1 files changed, 119 insertions, 42 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 121ffc115c4f..c9c8b19df27c 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -178,7 +178,7 @@ struct sock_common {
 	int			skc_bound_dev_if;
 	union {
 		struct hlist_node	skc_bind_node;
-		struct hlist_nulls_node skc_portaddr_node;
+		struct hlist_node	skc_portaddr_node;
 	};
 	struct proto		*skc_prot;
 	possible_net_t		skc_net;
@@ -438,6 +438,7 @@ struct sock {
 						  struct sk_buff *skb);
 	void                    (*sk_destruct)(struct sock *sk);
 	struct sock_reuseport __rcu	*sk_reuseport_cb;
+	struct rcu_head		sk_rcu;
 };
 
 #define __sk_user_data(sk) ((*((void __rcu **)&(sk)->sk_user_data)))
@@ -456,28 +457,32 @@ struct sock {
 #define SK_CAN_REUSE	1
 #define SK_FORCE_REUSE	2
 
+int sk_set_peek_off(struct sock *sk, int val);
+
 static inline int sk_peek_offset(struct sock *sk, int flags)
 {
-	if ((flags & MSG_PEEK) && (sk->sk_peek_off >= 0))
-		return sk->sk_peek_off;
-	else
-		return 0;
+	if (unlikely(flags & MSG_PEEK)) {
+		s32 off = READ_ONCE(sk->sk_peek_off);
+		if (off >= 0)
+			return off;
+	}
+
+	return 0;
 }
 
 static inline void sk_peek_offset_bwd(struct sock *sk, int val)
 {
-	if (sk->sk_peek_off >= 0) {
-		if (sk->sk_peek_off >= val)
-			sk->sk_peek_off -= val;
-		else
-			sk->sk_peek_off = 0;
+	s32 off = READ_ONCE(sk->sk_peek_off);
+
+	if (unlikely(off >= 0)) {
+		off = max_t(s32, off - val, 0);
+		WRITE_ONCE(sk->sk_peek_off, off);
 	}
 }
 
 static inline void sk_peek_offset_fwd(struct sock *sk, int val)
 {
-	if (sk->sk_peek_off >= 0)
-		sk->sk_peek_off += val;
+	sk_peek_offset_bwd(sk, -val);
 }
 
 /*
@@ -564,7 +569,7 @@ static inline bool __sk_del_node_init(struct sock *sk)
    modifications.
  */
 
-static inline void sock_hold(struct sock *sk)
+static __always_inline void sock_hold(struct sock *sk)
 {
 	atomic_inc(&sk->sk_refcnt);
 }
@@ -572,7 +577,7 @@ static inline void sock_hold(struct sock *sk)
 /* Ungrab socket in the context, which assumes that socket refcnt
    cannot hit zero, f.e. it is true in context of any socketcall.
  */
-static inline void __sock_put(struct sock *sk)
+static __always_inline void __sock_put(struct sock *sk)
 {
 	atomic_dec(&sk->sk_refcnt);
 }
@@ -625,7 +630,11 @@ static inline void sk_add_node(struct sock *sk, struct hlist_head *list)
 static inline void sk_add_node_rcu(struct sock *sk, struct hlist_head *list)
 {
 	sock_hold(sk);
-	hlist_add_head_rcu(&sk->sk_node, list);
+	if (IS_ENABLED(CONFIG_IPV6) && sk->sk_reuseport &&
+	    sk->sk_family == AF_INET6)
+		hlist_add_tail_rcu(&sk->sk_node, list);
+	else
+		hlist_add_head_rcu(&sk->sk_node, list);
 }
 
 static inline void __sk_nulls_add_node_rcu(struct sock *sk, struct hlist_nulls_head *list)
@@ -673,18 +682,18 @@ static inline void sk_add_bind_node(struct sock *sk,
 	hlist_for_each_entry(__sk, list, sk_bind_node)
 
 /**
- * sk_nulls_for_each_entry_offset - iterate over a list at a given struct offset
+ * sk_for_each_entry_offset_rcu - iterate over a list at a given struct offset
  * @tpos:	the type * to use as a loop cursor.
  * @pos:	the &struct hlist_node to use as a loop cursor.
  * @head:	the head for your list.
  * @offset:	offset of hlist_node within the struct.
  *
  */
-#define sk_nulls_for_each_entry_offset(tpos, pos, head, offset)		       \
-	for (pos = (head)->first;					       \
-	     (!is_a_nulls(pos)) &&					       \
+#define sk_for_each_entry_offset_rcu(tpos, pos, head, offset)		       \
+	for (pos = rcu_dereference((head)->first);			       \
+	     pos != NULL &&						       \
 		({ tpos = (typeof(*tpos) *)((void *)pos - offset); 1;});       \
-	     pos = pos->next)
+	     pos = rcu_dereference(pos->next))
 
 static inline struct user_namespace *sk_user_ns(struct sock *sk)
 {
@@ -724,6 +733,7 @@ enum sock_flags {
 		     */
 	SOCK_FILTER_LOCKED, /* Filter cannot be changed anymore */
 	SOCK_SELECT_ERR_QUEUE, /* Wake select on error queue */
+	SOCK_RCU_FREE, /* wait rcu grace period in sk_destruct() */
 };
 
