diff options
Diffstat (limited to 'net/ipv4/udp.c')
| -rw-r--r-- | net/ipv4/udp.c | 549 |
1 files changed, 413 insertions, 136 deletions
diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index 08a41f1e1cd2..6a320a614e54 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -74,11 +74,11 @@ #define pr_fmt(fmt) "UDP: " fmt +#include <linux/bpf-cgroup.h> #include <linux/uaccess.h> #include <asm/ioctls.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> @@ -106,12 +106,16 @@ #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> +#if IS_ENABLED(CONFIG_IPV6) +#include <net/ipv6_stubs.h> +#endif struct udp_table udp_table __read_mostly; EXPORT_SYMBOL(udp_table); @@ -119,8 +123,10 @@ EXPORT_SYMBOL(udp_table); long sysctl_udp_mem[3] __read_mostly; EXPORT_SYMBOL(sysctl_udp_mem); -atomic_long_t udp_memory_allocated; +atomic_long_t udp_memory_allocated ____cacheline_aligned_in_smp; 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) @@ -240,7 +246,7 @@ int udp_lib_get_port(struct sock *sk, unsigned short snum, inet_get_local_port_range(net, &low, &high); remaining = (high - low) + 1; - rand = prandom_u32(); + rand = get_random_u32(); first = reciprocal_scale(rand, remaining) + low; /* * force rand to be an odd multiple of UDP_HTABLE_SIZE @@ -386,7 +392,8 @@ static int compute_score(struct sock *sk, struct net *net, dif, sdif); if (!dev_match) return -1; - score += 4; + if (sk->sk_bound_dev_if) + score += 4; if (READ_ONCE(sk->sk_incoming_cpu) == raw_smp_processor_id()) score++; @@ -405,6 +412,22 @@ static u32 udp_ehashfn(const struct net *net, const __be32 laddr, udp_ehash_secret + net_hash_mix(net)); } +static struct sock *lookup_reuseport(struct net *net, struct sock *sk, + struct sk_buff *skb, + __be32 saddr, __be16 sport, + __be32 daddr, unsigned short hnum) +{ + struct sock *reuse_sk = NULL; + u32 hash; + + if (sk->sk_reuseport && sk->sk_state != TCP_ESTABLISHED) { + hash = udp_ehashfn(net, daddr, hnum, saddr, sport); + reuse_sk = reuseport_select_sock(sk, hash, skb, + sizeof(struct udphdr)); + } + return reuse_sk; +} + /* called with rcu_read_lock() */ static struct sock *udp4_lib_lookup2(struct net *net, __be32 saddr, __be16 sport, @@ -415,7 +438,6 @@ static struct sock *udp4_lib_lookup2(struct net *net, { struct sock *sk, *result; int score, badness; - u32 hash = 0; result = NULL; badness = 0; @@ -423,22 +445,42 @@ static struct sock *udp4_lib_lookup2(struct net *net, score = compute_score(sk, net, saddr, sport, daddr, hnum, dif, sdif); if (score > badness) { - if (sk->sk_reuseport && - sk->sk_state != TCP_ESTABLISHED) { - hash = udp_ehashfn(net, daddr, hnum, - saddr, sport); - result = reuseport_select_sock(sk, hash, skb, - sizeof(struct udphdr)); - if (result && !reuseport_has_conns(sk, false)) - return result; - } + result = lookup_reuseport(net, sk, skb, + saddr, sport, daddr, hnum); + /* Fall back to scoring if group has connections */ + if (result && !reuseport_has_conns(sk)) + return result; + + result = result ? : sk; badness = score; - result = sk; } } return result; } +static struct sock *udp4_lookup_run_bpf(struct net *net, + struct udp_table *udptable, + struct sk_buff *skb, + __be32 saddr, __be16 sport, + __be32 daddr, u16 hnum, const int dif) +{ + struct sock *sk, *reuse_sk; + bool no_reuseport; + + if (udptable != &udp_table) + return NULL; /* only UDP is supported */ + + no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport, + daddr, hnum, dif, &sk); + if (no_reuseport || IS_ERR_OR_NULL(sk)) + return sk; + + reuse_sk = lookup_reuseport(net, sk, skb, saddr, sport, daddr, hnum); + if (reuse_sk) + sk = reuse_sk; + return sk; +} + /* UDP is nearly always wildcards out the wazoo, it makes no sense to try * harder