diff options
Diffstat (limited to 'net/ipv4/udp.c')
| -rw-r--r-- | net/ipv4/udp.c | 3505 |
1 files changed, 2595 insertions, 910 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 766e6bab9113..ffe074cb5865 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-or-later /* * INET An implementation of the TCP/IP protocol suite for the LINUX * operating system. INET is implemented using the BSD Socket @@ -67,29 +68,24 @@ * YOSHIFUJI Hideaki @USAGI and: Support IPV6_V6ONLY socket option, which * Alexey Kuznetsov: allow both IPv4 and IPv6 sockets to bind * a single port at the same time. - * Derek Atkins <derek@ihtfp.com>: Add Encapulation Support + * Derek Atkins <derek@ihtfp.com>: Add Encapsulation Support * James Chapman : Add L2TP encapsulation type. - * - * - * 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. */ #define pr_fmt(fmt) "UDP: " fmt -#include <asm/uaccess.h> +#include <linux/bpf-cgroup.h> +#include <linux/uaccess.h> #include <asm/ioctls.h> -#include <linux/bootmem.h> +#include <linux/memblock.h> #include <linux/highmem.h> -#include <linux/swap.h> #include <linux/types.h> #include <linux/fcntl.h> #include <linux/module.h> #include <linux/socket.h> #include <linux/sockios.h> #include <linux/igmp.h> +#include <linux/inetdevice.h> #include <linux/in.h> #include <linux/errno.h> #include <linux/timer.h> @@ -97,67 +93,80 @@ #include <linux/inet.h> #include <linux/netdevice.h> #include <linux/slab.h> +#include <linux/sock_diag.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/ip.h> +#include <net/ip_tunnels.h> #include <net/route.h> #include <net/checksum.h> +#include <net/gso.h> #include <net/xfrm.h> #include <trace/events/udp.h> #include <linux/static_key.h> +#include <linux/btf_ids.h> #include <trace/events/skb.h> #include <net/busy_poll.h> #include "udp_impl.h" +#include <net/sock_reuseport.h> +#include <net/addrconf.h> +#include <net/udp_tunnel.h> +#include <net/gro.h> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6_stubs.h> +#endif +#include <net/rps.h> struct udp_table udp_table __read_mostly; -EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; -EXPORT_SYMBOL(sysctl_udp_mem); - -int sysctl_udp_rmem_min __read_mostly; -EXPORT_SYMBOL(sysctl_udp_rmem_min); +EXPORT_IPV6_MOD(sysctl_udp_mem); -int sysctl_udp_wmem_min __read_mostly; -EXPORT_SYMBOL(sysctl_udp_wmem_min); - -atomic_long_t udp_memory_allocated; -EXPORT_SYMBOL(udp_memory_allocated); +DEFINE_PER_CPU(int, udp_memory_per_cpu_fw_alloc); +EXPORT_PER_CPU_SYMBOL_GPL(udp_memory_per_cpu_fw_alloc); #define MAX_UDP_PORTS 65536 -#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN) +#define PORTS_PER_CHAIN (MAX_UDP_PORTS / UDP_HTABLE_SIZE_MIN_PERNET) + +static struct udp_table *udp_get_table_prot(struct sock *sk) +{ + return sk->sk_prot->h.udp_table ? : sock_net(sk)->ipv4.udp_table; +} 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 *sk, unsigned int log) { + kuid_t uid = sk_uid(sk); struct sock *sk2; - struct hlist_nulls_node *node; - kuid_t uid = sock_i_uid(sk); - sk_nulls_for_each(sk2, node, &hslot->head) + sk_for_each(sk2, &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) + inet_rcv_saddr_equal(sk, sk2, true)) { + if (sk2->sk_reuseport && sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + uid_eq(uid, sk_uid(sk2))) { + if (!bitmap) + return 0; + } else { + if (!bitmap) + return 1; __set_bit(udp_sk(sk2)->udp_port_hash >> log, bitmap); - else - return 1; + } } + } return 0; } @@ -166,64 +175,86 @@ static int udp_lib_lport_inuse(struct net *net, __u16 num, * 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 udp_hslot *hslot2, + struct sock *sk) { + kuid_t uid = sk_uid(sk); 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) + udp_portaddr_for_each_entry(sk2, &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; + inet_rcv_saddr_equal(sk, sk2, true)) { + if (sk2->sk_reuseport && sk->sk_reuseport && + !rcu_access_pointer(sk->sk_reuseport_cb) && + uid_eq(uid, sk_uid(sk2))) { + res = 0; + } else { + res = 1; + } break; } + } spin_unlock(&hslot2->lock); return res; } +static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot) +{ + struct net *net = sock_net(sk); + kuid_t uid = sk_uid(sk); + struct sock *sk2; + + sk_for_each(sk2, &hslot->head) { + if (net_eq(sock_net(sk2), net) && + sk2 != sk && + sk2->sk_family == sk->sk_family && + ipv6_only_sock(sk2) == ipv6_only_sock(sk) && + (udp_sk(sk2)->udp_port_hash == udp_sk(sk)->udp_port_hash) && + (sk2->sk_bound_dev_if == sk->sk_bound_dev_if) && + sk2->sk_reuseport && uid_eq(uid, sk_uid(sk2)) && + inet_rcv_saddr_equal(sk, sk2, false)) { + return reuseport_add_sock(sk, sk2, + inet_rcv_saddr_any(sk)); + } + } + + return reuseport_alloc(sk, inet_rcv_saddr_any(sk)); +} + /** * udp_lib_get_port - UDP/-Lite port lookup for IPv4 and IPv6 * * @sk: socket struct in question * @snum: port number to look up - * @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, - int (*saddr_comp)(const struct sock *sk1, - const struct sock *sk2), unsigned int hash2_nulladdr) { + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; - struct udp_table *udptable = sk->sk_prot->h.udp_table; - int error = 1; struct net *net = sock_net(sk); + int error = -EADDRINUSE; if (!snum) { + DECLARE_BITMAP(bitmap, PORTS_PER_CHAIN); + unsigned short first, last; 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_sk_get_local_port_range(sk, &low, &high); remaining = (high - low) + 1; - rand = net_random(); - first = (((u64)rand * remaining) >> 32) + low; + rand = get_random_u32(); + first = reciprocal_scale(rand, remaining) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE */ @@ -234,7 +265,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, bitmap_zero(bitmap, PORTS_PER_CHAIN); spin_lock_bh(&hslot->lock); udp_lib_lport_inuse(net, snum, hslot, bitmap, sk, - saddr_comp, udptable->log); + udptable->log); snum = first; /* @@ -245,11 +276,12 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, do { if (low <= snum && snum <= high && !test_bit(snum >> udptable->log, bitmap) && - !inet_is_reserved_local_port(snum)) + !inet_is_local_reserved_port(net, snum)) goto found; snum += rand; } while (snum != first); spin_unlock_bh(&hslot->lock); + cond_resched(); } while (++first != last); goto fail; } else { @@ -266,12 +298,11 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, if (hslot->count < hslot2->count) goto scan_primary_hash; - exist = udp_lib_lport_inuse2(net, snum, hslot2, - sk, saddr_comp); + exist = udp_lib_lport_inuse2(net, snum, hslot2, sk); if (!exist && (hash2_nulladdr != slot2)) { hslot2 = udp_hashslot2(udptable, hash2_nulladdr); exist = udp_lib_lport_inuse2(net, snum, hslot2, - sk, saddr_comp); + sk); } if (exist) goto fail_unlock; @@ -279,8 +310,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, goto found; } scan_primary_hash: - if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, - saddr_comp, 0)) + if (udp_lib_lport_inuse(net, snum, hslot, NULL, sk, 0)) goto fail_unlock; } found: @@ -288,257 +318,427 @@ found: 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); + if (sk->sk_reuseport && + udp_reuseport_add_sock(sk, hslot)) { + inet_sk(sk)->inet_num = 0; + udp_sk(sk)->udp_port_hash = 0; + udp_sk(sk)->udp_portaddr_hash ^= snum; + goto fail_unlock; + } + + sock_set_flag(sk, SOCK_RCU_FREE); + + sk_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); + if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport && + sk->sk_family == AF_INET6) + hlist_add_tail_rcu(&udp_sk(sk)->udp_portaddr_node, + &hslot2->head); + else + hlist_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); - -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)); -} - -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; -} +EXPORT_IPV6_MOD(udp_lib_get_port); 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); + ipv4_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); + ipv4_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); + return udp_lib_get_port(sk, snum, hash2_nulladdr); } -static inline int compute_score(struct sock *sk, struct net *net, __be32 saddr, - unsigned short hnum, - __be16 sport, __be32 daddr, __be16 dport, int dif) +static int compute_score(struct sock *sk, const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum, + int dif, int sdif) { - int score = -1; + int score; + struct inet_sock *inet; + bool dev_match; - 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); + if (!net_eq(sock_net(sk), net) || + udp_sk(sk)->udp_port_hash != hnum || + ipv6_only_sock(sk)) + return -1; - 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; - } + if (sk->sk_rcv_saddr != daddr) + return -1; + + score = (sk->sk_family == PF_INET) ? 2 : 1; + + inet = inet_sk(sk); + 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; + } + + dev_match = udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, + dif, sdif); + if (!dev_match) + return -1; + if (sk->sk_bound_dev_if) + score += 4; + + if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) + score++; return score; } -/* - * 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) +u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport, + const __be32 faddr, const __be16 fport) { - int score = -1; + net_get_random_once(&udp_ehash_secret, sizeof(udp_ehash_secret)); - 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; + return __inet_ehashfn(laddr, lport, faddr, fport, + udp_ehash_secret + net_hash_mix(net)); +} +EXPORT_IPV6_MOD(udp_ehashfn); - 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; +/** + * udp4_lib_lookup1() - Simplified lookup using primary hash (destination port) + * @net: Network namespace + * @saddr: Source address, network order + * @sport: Source port, network order + * @daddr: Destination address, network order + * @hnum: Destination port, host order + * @dif: Destination interface index + * @sdif: Destination bridge port index, if relevant + * @udptable: Set of UDP hash tables + * + * Simplified lookup to be used as fallback if no sockets are found due to a + * potential race between (receive) address change, and lookup happening before + * the rehash operation. This function ignores SO_REUSEPORT groups while scoring + * result sockets, because if we have one, we don't need the fallback at all. + * + * Called under rcu_read_lock(). + * + * Return: socket with highest matching score if any, NULL if none + */ +static struct sock *udp4_lib_lookup1(const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, + const struct udp_table *udptable) +{ + unsigned int slot = udp_hashfn(net, hnum, udptable->mask); + struct udp_hslot *hslot = &udptable->hash[slot]; + struct sock *sk, *result = NULL; + int score, badness = 0; + + sk_for_each_rcu(sk, &hslot->head) { + score = compute_score(sk, net, + saddr, sport, daddr, hnum, dif, sdif); + if (score > badness) { + result = sk; + badness = score; } } - return score; -} + return result; +} -/* 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) +/* called with rcu_read_lock() */ +static struct sock *udp4_lib_lookup2(const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, + struct udp_hslot *hslot2, + struct sk_buff *skb) { struct sock *sk, *result; - struct hlist_nulls_node *node; - int score, badness, matches = 0, reuseport = 0; - u32 hash = 0; + int score, badness; + bool need_rescore; -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); + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { + need_rescore = false; +rescore: + score = compute_score(need_rescore ? result : sk, net, saddr, + sport, daddr, hnum, dif, sdif); if (score > badness) { - result = sk; badness = score; - reuseport = sk->sk_reuseport; - if (reuseport) { - hash = inet_ehashfn(net, daddr, hnum, - saddr, sport); - matches = 1; + + if (need_rescore) + continue; + + if (sk->sk_state == TCP_ESTABLISHED) { + result = sk; + continue; } - } else if (score == badness && reuseport) { - matches++; - if (((u64)hash * matches) >> 32 == 0) + + result = inet_lookup_reuseport(net, sk, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, udp_ehashfn); + if (!result) { result = sk; - hash = next_pseudo_random32(hash); + continue; + } + + /* Fall back to scoring if group has connections */ + if (!reuseport_has_conns(sk)) + return result; + + /* Reuseport logic returned an error, keep original score. */ + if (IS_ERR(result)) + continue; + + /* compute_score is too long of a function to be + * inlined, and calling it again here yields + * measurable overhead for some + * workloads. Work around it by jumping + * backwards to rescore 'result'. + */ + need_rescore = true; + goto rescore; } } - /* - * 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. + return result; +} + +#if IS_ENABLED(CONFIG_BASE_SMALL) +static struct sock *udp4_lib_lookup4(const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, + struct udp_table *udptable) +{ + return NULL; +} + +static void udp_rehash4(struct udp_table *udptable, struct sock *sk, + u16 newhash4) +{ +} + +static void udp_unhash4(struct udp_table *udptable, struct sock *sk) +{ +} +#else /* !CONFIG_BASE_SMALL */ +static struct sock *udp4_lib_lookup4(const struct net *net, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned int hnum, + int dif, int sdif, + struct udp_table *udptable) +{ + const __portpair ports = INET_COMBINED_PORTS(sport, hnum); + const struct hlist_nulls_node *node; + struct udp_hslot *hslot4; + unsigned int hash4, slot; + struct udp_sock *up; + struct