diff options
Diffstat (limited to 'net/ipv4/udp.c')
| -rw-r--r-- | net/ipv4/udp.c | 1948 |
1 files changed, 1411 insertions, 537 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 1704c1474ea..7d5a8661df7 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -5,12 +5,10 @@ * * The User Datagram Protocol (UDP). * - * Version: $Id: udp.c,v 1.102 2002/02/01 22:01:04 davem Exp $ - * * Authors: Ross Biro * Fred N. van Kempen, <waltje@uWalt.NL.Mugnet.ORG> * Arnt Gulbrandsen, <agulbra@nvg.unit.no> - * Alan Cox, <Alan.Cox@linux.org> + * Alan Cox, <alan@lxorguk.ukuu.org.uk> * Hirokazu Takahashi, <taka@valinux.co.jp> * * Fixes: @@ -79,10 +77,13 @@ * 2 of the License, or (at your option) any later version. */ -#include <asm/system.h> +#define pr_fmt(fmt) "UDP: " fmt + #include <asm/uaccess.h> #include <asm/ioctls.h> #include <linux/bootmem.h> +#include <linux/highmem.h> +#include <linux/swap.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> @@ -95,247 +96,519 @@ #include <linux/mm.h> #include <linux/inet.h> #include <linux/netdevice.h> +#include <linux/slab.h> #include <net/tcp_states.h> #include <linux/skbuff.h> #include <linux/proc_fs.h> #include <linux/seq_file.h> #include <net/net_namespace.h> #include <net/icmp.h> +#include <net/inet_hashtables.h> #include <net/route.h> #include <net/checksum.h> #include <net/xfrm.h> +#include <trace/events/udp.h> +#include <linux/static_key.h> +#include <trace/events/skb.h> +#include <net/busy_poll.h> #include "udp_impl.h" -/* - * Snmp MIB for the UDP layer - */ - -DEFINE_SNMP_STAT(struct udp_mib, udp_statistics) __read_mostly; -EXPORT_SYMBOL(udp_statistics); - -DEFINE_SNMP_STAT(struct udp_mib, udp_stats_in6) __read_mostly; -EXPORT_SYMBOL(udp_stats_in6); +struct udp_table udp_table __read_mostly; +EXPORT_SYMBOL(udp_table); -struct hlist_head udp_hash[UDP_HTABLE_SIZE]; -DEFINE_RWLOCK(udp_hash_lock); +long sysctl_udp_mem[3] __read_mostly; +EXPORT_SYMBOL(sysctl_udp_mem); -int sysctl_udp_mem[3] __read_mostly; int sysctl_udp_rmem_min __read_mostly; -int sysctl_udp_wmem_min __read_mostly; - -EXPORT_SYMBOL(sysctl_udp_mem); EXPORT_SYMBOL(sysctl_udp_rmem_min); + +int sysctl_udp_wmem_min __read_mostly; EXPORT_SYMBOL(sysctl_udp_wmem_min); -atomic_t udp_memory_allocated; +atomic_long_t udp_memory_allocated; EXPORT_SYMBOL(udp_memory_allocated); -static inline int __udp_lib_lport_inuse(struct net *net, __u16 num, - const struct hlist_head udptable[]) -{ - struct sock *sk; - struct hlist_node *node; +#define MAX_UDP_PORTS 65536 +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) - sk_for_each(sk, node, &udptable[num & (UDP_HTABLE_SIZE - 1)]) - if (sk->sk_net == net && sk->sk_hash == num) - return 1; +static int udp_lib_lport_inuse(struct net *net, __u16 num, + const struct udp_hslot *hslot, + unsigned long *bitmap, + struct sock *sk, + int (*saddr_comp)(const struct sock *sk1, + const struct sock *sk2), + unsigned int log) +{ + struct sock *sk2; + struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); + + sk_nulls_for_each(sk2, node, &hslot->head) + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + (bitmap || udp_sk(sk2)->udp_port_hash == num) && + (!sk2->sk_reuse || !sk->sk_reuse) && + (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || + sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && + (*saddr_comp)(sk, sk2)) { + if (bitmap) + __set_bit(udp_sk(sk2)->udp_port_hash >> log, + bitmap); + else + return 1; + } return 0; } +/* + * Note: we still hold spinlock of primary hash chain, so no other writer + * can insert/delete a socket with local_port == num + */ +static int udp_lib_lport_inuse2(struct net *net, __u16 num, + struct udp_hslot *hslot2, + struct sock *sk, + int (*saddr_comp)(const struct sock *sk1, + const struct sock *sk2)) +{ + struct sock *sk2; + struct hlist_nulls_node *node; + kuid_t uid = sock_i_uid(sk); + int res = 0; + + spin_lock(&hslot2->lock); + udp_portaddr_for_each_entry(sk2, node, &hslot2->head) + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + (udp_sk(sk2)->udp_port_hash == num) && + (!sk2->sk_reuse || !sk->sk_reuse) && + (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if || + sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + (!sk2->sk_reuseport || !sk->sk_reuseport || + !uid_eq(uid, sock_i_uid(sk2))) && + (*saddr_comp)(sk, sk2)) { + res = 1; + break; + } + spin_unlock(&hslot2->lock); + return res; +} + /** - * __udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 + * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * * @sk: socket struct in question * @snum: port number to look up - * @udptable: hash list table, must be of UDP_HTABLE_SIZE * @saddr_comp: AF-dependent comparison of bound local IP addresses + * @hash2_nulladdr: AF-dependent hash value in secondary hash chains, + * with NULL address */ -int __udp_lib_get_port(struct sock *sk, unsigned short snum, - struct hlist_head udptable[], +int udp_lib_get_port(struct sock *sk, unsigned short snum, int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2 ) ) + const struct sock *sk2), + unsigned int hash2_nulladdr) { - struct hlist_node *node; - struct hlist_head *head; - struct sock *sk2; + struct udp_hslot *hslot, *hslot2; + struct udp_table *udptable = sk->sk_prot->h.udp_table; int error = 1; - struct net *net = sk->sk_net; - - write_lock_bh(&udp_hash_lock); + struct net *net = sock_net(sk); if (!snum) { - int i, low, high, remaining; - unsigned rover, best, best_size_so_far; + int low, high, remaining; + unsigned int rand; + unsigned short first, last; + DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); - inet_get_local_port_range(&low, &high); + inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - best_size_so_far = UINT_MAX; - best = rover = net_random() % remaining + low; - - /* 1st pass: look for empty (or shortest) hash chain */ - for (i = 0; i < UDP_HTABLE_SIZE; i++) { - int size = 0; - - head = &udptable[rover & (UDP_HTABLE_SIZE - 1)]; - if (hlist_empty(head)) - goto gotit; + rand = prandom_u32(); + first = (((u64)rand * remaining) >> 32) + low; + /* + * force rand to be an odd multiple of UDP_HTABLE_SIZE + */ + rand = (rand | 1) * (udptable->mask + 1); + last = first + udptable->mask + 1; + do { + hslot = udp_hashslot(udptable, net, first); + bitmap_zero(bitmap, PORTS_PER_CHAIN); + spin_lock_bh(&hslot->lock); + udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, + saddr_comp, udptable->log); - sk_for_each(sk2, node, head) { - if (++size >= best_size_so_far) - goto next; + snum = first; + /* + * Iterate on all possible values of snum for this hash. + * Using steps of an odd multiple of UDP_HTABLE_SIZE + * give us randomization and full range coverage. + */ + do { + if (low <= snum && snum <= high && + !test_bit(snum >> udptable->log, bitmap) && + !inet_is_local_reserved_port(net, snum)) + goto found; + snum += rand; + } while (snum != first); + spin_unlock_bh(&hslot->lock); + } while (++first != last); + goto fail; + } else { + hslot = udp_hashslot(udptable, net, snum); + spin_lock_bh(&hslot->lock); + if (hslot->count > 10) { + int exist; + unsigned int slot2 = udp_sk(sk)->udp_portaddr_hash ^ snum; + + slot2 &= udptable->mask; + hash2_nulladdr &= udptable->mask; + + hslot2 = udp_hashslot2(udptable, slot2); + if (hslot->count < hslot2->count) + goto scan_primary_hash; + + exist = udp_lib_lport_inuse2(net, snum, hslot2, + sk, saddr_comp); + if (!exist && (hash2_nulladdr != slot2)) { + hslot2 = udp_hashslot2(udptable, hash2_nulladdr); + exist = udp_lib_lport_inuse2(net, snum, hslot2, + sk, saddr_comp); } - best_size_so_far = size; - best = rover; - next: - /* fold back if end of range */ - if (++rover > high) - rover = low + ((rover - low) - & (UDP_HTABLE_SIZE - 1)); - - + if (exist) + goto fail_unlock; + else + goto found; } +scan_primary_hash: + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, + saddr_comp, 0)) + goto fail_unlock; + } +found: + inet_sk(sk)->inet_num = snum; + udp_sk(sk)->udp_port_hash = snum; + udp_sk(sk)->udp_portaddr_hash ^= snum; + if (sk_unhashed(sk)) { + sk_nulls_add_node_rcu(sk, &hslot->head); + hslot->count++; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + spin_lock(&hslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &hslot2->head); + hslot2->count++; + spin_unlock(&hslot2->lock); + } + error = 0; +fail_unlock: + spin_unlock_bh(&hslot->lock); +fail: + return error; +} +EXPORT_SYMBOL(udp_lib_get_port); - /* 2nd pass: find hole in shortest hash chain */ - rover = best; - for (i = 0; i < (1 << 16) / UDP_HTABLE_SIZE; i++) { - if (! __udp_lib_lport_inuse(net, rover, udptable)) - goto gotit; - rover += UDP_HTABLE_SIZE; - if (rover > high) - rover = low + ((rover - low) - & (UDP_HTABLE_SIZE - 1)); - } +static int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +{ + struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); + return (!ipv6_only_sock(sk2) && + (!inet1->inet_rcv_saddr || !inet2->inet_rcv_saddr || + inet1->inet_rcv_saddr == inet2->inet_rcv_saddr)); +} - /* All ports in use! */ - goto fail; +static unsigned int udp4_portaddr_hash(struct net *net, __be32 saddr, + unsigned int port) +{ + return jhash_1word((__force u32)saddr, net_hash_mix(net)) ^ port; +} -gotit: - snum = rover; - } else { - head = &udptable[snum & (UDP_HTABLE_SIZE - 1)]; +int udp_v4_get_port(struct sock *sk, unsigned short snum) +{ + unsigned int hash2_nulladdr = + udp4_portaddr_hash(sock_net(sk), htonl(INADDR_ANY), snum); + unsigned int hash2_partial = + udp4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, 0); + + /* precompute partial secondary hash */ + udp_sk(sk)->udp_portaddr_hash = hash2_partial; + return udp_lib_get_port(sk, snum, ipv4_rcv_saddr_equal, hash2_nulladdr); +} - sk_for_each(sk2, node, head) - if (sk2->sk_hash == snum && - sk2 != sk && - sk2->sk_net == net && - (!sk2->sk_reuse || !sk->sk_reuse) && - (!sk2->sk_bound_dev_if || !sk->sk_bound_dev_if - || sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && - (*saddr_comp)(sk, sk2) ) - goto fail; - } +static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, + unsigned short hnum, + __be16 sport, __be32 daddr, __be16 dport, int dif) +{ + int score = -1; - inet_sk(sk)->num = snum; - sk->sk_hash = snum; - if (sk_unhashed(sk)) { - head = &udptable[snum & (UDP_HTABLE_SIZE - 1)]; - sk_add_node(sk, head); - sock_prot_inuse_add(sk->sk_prot, 1); + if (net_eq(sock_net(sk), net) && udp_sk(sk)->udp_port_hash == hnum && + !ipv6_only_sock(sk)) { + struct inet_sock *inet = inet_sk(sk); + + score = (sk->sk_family == PF_INET ? 2 : 1); + if (inet->inet_rcv_saddr) { + if (inet->inet_rcv_saddr != daddr) + return -1; + score += 4; + } + if (inet->inet_daddr) { + if (inet->inet_daddr != saddr) + return -1; + score += 4; + } + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score += 4; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score += 4; + } } - error = 0; -fail: - write_unlock_bh(&udp_hash_lock); - return error; + return score; } -int udp_get_port(struct sock *sk, unsigned short snum, - int (*scmp)(const struct sock *, const struct sock *)) +/* + * In this second variant, we check (daddr, dport) matches (inet_rcv_sadd, inet_num) + */ +static inline int compute_score2(struct sock *sk, struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, int dif) { - return __udp_lib_get_port(sk, snum, udp_hash, scmp); + int score = -1; + + if (net_eq(sock_net(sk), net) && !ipv6_only_sock(sk)) { + struct inet_sock *inet = inet_sk(sk); + + if (inet->inet_rcv_saddr != daddr) + return -1; + if (inet->inet_num != hnum) + return -1; + + score = (sk->sk_family == PF_INET ? 2 : 1); + if (inet->inet_daddr) { + if (inet->inet_daddr != saddr) + return -1; + score += 4; + } + if (inet->inet_dport) { + if (inet->inet_dport != sport) + return -1; + score += 4; + } + if (sk->sk_bound_dev_if) { + if (sk->sk_bound_dev_if != dif) + return -1; + score += 4; + } + } + return score; } -int ipv4_rcv_saddr_equal(const struct sock *sk1, const struct sock *sk2) +static unsigned int udp_ehashfn(struct net *net, const __be32 laddr, + const __u16 lport, const __be32 faddr, + const __be16 fport) { - struct inet_sock *inet1 = inet_sk(sk1), *inet2 = inet_sk(sk2); + static u32 udp_ehash_secret __read_mostly; - return ( !ipv6_only_sock(sk2) && - (!inet1->rcv_saddr || !inet2->rcv_saddr || - inet1->rcv_saddr == inet2->rcv_saddr )); + net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); + + return __inet_ehashfn(laddr, lport, faddr, fport, + udp_ehash_secret + net_hash_mix(net)); } -static inline int udp_v4_get_port(struct sock *sk, unsigned short snum) + +/* called with read_rcu_lock() */ +static struct sock *udp4_lib_lookup2(struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, int dif, + struct udp_hslot *hslot2, unsigned int slot2) { - return udp_get_port(sk, snum, ipv4_rcv_saddr_equal); + struct sock *sk, *result; + struct hlist_nulls_node *node; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; + +begin: + result = NULL; + badness = 0; + udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + score = compute_score2(sk, net, saddr, sport, + daddr, hnum, dif); + if (score > badness) { + result = sk; + badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = udp_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; + } + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) + result = sk; + hash = next_pseudo_random32(hash); + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot2) + goto begin; + if (result) { + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) + result = NULL; + else if (unlikely(compute_score2(result, net, saddr, sport, + daddr, hnum, dif) < badness)) { + sock_put(result); + goto begin; + } + } + return result; } /* 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 hlist_head udptable[]) + int dif, struct udp_table *udptable) { - struct sock *sk, *result = NULL; - struct hlist_node *node; + struct sock *sk, *result; + struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - int badness = -1; - - read_lock(&udp_hash_lock); - sk_for_each(sk, node, &udptable[hnum & (UDP_HTABLE_SIZE - 1)]) { - struct inet_sock *inet = inet_sk(sk); - - if (sk->sk_net == net && sk->sk_hash == hnum && - !ipv6_only_sock(sk)) { - int score = (sk->sk_family == PF_INET ? 1 : 0); - if (inet->rcv_saddr) { - if (inet->rcv_saddr != daddr) - continue; - score+=2; - } - if (inet->daddr) { - if (inet->daddr != saddr) - continue; - score+=2; - } - if (inet->dport) { - if (inet->dport != sport) - continue; - score+=2; - } - if (sk->sk_bound_dev_if) { - if (sk->sk_bound_dev_if != dif) - continue; - score+=2; + unsigned int hash2, slot2, slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot2, *hslot = &udptable->hash[slot]; + int score, badness, matches = 0, reuseport = 0; + u32 hash = 0; + + rcu_read_lock(); + if (hslot->count > 10) { + hash2 = udp4_portaddr_hash(net, daddr, hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp4_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, + hslot2, slot2); + if (!result) { + hash2 = udp4_portaddr_hash(net, htonl(INADDR_ANY), hnum); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + if (hslot->count < hslot2->count) + goto begin; + + result = udp4_lib_lookup2(net, saddr, sport, + htonl(INADDR_ANY), hnum, dif, + hslot2, slot2); + } + rcu_read_unlock(); + return result; + } +begin: + result = NULL; + badness = 0; + sk_nulls_for_each_rcu(sk, node, &hslot->head) { + score = compute_score(sk, net, saddr, hnum, sport, + daddr, dport, dif); + if (score > badness) { + result = sk; + badness = score; + reuseport = sk->sk_reuseport; + if (reuseport) { + hash = udp_ehashfn(net, daddr, hnum, + saddr, sport); + matches = 1; } - if (score == 9) { + } else if (score == badness && reuseport) { + matches++; + if (((u64)hash * matches) >> 32 == 0) result = sk; - break; - } else if (score > badness) { - result = sk; - badness = score; - } + hash = next_pseudo_random32(hash); + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begin; + + if (result) { + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) + result = NULL; + else if (unlikely(compute_score(result, net, saddr, hnum, sport, + daddr, dport, dif) < badness)) { + sock_put(result); + goto begin; } } - if (result) - sock_hold(result); - read_unlock(&udp_hash_lock); + 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, + struct udp_table *udptable) +{ + const struct iphdr *iph = ip_hdr(skb); + + return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + udptable); +} + +struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, + __be32 daddr, __be16 dport, int dif) +{ + return __udp4_lib_lookup(net, saddr, sport, daddr, dport, dif, &udp_table); +} +EXPORT_SYMBOL_GPL(udp4_lib_lookup); -static inline struct sock *udp_v4_mcast_next(struct sock *sk, +static inline bool __udp_is_mcast_sock(struct net *net, struct sock *sk, + __be16 loc_port, __be32 loc_addr, + __be16 rmt_port, __be32 rmt_addr, + int dif, unsigned short hnum) +{ + struct inet_sock *inet = inet_sk(sk); + + if (!net_eq(sock_net(sk), net) || + udp_sk(sk)->udp_port_hash != hnum || + (inet->inet_daddr && inet->inet_daddr != rmt_addr) || + (inet->inet_dport != rmt_port && inet->inet_dport) || + (inet->inet_rcv_saddr && inet->inet_rcv_saddr != loc_addr) || + ipv6_only_sock(sk) || + (sk->sk_bound_dev_if && sk->sk_bound_dev_if != dif)) + return false; + if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif)) + return false; + return true; +} + +static inline struct sock *udp_v4_mcast_next(struct net *net, struct sock *sk, __be16 loc_port, __be32 loc_addr, __be16 