1 files changed, 176 insertions, 41 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 6a320a614e54..9592fe3e444a 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -129,7 +129,12 @@ 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,
@@ -232,16 +237,16 @@ static int udp_reuseport_add_sock(struct sock *sk, struct udp_hslot *hslot)
 int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		     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(net, &low, &high);
 		remaining = (high - low) + 1;
@@ -467,7 +472,7 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
 	struct sock *sk, *reuse_sk;
 	bool no_reuseport;
 
-	if (udptable != &udp_table)
+	if (udptable != net->ipv4.udp_table)
 		return NULL; /* only UDP is supported */
 
 	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP, saddr, sport,
@@ -548,10 +553,11 @@ struct sock *udp4_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport)
 {
 	const struct iphdr *iph = ip_hdr(skb);
+	struct net *net = dev_net(skb->dev);
 
-	return __udp4_lib_lookup(dev_net(skb->dev), iph->saddr, sport,
+	return __udp4_lib_lookup(net, iph->saddr, sport,
 				 iph->daddr, dport, inet_iif(skb),
-				 inet_sdif(skb), &udp_table, NULL);
+				 inet_sdif(skb), net->ipv4.udp_table, NULL);
 }
 
 /* Must be called under rcu_read_lock().
@@ -564,7 +570,7 @@ struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
 	struct sock *sk;
 
 	sk = __udp4_lib_lookup(net, saddr, sport, daddr, dport,
-			       dif, 0, &udp_table, NULL);
+			       dif, 0, net->ipv4.udp_table, NULL);
 	if (sk && !refcount_inc_not_zero(&sk->sk_refcnt))
 		sk = NULL;
 	return sk;
@@ -784,7 +790,8 @@ 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);
+			udp_sk(sk)->encap_err_rcv(sk, skb, err, uh->dest, info,
+						  (u8 *)(uh+1));
 		goto out;
 	}
 	if (!inet->recverr) {
@@ -801,7 +808,7 @@ out:
 
 int udp_err(struct sk_buff *skb, u32 info)
 {
-	return __udp4_lib_err(skb, info, &udp_table);
+	return __udp4_lib_err(skb, info, dev_net(skb->dev)->ipv4.udp_table);
 }
 
 /*
@@ -1448,7 +1455,7 @@ static void udp_rmem_release(struct sock *sk, int size, int partial,
 	if (likely(partial)) {
 		up->forward_deficit += size;
 		size = up->forward_deficit;
-		if (size < (sk->sk_rcvbuf >> 2) &&
+		if (size < READ_ONCE(up->forward_threshold) &&
 		    !skb_queue_empty(&up->reader_queue))
 			return;
 	} else {
@@ -1622,7 +1629,7 @@ static void udp_destruct_sock(struct sock *sk)
 
 int udp_init_sock(struct sock *sk)
 {
-	skb_queue_head_init(&udp_sk(sk)->reader_queue);
+	udp_lib_init_sock(sk);
 	sk->sk_destruct = udp_destruct_sock;
 	set_bit(SOCK_SUPPORT_ZC, &sk->sk_socket->flags);
 	return 0;
@@ -1998,7 +2005,7 @@ EXPORT_SYMBOL(udp_disconnect);
 void udp_lib_unhash(struct sock *sk)
 {
 	if (sk_hashed(sk)) {
-		struct udp_table *udptable = sk->sk_prot->h.udp_table;
+		struct udp_table *udptable = udp_get_table_prot(sk);
 		struct udp_hslot *hslot, *hslot2;
 
 		hslot  = udp_hashslot(udptable, sock_net(sk),
@@ -2029,7 +2036,7 @@ EXPORT_SYMBOL(udp_lib_unhash);
 void udp_lib_rehash(struct sock *sk, u16 newhash)
 {
 	if (sk_hashed(sk)) {
-		struct udp_table *udptable = sk->sk_prot->h.udp_table;
+		struct udp_table *udptable = udp_get_table_prot(sk);
 		struct udp_hslot *hslot, *hslot2, *nhslot2;
 
