1 files changed, 84 insertions, 77 deletions

diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c
index 23b05e28490b..6a320a614e54 100644
--- a/net/ipv4/udp.c
+++ b/net/ipv4/udp.c
@@ -74,6 +74,7 @@
 
 #define pr_fmt(fmt) "UDP: " fmt
 
+#include <linux/bpf-cgroup.h>
 #include <linux/uaccess.h>
 #include <asm/ioctls.h>
 #include <linux/memblock.h>
@@ -122,8 +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)
@@ -243,7 +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
@@ -445,7 +448,7 @@ static struct sock *udp4_lib_lookup2(struct net *net,
 			result = lookup_reuseport(net, sk, skb,
 						  saddr, sport, daddr, hnum);
 			/* Fall back to scoring if group has connections */
-			if (result && !reuseport_has_conns(sk, false))
+			if (result && !reuseport_has_conns(sk))
 				return result;
 
 			result = result ? : sk;
@@ -459,7 +462,7 @@ 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)
+					__be32 daddr, u16 hnum, const int dif)
 {
 	struct sock *sk, *reuse_sk;
 	bool no_reuseport;
@@ -467,8 +470,8 @@ static struct sock *udp4_lookup_run_bpf(struct net *net,
 	if (udptable != &udp_table)
 		return NULL; /* only UDP is supported */
 
-	no_reuseport = bpf_sk_lookup_run_v4(net, IPPROTO_UDP,
-					    saddr, sport, daddr, hnum, &sk);
+	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;
 
@@ -504,7 +507,7 @@ struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr,
 	/* Lookup redirect from BPF */
 	if (static_branch_unlikely(&bpf_sk_lookup_enabled)) {
 		sk = udp4_lookup_run_bpf(net, udptable, skb,
-					 saddr, sport, daddr, hnum);
+					 saddr, sport, daddr, hnum, dif);
 		if (sk) {
 			result = sk;
 			goto done;
@@ -780,6 +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) {
@@ -1460,11 +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);
 
@@ -1557,7 +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);
@@ -1593,7 +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);
@@ -1606,18 +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)
 {
@@ -1725,7 +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;
@@ -1734,7 +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;
@@ -1795,55 +1803,42 @@ busy_check:
 }
 EXPORT_SYMBOL(__skb_recv_udp);
 
-int udp_read_sock(struct sock *sk, read_descriptor_t *desc,
-		  sk_read_actor_t recv_actor)
+int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor)
 {
-	int copied = 0;
-
-	while (1) {
-		struct sk_buff *skb;
-		int err, used;
-
-		skb = skb_recv_udp(sk, 0, 1, &err);
-		if (!skb)
-			return err;
+	struct sk_buff *skb;
+	int err, copied;
 
-		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));
-			atomic_inc(&sk->sk_drops);
-			kfree_skb(skb);
-			continue;
-		}
+try_again:
+	skb = skb_recv_udp(sk, MSG_DONTWAIT, &err);
+	if (!skb)
+		return err;
 
-		used = recv_actor(desc, skb, 0, skb->len);
-		if (used <= 0) {
-			if (!copied)
-				copied = used;
-			kfree_skb(skb);
-			break;
-		} else if (used <= skb->len) {
-			copied += used;
-		}
+	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);
-		if (!desc->count)
-			break;
+		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_sock);
+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);
@@ -1858,7 +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;
 
@@ -1909,7 +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) {
@@ -2092,16 +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);
-		else
+			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;
 	}
@@ -2119,14 +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) {
@@ -2203,8 +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);
 
@@ -2212,11 +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;
 }
 
@@ -2250,7 +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;
 	}
@@ -2410,6 +2415,9 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 	__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.
@@ -2440,7 +2448,7 @@ int __udp4_lib_rcv(struct sk_buff *skb, struct udp_table *udptable,
 		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);
@@ -2465,6 +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);
 
@@ -2472,10 +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),
@@ -2488,6 +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),
@@ -2495,7 +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;
 }
 
@@ -2547,8 +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;
@@ -2599,7 +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);
@@ -2926,10 +2936,13 @@ 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),
@@ -2952,7 +2965,7 @@ static struct sock *udp_get_first(struct seq_file *seq, int start)
 	if (state->bpf_seq_afinfo)
 		afinfo = state->bpf_seq_afinfo;
 	else
-		afinfo = PDE_DATA(file_inode(seq->file));
+		afinfo = pde_data(file_inode(seq->file));
 
 	for (state->bucket = start; state->bucket <= afinfo->udp_table->mask;
 	     ++state->bucket) {
@@ -2985,7 +2998,7 @@ static struct sock *udp_get_next(struct seq_file *seq, struct sock *sk)
 	if (state->bpf_seq_afinfo)
 		afinfo = state->bpf_seq_afinfo;
 	else
-		afinfo = PDE_DATA(file_inode(seq->file));
+		afinfo = pde_data(file_inode(seq->file));
 
 	do {
 		sk = sk_next(sk);
@@ -3042,7 +3055,7 @@ void udp_seq_stop(struct seq_file *seq, void *v)
 	if (state->bpf_seq_afinfo)
 		afinfo = state->bpf_seq_afinfo;
 	else
-		afinfo = PDE_DATA(file_inode(seq->file));
+		afinfo = pde_data(file_inode(seq->file));
 
 	if (state->bucket <= afinfo->udp_table->mask)
 		spin_unlock_bh(&afinfo->udp_table->hash[state->bucket].lock);
@@ -3075,7 +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 {
@@ -3245,19 +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;
 }
 
@@ -3333,8 +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,