NAT_MANIP_SRC) + if (mtype == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; @@ -414,8 +413,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, struct icmphdr icmp; struct iphdr ip; } *inside; - const struct nf_conntrack_l4proto *l4proto; - struct nf_conntrack_tuple inner, target; + struct nf_conntrack_tuple target; int hdrlen = ip_hdrlen(skb); enum ip_conntrack_dir dir = CTINFO2DIR(ctinfo); unsigned long statusbit; @@ -447,7 +445,7 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, return 0; } - if (manip == IP_NAT_MANIP_SRC) + if (manip == NF_NAT_MANIP_SRC) statusbit = IPS_SRC_NAT; else statusbit = IPS_DST_NAT; @@ -463,16 +461,6 @@ int nf_nat_icmp_reply_translation(struct nf_conn *ct, "dir %s\n", skb, manip, dir == IP_CT_DIR_ORIGINAL ? "ORIG" : "REPLY"); - /* rcu_read_lock()ed by nf_hook_slow */ - l4proto = __nf_ct_l4proto_find(PF_INET, inside->ip.protocol); - - if (!nf_ct_get_tuple(skb, hdrlen + sizeof(struct icmphdr), - (hdrlen + - sizeof(struct icmphdr) + inside->ip.ihl * 4), - (u_int16_t)AF_INET, inside->ip.protocol, - &inner, l3proto, l4proto)) - return 0; - /* Change inner back to look like incoming packet. We do the opposite manip on this hook to normal, because it might not pass all hooks (locally-generated ICMP). Consider incoming @@ -575,26 +563,6 @@ static struct nf_ct_ext_type nat_extend __read_mostly = { #include <linux/netfilter/nfnetlink.h> #include <linux/netfilter/nfnetlink_conntrack.h> -static const struct nf_nat_protocol * -nf_nat_proto_find_get(u_int8_t protonum) -{ - const struct nf_nat_protocol *p; - - rcu_read_lock(); - p = __nf_nat_proto_find(protonum); - if (!try_module_get(p->me)) - p = &nf_nat_unknown_protocol; - rcu_read_unlock(); - - return p; -} - -static void -nf_nat_proto_put(const struct nf_nat_protocol *p) -{ - module_put(p->me); -} - static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { [CTA_PROTONAT_PORT_MIN] = { .type = NLA_U16 }, [CTA_PROTONAT_PORT_MAX] = { .type = NLA_U16 }, @@ -602,7 +570,7 @@ static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { static int nfnetlink_parse_nat_proto(struct nlattr *attr, const struct nf_conn *ct, - struct nf_nat_range *range) + struct nf_nat_ipv4_range *range) { struct nlattr *tb[CTA_PROTONAT_MAX+1]; const struct nf_nat_protocol *npt; @@ -612,21 +580,23 @@ static int nfnetlink_parse_nat_proto(struct nlattr *attr, if (err < 0) return err; - npt = nf_nat_proto_find_get(nf_ct_protonum(ct)); + rcu_read_lock(); + npt = __nf_nat_proto_find(nf_ct_protonum(ct)); if (npt->nlattr_to_range) err = npt->nlattr_to_range(tb, range); - nf_nat_proto_put(npt); + rcu_read_unlock(); return err; } static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { [CTA_NAT_MINIP] = { .type = NLA_U32 }, [CTA_NAT_MAXIP] = { .type = NLA_U32 }, + [CTA_NAT_PROTO] = { .type = NLA_NESTED }, }; static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range) + const struct nf_conn *ct, struct nf_nat_ipv4_range *range) { struct nlattr *tb[CTA_NAT_MAX+1]; int err; @@ -646,7 +616,7 @@ nfnetlink_parse_nat(const struct nlattr *nat, range->max_ip = nla_get_be32(tb[CTA_NAT_MAXIP]); if (range->min_ip) - range->flags |= IP_NAT_RANGE_MAP_IPS; + range->flags |= NF_NAT_RANGE_MAP_IPS; if (!tb[CTA_NAT_PROTO]) return 0; @@ -663,7 +633,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { - struct nf_nat_range range; + struct nf_nat_ipv4_range range; if (nfnetlink_parse_nat(attr, ct, &range) < 0) return -EINVAL; diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index b9a1136addb..dc1dd912baf 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -398,7 +398,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_range range; + struct nf_nat_ipv4_range range; if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */ nf_nat_follow_master(new, this); @@ -409,16 +409,16 @@ static void ip_nat_q931_expect(struct nf_conn *new, BUG_ON(new->status & IPS_NAT_DONE_MASK); /* Change src to where master sends to */ - range.flags = IP_NAT_RANGE_MAP_IPS; + range.flags = NF_NAT_RANGE_MAP_IPS; range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip; - nf_nat_setup_info(new, &range, IP_NAT_MANIP_SRC); + nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ - range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); range.min = range.max = this->saved_proto; range.min_ip = range.max_ip = new->master->tuplehash[!this->dir].tuple.src.u3.ip; - nf_nat_setup_info(new, &range, IP_NAT_MANIP_DST); + nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST); } /****************************************************************************/ @@ -496,21 +496,21 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_callforwarding_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_range range; + struct nf_nat_ipv4_range range; /* This must be a fresh one. */ BUG_ON(new->status & IPS_NAT_DONE_MASK); /* Change src to where master sends to */ - range.flags = IP_NAT_RANGE_MAP_IPS; + range.flags = NF_NAT_RANGE_MAP_IPS; range.min_ip = range.max_ip = new->tuplehash[!this->dir].tuple.src.u3.ip; - nf_nat_setup_info(new, &range, IP_NAT_MANIP_SRC); + nf_nat_setup_info(new, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ - range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); range.min = range.max = this->saved_proto; range.min_ip = range.max_ip = this->saved_ip; - nf_nat_setup_info(new, &range, IP_NAT_MANIP_DST); + nf_nat_setup_info(new, &range, NF_NAT_MANIP_DST); } /****************************************************************************/ diff --git a/net/ipv4/netfilter/nf_nat_helper.c b/net/ipv4/netfilter/nf_nat_helper.c index ebc5f8894f9..af65958f630 100644 --- a/net/ipv4/netfilter/nf_nat_helper.c +++ b/net/ipv4/netfilter/nf_nat_helper.c @@ -253,12 +253,6 @@ nf_nat_mangle_udp_packet(struct sk_buff *skb, struct udphdr *udph; int datalen, oldlen; - /* UDP helpers might accidentally mangle the wrong packet */ - iph = ip_hdr(skb); - if (skb->len < iph->ihl*4 + sizeof(*udph) + - match_offset + match_len) - return 0; - if (!skb_make_writable(skb, skb->len)) return 0; @@ -430,22 +424,22 @@ nf_nat_seq_adjust(struct sk_buff *skb, void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_range range; + struct nf_nat_ipv4_range range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); /* Change src to where master sends to */ - range.flags = IP_NAT_RANGE_MAP_IPS; + range.flags = NF_NAT_RANGE_MAP_IPS; range.min_ip = range.max_ip = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; - nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC); + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ - range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); range.min = range.max = exp->saved_proto; range.min_ip = range.max_ip = ct->master->tuplehash[!exp->dir].tuple.src.u3.ip; - nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST); + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); } EXPORT_SYMBOL(nf_nat_follow_master); diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 3e8284ba46b..c273d58980a 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -47,7 +47,7 @@ static void pptp_nat_expected(struct nf_conn *ct, struct nf_conntrack_tuple t; const struct nf_ct_pptp_master *ct_pptp_info; const struct nf_nat_pptp *nat_pptp_info; - struct nf_nat_range range; + struct nf_nat_ipv4_range range; ct_pptp_info = &nfct_help(master)->help.ct_pptp_info; nat_pptp_info = &nfct_nat(master)->help.nat_pptp_info; @@ -88,24 +88,24 @@ static void pptp_nat_expected(struct nf_conn *ct, BUG_ON(ct->status & IPS_NAT_DONE_MASK); /* Change src to where master sends to */ - range.flags = IP_NAT_RANGE_MAP_IPS; + range.flags = NF_NAT_RANGE_MAP_IPS; range.min_ip = range.max_ip = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; if (exp->dir == IP_CT_DIR_ORIGINAL) { - range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED; + range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; range.min = range.max = exp->saved_proto; } - nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC); + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); /* For DST manip, map port here to where it's expected. */ - range.flags = IP_NAT_RANGE_MAP_IPS; + range.flags = NF_NAT_RANGE_MAP_IPS; range.min_ip = range.max_ip = ct->master->tuplehash[!exp->dir].tuple.src.u3.ip; if (exp->dir == IP_CT_DIR_REPLY) { - range.flags |= IP_NAT_RANGE_PROTO_SPECIFIED; + range.flags |= NF_NAT_RANGE_PROTO_SPECIFIED; range.min = range.max = exp->saved_proto; } - nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST); + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); } /* outbound packets == from PNS to PAC */ diff --git a/net/ipv4/netfilter/nf_nat_proto_common.c b/net/ipv4/netfilter/nf_nat_proto_common.c index a3d99761860..9993bc93e10 100644 --- a/net/ipv4/netfilter/nf_nat_proto_common.c +++ b/net/ipv4/netfilter/nf_nat_proto_common.c @@ -26,7 +26,7 @@ bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple, { __be16 port; - if (maniptype == IP_NAT_MANIP_SRC) + if (maniptype == NF_NAT_MANIP_SRC) port = tuple->src.u.all; else port = tuple->dst.u.all; @@ -37,7 +37,7 @@ bool nf_nat_proto_in_range(const struct nf_conntrack_tuple *tuple, EXPORT_SYMBOL_GPL(nf_nat_proto_in_range); void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct, u_int16_t *rover) @@ -46,15 +46,15 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, __be16 *portptr; u_int16_t off; - if (maniptype == IP_NAT_MANIP_SRC) + if (maniptype == NF_NAT_MANIP_SRC) portptr = &tuple->src.u.all; else portptr = &tuple->dst.u.all; /* If no range specified... */ - if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) { + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { /* If it's dst rewrite, can't change port */ - if (maniptype == IP_NAT_MANIP_DST) + if (maniptype == NF_NAT_MANIP_DST) return; if (ntohs(*portptr) < 1024) { @@ -75,9 +75,9 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.all) - min + 1; } - if (range->flags & IP_NAT_RANGE_PROTO_RANDOM) + if (range->flags & NF_NAT_RANGE_PROTO_RANDOM) off = secure_ipv4_port_ephemeral(tuple->src.u3.ip, tuple->dst.u3.ip, - maniptype == IP_NAT_MANIP_SRC + maniptype == NF_NAT_MANIP_SRC ? tuple->dst.u.all : tuple->src.u.all); else @@ -87,7 +87,7 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, *portptr = htons(min + off % range_size); if (++i != range_size && nf_nat_used_tuple(tuple, ct)) continue; - if (!