tcp: Remove splice from tcp_epoll_ref

Currently the epoll reference for tcp sockets includes a bit indicating
whether the socket maps to a spliced connection.  However, the reference
also has the index of the connection structure which also indicates whether
it is spliced.  We can therefore avoid the splice bit in the epoll_ref by
unifying the first part of the non-spliced and spliced handlers where we
look up the connection state.

Signed-off-by: David Gibson <david@gibson.dropbear.id.au>
Signed-off-by: Stefano Brivio <sbrivio@redhat.com>

tcp.c

@@ -2851,7 +2851,6 @@ static void tcp_conn_from_sock(struct ctx *c, union epoll_ref ref,
 	int s;
 
 	assert(ref.r.p.tcp.tcp.listen);
-	assert(!ref.r.p.tcp.tcp.splice);
 
 	if (c->tcp.conn_count >= TCP_MAX_CONNS)
 		return;
@@ -2940,35 +2939,14 @@ static void tcp_timer_handler(struct ctx *c, union epoll_ref ref)
 }
 
 /**
- * tcp_sock_handler() - Handle new data from socket, or timerfd event
+ * tcp_tap_sock_handler() - Handle new data from non-spliced socket
  * @c:		Execution context
- * @ref:	epoll reference
+ * @conn:	Connection state
  * @events:	epoll events bitmap
- * @now:	Current timestamp
  */
-void tcp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
+static void tcp_tap_sock_handler(struct ctx *c, struct tcp_tap_conn *conn,
-		      const struct timespec *now)
+				 uint32_t events)
 {
-	struct tcp_tap_conn *conn;
-
-	if (ref.r.p.tcp.tcp.timer) {
-		tcp_timer_handler(c, ref);
-		return;
-	}
-
-	if (ref.r.p.tcp.tcp.listen) {
-		tcp_conn_from_sock(c, ref, now);
-		return;
-	}
-
-	if (ref.r.p.tcp.tcp.splice) {
-		tcp_sock_handler_splice(c, ref, events);
-		return;
-	}
-
-	if (!(conn = conn_at_idx(ref.r.p.tcp.tcp.index)))
-		return;
-
 	if (conn->events == CLOSED)
 		return;
 
@@ -3015,6 +2993,36 @@ void tcp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
 	}
 }
 
+/**
+ * tcp_sock_handler() - Handle new data from socket, or timerfd event
+ * @c:		Execution context
+ * @ref:	epoll reference
+ * @events:	epoll events bitmap
+ * @now:	Current timestamp
+ */
+void tcp_sock_handler(struct ctx *c, union epoll_ref ref, uint32_t events,
+		      const struct timespec *now)
+{
+	union tcp_conn *conn;
+
+	if (ref.r.p.tcp.tcp.timer) {
+		tcp_timer_handler(c, ref);
+		return;
+	}
+
+	if (ref.r.p.tcp.tcp.listen) {
+		tcp_conn_from_sock(c, ref, now);
+		return;
+	}
+
+	conn = tc + ref.r.p.tcp.tcp.index;
+
+	if (conn->c.spliced)
+		tcp_splice_sock_handler(c, &conn->splice, ref.r.s, events);
+	else
+		tcp_tap_sock_handler(c, &conn->tap, events);
+}
+
 /**
  * tcp_sock_init4() - Initialise listening sockets for a given IPv4 port
  * @c:		Execution context

tcp.h

@@ -32,7 +32,6 @@ void tcp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s,
 /**
  * union tcp_epoll_ref - epoll reference portion for TCP connections
  * @listen:		Set if this file descriptor is a listening socket
- * @splice:		Set if descriptor is associated to a spliced connection
  * @outbound:		Listening socket maps to outbound, spliced connection
  * @v6:			Set for IPv6 sockets or connections
  * @timer:		Reference is a timerfd descriptor for connection
@@ -42,7 +41,6 @@ void tcp_update_l2_buf(const unsigned char *eth_d, const unsigned char *eth_s,
 union tcp_epoll_ref {
 	struct {
 		uint32_t	listen:1,
-				splice:1,
 				outbound:1,
 				v6:1,
 				timer:1,