rmt_port, __be32 rmt_addr, int dif) { - struct hlist_node *node; + struct hlist_nulls_node *node; struct sock *s = sk; unsigned short hnum = ntohs(loc_port); - sk_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); - - if (s->sk_hash != hnum || - (inet->daddr && inet->daddr != rmt_addr) || - (inet->dport != rmt_port && inet->dport) || - (inet->rcv_saddr && inet->rcv_saddr != loc_addr) || - ipv6_only_sock(s) || - (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)) - continue; - if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif)) - continue; - goto found; + sk_nulls_for_each_from(s, node) { + if (__udp_is_mcast_sock(net, s, + loc_port, loc_addr, + rmt_port, rmt_addr, + dif, hnum)) + goto found; } s = NULL; found: @@ -353,21 +626,22 @@ found: * to find the appropriate port. */ -void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) +void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; - struct iphdr *iph = (struct iphdr*)skb->data; - struct udphdr *uh = (struct udphdr*)(skb->data+(iph->ihl<<2)); + const struct iphdr *iph = (const struct iphdr *)skb->data; + struct udphdr *uh = (struct udphdr *)(skb->data+(iph->ihl<<2)); const int type = icmp_hdr(skb)->type; const int code = icmp_hdr(skb)->code; struct sock *sk; int harderr; int err; + struct net *net = dev_net(skb->dev); - sk = __udp4_lib_lookup(skb->dev->nd_net, iph->daddr, uh->dest, + sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, udptable); if (sk == NULL) { - ICMP_INC_STATS_BH(ICMP_MIB_INERRORS); + ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); return; /* No socket for error */ } @@ -388,6 +662,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) break; case ICMP_DEST_UNREACH: if (code == ICMP_FRAG_NEEDED) { /* Path MTU discovery */ + ipv4_sk_update_pmtu(skb, sk, info); if (inet->pmtudisc != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; @@ -401,6 +676,9 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) err = icmp_err_convert[code].errno; } break; + case ICMP_REDIRECT: + ipv4_sk_redirect(skb, sk); + goto out; } /* @@ -410,9 +688,9 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct hlist_head udptable[]) if (!inet->recverr) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; - } else { - ip_icmp_error(sk, skb, err, uh->dest, info, (u8*)(uh+1)); - } + } else + ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); + sk->sk_err = err; sk->sk_error_report(sk); out: @@ -421,13 +699,13 @@ out: void udp_err(struct sk_buff *skb, u32 info) { - __udp4_lib_err(skb, info, udp_hash); + __udp4_lib_err(skb, info, &udp_table); } /* * Throw away all pending data and cancel the corking. Socket is locked. */ -static void udp_flush_pending_frames(struct sock *sk) +void udp_flush_pending_frames(struct sock *sk) { struct udp_sock *up = udp_sk(sk); @@ -437,112 +715,178 @@ static void udp_flush_pending_frames(struct sock *sk) ip_flush_pending_frames(sk); } } +EXPORT_SYMBOL(udp_flush_pending_frames); /** - * udp4_hwcsum_outgoing - handle outgoing HW checksumming - * @sk: socket we are sending on + * udp4_hwcsum - handle outgoing HW checksumming * @skb: sk_buff containing the filled-in UDP header * (checksum field must be zeroed out) + * @src: source IP address + * @dst: destination IP address */ -static void udp4_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, - __be32 src, __be32 dst, int len ) +void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { - unsigned int offset; struct udphdr *uh = udp_hdr(skb); + int offset = skb_transport_offset(skb); + int len = skb->len - offset; + int hlen = len; __wsum csum = 0; - if (skb_queue_len(&sk->sk_write_queue) == 1) { + if (!skb_has_frag_list(skb)) { /* * Only one fragment on the socket. */ skb->csum_start = skb_transport_header(skb) - skb->head; skb->csum_offset = offsetof(struct udphdr, check); - uh->check = ~csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, 0); + uh->check = ~csum_tcpudp_magic(src, dst, len, + IPPROTO_UDP, 0); } else { + struct sk_buff *frags; + /* * HW-checksum won't work as there are two or more * fragments on the socket so that all csums of sk_buffs * should be together */ - offset = skb_transport_offset(skb); - skb->csum = skb_checksum(skb, offset, skb->len - offset, 0); + skb_walk_frags(skb, frags) { + csum = csum_add(csum, frags->csum); + hlen -= frags->len; + } + csum = skb_checksum(skb, offset, hlen, csum); skb->ip_summed = CHECKSUM_NONE; - skb_queue_walk(&sk->sk_write_queue, skb) { - csum = csum_add(csum, skb->csum); - } - uh->check = csum_tcpudp_magic(src, dst, len, IPPROTO_UDP, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; } } +EXPORT_SYMBOL_GPL(udp4_hwcsum); -/* - * Push out all pending data as one UDP datagram. Socket is locked. +/* Function to set UDP checksum for an IPv4 UDP packet. This is intended + * for the simple case like when setting the checksum for a UDP tunnel. */ -static int udp_push_pending_frames(struct sock *sk) +void udp_set_csum(bool nocheck, struct sk_buff *skb, + __be32 saddr, __be32 daddr, int len) { - struct udp_sock *up = udp_sk(sk); + struct udphdr *uh = udp_hdr(skb); + + if (nocheck) + uh->check = 0; + else if (skb_is_gso(skb)) + uh->check = ~udp_v4_check(len, saddr, daddr, 0); + else if (skb_dst(skb) && skb_dst(skb)->dev && + (skb_dst(skb)->dev->features & NETIF_F_V4_CSUM)) { + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct udphdr, check); + uh->check = ~udp_v4_check(len, saddr, daddr, 0); + } else { + __wsum csum; + + BUG_ON(skb->ip_summed == CHECKSUM_PARTIAL); + + uh->check = 0; + csum = skb_checksum(skb, 0, len, 0); + uh->check = udp_v4_check(len, saddr, daddr, csum); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + + skb->ip_summed = CHECKSUM_UNNECESSARY; + } +} +EXPORT_SYMBOL(udp_set_csum); + +static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) +{ + struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); - struct flowi *fl = &inet->cork.fl; - struct sk_buff *skb; struct udphdr *uh; int err = 0; int is_udplite = IS_UDPLITE(sk); + int offset = skb_transport_offset(skb); + int len = skb->len - offset; __wsum csum = 0; - /* Grab the skbuff where UDP header space exists. */ - if ((skb = skb_peek(&sk->sk_write_queue)) == NULL) - goto out; - /* * Create a UDP header */ uh = udp_hdr(skb); - uh->source = fl->fl_ip_sport; - uh->dest = fl->fl_ip_dport; - uh->len = htons(up->len); + uh->source = inet->inet_sport; + uh->dest = fl4->fl4_dport; + uh->len = htons(len); uh->check = 0; if (is_udplite) /* UDP-Lite */ - csum = udplite_csum_outgoing(sk, skb); + csum = udplite_csum(skb); - else if (sk->sk_no_check == UDP_CSUM_NOXMIT) { /* UDP csum disabled */ + else if (sk->sk_no_check_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ - udp4_hwcsum_outgoing(sk, skb, fl->fl4_src,fl->fl4_dst, up->len); + udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; - } else /* `normal' UDP */ - csum = udp_csum_outgoing(sk, skb); + } else + csum = udp_csum(skb); /* add protocol-dependent pseudo-header */ - uh->check = csum_tcpudp_magic(fl->fl4_src, fl->fl4_dst, up->len, - sk->sk_protocol, csum ); + uh->check = csum_tcpudp_magic(fl4->saddr, fl4->daddr, len, + sk->sk_protocol, csum); if (uh->check == 0) uh->check = CSUM_MANGLED_0; send: - err = ip_push_pending_frames(sk); + err = ip_send_skb(sock_net(sk), skb); + if (err) { + if (err == -ENOBUFS && !inet->recverr) { + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); + err = 0; + } + } else + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); + return err; +} + +/* + * Push out all pending data as one UDP datagram. Socket is locked. + */ +int udp_push_pending_frames(struct sock *sk) +{ + struct udp_sock *up = udp_sk(sk); + struct inet_sock *inet = inet_sk(sk); + struct flowi4 *fl4 = &inet->cork.fl.u.ip4; + struct sk_buff *skb; + int err = 0; + + skb = ip_finish_skb(sk, fl4); + if (!skb) + goto out; + + err = udp_send_skb(skb, fl4); + out: up->len = 0; up->pending = 0; - if (!err) - UDP_INC_STATS_USER(UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } +EXPORT_SYMBOL(udp_push_pending_frames); int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); + struct flowi4 fl4_stack; + struct flowi4 *fl4; int ulen = len; struct ipcm_cookie ipc; struct rtable *rt = NULL; @@ -554,6 +898,8 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int err, is_udplite = IS_UDPLITE(sk); int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); + struct sk_buff *skb; + struct ip_options_data opt_copy; if (len > 0xFFFF) return -EMSGSIZE; @@ -562,11 +908,17 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Check the flags. */ - if (msg->msg_flags&MSG_OOB) /* Mirror BSD error message compatibility */ + if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; ipc.opt = NULL; + ipc.tx_flags = 0; + ipc.ttl = 