sock *sk; + + hash4 = udp_ehashfn(net, daddr, hnum, saddr, sport); + slot = hash4 & udptable->mask; + hslot4 = &udptable->hash4[slot]; + INET_ADDR_COOKIE(acookie, saddr, daddr); + +begin: + /* SLAB_TYPESAFE_BY_RCU not used, so we don't need to touch sk_refcnt */ + udp_lrpa_for_each_entry_rcu(up, node, &hslot4->nulls_head) { + sk = (struct sock *)up; + if (inet_match(net, sk, acookie, ports, dif, sdif)) + return sk; + } + + /* if the nulls value we got at the end of this lookup is not the + * expected one, we must restart lookup. We probably met an item that + * was moved to another chain due to rehash. */ - if (get_nulls_value(node) != slot2) + 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_score2(result, net, saddr, sport, - daddr, hnum, dif) < badness)) { - sock_put(result); - goto begin; - } + + return NULL; +} + +/* udp_rehash4() only checks hslot4, and hash4_cnt is not processed. */ +static void udp_rehash4(struct udp_table *udptable, struct sock *sk, + u16 newhash4) +{ + struct udp_hslot *hslot4, *nhslot4; + + hslot4 = udp_hashslot4(udptable, udp_sk(sk)->udp_lrpa_hash); + nhslot4 = udp_hashslot4(udptable, newhash4); + udp_sk(sk)->udp_lrpa_hash = newhash4; + + if (hslot4 != nhslot4) { + spin_lock_bh(&hslot4->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_lrpa_node); + hslot4->count--; + spin_unlock_bh(&hslot4->lock); + + spin_lock_bh(&nhslot4->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_lrpa_node, + &nhslot4->nulls_head); + nhslot4->count++; + spin_unlock_bh(&nhslot4->lock); } - return result; } +static void udp_unhash4(struct udp_table *udptable, struct sock *sk) +{ + struct udp_hslot *hslot2, *hslot4; + + if (udp_hashed4(sk)) { + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + hslot4 = udp_hashslot4(udptable, udp_sk(sk)->udp_lrpa_hash); + + spin_lock(&hslot4->lock); + hlist_nulls_del_init_rcu(&udp_sk(sk)->udp_lrpa_node); + hslot4->count--; + spin_unlock(&hslot4->lock); + + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + spin_unlock(&hslot2->lock); + } +} + +void udp_lib_hash4(struct sock *sk, u16 hash) +{ + struct udp_hslot *hslot, *hslot2, *hslot4; + struct net *net = sock_net(sk); + struct udp_table *udptable; + + /* Connected udp socket can re-connect to another remote address, which + * will be handled by rehash. Thus no need to redo hash4 here. + */ + if (udp_hashed4(sk)) + return; + + udptable = net->ipv4.udp_table; + hslot = udp_hashslot(udptable, net, udp_sk(sk)->udp_port_hash); + hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash); + hslot4 = udp_hashslot4(udptable, hash); + udp_sk(sk)->udp_lrpa_hash = hash; + + spin_lock_bh(&hslot->lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); + + spin_lock(&hslot4->lock); + hlist_nulls_add_head_rcu(&udp_sk(sk)->udp_lrpa_node, + &hslot4->nulls_head); + hslot4->count++; + spin_unlock(&hslot4->lock); + + spin_lock(&hslot2->lock); + udp_hash4_inc(hslot2); + spin_unlock(&hslot2->lock); + + spin_unlock_bh(&hslot->lock); +} +EXPORT_IPV6_MOD(udp_lib_hash4); + +/* call with sock lock */ +void udp4_hash4(struct sock *sk) +{ + struct net *net = sock_net(sk); + unsigned int hash; + + if (sk_unhashed(sk) || sk->sk_rcv_saddr == htonl(INADDR_ANY)) + return; + + hash = udp_ehashfn(net, sk->sk_rcv_saddr, sk->sk_num, + sk->sk_daddr, sk->sk_dport); + + udp_lib_hash4(sk, hash); +} +EXPORT_IPV6_MOD(udp4_hash4); +#endif /* CONFIG_BASE_SMALL */ + /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ -struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, - __be16 sport, __be32 daddr, __be16 dport, - int dif, struct udp_table *udptable) +struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr, + __be16 sport, __be32 daddr, __be16 dport, int dif, + int sdif, struct udp_table *udptable, struct sk_buff *skb) { - struct sock *sk, *result; - struct hlist_nulls_node *node; unsigned short hnum = ntohs(dport); - 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; + struct udp_hslot *hslot2; + struct sock *result, *sk; + unsigned int hash2; + + hash2 = ipv4_portaddr_hash(net, daddr, hnum); + hslot2 = udp_hashslot2(udptable, hash2); + + if (udp_has_hash4(hslot2)) { + result = udp4_lib_lookup4(net, saddr, sport, daddr, hnum, + dif, sdif, udptable); + if (result) /* udp4_lib_lookup4 return sk or NULL */ + 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) { + + /* Lookup connected or non-wildcard socket */ + result = udp4_lib_lookup2(net, saddr, sport, + daddr, hnum, dif, sdif, + hslot2, skb); + if (!IS_ERR_OR_NULL(result) && result->sk_state == TCP_ESTABLISHED) + goto done; + + /* Lookup redirect from BPF */ + if (static_branch_unlikely(&bpf_sk_lookup_enabled) && + udptable == net->ipv4.udp_table) { + sk = inet_lookup_run_sk_lookup(net, IPPROTO_UDP, skb, sizeof(struct udphdr), + saddr, sport, daddr, hnum, dif, + udp_ehashfn); + if (sk) { result = sk; - badness = score; - reuseport = sk->sk_reuseport; - if (reuseport) { - hash = inet_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); + goto done; } } - /* - * 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. + + /* Got non-wildcard socket or error on first lookup */ + if (result) + goto done; + + /* Lookup wildcard sockets */ + hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); + hslot2 = udp_hashslot2(udptable, hash2); + + result = udp4_lib_lookup2(net, saddr, sport, + htonl(INADDR_ANY), hnum, dif, sdif, + hslot2, skb); + if (!IS_ERR_OR_NULL(result)) + goto done; + + /* Primary hash (destination port) lookup as fallback for this race: + * 1. __ip4_datagram_connect() sets sk_rcv_saddr + * 2. lookup (this function): new sk_rcv_saddr, hashes not updated yet + * 3. rehash operation updating _secondary and four-tuple_ hashes + * The primary hash doesn't need an update after 1., so, thanks to this + * further step, 1. and 3. don't need to be atomic against the lookup. */ - if (get_nulls_value(node) != slot) - goto begin; + result = udp4_lib_lookup1(net, saddr, sport, daddr, hnum, dif, sdif, + udptable); - 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; - } - } - rcu_read_unlock(); +done: + if (IS_ERR(result)) + return NULL; return result; } EXPORT_SYMBOL_GPL(__udp4_lib_lookup); @@ -547,52 +747,174 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, __be16 sport, __be16 dport, struct udp_table *udptable) { - struct sock *sk; const struct iphdr *iph = ip_hdr(skb); - if (unlikely(sk = skb_steal_sock(skb))) - return sk; - else - return __udp4_lib_lookup(dev_net(skb_dst(skb)->dev), iph->saddr, sport, - iph->daddr, dport, inet_iif(skb), - udptable); + return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport, + iph->daddr, dport, inet_iif(skb), + inet_sdif(skb), udptable, skb); } -struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport, +struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, + __be16 sport, __be16 dport) +{ + const u16 offset = NAPI_GRO_CB(skb)->network_offsets[skb->encapsulation]; + const struct iphdr *iph = (struct iphdr *)(skb->data + offset); + struct net *net = dev_net(skb->dev); + int iif, sdif; + + inet_get_iif_sdif(skb, &iif, &sdif); + + return __udp4_lib_lookup(net, iph->saddr, sport, + iph->daddr, dport, iif, + sdif, net->ipv4.udp_table, NULL); +} + +/* Must be called under rcu_read_lock(). + * Does increment socket refcount. + */ +#if IS_ENABLED(CONFIG_NF_TPROXY_IPV4) || IS_ENABLED(CONFIG_NF_SOCKET_IPV4) +struct sock *udp4_lib_lookup(const 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); + struct sock *sk; + + sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport, + dif, 0, net->ipv4.udp_table, NULL); + if (sk && !refcount_inc_not_zero(&sk->sk_refcnt)) + sk = NULL; + return sk; } EXPORT_SYMBOL_GPL(udp4_lib_lookup); +#endif -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) +static inline bool __udp_is_mcast_sock(struct net *net, const struct sock *sk, + __be16 loc_port, __be32 loc_addr, + __be16 rmt_port, __be32 rmt_addr, + int dif, int sdif, unsigned short hnum) { - struct hlist_nulls_node *node; - struct sock *s = sk; - unsigned short hnum = ntohs(loc_port); + const 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) || + !udp_sk_bound_dev_eq(net, sk->sk_bound_dev_if, dif, sdif)) + return false; + if (!ip_mc_sf_allow(sk, loc_addr, rmt_addr, dif, sdif)) + return false; + return true; +} - sk_nulls_for_each_from(s, node) { - struct inet_sock *inet = inet_sk(s); - - if (!net_eq(sock_net(s), net) || - udp_sk(s)->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(s) || - (s->sk_bound_dev_if && s->sk_bound_dev_if != dif)) - continue; - if (!ip_mc_sf_allow(s, loc_addr, rmt_addr, dif)) +DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); +EXPORT_IPV6_MOD(udp_encap_needed_key); + +#if IS_ENABLED(CONFIG_IPV6) +DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); +EXPORT_IPV6_MOD(udpv6_encap_needed_key); +#endif + +void udp_encap_enable(void) +{ + static_branch_inc(&udp_encap_needed_key); +} +EXPORT_SYMBOL(udp_encap_enable); + +void udp_encap_disable(void) +{ + static_branch_dec(&udp_encap_needed_key); +} +EXPORT_SYMBOL(udp_encap_disable); + +/* Handler for tunnels with arbitrary destination ports: no socket lookup, go + * through error handlers in encapsulations looking for a match. + */ +static int __udp4_lib_err_encap_no_sk(struct sk_buff *skb, u32 info) +{ + int i; + + for (i = 0; i < MAX_IPTUN_ENCAP_OPS; i++) { + int (*handler)(struct sk_buff *skb, u32 info); + const struct ip_tunnel_encap_ops *encap; + + encap = rcu_dereference(iptun_encaps[i]); + if (!encap) continue; - goto found; + handler = encap->err_handler; + if (handler && !handler(skb, info)) + return 0; } - s = NULL; -found: - return s; + + return -ENOENT; +} + +/* Try to match ICMP errors to UDP tunnels by looking up a socket without + * reversing source and destination port: this will match tunnels that force the + * same destination port on both endpoints (e.g. VXLAN, GENEVE). Note that + * lwtunnels might actually break this assumption by being configured with + * different destination ports on endpoints, in this case we won't be able to + * trace ICMP messages back to them. + * + * If this doesn't match any socket, probe tunnels with arbitrary destination + * ports (e.g. FoU, GUE): there, the receiving socket is useless, as the port + * we've sent packets to won't necessarily match the local destination port. + * + * Then ask the tunnel implementation to match the error against a valid + * association. + * + * Return an error if we can't find a match, the socket if we need further + * processing, zero otherwise. + */ +static struct sock *__udp4_lib_err_encap(struct net *net, + const struct iphdr *iph, + struct udphdr *uh, + struct udp_table *udptable, + struct sock *sk, + struct sk_buff *skb, u32 info) +{ + int (*lookup)(struct sock *sk, struct sk_buff *skb); + int network_offset, transport_offset; + struct udp_sock *up; + + network_offset = skb_network_offset(skb); + transport_offset = skb_transport_offset(skb); + + /* Network header needs to point to the outer IPv4 header inside ICMP */ + skb_reset_network_header(skb); + + /* Transport header needs to point to the UDP header */ + skb_set_transport_header(skb, iph->ihl << 2); + + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (lookup && lookup(sk, skb)) + sk = NULL; + + goto out; + } + + sk = __udp4_lib_lookup(net, iph->daddr, uh->source, + iph->saddr, uh->dest, skb->dev->ifindex, 0, + udptable, NULL); + if (sk) { + up = udp_sk(sk); + + lookup = READ_ONCE(up->encap_err_lookup); + if (!lookup || lookup(sk, skb)) + sk = NULL; + } + +out: + if (!sk) + sk = ERR_PTR(__udp4_lib_err_encap_no_sk(skb, info)); + + skb_set_transport_header(skb, transport_offset); + skb_set_network_header(skb, network_offset); + + return sk; } /* @@ -606,23 +928,39 @@ found: * to find the appropriate port. */ -void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) +int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) { struct inet_sock *inet; 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; + bool tunnel = false; struct sock *sk; int harderr; int err; struct net *net = dev_net(skb->dev); sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, - iph->saddr, uh->source, skb->dev->ifindex, udptable); - if (sk == NULL) { - ICMP_INC_STATS_BH(net, ICMP_MIB_INERRORS); - return; /* No socket for error */ + iph->saddr, uh->source, skb->dev->ifindex, + inet_sdif(skb), udptable, NULL); + + if (!sk || READ_ONCE(udp_sk(sk)->encap_type)) { + /* No socket for error: try tunnels before discarding */ + if (static_branch_unlikely(&udp_encap_needed_key)) { + sk = __udp4_lib_err_encap(net, iph, uh, udptable, sk, skb, + info); + if (!sk) + return 0; + } else + sk = ERR_PTR(-ENOENT); + + if (IS_ERR(sk)) { + __ICMP_INC_STATS(net, ICMP_MIB_INERRORS); + return PTR_ERR(sk); + } + + tunnel = true; } err = 0; @@ -643,7 +981,7 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) 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) { + if (READ_ONCE(inet->pmtudisc) != IP_PMTUDISC_DONT) { err = EMSGSIZE; harderr = 1; break; @@ -658,28 +996,35 @@ void __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) break; case ICMP_REDIRECT: ipv4_sk_redirect(skb, sk); - break; + goto out; } /* * RFC1122: OK. Passes ICMP errors back to application, as per * 4.1.3.3. */ - if (!inet->recverr) { + if (tunnel) { + /* ...not for tunnels though: we don't have a sending socket */ + if (udp_sk(sk)->encap_err_rcv) + udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info, + (u8 *)(uh+1)); + goto out; + } + if (!inet_test_bit(RECVERR, sk)) { if (!harderr || sk->sk_state != TCP_ESTABLISHED) goto out; } else ip_icmp_error(sk, skb, err, uh->dest, info, (u8 *)(uh+1)); sk->sk_err = err; - sk->sk_error_report(sk); + sk_error_report(sk); out: - sock_put(sk); + return 0; } -void udp_err(struct sk_buff *skb, u32 info) +int udp_err(struct sk_buff *skb, u32 info) { - __udp4_lib_err(skb, info, &udp_table); + return __udp4_lib_err(skb, info, dev_net(skb->dev)->ipv4.udp_table); } /* @@ -691,11 +1036,11 @@ void udp_flush_pending_frames(struct sock *sk) if (up->pending) { up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); ip_flush_pending_frames(sk); } } -EXPORT_SYMBOL(udp_flush_pending_frames); +EXPORT_IPV6_MOD(udp_flush_pending_frames); /** * udp4_hwcsum - handle outgoing HW checksumming @@ -704,16 +1049,15 @@ EXPORT_SYMBOL(udp_flush_pending_frames); * @src: source IP address * @dst: destination IP address */ -static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) +void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) { struct udphdr *uh = udp_hdr(skb); - struct sk_buff *frags = skb_shinfo(skb)->frag_list; int offset = skb_transport_offset(skb); int len = skb->len - offset; int hlen = len; __wsum csum = 0; - if (!frags) { + if (!skb_has_frag_list(skb)) { /* * Only one fragment on the socket. */ @@ -722,15 +1066,17 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) 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 */ - do { + skb_walk_frags(skb, frags) { csum = csum_add(csum, frags->csum); hlen -= frags->len; - } while ((frags = frags->next)); + } csum = skb_checksum(skb, offset, hlen, csum); skb->ip_summed = CHECKSUM_NONE; @@ -740,16 +1086,45 @@ static void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst) uh->check = CSUM_MANGLED_0; } } +EXPORT_SYMBOL_GPL(udp4_hwcsum); -static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) +/* 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. + */ +void udp_set_csum(bool nocheck, struct sk_buff *skb, + __be32 saddr, __be32 daddr, int len) +{ + 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->ip_summed == CHECKSUM_PARTIAL) { + uh->check = 0; + uh->check = udp_v4_check(len, saddr, daddr, lco_csum(skb)); + if (uh->check == 0) + uh->check = CSUM_MANGLED_0; + } else { + 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); + } +} +EXPORT_SYMBOL(udp_set_csum); + +static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, + struct inet_cork *cork) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct udphdr *uh; - int err = 0; + int err; int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; + int datalen = len - sizeof(*uh); __wsum csum = 0; /* @@ -761,15 +1136,48 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) uh->len = htons(len); uh->check = 0; + if (cork->gso_size) { + const int hlen = skb_network_header_len(skb) + + sizeof(struct udphdr); + + if (hlen + min(datalen, cork->gso_size) > cork->fragsize) { + kfree_skb(skb); + return -EMSGSIZE; + } + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { + kfree_skb(skb); + return -EINVAL; + } + if (sk->sk_no_check_tx) { + kfree_skb(skb); + return -EINVAL; + } + if (is_udplite || dst_xfrm(skb_dst(skb))) { + kfree_skb(skb); + return -EIO; + } + + if (datalen > cork->gso_size) { + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(datalen, + cork->gso_size); + + /* Don't checksum the payload, skb will get segmented */ + goto csum_partial; + } + } + if (is_udplite) /* UDP-Lite */ 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 off */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ +csum_partial: udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; @@ -786,14 +1194,15 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) send: 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); + if (err == -ENOBUFS && + !inet_test_bit(RECVERR, sk)) { + UDP_INC_STATS(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); err = 0; } } else - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_OUTDATAGRAMS, is_udplite); + UDP_INC_STATS(sock_net(sk), + UDP_MIB_OUTDATAGRAMS, is_udplite); return err; } @@ -812,20 +1221,57 @@ int udp_push_pending_frames(struct sock *sk) if (!skb) goto out; - err = udp_send_skb(skb, fl4); + err = udp_send_skb(skb, fl4, &inet->cork.base); out: up->len = 0; - up->pending = 0; + WRITE_ONCE(up->pending, 0); return err; } -EXPORT_SYMBOL(udp_push_pending_frames); +EXPORT_IPV6_MOD(udp_push_pending_frames); + +static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) +{ + switch (cmsg->cmsg_type) { + case UDP_SEGMENT: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16))) + return -EINVAL; + *gso_size = *(__u16 *)CMSG_DATA(cmsg); + return 0; + default: + return -EINVAL; + } +} + +int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) +{ + struct cmsghdr *cmsg; + bool need_ip = false; + int err; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + if (cmsg->cmsg_level != SOL_UDP) { + need_ip = true; + continue; + } + + err = __udp_cmsg_send(cmsg, gso_size); + if (err) + return err; + } + + return need_ip; +} +EXPORT_IPV6_MOD_GPL(udp_cmsg_send); -int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len) +int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); struct udp_sock *up = udp_sk(sk); + DECLARE_SOCKADDR(struct sockaddr_in *, usin, msg->msg_name); struct flowi4 fl4_stack; struct flowi4 *fl4; int ulen = len; @@ -834,13 +1280,14 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, int free = 0; int connected = 0; __be32 daddr, faddr, saddr; + u8 scope; __be16 dport; - u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = udp_test_bit(CORK, sk) || 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; + int uc_index; if (len > 0xFFFF) return -EMSGSIZE; @@ -852,13 +1299,10 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, if (msg->msg_flags & MSG_OOB) /* Mirror BSD error message compatibility */ return -EOPNOTSUPP; - ipc.opt = NULL; - ipc.tx_flags = 0; - getfrag = is_udplite ? udplite_getfrag : ip_generic_getfrag; fl4 = &inet->cork.fl.u.ip4; - if (up->pending) { + if (READ_ONCE(up->pending)) { /* * There are pending frames. * The socket lock must be held while it's corked. @@ -878,8 +1322,7 @@ 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; + if (usin) { if (msg->msg_namelen < sizeof(*usin)) return -EINVAL; if (usin->sin_family != AF_INET) { @@ -901,19 +1344,23 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, */ connected = 1; } - ipc.addr = inet->inet_saddr; - - ipc.oif = sk->sk_bound_dev_if; - sock_tx_timestamp(sk, &ipc.tx_flags); + ipcm_init_sk(&ipc, inet); + ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { - err = ip_cmsg_send(sock_net(sk), msg, &ipc); - if (err) + err = udp_cmsg_send(sk, msg, &ipc.gso_size); + if (err > 0) { + err = ip_cmsg_send(sk, msg, &ipc, + sk->sk_family == AF_INET6); + connected = 0; + } + if (unlikely(err < 0)) { + kfree(ipc.opt); return err; + } if (ipc.opt) free = 1; - connected = 0; } if (!ipc.opt) { struct ip_options_rcu *inet_opt; @@ -928,51 +1375,84 @@ int udp_sendmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, rcu_read_unlock(); } + if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { + err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, + (struct sockaddr *)usin, + &msg->msg_namelen, + &ipc.addr); + if (err) + goto out_free; + if (usin) { + if (usin->sin_port == 0) { + /* BPF program set invalid port. Reject it. */ + err = -EINVAL; + goto out_free; + } + daddr = usin->sin_addr.s_addr; + dport = usin->sin_port; + } + } + saddr = ipc.addr; ipc.addr = faddr = daddr; if (ipc.opt && ipc.opt->opt.srr) { - if (!daddr) - return -EINVAL; + if (!daddr) { + err = -EINVAL; + goto out_free; + } faddr = ipc.opt->opt.faddr; connected = 0; } - tos = RT_TOS(inet->tos); - if (sock_flag(sk, SOCK_LOCALROUTE) || - (msg->msg_flags & MSG_DONTROUTE) || - (ipc.opt && ipc.opt->opt.is_strictroute)) { - tos |= RTO_ONLINK; + scope = ip_sendmsg_scope(inet, &ipc, msg); + if (scope == RT_SCOPE_LINK) connected = 0; - } + uc_index = READ_ONCE(inet->uc_index); if (ipv4_is_multicast(daddr)) { - if (!ipc.oif) - ipc.oif = inet->mc_index; + if (!ipc.oif || netif_index_is_l3_master(sock_net(sk), ipc.oif)) + ipc.oif = READ_ONCE(inet->mc_index); if (!saddr) - saddr = inet->mc_addr; + saddr = READ_ONCE(inet->mc_addr); connected = 0; - } else if (!ipc.oif) - ipc.oif = inet->uc_index; + } else if (!ipc.oif) { + ipc.oif = uc_index; + } else if (ipv4_is_lbcast(daddr) && uc_index) { + /* oif is set, packet is to local broadcast and + * uc_index is set. oif is most likely set + * by sk_bound_dev_if. If uc_index != oif check if the + * oif is an L3 master and uc_index is an L3 slave. + * If so, we want to allow the send using the uc_index. + */ + if (ipc.oif != uc_index && + ipc.oif == l3mdev_master_ifindex_by_index(sock_net(sk), + uc_index)) { + ipc.oif = uc_index; + } + } if (connected) - rt = (struct rtable *)sk_dst_check(sk, 0); + rt = dst_rtable(sk_dst_check(sk, 0)); - if (rt == NULL) { + if (!rt) { struct net *net = sock_net(sk); + __u8 flow_flags = inet_sk_flowi_flags(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)|FLOWI_FLAG_CAN_SLEEP, - faddr, saddr, dport, inet->inet_sport); - security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); + flowi4_init_output(fl4, ipc.oif, ipc.sockc.mark, + ipc.tos & INET_DSCP_MASK, scope, + sk->sk_protocol, flow_flags, faddr, saddr, + dport, inet->inet_sport, + sk_uid(sk)); + + security_sk_classify_flow(sk, flowi4_to_flowi_common(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(net, IPSTATS_MIB_OUTNOROUTES); + IP_INC_STATS(net, IPSTATS_MIB_OUTNOROUTES); goto out; } @@ -994,12 +1474,14 @@ back_from_confirm: /* Lockless fast path for the non-corking case. */ if (!corkreq) { - skb = ip_make_skb(sk, fl4, getfrag, msg->msg_iov, ulen, + struct inet_cork cork; + + skb = ip_make_skb(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, - msg->msg_flags); + &cork, msg->msg_flags); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_send_skb(skb, fl4); + err = udp_send_skb(skb, fl4, &cork); goto out; } @@ -1009,7 +1491,7 @@ back_from_confirm: /* ... which is an evident application bug. --ANK */ release_sock(sk); - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("cork app bug 2\n")); + net_dbg_ratelimited("socket already corked\n"); err = -EINVAL; goto out; } @@ -1021,11 +1503,11 @@ back_from_confirm: fl4->saddr = saddr; fl4->fl4_dport = dport; fl4->fl4_sport = inet->inet_sport; - up->pending = AF_INET; + WRITE_ONCE(up->pending, AF_INET); do_append_data: up->len += ulen; - err = ip_append_data(sk, fl4, getfrag, msg->msg_iov, ulen, + err = ip_append_data(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, corkreq ? msg->msg_flags|MSG_MORE : msg->msg_flags); if (err) @@ -1033,11 +1515,12 @@ do_append_data: else if (!corkreq) err = udp_push_pending_frames(sk); else if (unlikely(skb_queue_empty(&sk->sk_write_queue))) - up->pending = 0; + WRITE_ONCE(up->pending, 0); release_sock(sk); out: ip_rt_put(rt); +out_free: if (free) kfree(ipc.opt); if (!err) @@ -1050,13 +1533,14 @@ out: * seems like overkill. */ if (err == -ENOBUFS || test_bit(SOCK_NOSPACE, &sk->sk_socket->flags)) { - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_SNDBUFERRORS, is_udplite); + UDP_INC_STATS(sock_net(sk), + UDP_MIB_SNDBUFERRORS, is_udplite); } return err; do_confirm: - dst_confirm(&rt->dst); + if (msg->msg_flags & MSG_PROBE) + dst_confirm_neigh(&rt->dst, &fl4->daddr); if (!(msg->msg_flags&MSG_PROBE) || len) goto back_from_confirm; err = 0; @@ -1064,93 +1548,377 @@ do_confirm: } EXPORT_SYMBOL(udp_sendmsg); -int udp_sendpage(struct sock *sk, struct page *page, int offset, - size_t size, int flags) +void udp_splice_eof(struct socket *sock) { - struct inet_sock *inet = inet_sk(sk); + struct sock *sk = sock->sk; struct udp_sock *up = udp_sk(sk); - int ret; - if (!up->pending) { - struct msghdr msg = { .msg_flags = flags|MSG_MORE }; + if (!READ_ONCE(up->pending) || udp_test_bit(CORK, sk)) + return; + + lock_sock(sk); + if (up->pending && !udp_test_bit(CORK, sk)) + udp_push_pending_frames(sk); + release_sock(sk); +} +EXPORT_IPV6_MOD_GPL(udp_splice_eof); + +#define UDP_SKB_IS_STATELESS 0x80000000 + +/* all head states (dst, sk, nf conntrack) except skb extensions are + * cleared by udp_rcv(). + * + * We need to preserve secpath, if present, to eventually process + * IP_CMSG_PASSSEC at recvmsg() time. + * + * Other extensions can be cleared. + */ +static bool udp_try_make_stateless(struct sk_buff *skb) +{ + if (!skb_has_extensions(skb)) + return true; + + if (!secpath_exists(skb)) { + skb_ext_reset(skb); + return true; + } + + return false; +} + +static void udp_set_dev_scratch(struct sk_buff *skb) +{ + struct udp_dev_scratch *scratch = udp_skb_scratch(skb); + + BUILD_BUG_ON(sizeof(struct udp_dev_scratch) > sizeof(long)); + scratch->_tsize_state = skb->truesize; +#if BITS_PER_LONG == 64 + scratch->len = skb->len; + scratch->csum_unnecessary = !!skb_csum_unnecessary(skb); + scratch->is_linear = !skb_is_nonlinear(skb); +#endif + if (udp_try_make_stateless(skb)) + scratch->_tsize_state |= UDP_SKB_IS_STATELESS; +} + +static void udp_skb_csum_unnecessary_set(struct sk_buff *skb) +{ + /* We come here after udp_lib_checksum_complete() returned 0. + * This means that __skb_checksum_complete() might have + * set skb->csum_valid to 1. + * On 64bit platforms, we can set csum_unnecessary + * to true, but only if the skb is not shared. + */ +#if BITS_PER_LONG == 64 + if (!skb_shared(skb)) + udp_skb_scratch(skb)->csum_unnecessary = true; +#endif +} + +static int udp_skb_truesize(struct sk_buff *skb) +{ + return udp_skb_scratch(skb)->_tsize_state & ~UDP_SKB_IS_STATELESS; +} + +static bool udp_skb_has_head_state(struct sk_buff *skb) +{ + return !