tcp_splice.c

@@ -166,11 +166,9 @@ static int tcp_splice_epoll_ctl(const struct ctx *c,
 {
 	int m = conn->c.in_epoll ? EPOLL_CTL_MOD : EPOLL_CTL_ADD;
 	union epoll_ref ref_a = { .r.proto = IPPROTO_TCP, .r.s = conn->a,
-				  .r.p.tcp.tcp.splice = 1,
 				  .r.p.tcp.tcp.index = CONN_IDX(conn),
 				  .r.p.tcp.tcp.v6 = CONN_V6(conn) };
 	union epoll_ref ref_b = { .r.proto = IPPROTO_TCP, .r.s = conn->b,
-				  .r.p.tcp.tcp.splice = 1,
 				  .r.p.tcp.tcp.index = CONN_IDX(conn),
 				  .r.p.tcp.tcp.v6 = CONN_V6(conn) };
 	struct epoll_event ev_a = { .data.u64 = ref_a.u64 };
@@ -547,24 +545,20 @@ bool tcp_splice_conn_from_sock(struct ctx *c, union epoll_ref ref,
 }
 
 /**
- * tcp_sock_handler_splice() - Handler for socket mapped to spliced connection
+ * tcp_splice_sock_handler() - Handler for socket mapped to spliced connection
  * @c:		Execution context
- * @ref:	epoll reference
+ * @conn:	Connection state
+ * @s:		Socket fd on which an event has occurred
  * @events:	epoll events bitmap
  *
  * #syscalls:pasta splice
  */
-void tcp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
+void tcp_splice_sock_handler(struct ctx *c, struct tcp_splice_conn *conn,
-			     uint32_t events)
+			     int s, uint32_t events)
 {
 	uint8_t lowat_set_flag, lowat_act_flag;
 	int from, to, *pipes, eof, never_read;
 	uint32_t *seq_read, *seq_write;
-	struct tcp_splice_conn *conn;
-
-	assert(!ref.r.p.tcp.tcp.listen);
-
-	conn = CONN(ref.r.p.tcp.tcp.index);
 
 	if (conn->events == SPLICE_CLOSED)
 		return;
@@ -580,25 +574,25 @@ void tcp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
 	}
 
 	if (events & EPOLLOUT) {
-		if (ref.r.s == conn->a)
+		if (s == conn->a)
 			conn_event(c, conn, ~A_OUT_WAIT);
 		else
 			conn_event(c, conn, ~B_OUT_WAIT);
 
-		tcp_splice_dir(conn, ref.r.s, 1, &from, &to, &pipes);
+		tcp_splice_dir(conn, s, 1, &from, &to, &pipes);
 	} else {
-		tcp_splice_dir(conn, ref.r.s, 0, &from, &to, &pipes);
+		tcp_splice_dir(conn, s, 0, &from, &to, &pipes);
 	}
 
 	if (events & EPOLLRDHUP) {
-		if (ref.r.s == conn->a)
+		if (s == conn->a)
 			conn_event(c, conn, A_FIN_RCVD);
 		else
 			conn_event(c, conn, B_FIN_RCVD);
 	}
 
 	if (events & EPOLLHUP) {
-		if (ref.r.s == conn->a)
+		if (s == conn->a)
 			conn_event(c, conn, A_FIN_SENT); /* Fake, but implied */
 		else
 			conn_event(c, conn, B_FIN_SENT);

tcp_splice.h

@@ -8,8 +8,8 @@
 
 struct tcp_splice_conn;
 
-void tcp_sock_handler_splice(struct ctx *c, union epoll_ref ref,
+void tcp_splice_sock_handler(struct ctx *c, struct tcp_splice_conn *conn,
-			     uint32_t events);
+			     int s, uint32_t events);
 bool tcp_splice_conn_from_sock(struct ctx *c, union epoll_ref ref,
 			       struct tcp_splice_conn *conn, int s,
 			       const struct sockaddr *sa);