0; + ipc.tos = -1; + getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; + + fl4 = &inet->cork.fl.u.ip4; if (up->pending) { /* * There are pending frames. @@ -588,7 +940,7 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, * Get and verify the address. */ if (msg->msg_name) { - struct sockaddr_in * usin = (struct sockaddr_in*)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -603,40 +955,54 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, } else { if (sk->sk_state != TCP_ESTABLISHED) return -EDESTADDRREQ; - daddr = inet->daddr; - dport = inet->dport; + daddr = inet->inet_daddr; + dport = inet->inet_dport; /* Open fast path for connected socket. Route will not be used, if at least one option is set. */ connected = 1; } - ipc.addr = inet->saddr; + ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; + + sock_tx_timestamp(sk, &ipc.tx_flags); + if (msg->msg_controllen) { - err = ip_cmsg_send(msg, &ipc); + err = ip_cmsg_send(sock_net(sk), msg, &ipc, + sk->sk_family == AF_INET6); if (err) return err; if (ipc.opt) free = 1; connected = 0; } - if (!ipc.opt) - ipc.opt = inet->opt; + if (!ipc.opt) { + struct ip_options_rcu *inet_opt; + + rcu_read_lock(); + inet_opt = rcu_dereference(inet->inet_opt); + if (inet_opt) { + memcpy(&opt_copy, inet_opt, + sizeof(*inet_opt) + inet_opt->opt.optlen); + ipc.opt = &opt_copy.opt; + } + rcu_read_unlock(); + } saddr = ipc.addr; ipc.addr = faddr = daddr; - if (ipc.opt && ipc.opt->srr) { + if (ipc.opt && ipc.opt->opt.srr) { if (!daddr) return -EINVAL; - faddr = ipc.opt->faddr; + faddr = ipc.opt->opt.faddr; connected = 0; } - tos = RT_TOS(inet->tos); + tos = get_rttos(&ipc, inet); if (sock_flag(sk, SOCK_LOCALROUTE) || (msg->msg_flags & MSG_DONTROUTE) || - (ipc.opt && ipc.opt->is_strictroute)) { + (ipc.opt && ipc.opt->opt.is_strictroute)) { tos |= RTO_ONLINK; connected = 0; } @@ -647,26 +1013,28 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (!saddr) saddr = inet->mc_addr; connected = 0; - } + } else if (!ipc.oif) + ipc.oif = inet->uc_index; if (connected) - rt = (struct rtable*)sk_dst_check(sk, 0); + rt = (struct rtable *)sk_dst_check(sk, 0); if (rt == NULL) { - struct flowi fl = { .oif = ipc.oif, - .nl_u = { .ip4_u = - { .daddr = faddr, - .saddr = saddr, - .tos = tos } }, - .proto = sk->sk_protocol, - .uli_u = { .ports = - { .sport = inet->sport, - .dport = dport } } }; - security_sk_classify_flow(sk, &fl); - err = ip_route_output_flow(&init_net, &rt, &fl, sk, 1); - if (err) { + struct net *net = sock_net(sk); + + fl4 = &fl4_stack; + flowi4_init_output(fl4, ipc.oif, sk->sk_mark, tos, + RT_SCOPE_UNIVERSE, sk->sk_protocol, + inet_sk_flowi_flags(sk), + faddr, saddr, dport, inet->inet_sport); + + security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); + rt = ip_route_output_flow(net, fl4, sk); + if (IS_ERR(rt)) { + err = PTR_ERR(rt); + rt = NULL; if (err == -ENETUNREACH) - IP_INC_STATS_BH(IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -675,16 +1043,27 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, !sock_flag(sk, SOCK_BROADCAST)) goto out; if (connected) - sk_dst_set(sk, dst_clone(&rt->u.dst)); + sk_dst_set(sk, dst_clone(&rt->dst)); } if (msg->msg_flags&MSG_CONFIRM) goto do_confirm; back_from_confirm: - saddr = rt->rt_src; + saddr = fl4->saddr; if (!ipc.addr) - daddr = ipc.addr = rt->rt_dst; + daddr = ipc.addr = fl4->daddr; + + /* Lockless fast path for the non-corking case. */ + if (!corkreq) { + skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), &ipc, &rt, + msg->msg_flags); + err = PTR_ERR(skb); + if (!IS_ERR_OR_NULL(skb)) + err = udp_send_skb(skb, fl4); + goto out; + } lock_sock(sk); if (unlikely(up->pending)) { @@ -692,25 +1071,25 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 2\n"); + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("cork app bug 2\n")); err = -EINVAL; goto out; } /* * Now cork the socket to pend data. */ - inet->cork.fl.fl4_dst = daddr; - inet->cork.fl.fl_ip_dport = dport; - inet->cork.fl.fl4_src = saddr; - inet->cork.fl.fl_ip_sport = inet->sport; + fl4 = &inet->cork.fl.u.ip4; + fl4->daddr = daddr; + fl4->saddr = saddr; + fl4->fl4_dport = dport; + fl4->fl4_sport = inet->inet_sport; up->pending = AF_INET; do_append_data: up->len += ulen; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; - err = ip_append_data(sk, getfrag, msg->msg_iov, ulen, - sizeof(struct udphdr), &ipc, rt, - corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); + err = ip_append_data(sk, fl4, getfrag, msg->msg_iov, ulen, + sizeof(struct udphdr), &ipc, &rt, + corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) udp_flush_pending_frames(sk); else if (!corkreq) @@ -733,24 +1112,30 @@ out: * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP_INC_STATS_USER(UDP_MIB_SNDBUFERRORS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: - dst_confirm(&rt->u.dst); + dst_confirm(&rt->dst); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; goto out; } +EXPORT_SYMBOL(udp_sendmsg); int udp_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { + struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); int ret; + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + if (!up->pending) { struct msghdr msg = { .msg_flags = flags|MSG_MORE }; @@ -768,11 +1153,12 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, if (unlikely(!up->pending)) { release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG "udp cork app bug 3\n"); + LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("udp cork app bug 3\n")); return -EINVAL; } - ret = ip_append_page(sk, page, offset, size, flags); + ret = ip_append_page(sk, &inet->cork.fl.u.ip4, + page, offset, size, flags); if (ret == -EOPNOTSUPP) { release_sock(sk); return sock_no_sendpage(sk->sk_socket, page, offset, @@ -793,6 +1179,46 @@ out: return ret; } + +/** + * first_packet_length - return length of first packet in receive queue + * @sk: socket + * + * Drops all bad checksum frames, until a valid one is found. + * Returns the length of found skb, or 0 if none is found. + */ +static unsigned int first_packet_length(struct sock *sk) +{ + struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; + struct sk_buff *skb; + unsigned int res; + + __skb_queue_head_init(&list_kill); + + spin_lock_bh(&rcvq->lock); + while ((skb = skb_peek(rcvq)) != NULL && + udp_lib_checksum_complete(skb)) { + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + atomic_inc(&sk->sk_drops); + __skb_unlink(skb, rcvq); + __skb_queue_tail(&list_kill, skb); + } + res = skb ? skb->len : 0; + spin_unlock_bh(&rcvq->lock); + + if (!skb_queue_empty(&list_kill)) { + bool slow = lock_sock_fast(sk); + + __skb_queue_purge(&list_kill); + sk_mem_reclaim_partial(sk); + unlock_sock_fast(sk, slow); + } + return res; +} + /* * IOCTL requests applicable to the UDP protocol */ @@ -802,27 +1228,23 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) switch (cmd) { case SIOCOUTQ: { - int amount = atomic_read(&sk->sk_wmem_alloc); + int amount = sk_wmem_alloc_get(sk); + return put_user(amount, (int __user *)arg); } case SIOCINQ: { - struct sk_buff *skb; - unsigned long amount; + unsigned int amount = first_packet_length(sk); - amount = 0; - spin_lock_bh(&sk->sk_receive_queue.lock); - skb = skb_peek(&sk->sk_receive_queue); - if (skb != NULL) { + if (amount) /* * We will only return the amount * of this packet since that is all * that will be read. */ - amount = skb->len - sizeof(struct udphdr); - } - spin_unlock_bh(&sk->sk_receive_queue.lock); + amount -= sizeof(struct udphdr); + return put_user(amount, (int __user *)arg); } @@ -832,6 +1254,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) return 0; } +EXPORT_SYMBOL(udp_ioctl); /* * This should be easy, if there is something there we @@ -842,25 +1265,20 @@ int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, size_t len, int noblock, int flags, int *addr_len) { struct inet_sock *inet = inet_sk(sk); - struct sockaddr_in *sin = (struct sockaddr_in *)msg->msg_name; + DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); struct sk_buff *skb; unsigned int ulen, copied; - int peeked; + int peeked, off = 0; int err; int is_udplite = IS_UDPLITE(sk); - - /* - * Check any passed addresses - */ - if (addr_len) - *addr_len=sizeof(*sin); + bool slow; if (flags & MSG_ERRQUEUE) - return ip_recv_error(sk, msg, len); + return ip_recv_error(sk, msg, len, addr_len); try_again: skb = __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0), - &peeked, &err); + &peeked, &off, &err); if (!skb) goto out; @@ -884,29 +1302,39 @@ try_again: if (skb_csum_unnecessary(skb)) err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied ); + msg->msg_iov, copied); else { - err = skb_copy_and_csum_datagram_iovec(skb, sizeof(struct udphdr), msg->msg_iov); + err = skb_copy_and_csum_datagram_iovec(skb, + sizeof(struct udphdr), + msg->msg_iov); if (err == -EINVAL) goto csum_copy_err; } - if (err) + if (unlikely(err)) { + trace_kfree_skb(skb, udp_recvmsg); + if (!peeked) { + atomic_inc(&sk->sk_drops); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); + } goto out_free; + } if (!peeked) - UDP_INC_STATS_USER(UDP_MIB_INDATAGRAMS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); - sock_recv_timestamp(msg, sk, skb); + sock_recv_ts_and_drops(msg, sk, skb); /* Copy the address. */ - if (sin) - { + if (sin) { sin->sin_family = AF_INET; sin->sin_port = udp_hdr(skb)->source; sin->sin_addr.s_addr = ip_hdr(skb)->saddr; memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); + *addr_len = sizeof(*sin); } if (inet->cmsg_flags) ip_cmsg_recv(msg, skb); @@ -916,20 +1344,23 @@ try_again: err = ulen; out_free: - lock_sock(sk); - skb_free_datagram(sk, skb); - release_sock(sk); + skb_free_datagram_locked(sk, skb); out: return err; csum_copy_err: - lock_sock(sk); - if (!skb_kill_datagram(sk, skb, flags)) - UDP_INC_STATS_USER(UDP_MIB_INERRORS, is_udplite); - release_sock(sk); + slow = lock_sock_fast(sk); + if (!skb_kill_datagram(sk, skb, flags)) { + UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); + UDP_INC_STATS_USER(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + } + unlock_sock_fast(sk, slow); if (noblock) return -EAGAIN; + + /* starting over for a new packet */ + msg->msg_flags &= ~MSG_TRUNC; goto try_again; } @@ -942,19 +1373,125 @@ int udp_disconnect(struct sock *sk, int flags) */ sk->sk_state = TCP_CLOSE; - inet->daddr = 0; - inet->dport = 0; + inet->inet_daddr = 0; + inet->inet_dport = 0; + sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) inet_reset_saddr(sk); if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); - inet->sport = 0; + inet->inet_sport = 0; } sk_dst_reset(sk); return 0; } +EXPORT_SYMBOL(udp_disconnect); + +void udp_lib_unhash(struct sock *sk) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2; + + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + + spin_lock_bh(&hslot->lock); + if (sk_nulls_del_node_init_rcu(sk)) { + hslot->count--; + inet_sk(sk)->inet_num = 0; + sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + } + spin_unlock_bh(&hslot->lock); + } +} +EXPORT_SYMBOL(udp_lib_unhash); + +/* + * inet_rcv_saddr was changed, we must rehash secondary hash + */ +void udp_lib_rehash(struct sock *sk, u16 newhash) +{ + if (sk_hashed(sk)) { + struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_hslot *hslot, *hslot2, *nhslot2; + + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + nhslot2 = udp_hashslot2(udptable, newhash); + udp_sk(sk)->udp_portaddr_hash = newhash; + if (hslot2 != nhslot2) { + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); + /* we must lock primary chain too */ + spin_lock_bh(&hslot->lock); + + spin_lock(&hslot2->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + + spin_unlock_bh(&hslot->lock); + } + } +} +EXPORT_SYMBOL(udp_lib_rehash); + +static void udp_v4_rehash(struct sock *sk) +{ + u16 new_hash = udp4_portaddr_hash(sock_net(sk), + inet_sk(sk)->inet_rcv_saddr, + inet_sk(sk)->inet_num); + udp_lib_rehash(sk, new_hash); +} + +static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) +{ + int rc; + + if (inet_sk(sk)->inet_daddr) { + sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); + } + + rc = sock_queue_rcv_skb(sk, skb); + if (rc < 0) { + int is_udplite = IS_UDPLITE(sk); + + /* Note that an ENOMEM error is charged twice */ + if (rc == -ENOMEM) + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + is_udplite); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + kfree_skb(skb); + trace_udp_fail_queue_rcv_skb(rc, sk); + return -1; + } + + return 0; + +} + +static struct static_key udp_encap_needed __read_mostly; +void udp_encap_enable(void) +{ + if (!static_key_enabled(&udp_encap_needed)) + static_key_slow_inc(&udp_encap_needed); +} +EXPORT_SYMBOL(udp_encap_enable); /* returns: * -1: error @@ -964,7 +1501,7 @@ int udp_disconnect(struct sock *sk, int flags) * Note that in the success and error cases, the skb is assumed to * have either been requeued or freed. */ -int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) +int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { struct udp_sock *up = udp_sk(sk); int rc; @@ -977,7 +1514,9 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) goto drop; nf_reset(skb); - if (up->encap_type) { + if (static_key_false(&udp_encap_needed) && up->encap_type) { + int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); + /* * This is an encapsulation socket so pass the skb to * the socket's udp_encap_rcv() hook. Otherwise, just @@ -990,13 +1529,18 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - if (skb->len > sizeof(struct udphdr) && - up->encap_rcv != NULL) { + encap_rcv = ACCESS_ONCE(up->encap_rcv); + if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { int ret; - ret = (*up->encap_rcv)(sk, skb); + /* Verify checksum before giving to encap */ + if (udp_lib_checksum_complete(skb)) + goto csum_error; + + ret = encap_rcv(sk, skb); if (ret <= 0) { - UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, + UDP_INC_STATS_BH(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); return -ret; } @@ -1022,9 +1566,8 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) * provided by the application." */ if (up->pcrlen == 0) { /* full coverage was set */ - LIMIT_NETDEBUG(KERN_WARNING "UDPLITE: partial coverage " - "%d while full coverage %d requested\n", - UDP_SKB_CB(skb)->cscov, skb->len); + LIMIT_NETDEBUG(KERN_WARNING "UDPLite: partial coverage %d while full coverage %d requested\n", + UDP_SKB_CB(skb)->cscov, skb->len); goto drop; } /* The next case involves violating the min. coverage requested @@ -1034,82 +1577,135 @@ int udp_queue_rcv_skb(struct sock * sk, struct sk_buff *skb) * Therefore the above ...()->partial_cov statement is essential. */ if (UDP_SKB_CB(skb)->cscov < up->pcrlen) { - LIMIT_NETDEBUG(KERN_WARNING - "UDPLITE: coverage %d too small, need min %d\n", - UDP_SKB_CB(skb)->cscov, up->pcrlen); + LIMIT_NETDEBUG(KERN_WARNING "UDPLite: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, up->pcrlen); goto drop; } } - if (sk->sk_filter) { - if (udp_lib_checksum_complete(skb)) - goto drop; + if (rcu_access_pointer(sk->sk_filter) && + udp_lib_checksum_complete(skb)) + goto csum_error; + + + if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) { + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + is_udplite); + goto drop; } - if ((rc = sock_queue_rcv_skb(sk,skb)) < 0) { - /* Note that an ENOMEM error is charged twice */ - if (rc == -ENOMEM) - UDP_INC_STATS_BH(UDP_MIB_RCVBUFERRORS, is_udplite); + rc = 0; + + ipv4_pktinfo_prepare(sk, skb); + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) + rc = __udp_queue_rcv_skb(sk, skb); + else if (sk_add_backlog(sk, skb, sk->sk_rcvbuf)) { + bh_unlock_sock(sk); goto drop; } + bh_unlock_sock(sk); - return 0; + return rc; +csum_error: + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: - UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + atomic_inc(&sk->sk_drops); kfree_skb(skb); return -1; } + +static void flush_stack(struct sock **stack, unsigned int count, + struct sk_buff *skb, unsigned int final) +{ + unsigned int i; + struct sk_buff *skb1 = NULL; + struct sock *sk; + + for (i = 0; i < count; i++) { + sk = stack[i]; + if (likely(skb1 == NULL)) + skb1 = (i == final) ? skb : skb_clone(skb, GFP_ATOMIC); + + if (!skb1) { + atomic_inc(&sk->sk_drops); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + } + + if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0) + skb1 = NULL; + } + if (unlikely(skb1)) + kfree_skb(skb1); +} + +/* For TCP sockets, sk_rx_dst is protected by socket lock + * For UDP, we use xchg() to guard against concurrent changes. + */ +static void udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) +{ + struct dst_entry *old; + + dst_hold(dst); + old = xchg(&sk->sk_rx_dst, dst); + dst_release(old); +} + /* * Multicasts and broadcasts go to each listener. * - * Note: called only from the BH handler context, - * so we don't need to lock the hashes. + * Note: called only from the BH handler context. */ -static int __udp4_lib_mcast_deliver(struct sk_buff *skb, +static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udphdr *uh, __be32 saddr, __be32 daddr, - struct hlist_head udptable[]) + struct udp_table *udptable) { - struct sock *sk; + struct sock *sk, *stack[256 / sizeof(struct sock *)]; + struct udp_hslot *hslot = udp_hashslot(udptable, net, ntohs(uh->dest)); int dif; + unsigned int i, count = 0; - read_lock(&udp_hash_lock); - sk = sk_head(&udptable[ntohs(uh->dest) & (UDP_HTABLE_SIZE - 1)]); + spin_lock(&hslot->lock); + sk = sk_nulls_head(&hslot->head); dif = skb->dev->ifindex; - sk = udp_v4_mcast_next(sk, uh->dest, daddr, uh->source, saddr, dif); - if (sk) { - struct sock *sknext = NULL; + sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); + while (sk) { + stack[count++] = sk; + sk = udp_v4_mcast_next(net, sk_nulls_next(sk), uh->dest, + daddr, uh->source, saddr, dif); + if (unlikely(count == ARRAY_SIZE(stack))) { + if (!sk) + break; + flush_stack(stack, count, skb, ~0); + count = 0; + } + } + /* + * before releasing chain lock, we must take a reference on sockets + */ + for (i = 0; i < count; i++) + sock_hold(stack[i]); - do { - struct sk_buff *skb1 = skb; - - sknext = udp_v4_mcast_next(sk_next(sk), uh->dest, daddr, - uh->source, saddr, dif); - if (sknext) - skb1 = skb_clone(skb, GFP_ATOMIC); - - if (skb1) { - int ret = 0; - - bh_lock_sock_nested(sk); - if (!sock_owned_by_user(sk)) - ret = udp_queue_rcv_skb(sk, skb1); - else - sk_add_backlog(sk, skb1); - bh_unlock_sock(sk); - - if (ret > 0) - /* we should probably re-process instead - * of dropping packets here. */ - kfree_skb(skb1); - } - sk = sknext; - } while (sknext); - } else + spin_unlock(&hslot->lock); + + /* + * do the slow work with no lock held + */ + if (count) { + flush_stack(stack, count, skb, count - 1); + + for (i = 0; i < count; i++) + sock_put(stack[i]); + } else { kfree_skb(skb); - read_unlock(&udp_hash_lock); + } return 0; } @@ -1121,7 +1717,6 @@ static int __udp4_lib_mcast_deliver(struct sk_buff *skb, static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, int proto) { - const struct iphdr *iph; int err; UDP_SKB_CB(skb)->partial_cov = 0; @@ -1133,37 +1728,23 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, return err; } - iph = ip_hdr(skb); - if (uh->check == 0) { - skb->ip_summed = CHECKSUM_UNNECESSARY; - } else if (skb->ip_summed == CHECKSUM_COMPLETE) { - if (!csum_tcpudp_magic(iph->saddr, iph->daddr, skb->len, - proto, skb->csum)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - } - if (!skb_csum_unnecessary(skb)) - skb->csum = csum_tcpudp_nofold(iph->saddr, iph->daddr, - skb->len, proto, 0); - /* Probably, we should checksum udp header (it should be in cache - * in any case) and data in tiny packets (< rx copybreak). - */ - - return 0; + return skb_checksum_init_zero_check(skb, proto, uh->check, + inet_compute_pseudo); } /* * All we need to do is get the socket, and then do a checksum. */ -int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], +int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { struct sock *sk; - struct udphdr *uh = udp_hdr(skb); + struct udphdr *uh; unsigned short ulen; - struct rtable *rt = (struct rtable*)skb->dst; - __be32 saddr = ip_hdr(skb)->saddr; - __be32 daddr = ip_hdr(skb)->daddr; + struct rtable *rt = skb_rtable(skb); + __be32 saddr, daddr; + struct net *net = dev_net(skb->dev); /* * Validate the packet. @@ -1171,7 +1752,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto drop; /* No space for header. */ + uh = udp_hdr(skb); ulen = ntohs(uh->len); + saddr = ip_hdr(skb)->saddr; + daddr = ip_hdr(skb)->daddr; + if (ulen > skb->len) goto short_packet; @@ -1185,20 +1770,34 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (udp4_csum_init(skb, uh, proto)) goto csum_error; - if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) - return __udp4_lib_mcast_deliver(skb, uh, saddr, daddr, udptable); + sk = skb_steal_sock(skb); + if (sk) { + struct dst_entry *dst = skb_dst(skb); + int ret; + + if (unlikely(sk->sk_rx_dst != dst)) + udp_sk_rx_dst_set(sk, dst); + + ret = udp_queue_rcv_skb(sk, skb); + sock_put(sk); + /* a return value > 0 means to resubmit the input, but + * it wants the return to be -protocol, or 0 + */ + if (ret > 0) + return -ret; + return 0; + } else { + if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) + return __udp4_lib_mcast_deliver(net, skb, uh, + saddr, daddr, udptable); - sk = __udp4_lib_lookup(skb->dev->nd_net, saddr, uh->source, daddr, - uh->dest, inet_iif(skb), udptable); + sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); + } if (sk != NULL) { - int ret = 0; - bh_lock_sock_nested(sk); - if (!sock_owned_by_user(sk)) - ret = udp_queue_rcv_skb(sk, skb); - else - sk_add_backlog(sk, skb); - bh_unlock_sock(sk); + int ret; + + ret = udp_queue_rcv_skb(sk, skb); sock_put(sk); /* a return value > 0 means to resubmit the input, but @@ -1217,7 +1816,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], if (udp_lib_checksum_complete(skb)) goto csum_error; - UDP_INC_STATS_BH(UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + UDP_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); /* @@ -1228,14 +1827,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct hlist_head udptable[], return 0; short_packet: - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %u.%u.%u.%u:%u %d/%d to %u.%u.%u.%u:%u\n", - proto == IPPROTO_UDPLITE ? "-Lite" : "", - NIPQUAD(saddr), - ntohs(uh->source), - ulen, - skb->len, - NIPQUAD(daddr), - ntohs(uh->dest)); + LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: short packet: From %pI4:%u %d/%d to %pI4:%u\n", + proto == IPPROTO_UDPLITE ? "Lite" : "", + &saddr, ntohs(uh->source), + ulen, skb->len, + &daddr, ntohs(uh->dest)); goto drop; csum_error: @@ -1243,50 +1839,192 @@ csum_error: * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ - LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %d.%d.%d.%d:%d to %d.%d.%d.%d:%d ulen %d\n", - proto == IPPROTO_UDPLITE ? "-Lite" : "", - NIPQUAD(saddr), - ntohs(uh->source), - NIPQUAD(daddr), - ntohs(uh->dest), + LIMIT_NETDEBUG(KERN_DEBUG "UDP%s: bad checksum. From %pI4:%u to %pI4:%u ulen %d\n", + proto == IPPROTO_UDPLITE ? "Lite" : "", + &saddr, ntohs(uh->source), &daddr, ntohs(uh->dest), ulen); + UDP_INC_STATS_BH(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: - UDP_INC_STATS_BH(UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); kfree_skb(skb); return 0; } +/* We can only early demux multicast if there is a single matching socket. + * If more than one socket found returns NULL + */ +static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net, + __be16 loc_port, __be32 loc_addr, + __be16 rmt_port, __be32 rmt_addr, + int dif) +{ + struct sock *sk, *result; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(loc_port); + unsigned int count, slot = udp_hashfn(net, hnum, udp_table.mask); + struct udp_hslot *hslot = &udp_table.hash[slot]; + + /* Do not bother scanning a too big list */ + if (hslot->count > 10) + return NULL; + + rcu_read_lock(); +begin: + count = 0; + result = NULL; + sk_nulls_for_each_rcu(sk, node, &hslot->head) { + if (__udp_is_mcast_sock(net, sk, + loc_port, loc_addr, + rmt_port, rmt_addr, + dif, hnum)) { + result = sk; + ++count; + } + } + /* + * if the nulls value we got at the end of this lookup is + * not the expected one, we must restart lookup. + * We probably met an item that was moved to another chain. + */ + if (get_nulls_value(node) != slot) + goto begin; + + if (result) { + if (count != 1 || + unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) + result = NULL; + else if (unlikely(!__udp_is_mcast_sock(net, result, + loc_port, loc_addr, + rmt_port, rmt_addr, + dif, hnum))) { + sock_put(result); + result = NULL; + } + } + rcu_read_unlock(); + return result; +} + +/* For unicast we should only early demux connected sockets or we can + * break forwarding setups. The chains here can be long so only check + * if the first socket is an exact match and if not move on. + */ +static struct sock *__udp4_lib_demux_lookup(struct net *net, + __be16 loc_port, __be32 loc_addr, + __be16 rmt_port, __be32 rmt_addr, + int dif) +{ + struct sock *sk, *result; + struct hlist_nulls_node *node; + unsigned short hnum = ntohs(loc_port); + unsigned int hash2 = udp4_portaddr_hash(net, loc_addr, hnum); + unsigned int slot2 = hash2 & udp_table.mask; + struct udp_hslot *hslot2 = &udp_table.hash2[slot2]; + INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); + const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum); + + rcu_read_lock(); + result = NULL; + udp_portaddr_for_each_entry_rcu(sk, node, &hslot2->head) { + if (INET_MATCH(sk, net, acookie, + rmt_addr, loc_addr, ports, dif)) + result = sk; + /* Only check first socket in chain */ + break; + } + + if (result) { + if (unlikely(!atomic_inc_not_zero_hint(&result->sk_refcnt, 2))) + result = NULL; + else if (unlikely(!INET_MATCH(sk, net, acookie, + rmt_addr, loc_addr, + ports, dif))) { + sock_put(result); + result = NULL; + } + } + rcu_read_unlock(); + return result; +} + +void udp_v4_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + const struct iphdr *iph; + const struct udphdr *uh; + struct sock *sk; + struct dst_entry *dst; + int dif = skb->dev->ifindex; + + /* validate