 		hslot2 = udp_hashslot2(udptable, udp_sk(sk)->udp_portaddr_hash);
@@ -2518,10 +2525,14 @@ static struct sock *__udp4_lib_mcast_demux_lookup(struct net *net,
 						  __be16 rmt_port, __be32 rmt_addr,
 						  int dif, int sdif)
 {
-	struct sock *sk, *result;
+	struct udp_table *udptable = net->ipv4.udp_table;
 	unsigned short hnum = ntohs(loc_port);
-	unsigned int slot = udp_hashfn(net, hnum, udp_table.mask);
-	struct udp_hslot *hslot = &udp_table.hash[slot];
+	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)
@@ -2549,14 +2560,19 @@ static struct sock *__udp4_lib_demux_lookup(struct net *net,
 					    __be16 rmt_port, __be32 rmt_addr,
 					    int dif, int sdif)
 {
-	unsigned short hnum = ntohs(loc_port);
-	unsigned int hash2 = ipv4_portaddr_hash(net, loc_addr, hnum);
-	unsigned int slot2 = hash2 & udp_table.mask;
-	struct udp_hslot *hslot2 = &udp_table.hash2[slot2];
+	struct udp_table *udptable = net->ipv4.udp_table;
 	INET_ADDR_COOKIE(acookie, rmt_addr, loc_addr);
-	const __portpair ports = INET_COMBINED_PORTS(rmt_port, hnum);
+	unsigned short hnum = ntohs(loc_port);
+	unsigned int hash2, slot2;
+	struct udp_hslot *hslot2;
+	__portpair ports;
 	struct sock *sk;
 
+	hash2 = ipv4_portaddr_hash(net, loc_addr, hnum);
+	slot2 = hash2 & udptable->mask;
+	hslot2 = &udptable->hash2[slot2];
+	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;
@@ -2636,7 +2652,7 @@ int udp_v4_early_demux(struct sk_buff *skb)
 
 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)
@@ -2672,6 +2688,18 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 	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;
 
@@ -2785,7 +2813,7 @@ EXPORT_SYMBOL(udp_lib_setsockopt);
 int udp_setsockopt(struct sock *sk, int level, int optname, sockptr_t optval,
 		   unsigned int optlen)
 {
-	if (level == SOL_UDP  ||  level == SOL_UDPLITE)
+	if (level == SOL_UDP  ||  level == SOL_UDPLITE || level == SOL_SOCKET)
 		return udp_lib_setsockopt(sk, level, optname,
 					  optval, optlen,
 					  udp_push_pending_frames);
@@ -2947,7 +2975,7 @@ struct proto udp_prot = {
 	.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,
+	.h.udp_table		= NULL,
 	.diag_destroy		= udp_abort,
 };
 EXPORT_SYMBOL(udp_prot);
@@ -2955,21 +2983,30 @@ EXPORT_SYMBOL(udp_prot);
 /* ------------------------------------------------------------------------ */
 #ifdef CONFIG_PROC_FS
 
+static struct udp_table *udp_get_table_afinfo(struct udp_seq_afinfo *afinfo,
+					      struct net *net)
+{
+	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_seq_afinfo *afinfo;
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct udp_seq_afinfo *afinfo;
+	struct udp_table *udptable;
+	struct sock *sk;
 
 	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;
+	udptable = udp_get_table_afinfo(afinfo, net);
+
+	for (state->bucket = start; state->bucket <= udptable->mask;
 	     ++state->bucket) {
-		struct udp_hslot *hslot = &afinfo->udp_table->hash[state->bucket];
+		struct udp_hslot *hslot = &udptable->hash[state->bucket];
 
 		if (hlist_empty(&hslot->head))
 			continue;
@@ -2991,9 +3028,10 @@ found:
 
 static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
 {
-	struct udp_seq_afinfo *afinfo;
 	struct udp_iter_state *state = seq->private;
 	struct net *net = seq_file_net(seq);
+	struct udp_seq_afinfo *afinfo;
+	struct udp_table *udptable;
 
 	if (state->bpf_seq_afinfo)
 		afinfo = state->bpf_seq_afinfo;
@@ -3007,8 +3045,11 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
 			 sk->sk_family != afinfo->family)));
 
 	if (!sk) {
-		if (state->bucket <= afinfo->udp_table->mask)
-			spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock);
+		udptable = udp_get_table_afinfo(afinfo, net);
+
+		if (state->bucket <= udptable->mask)
+			spin_unlock_bh(&udptable->hash[state->bucket].lock);
+
 		return udp_get_first(seq, state->bucket + 1);
 	}
 	return sk;
@@ -3049,16 +3090,19 @@ EXPORT_SYMBOL(udp_seq_next);
 
 void udp_seq_stop(struct seq_file *seq, void *v)
 {
-	struct udp_seq_afinfo *afinfo;
 	struct udp_iter_state *state = seq->private;
+	struct udp_seq_afinfo *afinfo;
+	struct udp_table *udptable;
 