(udp_skb_scratch(skb)->_tsize_state & UDP_SKB_IS_STATELESS); +} + +/* fully reclaim rmem/fwd memory allocated for skb */ +static void udp_rmem_release(struct sock *sk, unsigned int size, + int partial, bool rx_queue_lock_held) +{ + struct udp_sock *up = udp_sk(sk); + struct sk_buff_head *sk_queue; + unsigned int amt; + + if (likely(partial)) { + up->forward_deficit += size; + size = up->forward_deficit; + if (size < READ_ONCE(up->forward_threshold) && + !skb_queue_empty(&up->reader_queue)) + return; + } else { + size += up->forward_deficit; + } + up->forward_deficit = 0; + + /* acquire the sk_receive_queue for fwd allocated memory scheduling, + * if the called don't held it already + */ + sk_queue = &sk->sk_receive_queue; + if (!rx_queue_lock_held) + spin_lock(&sk_queue->lock); + + amt = (size + sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); + sk_forward_alloc_add(sk, size - amt); + + if (amt) + __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); + + atomic_sub(size, &sk->sk_rmem_alloc); - /* Call udp_sendmsg to specify destination address which - * sendpage interface can't pass. - * This will succeed only when the socket is connected. + /* this can save us from acquiring the rx queue lock on next receive */ + skb_queue_splice_tail_init(sk_queue, &up->reader_queue); + + if (!rx_queue_lock_held) + spin_unlock(&sk_queue->lock); +} + +/* Note: called with reader_queue.lock held. + * Instead of using skb->truesize here, find a copy of it in skb->dev_scratch + * This avoids a cache line miss while receive_queue lock is held. + * Look at __udp_enqueue_schedule_skb() to find where this copy is done. + */ +void udp_skb_destructor(struct sock *sk, struct sk_buff *skb) +{ + prefetch(&skb->data); + udp_rmem_release(sk, udp_skb_truesize(skb), 1, false); +} +EXPORT_IPV6_MOD(udp_skb_destructor); + +/* as above, but the caller held the rx queue lock, too */ +static void udp_skb_dtor_locked(struct sock *sk, struct sk_buff *skb) +{ + prefetch(&skb->data); + udp_rmem_release(sk, udp_skb_truesize(skb), 1, true); +} + +static int udp_rmem_schedule(struct sock *sk, int size) +{ + int delta; + + delta = size - sk->sk_forward_alloc; + if (delta > 0 && !__sk_mem_schedule(sk, delta, SK_MEM_RECV)) + return -ENOBUFS; + + return 0; +} + +int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) +{ + struct sk_buff_head *list = &sk->sk_receive_queue; + struct udp_prod_queue *udp_prod_queue; + struct sk_buff *next, *to_drop = NULL; + struct llist_node *ll_list; + unsigned int rmem, rcvbuf; + int size, err = -ENOMEM; + int total_size = 0; + int q_size = 0; + int dropcount; + int nb = 0; + + rmem = atomic_read(&sk->sk_rmem_alloc); + rcvbuf = READ_ONCE(sk->sk_rcvbuf); + size = skb->truesize; + + udp_prod_queue = &udp_sk(sk)->udp_prod_queue[numa_node_id()]; + + rmem += atomic_read(&udp_prod_queue->rmem_alloc); + + /* Immediately drop when the receive queue is full. + * Cast to unsigned int performs the boundary check for INT_MAX. + */ + if (rmem + size > rcvbuf) { + if (rcvbuf > INT_MAX >> 1) + goto drop; + + /* Accept the packet if queue is empty. */ + if (rmem) + goto drop; + } + + /* Under mem pressure, it might be helpful to help udp_recvmsg() + * having linear skbs : + * - Reduce memory overhead and thus increase receive queue capacity + * - Less cache line misses at copyout() time + * - Less work at consume_skb() (less alien page frag freeing) + */ + if (rmem > (rcvbuf >> 1)) { + skb_condense(skb); + size = skb->truesize; + } + + udp_set_dev_scratch(skb); + + atomic_add(size, &udp_prod_queue->rmem_alloc); + + if (!llist_add(&skb->ll_node, &udp_prod_queue->ll_root)) + return 0; + + dropcount = sock_flag(sk, SOCK_RXQ_OVFL) ? sk_drops_read(sk) : 0; + + spin_lock(&list->lock); + + ll_list = llist_del_all(&udp_prod_queue->ll_root); + + ll_list = llist_reverse_order(ll_list); + + llist_for_each_entry_safe(skb, next, ll_list, ll_node) { + size = udp_skb_truesize(skb); + total_size += size; + err = udp_rmem_schedule(sk, size); + if (unlikely(err)) { + /* Free the skbs outside of locked section. */ + skb->next = to_drop; + to_drop = skb; + continue; + } + + q_size += size; + sk_forward_alloc_add(sk, -size); + + /* no need to setup a destructor, we will explicitly release the + * forward allocated memory on dequeue */ - ret = udp_sendmsg(NULL, sk, &msg, 0); - if (ret < 0) - return ret; + SOCK_SKB_CB(skb)->dropcount = dropcount; + nb++; + __skb_queue_tail(list, skb); } - lock_sock(sk); + atomic_add(q_size, &sk->sk_rmem_alloc); - if (unlikely(!up->pending)) { - release_sock(sk); + spin_unlock(&list->lock); - LIMIT_NETDEBUG(KERN_DEBUG pr_fmt("udp cork app bug 3\n")); - return -EINVAL; + if (!sock_flag(sk, SOCK_DEAD)) { + /* Multiple threads might be blocked in recvmsg(), + * using prepare_to_wait_exclusive(). + */ + while (nb) { + INDIRECT_CALL_1(sk->sk_data_ready, + sock_def_readable, sk); + nb--; + } } - 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, - size, flags); + if (unlikely(to_drop)) { + for (nb = 0; to_drop != NULL; nb++) { + skb = to_drop; + to_drop = skb->next; + skb_mark_not_on_list(skb); + /* TODO: update SNMP values. */ + sk_skb_reason_drop(sk, skb, SKB_DROP_REASON_PROTO_MEM); + } + numa_drop_add(&udp_sk(sk)->drop_counters, nb); } - if (ret < 0) { - udp_flush_pending_frames(sk); - goto out; + + atomic_sub(total_size, &udp_prod_queue->rmem_alloc); + + return 0; + +drop: + udp_drops_inc(sk); + return err; +} +EXPORT_IPV6_MOD_GPL(__udp_enqueue_schedule_skb); + +void udp_destruct_common(struct sock *sk) +{ + /* reclaim completely the forward allocated memory */ + struct udp_sock *up = udp_sk(sk); + unsigned int total = 0; + struct sk_buff *skb; + + skb_queue_splice_tail_init(&sk->sk_receive_queue, &up->reader_queue); + while ((skb = __skb_dequeue(&up->reader_queue)) != NULL) { + total += skb->truesize; + kfree_skb(skb); } + udp_rmem_release(sk, total, 0, true); + kfree(up->udp_prod_queue); +} +EXPORT_IPV6_MOD_GPL(udp_destruct_common); - up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) - ret = udp_push_pending_frames(sk); - if (!ret) - ret = size; -out: - release_sock(sk); - return ret; +static void udp_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); + inet_sock_destruct(sk); } +int udp_init_sock(struct sock *sk) +{ + int res = udp_lib_init_sock(sk); + + sk->sk_destruct = udp_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); + return res; +} + +void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) +{ + if (unlikely(READ_ONCE(udp_sk(sk)->peeking_with_offset))) + sk_peek_offset_bwd(sk, len); + + if (!skb_shared(skb)) { + skb_attempt_defer_free(skb); + return; + } + + if (!skb_unref(skb)) + return; + + /* In the more common cases we cleared the head states previously, + * see __udp_queue_rcv_skb(). + */ + if (unlikely(udp_skb_has_head_state(skb))) + skb_release_head_state(skb); + __consume_stateless_skb(skb); +} +EXPORT_IPV6_MOD_GPL(skb_consume_udp); + +static struct sk_buff *__first_packet_length(struct sock *sk, + struct sk_buff_head *rcvq, + unsigned int *total) +{ + struct sk_buff *skb; + + while ((skb = skb_peek(rcvq)) != NULL) { + if (udp_lib_checksum_complete(skb)) { + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + udp_drops_inc(sk); + __skb_unlink(skb, rcvq); + *total += skb->truesize; + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); + } else { + udp_skb_csum_unnecessary_set(skb); + break; + } + } + return skb; +} /** * 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. + * Returns the length of found skb, or -1 if none is found. */ -static unsigned int first_packet_length(struct sock *sk) +static int first_packet_length(struct sock *sk) { - struct sk_buff_head list_kill, *rcvq = &sk->sk_receive_queue; + struct sk_buff_head *rcvq = &udp_sk(sk)->reader_queue; + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + unsigned int total = 0; struct sk_buff *skb; - unsigned int res; - - __skb_queue_head_init(&list_kill); + int res; 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); + skb = __first_packet_length(sk, rcvq, &total); + if (!skb && !skb_queue_empty_lockless(sk_queue)) { + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, rcvq); + spin_unlock(&sk_queue->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); + skb = __first_packet_length(sk, rcvq, &total); } + res = skb ? skb->len : -1; + if (total) + udp_rmem_release(sk, total, 1, false); + spin_unlock_bh(&rcvq->lock); return res; } @@ -1158,29 +1926,19 @@ static unsigned int first_packet_length(struct sock *sk) * IOCTL requests applicable to the UDP protocol */ -int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) +int udp_ioctl(struct sock *sk, int cmd, int *karg) { switch (cmd) { case SIOCOUTQ: { - int amount = sk_wmem_alloc_get(sk); - - return put_user(amount, (int __user *)arg); + *karg = sk_wmem_alloc_get(sk); + return 0; } case SIOCINQ: { - unsigned int amount = first_packet_length(sk); - - if (amount) - /* - * We will only return the amount - * of this packet since that is all - * that will be read. - */ - amount -= sizeof(struct udphdr); - - return put_user(amount, (int __user *)arg); + *karg = max_t(int, 0, first_packet_length(sk)); + return 0; } default: @@ -1189,44 +1947,133 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) return 0; } -EXPORT_SYMBOL(udp_ioctl); +EXPORT_IPV6_MOD(udp_ioctl); + +struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, + int *off, int *err) +{ + struct sk_buff_head *sk_queue = &sk->sk_receive_queue; + struct sk_buff_head *queue; + struct sk_buff *last; + long timeo; + int error; + + queue = &udp_sk(sk)->reader_queue; + timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); + do { + struct sk_buff *skb; + + error = sock_error(sk); + if (error) + break; + + error = -EAGAIN; + do { + spin_lock_bh(&queue->lock); + skb = __skb_try_recv_from_queue(queue, flags, off, err, + &last); + if (skb) { + if (!(flags & MSG_PEEK)) + udp_skb_destructor(sk, skb); + spin_unlock_bh(&queue->lock); + return skb; + } + + if (skb_queue_empty_lockless(sk_queue)) { + spin_unlock_bh(&queue->lock); + goto busy_check; + } + + /* refill the reader queue and walk it again + * keep both queues locked to avoid re-acquiring + * the sk_receive_queue lock if fwd memory scheduling + * is needed. + */ + spin_lock(&sk_queue->lock); + skb_queue_splice_tail_init(sk_queue, queue); + + skb = __skb_try_recv_from_queue(queue, flags, off, err, + &last); + if (skb && !(flags & MSG_PEEK)) + udp_skb_dtor_locked(sk, skb); + spin_unlock(&sk_queue->lock); + spin_unlock_bh(&queue->lock); + if (skb) + return skb; + +busy_check: + if (!sk_can_busy_loop(sk)) + break; + + sk_busy_loop(sk, flags & MSG_DONTWAIT); + } while (!skb_queue_empty_lockless(sk_queue)); + + /* sk_queue is empty, reader_queue may contain peeked packets */ + } while (timeo && + !__skb_wait_for_more_packets(sk, &sk->sk_receive_queue, + &error, &timeo, + (struct sk_buff *)sk_queue)); + + *err = error; + return NULL; +} +EXPORT_SYMBOL(__skb_recv_udp); + +int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) +{ + struct sk_buff *skb; + int err; + +try_again: + skb = skb_recv_udp(sk, MSG_DONTWAIT, &err); + if (!skb) + return err; + + if (udp_lib_checksum_complete(skb)) { + int is_udplite = IS_UDPLITE(sk); + struct net *net = sock_net(sk); + + __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, is_udplite); + __UDP_INC_STATS(net, UDP_MIB_INERRORS, is_udplite); + udp_drops_inc(sk); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); + goto try_again; + } + + WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); + return recv_actor(sk, skb); +} +EXPORT_IPV6_MOD(udp_read_skb); /* * This should be easy, if there is something there we * return it, otherwise we block. */ -int udp_recvmsg(struct kiocb *iocb, struct sock *sk, struct msghdr *msg, - size_t len, int noblock, int flags, int *addr_len) +int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, 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, off = 0; - int err; + int off, err, peeking = flags & MSG_PEEK; int is_udplite = IS_UDPLITE(sk); - bool slow; - - /* - * Check any passed addresses - */ - if (addr_len) - *addr_len = sizeof(*sin); + bool checksum_valid = false; 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, &off, &err); + off = sk_peek_offset(sk, flags); + skb = __skb_recv_udp(sk, flags, &off, &err); if (!skb) - goto out; + return err; - ulen = skb->len - sizeof(struct udphdr); + ulen = udp_skb_len(skb); copied = len; - if (copied > ulen) - copied = ulen; + if (copied > ulen - off) + copied = ulen - off; else if (copied < ulen) msg->msg_flags |= MSG_TRUNC; @@ -1236,38 +2083,41 @@ try_again: * coverage checksum (UDP-Lite), do it before the copy. */ - if (copied < ulen || UDP_SKB_CB(skb)->partial_cov) { - if (udp_lib_checksum_complete(skb)) + if (copied < ulen || peeking || + (is_udplite && UDP_SKB_CB(skb)->partial_cov)) { + checksum_valid = udp_skb_csum_unnecessary(skb) || + !