the packet */ + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) + return; + + iph = ip_hdr(skb); + uh = udp_hdr(skb); + + if (skb->pkt_type == PACKET_BROADCAST || + skb->pkt_type == PACKET_MULTICAST) + sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, + uh->source, iph->saddr, dif); + else if (skb->pkt_type == PACKET_HOST) + sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, + uh->source, iph->saddr, dif); + else + return; + + if (!sk) + return; + + skb->sk = sk; + skb->destructor = sock_edemux; + dst = sk->sk_rx_dst; + + if (dst) + dst = dst_check(dst, 0); + if (dst) + skb_dst_set_noref(skb, dst); +} + int udp_rcv(struct sk_buff *skb) { - return __udp4_lib_rcv(skb, udp_hash, IPPROTO_UDP); + return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); } -int udp_destroy_sock(struct sock *sk) +void udp_destroy_sock(struct sock *sk) { - lock_sock(sk); + struct udp_sock *up = udp_sk(sk); + bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); - release_sock(sk); - return 0; + unlock_sock_fast(sk, slow); + if (static_key_false(&udp_encap_needed) && up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = ACCESS_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } } /* * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen, + char __user *optval, unsigned int optlen, int (*push_pending_frames)(struct sock *)) { struct udp_sock *up = udp_sk(sk); - int val; + int val, valbool; int err = 0; int is_udplite = IS_UDPLITE(sk); - if (optlen<sizeof(int)) + if (optlen < sizeof(int)) return -EINVAL; if (get_user(val, (int __user *)optval)) return -EFAULT; + valbool = val ? 1 : 0; + switch (optname) { case UDP_CORK: if (val != 0) { @@ -1308,6 +2046,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, /* FALLTHROUGH */ case UDP_ENCAP_L2TPINUDP: up->encap_type = val; + udp_encap_enable(); break; default: err = -ENOPROTOOPT; @@ -1315,6 +2054,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, } break; + case UDP_NO_CHECK6_TX: + up->no_check6_tx = valbool; + break; + + case UDP_NO_CHECK6_RX: + up->no_check6_rx = valbool; + break; + /* * UDP-Lite's partial checksum coverage (RFC 3828). */ @@ -1325,6 +2072,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Illegal coverage: use default (8) */ val = 8; + else if (val > USHRT_MAX) + val = USHRT_MAX; up->pcslen = val; up->pcflag |= UDPLITE_SEND_CC; break; @@ -1337,6 +2086,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return -ENOPROTOOPT; if (val != 0 && val < 8) /* Avoid silly minimal values. */ val = 8; + else if (val > USHRT_MAX) + val = USHRT_MAX; up->pcrlen = val; up->pcflag |= UDPLITE_RECV_CC; break; @@ -1348,9 +2099,10 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return err; } +EXPORT_SYMBOL(udp_lib_setsockopt); int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1360,7 +2112,7 @@ int udp_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_COMPAT int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, int optlen) + char __user *optval, unsigned int optlen) { if (level == SOL_UDP || level == SOL_UDPLITE) return udp_lib_setsockopt(sk, level, optname, optval, optlen, @@ -1375,7 +2127,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, struct udp_sock *up = udp_sk(sk); int val, len; - if (get_user(len,optlen)) + if (get_user(len, optlen)) return -EFAULT; len = min_t(unsigned int, len, sizeof(int)); @@ -1392,6 +2144,14 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->encap_type; break; + case UDP_NO_CHECK6_TX: + val = up->no_check6_tx; + break; + + case UDP_NO_CHECK6_RX: + val = up->no_check6_rx; + break; + /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: @@ -1408,10 +2168,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (put_user(len, optlen)) return -EFAULT; - if (copy_to_user(optval, &val,len)) + if (copy_to_user(optval, &val, len)) return -EFAULT; return 0; } +EXPORT_SYMBOL(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -1447,34 +2208,18 @@ unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) { unsigned int mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - int is_lite = IS_UDPLITE(sk); - /* Check for false positives due to checksum errors */ - if ( (mask & POLLRDNORM) && - !(file->f_flags & O_NONBLOCK) && - !(sk->sk_shutdown & RCV_SHUTDOWN)){ - struct sk_buff_head *rcvq = &sk->sk_receive_queue; - struct sk_buff *skb; - - spin_lock_bh(&rcvq->lock); - while ((skb = skb_peek(rcvq)) != NULL && - udp_lib_checksum_complete(skb)) { - UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_lite); - __skb_unlink(skb, rcvq); - kfree_skb(skb); - } - spin_unlock_bh(&rcvq->lock); + sock_rps_record_flow(sk); - /* nothing to see, move along */ - if (skb == NULL) - mask &= ~(POLLIN | POLLRDNORM); - } + /* Check for false positives due to checksum errors */ + if ((mask & POLLRDNORM) && !(file->f_flags & O_NONBLOCK) && + !(sk->sk_shutdown & RCV_SHUTDOWN) && !first_packet_length(sk)) + mask &= ~(POLLIN | POLLRDNORM); return mask; } - -DEFINE_PROTO_INUSE(udp) +EXPORT_SYMBOL(udp_poll); struct proto udp_prot = { .name = "UDP", @@ -1489,36 +2234,52 @@ struct proto udp_prot = { .sendmsg = udp_sendmsg, .recvmsg = udp_recvmsg, .sendpage = udp_sendpage, - .backlog_rcv = udp_queue_rcv_skb, + .backlog_rcv = __udp_queue_rcv_skb, + .release_cb = ip4_datagram_release_cb, .hash = udp_lib_hash, .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, .get_port = udp_v4_get_port, .memory_allocated = &udp_memory_allocated, .sysctl_mem = sysctl_udp_mem, .sysctl_wmem = &sysctl_udp_wmem_min, .sysctl_rmem = &sysctl_udp_rmem_min, .obj_size = sizeof(struct udp_sock), + .slab_flags = SLAB_DESTROY_BY_RCU, + .h.udp_table = &udp_table, #ifdef CONFIG_COMPAT .compat_setsockopt = compat_udp_setsockopt, .compat_getsockopt = compat_udp_getsockopt, #endif - REF_PROTO_INUSE(udp) + .clear_sk = sk_prot_clear_portaddr_nulls, }; +EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS -static struct sock *udp_get_first(struct seq_file *seq) +static struct sock *udp_get_first(struct seq_file *seq, int start) { struct sock *sk; struct udp_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); + + for (state->bucket = start; state->bucket <= state->udp_table->mask; + ++state->bucket) { + struct hlist_nulls_node *node; + struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + + if (hlist_nulls_empty(&hslot->head)) + continue; - for (state->bucket = 0; state->bucket < UDP_HTABLE_SIZE; ++state->bucket) { - struct hlist_node *node; - sk_for_each(sk, node, state->hashtable + state->bucket) { + spin_lock_bh(&hslot->lock); + sk_nulls_for_each(sk, node, &hslot->head) { + if (!net_eq(sock_net(sk), net)) + continue; if (sk->sk_family == state->family) goto found; } + spin_unlock_bh(&hslot->lock); } sk = NULL; found: @@ -1528,23 +2289,23 @@ found: static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { struct udp_iter_state *state = seq->private; + struct net *net = seq_file_net(seq); do { - sk = sk_next(sk); -try_again: - ; - } while (sk && sk->sk_family != state->family); + sk = sk_nulls_next(sk); + } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); - if (!sk && ++state->bucket < UDP_HTABLE_SIZE) { - sk = sk_head(state->hashtable + state->bucket); - goto try_again; + if (!sk) { + if (state->bucket <= state->udp_table->mask) + spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); + return udp_get_first(seq, state->bucket + 1); } return sk; } static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) { - struct sock *sk = udp_get_first(seq); + struct sock *sk = udp_get_first(seq, 0); if (sk) while (pos && (sk = udp_get_next(seq, sk)) != NULL) @@ -1553,9 +2314,10 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) } static void *udp_seq_start(struct seq_file *seq, loff_t *pos) - __acquires(udp_hash_lock) { - read_lock(&udp_hash_lock); + struct udp_iter_state *state = seq->private; + state->bucket = MAX_UDP_PORTS; + return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } @@ -1573,137 +2335,189 @@ static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) } static void udp_seq_stop(struct seq_file *seq, void *v) - __releases(udp_hash_lock) { - read_unlock(&udp_hash_lock); + struct udp_iter_state *state = seq->private; + + if (state->bucket <= state->udp_table->mask) + spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); } -static int udp_seq_open(struct inode *inode, struct file *file) +int udp_seq_open(struct inode *inode, struct file *file) { - struct udp_seq_afinfo *afinfo = PDE(inode)->data; - struct seq_file *seq; - int rc = -ENOMEM; - struct udp_iter_state *s = kzalloc(sizeof(*s), GFP_KERNEL); + struct udp_seq_afinfo *afinfo = PDE_DATA(inode); + struct udp_iter_state *s; + int err; - if (!s) - goto out; + err = seq_open_net(inode, file, &afinfo->seq_ops, + sizeof(struct