 	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);
+	udptable = udp_get_table_afinfo(afinfo, seq_file_net(seq));
+
+	if (state->bucket <= udptable->mask)
+		spin_unlock_bh(&udptable->hash[state->bucket].lock);
 }
 EXPORT_SYMBOL(udp_seq_stop);
 
@@ -3171,7 +3215,7 @@ EXPORT_SYMBOL(udp_seq_ops);
 
 static struct udp_seq_afinfo udp4_seq_afinfo = {
 	.family		= AF_INET,
-	.udp_table	= &udp_table,
+	.udp_table	= NULL,
 };
 
 static int __net_init udp4_proc_init_net(struct net *net)
@@ -3233,7 +3277,7 @@ void __init udp_table_init(struct udp_table *table, const char *name)
 					      &table->log,
 					      &table->mask,
 					      UDP_HTABLE_SIZE_MIN,
-					      64 * 1024);
+					      UDP_HTABLE_SIZE_MAX);
 
 	table->hash2 = table->hash + (table->mask + 1);
 	for (i = 0; i <= table->mask; i++) {
@@ -3258,7 +3302,7 @@ u32 udp_flow_hashrnd(void)
 }
 EXPORT_SYMBOL(udp_flow_hashrnd);
 
-static int __net_init udp_sysctl_init(struct net *net)
+static void __net_init udp_sysctl_init(struct net *net)
 {
 	net->ipv4.sysctl_udp_rmem_min = PAGE_SIZE;
 	net->ipv4.sysctl_udp_wmem_min = PAGE_SIZE;
@@ -3266,12 +3310,103 @@ static int __net_init udp_sysctl_init(struct net *net)
 #ifdef CONFIG_NET_L3_MASTER_DEV
 	net->ipv4.sysctl_udp_l3mdev_accept = 0;
 #endif
+}
+
+static struct udp_table __net_init *udp_pernet_table_alloc(unsigned int hash_entries)
+{
+	struct udp_table *udptable;
+	int i;
+
+	udptable = kmalloc(sizeof(*udptable), GFP_KERNEL);
+	if (!udptable)
+		goto out;
+
+	udptable->hash = vmalloc_huge(hash_entries * 2 * sizeof(struct udp_hslot),
+				      GFP_KERNEL_ACCOUNT);
+	if (!udptable->hash)
+		goto free_table;
+
+	udptable->hash2 = 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].head);
+		udptable->hash2[i].count = 0;
+		spin_lock_init(&udptable->hash2[i].lock);
+	}
+
+	return udptable;
+
+free_table:
+	kfree(udptable);
+out:
+	return NULL;
+}
+
+static void __net_exit udp_pernet_table_free(struct net *net)
+{
+	struct udp_table *udptable = net->ipv4.udp_table;
+
+	if (udptable == &udp_table)
+		return;
+
+	kvfree(udptable->hash);
+	kfree(udptable);
+}
+
+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)
+{
+	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_sysctl_init,
+	.init	= udp_pernet_init,
+	.exit	= udp_pernet_exit,
 };
 
 #if defined(CONFIG_BPF_SYSCALL) && defined(CONFIG_PROC_FS)
@@ -3289,7 +3424,7 @@ static int bpf_iter_init_udp(void *priv_data, struct bpf_iter_aux_info *aux)
 		return -ENOMEM;
 
 	afinfo->family = AF_UNSPEC;
-	afinfo->udp_table = &udp_table;
+	afinfo->udp_table = NULL;
 	st->bpf_seq_afinfo = afinfo;
 	ret = bpf_iter_init_seq_net(priv_data, aux);
 	if (ret)