1 files changed, 194 insertions, 60 deletions

diff --git a/include/net/udp.h b/include/net/udp.h
index 295d52a73598..a772510b2aa5 100644
--- a/include/net/udp.h
+++ b/include/net/udp.h
@@ -21,6 +21,7 @@
 #include <linux/list.h>
 #include <linux/bug.h>
 #include <net/inet_sock.h>
+#include <net/gso.h>
 #include <net/sock.h>
 #include <net/snmp.h>
 #include <net/ip.h>
@@ -49,39 +50,68 @@ struct udp_skb_cb {
 #define UDP_SKB_CB(__skb)	((struct udp_skb_cb *)((__skb)->cb))
 
 /**
- *	struct udp_hslot - UDP hash slot
+ *	struct udp_hslot - UDP hash slot used by udp_table.hash/hash4
  *
  *	@head:	head of list of sockets
+ *	@nulls_head:	head of list of sockets, only used by hash4
  *	@count:	number of sockets in 'head' list
  *	@lock:	spinlock protecting changes to head/count
  */
 struct udp_hslot {
-	struct hlist_head	head;
+	union {
+		struct hlist_head	head;
+		/* hash4 uses hlist_nulls to avoid moving wrongly onto another
+		 * hlist, because rehash() can happen with lookup().
+		 */
+		struct hlist_nulls_head	nulls_head;
+	};
 	int			count;
 	spinlock_t		lock;
-} __attribute__((aligned(2 * sizeof(long))));
+} __aligned(2 * sizeof(long));
+
+/**
+ *	struct udp_hslot_main - UDP hash slot used by udp_table.hash2
+ *
+ *	@hslot:	basic hash slot
+ *	@hash4_cnt: number of sockets in hslot4 of the same
+ *		    (local port, local address)
+ */
+struct udp_hslot_main {
+	struct udp_hslot	hslot; /* must be the first member */
+#if !IS_ENABLED(CONFIG_BASE_SMALL)
+	u32			hash4_cnt;
+#endif
+} __aligned(2 * sizeof(long));
+#define UDP_HSLOT_MAIN(__hslot) ((struct udp_hslot_main *)(__hslot))
 
 /**
  *	struct udp_table - UDP table
  *
  *	@hash:	hash table, sockets are hashed on (local port)
  *	@hash2:	hash table, sockets are hashed on (local port, local address)
+ *	@hash4:	hash table, connected sockets are hashed on
+ *		(local port, local address, remote port, remote address)
  *	@mask:	number of slots in hash tables, minus 1
  *	@log:	log2(number of slots in hash table)
  */
 struct udp_table {
 	struct udp_hslot	*hash;
-	struct udp_hslot	*hash2;
+	struct udp_hslot_main	*hash2;
+#if !IS_ENABLED(CONFIG_BASE_SMALL)
+	struct udp_hslot	*hash4;
+#endif
 	unsigned int		mask;
 	unsigned int		log;
 };
 extern struct udp_table udp_table;
 void udp_table_init(struct udp_table *, const char *);
 static inline struct udp_hslot *udp_hashslot(struct udp_table *table,
-					     struct net *net, unsigned int num)
+					     const struct net *net,
+					     unsigned int num)
 {
 	return &table->hash[udp_hashfn(net, num, table->mask)];
 }
+
 /*
  * For secondary hash, net_hash_mix() is performed before calling
  * udp_hashslot2(), this explains difference with udp_hashslot()
@@ -89,12 +119,94 @@ static inline struct udp_hslot *udp_hashslot(struct udp_table *table,
 static inline struct udp_hslot *udp_hashslot2(struct udp_table *table,
 					      unsigned int hash)
 {
-	return &table->hash2[hash & table->mask];
+	return &table->hash2[hash & table->mask].hslot;
+}
+
+#if IS_ENABLED(CONFIG_BASE_SMALL)
+static inline void udp_table_hash4_init(struct udp_table *table)
+{
+}
+
+static inline struct udp_hslot *udp_hashslot4(struct udp_table *table,
+					      unsigned int hash)
+{
+	BUILD_BUG();
+	return NULL;
+}
+
+static inline bool udp_hashed4(const struct sock *sk)
+{
+	return false;
 }
 