__udp_lib_checksum_complete(skb); + if (!checksum_valid) goto csum_copy_err; } - if (skb_csum_unnecessary(skb)) - err = skb_copy_datagram_iovec(skb, sizeof(struct udphdr), - msg->msg_iov, copied); - else { - err = skb_copy_and_csum_datagram_iovec(skb, - sizeof(struct udphdr), - msg->msg_iov); + if (checksum_valid || udp_skb_csum_unnecessary(skb)) { + if (udp_skb_is_linear(skb)) + err = copy_linear_skb(skb, copied, off, &msg->msg_iter); + else + err = skb_copy_datagram_msg(skb, off, msg, copied); + } else { + err = skb_copy_and_csum_datagram_msg(skb, off, msg); if (err == -EINVAL) goto csum_copy_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); + if (!peeking) { + udp_drops_inc(sk); + UDP_INC_STATS(sock_net(sk), + UDP_MIB_INERRORS, is_udplite); } - goto out_free; + kfree_skb(skb); + return err; } - if (!peeked) - UDP_INC_STATS_USER(sock_net(sk), - UDP_MIB_INDATAGRAMS, is_udplite); + if (!peeking) + UDP_INC_STATS(sock_net(sk), + UDP_MIB_INDATAGRAMS, is_udplite); - sock_recv_ts_and_drops(msg, sk, skb); + sock_recv_cmsgs(msg, sk, skb); /* Copy the address. */ if (sin) { @@ -1275,37 +2125,68 @@ try_again: 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); + + BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, + (struct sockaddr *)sin, + addr_len); } - if (inet->cmsg_flags) - ip_cmsg_recv(msg, skb); + + if (udp_test_bit(GRO_ENABLED, sk)) + udp_cmsg_recv(msg, sk, skb); + + if (inet_cmsg_flags(inet)) + ip_cmsg_recv_offset(msg, sk, skb, sizeof(struct udphdr), off); err = copied; if (flags & MSG_TRUNC) err = ulen; -out_free: - skb_free_datagram_locked(sk, skb); -out: + skb_consume_udp(sk, skb, peeking ? -err : err); return err; csum_copy_err: - 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); + if (!__sk_queue_drop_skb(sk, &udp_sk(sk)->reader_queue, skb, flags, + udp_skb_destructor)) { + UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); + UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); } - unlock_sock_fast(sk, slow); + kfree_skb_reason(skb, SKB_DROP_REASON_UDP_CSUM); - if (noblock) - return -EAGAIN; - - /* starting over for a new packet */ + /* starting over for a new packet, but check if we need to yield */ + cond_resched(); msg->msg_flags &= ~MSG_TRUNC; goto try_again; } +int udp_pre_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) +{ + /* This check is replicated from __ip4_datagram_connect() and + * intended to prevent BPF program called below from accessing bytes + * that are out of the bound specified by user in addr_len. + */ + if (addr_len < sizeof(struct sockaddr_in)) + return -EINVAL; -int udp_disconnect(struct sock *sk, int flags) + return BPF_CGROUP_RUN_PROG_INET4_CONNECT_LOCK(sk, uaddr, &addr_len); +} +EXPORT_IPV6_MOD(udp_pre_connect); + +static int udp_connect(struct sock *sk, struct sockaddr_unsized *uaddr, + int addr_len) +{ + int res; + + lock_sock(sk); + res = __ip4_datagram_connect(sk, uaddr, addr_len); + if (!res) + udp4_hash4(sk); + release_sock(sk); + return res; +} + +int __udp_disconnect(struct sock *sk, int flags) { struct inet_sock *inet = inet_sk(sk); /* @@ -1317,8 +2198,12 @@ int udp_disconnect(struct sock *sk, int flags) inet->inet_dport = 0; sock_rps_reset_rxhash(sk); sk->sk_bound_dev_if = 0; - if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) + if (!(sk->sk_userlocks & SOCK_BINDADDR_LOCK)) { inet_reset_saddr(sk); + if (sk->sk_prot->rehash && + (sk->sk_userlocks & SOCK_BINDPORT_LOCK)) + sk->sk_prot->rehash(sk); + } if (!(sk->sk_userlocks & SOCK_BINDPORT_LOCK)) { sk->sk_prot->unhash(sk); @@ -1327,110 +2212,160 @@ int udp_disconnect(struct sock *sk, int flags) sk_dst_reset(sk); return 0; } -EXPORT_SYMBOL(udp_disconnect); +EXPORT_SYMBOL(__udp_disconnect); + +int udp_disconnect(struct sock *sk, int flags) +{ + lock_sock(sk); + __udp_disconnect(sk, flags); + release_sock(sk); + return 0; +} +EXPORT_IPV6_MOD(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_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2; + sock_rps_delete_flow(sk); 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)) { + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); + if (sk_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); + hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); hslot2->count--; spin_unlock(&hslot2->lock); + + udp_unhash4(udptable, sk); } spin_unlock_bh(&hslot->lock); } } -EXPORT_SYMBOL(udp_lib_unhash); +EXPORT_IPV6_MOD(udp_lib_unhash); /* * inet_rcv_saddr was changed, we must rehash secondary hash */ -void udp_lib_rehash(struct sock *sk, u16 newhash) +void udp_lib_rehash(struct sock *sk, u16 newhash, u16 newhash4) { if (sk_hashed(sk)) { - struct udp_table *udptable = sk->sk_prot->h.udp_table; + struct udp_table *udptable = udp_get_table_prot(sk); struct udp_hslot *hslot, *hslot2, *nhslot2; + hslot = udp_hashslot(udptable, sock_net(sk), + udp_sk(sk)->udp_port_hash); 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); + + if (hslot2 != nhslot2 || + rcu_access_pointer(sk->sk_reuseport_cb)) { /* we must lock primary chain too */ spin_lock_bh(&hslot->lock); + if (rcu_access_pointer(sk->sk_reuseport_cb)) + reuseport_detach_sock(sk); + + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + hlist_del_init_rcu(&udp_sk(sk)->udp_portaddr_node); + hslot2->count--; + spin_unlock(&hslot2->lock); + + spin_lock(&nhslot2->lock); + hlist_add_head_rcu(&udp_sk(sk)->udp_portaddr_node, + &nhslot2->head); + nhslot2->count++; + spin_unlock(&nhslot2->lock); + } - 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); + } + + /* Now process hash4 if necessary: + * (1) update hslot4; + * (2) update hslot2->hash4_cnt. + * Note that hslot2/hslot4 should be checked separately, as + * either of them may change with the other unchanged. + */ + if (udp_hashed4(sk)) { + spin_lock_bh(&hslot->lock); + + udp_rehash4(udptable, sk, newhash4); + if (hslot2 != nhslot2) { + spin_lock(&hslot2->lock); + udp_hash4_dec(hslot2); + 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_lock(&nhslot2->lock); + udp_hash4_inc(nhslot2); + spin_unlock(&nhslot2->lock); + } spin_unlock_bh(&hslot->lock); } } } -EXPORT_SYMBOL(udp_lib_rehash); +EXPORT_IPV6_MOD(udp_lib_rehash); -static void udp_v4_rehash(struct sock *sk) +void udp_v4_rehash(struct sock *sk) { - u16 new_hash = udp4_portaddr_hash(sock_net(sk), + u16 new_hash = ipv4_portaddr_hash(sock_net(sk), inet_sk(sk)->inet_rcv_saddr, inet_sk(sk)->inet_num); - udp_lib_rehash(sk, new_hash); + u16 new_hash4 = udp_ehashfn(sock_net(sk), + sk->sk_rcv_saddr, sk->sk_num, + sk->sk_daddr, sk->sk_dport); + + udp_lib_rehash(sk, new_hash, new_hash4); } static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { int rc; - if (inet_sk(sk)->inet_daddr) + if (inet_sk(sk)->inet_daddr) { sock_rps_save_rxhash(sk, skb); + sk_mark_napi_id(sk, skb); + sk_incoming_cpu_update(sk); + } else { + sk_mark_napi_id_once(sk, skb); + } - rc = sock_queue_rcv_skb(sk, skb); + rc = __udp_enqueue_schedule_skb(sk, skb); if (rc < 0) { int is_udplite = IS_UDPLITE(sk); + int drop_reason; /* 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); + if (rc == -ENOMEM) { + UDP_INC_STATS(sock_net(sk), UDP_MIB_RCVBUFERRORS, + is_udplite); + drop_reason = SKB_DROP_REASON_SOCKET_RCVBUFF; + } else { + UDP_INC_STATS(sock_net(sk), UDP_MIB_MEMERRORS, + is_udplite); + drop_reason = SKB_DROP_REASON_PROTO_MEM; + } + UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + trace_udp_fail_queue_rcv_skb(rc, sk, skb); + sk_skb_reason_drop(sk, skb, drop_reason); 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 * 0: success @@ -1439,20 +2374,23 @@ EXPORT_SYMBOL(udp_encap_enable); * 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) +static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) { + enum skb_drop_reason drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); - int rc; int is_udplite = IS_UDPLITE(sk); /* * Charge it to the socket, dropping if the queue is full. */ - if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) + if (!xfrm4_policy_check(sk, XFRM_POLICY_IN, skb)) { + drop_reason = SKB_DROP_REASON_XFRM_POLICY; goto drop; - nf_reset(skb); + } + nf_reset_ct(skb); - if (static_key_false(&udp_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && + READ_ONCE(up->encap_type)) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -1467,15 +2405,19 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) */ /* if we're overly short, let UDP handle it */ - encap_rcv = ACCESS_ONCE(up->encap_rcv); - if (skb->len > sizeof(struct udphdr) && encap_rcv != NULL) { + encap_rcv = READ_ONCE(up->encap_rcv); + if (encap_rcv) { int ret; + /* 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(sock_net(sk), - UDP_MIB_INDATAGRAMS, - is_udplite); + __UDP_INC_STATS(sock_net(sk), + UDP_MIB_INDATAGRAMS, + is_udplite); return -ret; } } @@ -1486,7 +2428,8 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) /* * UDP-Lite specific tests, ignored on UDP sockets */ - if ((is_udplite & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { + if (udp_test_bit(UDPLITE_RECV_CC, sk) && UDP_SKB_CB(skb)->partial_cov) { + u16 pcrlen = READ_ONCE(up->pcrlen); /* * MIB statistics other than incrementing the error count are @@ -1499,9 +2442,9 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * delivery of packets with coverage values less than a value * 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); + if (pcrlen == 0) { /* full coverage was set */ + net_dbg_ratelimited("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 @@ -1510,72 +2453,74 @@ int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) * that it wants x while sender emits packets of smaller size y. * 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); + if (UDP_SKB_CB(skb)->cscov < pcrlen) { + net_dbg_ratelimited("UDPLite: coverage %d too small, need min %d\n", + UDP_SKB_CB(skb)->cscov, pcrlen); goto drop; } } + prefetch(&sk->sk_rmem_alloc); if (rcu_access_pointer(sk->sk_filter) && udp_lib_checksum_complete(skb)) - goto csum_error; - + goto csum_error; - if (sk_rcvqueues_full(sk, skb, sk->sk_rcvbuf)) + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr), &drop_reason)) goto drop; - rc = 0; + udp_csum_pull_header(skb); - ipv4_pktinfo_prepare(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 rc; + ipv4_pktinfo_prepare(sk, skb, true); + return __udp_queue_rcv_skb(sk, skb); csum_error: - UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); + drop_reason = SKB_DROP_REASON_UDP_CSUM; + __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: - UDP_INC_STATS_BH(sock_net(sk), UDP_MIB_INERRORS, is_udplite); - atomic_inc(&sk->sk_drops); - kfree_skb(skb); + __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); + udp_drops_inc(sk); + sk_skb_reason_drop(sk, skb, drop_reason); return -1; } - -static void flush_stack(struct sock **stack, unsigned int count, - struct sk_buff *skb, unsigned int final) +static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) { - unsigned int i; - struct sk_buff *skb1 = NULL; - struct sock *sk; + struct sk_buff *next, *segs; + int ret; - 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 (likely(!udp_unexpected_gso(sk, skb))) + return udp_queue_rcv_one_skb(sk, skb); - if (skb1 && udp_queue_rcv_skb(sk, skb1) <= 0) - skb1 = NULL; + BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_GSO_CB_OFFSET); + __skb_push(skb, -skb_mac_offset(skb)); + segs = udp_rcv_segment(sk, skb, true); + skb_list_walk_safe(segs, skb, next) { + __skb_pull(skb, skb_transport_offset(skb)); + + udp_post_segment_fix_csum(skb); + ret = udp_queue_rcv_one_skb(sk, skb); + if (ret > 0) + ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } - if (unlikely(skb1)) - kfree_skb(skb1); + return 0; } +/* For TCP sockets, sk_rx_dst is protected by socket lock + * For UDP, we use xchg() to guard against concurrent changes. + */ +bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) +{ + struct dst_entry *old; + + if (dst_hold_safe(dst)) { + old = unrcu_pointer(xchg(&sk->sk_rx_dst, RCU_INITIALIZER(dst))); + dst_release(old); + return old != dst; + } + return false; +} +EXPORT_IPV6_MOD(udp_sk_rx_dst_set); + /* * Multicasts and broadcasts go to each listener. * @@ -1584,59 +2529,76 @@ static void flush_stack(struct sock **stack, unsigned int count, static int __udp4_lib_mcast_deliver(struct net *net, struct sk_buff *skb, struct udphdr *uh, __be32 saddr, __be32 daddr, - struct udp_table *udptable) -{ - 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; - - spin_lock(&hslot->lock); - sk = sk_nulls_head(&hslot->head); - dif = skb->dev->ifindex; - sk = udp_v4_mcast_next(net, sk, uh->dest, daddr, uh->source, saddr, dif); - 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; - } + struct udp_table *udptable, + int proto) +{ + struct sock *sk, *first = NULL; + unsigned short hnum = ntohs(uh->dest); + struct udp_hslot *hslot = udp_hashslot(udptable, net, hnum); + unsigned int hash2 = 0, hash2_any = 0, use_hash2 = (hslot->count > 10); + unsigned int offset = offsetof(typeof(*sk), sk_node); + int dif = skb->dev->ifindex; + int sdif = inet_sdif(skb); + struct hlist_node *node; + struct sk_buff *nskb; + + if (use_hash2) { + hash2_any = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum) & + udptable->mask; + hash2 = ipv4_portaddr_hash(net, daddr, hnum) & udptable->mask; +start_lookup: + hslot = &udptable->hash2[hash2].hslot; + offset = offsetof(typeof(*sk), __sk_common.skc_portaddr_node); } - /* - * before releasing chain lock, we must take a reference on sockets - */ - for (i = 0; i < count; i++) - sock_hold(stack[i]); - spin_unlock(&hslot->lock); + sk_for_each_entry_offset_rcu(sk, node, &hslot->head, offset) { + if (!