Adding upstream version 4.19.289.upstream/4.19.289

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

1 files changed, 33 insertions, 11 deletions

diff --git a/include/net/sock.h b/include/net/sock.h
index 9eb656683..616e84d16 100644
--- a/include/net/sock.h
+++ b/include/net/sock.h
@@ -312,6 +312,7 @@ struct sock_common {
   *	@sk_cgrp_data: cgroup data for this cgroup
   *	@sk_memcg: this socket's memory cgroup association
   *	@sk_write_pending: a write to stream socket waits to start
+  *	@sk_wait_pending: number of threads blocked on this socket
   *	@sk_state_change: callback to indicate change in the state of the sock
   *	@sk_data_ready: callback to indicate there is data to be processed
   *	@sk_write_space: callback to indicate there is bf sending space available
@@ -392,6 +393,7 @@ struct sock {
 	unsigned int		sk_napi_id;
 #endif
 	int			sk_rcvbuf;
+	int			sk_wait_pending;
 
 	struct sk_filter __rcu	*sk_filter;
 	union {
@@ -986,8 +988,12 @@ static inline void sock_rps_record_flow(const struct sock *sk)
 		 * OR	an additional socket flag
 		 * [1] : sk_state and sk_prot are in the same cache line.
 		 */
-		if (sk->sk_state == TCP_ESTABLISHED)
-			sock_rps_record_flow_hash(sk->sk_rxhash);
+		if (sk->sk_state == TCP_ESTABLISHED) {
+			/* This READ_ONCE() is paired with the WRITE_ONCE()
+			 * from sock_rps_save_rxhash() and sock_rps_reset_rxhash().
+			 */
+			sock_rps_record_flow_hash(READ_ONCE(sk->sk_rxhash));
+		}
 	}
 #endif
 }
@@ -996,20 +1002,25 @@ static inline void sock_rps_save_rxhash(struct sock *sk,
 					const struct sk_buff *skb)
 {
 #ifdef CONFIG_RPS
-	if (unlikely(sk->sk_rxhash != skb->hash))
-		sk->sk_rxhash = skb->hash;
+	/* The following WRITE_ONCE() is paired with the READ_ONCE()
+	 * here, and another one in sock_rps_record_flow().
+	 */
+	if (unlikely(READ_ONCE(sk->sk_rxhash) != skb->hash))
+		WRITE_ONCE(sk->sk_rxhash, skb->hash);
 #endif
 }
 
 static inline void sock_rps_reset_rxhash(struct sock *sk)
 {
 #ifdef CONFIG_RPS
-	sk->sk_rxhash = 0;
+	/* Paired with READ_ONCE() in sock_rps_record_flow() */
+	WRITE_ONCE(sk->sk_rxhash, 0);
 #endif
 }
 
 #define sk_wait_event(__sk, __timeo, __condition, __wait)		\
 	({	int __rc;						\
+		__sk->sk_wait_pending++;				\
 		release_sock(__sk);					\
 		__rc = __condition;					\
 		if (!__rc) {						\
@@ -1019,6 +1030,7 @@ static inline void sock_rps_reset_rxhash(struct sock *sk)
 		}							\
 		sched_annotate_sleep();					\
 		lock_sock(__sk);					\
+		__sk->sk_wait_pending--;				\
 		__rc = __condition;					\
 		__rc;							\
 	})
@@ -1130,7 +1142,7 @@ struct proto {
 	unsigned int		inuse_idx;
 #endif
 
-	bool			(*stream_memory_free)(const struct sock *sk);
+	bool			(*stream_memory_free)(const struct sock *sk, int wake);
 	bool			(*stream_memory_read)(const struct sock *sk);
 	/* Memory pressure */
 	void			(*enter_memory_pressure)(struct sock *sk);
@@ -1212,19 +1224,29 @@ static inline void sk_refcnt_debug_release(const struct sock *sk)
 #define sk_refcnt_debug_release(sk) do { } while (0)
 #endif /* SOCK_REFCNT_DEBUG */
 
-static inline bool sk_stream_memory_free(const struct sock *sk)
+static inline bool __sk_stream_memory_free(const struct sock *sk, int wake)
 {
 	if (sk->sk_wmem_queued >= sk->sk_sndbuf)
 		return false;
 
 	return sk->sk_prot->stream_memory_free ?
-		sk->sk_prot->stream_memory_free(sk) : true;
+		sk->sk_prot->stream_memory_free(sk, wake) : true;
 }
 
-static inline bool sk_stream_is_writeable(const struct sock *sk)
+static inline bool sk_stream_memory_free(const struct sock *sk)
+{
+	return __sk_stream_memory_free(sk, 0);
+}
+
+static inline bool __sk_stream_is_writeable(const struct sock *sk, int wake)
 {
 	return sk_stream_wspace(sk) >= sk_stream_min_wspace(sk) &&
-	       sk_stream_memory_free(sk);
+	       __sk_stream_memory_free(sk, wake);
+}
+
+static inline bool sk_stream_is_writeable(const struct sock *sk)
+{
+	return __sk_stream_is_writeable(sk, 0);
 }
 
 static inline int sk_under_cgroup_hierarchy(struct sock *sk,
@@ -2406,7 +2428,7 @@ static inline void sock_recv_ts_and_drops(struct msghdr *msg, struct sock *sk,
 		__sock_recv_ts_and_drops(msg, sk, skb);
 	else if (unlikely(sock_flag(sk, SOCK_TIMESTAMP)))
 		sock_write_timestamp(sk, skb->tstamp);
-	else if (unlikely(sk->sk_stamp == SK_DEFAULT_STAMP))
+	else if (unlikely(sock_read_timestamp(sk) == SK_DEFAULT_STAMP))
 		sock_write_timestamp(sk, 0);
 }