 #define SK_FLAGS_TIMESTAMP ((1UL << SOCK_TIMESTAMP) | (1UL << SOCK_TIMESTAMPING_RX_SOFTWARE))
@@ -916,6 +926,17 @@ void sk_stream_kill_queues(struct sock *sk);
 void sk_set_memalloc(struct sock *sk);
 void sk_clear_memalloc(struct sock *sk);
 
+void __sk_flush_backlog(struct sock *sk);
+
+static inline bool sk_flush_backlog(struct sock *sk)
+{
+	if (unlikely(READ_ONCE(sk->sk_backlog.tail))) {
+		__sk_flush_backlog(sk);
+		return true;
+	}
+	return false;
+}
+
 int sk_wait_data(struct sock *sk, long *timeo, const struct sk_buff *skb);
 
 struct request_sock_ops;
@@ -1314,24 +1335,14 @@ static inline void sk_wmem_free_skb(struct sock *sk, struct sk_buff *skb)
 	__kfree_skb(skb);
 }
 
-/* Used by processes to "lock" a socket state, so that
- * interrupts and bottom half handlers won't change it
- * from under us. It essentially blocks any incoming
- * packets, so that we won't get any new data or any
- * packets that change the state of the socket.
- *
- * While locked, BH processing will add new packets to
- * the backlog queue.  This queue is processed by the
- * owner of the socket lock right before it is released.
- *
- * Since ~2.3.5 it is also exclusive sleep lock serializing
- * accesses from user process context.
- */
-#define sock_owned_by_user(sk)	((sk)->sk_lock.owned)
-
 static inline void sock_release_ownership(struct sock *sk)
 {
-	sk->sk_lock.owned = 0;
+	if (sk->sk_lock.owned) {
+		sk->sk_lock.owned = 0;
+
+		/* The sk_lock has mutex_unlock() semantics: */
+		mutex_release(&sk->sk_lock.dep_map, 1, _RET_IP_);
+	}
 }
 
 /*
@@ -1353,6 +1364,16 @@ do {									\
 	lockdep_init_map(&(sk)->sk_lock.dep_map, (name), (key), 0);	\
 } while (0)
 
+#ifdef CONFIG_LOCKDEP
+static inline bool lockdep_sock_is_held(const struct sock *csk)
+{
+	struct sock *sk = (struct sock *)csk;
+
+	return lockdep_is_held(&sk->sk_lock) ||
+	       lockdep_is_held(&sk->sk_lock.slock);
+}
+#endif
+
 void lock_sock_nested(struct sock *sk, int subclass);
 
 static inline void lock_sock(struct sock *sk)
@@ -1386,6 +1407,40 @@ static inline void unlock_sock_fast(struct sock *sk, bool slow)
 		spin_unlock_bh(&sk->sk_lock.slock);
 }
 
+/* Used by processes to "lock" a socket state, so that
+ * interrupts and bottom half handlers won't change it
+ * from under us. It essentially blocks any incoming
+ * packets, so that we won't get any new data or any
+ * packets that change the state of the socket.
+ *
+ * While locked, BH processing will add new packets to
+ * the backlog queue.  This queue is processed by the
+ * owner of the socket lock right before it is released.
+ *
+ * Since ~2.3.5 it is also exclusive sleep lock serializing
+ * accesses from user process context.
+ */
+
+static inline void sock_owned_by_me(const struct sock *sk)
+{
+#ifdef CONFIG_LOCKDEP
+	WARN_ON_ONCE(!lockdep_sock_is_held(sk) && debug_locks);
+#endif
+}
+
+static inline bool sock_owned_by_user(const struct sock *sk)
+{
+	sock_owned_by_me(sk);
+	return sk->sk_lock.owned;
+}
+
+/* no reclassification while locks are held */
+static inline bool sock_allow_reclassification(const struct sock *csk)
+{
+	struct sock *sk = (struct sock *)csk;
+
+	return !sk->sk_lock.owned && !spin_is_locked(&sk->sk_lock.slock);
+}
 