than this. -DaveM */ @@ -446,27 +488,45 @@ struct sock *__udp4_lib_lookup(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 *result; unsigned short hnum = ntohs(dport); unsigned int hash2, slot2; struct udp_hslot *hslot2; + struct sock *result, *sk; hash2 = ipv4_portaddr_hash(net, daddr, hnum); slot2 = hash2 & udptable->mask; hslot2 = &udptable->hash2[slot2]; + /* Lookup connected or non-wildcard socket */ result = udp4_lib_lookup2(net, saddr, sport, daddr, hnum, dif, sdif, hslot2, skb); - if (!result) { - hash2 = ipv4_portaddr_hash(net, htonl(INADDR_ANY), hnum); - slot2 = hash2 & udptable->mask; - hslot2 = &udptable->hash2[slot2]; - - result = udp4_lib_lookup2(net, saddr, sport, - htonl(INADDR_ANY), 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)) { + sk = udp4_lookup_run_bpf(net, udptable, skb, + saddr, sport, daddr, hnum, dif); + if (sk) { + result = sk; + goto done; + } } + + /* 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); + slot2 = hash2 & udptable->mask; + hslot2 = &udptable->hash2[slot2]; + + result = udp4_lib_lookup2(net, saddr, sport, + htonl(INADDR_ANY), hnum, dif, sdif, + hslot2, skb); +done: if (IS_ERR(result)) return NULL; return result; @@ -484,7 +544,7 @@ static inline struct sock *__udp4_lib_lookup_skb(struct sk_buff *skb, inet_sdif(skb), udptable, skb); } -struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, +struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb, __be16 sport, __be16 dport) { const struct iphdr *iph = ip_hdr(skb); @@ -493,7 +553,6 @@ struct sock *udp4_lib_lookup_skb(struct sk_buff *skb, iph->daddr, dport, inet_iif(skb), inet_sdif(skb), &udp_table, NULL); } -EXPORT_SYMBOL_GPL(udp4_lib_lookup_skb); /* Must be called under rcu_read_lock(). * Does increment socket refcount. @@ -540,6 +599,12 @@ void udp_encap_enable(void) } 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. */ @@ -583,10 +648,12 @@ 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 sock *sk; + struct udp_sock *up; network_offset = skb_network_offset(skb); transport_offset = skb_transport_offset(skb); @@ -597,18 +664,28 @@ static struct sock *__udp4_lib_err_encap(struct net *net, /* 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) { - int (*lookup)(struct sock *sk, struct sk_buff *skb); - struct udp_sock *up = udp_sk(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)); @@ -645,15 +722,16 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) sk = __udp4_lib_lookup(net, iph->daddr, uh->dest, iph->saddr, uh->source, skb->dev->ifindex, inet_sdif(skb), udptable, NULL); - if (!sk) { + + if (!sk || udp_sk(sk)->encap_type) { /* No socket for error: try tunnels before discarding */ - sk = ERR_PTR(-ENOENT); if (static_branch_unlikely(&udp_encap_needed_key)) { - sk = __udp4_lib_err_encap(net, iph, uh, udptable, skb, + 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); @@ -705,6 +783,8 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) */ 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, iph->ihl << 2); goto out; } if (!inet->recverr) { @@ -714,7 +794,7 @@ int __udp4_lib_err(struct sk_buff *skb, u32 info, struct udp_table *udptable) 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: return 0; } @@ -817,7 +897,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); struct udphdr *uh; - int err = 0; + int err; int is_udplite = IS_UDPLITE(sk); int offset = skb_transport_offset(skb); int len = skb->len - offset; @@ -841,7 +921,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, kfree_skb(skb); return -EINVAL; } - if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) { + if (datalen > cork->gso_size * UDP_MAX_SEGMENTS) { kfree_skb(skb); return -EINVAL; } @@ -978,7 +1058,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) __be16 dport; u8 tos; int err, is_udplite = IS_UDPLITE(sk); - int corkreq = up->corkflag || msg->msg_flags&MSG_MORE; + int corkreq = READ_ONCE(up->corkflag) || msg->msg_flags&MSG_MORE; int (*getfrag)(void *, char *, int, int, int, struct sk_buff *); struct sk_buff *skb; struct ip_options_data opt_copy; @@ -1040,7 +1120,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) } ipcm_init_sk(&ipc, inet); - ipc.gso_size = up->gso_size; + ipc.gso_size = READ_ONCE(up->gso_size); if (msg->msg_controllen) { err = udp_cmsg_send(sk, msg, &ipc.gso_size); @@ -1068,7 +1148,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) rcu_read_unlock(); } - if (cgroup_bpf_enabled && !connected) { + if (cgroup_bpf_enabled(CGROUP_UDP4_SENDMSG) && !connected) { err = BPF_CGROUP_RUN_PROG_UDP4_SENDMSG_LOCK(sk, (struct sockaddr *)usin, &ipc.addr); if (err) @@ -1113,7 +1193,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.oif = inet->uc_index; } else if (ipv4_is_lbcast(daddr) && inet->uc_index) { /* oif is set, packet is to local broadcast and - * and uc_index is set. oif is most likely set + * 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. @@ -1140,7 +1220,7 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) faddr, saddr, dport, inet->inet_sport, sk->sk_uid); - security_sk_classify_flow(sk, flowi4_to_flowi(fl4)); + 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); @@ -1286,7 +1366,7 @@ int udp_sendpage(struct sock *sk, struct page *page, int offset, } up->len += size; - if (!(up->corkflag || (flags&MSG_MORE))) + if (!(READ_ONCE(up->corkflag) || (flags&MSG_MORE))) ret = udp_push_pending_frames(sk); if (!ret) ret = size; @@ -1385,11 +1465,11 @@ static void udp_rmem_release(struct sock *sk, int size, int partial, sk->sk_forward_alloc += size; - amt = (sk->sk_forward_alloc - partial) & ~(SK_MEM_QUANTUM - 1); + amt = (sk->sk_forward_alloc - partial) & ~(PAGE_SIZE - 1); sk->sk_forward_alloc -= amt; if (amt) - __sk_mem_reduce_allocated(sk, amt >> SK_MEM_QUANTUM_SHIFT); + __sk_mem_reduce_allocated(sk, amt >> PAGE_SHIFT); atomic_sub(size, &sk->sk_rmem_alloc); @@ -1482,7 +1562,7 @@ int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb) spin_lock(&list->lock); if (size >= sk->sk_forward_alloc) { amt = sk_mem_pages(size); - delta = amt << SK_MEM_QUANTUM_SHIFT; + delta = amt << PAGE_SHIFT; if (!__sk_mem_raise_allocated(sk, delta, amt, SK_MEM_RECV)) { err = -ENOBUFS; spin_unlock(&list->lock); @@ -1518,7 +1598,7 @@ drop: } EXPORT_SYMBOL_GPL(__udp_enqueue_schedule_skb); -void udp_destruct_sock(struct sock *sk) +void udp_destruct_common(struct sock *sk) { /* reclaim completely the forward allocated memory */ struct udp_sock *up = udp_sk(sk); @@ -1531,18 +1611,22 @@ void udp_destruct_sock(struct sock *sk) kfree_skb(skb); } udp_rmem_release(sk, total, 0, true); +} +EXPORT_SYMBOL_GPL(udp_destruct_common); +static void udp_destruct_sock(struct sock *sk) +{ + udp_destruct_common(sk); inet_sock_destruct(sk); } -EXPORT_SYMBOL_GPL(udp_destruct_sock); int udp_init_sock(struct sock *sk) { skb_queue_head_init(&udp_sk(sk)->reader_queue); sk->sk_destruct = udp_destruct_sock; + set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags); return 0; } -EXPORT_SYMBOL_GPL(udp_init_sock); void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len) { @@ -1650,7 +1734,7 @@ int udp_ioctl(struct sock *sk, int cmd, unsigned long arg) EXPORT_SYMBOL(udp_ioctl); struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, - int noblock, int *off, int *err) + int *off, int *err) { struct sk_buff_head *sk_queue = &sk->sk_receive_queue; struct sk_buff_head *queue; @@ -1659,7 +1743,6 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int error; queue = &udp_sk(sk)->reader_queue; - flags |= noblock ? MSG_DONTWAIT : 0; timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); do { struct sk_buff *skb; @@ -1671,10 +1754,11 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, error = -EAGAIN; do { spin_lock_bh(&queue->lock); - skb = __skb_try_recv_from_queue(sk, queue, flags, - udp_skb_destructor, - off, err, &last); + skb = __skb_try_recv_from_queue(sk, queue, flags, off, + err, &last); if (skb) { + if (!