(range->flags & IP_NAT_RANGE_PROTO_RANDOM)) + if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM)) *rover = off; return; } @@ -96,31 +96,19 @@ void nf_nat_proto_unique_tuple(struct nf_conntrack_tuple *tuple, EXPORT_SYMBOL_GPL(nf_nat_proto_unique_tuple); #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) -int nf_nat_proto_range_to_nlattr(struct sk_buff *skb, - const struct nf_nat_range *range) -{ - NLA_PUT_BE16(skb, CTA_PROTONAT_PORT_MIN, range->min.all); - NLA_PUT_BE16(skb, CTA_PROTONAT_PORT_MAX, range->max.all); - return 0; - -nla_put_failure: - return -1; -} -EXPORT_SYMBOL_GPL(nf_nat_proto_nlattr_to_range); - int nf_nat_proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_ipv4_range *range) { if (tb[CTA_PROTONAT_PORT_MIN]) { range->min.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); range->max.all = range->min.tcp.port; - range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED; + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } if (tb[CTA_PROTONAT_PORT_MAX]) { range->max.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MAX]); - range->flags |= IP_NAT_RANGE_PROTO_SPECIFIED; + range->flags |= NF_NAT_RANGE_PROTO_SPECIFIED; } return 0; } -EXPORT_SYMBOL_GPL(nf_nat_proto_range_to_nlattr); +EXPORT_SYMBOL_GPL(nf_nat_proto_nlattr_to_range); #endif diff --git a/net/ipv4/netfilter/nf_nat_proto_dccp.c b/net/ipv4/netfilter/nf_nat_proto_dccp.c index 570faf2667b..3f67138d187 100644 --- a/net/ipv4/netfilter/nf_nat_proto_dccp.c +++ b/net/ipv4/netfilter/nf_nat_proto_dccp.c @@ -24,7 +24,7 @@ static u_int16_t dccp_port_rover; static void dccp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -54,7 +54,7 @@ dccp_manip_pkt(struct sk_buff *skb, iph = (struct iphdr *)(skb->data + iphdroff); hdr = (struct dccp_hdr *)(skb->data + hdroff); - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { oldip = iph->saddr; newip = tuple->src.u3.ip; newport = tuple->src.u.dccp.port; @@ -80,12 +80,10 @@ dccp_manip_pkt(struct sk_buff *skb, static const struct nf_nat_protocol nf_nat_protocol_dccp = { .protonum = IPPROTO_DCCP, - .me = THIS_MODULE, .manip_pkt = dccp_manip_pkt, .in_range = nf_nat_proto_in_range, .unique_tuple = dccp_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index bc8d83a31c7..46ba0b9ab98 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -39,7 +39,7 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE"); /* generate unique tuple ... */ static void gre_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -52,12 +52,12 @@ gre_unique_tuple(struct nf_conntrack_tuple *tuple, if (!ct->master) return; - if (maniptype == IP_NAT_MANIP_SRC) + if (maniptype == NF_NAT_MANIP_SRC) keyptr = &tuple->src.u.gre.key; else keyptr = &tuple->dst.u.gre.key; - if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) { + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) { pr_debug("%p: NATing GRE PPTP\n", ct); min = 1; range_size = 0xffff; @@ -99,7 +99,7 @@ gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, /* we only have destination manip of a packet, since 'source key' * is not present in the packet itself */ - if (maniptype != IP_NAT_MANIP_DST) + if (maniptype != NF_NAT_MANIP_DST) return true; switch (greh->version) { case GRE_VERSION_1701: @@ -119,12 +119,10 @@ gre_manip_pkt(struct sk_buff *skb, unsigned int iphdroff, static const struct nf_nat_protocol gre = { .protonum = IPPROTO_GRE, - .me = THIS_MODULE, .manip_pkt = gre_manip_pkt, .in_range = nf_nat_proto_in_range, .unique_tuple = gre_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index 9f4dc1235dc..b35172851ba 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -30,7 +30,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple, static void icmp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -40,7 +40,7 @@ icmp_unique_tuple(struct nf_conntrack_tuple *tuple, range_size = ntohs(range->max.icmp.id) - ntohs(range->min.icmp.id) + 1; /* If no range specified... */ - if (!(range->flags & IP_NAT_RANGE_PROTO_SPECIFIED)) + if (!(range->flags & NF_NAT_RANGE_PROTO_SPECIFIED)) range_size = 0xFFFF; for (i = 0; ; ++id) { @@ -74,12 +74,10 @@ icmp_manip_pkt(struct sk_buff *skb, const struct nf_nat_protocol nf_nat_protocol_icmp = { .protonum = IPPROTO_ICMP, - .me = THIS_MODULE, .manip_pkt = icmp_manip_pkt, .in_range = icmp_in_range, .unique_tuple = icmp_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_sctp.c b/net/ipv4/netfilter/nf_nat_proto_sctp.c index bd5a80a62a5..3cce9b6c1c2 100644 --- a/net/ipv4/netfilter/nf_nat_proto_sctp.c +++ b/net/ipv4/netfilter/nf_nat_proto_sctp.c @@ -19,7 +19,7 @@ static u_int16_t nf_sctp_port_rover; static void sctp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -46,7 +46,7 @@ sctp_manip_pkt(struct sk_buff *skb, iph = (struct iphdr *)(skb->data + iphdroff); hdr = (struct sctphdr *)(skb->data + hdroff); - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src ip and src pt */ oldip = iph->saddr; newip = tuple->src.u3.ip; @@ -70,12 +70,10 @@ sctp_manip_pkt(struct sk_buff *skb, static const struct nf_nat_protocol nf_nat_protocol_sctp = { .protonum = IPPROTO_SCTP, - .me = THIS_MODULE, .manip_pkt = sctp_manip_pkt, .in_range = nf_nat_proto_in_range, .unique_tuple = sctp_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_tcp.c b/net/ipv4/netfilter/nf_nat_proto_tcp.c index 0d67bb80130..9fb4b4e72bb 100644 --- a/net/ipv4/netfilter/nf_nat_proto_tcp.c +++ b/net/ipv4/netfilter/nf_nat_proto_tcp.c @@ -23,7 +23,7 @@ static u_int16_t tcp_port_rover; static void tcp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -55,7 +55,7 @@ tcp_manip_pkt(struct sk_buff *skb, iph = (struct iphdr *)(skb->data + iphdroff); hdr = (struct tcphdr *)(skb->data + hdroff); - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src ip and src pt */ oldip = iph->saddr; newip = tuple->src.u3.ip; @@ -82,12 +82,10 @@ tcp_manip_pkt(struct sk_buff *skb, const struct nf_nat_protocol nf_nat_protocol_tcp = { .protonum = IPPROTO_TCP, - .me = THIS_MODULE, .manip_pkt = tcp_manip_pkt, .in_range = nf_nat_proto_in_range, .unique_tuple = tcp_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_udp.c b/net/ipv4/netfilter/nf_nat_proto_udp.c index 0b1b8601cba..9883336e628 100644 --- a/net/ipv4/netfilter/nf_nat_proto_udp.c +++ b/net/ipv4/netfilter/nf_nat_proto_udp.c @@ -22,7 +22,7 @@ static u_int16_t udp_port_rover; static void udp_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -47,7 +47,7 @@ udp_manip_pkt(struct sk_buff *skb, iph = (struct iphdr *)(skb->data + iphdroff); hdr = (struct udphdr *)(skb->data + hdroff); - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src ip and src pt */ oldip = iph->saddr; newip = tuple->src.u3.ip; @@ -73,12 +73,10 @@ udp_manip_pkt(struct sk_buff *skb, const struct nf_nat_protocol nf_nat_protocol_udp = { .protonum = IPPROTO_UDP, - .me = THIS_MODULE, .manip_pkt = udp_manip_pkt, .in_range = nf_nat_proto_in_range, .unique_tuple = udp_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_udplite.c b/net/ipv4/netfilter/nf_nat_proto_udplite.c index f83ef23e2ab..d24d10a7beb 100644 --- a/net/ipv4/netfilter/nf_nat_proto_udplite.c +++ b/net/ipv4/netfilter/nf_nat_proto_udplite.c @@ -21,7 +21,7 @@ static u_int16_t udplite_port_rover; static void udplite_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -47,7 +47,7 @@ udplite_manip_pkt(struct sk_buff *skb, iph = (struct iphdr *)(skb->data + iphdroff); hdr = (struct udphdr *)(skb->data + hdroff); - if (maniptype == IP_NAT_MANIP_SRC) { + if (maniptype == NF_NAT_MANIP_SRC) { /* Get rid of src ip and src pt */ oldip = iph->saddr; newip = tuple->src.u3.ip; @@ -72,12 +72,10 @@ udplite_manip_pkt(struct sk_buff *skb, static const struct nf_nat_protocol nf_nat_protocol_udplite = { .protonum = IPPROTO_UDPLITE, - .me = THIS_MODULE, .manip_pkt = udplite_manip_pkt, .in_range = nf_nat_proto_in_range, .unique_tuple = udplite_unique_tuple, #if defined(CONFIG_NF_CT_NETLINK) || defined(CONFIG_NF_CT_NETLINK_MODULE) - .range_to_nlattr = nf_nat_proto_range_to_nlattr, .nlattr_to_range = nf_nat_proto_nlattr_to_range, #endif }; diff --git a/net/ipv4/netfilter/nf_nat_proto_unknown.c b/net/ipv4/netfilter/nf_nat_proto_unknown.c index a50f2bc1c73..e0afe8112b1 100644 --- a/net/ipv4/netfilter/nf_nat_proto_unknown.c +++ b/net/ipv4/netfilter/nf_nat_proto_unknown.c @@ -27,7 +27,7 @@ static bool unknown_in_range(const struct nf_conntrack_tuple *tuple, } static void unknown_unique_tuple(struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_ipv4_range *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -46,7 +46,6 @@ unknown_manip_pkt(struct sk_buff *skb, } const struct nf_nat_protocol nf_nat_unknown_protocol = { - /* .me isn't set: getting a ref to this cannot fail. */ .manip_pkt = unknown_manip_pkt, .in_range = unknown_in_range, .unique_tuple = unknown_unique_tuple, diff --git a/net/ipv4/netfilter/nf_nat_rule.c b/net/ipv4/netfilter/nf_nat_rule.c index 733c9abc1cb..d2a9dc314e0 100644 --- a/net/ipv4/netfilter/nf_nat_rule.c +++ b/net/ipv4/netfilter/nf_nat_rule.c @@ -44,7 +44,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; NF_CT_ASSERT(par->hooknum == NF_INET_POST_ROUTING || par->hooknum == NF_INET_LOCAL_IN); @@ -56,7 +56,7 @@ ipt_snat_target(struct sk_buff *skb, const struct xt_action_param *par) ctinfo == IP_CT_RELATED_REPLY)); NF_CT_ASSERT(par->out != NULL); - return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_SRC); + return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_SRC); } static unsigned int @@ -64,7 +64,7 @@ ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; NF_CT_ASSERT(par->hooknum == NF_INET_PRE_ROUTING || par->hooknum == NF_INET_LOCAL_OUT); @@ -74,12 +74,12 @@ ipt_dnat_target(struct sk_buff *skb, const struct xt_action_param *par) /* Connection must be valid and new. */ NF_CT_ASSERT(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED)); - return nf_nat_setup_info(ct, &mr->range[0], IP_NAT_MANIP_DST); + return nf_nat_setup_info(ct, &mr->range[0], NF_NAT_MANIP_DST); } static int ipt_snat_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; /* Must be a valid range */ if (mr->rangesize != 1) { @@ -91,7 +91,7 @@ static int ipt_snat_checkentry(const struct xt_tgchk_param *par) static int ipt_dnat_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_multi_range_compat *mr = par->targinfo; + const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; /* Must be a valid range */ if (mr->rangesize != 1) { @@ -105,13 +105,13 @@ static unsigned int 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). + per-proto parts (hence not NF_NAT_RANGE_PROTO_SPECIFIED). */ - struct nf_nat_range range; + struct nf_nat_ipv4_range range; range.flags = 0; pr_debug("Allocating NULL binding for %p (%pI4)\n", ct, - HOOK2MANIP(hooknum) == IP_NAT_MANIP_SRC ? + HOOK2MANIP(hooknum) == NF_NAT_MANIP_SRC ? &ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.ip : &ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.ip); @@ -140,7 +140,7 @@ int nf_nat_rule_find(struct sk_buff *skb, static struct xt_target ipt_snat_reg __read_mostly = { .name = "SNAT", .target = ipt_snat_target, - .targetsize = sizeof(struct nf_nat_multi_range_compat), + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = (1 << NF_INET_POST_ROUTING) | (1 << NF_INET_LOCAL_IN), .checkentry = ipt_snat_checkentry, @@ -150,7 +150,7 @@ static struct xt_target ipt_snat_reg __read_mostly = { static struct xt_target ipt_dnat_reg __read_mostly = { .name = "DNAT", .target = ipt_dnat_target, - .targetsize = sizeof(struct nf_nat_multi_range_compat), + .targetsize = sizeof(struct nf_nat_ipv4_multi_range_compat), .table = "nat", .hooks = (1 << NF_INET_PRE_ROUTING) | (1 << NF_INET_LOCAL_OUT), .checkentry = ipt_dnat_checkentry, diff --git a/net/ipv4/netfilter/nf_nat_sip.c b/net/ipv4/netfilter/nf_nat_sip.c index 78844d9208f..d0319f96269 100644 --- a/net/ipv4/netfilter/nf_nat_sip.c +++ b/net/ipv4/netfilter/nf_nat_sip.c @@ -249,25 +249,25 @@ static void ip_nat_sip_seq_adjust(struct sk_buff *skb, s16 off) static void ip_nat_sip_expected(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_range range; + struct nf_nat_ipv4_range range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); /* For DST manip, map port here to where it's expected. */ - range.flags = (IP_NAT_RANGE_MAP_IPS | IP_NAT_RANGE_PROTO_SPECIFIED); + range.flags = (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED); range.min = range.max = exp->saved_proto; range.min_ip = range.max_ip = exp->saved_ip; - nf_nat_setup_info(ct, &range, IP_NAT_MANIP_DST); + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); /* Change src to where master sends to, but only if the connection * actually came from the same source. */ if (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.ip == ct->master->tuplehash[exp->dir].tuple.src.u3.ip) { - range.flags = IP_NAT_RANGE_MAP_IPS; + range.flags = NF_NAT_RANGE_MAP_IPS; range.min_ip = range.max_ip = ct->master->tuplehash[!exp->dir].tuple.dst.u3.ip; - nf_nat_setup_info(ct, &range, IP_NAT_MANIP_SRC); + nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); } } diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 92900482ede..3828a422982 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -137,7 +137,7 @@ nf_nat_fn(unsigned int hooknum, return ret; } else pr_debug("Already setup manip %s for ct %p\n", - maniptype == IP_NAT_MANIP_SRC ? "SRC" : "DST", + maniptype == NF_NAT_MANIP_SRC ? "SRC" : "DST", ct); break; diff --git a/net/ipv4/ping.c b/net/ipv4/ping.c index a06f73fdb3c..43d4c3b2236 100644 --- a/net/ipv4/ping.c +++ b/net/ipv4/ping.c @@ -339,7 +339,6 @@ void ping_err(struct sk_buff *skb, u32 info) sk = ping_v4_lookup(net, iph->daddr, iph->saddr, ntohs(icmph->un.echo.id), skb->dev->ifindex); if (sk == NULL) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); pr_debug("no socket, dropping\n"); return; /* No socket for error */ } @@ -679,7 +678,6 @@ static int ping_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) pr_debug("ping_queue_rcv_skb(sk=%p,sk->num=%d,skb=%p)\n", inet_sk(sk), inet_sk(sk)->inet_num, skb); if (sock_queue_rcv_skb(sk, skb) < 0) { - ICMP_INC_STATS_BH(sock_net(sk), ICMP_MIB_INERRORS); kfree_skb(skb); pr_debug("ping_queue_rcv_skb -> failed\n"); return -1; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 466ea8bb7a4..3569d8ecaea 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -56,17 +56,17 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) local_bh_disable(); orphans = percpu_counter_sum_positive(&tcp_orphan_count); - sockets = percpu_counter_sum_positive(&tcp_sockets_allocated); + sockets = proto_sockets_allocated_sum_positive(&tcp_prot); local_bh_enable(); socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %ld\n", sock_prot_inuse_get(net, &tcp_prot), orphans, tcp_death_row.tw_count, sockets, - atomic_long_read(&tcp_memory_allocated)); + proto_memory_allocated(&tcp_prot)); seq_printf(seq, "UDP: inuse %d mem %ld\n", sock_prot_inuse_get(net, &udp_prot), - atomic_long_read(&udp_memory_allocated)); + proto_memory_allocated(&udp_prot)); seq_printf(seq, "UDPLITE: inuse %d\n", sock_prot_inuse_get(net, &udplite_prot)); seq_printf(seq, "RAW: inuse %d\n", @@ -288,7 +288,7 @@ static void icmpmsg_put(struct seq_file *seq) count = 0; for (i = 0; i < ICMPMSG_MIB_MAX; i++) { - val = snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, i); + val = atomic_long_read(&net->mib.icmpmsg_statistics->mibs[i]); if (val) { type[count] = i; vals[count++] = val; @@ -307,6 +307,7 @@ static void icmp_put(struct seq_file *seq) { int i; struct net *net = seq->private; + atomic_long_t *ptr = net->mib.icmpmsg_statistics->mibs; seq_puts(seq, "\nIcmp: InMsgs InErrors"); for (i=0; icmpmibmap[i].name != NULL; i++) @@ -319,15 +320,13 @@ static void icmp_put(struct seq_file *seq) snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_INERRORS)); for (i=0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, - icmpmibmap[i].index)); + atomic_long_read(ptr + icmpmibmap[i].index)); seq_printf(seq, " %lu %lu", snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTMSGS), snmp_fold_field((void __percpu **) net->mib.icmp_statistics, ICMP_MIB_OUTERRORS)); for (i=0; icmpmibmap[i].name != NULL; i++) seq_printf(seq, " %lu", - snmp_fold_field((void __percpu **) net->mib.icmpmsg_statistics, - icmpmibmap[i].index | 0x100)); + atomic_long_read(ptr + (icmpmibmap[i].index | 0x100))); } /* diff --git a/net/ipv4/raw.c b/net/ipv4/raw.c index 007e2eb769d..3ccda5ae8a2 100644 --- a/net/ipv4/raw.c +++ b/net/ipv4/raw.c @@ -292,7 +292,8 @@ static int raw_rcv_skb(struct sock * sk, struct sk_buff * skb) { /* Charge it to the socket. */ - if (ip_queue_rcv_skb(sk, skb) < 0) { + ipv4_pktinfo_prepare(skb); + if (sock_queue_rcv_skb(sk, skb) < 0) { kfree_skb(skb); return NET_RX_DROP; } @@ -327,6 +328,7 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, unsigned int iphlen; int err; struct rtable *rt = *rtp; + int hlen, tlen; if (length > rt->dst.dev->mtu) { ip_local_error(sk, EMSGSIZE, fl4->daddr, inet->inet_dport, @@ -336,12 +338,14 @@ static int raw_send_hdrinc(struct sock *sk, struct flowi4 *fl4, if (flags&MSG_PROBE) goto out; + hlen = LL_RESERVED_SPACE(rt->dst.dev); + tlen = rt->dst.dev->needed_tailroom; skb = sock_alloc_send_skb(sk, - length + LL_ALLOCATED_SPACE(rt->dst.dev) + 15, + length + hlen + tlen + 15, flags & MSG_DONTWAIT, &err); if (skb == NULL) goto error; - skb_reserve(skb, LL_RESERVED_SPACE(rt->dst.dev)); + skb_reserve(skb, hlen); skb->priority = sk->sk_priority; skb->mark = sk->sk_mark; diff --git a/net/ipv4/route.c b/net/ipv4/route.c index 155138d8ec8..bcacf54e541 100644 --- a/net/ipv4/route.c +++ b/net/ipv4/route.c @@ -91,6 +91,7 @@ #include <linux/rcupdate.h> #include <linux/times.h> #include <linux/slab.h> +#include <linux/prefetch.h> #include <net/dst.h> #include <net/net_namespace.h> #include <net/protocol.h> @@ -108,11 +109,10 @@ #ifdef CONFIG_SYSCTL #include <linux/sysctl.h> #endif -#include <net/atmclip.h> #include <net/secure_seq.h> #define RT_FL_TOS(oldflp4) \ - ((u32)(oldflp4->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK))) + ((oldflp4)->flowi4_tos & (IPTOS_RT_MASK | RTO_ONLINK)) #define IP_MAX_MTU 0xFFF0 @@ -120,6 +120,7 @@ static int ip_rt_max_size; static int ip_rt_gc_timeout __read_mostly = RT_GC_TIMEOUT; +static int ip_rt_gc_interval __read_mostly = 60 * HZ; static int ip_rt_gc_min_interval __read_mostly = HZ / 2; static int ip_rt_redirect_number __read_mostly = 9; static int ip_rt_redirect_load __read_mostly = HZ / 50; @@ -131,6 +132,10 @@ static int ip_rt_mtu_expires __read_mostly = 10 * 60 * HZ; static int ip_rt_min_pmtu __read_mostly = 512 + 20 + 20; static int ip_rt_min_advmss __read_mostly = 256; static int rt_chain_length_max __read_mostly = 20; +static int redirect_genid; + +static struct delayed_work expires_work; +static unsigned long expires_ljiffies; /* * Interface to generic destination cache. @@ -138,7 +143,7 @@ static int rt_chain_length_max __read_mostly = 20; static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ipv4_default_advmss(const struct dst_entry *dst); -static unsigned int ipv4_default_mtu(const struct dst_entry *dst); +static unsigned int ipv4_mtu(const struct dst_entry *dst); static void ipv4_dst_destroy(struct dst_entry *dst); static struct dst_entry *ipv4_negative_advice(struct dst_entry *dst); static void ipv4_link_failure(struct sk_buff *skb); @@ -193,7 +198,7 @@ static struct dst_ops ipv4_dst_ops = { .gc = rt_garbage_collect, .check = ipv4_dst_check, .default_advmss = ipv4_default_advmss, - .default_mtu = ipv4_default_mtu, + .mtu = ipv4_mtu, .cow_metrics = ipv4_cow_metrics, .destroy = ipv4_dst_destroy, .ifdown = ipv4_dst_ifdown, @@ -416,9 +421,13 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) else { struct rtable *r = v; struct neighbour *n; - int len; + int len, HHUptod; + + rcu_read_lock(); + n = dst_get_neighbour_noref(&r->dst); + HHUptod = (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0; + rcu_read_unlock(); - n = dst_get_neighbour(&r->dst); seq_printf(seq, "%s\t%08X\t%08X\t%8X\t%d\t%u\t%d\t" "%08X\t%d\t%u\t%u\t%02X\t%d\t%1d\t%08X%n", r->dst.dev ? r->dst.dev->name : "*", @@ -432,7 +441,7 @@ static int rt_cache_seq_show(struct seq_file *seq, void *v) dst_metric(&r->dst, RTAX_RTTVAR)), r->rt_key_tos, -1, - (n && (n->nud_state & NUD_CONNECTED)) ? 