 struct sock *sk_alloc(struct net *net, int family, gfp_t priority,
 		      struct proto *prot, int kern);
@@ -1395,6 +1450,7 @@ struct sock *sk_clone_lock(const struct sock *sk, const gfp_t priority);
 
 struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force,
 			     gfp_t priority);
+void __sock_wfree(struct sk_buff *skb);
 void sock_wfree(struct sk_buff *skb);
 void skb_orphan_partial(struct sk_buff *skb);
 void sock_rfree(struct sk_buff *skb);
@@ -1422,8 +1478,11 @@ void sk_send_sigurg(struct sock *sk);
 
 struct sockcm_cookie {
 	u32 mark;
+	u16 tsflags;
 };
 
+int __sock_cmsg_send(struct sock *sk, struct msghdr *msg, struct cmsghdr *cmsg,
+		     struct sockcm_cookie *sockc);
 int sock_cmsg_send(struct sock *sk, struct msghdr *msg,
 		   struct sockcm_cookie *sockc);
 
@@ -1588,8 +1647,8 @@ static inline void sk_rethink_txhash(struct sock *sk)
 static inline struct dst_entry *
 __sk_dst_get(struct sock *sk)
 {
-	return rcu_dereference_check(sk->sk_dst_cache, sock_owned_by_user(sk) ||
-						       lockdep_is_held(&sk->sk_lock.slock));
+	return rcu_dereference_check(sk->sk_dst_cache,
+				     lockdep_sock_is_held(sk));
 }
 
 static inline struct dst_entry *
@@ -1861,6 +1920,7 @@ void sk_reset_timer(struct sock *sk, struct timer_list *timer,
 
 void sk_stop_timer(struct sock *sk, struct timer_list *timer);
 
+int __sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 int sock_queue_rcv_skb(struct sock *sk, struct sk_buff *skb);
 
 int sock_queue_err_skb(struct sock *sk, struct sk_buff *skb);
@@ -1897,11 +1957,19 @@ static inline unsigned long sock_wspace(struct sock *sk)
  */
 static inline void sk_set_bit(int nr, struct sock *sk)
 {
+	if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
+	    !sock_flag(sk, SOCK_FASYNC))
+		return;
+
 	set_bit(nr, &sk->sk_wq_raw->flags);
 }
 
 static inline void sk_clear_bit(int nr, struct sock *sk)
 {
+	if ((nr == SOCKWQ_ASYNC_NOSPACE || nr == SOCKWQ_ASYNC_WAITDATA) &&
+	    !sock_flag(sk, SOCK_FASYNC))
+		return;
+
 	clear_bit(nr, &sk->sk_wq_raw->flags);
 }
 
@@ -2011,6 +2079,13 @@ sock_skb_set_dropcount(const struct sock *sk, struct sk_buff *skb)
 	SOCK_SKB_CB(skb)->dropcount = atomic_read(&sk->sk_drops);
 }
 
+static inline void sk_drops_add(struct sock *sk, const struct sk_buff *skb)
+{
+	int segs = max_t(u16, 1, skb_shinfo(skb)->gso_segs);
+
+	atomic_add(segs, &sk->sk_drops);
+}
+
 void __sock_recv_timestamp(struct msghdr *msg, struct sock *sk,
 			   struct sk_buff *skb);
 void __sock_recv_wifi_status(struct msghdr *msg, struct sock *sk,
@@ -2058,19 +2133,21 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 		sk->sk_stamp = skb->tstamp;
 }
 
-void __sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags);
+void __sock_tx_timestamp(__u16 tsflags, __u8 *tx_flags);
 
 /**
  * sock_tx_timestamp - checks whether the outgoing packet is to be time stamped
  * @sk:		socket sending this packet
+ * @tsflags:	timestamping flags to use
  * @tx_flags:	completed with instructions for time stamping
  *
  * Note : callers should take care of initial *tx_flags value (usually 0)
  */
-static inline void sock_tx_timestamp(const struct sock *sk, __u8 *tx_flags)
+static inline void sock_tx_timestamp(const struct sock *sk, __u16 tsflags,
+				     __u8 *tx_flags)
 {
-	if (unlikely(sk->sk_tsflags))
-		__sock_tx_timestamp(sk, tx_flags);
+	if (unlikely(tsflags))
+		__sock_tx_timestamp(tsflags, tx_flags);
 	if (unlikely(sock_flag(sk, SOCK_WIFI_STATUS)))
 		*tx_flags |= SKBTX_WIFI_STATUS;
 }