(flags & MSG_PEEK)) + udp_skb_destructor(sk, skb); spin_unlock_bh(&queue->lock); return skb; } @@ -1692,9 +1776,10 @@ struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, spin_lock(&sk_queue->lock); skb_queue_splice_tail_init(sk_queue, queue); - skb = __skb_try_recv_from_queue(sk, queue, flags, - udp_skb_dtor_locked, - off, err, &last); + skb = __skb_try_recv_from_queue(sk, 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) @@ -1718,13 +1803,42 @@ busy_check: } EXPORT_SYMBOL(__skb_recv_udp); +int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor) +{ + struct sk_buff *skb; + int err, copied; + +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); + atomic_inc(&sk->sk_drops); + kfree_skb(skb); + goto try_again; + } + + WARN_ON_ONCE(!skb_set_owner_sk_safe(skb, sk)); + copied = recv_actor(sk, skb); + kfree_skb(skb); + + return copied; +} +EXPORT_SYMBOL(udp_read_skb); + /* * This should be easy, if there is something there we * return it, otherwise we block. */ -int udp_recvmsg(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); DECLARE_SOCKADDR(struct sockaddr_in *, sin, msg->msg_name); @@ -1739,7 +1853,7 @@ int udp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int noblock, try_again: off = sk_peek_offset(sk, flags); - skb = __skb_recv_udp(sk, flags, noblock, &off, &err); + skb = __skb_recv_udp(sk, flags, &off, &err); if (!skb) return err; @@ -1790,7 +1904,7 @@ try_again: 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) { @@ -1800,9 +1914,8 @@ try_again: memset(sin->sin_zero, 0, sizeof(sin->sin_zero)); *addr_len = sizeof(*sin); - if (cgroup_bpf_enabled) - BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, - (struct sockaddr *)sin); + BPF_CGROUP_RUN_PROG_UDP4_RECVMSG_LOCK(sk, + (struct sockaddr *)sin); } if (udp_sk(sk)->gro_enabled) @@ -1974,13 +2087,20 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *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) + 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); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); trace_udp_fail_queue_rcv_skb(rc, sk); return -1; } @@ -1998,14 +2118,17 @@ static 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) { + int drop_reason = SKB_DROP_REASON_NOT_SPECIFIED; struct udp_sock *up = udp_sk(sk); 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_ct(skb); if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { @@ -2046,7 +2169,7 @@ static int udp_queue_rcv_one_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 ((up->pcflag & UDPLITE_RECV_CC) && UDP_SKB_CB(skb)->partial_cov) { /* * MIB statistics other than incrementing the error count are @@ -2082,8 +2205,10 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) udp_lib_checksum_complete(skb)) goto csum_error; - if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) + if (sk_filter_trim_cap(sk, skb, sizeof(struct udphdr))) { + drop_reason = SKB_DROP_REASON_SOCKET_FILTER; goto drop; + } udp_csum_pull_header(skb); @@ -2091,11 +2216,12 @@ static int udp_queue_rcv_one_skb(struct sock *sk, struct sk_buff *skb) return __udp_queue_rcv_skb(sk, skb); csum_error: + drop_reason = SKB_DROP_REASON_UDP_CSUM; __UDP_INC_STATS(sock_net(sk), UDP_MIB_CSUMERRORS, is_udplite); drop: __UDP_INC_STATS(sock_net(sk), UDP_MIB_INERRORS, is_udplite); atomic_inc(&sk->sk_drops); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return -1; } @@ -2107,14 +2233,16 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (likely(!udp_unexpected_gso(sk, skb))) return udp_queue_rcv_one_skb(sk, skb); - BUILD_BUG_ON(sizeof(struct udp_skb_cb) > SKB_SGO_CB_OFFSET); + 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); + ip_protocol_deliver_rcu(dev_net(skb->dev), skb, ret); } return 0; } @@ -2127,7 +2255,7 @@ bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst) struct dst_entry *old; if (dst_hold_safe(dst)) { - old = xchg(&sk->sk_rx_dst, dst); + old = xchg((__force struct dst_entry **)&sk->sk_rx_dst, dst); dst_release(old); return old != dst; } @@ -2286,6 +2414,10 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, 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. @@ -2311,16 +2443,17 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp4_csum_init(skb, uh, proto)) goto csum_error; - sk = skb_steal_sock(skb); + sk = skb_steal_sock(skb, &refcounted); if (sk) { struct dst_entry *dst = skb_dst(skb); int ret; - if (unlikely(sk->sk_rx_dst != dst)) + if (unlikely(rcu_dereference(sk->sk_rx_dst) != dst)) udp_sk_rx_dst_set(sk, dst); ret = udp_unicast_rcv_skb(sk, skb, uh); - sock_put(sk); + if (refcounted) + sock_put(sk); return ret; } @@ -2340,6 +2473,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, if (udp_lib_checksum_complete(skb)) goto csum_error; + 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); @@ -2347,10 +2481,11 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable, * Hmm. We got an UDP packet to a port to which we * don't wanna listen. Ignore it. */ - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; short_packet: + 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), @@ -2363,6 +2498,7 @@ csum_error: * RFC1122: OK. Discards the bad packet silently (as far as * the network is concerned, anyway) as per 4.1.3.4 (MUST). */ + 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), @@ -2370,7 +2506,7 @@ csum_error: __UDP_INC_STATS(net, UDP_MIB_CSUMERRORS, proto == IPPROTO_UDPLITE); drop: __UDP_INC_STATS(net, UDP_MIB_INERRORS, proto == IPPROTO_UDPLITE); - kfree_skb(skb); + kfree_skb_reason(skb, drop_reason); return 0; } @@ -2422,8 +2558,7 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net, struct sock *sk; udp_portaddr_for_each_entry_rcu(sk, &hslot2->head) { - if (INET_MATCH(sk, net, acookie, rmt_addr, - loc_addr, ports, dif, sdif)) + if (inet_match(net, sk, acookie, ports, dif, sdif)) return sk; /* Only check first socket in chain */ break; @@ -2474,7 +2609,7 @@ int udp_v4_early_demux(struct sk_buff *skb) skb->sk = sk; skb->destructor = sock_efree; - dst = READ_ONCE(sk->sk_rx_dst); + dst = rcu_dereference(sk->sk_rx_dst); if (dst) dst = dst_check(dst, 0); @@ -2492,7 +2627,8 @@ int udp_v4_early_demux(struct sk_buff *skb) */ if (!inet_sk(sk)->inet_daddr && in_dev) return ip_mc_validate_source(skb, iph->daddr, - iph->saddr, iph->tos, + iph->saddr, + iph->tos & IPTOS_RT_MASK, skb->dev, in_dev, &itag); } return 0; @@ -2507,6 +2643,9 @@ 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_branch_unlikely(&udp_encap_needed_key)) { @@ -2525,7 +2664,7 @@ void udp_destroy_sock(struct sock *sk) * 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); @@ -2536,7 +2675,7 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, 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; @@ -2544,9 +2683,9 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: if (val != 0) { - up->corkflag = 1; + WRITE_ONCE(up->corkflag, 1); } else { - up->corkflag = 0; + WRITE_ONCE(up->corkflag, 0); lock_sock(sk); push_pending_frames(sk); release_sock(sk); @@ -2559,9 +2698,14 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, #ifdef CONFIG_XFRM case UDP_ENCAP_ESPINUDP: case UDP_ENCAP_ESPINUDP_NON_IKE: - up->encap_rcv = xfrm4_udp_encap_rcv; +#if IS_ENABLED(CONFIG_IPV6) + if (sk->sk_family == AF_INET6) + up->encap_rcv = ipv6_stub->xfrm6_udp_encap_rcv; + else +#endif + up->encap_rcv = xfrm4_udp_encap_rcv; #endif - /* FALLTHROUGH */ + fallthrough; case UDP_ENCAP_L2TPINUDP: up->encap_type = val; lock_sock(sk); @@ -2585,14 +2729,17 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, case UDP_SEGMENT: if (val < 0 || val > USHRT_MAX) return -EINVAL; - up->gso_size = val; + WRITE_ONCE(up->gso_size, val); break; case UDP_GRO: lock_sock(sk); + + /* when enabling GRO, accept the related GSO packet type */ if (valbool) udp_tunnel_encap_enable(sk->sk_socket); up->gro_enabled = valbool; + up->accept_udp_l4 = valbool; release_sock(sk); break; @@ -2635,26 +2782,16 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, } EXPORT_SYMBOL(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, + 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) { @@ -2671,7 +2808,7 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, switch (optname) { case UDP_CORK: - val = up->corkflag; + val = READ_ONCE(up->corkflag); break; case UDP_ENCAP: @@ -2687,7 +2824,11 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, break; case UDP_SEGMENT: - val = up->gso_size; + val = READ_ONCE(up->gso_size); + break; + + case UDP_GRO: + val = up->gro_enabled; break; /* The following two cannot be changed on UDP sockets, the return is @@ -2720,20 +2861,11 @@ 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 @@ -2755,6 +2887,9 @@ __poll_t udp_poll(struct file *file, struct socket *sock, poll_table *wait) !(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; } @@ -2764,10 +2899,17 @@ int udp_abort(struct sock *sk, int err) { 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->sk_error_report(sk); + sk_error_report(sk); __udp_disconnect(sk, 0); +out: release_sock(sk); return 0; @@ -2794,16 +2936,18 @@ struct proto udp_prot = { .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 .memory_allocated = &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 = &udp_table, -#ifdef CONFIG_COMPAT - .compat_setsockopt = compat_udp_setsockopt, - .compat_getsockopt = compat_udp_getsockopt, -#endif .diag_destroy = udp_abort, }; EXPORT_SYMBOL(udp_prot); @@ -2814,10 +2958,15 @@ EXPORT_SYMBOL(udp_prot); static struct sock *udp_get_first(struct seq_file *seq, int start) { struct sock *sk; - struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); + struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + if (state->bpf_seq_afinfo) + afinfo = state->bpf_seq_afinfo; + else + afinfo = pde_data(file_inode(seq->file)); + for (state->bucket = start; state->bucket <= afinfo->udp_table->mask; ++state->bucket) { struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket]; @@ -2829,7 +2978,8 @@ static struct sock *udp_get_first(struct seq_file *seq, int start) sk_for_each(sk, &hslot->head) { if (!net_eq(sock_net(sk), net)) continue; - if (sk->sk_family == afinfo->family) + if (afinfo->family == AF_UNSPEC || + sk->sk_family == afinfo->family) goto found; } spin_unlock_bh(&hslot->lock); @@ -2841,13 +2991,20 @@ found: static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk) { - struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); + struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; struct net *net = seq_file_net(seq); + if (state->bpf_seq_afinfo) + afinfo = state->bpf_seq_afinfo; + else + afinfo = pde_data(file_inode(seq->file)); + do { sk = sk_next(sk); - } while (sk && (!net_eq(sock_net(sk), net) || sk->sk_family != afinfo->family)); + } while (sk && (!net_eq(sock_net(sk), net) || + (afinfo->family != AF_UNSPEC && + sk->sk_family != afinfo->family))); if (!sk) { if (state->bucket <= afinfo->udp_table->mask) @@ -2892,9 +3049,14 @@ EXPORT_SYMBOL(udp_seq_next); void udp_seq_stop(struct seq_file *seq, void *v) { - struct udp_seq_afinfo *afinfo = PDE_DATA(file_inode(seq->file)); + struct udp_seq_afinfo *afinfo; struct udp_iter_state *state = seq->private; + if (state->bpf_seq_afinfo) + afinfo = state->bpf_seq_afinfo; + else + afinfo = pde_data(file_inode(seq->file)); + if (state->bucket <= afinfo->udp_table->mask) spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock); } @@ -2926,7 +3088,7 @@ int udp4_seq_show(struct seq_file *seq, void *v) { seq_setwidth(seq, 127); if (v == SEQ_START_TOKEN) - seq_puts(seq, " 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 { @@ -2938,6 +3100,67 @@ int udp4_seq_show(struct seq_file *seq, void *v) return 0; } +#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); +}; + +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; + + if (v == SEQ_START_TOKEN) + return 0; + + uid = from_kuid_munged(seq_user_ns(seq), sock_i_uid(sk)); + meta.seq = seq; + prog = bpf_iter_get_info(&meta, false); + return udp_prog_seq_show(prog, &meta, v, uid, state->bucket); +} + +static void bpf_iter_udp_seq_stop(struct seq_file *seq, void *v) +{ + 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); + } + + udp_seq_stop(seq, v); +} + +static const struct seq_operations bpf_iter_udp_seq_ops = { + .start = udp_seq_start, + .next = udp_seq_next, + .stop = bpf_iter_udp_seq_stop, + .show = bpf_iter_udp_seq_show, +}; +#endif + const struct seq_operations udp_seq_ops = { .start = udp_seq_start, .next = udp_seq_next, @@ -3035,19 +3258,15 @@ u32 udp_flow_hashrnd(void) } EXPORT_SYMBOL(udp_flow_hashrnd); -static void __udp_sysctl_init(struct net *net) +static int __net_init udp_sysctl_init(struct net *net) { - net->ipv4.sysctl_udp_rmem_min = SK_MEM_QUANTUM; - net->ipv4.sysctl_udp_wmem_min = SK_MEM_QUANTUM; + net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE; + net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE; #ifdef CONFIG_NET_L3_MASTER_DEV net->ipv4.sysctl_udp_l3mdev_accept = 0; #endif -} -static int __net_init udp_sysctl_init(struct net *net) -{ - __udp_sysctl_init(net); return 0; } @@ -3055,6 +3274,62 @@ static struct pernet_operations __net_initdata udp_sysctl_ops = { .init = udp_sysctl_init, }; +#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_init_udp(void *priv_data, struct bpf_iter_aux_info *aux) +{ + struct udp_iter_state *st = priv_data; + struct udp_seq_afinfo *afinfo; + int ret; + + afinfo = kmalloc(sizeof(*afinfo), GFP_USER | __GFP_NOWARN); + if (!afinfo) + return -ENOMEM; + + afinfo->family = AF_UNSPEC; + afinfo->udp_table = &udp_table; + st->bpf_seq_afinfo = afinfo; + ret = bpf_iter_init_seq_net(priv_data, aux); + if (ret) + kfree(afinfo); + return ret; +} + +static void bpf_iter_fini_udp(void *priv_data) +{ + struct udp_iter_state *st = priv_data; + + kfree(st->bpf_seq_afinfo); + bpf_iter_fini_seq_net(priv_data); +} + +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 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 }, + }, + .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; @@ -3067,8 +3342,6 @@ void __init udp_init(void) sysctl_udp_mem[1] = limit; sysctl_udp_mem[2] = sysctl_udp_mem[0] * 2; - __udp_sysctl_init(&init_net); - /* 16 spinlocks per cpu */ udp_busylocks_log = ilog2(nr_cpu_ids) + 4; udp_busylocks = kmalloc(sizeof(spinlock_t) << udp_busylocks_log, @@ -3080,4 +3353,8 @@ void __init udp_init(void) 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 } |