1 : 0, + HHUptod, r->rt_spec_dst, &len); seq_printf(seq, "%*s\n", 127 - len, ""); @@ -825,6 +834,97 @@ static int has_noalias(const struct rtable *head, const struct rtable *rth) return ONE; } +static void rt_check_expire(void) +{ + static unsigned int rover; + unsigned int i = rover, goal; + struct rtable *rth; + struct rtable __rcu **rthp; + unsigned long samples = 0; + unsigned long sum = 0, sum2 = 0; + unsigned long delta; + u64 mult; + + delta = jiffies - expires_ljiffies; + expires_ljiffies = jiffies; + mult = ((u64)delta) << rt_hash_log; + if (ip_rt_gc_timeout > 1) + do_div(mult, ip_rt_gc_timeout); + goal = (unsigned int)mult; + if (goal > rt_hash_mask) + goal = rt_hash_mask + 1; + for (; goal > 0; goal--) { + unsigned long tmo = ip_rt_gc_timeout; + unsigned long length; + + i = (i + 1) & rt_hash_mask; + rthp = &rt_hash_table[i].chain; + + if (need_resched()) + cond_resched(); + + samples++; + + if (rcu_dereference_raw(*rthp) == NULL) + continue; + length = 0; + spin_lock_bh(rt_hash_lock_addr(i)); + 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; + rt_free(rth); + continue; + } + if (rth->dst.expires) { + /* Entry is expired even if it is in use */ + if (time_before_eq(jiffies, rth->dst.expires)) { +nofree: + tmo >>= 1; + rthp = &rth->dst.rt_next; + /* + * We only count entries on + * a chain with equal hash inputs once + * so that entries for different QOS + * levels, and other non-hash input + * attributes don't unfairly skew + * the length computation + */ + length += has_noalias(rt_hash_table[i].chain, rth); + continue; + } + } else if (!rt_may_expire(rth, tmo, ip_rt_gc_timeout)) + goto nofree; + + /* Cleanup aged off entries. */ + *rthp = rth->dst.rt_next; + rt_free(rth); + } + spin_unlock_bh(rt_hash_lock_addr(i)); + sum += length; + sum2 += length*length; + } + if (samples) { + unsigned long avg = sum / samples; + unsigned long sd = int_sqrt(sum2 / samples - avg*avg); + rt_chain_length_max = max_t(unsigned long, + ip_rt_gc_elasticity, + (avg + 4*sd) >> FRACT_BITS); + } + rover = i; +} + +/* + * rt_worker_func() is run in process context. + * we call rt_check_expire() to scan part of the hash table + */ +static void rt_worker_func(struct work_struct *work) +{ + rt_check_expire(); + schedule_delayed_work(&expires_work, ip_rt_gc_interval); +} + /* * Perturbation of rt_genid by a small quantity [1..256] * Using 8 bits of shuffling ensure we can call rt_cache_invalidate() @@ -837,6 +937,7 @@ static void rt_cache_invalidate(struct net *net) get_random_bytes(&shuffle, sizeof(shuffle)); atomic_add(shuffle + 1U, &net->ipv4.rt_genid); + redirect_genid++; } /* @@ -1013,23 +1114,18 @@ static int slow_chain_length(const struct rtable *head) static struct neighbour *ipv4_neigh_lookup(const struct dst_entry *dst, const void *daddr) { - struct neigh_table *tbl = &arp_tbl; static const __be32 inaddr_any = 0; struct net_device *dev = dst->dev; const __be32 *pkey = daddr; struct neighbour *n; -#if defined(CONFIG_ATM_CLIP) || defined(CONFIG_ATM_CLIP_MODULE) - if (dev->type == ARPHRD_ATM) - tbl = clip_tbl_hook; -#endif if (dev->flags & (IFF_LOOPBACK | IFF_POINTOPOINT)) pkey = &inaddr_any; - n = __ipv4_neigh_lookup(tbl, dev, *(__force u32 *)pkey); + n = __ipv4_neigh_lookup(&arp_tbl, dev, *(__force u32 *)pkey); if (n) return n; - return neigh_create(tbl, pkey, dev); + return neigh_create(&arp_tbl, pkey, dev); } static int rt_bind_neighbour(struct rtable *rt) @@ -1265,7 +1361,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) { struct rtable *rt = (struct rtable *) dst; - if (rt) { + if (rt && !(rt->dst.flags & DST_NOPEER)) { if (rt->peer == NULL) rt_bind_peer(rt, rt->rt_dst, 1); @@ -1276,7 +1372,7 @@ void __ip_select_ident(struct iphdr *iph, struct dst_entry *dst, int more) iph->id = htons(inet_getid(rt->peer, more)); return; } - } else + } else if (!rt) printk(KERN_DEBUG "rt_bind_peer(0) @%p\n", __builtin_return_address(0)); @@ -1304,16 +1400,40 @@ static void rt_del(unsigned hash, struct rtable *rt) spin_unlock_bh(rt_hash_lock_addr(hash)); } +static void check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) +{ + struct rtable *rt = (struct rtable *) dst; + __be32 orig_gw = rt->rt_gateway; + struct neighbour *n, *old_n; + + dst_confirm(&rt->dst); + + rt->rt_gateway = peer->redirect_learned.a4; + + n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); + if (IS_ERR(n)) { + rt->rt_gateway = orig_gw; + return; + } + old_n = xchg(&rt->dst._neighbour, n); + if (old_n) + neigh_release(old_n); + if (!(n->nud_state & NUD_VALID)) { + neigh_event_send(n, NULL); + } else { + rt->rt_flags |= RTCF_REDIRECTED; + call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); + } +} + /* called in rcu_read_lock() section */ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, __be32 saddr, struct net_device *dev) { int s, i; struct in_device *in_dev = __in_dev_get_rcu(dev); - struct rtable *rt; __be32 skeys[2] = { saddr, 0 }; int ikeys[2] = { dev->ifindex, 0 }; - struct flowi4 fl4; struct inet_peer *peer; struct net *net; @@ -1336,33 +1456,44 @@ void ip_rt_redirect(__be32 old_gw, __be32 daddr, __be32 new_gw, goto reject_redirect; } - memset(&fl4, 0, sizeof(fl4)); - fl4.daddr = daddr; for (s = 0; s < 2; s++) { for (i = 0; i < 2; i++) { - fl4.flowi4_oif = ikeys[i]; - fl4.saddr = skeys[s]; - rt = __ip_route_output_key(net, &fl4); - if (IS_ERR(rt)) - continue; - - if (rt->dst.error || rt->dst.dev != dev || - rt->rt_gateway != old_gw) { - ip_rt_put(rt); - continue; - } - - if (!rt->peer) - rt_bind_peer(rt, rt->rt_dst, 1); + unsigned int hash; + struct rtable __rcu **rthp; + struct rtable *rt; + + hash = rt_hash(daddr, skeys[s], ikeys[i], rt_genid(net)); + + rthp = &rt_hash_table[hash].chain; + + while ((rt = rcu_dereference(*rthp)) != NULL) { + rthp = &rt->dst.rt_next; + + if (rt->rt_key_dst != daddr || + rt->rt_key_src != skeys[s] || + rt->rt_oif != ikeys[i] || + rt_is_input_route(rt) || + rt_is_expired(rt) || + !net_eq(dev_net(rt->dst.dev), net) || + rt->dst.error || + rt->dst.dev != dev || + rt->rt_gateway != old_gw) + continue; - peer = rt->peer; - if (peer) { - peer->redirect_learned.a4 = new_gw; - atomic_inc(&__rt_peer_genid); + if (!rt->peer) + rt_bind_peer(rt, rt->rt_dst, 1); + + peer = rt->peer; + if (peer) { + if (peer->redirect_learned.a4 != new_gw || + peer->redirect_genid != redirect_genid) { + peer->redirect_learned.a4 = new_gw; + peer->redirect_genid = redirect_genid; + atomic_inc(&__rt_peer_genid); + } + check_peer_redir(&rt->dst, peer); + } } - - ip_rt_put(rt); - return; } } return; @@ -1649,40 +1780,9 @@ static void ip_rt_update_pmtu(struct dst_entry *dst, u32 mtu) } } -static int check_peer_redir(struct dst_entry *dst, struct inet_peer *peer) -{ - struct rtable *rt = (struct rtable *) dst; - __be32 orig_gw = rt->rt_gateway; - struct neighbour *n, *old_n; - - dst_confirm(&rt->dst); - - rt->rt_gateway = peer->redirect_learned.a4; - - n = ipv4_neigh_lookup(&rt->dst, &rt->rt_gateway); - if (IS_ERR(n)) - return PTR_ERR(n); - old_n = xchg(&rt->dst._neighbour, n); - if (old_n) - neigh_release(old_n); - if (!n || !(n->nud_state & NUD_VALID)) { - if (n) - neigh_event_send(n, NULL); - rt->rt_gateway = orig_gw; - return -EAGAIN; - } else { - rt->rt_flags |= RTCF_REDIRECTED; - call_netevent_notifiers(NETEVENT_NEIGH_UPDATE, n); - } - return 0; -} -static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +static void ipv4_validate_peer(struct rtable *rt) { - struct rtable *rt = (struct rtable *) dst; - - if (rt_is_expired(rt)) - return NULL; if (rt->rt_peer_genid != rt_peer_genid()) { struct inet_peer *peer; @@ -1691,17 +1791,26 @@ static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) peer = rt->peer; if (peer) { - check_peer_pmtu(dst, peer); + check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && - peer->redirect_learned.a4 != rt->rt_gateway) { - if (check_peer_redir(dst, peer)) - return NULL; - } + peer->redirect_learned.a4 != rt->rt_gateway) + check_peer_redir(&rt->dst, peer); } rt->rt_peer_genid = rt_peer_genid(); } +} + +static struct dst_entry *ipv4_dst_check(struct dst_entry *dst, u32 cookie) +{ + struct rtable *rt = (struct rtable *) dst; + + if (rt_is_expired(rt)) + return NULL; + ipv4_validate_peer(rt); return dst; } @@ -1806,12 +1915,17 @@ static unsigned int ipv4_default_advmss(const struct dst_entry *dst) return advmss; } -static unsigned int ipv4_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_mtu(const struct dst_entry *dst) { - unsigned int mtu = dst->dev->mtu; + const struct rtable *rt = (const struct rtable *) dst; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + if (mtu && rt_is_output_route(rt)) + return mtu; + + mtu = dst->dev->mtu; if (unlikely(dst_metric_locked(dst, RTAX_MTU))) { - const struct rtable *rt = (const struct rtable *) dst; if (rt->rt_gateway != rt->rt_dst && mtu > 576) mtu = 576; @@ -1844,6 +1958,8 @@ static void rt_init_metrics(struct rtable *rt, const struct flowi4 *fl4, dst_init_metrics(&rt->dst, peer->metrics, false); check_peer_pmtu(&rt->dst, peer); + if (peer->redirect_genid != redirect_genid) + peer->redirect_learned.a4 = 0; if (peer->redirect_learned.a4 && peer->redirect_learned.a4 != rt->rt_gateway) { rt->rt_gateway = peer->redirect_learned.a4; @@ -2349,6 +2465,7 @@ int ip_route_input_common(struct sk_buff *skb, __be32 daddr, __be32 saddr, rth->rt_mark == skb->mark && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + ipv4_validate_peer(rth); if (noref) { dst_use_noref(&rth->dst, jiffies); skb_dst_set_noref(skb, &rth->dst); @@ -2407,11 +2524,11 @@ EXPORT_SYMBOL(ip_route_input_common); static struct rtable *__mkroute_output(const struct fib_result *res, const struct flowi4 *fl4, __be32 orig_daddr, __be32 orig_saddr, - int orig_oif, struct net_device *dev_out, + int orig_oif, __u8 orig_rtos, + struct net_device *dev_out, unsigned int flags) { struct fib_info *fi = res->fi; - u32 tos = RT_FL_TOS(fl4); struct in_device *in_dev; u16 type = res->type; struct rtable *rth; @@ -2462,7 +2579,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, rth->rt_genid = rt_genid(dev_net(dev_out)); rth->rt_flags = flags; rth->rt_type = type; - rth->rt_key_tos = tos; + rth->rt_key_tos = orig_rtos; rth->rt_dst = fl4->daddr; rth->rt_src = fl4->saddr; rth->rt_route_iif = 0; @@ -2512,7 +2629,7 @@ static struct rtable *__mkroute_output(const struct fib_result *res, static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) { struct net_device *dev_out = NULL; - u32 tos = RT_FL_TOS(fl4); + __u8 tos = RT_FL_TOS(fl4); unsigned int flags = 0; struct fib_result res; struct rtable *rth; @@ -2688,7 +2805,7 @@ static struct rtable *ip_route_output_slow(struct net *net, struct flowi4 *fl4) make_route: rth = __mkroute_output(&res, fl4, orig_daddr, orig_saddr, orig_oif, - dev_out, flags); + tos, dev_out, flags); if (!IS_ERR(rth)) { unsigned int hash; @@ -2724,6 +2841,7 @@ struct rtable *__ip_route_output_key(struct net *net, struct flowi4 *flp4) (IPTOS_RT_MASK | RTO_ONLINK)) && net_eq(dev_net(rth->dst.dev), net) && !rt_is_expired(rth)) { + ipv4_validate_peer(rth); dst_use(&rth->dst, jiffies); RT_CACHE_STAT_INC(out_hit); rcu_read_unlock_bh(); @@ -2747,9 +2865,11 @@ static struct dst_entry *ipv4_blackhole_dst_check(struct dst_entry *dst, u32 coo return NULL; } -static unsigned int ipv4_blackhole_default_mtu(const struct dst_entry *dst) +static unsigned int ipv4_blackhole_mtu(const struct dst_entry *dst) { - return 0; + unsigned int mtu = dst_metric_raw(dst, RTAX_MTU); + + return mtu ? : dst->dev->mtu; } static void ipv4_rt_blackhole_update_pmtu(struct dst_entry *dst, u32 mtu) @@ -2767,7 +2887,7 @@ static struct dst_ops ipv4_dst_blackhole_ops = { .protocol = cpu_to_be16(ETH_P_IP), .destroy = ipv4_dst_destroy, .check = ipv4_blackhole_dst_check, - .default_mtu = ipv4_blackhole_default_mtu, + .mtu = ipv4_blackhole_mtu, .default_advmss = ipv4_default_advmss, .update_pmtu = ipv4_rt_blackhole_update_pmtu, .cow_metrics = ipv4_rt_blackhole_cow_metrics, @@ -2845,7 +2965,7 @@ static int rt_fill_info(struct net *net, struct rtable *rt = skb_rtable(skb); struct rtmsg *r; struct nlmsghdr *nlh; - long expires = 0; + unsigned long expires = 0; const struct inet_peer *peer = rt->peer; u32 id = 0, ts = 0, tsage = 0, error; @@ -2902,8 +3022,12 @@ static int rt_fill_info(struct net *net, tsage = get_seconds() - peer->tcp_ts_stamp; } expires = ACCESS_ONCE(peer->pmtu_expires); - if (expires) - expires -= jiffies; + if (expires) { + if (time_before(jiffies, expires)) + expires -= jiffies; + else + expires = 0; + } } if (rt_is_input_route(rt)) { @@ -3145,6 +3269,13 @@ static ctl_table ipv4_route_table[] = { .proc_handler = proc_dointvec_jiffies, }, { + .procname = "gc_interval", + .data = &ip_rt_gc_interval, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec_jiffies, + }, + { .procname = "redirect_load", .data = &ip_rt_redirect_load, .maxlen = sizeof(int), @@ -3354,6 +3485,11 @@ int __init ip_rt_init(void) devinet_init(); ip_fib_init(); + INIT_DELAYED_WORK_DEFERRABLE(&expires_work, rt_worker_func); + expires_ljiffies = jiffies; + schedule_delayed_work(&expires_work, + net_random() % ip_rt_gc_interval + ip_rt_gc_interval); + if (ip_rt_proc_init()) printk(KERN_ERR "Unable to create route proc files\n"); #ifdef CONFIG_XFRM diff --git a/net/ipv4/syncookies.c b/net/ipv4/syncookies.c index 90f6544c13e..51fdbb49043 100644 --- a/net/ipv4/syncookies.c +++ b/net/ipv4/syncookies.c @@ -245,7 +245,7 @@ bool cookie_check_timestamp(struct tcp_options_received *tcp_opt, bool *ecn_ok) if (!sysctl_tcp_timestamps) return false; - tcp_opt->sack_ok = (options >> 4) & 0x1; + tcp_opt->sack_ok = (options & (1 << 4)) ? TCP_SACK_SEEN : 0; *ecn_ok = (options >> 5) & 1; if (*ecn_ok && !sysctl_tcp_ecn) return false; diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 69fd7201129..4aa7e9dc0cb 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -14,6 +14,7 @@ #include <linux/init.h> #include <linux/slab.h> #include <linux/nsproxy.h> +#include <linux/swap.h> #include <net/snmp.h> #include <net/icmp.h> #include <net/ip.h> @@ -23,6 +24,7 @@ #include <net/cipso_ipv4.h> #include <net/inet_frag.h> #include <net/ping.h> +#include <net/tcp_memcontrol.h> static int zero; static int tcp_retr1_max = 255; @@ -73,7 +75,7 @@ static int ipv4_local_port_range(ctl_table *table, int write, } -void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high) +static void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t *high) { gid_t *data = table->data; unsigned seq; @@ -86,7 +88,7 @@ void inet_get_ping_group_range_table(struct ctl_table *table, gid_t *low, gid_t } /* Update system visible IP port range */ -static void set_ping_group_range(struct ctl_table *table, int range[2]) +static void set_ping_group_range(struct ctl_table *table, gid_t range[2]) { gid_t *data = table->data; write_seqlock(&sysctl_local_ports.lock); @@ -174,6 +176,49 @@ static int proc_allowed_congestion_control(ctl_table *ctl, return ret; } +static int ipv4_tcp_mem(ctl_table *ctl, int write, + void __user *buffer, size_t *lenp, + loff_t *ppos) +{ + int ret; + unsigned long vec[3]; + struct net *net = current->nsproxy->net_ns; +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + struct mem_cgroup *memcg; +#endif + + ctl_table tmp = { + .data = &vec, + .maxlen = sizeof(vec), + .mode = ctl->mode, + }; + + if (!write) { + ctl->data = &net->ipv4.sysctl_tcp_mem; + return proc_doulongvec_minmax(ctl, write, buffer, lenp, ppos); + } + + ret = proc_doulongvec_minmax(&tmp, write, buffer, lenp, ppos); + if (ret) + return ret; + +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + rcu_read_lock(); + memcg = mem_cgroup_from_task(current); + + tcp_prot_mem(memcg, vec[0], 0); + tcp_prot_mem(memcg, vec[1], 1); + tcp_prot_mem(memcg, vec[2], 2); + rcu_read_unlock(); +#endif + + net->ipv4.sysctl_tcp_mem[0] = vec[0]; + net->ipv4.sysctl_tcp_mem[1] = vec[1]; + net->ipv4.sysctl_tcp_mem[2] = vec[2]; + + return 0; +} + static struct ctl_table ipv4_table[] = { { .procname = "tcp_timestamps", @@ -433,13 +478,6 @@ static struct ctl_table ipv4_table[] = { .proc_handler = proc_dointvec }, { - .procname = "tcp_mem", - .data = &sysctl_tcp_mem, - .maxlen = sizeof(sysctl_tcp_mem), - .mode = 0644, - .proc_handler = proc_doulongvec_minmax - }, - { .procname = "tcp_wmem", .data = &sysctl_tcp_wmem, .maxlen = sizeof(sysctl_tcp_wmem), @@ -721,6 +759,12 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = ipv4_ping_group_range, }, + { + .procname = "tcp_mem", + .maxlen = sizeof(init_net.ipv4.sysctl_tcp_mem), + .mode = 0644, + .proc_handler = ipv4_tcp_mem, + }, { } }; @@ -734,6 +778,7 @@ EXPORT_SYMBOL_GPL(net_ipv4_ctl_path); static __net_init int ipv4_sysctl_init_net(struct net *net) { struct ctl_table *table; + unsigned long limit; table = ipv4_net_table; if (!net_eq(net, &init_net)) { @@ -769,6 +814,12 @@ static __net_init int ipv4_sysctl_init_net(struct net *net) net->ipv4.sysctl_rt_cache_rebuild_count = 4; + limit = nr_free_buffer_pages() / 8; + limit = max(limit, 128UL); + net->ipv4.sysctl_tcp_mem[0] = limit / 4 * 3; + net->ipv4.sysctl_tcp_mem[1] = limit; + net->ipv4.sysctl_tcp_mem[2] = net->ipv4.sysctl_tcp_mem[0] * 2; + net->ipv4.ipv4_hdr = register_net_sysctl_table(net, net_ipv4_ctl_path, table); if (net->ipv4.ipv4_hdr == NULL) diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 34f5db1e1c8..9bcdec3ad77 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -282,11 +282,9 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); -long sysctl_tcp_mem[3] __read_mostly; int sysctl_tcp_wmem[3] __read_mostly; int sysctl_tcp_rmem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_tcp_mem); EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); @@ -888,18 +886,18 @@ int tcp_sendpage(struct sock *sk, struct page *page, int offset, } EXPORT_SYMBOL(tcp_sendpage); -#define TCP_PAGE(sk) (sk->sk_sndmsg_page) -#define TCP_OFF(sk) (sk->sk_sndmsg_off) - -static inline int select_size(const struct sock *sk, int sg) +static inline int select_size(const struct sock *sk, bool sg) { const struct tcp_sock *tp = tcp_sk(sk); int tmp = tp->mss_cache; if (sg) { - if (sk_can_gso(sk)) - tmp = 0; - else { + if (sk_can_gso(sk)) { + /* Small frames wont use a full page: + * Payload will immediately follow tcp header. + */ + tmp = SKB_WITH_OVERHEAD(2048 - MAX_TCP_HEADER); + } else { int pgbreak = SKB_MAX_HEAD(MAX_TCP_HEADER); if (tmp >= pgbreak && @@ -917,9 +915,9 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct iovec *iov; struct tcp_sock *tp = tcp_sk(sk); struct sk_buff *skb; - int iovlen, flags; + int iovlen, flags, err, copied; int mss_now, size_goal; - int sg, err, copied; + bool sg; long timeo; lock_sock(sk); @@ -946,7 +944,7 @@ int tcp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN)) goto out_err; - sg = sk->sk_route_caps & NETIF_F_SG; + sg = !!(sk->sk_route_caps & NETIF_F_SG); while (--iovlen >= 0) { size_t seglen = iov->iov_len; @@ -1005,8 +1003,13 @@ new_segment: } else { int merge = 0; int i = skb_shinfo(skb)->nr_frags; - struct page *page = TCP_PAGE(sk); - int off = TCP_OFF(sk); + struct page *page = sk->sk_sndmsg_page; + int off; + + if (page && page_count(page) == 1) + sk->sk_sndmsg_off = 0; + + off = sk->sk_sndmsg_off; if (skb_can_coalesce(skb, i, page, off) && off != PAGE_SIZE) { @@ -1023,7 +1026,7 @@ new_segment: } else if (page) { if (off == PAGE_SIZE) { put_page(page); - TCP_PAGE(sk) = page = NULL; + sk->sk_sndmsg_page = page = NULL; off = 0; } } else @@ -1049,9 +1052,9 @@ new_segment: /* If this page was new, give it to the * socket so it does not get leaked. */ - if (!TCP_PAGE(sk)) { - TCP_PAGE(sk) = page; - TCP_OFF(sk) = 0; + if (!sk->sk_sndmsg_page) { + sk->sk_sndmsg_page = page; + sk->sk_sndmsg_off = 0; } goto do_error; } @@ -1061,15 +1064,15 @@ new_segment: skb_frag_size_add(&skb_shinfo(skb)->frags[i - 1], copy); } else { skb_fill_page_desc(skb, i, page, off, copy); - if (TCP_PAGE(sk)) { + if (sk->sk_sndmsg_page) { get_page(page); } else if (off + copy < PAGE_SIZE) { get_page(page); - TCP_PAGE(sk) = page; + sk->sk_sndmsg_page = page; } } - TCP_OFF(sk) = off + copy; + sk->sk_sndmsg_off = off + copy; } if (!copied) @@ -2653,7 +2656,8 @@ int compat_tcp_getsockopt(struct sock *sk, int level, int optname, EXPORT_SYMBOL(compat_tcp_getsockopt); #endif -struct sk_buff *tcp_tso_segment(struct sk_buff *skb, u32 features) +struct sk_buff *tcp_tso_segment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); struct tcphdr *th; @@ -3272,14 +3276,9 @@ void __init tcp_init(void) sysctl_tcp_max_orphans = cnt / 2; sysctl_max_syn_backlog = max(128, cnt / 256); - limit = nr_free_buffer_pages() / 8; - limit = max(limit, 128UL); - sysctl_tcp_mem[0] = limit / 4 * 3; - sysctl_tcp_mem[1] = limit; - sysctl_tcp_mem[2] = sysctl_tcp_mem[0] * 2; - /* Set per-socket limits to no more than 1/128 the pressure threshold */ - limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7); + limit = ((unsigned long)init_net.ipv4.sysctl_tcp_mem[1]) + << (PAGE_SHIFT - 7); max_share = min(4UL*1024*1024, limit); sysctl_tcp_wmem[0] = SK_MEM_QUANTUM; diff --git a/net/ipv4/tcp_cong.c b/net/ipv4/tcp_cong.c index 850c737e08e..fc6d475f488 100644 --- a/net/ipv4/tcp_cong.c +++ b/net/ipv4/tcp_cong.c @@ -292,7 +292,7 @@ int tcp_is_cwnd_limited(const struct sock *sk, u32 in_flight) left * sysctl_tcp_tso_win_divisor < tp->snd_cwnd && left * tp->mss_cache < sk->sk_gso_max_size) return 1; - return left <= tcp_max_burst(tp); + return left <= tcp_max_tso_deferred_mss(tp); } EXPORT_SYMBOL_GPL(tcp_is_cwnd_limited); diff --git a/net/ipv4/tcp_diag.c b/net/ipv4/tcp_diag.c index 939edb3b8e4..8cd357a8be7 100644 --- a/net/ipv4/tcp_diag.c +++ b/net/ipv4/tcp_diag.c @@ -34,11 +34,23 @@ static void tcp_diag_get_info(struct sock *sk, struct inet_diag_msg *r, tcp_get_info(sk, info); } +static void tcp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct inet_diag_req *r, struct nlattr *bc) +{ + inet_diag_dump_icsk(&tcp_hashinfo, skb, cb, r, bc); +} + +static int tcp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, + struct inet_diag_req *req) +{ + return inet_diag_dump_one_icsk(&tcp_hashinfo, in_skb, nlh, req); +} + static const struct inet_diag_handler tcp_diag_handler = { - .idiag_hashinfo = &tcp_hashinfo, + .dump = tcp_diag_dump, + .dump_one = tcp_diag_dump_one, .idiag_get_info = tcp_diag_get_info, - .idiag_type = TCPDIAG_GETSOCK, - .idiag_info_size = sizeof(struct tcp_info), + .idiag_type = IPPROTO_TCP, }; static int __init tcp_diag_init(void) @@ -54,4 +66,4 @@ static void __exit tcp_diag_exit(void) module_init(tcp_diag_init); module_exit(tcp_diag_exit); MODULE_LICENSE("GPL"); -MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_INET_DIAG, TCPDIAG_GETSOCK); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-6 /* AF_INET - IPPROTO_TCP */); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 52b5c2d0ecd..2877c3e0958 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -322,7 +322,7 @@ static void tcp_grow_window(struct sock *sk, const struct sk_buff *skb) /* Check #1 */ if (tp->rcv_ssthresh < tp->window_clamp && (int)tp->rcv_ssthresh < tcp_space(sk) && - !tcp_memory_pressure) { + !sk_under_memory_pressure(sk)) { int incr; /* Check #2. Increase window, if skb with such overhead @@ -411,8 +411,8 @@ static void tcp_clamp_window(struct sock *sk) if (sk->sk_rcvbuf < sysctl_tcp_rmem[2] && !