+static inline unsigned int udp_hash4_slot_size(void)
+{
+	return 0;
+}
+
+static inline bool udp_has_hash4(const struct udp_hslot *hslot2)
+{
+	return false;
+}
+
+static inline void udp_hash4_inc(struct udp_hslot *hslot2)
+{
+}
+
+static inline void udp_hash4_dec(struct udp_hslot *hslot2)
+{
+}
+#else /* !CONFIG_BASE_SMALL */
+
+/* Must be called with table->hash2 initialized */
+static inline void udp_table_hash4_init(struct udp_table *table)
+{
+	table->hash4 = (void *)(table->hash2 + (table->mask + 1));
+	for (int i = 0; i <= table->mask; i++) {
+		table->hash2[i].hash4_cnt = 0;
+
+		INIT_HLIST_NULLS_HEAD(&table->hash4[i].nulls_head, i);
+		table->hash4[i].count = 0;
+		spin_lock_init(&table->hash4[i].lock);
+	}
+}
+
+static inline struct udp_hslot *udp_hashslot4(struct udp_table *table,
+					      unsigned int hash)
+{
+	return &table->hash4[hash & table->mask];
+}
+
+static inline bool udp_hashed4(const struct sock *sk)
+{
+	return !hlist_nulls_unhashed(&udp_sk(sk)->udp_lrpa_node);
+}
+
+static inline unsigned int udp_hash4_slot_size(void)
+{
+	return sizeof(struct udp_hslot);
+}
+
+static inline bool udp_has_hash4(const struct udp_hslot *hslot2)
+{
+	return UDP_HSLOT_MAIN(hslot2)->hash4_cnt;
+}
+
+static inline void udp_hash4_inc(struct udp_hslot *hslot2)
+{
+	UDP_HSLOT_MAIN(hslot2)->hash4_cnt++;
+}
+
+static inline void udp_hash4_dec(struct udp_hslot *hslot2)
+{
+	UDP_HSLOT_MAIN(hslot2)->hash4_cnt--;
+}
+#endif /* CONFIG_BASE_SMALL */
+
 extern struct proto udp_prot;
 
 extern atomic_long_t udp_memory_allocated;
+DECLARE_PER_CPU(int, udp_memory_per_cpu_fw_alloc);
 
 /* sysctl variables for udp */
 extern long sysctl_udp_mem[3];
@@ -164,34 +276,23 @@ static inline void udp_csum_pull_header(struct sk_buff *skb)
 	UDP_SKB_CB(skb)->cscov -= sizeof(struct udphdr);
 }
 
-typedef struct sock *(*udp_lookup_t)(struct sk_buff *skb, __be16 sport,
+typedef struct sock *(*udp_lookup_t)(const struct sk_buff *skb, __be16 sport,
 				     __be16 dport);
 
-INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
-							   struct sk_buff *));
-INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
-INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp6_gro_receive(struct list_head *,
-							   struct sk_buff *));
-INDIRECT_CALLABLE_DECLARE(int udp6_gro_complete(struct sk_buff *, int));
-struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
-				struct udphdr *uh, struct sock *sk);
-int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
+void udp_v6_early_demux(struct sk_buff *skb);
+INDIRECT_CALLABLE_DECLARE(int udpv6_rcv(struct sk_buff *));
 
 struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb,
-				  netdev_features_t features);
+				  netdev_features_t features, bool is_ipv6);
 
-static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
+static inline void udp_lib_init_sock(struct sock *sk)
 {
-	struct udphdr *uh;
-	unsigned int hlen, off;
+	struct udp_sock *up = udp_sk(sk);
 
-	off  = skb_gro_offset(skb);
-	hlen = off + sizeof(*uh);
-	uh   = skb_gro_header_fast(skb, off);
-	if (skb_gro_header_hard(skb, hlen))
-		uh = skb_gro_header_slow(skb, hlen, off);
-
-	return uh;
+	skb_queue_head_init(&up->reader_queue);
+	INIT_HLIST_NODE(&up->tunnel_list);
+	up->forward_threshold = sk->sk_rcvbuf >> 2;
+	set_bit(SOCK_CUSTOM_SOCKOPT, &sk->sk_socket->flags);
 }
 
 /* hash routines shared between UDPv4/6 and UDP-Litev4/6 */
@@ -202,13 +303,29 @@ static inline int udp_lib_hash(struct sock *sk)
 }
 
 void udp_lib_unhash(struct sock *sk);
-void udp_lib_rehash(struct sock *sk, u16 new_hash);
+void udp_lib_rehash(struct sock *sk, u16 new_hash, u16 new_hash4);
+u32 udp_ehashfn(const struct net *net, const __be32 laddr, const __u16 lport,
+		const __be32 faddr, const __be16 fport);
 
 static inline void udp_lib_close(struct sock *sk, long timeout)
 {
 	sk_common_release(sk);
 }
 