udp_iter_state)); + if (err < 0) + return err; + + s = ((struct seq_file *)file->private_data)->private; s->family = afinfo->family; - s->hashtable = afinfo->hashtable; - s->seq_ops.start = udp_seq_start; - s->seq_ops.next = udp_seq_next; - s->seq_ops.show = afinfo->seq_show; - s->seq_ops.stop = udp_seq_stop; - - rc = seq_open(file, &s->seq_ops); - if (rc) - goto out_kfree; - - seq = file->private_data; - seq->private = s; -out: - return rc; -out_kfree: - kfree(s); - goto out; + s->udp_table = afinfo->udp_table; + return err; } +EXPORT_SYMBOL(udp_seq_open); /* ------------------------------------------------------------------------ */ -int udp_proc_register(struct udp_seq_afinfo *afinfo) +int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) { struct proc_dir_entry *p; int rc = 0; - if (!afinfo) - return -EINVAL; - afinfo->seq_fops->owner = afinfo->owner; - afinfo->seq_fops->open = udp_seq_open; - afinfo->seq_fops->read = seq_read; - afinfo->seq_fops->llseek = seq_lseek; - afinfo->seq_fops->release = seq_release_private; - - p = proc_net_fops_create(&init_net, afinfo->name, S_IRUGO, afinfo->seq_fops); - if (p) - p->data = afinfo; - else + afinfo->seq_ops.start = udp_seq_start; + afinfo->seq_ops.next = udp_seq_next; + afinfo->seq_ops.stop = udp_seq_stop; + + p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, + afinfo->seq_fops, afinfo); + if (!p) rc = -ENOMEM; return rc; } +EXPORT_SYMBOL(udp_proc_register); -void udp_proc_unregister(struct udp_seq_afinfo *afinfo) +void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo) { - if (!afinfo) - return; - proc_net_remove(&init_net, afinfo->name); - memset(afinfo->seq_fops, 0, sizeof(*afinfo->seq_fops)); + remove_proc_entry(afinfo->name, net->proc_net); } +EXPORT_SYMBOL(udp_proc_unregister); /* ------------------------------------------------------------------------ */ -static void udp4_format_sock(struct sock *sp, char *tmpbuf, int bucket) +static void udp4_format_sock(struct sock *sp, struct seq_file *f, + int bucket) { struct inet_sock *inet = inet_sk(sp); - __be32 dest = inet->daddr; - __be32 src = inet->rcv_saddr; - __u16 destp = ntohs(inet->dport); - __u16 srcp = ntohs(inet->sport); + __be32 dest = inet->inet_daddr; + __be32 src = inet->inet_rcv_saddr; + __u16 destp = ntohs(inet->inet_dport); + __u16 srcp = ntohs(inet->inet_sport); - sprintf(tmpbuf, "%4d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %p", + seq_printf(f, "%5d: %08X:%04X %08X:%04X" + " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %d", bucket, src, srcp, dest, destp, sp->sk_state, - atomic_read(&sp->sk_wmem_alloc), - atomic_read(&sp->sk_rmem_alloc), - 0, 0L, 0, sock_i_uid(sp), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp); + sk_wmem_alloc_get(sp), + sk_rmem_alloc_get(sp), + 0, 0L, 0, + from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), + 0, sock_i_ino(sp), + atomic_read(&sp->sk_refcnt), sp, + atomic_read(&sp->sk_drops)); } int udp4_seq_show(struct seq_file *seq, void *v) { + seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) - seq_printf(seq, "%-127s\n", - " sl local_address rem_address st tx_queue " + seq_puts(seq, " sl local_address rem_address st tx_queue " "rx_queue tr tm->when retrnsmt uid timeout " - "inode"); + "inode ref pointer drops"); else { - char tmpbuf[129]; struct udp_iter_state *state = seq->private; - udp4_format_sock(v, tmpbuf, state->bucket); - seq_printf(seq, "%-127s\n", tmpbuf); + udp4_format_sock(v, seq, state->bucket); } + seq_pad(seq, '\n'); return 0; } +static const struct file_operations udp_afinfo_seq_fops = { + .owner = THIS_MODULE, + .open = udp_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = seq_release_net +}; + /* ------------------------------------------------------------------------ */ -static struct file_operations udp4_seq_fops; static struct udp_seq_afinfo udp4_seq_afinfo = { - .owner = THIS_MODULE, .name = "udp", .family = AF_INET, - .hashtable = udp_hash, - .seq_show = udp4_seq_show, - .seq_fops = &udp4_seq_fops, + .udp_table = &udp_table, + .seq_fops = &udp_afinfo_seq_fops, + .seq_ops = { + .show = udp4_seq_show, + }, +}; + +static int __net_init udp4_proc_init_net(struct net *net) +{ + return udp_proc_register(net, &udp4_seq_afinfo); +} + +static void __net_exit udp4_proc_exit_net(struct net *net) +{ + udp_proc_unregister(net, &udp4_seq_afinfo); +} + +static struct pernet_operations udp4_net_ops = { + .init = udp4_proc_init_net, + .exit = udp4_proc_exit_net, }; int __init udp4_proc_init(void) { - return udp_proc_register(&udp4_seq_afinfo); + return register_pernet_subsys(&udp4_net_ops); } void udp4_proc_exit(void) { - udp_proc_unregister(&udp4_seq_afinfo); + unregister_pernet_subsys(&udp4_net_ops); } #endif /* CONFIG_PROC_FS */ +static __initdata unsigned long uhash_entries; +static int __init set_uhash_entries(char *str) +{ + ssize_t ret; + + if (!str) + return 0; + + ret = kstrtoul(str, 0, &uhash_entries); + if (ret) + return 0; + + if (uhash_entries && uhash_entries < UDP_HTABLE_SIZE_MIN) + uhash_entries = UDP_HTABLE_SIZE_MIN; + return 1; +} +__setup("uhash_entries=", set_uhash_entries); + +void __init udp_table_init(struct udp_table *table, const char *name) +{ + unsigned int i; + + table->hash = alloc_large_system_hash(name, + 2 * sizeof(struct udp_hslot), + uhash_entries, + 21, /* one slot per 2 MB */ + 0, + &table->log, + &table->mask, + UDP_HTABLE_SIZE_MIN, + 64 * 1024); + + table->hash2 = table->hash + (table->mask + 1); + for (i = 0; i <= table->mask; i++) { + INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); + table->hash[i].count = 0; + spin_lock_init(&table->hash[i].lock); + } + for (i = 0; i <= table->mask; i++) { + INIT_HLIST_NULLS_HEAD(&table->hash2[i].head, i); + table->hash2[i].count = 0; + spin_lock_init(&table->hash2[i].lock); + } +} + void __init udp_init(void) { unsigned long limit; - /* Set the pressure threshold up by the same strategy of TCP. It is a - * fraction of global memory that is up to 1/2 at 256 MB, decreasing - * toward zero with the amount of memory, with a floor of 128 pages. - */ - limit = min(nr_all_pages, 1UL<<(28-PAGE_SHIFT)) >> (20-PAGE_SHIFT); - limit = (limit * (nr_all_pages >> (20-PAGE_SHIFT))) >> (PAGE_SHIFT-11); + udp_table_init(&udp_table, "UDP"); + limit = nr_free_buffer_pages() / 8; limit = max(limit, 128UL); sysctl_udp_mem[0] = limit / 4 * 3; sysctl_udp_mem[1] = limit; @@ -1713,18 +2527,78 @@ void __init udp_init(void) sysctl_udp_wmem_min = SK_MEM_QUANTUM; } -EXPORT_SYMBOL(udp_disconnect); -EXPORT_SYMBOL(udp_hash); -EXPORT_SYMBOL(udp_hash_lock); -EXPORT_SYMBOL(udp_ioctl); -EXPORT_SYMBOL(udp_get_port); -EXPORT_SYMBOL(udp_prot); -EXPORT_SYMBOL(udp_sendmsg); -EXPORT_SYMBOL(udp_lib_getsockopt); -EXPORT_SYMBOL(udp_lib_setsockopt); -EXPORT_SYMBOL(udp_poll); +struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, + netdev_features_t features) +{ + struct sk_buff *segs = ERR_PTR(-EINVAL); + u16 mac_offset = skb->mac_header; + int mac_len = skb->mac_len; + int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb); + __be16 protocol = skb->protocol; + netdev_features_t enc_features; + int udp_offset, outer_hlen; + unsigned int oldlen; + bool need_csum; + + oldlen = (u16)~skb->len; + + if (unlikely(!pskb_may_pull(skb, tnl_hlen))) + goto out; -#ifdef CONFIG_PROC_FS -EXPORT_SYMBOL(udp_proc_register); -EXPORT_SYMBOL(udp_proc_unregister); -#endif + skb->encapsulation = 0; + __skb_pull(skb, tnl_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, skb_inner_network_offset(skb)); + skb->mac_len = skb_inner_network_offset(skb); + skb->protocol = htons(ETH_P_TEB); + + need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP_TUNNEL_CSUM); + if (need_csum) + skb->encap_hdr_csum = 1; + + /* segment inner packet. */ + enc_features = skb->dev->hw_enc_features & netif_skb_features(skb); + segs = skb_mac_gso_segment(skb, enc_features); + if (!segs || IS_ERR(segs)) { + skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset, + mac_len); + goto out; + } + + outer_hlen = skb_tnl_header_len(skb); + udp_offset = outer_hlen - tnl_hlen; + skb = segs; + do { + struct udphdr *uh; + int len; + + skb_reset_inner_headers(skb); + skb->encapsulation = 1; + + skb->mac_len = mac_len; + + skb_push(skb, outer_hlen); + skb_reset_mac_header(skb); + skb_set_network_header(skb, mac_len); + skb_set_transport_header(skb, udp_offset); + len = skb->len - udp_offset; + uh = udp_hdr(skb); + uh->len = htons(len); + + if (need_csum) { + __be32 delta = htonl(oldlen + len); + + uh->check = ~csum_fold((__force __wsum) + ((__force u32)uh->check + + (__force u32)delta)); + uh->check = gso_make_checksum(skb, ~uh->check); + + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } + + skb->protocol = protocol; + } while ((skb = skb->next)); +out: + return segs; +} |