(sk->sk_userlocks & SOCK_RCVBUF_LOCK) && - !tcp_memory_pressure && - atomic_long_read(&tcp_memory_allocated) < sysctl_tcp_mem[0]) { + !sk_under_memory_pressure(sk) && + sk_memory_allocated(sk) < sk_prot_mem_limits(sk, 0)) { sk->sk_rcvbuf = min(atomic_read(&sk->sk_rmem_alloc), sysctl_tcp_rmem[2]); } @@ -865,13 +865,13 @@ static void tcp_disable_fack(struct tcp_sock *tp) /* RFC3517 uses different metric in lost marker => reset on change */ if (tcp_is_fack(tp)) tp->lost_skb_hint = NULL; - tp->rx_opt.sack_ok &= ~2; + tp->rx_opt.sack_ok &= ~TCP_FACK_ENABLED; } /* Take a notice that peer is sending D-SACKs */ static void tcp_dsack_seen(struct tcp_sock *tp) { - tp->rx_opt.sack_ok |= 4; + tp->rx_opt.sack_ok |= TCP_DSACK_SEEN; } /* Initialize metrics on socket. */ @@ -2663,7 +2663,7 @@ static void DBGUNDO(struct sock *sk, const char *msg) tp->snd_ssthresh, tp->prior_ssthresh, tp->packets_out); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); printk(KERN_DEBUG "Undo %s %pI6/%u c%u l%u ss%u/%u p%u\n", @@ -2858,7 +2858,7 @@ static void tcp_try_keep_open(struct sock *sk) struct tcp_sock *tp = tcp_sk(sk); int state = TCP_CA_Open; - if (tcp_left_out(tp) || tcp_any_retrans_done(sk) || tp->undo_marker) + if (tcp_left_out(tp) || tcp_any_retrans_done(sk)) state = TCP_CA_Disorder; if (inet_csk(sk)->icsk_ca_state != state) { @@ -2881,7 +2881,8 @@ static void tcp_try_to_open(struct sock *sk, int flag) if (inet_csk(sk)->icsk_ca_state != TCP_CA_CWR) { tcp_try_keep_open(sk); - tcp_moderate_cwnd(tp); + if (inet_csk(sk)->icsk_ca_state != TCP_CA_Open) + tcp_moderate_cwnd(tp); } else { tcp_cwnd_down(sk, flag); } @@ -3009,11 +3010,11 @@ static void tcp_update_cwnd_in_recovery(struct sock *sk, int newly_acked_sacked, * tcp_xmit_retransmit_queue(). */ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, - int newly_acked_sacked, int flag) + int newly_acked_sacked, bool is_dupack, + int flag) { struct inet_connection_sock *icsk = inet_csk(sk); struct tcp_sock *tp = tcp_sk(sk); - int is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); int do_lost = is_dupack || ((flag & FLAG_DATA_SACKED) && (tcp_fackets_out(tp) > tp->reordering)); int fast_rexmit = 0, mib_idx; @@ -3066,17 +3067,6 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, } break; - case TCP_CA_Disorder: - tcp_try_undo_dsack(sk); - if (!tp->undo_marker || - /* For SACK case do not Open to allow to undo - * catching for all duplicate ACKs. */ - tcp_is_reno(tp) || tp->snd_una != tp->high_seq) { - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Open); - } - break; - case TCP_CA_Recovery: if (tcp_is_reno(tp)) tcp_reset_reno_sack(tp); @@ -3117,7 +3107,7 @@ static void tcp_fastretrans_alert(struct sock *sk, int pkts_acked, tcp_add_reno_sack(sk); } - if (icsk->icsk_ca_state == TCP_CA_Disorder) + if (icsk->icsk_ca_state <= TCP_CA_Disorder) tcp_try_undo_dsack(sk); if (!tcp_time_to_recover(sk)) { @@ -3681,10 +3671,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) u32 prior_snd_una = tp->snd_una; u32 ack_seq = TCP_SKB_CB(skb)->seq; u32 ack = TCP_SKB_CB(skb)->ack_seq; + bool is_dupack = false; u32 prior_in_flight; u32 prior_fackets; int prior_packets; int prior_sacked = tp->sacked_out; + int pkts_acked = 0; int newly_acked_sacked = 0; int frto_cwnd = 0; @@ -3757,6 +3749,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) /* See if we can take anything off of the retransmit queue. */ flag |= tcp_clean_rtx_queue(sk, prior_fackets, prior_snd_una); + pkts_acked = prior_packets - tp->packets_out; newly_acked_sacked = (prior_packets - prior_sacked) - (tp->packets_out - tp->sacked_out); @@ -3771,8 +3764,9 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if ((flag & FLAG_DATA_ACKED) && !frto_cwnd && tcp_may_raise_cwnd(sk, flag)) tcp_cong_avoid(sk, ack, prior_in_flight); - tcp_fastretrans_alert(sk, prior_packets - tp->packets_out, - newly_acked_sacked, flag); + is_dupack = !(flag & (FLAG_SND_UNA_ADVANCED | FLAG_NOT_DUP)); + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); } else { if ((flag & FLAG_DATA_ACKED) && !frto_cwnd) tcp_cong_avoid(sk, ack, prior_in_flight); @@ -3784,6 +3778,10 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) return 1; no_queue: + /* If data was DSACKed, see if we can undo a cwnd reduction. */ + if (flag & FLAG_DSACKING_ACK) + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3797,10 +3795,14 @@ invalid_ack: return -1; old_ack: + /* If data was SACKed, tag it and see if we should send more data. + * If data was DSACKed, see if we can undo a cwnd reduction. + */ if (TCP_SKB_CB(skb)->sacked) { - tcp_sacktag_write_queue(sk, skb, prior_snd_una); - if (icsk->icsk_ca_state == TCP_CA_Open) - tcp_try_keep_open(sk); + flag |= tcp_sacktag_write_queue(sk, skb, prior_snd_una); + newly_acked_sacked = tp->sacked_out - prior_sacked; + tcp_fastretrans_alert(sk, pkts_acked, newly_acked_sacked, + is_dupack, flag); } SOCK_DEBUG(sk, "Ack %u before %u:%u\n", ack, tp->snd_una, tp->snd_nxt); @@ -3876,7 +3878,7 @@ void tcp_parse_options(const struct sk_buff *skb, struct tcp_options_received *o case TCPOPT_SACK_PERM: if (opsize == TCPOLEN_SACK_PERM && th->syn && !estab && sysctl_tcp_sack) { - opt_rx->sack_ok = 1; + opt_rx->sack_ok = TCP_SACK_SEEN; tcp_sack_reset(opt_rx); } break; @@ -4864,7 +4866,7 @@ static int tcp_prune_queue(struct sock *sk) if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf) tcp_clamp_window(sk); - else if (tcp_memory_pressure) + else if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); tcp_collapse_ofo_queue(sk); @@ -4930,11 +4932,11 @@ static int tcp_should_expand_sndbuf(const struct sock *sk) return 0; /* If we are under global TCP memory pressure, do not expand. */ - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) return 0; /* If we are under soft global TCP memory pressure, do not expand. */ - if (atomic_long_read(&tcp_memory_allocated) >= sysctl_tcp_mem[0]) + if (sk_memory_allocated(sk) >= sk_prot_mem_limits(sk, 0)) return 0; /* If we filled the congestion window, do not expand. */ @@ -5809,6 +5811,8 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb, goto discard; if (th->syn) { + if (th->fin) + goto discard; if (icsk->icsk_af_ops->conn_request(sk, skb) < 0) return 1; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index a7443159c40..1eb4ad57670 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -73,6 +73,7 @@ #include <net/xfrm.h> #include <net/netdma.h> #include <net/secure_seq.h> +#include <net/tcp_memcontrol.h> #include <linux/inet.h> #include <linux/ipv6.h> @@ -1510,6 +1511,8 @@ exit: NET_INC_STATS_BH(sock_net(sk), LINUX_MIB_LISTENDROPS); return NULL; put_and_exit: + tcp_clear_xmit_timers(newsk); + tcp_cleanup_congestion_control(newsk); bh_unlock_sock(newsk); sock_put(newsk); goto exit; @@ -1915,7 +1918,8 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_rcvbuf = sysctl_tcp_rmem[1]; local_bh_disable(); - percpu_counter_inc(&tcp_sockets_allocated); + sock_update_memcg(sk); + sk_sockets_allocated_inc(sk); local_bh_enable(); return 0; @@ -1971,7 +1975,8 @@ void tcp_v4_destroy_sock(struct sock *sk) tp->cookie_values = NULL; } - percpu_counter_dec(&tcp_sockets_allocated); + sk_sockets_allocated_dec(sk); + sock_release_memcg(sk); } EXPORT_SYMBOL(tcp_v4_destroy_sock); @@ -2618,7 +2623,6 @@ struct proto tcp_prot = { .orphan_count = &tcp_orphan_count, .memory_allocated = &tcp_memory_allocated, .memory_pressure = &tcp_memory_pressure, - .sysctl_mem = sysctl_tcp_mem, .sysctl_wmem = sysctl_tcp_wmem, .sysctl_rmem = sysctl_tcp_rmem, .max_header = MAX_TCP_HEADER, @@ -2632,10 +2636,14 @@ struct proto tcp_prot = { .compat_setsockopt = compat_tcp_setsockopt, .compat_getsockopt = compat_tcp_getsockopt, #endif +#ifdef CONFIG_CGROUP_MEM_RES_CTLR_KMEM + .init_cgroup = tcp_init_cgroup, + .destroy_cgroup = tcp_destroy_cgroup, + .proto_cgroup = tcp_proto_cgroup, +#endif }; EXPORT_SYMBOL(tcp_prot); - static int __net_init tcp_sk_init(struct net *net) { return inet_ctl_sock_create(&net->ipv4.tcp_sock, diff --git a/net/ipv4/tcp_memcontrol.c b/net/ipv4/tcp_memcontrol.c new file mode 100644 index 00000000000..7fed04f875c --- /dev/null +++ b/net/ipv4/tcp_memcontrol.c @@ -0,0 +1,272 @@ +#include <net/tcp.h> +#include <net/tcp_memcontrol.h> +#include <net/sock.h> +#include <net/ip.h> +#include <linux/nsproxy.h> +#include <linux/memcontrol.h> +#include <linux/module.h> + +static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft); +static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft, + const char *buffer); +static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event); + +static struct cftype tcp_files[] = { + { + .name = "kmem.tcp.limit_in_bytes", + .write_string = tcp_cgroup_write, + .read_u64 = tcp_cgroup_read, + .private = RES_LIMIT, + }, + { + .name = "kmem.tcp.usage_in_bytes", + .read_u64 = tcp_cgroup_read, + .private = RES_USAGE, + }, + { + .name = "kmem.tcp.failcnt", + .private = RES_FAILCNT, + .trigger = tcp_cgroup_reset, + .read_u64 = tcp_cgroup_read, + }, + { + .name = "kmem.tcp.max_usage_in_bytes", + .private = RES_MAX_USAGE, + .trigger = tcp_cgroup_reset, + .read_u64 = tcp_cgroup_read, + }, +}; + +static inline struct tcp_memcontrol *tcp_from_cgproto(struct