+/* hash4 routines shared between UDPv4/6 */
+#if IS_ENABLED(CONFIG_BASE_SMALL)
+static inline void udp_lib_hash4(struct sock *sk, u16 hash)
+{
+}
+
+static inline void udp4_hash4(struct sock *sk)
+{
+}
+#else /* !CONFIG_BASE_SMALL */
+void udp_lib_hash4(struct sock *sk, u16 hash);
+void udp4_hash4(struct sock *sk);
+#endif /* CONFIG_BASE_SMALL */
+
 int udp_lib_get_port(struct sock *sk, unsigned short snum,
 		     unsigned int hash2_nulladdr);
 
@@ -241,7 +358,7 @@ static inline __be16 udp_flow_src_port(struct net *net, struct sk_buff *skb,
 	}
 
 	/* Since this is being sent on the wire obfuscate hash a bit
-	 * to minimize possbility that any useful information to an
+	 * to minimize possibility that any useful information to an
 	 * attacker is leaked. Only upper 16 bits are relevant in the
 	 * computation for 16 bit port value.
 	 */
@@ -255,11 +372,11 @@ static inline int udp_rqueue_get(struct sock *sk)
 	return sk_rmem_alloc_get(sk) - READ_ONCE(udp_sk(sk)->forward_deficit);
 }
 
-static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
+static inline bool udp_sk_bound_dev_eq(const struct net *net, int bound_dev_if,
 				       int dif, int sdif)
 {
 #if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
-	return inet_bound_dev_eq(!!net->ipv4.sysctl_udp_l3mdev_accept,
+	return inet_bound_dev_eq(!!READ_ONCE(net->ipv4.sysctl_udp_l3mdev_accept),
 				 bound_dev_if, dif, sdif);
 #else
 	return inet_bound_dev_eq(true, bound_dev_if, dif, sdif);
@@ -267,34 +384,32 @@ static inline bool udp_sk_bound_dev_eq(struct net *net, int bound_dev_if,
 }
 
 /* net/ipv4/udp.c */
-void udp_destruct_sock(struct sock *sk);
+void udp_destruct_common(struct sock *sk);
 void skb_consume_udp(struct sock *sk, struct sk_buff *skb, int len);
 int __udp_enqueue_schedule_skb(struct sock *sk, struct sk_buff *skb);
 void udp_skb_destructor(struct sock *sk, struct sk_buff *skb);
-struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags,
-			       int noblock, int *off, int *err);
+struct sk_buff *__skb_recv_udp(struct sock *sk, unsigned int flags, int *off,
+			       int *err);
 static inline struct sk_buff *skb_recv_udp(struct sock *sk, unsigned int flags,
-					   int noblock, int *err)
+					   int *err)
 {
 	int off = 0;
 
-	return __skb_recv_udp(sk, flags, noblock, &off, err);
+	return __skb_recv_udp(sk, flags, &off, err);
 }
 
 int udp_v4_early_demux(struct sk_buff *skb);
 bool udp_sk_rx_dst_set(struct sock *sk, struct dst_entry *dst);
-int udp_get_port(struct sock *sk, unsigned short snum,
-		 int (*saddr_cmp)(const struct sock *,
-				  const struct sock *));
 int udp_err(struct sk_buff *, u32);
 int udp_abort(struct sock *sk, int err);
 int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len);
+void udp_splice_eof(struct socket *sock);
 int udp_push_pending_frames(struct sock *sk);
 void udp_flush_pending_frames(struct sock *sk);
 int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size);
 void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst);
 int udp_rcv(struct sk_buff *skb);
-int udp_ioctl(struct sock *sk, int cmd, unsigned long arg);
+int udp_ioctl(struct sock *sk, int cmd, int *karg);
 int udp_init_sock(struct sock *sk);
 int udp_pre_connect(struct sock *sk, struct sockaddr *uaddr, int addr_len);
 int __udp_disconnect(struct sock *sk, int flags);
@@ -308,24 +423,26 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname,
 int udp_lib_setsockopt(struct sock *sk, int level, int optname,
 		       sockptr_t optval, unsigned int optlen,
 		       int (*push_pending_frames)(struct sock *));
-struct sock *udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+struct sock *udp4_lib_lookup(const struct net *net, __be32 saddr, __be16 sport,
 			     __be32 daddr, __be16 dport, int dif);
-struct sock *__udp4_lib_lookup(struct net *net, __be32 saddr, __be16 sport,
+struct sock *__udp4_lib_lookup(const struct net *net, __be32 saddr,
+			       __be16 sport,
 			       __be32 daddr, __be16 dport, int dif, int sdif,
 			       struct udp_table *tbl, struct sk_buff *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);
-struct sock *udp6_lib_lookup(struct net *net,
+struct sock *udp6_lib_lookup(const struct net *net,
 			     const struct in6_addr *saddr, __be16 sport,
 			     const struct in6_addr *daddr, __be16 dport,
 			     int dif);
-struct sock *__udp6_lib_lookup(struct net *net,
+struct sock *__udp6_lib_lookup(const struct net *net,
 			       const struct in6_addr *saddr, __be16 sport,
 			       const struct in6_addr *daddr, __be16 dport,
 			       int dif, int sdif, struct udp_table *tbl,
 			       struct sk_buff *skb);
-struct sock *udp6_lib_lookup_skb(struct sk_buff *skb,
+struct sock *udp6_lib_lookup_skb(const struct sk_buff *skb,
 				 __be16 sport, __be16 dport);
+int udp_read_skb(struct sock *sk, skb_read_actor_t recv_actor);
 
