diff options
Diffstat (limited to 'net/ipv4')
65 files changed, 1654 insertions, 811 deletions
diff --git a/net/ipv4/Kconfig b/net/ipv4/Kconfig index 251f6621435..335ca7abbd4 100644 --- a/net/ipv4/Kconfig +++ b/net/ipv4/Kconfig @@ -407,6 +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->n |