cg_proto *cg_proto) +{ + return container_of(cg_proto, struct tcp_memcontrol, cg_proto); +} + +static void memcg_tcp_enter_memory_pressure(struct sock *sk) +{ + if (sk->sk_cgrp->memory_pressure) + *sk->sk_cgrp->memory_pressure = 1; +} +EXPORT_SYMBOL(memcg_tcp_enter_memory_pressure); + +int tcp_init_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + /* + * The root cgroup does not use res_counters, but rather, + * rely on the data already collected by the network + * subsystem + */ + struct res_counter *res_parent = NULL; + struct cg_proto *cg_proto, *parent_cg; + struct tcp_memcontrol *tcp; + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct net *net = current->nsproxy->net_ns; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + goto create_files; + + tcp = tcp_from_cgproto(cg_proto); + + tcp->tcp_prot_mem[0] = net->ipv4.sysctl_tcp_mem[0]; + tcp->tcp_prot_mem[1] = net->ipv4.sysctl_tcp_mem[1]; + tcp->tcp_prot_mem[2] = net->ipv4.sysctl_tcp_mem[2]; + tcp->tcp_memory_pressure = 0; + + parent_cg = tcp_prot.proto_cgroup(parent); + if (parent_cg) + res_parent = parent_cg->memory_allocated; + + res_counter_init(&tcp->tcp_memory_allocated, res_parent); + percpu_counter_init(&tcp->tcp_sockets_allocated, 0); + + cg_proto->enter_memory_pressure = memcg_tcp_enter_memory_pressure; + cg_proto->memory_pressure = &tcp->tcp_memory_pressure; + cg_proto->sysctl_mem = tcp->tcp_prot_mem; + cg_proto->memory_allocated = &tcp->tcp_memory_allocated; + cg_proto->sockets_allocated = &tcp->tcp_sockets_allocated; + cg_proto->memcg = memcg; + +create_files: + return cgroup_add_files(cgrp, ss, tcp_files, + ARRAY_SIZE(tcp_files)); +} +EXPORT_SYMBOL(tcp_init_cgroup); + +void tcp_destroy_cgroup(struct cgroup *cgrp, struct cgroup_subsys *ss) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cgrp); + struct cg_proto *cg_proto; + struct tcp_memcontrol *tcp; + u64 val; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return; + + tcp = tcp_from_cgproto(cg_proto); + percpu_counter_destroy(&tcp->tcp_sockets_allocated); + + val = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE); + + if (val != RESOURCE_MAX) + jump_label_dec(&memcg_socket_limit_enabled); +} +EXPORT_SYMBOL(tcp_destroy_cgroup); + +static int tcp_update_limit(struct mem_cgroup *memcg, u64 val) +{ + struct net *net = current->nsproxy->net_ns; + struct tcp_memcontrol *tcp; + struct cg_proto *cg_proto; + u64 old_lim; + int i; + int ret; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return -EINVAL; + + if (val > RESOURCE_MAX) + val = RESOURCE_MAX; + + tcp = tcp_from_cgproto(cg_proto); + + old_lim = res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); + ret = res_counter_set_limit(&tcp->tcp_memory_allocated, val); + if (ret) + return ret; + + for (i = 0; i < 3; i++) + tcp->tcp_prot_mem[i] = min_t(long, val >> PAGE_SHIFT, + net->ipv4.sysctl_tcp_mem[i]); + + if (val == RESOURCE_MAX && old_lim != RESOURCE_MAX) + jump_label_dec(&memcg_socket_limit_enabled); + else if (old_lim == RESOURCE_MAX && val != RESOURCE_MAX) + jump_label_inc(&memcg_socket_limit_enabled); + + return 0; +} + +static int tcp_cgroup_write(struct cgroup *cont, struct cftype *cft, + const char *buffer) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + unsigned long long val; + int ret = 0; + + switch (cft->private) { + case RES_LIMIT: + /* see memcontrol.c */ + ret = res_counter_memparse_write_strategy(buffer, &val); + if (ret) + break; + ret = tcp_update_limit(memcg, val); + break; + default: + ret = -EINVAL; + break; + } + return ret; +} + +static u64 tcp_read_stat(struct mem_cgroup *memcg, int type, u64 default_val) +{ + struct tcp_memcontrol *tcp; + struct cg_proto *cg_proto; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return default_val; + + tcp = tcp_from_cgproto(cg_proto); + return res_counter_read_u64(&tcp->tcp_memory_allocated, type); +} + +static u64 tcp_read_usage(struct mem_cgroup *memcg) +{ + struct tcp_memcontrol *tcp; + struct cg_proto *cg_proto; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return atomic_long_read(&tcp_memory_allocated) << PAGE_SHIFT; + + tcp = tcp_from_cgproto(cg_proto); + return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_USAGE); +} + +static u64 tcp_cgroup_read(struct cgroup *cont, struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + u64 val; + + switch (cft->private) { + case RES_LIMIT: + val = tcp_read_stat(memcg, RES_LIMIT, RESOURCE_MAX); + break; + case RES_USAGE: + val = tcp_read_usage(memcg); + break; + case RES_FAILCNT: + case RES_MAX_USAGE: + val = tcp_read_stat(memcg, cft->private, 0); + break; + default: + BUG(); + } + return val; +} + +static int tcp_cgroup_reset(struct cgroup *cont, unsigned int event) +{ + struct mem_cgroup *memcg; + struct tcp_memcontrol *tcp; + struct cg_proto *cg_proto; + + memcg = mem_cgroup_from_cont(cont); + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return 0; + tcp = tcp_from_cgproto(cg_proto); + + switch (event) { + case RES_MAX_USAGE: + res_counter_reset_max(&tcp->tcp_memory_allocated); + break; + case RES_FAILCNT: + res_counter_reset_failcnt(&tcp->tcp_memory_allocated); + break; + } + + return 0; +} + +unsigned long long tcp_max_memory(const struct mem_cgroup *memcg) +{ + struct tcp_memcontrol *tcp; + struct cg_proto *cg_proto; + + cg_proto = tcp_prot.proto_cgroup((struct mem_cgroup *)memcg); + if (!cg_proto) + return 0; + + tcp = tcp_from_cgproto(cg_proto); + return res_counter_read_u64(&tcp->tcp_memory_allocated, RES_LIMIT); +} + +void tcp_prot_mem(struct mem_cgroup *memcg, long val, int idx) +{ + struct tcp_memcontrol *tcp; + struct cg_proto *cg_proto; + + cg_proto = tcp_prot.proto_cgroup(memcg); + if (!cg_proto) + return; + + tcp = tcp_from_cgproto(cg_proto); + + tcp->tcp_prot_mem[idx] = val; +} diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 66363b689ad..550e755747e 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -336,15 +336,15 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) tcptw->tw_ts_recent = tp->rx_opt.ts_recent; tcptw->tw_ts_recent_stamp = tp->rx_opt.ts_recent_stamp; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (tw->tw_family == PF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); struct inet6_timewait_sock *tw6; tw->tw_ipv6_offset = inet6_tw_offset(sk->sk_prot); tw6 = inet6_twsk((struct sock *)tw); - ipv6_addr_copy(&tw6->tw_v6_daddr, &np->daddr); - ipv6_addr_copy(&tw6->tw_v6_rcv_saddr, &np->rcv_saddr); + tw6->tw_v6_daddr = np->daddr; + tw6->tw_v6_rcv_saddr = np->rcv_saddr; tw->tw_tclass = np->tclass; tw->tw_ipv6only = np->ipv6only; } @@ -425,7 +425,7 @@ static inline void TCP_ECN_openreq_child(struct tcp_sock *tp, */ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, struct sk_buff *skb) { - struct sock *newsk = inet_csk_clone(sk, req, GFP_ATOMIC); + struct sock *newsk = inet_csk_clone_lock(sk, req, GFP_ATOMIC); if (newsk != NULL) { const struct inet_request_sock *ireq = inet_rsk(req); @@ -495,7 +495,9 @@ struct sock *tcp_create_openreq_child(struct sock *sk, struct request_sock *req, newtp->frto_counter = 0; newtp->frto_highmark = 0; - newicsk->icsk_ca_ops = &tcp_init_congestion_ops; + if (newicsk->icsk_ca_ops != &tcp_init_congestion_ops && + !try_module_get(newicsk->icsk_ca_ops->owner)) + newicsk->icsk_ca_ops = &tcp_init_congestion_ops; tcp_set_ca_state(newsk, TCP_CA_Open); tcp_init_xmit_timers(newsk); diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 980b98f6288..8c8de2780c7 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1093,6 +1093,13 @@ static void __pskb_trim_head(struct sk_buff *skb, int len) { int i, k, eat; + eat = min_t(int, len, skb_headlen(skb)); + if (eat) { + __skb_pull(skb, eat); + len -= eat; + if (!len) + return; + } eat = len; k = 0; for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) { @@ -1124,11 +1131,7 @@ int tcp_trim_head(struct sock *sk, struct sk_buff *skb, u32 len) if (skb_cloned(skb) && pskb_expand_head(skb, 0, 0, GFP_ATOMIC)) return -ENOMEM; - /* If len == headlen, we avoid __skb_pull to preserve alignment. */ - if (unlikely(len < skb_headlen(skb))) - __skb_pull(skb, len); - else - __pskb_trim_head(skb, len - skb_headlen(skb)); + __pskb_trim_head(skb, len); TCP_SKB_CB(skb)->seq += len; skb->ip_summed = CHECKSUM_PARTIAL; @@ -1382,7 +1385,7 @@ static inline int tcp_minshall_check(const struct tcp_sock *tp) /* Return 0, if packet can be sent now without violation Nagle's rules: * 1. It is full sized. * 2. Or it contains FIN. (already checked by caller) - * 3. Or TCP_NODELAY was set. + * 3. Or TCP_CORK is not set, and TCP_NODELAY is set. * 4. Or TCP_CORK is not set, and all sent packets are ACKed. * With Minshall's modification: all sent small packets are ACKed. */ @@ -1581,7 +1584,7 @@ static int tcp_tso_should_defer(struct sock *sk, struct sk_buff *skb) * frame, so if we have space for more than 3 frames * then send now. */ - if (limit > tcp_max_burst(tp) * tp->mss_cache) + if (limit > tcp_max_tso_deferred_mss(tp) * tp->mss_cache) goto send_now; } @@ -1919,7 +1922,7 @@ u32 __tcp_select_window(struct sock *sk) if (free_space < (full_space >> 1)) { icsk->icsk_ack.quick = 0; - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) tp->rcv_ssthresh = min(tp->rcv_ssthresh, 4U * tp->advmss); @@ -2147,7 +2150,15 @@ int tcp_retransmit_skb(struct sock *sk, struct sk_buff *skb) */ TCP_SKB_CB(skb)->when = tcp_time_stamp; - err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + /* make sure skb->data is aligned on arches that require it */ + if (unlikely(NET_IP_ALIGN && ((unsigned long)skb->data & 3))) { + struct sk_buff *nskb = __pskb_copy(skb, MAX_TCP_HEADER, + GFP_ATOMIC); + err = nskb ? tcp_transmit_skb(sk, nskb, 0, GFP_ATOMIC) : + -ENOBUFS; + } else { + err = tcp_transmit_skb(sk, skb, 1, GFP_ATOMIC); + } if (err == 0) { /* Update global TCP statistics. */ diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 2e0f0af76c1..a516d1e399d 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -171,13 +171,13 @@ static int tcp_write_timeout(struct sock *sk) { struct inet_connection_sock *icsk = inet_csk(sk); int retry_until; - bool do_reset, syn_set = 0; + bool do_reset, syn_set = false; 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; + syn_set = true; } else { if (retransmits_timed_out(sk, sysctl_tcp_retries1, 0, 0)) { /* Black hole detection */ @@ -261,7 +261,7 @@ static void tcp_delack_timer(unsigned long data) } out: - if (tcp_memory_pressure) + if (sk_under_memory_pressure(sk)) sk_mem_reclaim(sk); out_unlock: bh_unlock_sock(sk); @@ -340,7 +340,7 @@ void tcp_retransmit_timer(struct sock *sk) &inet->inet_daddr, ntohs(inet->inet_dport), inet->inet_num, tp->snd_una, tp->snd_nxt); } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) else if (sk->sk_family == AF_INET6) { struct ipv6_pinfo *np = inet6_sk(sk); LIMIT_NETDEBUG(KERN_DEBUG "TCP: Peer %pI6:%u/%u unexpectedly shrunk window %u:%u (repaired)\n", diff --git a/net/ipv4/tunnel4.c b/net/ipv4/tunnel4.c index ac3b3ee4b07..01775983b99 100644 --- a/net/ipv4/tunnel4.c +++ b/net/ipv4/tunnel4.c @@ -105,7 +105,7 @@ drop: return 0; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static int tunnel64_rcv(struct sk_buff *skb) { struct xfrm_tunnel *handler; @@ -134,7 +134,7 @@ static void tunnel4_err(struct sk_buff *skb, u32 info) break; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static void tunnel64_err(struct sk_buff *skb, u32 info) { struct xfrm_tunnel *handler; @@ -152,7 +152,7 @@ static const struct net_protocol tunnel4_protocol = { .netns_ok = 1, }; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static const struct net_protocol tunnel64_protocol = { .handler = tunnel64_rcv, .err_handler = tunnel64_err, @@ -167,7 +167,7 @@ static int __init tunnel4_init(void) printk(KERN_ERR "tunnel4 init: can't add protocol\n"); return -EAGAIN; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (inet_add_protocol(&tunnel64_protocol, IPPROTO_IPV6)) { printk(KERN_ERR "tunnel64 init: can't add protocol\n"); inet_del_protocol(&tunnel4_protocol, IPPROTO_IPIP); @@ -179,7 +179,7 @@ static int __init tunnel4_init(void) static void __exit tunnel4_fini(void) { -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (inet_del_protocol(&tunnel64_protocol, IPPROTO_IPV6)) printk(KERN_ERR "tunnel64 close: can't remove protocol\n"); #endif diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index ab0966df1e2..5d075b5f70f 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -445,7 +445,7 @@ exact_match: /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ -static struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, +struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, __be32 daddr, __be16 dport, int dif, struct udp_table *udptable) { @@ -512,6 +512,7 @@ begin: rcu_read_unlock(); return result; } +EXPORT_SYMBOL_GPL(__udp4_lib_lookup); static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, @@ -1164,7 +1165,7 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, struct inet_sock *inet = inet_sk(sk); struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; struct sk_buff *skb; - unsigned int ulen; + unsigned int ulen, copied; int peeked; int err; int is_udplite = IS_UDPLITE(sk); @@ -1186,9 +1187,10 @@ try_again: goto out; ulen = skb->len - sizeof(struct udphdr); - if (len > ulen) - len = ulen; - else if (len < ulen) + copied = len; + if (copied > ulen) + copied = ulen; + else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; /* @@ -1197,14 +1199,14 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (len < ulen || UDP_SKB_CB(skb)->partial_cov) { + if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { if (udp_lib_checksum_complete(skb)) goto csum_copy_err; } if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, len); + msg->msg_iov, copied); else { err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), @@ -1233,7 +1235,7 @@ try_again: if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); - err = len; + err = copied; if (flags & MSG_TRUNC) err = ulen; @@ -1357,7 +1359,7 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (inet_sk(sk)->inet_daddr) sock_rps_save_rxhash(sk, skb); - rc = ip_queue_rcv_skb(sk, skb); + rc = sock_queue_rcv_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); @@ -1473,6 +1475,7 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) rc = 0; + ipv4_pktinfo_prepare(skb); bh_lock_sock(sk); if (!sock_owned_by_user(sk)) rc = __udp_queue_rcv_skb(sk, skb); @@ -2246,7 +2249,8 @@ int udp4_ufo_send_check(struct sk_buff *skb) return 0; } -struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, u32 features) +struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, + netdev_features_t features) { struct sk_buff *segs = ERR_PTR(-EINVAL); unsigned int mss; diff --git a/net/ipv4/udp_diag.c b/net/ipv4/udp_diag.c new file mode 100644 index 00000000000..69f8a7ca63d --- /dev/null +++ b/net/ipv4/udp_diag.c @@ -0,0 +1,201 @@ +/* + * udp_diag.c Module for monitoring UDP transport protocols sockets. + * + * Authors: Pavel Emelyanov, <xemul@parallels.com> + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of the GNU General Public License + * as published by the Free Software Foundation; either version + * 2 of the License, or (at your option) any later version. + */ + + +#include <linux/module.h> +#include <linux/inet_diag.h> +#include <linux/udp.h> +#include <net/udp.h> +#include <net/udplite.h> +#include <linux/inet_diag.h> +#include <linux/sock_diag.h> + +static int sk_diag_dump(struct sock *sk, struct sk_buff *skb, + struct netlink_callback *cb, struct inet_diag_req *req, + struct nlattr *bc) +{ + if (!inet_diag_bc_sk(bc, sk)) + return 0; + + return inet_sk_diag_fill(sk, NULL, skb, req, NETLINK_CB(cb->skb).pid, + cb->nlh->nlmsg_seq, NLM_F_MULTI, cb->nlh); +} + +static int udp_dump_one(struct udp_table *tbl, struct sk_buff *in_skb, + const struct nlmsghdr *nlh, struct inet_diag_req *req) +{ + int err = -EINVAL; + struct sock *sk; + struct sk_buff *rep; + + if (req->sdiag_family == AF_INET) + sk = __udp4_lib_lookup(&init_net, + req->id.idiag_src[0], req->id.idiag_sport, + req->id.idiag_dst[0], req->id.idiag_dport, + req->id.idiag_if, tbl); +#if IS_ENABLED(CONFIG_IPV6) + else if (req->sdiag_family == AF_INET6) + sk = __udp6_lib_lookup(&init_net, + (struct in6_addr *)req->id.idiag_src, + req->id.idiag_sport, + (struct in6_addr *)req->id.idiag_dst, + req->id.idiag_dport, + req->id.idiag_if, tbl); +#endif + else + goto out_nosk; + + err = -ENOENT; + if (sk == NULL) + goto out_nosk; + + err = sock_diag_check_cookie(sk, req->id.idiag_cookie); + if (err) + goto out; + + err = -ENOMEM; + rep = alloc_skb(NLMSG_SPACE((sizeof(struct inet_diag_msg) + + sizeof(struct inet_diag_meminfo) + + 64)), GFP_KERNEL); + if (!rep) + goto out; + + err = inet_sk_diag_fill(sk, NULL, rep, req, + NETLINK_CB(in_skb).pid, + nlh->nlmsg_seq, 0, nlh); + if (err < 0) { + WARN_ON(err == -EMSGSIZE); + kfree_skb(rep); + goto out; + } + err = netlink_unicast(sock_diag_nlsk, rep, NETLINK_CB(in_skb).pid, + MSG_DONTWAIT); + if (err > 0) + err = 0; +out: + if (sk) + sock_put(sk); +out_nosk: + return err; +} + +static void udp_dump(struct udp_table *table, struct sk_buff *skb, struct netlink_callback *cb, + struct inet_diag_req *r, struct nlattr *bc) +{ + int num, s_num, slot, s_slot; + + s_slot = cb->args[0]; + num = s_num = cb->args[1]; + + for (slot = s_slot; slot <= table->mask; num = s_num = 0, slot++) { + struct sock *sk; + struct hlist_nulls_node *node; + struct udp_hslot *hslot = &table->hash[slot]; + + if (hlist_nulls_empty(&hslot->head)) + continue; + + spin_lock_bh(&hslot->lock); + sk_nulls_for_each(sk, node, &hslot->head) { + struct inet_sock *inet = inet_sk(sk); + + if (num < s_num) + goto next; + if (!(r->idiag_states & (1 << sk->sk_state))) + goto next; + if (r->sdiag_family != AF_UNSPEC && + sk->sk_family != r->sdiag_family) + goto next; + if (r->id.idiag_sport != inet->inet_sport && + r->id.idiag_sport) + goto next; + if (r->id.idiag_dport != inet->inet_dport && + r->id.idiag_dport) + goto next; + + if (sk_diag_dump(sk, skb, cb, r, bc) < 0) { + spin_unlock_bh(&hslot->lock); + goto done; + } +next: + num++; + } + spin_unlock_bh(&hslot->lock); + } +done: + cb->args[0] = slot; + cb->args[1] = num; +} + +static void udp_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct inet_diag_req *r, struct nlattr *bc) +{ + udp_dump(&udp_table, skb, cb, r, bc); +} + +static int udp_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, + struct inet_diag_req *req) +{ + return udp_dump_one(&udp_table, in_skb, nlh, req); +} + +static const struct inet_diag_handler udp_diag_handler = { + .dump = udp_diag_dump, + .dump_one = udp_diag_dump_one, + .idiag_type = IPPROTO_UDP, +}; + +static void udplite_diag_dump(struct sk_buff *skb, struct netlink_callback *cb, + struct inet_diag_req *r, struct nlattr *bc) +{ + udp_dump(&udplite_table, skb, cb, r, bc); +} + +static int udplite_diag_dump_one(struct sk_buff *in_skb, const struct nlmsghdr *nlh, + struct inet_diag_req *req) +{ + return udp_dump_one(&udplite_table, in_skb, nlh, req); +} + +static const struct inet_diag_handler udplite_diag_handler = { + .dump = udplite_diag_dump, + .dump_one = udplite_diag_dump_one, + .idiag_type = IPPROTO_UDPLITE, +}; + +static int __init udp_diag_init(void) +{ + int err; + + err = inet_diag_register(&udp_diag_handler); + if (err) + goto out; + err = inet_diag_register(&udplite_diag_handler); + if (err) + goto out_lite; +out: + return err; +out_lite: + inet_diag_unregister(&udp_diag_handler); + goto out; +} + +static void __exit udp_diag_exit(void) +{ + inet_diag_unregister(&udplite_diag_handler); + inet_diag_unregister(&udp_diag_handler); +} + +module_init(udp_diag_init); +module_exit(udp_diag_exit); +MODULE_LICENSE("GPL"); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-17 /* AF_INET - IPPROTO_UDP */); +MODULE_ALIAS_NET_PF_PROTO_TYPE(PF_NETLINK, NETLINK_SOCK_DIAG, 2-136 /* AF_INET - IPPROTO_UDPLITE */); diff --git a/net/ipv4/xfrm4_tunnel.c b/net/ipv4/xfrm4_tunnel.c index 82806455e85..9247d9d70e9 100644 --- a/net/ipv4/xfrm4_tunnel.c +++ b/net/ipv4/xfrm4_tunnel.c @@ -64,7 +64,7 @@ static struct xfrm_tunnel xfrm_tunnel_handler __read_mostly = { .priority = 2, }; -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) static struct xfrm_tunnel xfrm64_tunnel_handler __read_mostly = { .handler = xfrm_tunnel_rcv, .err_handler = xfrm_tunnel_err, @@ -84,7 +84,7 @@ static int __init ipip_init(void) xfrm_unregister_type(&ipip_type, AF_INET); return -EAGAIN; } -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (xfrm4_tunnel_register(&xfrm64_tunnel_handler, AF_INET6)) { printk(KERN_INFO "ipip init: can't add xfrm handler for AF_INET6\n"); xfrm4_tunnel_deregister(&xfrm_tunnel_handler, AF_INET); @@ -97,7 +97,7 @@ static int __init ipip_init(void) static void __exit ipip_fini(void) { -#if defined(CONFIG_IPV6) || defined(CONFIG_IPV6_MODULE) +#if IS_ENABLED(CONFIG_IPV6) if (xfrm4_tunnel_deregister(&xfrm64_tunnel_handler, AF_INET6)) printk(KERN_INFO "ipip close: can't remove xfrm handler for AF_INET6\n"); #endif |