__udp_is_mcast_sock(net, sk, uh->dest, daddr, + uh->source, saddr, dif, sdif, hnum)) + continue; - /* - * do the slow work with no lock held - */ - if (count) { - flush_stack(stack, count, skb, count - 1); + if (!first) { + first = sk; + continue; + } + nskb = skb_clone(skb, GFP_ATOMIC); + + if (unlikely(!nskb)) { + udp_drops_inc(sk); + __UDP_INC_STATS(net, UDP_MIB_RCVBUFERRORS, + IS_UDPLITE(sk)); + __UDP_INC_STATS(net, UDP_MIB_INERRORS, + IS_UDPLITE(sk)); + continue; + } + if (udp_queue_rcv_skb(sk, nskb) > 0) + consume_skb(nskb); + } + + /* Also lookup *:port if we are using hash2 and haven't done so yet. */ + if (use_hash2 && hash2 != hash2_any) { + hash2 = hash2_any; + goto start_lookup; + } - for (i = 0; i < count; i++) - sock_put(stack[i]); + if (first) { + if (udp_queue_rcv_skb(first, skb) > 0) + consume_skb(skb); } else { kfree_skb(skb); + __UDP_INC_STATS(net, UDP_MIB_IGNOREDMULTI, + proto == IPPROTO_UDPLITE); } return 0; } /* Initialize UDP checksum. If exited with zero value (success), * CHECKSUM_UNNECESSARY means, that no more checks are required. - * Otherwise, csum completion requires chacksumming packet body, + * Otherwise, csum completion requires checksumming packet body, * including udp header and folding it to skb->csum. */ 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; @@ -1646,23 +2608,54 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, err = udplite_checksum_init(skb, uh); if (err) return err; + + if (UDP_SKB_CB(skb)->partial_cov) { + skb->csum = inet_compute_pseudo(skb, proto); + return 0; + } } - 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). + /* Note, we are only interested in != 0 or == 0, thus the + * force to int. */ + err = (__force int)skb_checksum_init_zero_check(skb, proto, uh->check, + inet_compute_pseudo); + if (err) + return err; + + if (skb->ip_summed == CHECKSUM_COMPLETE && !skb->csum_valid) { + /* If SW calculated the value, we know it's bad */ + if (skb->csum_complete_sw) + return 1; + + /* HW says the value is bad. Let's validate that. + * skb->csum is no longer the full packet checksum, + * so don't treat it as such. + */ + skb_checksum_complete_unset(skb); + } + + return 0; +} + +/* wrapper for udp_queue_rcv_skb taking care of csum conversion and + * return code conversion for ip layer consumption + */ +static int udp_unicast_rcv_skb(struct sock *sk, struct sk_buff *skb, + struct udphdr *uh) +{ + int ret; + + if (inet_get_convert_csum(sk) && uh->check && !IS_UDPLITE(sk)) + skb_checksum_try_convert(skb, IPPROTO_UDP, inet_compute_pseudo); + ret = udp_queue_rcv_skb(sk, skb); + + /* 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; } @@ -1673,12 +2666,16 @@ static inline int udp4_csum_init(struct sk_buff *skb, struct udphdr *uh, int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, int proto) { - struct sock *sk; + struct sock *sk = NULL; struct udphdr *uh; unsigned short ulen; struct rtable *rt = skb_rtable(skb); __be32 saddr, daddr; struct net *net = dev_net(skb->dev); + bool refcounted; + int drop_reason; + + drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; /* * Validate the packet. @@ -1704,51 +2701,58 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) - return __udp4_lib_mcast_deliver(net, skb, uh, - saddr, daddr, udptable); - - sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); + sk = inet_steal_sock(net, skb, sizeof(struct udphdr), saddr, uh->source, daddr, uh->dest, + &refcounted, udp_ehashfn); + if (IS_ERR(sk)) + goto no_sk; - if (sk != NULL) { + if (sk) { + struct dst_entry *dst = skb_dst(skb); int ret; - sk_mark_napi_id(sk, skb); - ret = udp_queue_rcv_skb(sk, skb); - sock_put(sk); + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) + udp_sk_rx_dst_set(sk, dst); - /* 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; + ret = udp_unicast_rcv_skb(sk, skb, uh); + if (refcounted) + sock_put(sk); + return ret; } + if (rt->rt_flags & (RTCF_BROADCAST|RTCF_MULTICAST)) + return __udp4_lib_mcast_deliver(net, skb, uh, + saddr, daddr, udptable, proto); + + sk = __udp4_lib_lookup_skb(skb, uh->source, uh->dest, udptable); + if (sk) + return udp_unicast_rcv_skb(sk, skb, uh); +no_sk: if (!xfrm4_policy_check(NULL, XFRM_POLICY_IN, skb)) goto drop; - nf_reset(skb); + nf_reset_ct(skb); /* No socket. Drop packet silently, if checksum is wrong */ if (udp_lib_checksum_complete(skb)) goto csum_error; - UDP_INC_STATS_BH(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); + drop_reason = SKB_DROP_REASON_NO_SOCKET; + __UDP_INC_STATS(net, UDP_MIB_NOPORTS, proto == IPPROTO_UDPLITE); icmp_send(skb, ICMP_DEST_UNREACH, ICMP_PORT_UNREACH, 0); /* * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ - kfree_skb(skb); + sk_skb_reason_drop(sk, skb, drop_reason); return 0; short_packet: - 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)); + drop_reason = SKB_DROP_REASON_PKT_TOO_SMALL; + net_dbg_ratelimited("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: @@ -1756,81 +2760,305 @@ 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 %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_reason = SKB_DROP_REASON_UDP_CSUM; + net_dbg_ratelimited("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(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: - UDP_INC_STATS_BH(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); + sk_skb_reason_drop(sk, skb, drop_reason); 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, int sdif) +{ + struct udp_table *udptable = net->ipv4.udp_table; + unsigned short hnum = ntohs(loc_port); + struct sock *sk, *result; + struct udp_hslot *hslot; + unsigned int slot; + + slot = udp_hashfn(net, hnum, udptable->mask); + hslot = &udptable->hash[slot]; + + /* Do not bother scanning a too big list */ + if (hslot->count > 10) + return NULL; + + result = NULL; + sk_for_each_rcu(sk, &hslot->head) { + if (__udp_is_mcast_sock(net, sk, loc_port, loc_addr, + rmt_port, rmt_addr, dif, sdif, hnum)) { + if (result) + return NULL; + result = sk; + } + } + + 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, int sdif) +{ + struct udp_table *udptable = net->ipv4.udp_table; + INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr); + unsigned short hnum = ntohs(loc_port); + struct udp_hslot *hslot2; + unsigned int hash2; + __portpair ports; + struct sock *sk; + + hash2 = ipv4_portaddr_hash(net, loc_addr, hnum); + hslot2 = udp_hashslot2(udptable, hash2); + ports = INET_COMBINED_PORTS(rmt_port, hnum); + + udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { + if (inet_match(net, sk, acookie, ports, dif, sdif)) + return sk; + /* Only check first socket in chain */ + break; + } + return NULL; +} + +enum skb_drop_reason udp_v4_early_demux(struct sk_buff *skb) +{ + struct net *net = dev_net(skb->dev); + struct in_device *in_dev = NULL; + const struct iphdr *iph; + const struct udphdr *uh; + struct sock *sk = NULL; + struct dst_entry *dst; + int dif = skb->dev->ifindex; + int sdif = inet_sdif(skb); + int ours; + + /* validate the packet */ + if (!pskb_may_pull(skb, skb_transport_offset(skb) + sizeof(struct udphdr))) + return SKB_NOT_DROPPED_YET; + + iph = ip_hdr(skb); + uh = udp_hdr(skb); + + if (skb->pkt_type == PACKET_MULTICAST) { + in_dev = __in_dev_get_rcu(skb->dev); + + if (!in_dev) + return SKB_NOT_DROPPED_YET; + + ours = ip_check_mc_rcu(in_dev, iph->daddr, iph->saddr, + iph->protocol); + if (!ours) + return SKB_NOT_DROPPED_YET; + + sk = __udp4_lib_mcast_demux_lookup(net, uh->dest, iph->daddr, + uh->source, iph->saddr, + dif, sdif); + } else if (skb->pkt_type == PACKET_HOST) { + sk = __udp4_lib_demux_lookup(net, uh->dest, iph->daddr, + uh->source, iph->saddr, dif, sdif); + } + + if (!sk) + return SKB_NOT_DROPPED_YET; + + skb->sk = sk; + DEBUG_NET_WARN_ON_ONCE(sk_is_refcounted(sk)); + skb->destructor = sock_pfree; + dst = rcu_dereference(sk->sk_rx_dst); + + if (dst) + dst = dst_check(dst, 0); + if (dst) { + u32 itag = 0; + + /* set noref for now. + * any place which wants to hold dst has to call + * dst_hold_safe() + */ + skb_dst_set_noref(skb, dst); + + /* for unconnected multicast sockets we need to validate + * the source on each packet + */ + if (!inet_sk(sk)->inet_daddr && in_dev) + return ip_mc_validate_source(skb, iph->daddr, + iph->saddr, + ip4h_dscp(iph), + skb->dev, in_dev, &itag); + } + return SKB_NOT_DROPPED_YET; +} + int udp_rcv(struct sk_buff *skb) { - return __udp4_lib_rcv(skb, &udp_table, IPPROTO_UDP); + return __udp4_lib_rcv(skb, dev_net(skb->dev)->ipv4.udp_table, IPPROTO_UDP); } void udp_destroy_sock(struct sock *sk) { struct udp_sock *up = udp_sk(sk); bool slow = lock_sock_fast(sk); + + /* protects from races with udp_abort() */ + sock_set_flag(sk, SOCK_DEAD); udp_flush_pending_frames(sk); 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); + if (static_branch_unlikely(&udp_encap_needed_key)) { + if (up->encap_type) { + void (*encap_destroy)(struct sock *sk); + encap_destroy = READ_ONCE(up->encap_destroy); + if (encap_destroy) + encap_destroy(sk); + } + if (udp_test_bit(ENCAP_ENABLED, sk)) { + static_branch_dec(&udp_encap_needed_key); + udp_tunnel_cleanup_gro(sk); + } + } +} + +typedef struct sk_buff *(*udp_gro_receive_t)(struct sock *sk, + struct list_head *head, + struct sk_buff *skb); + +static void set_xfrm_gro_udp_encap_rcv(__u16 encap_type, unsigned short family, + struct sock *sk) +{ +#ifdef CONFIG_XFRM + udp_gro_receive_t new_gro_receive; + + if (udp_test_bit(GRO_ENABLED, sk) && encap_type == UDP_ENCAP_ESPINUDP) { + if (IS_ENABLED(CONFIG_IPV6) && family == AF_INET6) + new_gro_receive = ipv6_stub->xfrm6_gro_udp_encap_rcv; + else + new_gro_receive = xfrm4_gro_udp_encap_rcv; + + if (udp_sk(sk)->gro_receive != new_gro_receive) { + /* + * With IPV6_ADDRFORM the gro callback could change + * after being set, unregister the old one, if valid. + */ + if (udp_sk(sk)->gro_receive) + udp_tunnel_update_gro_rcv(sk, false); + + WRITE_ONCE(udp_sk(sk)->gro_receive, new_gro_receive); + udp_tunnel_update_gro_rcv(sk, true); + } } +#endif } /* * Socket option code for UDP */ int udp_lib_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen, + sockptr_t 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 (level == SOL_SOCKET) { + err = sk_setsockopt(sk, level, optname, optval, optlen); + + if (optname == SO_RCVBUF || optname == SO_RCVBUFFORCE) { + sockopt_lock_sock(sk); + /* paired with READ_ONCE in udp_rmem_release() */ + WRITE_ONCE(up->forward_threshold, sk->sk_rcvbuf >> 2); + sockopt_release_sock(sk); + } + return err; + } + if (optlen < sizeof(int)) return -EINVAL; - if (get_user(val, (int __user *)optval)) + if (copy_from_sockptr(&val, optval, sizeof(val))) return -EFAULT; + valbool = val ? 1 : 0; + switch (optname) { case UDP_CORK: if (val != 0) { - up->corkflag = 1; + udp_set_bit(CORK, sk); } else { - up->corkflag = 0; + udp_clear_bit(CORK, sk); lock_sock(sk); - (*push_pending_frames)(sk); + push_pending_frames(sk); release_sock(sk); } break; case UDP_ENCAP: + sockopt_lock_sock(sk); switch (val) { case 0: +#ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: - case UDP_ENCAP_ESPINUDP_NON_IKE: - up->encap_rcv = xfrm4_udp_encap_rcv; - /* FALLTHROUGH */ + set_xfrm_gro_udp_encap_rcv(val, sk->sk_family, sk); +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + WRITE_ONCE(up->encap_rcv, + ipv6_stub->xfrm6_udp_encap_rcv); + else +#endif + WRITE_ONCE(up->encap_rcv, + xfrm4_udp_encap_rcv); +#endif + fallthrough; case UDP_ENCAP_L2TPINUDP: - up->encap_type = val; - udp_encap_enable(); + WRITE_ONCE(up->encap_type, val); + udp_tunnel_encap_enable(sk); break; default: err = -ENOPROTOOPT; break; } + sockopt_release_sock(sk); + break; + + case UDP_NO_CHECK6_TX: + udp_set_no_check6_tx(sk, valbool); + break; + + case UDP_NO_CHECK6_RX: + udp_set_no_check6_rx(sk, valbool); + break; + + case UDP_SEGMENT: + if (val < 0 || val > USHRT_MAX) + return -EINVAL; + WRITE_ONCE(up->gso_size, val); + break; + + case UDP_GRO: + sockopt_lock_sock(sk); + /* when enabling GRO, accept the related GSO packet type */ + if (valbool) + udp_tunnel_encap_enable(sk); + udp_assign_bit(GRO_ENABLED, sk, valbool); + udp_assign_bit(ACCEPT_L4, sk, valbool); + set_xfrm_gro_udp_encap_rcv(up->encap_type, sk->sk_family, sk); + sockopt_release_sock(sk); break; /* @@ -1845,8 +3073,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, val = 8; else if (val > USHRT_MAX) val = USHRT_MAX; - up->pcslen = val; - up->pcflag |= UDPLITE_SEND_CC; + WRITE_ONCE(up->pcslen, val); + udp_set_bit(UDPLITE_SEND_CC, sk); break; /* The receiver specifies a minimum checksum coverage value. To make @@ -1859,8 +3087,8 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, val = 8; else if (val > USHRT_MAX) val = USHRT_MAX; - up->pcrlen = val; - up->pcflag |= UDPLITE_RECV_CC; + WRITE_ONCE(up->pcrlen, val); + udp_set_bit(UDPLITE_RECV_CC, sk); break; default: @@ -1870,28 +3098,18 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, return err; } -EXPORT_SYMBOL(udp_lib_setsockopt); +EXPORT_IPV6_MOD(udp_lib_setsockopt); -int udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) +int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval, + unsigned int optlen) { - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, + if (level == SOL_UDP || level == SOL_UDPLITE || level == SOL_SOCKET) + return udp_lib_setsockopt(sk, level, optname, + optval, optlen, udp_push_pending_frames); return