 /* UDP uses skb->dev_scratch to cache as much information as possible and avoid
  * possibly multiple cache miss on dequeue()
@@ -390,14 +507,7 @@ static inline bool udp_skb_is_linear(struct sk_buff *skb)
 static inline int copy_linear_skb(struct sk_buff *skb, int len, int off,
 				  struct iov_iter *to)
 {
-	int n;
-
-	n = copy_to_iter(skb->data + off, len, to);
-	if (n == len)
-		return 0;
-
-	iov_iter_revert(to, n);
-	return -EFAULT;
+	return copy_to_iter_full(skb->data + off, len, to) ? 0 : -EFAULT;
 }
 
 /*
@@ -447,7 +557,6 @@ struct udp_seq_afinfo {
 struct udp_iter_state {
 	struct seq_net_private  p;
 	int			bucket;
-	struct udp_seq_afinfo	*bpf_seq_afinfo;
 };
 
 void *udp_seq_start(struct seq_file *seq, loff_t *pos);
@@ -467,6 +576,7 @@ void udp_init(void);
 
 DECLARE_STATIC_KEY_FALSE(udp_encap_needed_key);
 void udp_encap_enable(void);
+void udp_encap_disable(void);
 #if IS_ENABLED(CONFIG_IPV6)
 DECLARE_STATIC_KEY_FALSE(udpv6_encap_needed_key);
 void udpv6_encap_enable(void);
@@ -488,8 +598,9 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	 * CHECKSUM_NONE in __udp_gso_segment. UDP GRO indeed builds partial
 	 * packets in udp_gro_complete_segment. As does UDP GSO, verified by
 	 * udp_send_skb. But when those packets are looped in dev_loopback_xmit
-	 * their ip_summed is set to CHECKSUM_UNNECESSARY. Reset in this
-	 * specific case, where PARTIAL is both correct and required.
+	 * their ip_summed CHECKSUM_NONE is changed to CHECKSUM_UNNECESSARY.
+	 * Reset in this specific case, where PARTIAL is both correct and
+	 * required.
 	 */
 	if (skb->pkt_type == PACKET_LOOPBACK)
 		skb->ip_summed = CHECKSUM_PARTIAL;
@@ -511,9 +622,32 @@ static inline struct sk_buff *udp_rcv_segment(struct sock *sk,
 	return segs;
 }
 
-#ifdef CONFIG_BPF_STREAM_PARSER
+static inline void udp_post_segment_fix_csum(struct sk_buff *skb)
+{
+	/* UDP-lite can't land here - no GRO */
+	WARN_ON_ONCE(UDP_SKB_CB(skb)->partial_cov);
+
+	/* UDP packets generated with UDP_SEGMENT and traversing:
+	 *
+	 * UDP tunnel(xmit) -> veth (segmentation) -> veth (gro) -> UDP tunnel (rx)
+	 *
+	 * can reach an UDP socket with CHECKSUM_NONE, because
+	 * __iptunnel_pull_header() converts CHECKSUM_PARTIAL into NONE.
+	 * SKB_GSO_UDP_L4 or SKB_GSO_FRAGLIST packets with no UDP tunnel will
+	 * have a valid checksum, as the GRO engine validates the UDP csum
+	 * before the aggregation and nobody strips such info in between.
+	 * Instead of adding another check in the tunnel fastpath, we can force
+	 * a valid csum after the segmentation.
+	 * Additionally fixup the UDP CB.
+	 */
+	UDP_SKB_CB(skb)->cscov = skb->len;
+	if (skb->ip_summed == CHECKSUM_NONE && !skb->csum_valid)
+		skb->csum_valid = 1;
+}
+
+#ifdef CONFIG_BPF_SYSCALL
 struct sk_psock;
-struct proto *udp_bpf_get_proto(struct sock *sk, struct sk_psock *psock);
-#endif /* BPF_STREAM_PARSER */
+int udp_bpf_update_proto(struct sock *sk, struct sk_psock *psock, bool restore);
+#endif
 
 #endif	/* _UDP_H */