ip_setsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udp_setsockopt(struct sock *sk, int level, int optname, - char __user *optval, unsigned int optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_setsockopt(sk, level, optname, optval, optlen, - udp_push_pending_frames); - return compat_ip_setsockopt(sk, level, optname, optval, optlen); -} -#endif - int udp_lib_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) { @@ -1901,28 +3119,44 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, if (get_user(len, optlen)) return -EFAULT; - len = min_t(unsigned int, len, sizeof(int)); - if (len < 0) return -EINVAL; + len = min_t(unsigned int, len, sizeof(int)); + switch (optname) { case UDP_CORK: - val = up->corkflag; + val = udp_test_bit(CORK, sk); break; case UDP_ENCAP: - val = up->encap_type; + val = READ_ONCE(up->encap_type); + break; + + case UDP_NO_CHECK6_TX: + val = udp_get_no_check6_tx(sk); + break; + + case UDP_NO_CHECK6_RX: + val = udp_get_no_check6_rx(sk); + break; + + case UDP_SEGMENT: + val = READ_ONCE(up->gso_size); + break; + + case UDP_GRO: + val = udp_test_bit(GRO_ENABLED, sk); 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: - val = up->pcslen; + val = READ_ONCE(up->pcslen); break; case UDPLITE_RECV_CSCOV: - val = up->pcrlen; + val = READ_ONCE(up->pcrlen); break; default: @@ -1935,7 +3169,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, return -EFAULT; return 0; } -EXPORT_SYMBOL(udp_lib_getsockopt); +EXPORT_IPV6_MOD(udp_lib_getsockopt); int udp_getsockopt(struct sock *sk, int level, int optname, char __user *optval, int __user *optlen) @@ -1945,20 +3179,11 @@ int udp_getsockopt(struct sock *sk, int level, int optname, return ip_getsockopt(sk, level, optname, optval, optlen); } -#ifdef CONFIG_COMPAT -int compat_udp_getsockopt(struct sock *sk, int level, int optname, - char __user *optval, int __user *optlen) -{ - if (level == SOL_UDP || level == SOL_UDPLITE) - return udp_lib_getsockopt(sk, level, optname, optval, optlen); - return compat_ip_getsockopt(sk, level, optname, optval, optlen); -} -#endif /** * udp_poll - wait for a UDP event. - * @file - file struct - * @sock - socket - * @wait - poll table + * @file: - file struct + * @sock: - socket + * @wait: - poll table * * This is same as datagram poll, except for the special case of * blocking sockets. If application is using a blocking fd @@ -1967,79 +3192,135 @@ int compat_udp_getsockopt(struct sock *sk, int level, int optname, * but then block when reading it. Add special case code * to work around these arguably broken applications. */ -unsigned int udp_poll(struct file *file, struct socket *sock, poll_table *wait) +__poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) { - unsigned int mask = datagram_poll(file, sock, wait); + __poll_t mask = datagram_poll(file, sock, wait); struct sock *sk = sock->sk; - sock_rps_record_flow(sk); + if (!skb_queue_empty_lockless(&udp_sk(sk)->reader_queue)) + mask |= EPOLLIN | EPOLLRDNORM; /* 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); + if ((mask & EPOLLRDNORM) && !(file->f_flags & O_NONBLOCK) && + !(sk->sk_shutdown & RCV_SHUTDOWN) && first_packet_length(sk) == -1) + mask &= ~(EPOLLIN | EPOLLRDNORM); + /* psock ingress_msg queue should not contain any bad checksum frames */ + if (sk_is_readable(sk)) + mask |= EPOLLIN | EPOLLRDNORM; return mask; } -EXPORT_SYMBOL(udp_poll); +EXPORT_IPV6_MOD(udp_poll); + +int udp_abort(struct sock *sk, int err) +{ + if (!has_current_bpf_ctx()) + lock_sock(sk); + + /* udp{v6}_destroy_sock() sets it under the sk lock, avoid racing + * with close() + */ + if (sock_flag(sk, SOCK_DEAD)) + goto out; + + sk->sk_err = err; + sk_error_report(sk); + __udp_disconnect(sk, 0); + +out: + if (!has_current_bpf_ctx()) + release_sock(sk); + + return 0; +} +EXPORT_IPV6_MOD_GPL(udp_abort); struct proto udp_prot = { - .name = "UDP", - .owner = THIS_MODULE, - .close = udp_lib_close, - .connect = ip4_datagram_connect, - .disconnect = udp_disconnect, - .ioctl = udp_ioctl, - .destroy = udp_destroy_sock, - .setsockopt = udp_setsockopt, - .getsockopt = udp_getsockopt, - .sendmsg = udp_sendmsg, - .recvmsg = udp_recvmsg, - .sendpage = udp_sendpage, - .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, + .name = "UDP", + .owner = THIS_MODULE, + .close = udp_lib_close, + .pre_connect = udp_pre_connect, + .connect = udp_connect, + .disconnect = udp_disconnect, + .ioctl = udp_ioctl, + .init = udp_init_sock, + .destroy = udp_destroy_sock, + .setsockopt = udp_setsockopt, + .getsockopt = udp_getsockopt, + .sendmsg = udp_sendmsg, + .recvmsg = udp_recvmsg, + .splice_eof = udp_splice_eof, + .release_cb = ip4_datagram_release_cb, + .hash = udp_lib_hash, + .unhash = udp_lib_unhash, + .rehash = udp_v4_rehash, + .get_port = udp_v4_get_port, + .put_port = udp_lib_unhash, +#ifdef CONFIG_BPF_SYSCALL + .psock_update_sk_prot = udp_bpf_update_proto, #endif - .clear_sk = sk_prot_clear_portaddr_nulls, + .memory_allocated = &net_aligned_data.udp_memory_allocated, + .per_cpu_fw_alloc = &udp_memory_per_cpu_fw_alloc, + + .sysctl_mem = sysctl_udp_mem, + .sysctl_wmem_offset = offsetof(struct net, ipv4.sysctl_udp_wmem_min), + .sysctl_rmem_offset = offsetof(struct net, ipv4.sysctl_udp_rmem_min), + .obj_size = sizeof(struct udp_sock), + .h.udp_table = NULL, + .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); /* ------------------------------------------------------------------------ */ #ifdef CONFIG_PROC_FS +static unsigned short seq_file_family(const struct seq_file *seq); +static bool seq_sk_match(struct seq_file *seq, const struct sock *sk) +{ + unsigned short family = seq_file_family(seq); + + /* AF_UNSPEC is used as a match all */ + return ((family == AF_UNSPEC || family == sk->sk_family) && + net_eq(sock_net(sk), seq_file_net(seq))); +} + +#ifdef CONFIG_BPF_SYSCALL +static const struct seq_operations bpf_iter_udp_seq_ops; +#endif +static struct udp_table *udp_get_table_seq(struct seq_file *seq, + struct net *net) +{ + const struct udp_seq_afinfo *afinfo; + +#ifdef CONFIG_BPF_SYSCALL + if (seq->op == &bpf_iter_udp_seq_ops) + return net->ipv4.udp_table; +#endif + + afinfo = pde_data(file_inode(seq->file)); + return afinfo->udp_table ? : net->ipv4.udp_table; +} + 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); + struct udp_table *udptable; + struct sock *sk; + + udptable = udp_get_table_seq(seq, net); - for (state->bucket = start; state->bucket <= state->udp_table->mask; + for (state->bucket = start; state->bucket <= udptable->mask; ++state->bucket) { - struct hlist_nulls_node *node; - struct udp_hslot *hslot = &state->udp_table->hash[state->bucket]; + struct udp_hslot *hslot = &udptable->hash[state->bucket]; - if (hlist_nulls_empty(&hslot->head)) + if (hlist_empty(&hslot->head)) continue; 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) + sk_for_each(sk, &hslot->head) { + if (seq_sk_match(seq, sk)) goto found; } spin_unlock_bh(&hslot->lock); @@ -2053,14 +3334,18 @@ 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); + struct udp_table *udptable; do { - sk = sk_nulls_next(sk); - } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != state->family)); + sk = sk_next(sk); + } while (sk && !seq_sk_match(seq, sk)); if (!sk) { - if (state->bucket <= state->udp_table->mask) - spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); + udptable = udp_get_table_seq(seq, net); + + if (state->bucket <= udptable->mask) + spin_unlock_bh(&udptable->hash[state->bucket].lock); + return udp_get_first(seq, state->bucket + 1); } return sk; @@ -2076,15 +3361,16 @@ static struct sock *udp_get_idx(struct seq_file *seq, loff_t pos) return pos ? NULL : sk; } -static void *udp_seq_start(struct seq_file *seq, loff_t *pos) +void *udp_seq_start(struct seq_file *seq, loff_t *pos) { struct udp_iter_state *state = seq->private; state->bucket = MAX_UDP_PORTS; return *pos ? udp_get_idx(seq, *pos-1) : SEQ_START_TOKEN; } +EXPORT_IPV6_MOD(udp_seq_start); -static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) { struct sock *sk; @@ -2096,60 +3382,23 @@ static void *udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++*pos; return sk; } +EXPORT_IPV6_MOD(udp_seq_next); -static void udp_seq_stop(struct seq_file *seq, void *v) +void udp_seq_stop(struct seq_file *seq, void *v) { struct udp_iter_state *state = seq->private; + struct udp_table *udptable; - if (state->bucket <= state->udp_table->mask) - spin_unlock_bh(&state->udp_table->hash[state->bucket].lock); -} - -int udp_seq_open(struct inode *inode, struct file *file) -{ - struct udp_seq_afinfo *afinfo = PDE_DATA(inode); - struct udp_iter_state *s; - int err; - - 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->udp_table = afinfo->udp_table; - return err; -} -EXPORT_SYMBOL(udp_seq_open); - -/* ------------------------------------------------------------------------ */ -int udp_proc_register(struct net *net, struct udp_seq_afinfo *afinfo) -{ - struct proc_dir_entry *p; - int rc = 0; - - afinfo->seq_ops.start = udp_seq_start; - afinfo->seq_ops.next = udp_seq_next; - afinfo->seq_ops.stop = udp_seq_stop; + udptable = udp_get_table_seq(seq, seq_file_net(seq)); - p = proc_create_data(afinfo->name, S_IRUGO, net->proc_net, - afinfo->seq_fops, afinfo); - if (!p) - rc = -ENOMEM; - return rc; + if (state->bucket <= udptable->mask) + spin_unlock_bh(&udptable->hash[state->bucket].lock); } -EXPORT_SYMBOL(udp_proc_register); - -void udp_proc_unregister(struct net *net, struct udp_seq_afinfo *afinfo) -{ - remove_proc_entry(afinfo->name, net->proc_net); -} -EXPORT_SYMBOL(udp_proc_unregister); +EXPORT_IPV6_MOD(udp_seq_stop); /* ------------------------------------------------------------------------ */ static void udp4_format_sock(struct sock *sp, struct seq_file *f, - int bucket, int *len) + int bucket) { struct inet_sock *inet = inet_sk(sp); __be32 dest = inet->inet_daddr; @@ -2158,61 +3407,345 @@ static void udp4_format_sock(struct sock *sp, struct seq_file *f, __u16 srcp = ntohs(inet->inet_sport); seq_printf(f, "%5d: %08X:%04X %08X:%04X" - " %02X %08X:%08X %02X:%08lX %08X %5d %8d %lu %d %pK %d%n", + " %02X %08X:%08X %02X:%08lX %08X %5u %8d %lu %d %pK %u", bucket, src, srcp, dest, destp, sp->sk_state, sk_wmem_alloc_get(sp), - sk_rmem_alloc_get(sp), + udp_rqueue_get(sp), 0, 0L, 0, - from_kuid_munged(seq_user_ns(f), sock_i_uid(sp)), + from_kuid_munged(seq_user_ns(f), sk_uid(sp)), 0, sock_i_ino(sp), - atomic_read(&sp->sk_refcnt), sp, - atomic_read(&sp->sk_drops), len); + refcount_read(&sp->sk_refcnt), sp, + sk_drops_read(sp)); } 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 ref pointer drops"); else { struct udp_iter_state *state = seq->private; - int len; - udp4_format_sock(v, seq, state->bucket, &len); - seq_printf(seq, "%*s\n", 127 - len, ""); + 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 +#ifdef CONFIG_BPF_SYSCALL +struct bpf_iter__udp { + __bpf_md_ptr(struct bpf_iter_meta *, meta); + __bpf_md_ptr(struct udp_sock *, udp_sk); + uid_t uid __aligned(8); + int bucket __aligned(8); }; -/* ------------------------------------------------------------------------ */ +union bpf_udp_iter_batch_item { + struct sock *sk; + __u64 cookie; +}; + +struct bpf_udp_iter_state { + struct udp_iter_state state; + unsigned int cur_sk; + unsigned int end_sk; + unsigned int max_sk; + union bpf_udp_iter_batch_item *batch; +}; + +static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter, + unsigned int new_batch_sz, gfp_t flags); +static struct sock *bpf_iter_udp_resume(struct sock *first_sk, + union bpf_udp_iter_batch_item *cookies, + int n_cookies) +{ + struct sock *sk = NULL; + int i; + + for (i = 0; i < n_cookies; i++) { + sk = first_sk; + udp_portaddr_for_each_entry_from(sk) + if (cookies[i].cookie == atomic64_read(&sk->sk_cookie)) + goto done; + } +done: + return sk; +} + +static struct sock *bpf_iter_udp_batch(struct seq_file *seq) +{ + struct bpf_udp_iter_state *iter = seq->private; + struct udp_iter_state *state = &iter->state; + unsigned int find_cookie, end_cookie; + struct net *net = seq_file_net(seq); + struct udp_table *udptable; + unsigned int batch_sks = 0; + int resume_bucket; + int resizes = 0; + struct sock *sk; + int err = 0; + + resume_bucket = state->bucket; + + /* The current batch is done, so advance the bucket. */ + if (iter->cur_sk == iter->end_sk) + state->bucket++; + + udptable = udp_get_table_seq(seq, net); + +again: + /* New batch for the next bucket. + * Iterate over the hash table to find a bucket with sockets matching + * the iterator attributes, and return the first matching socket from + * the bucket. The remaining matched sockets from the bucket are batched + * before releasing the bucket lock. This allows BPF programs that are + * called in seq_show to acquire the bucket lock if needed. + */ + find_cookie = iter->cur_sk; + end_cookie = iter->end_sk; + iter->cur_sk = 0; + iter->end_sk = 0; + batch_sks = 0; + + for (; state->bucket <= udptable->mask; state->bucket++) { + struct udp_hslot *hslot2 = &udptable->hash2[state->bucket].hslot; + + if (hlist_empty(&hslot2->head)) + goto next_bucket; + + spin_lock_bh(&hslot2->lock); + sk = hlist_entry_safe(hslot2->head.first, struct sock, + __sk_common.skc_portaddr_node); + /* Resume from the first (in iteration order) unseen socket from + * the last batch that still exists in resume_bucket. Most of + * the time this will just be where the last iteration left off + * in resume_bucket unless that socket disappeared between + * reads. + */ + if (state->bucket == resume_bucket) + sk = bpf_iter_udp_resume(sk, &iter->batch[find_cookie], + end_cookie - find_cookie); +fill_batch: + udp_portaddr_for_each_entry_from(sk) { + if (seq_sk_match(seq, sk)) { + if (iter->end_sk < iter->max_sk) { + sock_hold(sk); + iter->batch[iter->end_sk++].sk = sk; + } + batch_sks++; + } + } + + /* Allocate a larger batch and try again. */ + if (unlikely(resizes <= 1 && iter->end_sk && + iter->end_sk != batch_sks)) { + resizes++; + + /* First, try with GFP_USER to maximize the chances of + * grabbing more memory. + */ + if (resizes == 1) { + spin_unlock_bh(&hslot2->lock); + err = bpf_iter_udp_realloc_batch(iter, + batch_sks * 3 / 2, + GFP_USER); + if (err) + return ERR_PTR(err); + /* Start over. */ + goto again; + } + + /* Next, hold onto the lock, so the bucket doesn't + * change while we get the rest of the sockets. + */ + err = bpf_iter_udp_realloc_batch(iter, batch_sks, + GFP_NOWAIT); + if (err) { + spin_unlock_bh(&hslot2->lock); + return ERR_PTR(err); + } + + /* Pick up where we left off. */ + sk = iter->batch[iter->end_sk - 1].sk; + sk = hlist_entry_safe(sk->__sk_common.skc_portaddr_node.next, + struct sock, + __sk_common.skc_portaddr_node); + batch_sks = iter->end_sk; + goto fill_batch; + } + + spin_unlock_bh(&hslot2->lock); + + if (iter->end_sk) + break; +next_bucket: + resizes = 0; + } + + WARN_ON_ONCE(iter->end_sk != batch_sks); + return iter->end_sk ? iter->batch[0].sk : NULL; +} + +static void *bpf_iter_udp_seq_next(struct seq_file *seq, void *v, loff_t *pos) +{ + struct bpf_udp_iter_state *iter = seq->private; + struct sock *sk; + + /* Whenever seq_next() is called, the iter->cur_sk is + * done with seq_show(), so unref the iter->cur_sk. + */ + if (iter->cur_sk < iter->end_sk) + sock_put(iter->batch[iter->cur_sk++].sk); + + /* After updating iter->cur_sk, check if there are more sockets + * available in the current bucket batch. + */ + if (iter->cur_sk < iter->end_sk) + sk = iter->batch[iter->cur_sk].sk; + else + /* Prepare a new batch. */ + sk = bpf_iter_udp_batch(seq); + + ++*pos; + return sk; +} + +static void *bpf_iter_udp_seq_start(struct seq_file *seq, loff_t *pos) +{ + /* bpf iter does not support lseek, so it always + * continue from where it was stop()-ped. + */ + if (*pos) + return bpf_iter_udp_batch(seq); + + return SEQ_START_TOKEN; +} + +static int udp_prog_seq_show(struct bpf_prog *prog, struct bpf_iter_meta *meta, + struct udp_sock *udp_sk, uid_t uid, int bucket) +{ + struct bpf_iter__udp ctx; + + meta->seq_num--; /* skip SEQ_START_TOKEN */ + ctx.meta = meta; + ctx.udp_sk = udp_sk; + ctx.uid = uid; + ctx.bucket = bucket; + return bpf_iter_run_prog(prog, &ctx); +} + +static int bpf_iter_udp_seq_show(struct seq_file *seq, void *v) +{ + struct udp_iter_state *state = seq->private; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + struct sock *sk = v; + uid_t uid; + int ret; + + if (v == SEQ_START_TOKEN) + return 0; + + lock_sock(sk); + + if (unlikely(sk_unhashed(sk))) { + ret = SEQ_SKIP; + goto unlock; + } + + uid = from_kuid_munged(seq_user_ns(seq), sk_uid(sk)); + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + ret = udp_prog_seq_show(prog, &meta, v, uid, state->bucket); + +unlock: + release_sock(sk); + return ret; +} + +static void bpf_iter_udp_put_batch(struct bpf_udp_iter_state *iter) +{ + union bpf_udp_iter_batch_item *item; + unsigned int cur_sk = iter->cur_sk; + __u64 cookie; + + /* Remember the cookies of the sockets we haven't seen yet, so we can + * pick up where we left off next time around. + */ + while (cur_sk < iter->end_sk) { + item = &iter->batch[cur_sk++]; + cookie = sock_gen_cookie(item->sk); + sock_put(item->sk); + item->cookie = cookie; + } +} + +static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) +{ + struct bpf_udp_iter_state *iter = seq->private; + struct bpf_iter_meta meta; + struct bpf_prog *prog; + + if (!v) { + meta.seq = seq; + prog = bpf_iter_get_info(&meta, true); + if (prog) + (void)udp_prog_seq_show(prog, &meta, v, 0, 0); + } + + if (iter->cur_sk < iter->end_sk) + bpf_iter_udp_put_batch(iter); +} + +static const struct seq_operations bpf_iter_udp_seq_ops = { + .start = bpf_iter_udp_seq_start, + .next = bpf_iter_udp_seq_next, + .stop = bpf_iter_udp_seq_stop, + .show = bpf_iter_udp_seq_show, +}; +#endif + +static unsigned short seq_file_family(const struct seq_file *seq) +{ + const struct udp_seq_afinfo *afinfo; + +#ifdef CONFIG_BPF_SYSCALL + /* BPF iterator: bpf programs to filter sockets. */ + if (seq->op == &bpf_iter_udp_seq_ops) + return AF_UNSPEC; +#endif + + /* Proc fs iterator */ + afinfo = pde_data(file_inode(seq->file)); + return afinfo->family; +} + +const struct seq_operations udp_seq_ops = { + .start = udp_seq_start, + .next = udp_seq_next, + .stop = udp_seq_stop, + .show = udp4_seq_show, +}; +EXPORT_IPV6_MOD(udp_seq_ops); + static struct udp_seq_afinfo udp4_seq_afinfo = { - .name = "udp", .family = AF_INET, - .udp_table = &udp_table, - .seq_fops = &udp_afinfo_seq_fops, - .seq_ops = { - .show = udp4_seq_show, - }, + .udp_table = NULL, }; static int __net_init udp4_proc_init_net(struct net *net) { - return udp_proc_register(net, &udp4_seq_afinfo); + if (!proc_create_net_data("udp", 0444, net->proc_net, &udp_seq_ops, + sizeof(struct udp_iter_state), &udp4_seq_afinfo)) + return -ENOMEM; + return 0; } static void __net_exit udp4_proc_exit_net(struct net *net) { - udp_proc_unregister(net, &udp4_seq_afinfo); + remove_proc_entry("udp", net->proc_net); } static struct pernet_operations udp4_net_ops = { @@ -2251,105 +3784,257 @@ __setup("uhash_entries=", set_uhash_entries); void __init udp_table_init(struct udp_table *table, const char *name) { - unsigned int i; + unsigned int i, slot_size; + slot_size = sizeof(struct udp_hslot) + sizeof(struct udp_hslot_main) + + udp_hash4_slot_size(); table->hash = alloc_large_system_hash(name, - 2 * sizeof(struct udp_hslot), + slot_size, uhash_entries, 21, /* one slot per 2 MB */ 0, &table->log, &table->mask, UDP_HTABLE_SIZE_MIN, - 64 * 1024); + UDP_HTABLE_SIZE_MAX); - table->hash2 = table->hash + (table->mask + 1); + table->hash2 = (void *)(table->hash + (table->mask + 1)); for (i = 0; i <= table->mask; i++) { - INIT_HLIST_NULLS_HEAD(&table->hash[i].head, i); + INIT_HLIST_HEAD(&table->hash[i].head); 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); + INIT_HLIST_HEAD(&table->hash2[i].hslot.head); + table->hash2[i].hslot.count = 0; + spin_lock_init(&table->hash2[i].hslot.lock); } + udp_table_hash4_init(table); } -void __init udp_init(void) +u32 udp_flow_hashrnd(void) { - unsigned long limit; + static u32 hashrnd __read_mostly; - 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; - sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; + net_get_random_once(&hashrnd, sizeof(hashrnd)); - sysctl_udp_rmem_min = SK_MEM_QUANTUM; - sysctl_udp_wmem_min = SK_MEM_QUANTUM; + return hashrnd; } +EXPORT_SYMBOL(udp_flow_hashrnd); -struct sk_buff *skb_udp_tunnel_segment(struct sk_buff *skb, - netdev_features_t features) +static void __net_init udp_sysctl_init(struct net *net) { - struct sk_buff *segs = ERR_PTR(-EINVAL); - 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 outer_hlen; + net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; + net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; - if (unlikely(!pskb_may_pull(skb, tnl_hlen))) - goto out; +#ifdef CONFIG_NET_L3_MASTER_DEV + net->ipv4.sysctl_udp_l3mdev_accept = 0; +#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); - - /* 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)) +static struct udp_table __net_init *udp_pernet_table_alloc(unsigned int hash_entries) +{ + struct udp_table *udptable; + unsigned int slot_size; + int i; + + udptable = kmalloc(sizeof(*udptable), GFP_KERNEL); + if (!udptable) goto out; - outer_hlen = skb_tnl_header_len(skb); - skb = segs; - do { - struct udphdr *uh; - int udp_offset = outer_hlen - tnl_hlen; + slot_size = sizeof(struct udp_hslot) + sizeof(struct udp_hslot_main) + + udp_hash4_slot_size(); + udptable->hash = vmalloc_huge(hash_entries * slot_size, + GFP_KERNEL_ACCOUNT); + if (!udptable->hash) + goto free_table; + + udptable->hash2 = (void *)(udptable->hash + hash_entries); + udptable->mask = hash_entries - 1; + udptable->log = ilog2(hash_entries); + + for (i = 0; i < hash_entries; i++) { + INIT_HLIST_HEAD(&udptable->hash[i].head); + udptable->hash[i].count = 0; + spin_lock_init(&udptable->hash[i].lock); + + INIT_HLIST_HEAD(&udptable->hash2[i].hslot.head); + udptable->hash2[i].hslot.count = 0; + spin_lock_init(&udptable->hash2[i].hslot.lock); + } + udp_table_hash4_init(udptable); - skb_reset_inner_headers(skb); - skb->encapsulation = 1; + return udptable; - skb->mac_len = mac_len; +free_table: + kfree(udptable); +out: + return NULL; +} - skb_push(skb, outer_hlen); - skb_reset_mac_header(skb); - skb_set_network_header(skb, mac_len); - skb_set_transport_header(skb, udp_offset); - uh = udp_hdr(skb); - uh->len = htons(skb->len - udp_offset); +static void __net_exit udp_pernet_table_free(struct net *net) +{ + struct udp_table *udptable = net->ipv4.udp_table; - /* csum segment if tunnel sets skb with csum. */ - if (unlikely(uh->check)) { - struct iphdr *iph = ip_hdr(skb); + if (udptable == &udp_table) + return; - uh->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, - skb->len - udp_offset, - IPPROTO_UDP, 0); - uh->check = csum_fold(skb_checksum(skb, udp_offset, - skb->len - udp_offset, 0)); - if (uh->check == 0) - uh->check = CSUM_MANGLED_0; + kvfree(udptable->hash); + kfree(udptable); +} - } - skb->protocol = protocol; - } while ((skb = skb->next)); -out: - return segs; +static void __net_init udp_set_table(struct net *net) +{ + struct udp_table *udptable; + unsigned int hash_entries; + struct net *old_net; + + if (net_eq(net, &init_net)) + goto fallback; + + old_net = current->nsproxy->net_ns; + hash_entries = READ_ONCE(old_net->ipv4.sysctl_udp_child_hash_entries); + if (!hash_entries) + goto fallback; + + /* Set min to keep the bitmap on stack in udp_lib_get_port() */ + if (hash_entries < UDP_HTABLE_SIZE_MIN_PERNET) + hash_entries = UDP_HTABLE_SIZE_MIN_PERNET; + else + hash_entries = roundup_pow_of_two(hash_entries); + + udptable = udp_pernet_table_alloc(hash_entries); + if (udptable) { + net->ipv4.udp_table = udptable; + } else { + pr_warn("Failed to allocate UDP hash table (entries: %u) " + "for a netns, fallback to the global one\n", + hash_entries); +fallback: + net->ipv4.udp_table = &udp_table; + } +} + +static int __net_init udp_pernet_init(struct net *net) +{ +#if IS_ENABLED(CONFIG_NET_UDP_TUNNEL) + int i; + + /* No tunnel is configured */ + for (i = 0; i < ARRAY_SIZE(net->ipv4.udp_tunnel_gro); ++i) { + INIT_HLIST_HEAD(&net->ipv4.udp_tunnel_gro[i].list); + RCU_INIT_POINTER(net->ipv4.udp_tunnel_gro[i].sk, NULL); + } +#endif + udp_sysctl_init(net); + udp_set_table(net); + + return 0; +} + +static void __net_exit udp_pernet_exit(struct net *net) +{ + udp_pernet_table_free(net); +} + +static struct pernet_operations __net_initdata udp_sysctl_ops = { + .init = udp_pernet_init, + .exit = udp_pernet_exit, +}; + +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) +DEFINE_BPF_ITER_FUNC(udp, struct bpf_iter_meta *meta, + struct udp_sock *udp_sk, uid_t uid, int bucket) + +static int bpf_iter_udp_realloc_batch(struct bpf_udp_iter_state *iter, + unsigned int new_batch_sz, gfp_t flags) +{ + union bpf_udp_iter_batch_item *new_batch; + + new_batch = kvmalloc_array(new_batch_sz, sizeof(*new_batch), + flags | __GFP_NOWARN); + if (!new_batch) + return -ENOMEM; + + if (flags != GFP_NOWAIT) + bpf_iter_udp_put_batch(iter); + + memcpy(new_batch, iter->batch, sizeof(*iter->batch) * iter->end_sk); + kvfree(iter->batch); + iter->batch = new_batch; + iter->max_sk = new_batch_sz; + + return 0; +} + +#define INIT_BATCH_SZ 16 + +static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct bpf_udp_iter_state *iter = priv_data; + int ret; + + ret = bpf_iter_init_seq_net(priv_data, aux); + if (ret) + return ret; + + ret = bpf_iter_udp_realloc_batch(iter, INIT_BATCH_SZ, GFP_USER); + if (ret) + bpf_iter_fini_seq_net(priv_data); + + iter->state.bucket = -1; + + return ret; +} + +static void bpf_iter_fini_udp(void *priv_data) +{ + struct bpf_udp_iter_state *iter = priv_data; + + bpf_iter_fini_seq_net(priv_data); + kvfree(iter->batch); +} + +static const struct bpf_iter_seq_info udp_seq_info = { + .seq_ops = &bpf_iter_udp_seq_ops, + .init_seq_private = bpf_iter_init_udp, + .fini_seq_private = bpf_iter_fini_udp, + .seq_priv_size = sizeof(struct bpf_udp_iter_state), +}; + +static struct bpf_iter_reg udp_reg_info = { + .target = "udp", + .ctx_arg_info_size = 1, + .ctx_arg_info = { + { offsetof(struct bpf_iter__udp, udp_sk), + PTR_TO_BTF_ID_OR_NULL | PTR_TRUSTED }, + }, + .seq_info = &udp_seq_info, +}; + +static void __init bpf_iter_register(void) +{ + udp_reg_info.ctx_arg_info[0].btf_id = btf_sock_ids[BTF_SOCK_TYPE_UDP]; + if (bpf_iter_reg_target(&udp_reg_info)) + pr_warn("Warning: could not register bpf iterator udp\n"); +} +#endif + +void __init udp_init(void) +{ + unsigned long limit; + + 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; + sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; + + if (register_pernet_subsys(&udp_sysctl_ops)) + panic("UDP: failed to init sysctl parameters.\n"); + +#if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS) + bpf_iter_register(); +#endif } |