tcp_splice: Simplify tracking of read/written bytes

For each each direction of each spliced connection, we keep track of how
many bytes we've read from one socket and written to the other.  However,
we never actually care about the absolute values of these, only the
difference between them, which represents how much data is currently "in
flight" in the splicing pipe.

Simplify the handling by having a single variable tracking the number of
bytes in the pipe.

As a bonus, the new scheme makes it clearer that we don't need to worry
about overflows: pending can never become larger than the maximum pipe
bufffer size, well within 32-bits.

I _think_ the old scheme was safe in the case of overflow - again under
the assumption that read/written can never be further apart than the pipe
buffer size.  However, it's much harder to reason about this case.  It's
certainly plausible that an overflow could occur - sending 4GiB through
a local socket is entirely achievable.

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

2 files changed, 11 insertions, 13 deletions

diff --git a/tcp_conn.h b/tcp_conn.h
index 9f5bee0..c8381aa 100644
--- a/tcp_conn.h
+++ b/tcp_conn.h
@@ -206,8 +206,7 @@ struct tcp_tap_transfer_ext {
  * @f:			Generic flow information
  * @s:			File descriptor for sockets
  * @pipe:		File descriptors for pipes
- * @read:		Bytes read (not fully written to other side in one shot)
- * @written:		Bytes written (not fully written from one other side read)
+ * @pending:		Bytes currently in each pipe
  * @events:		Events observed/actions performed on connection
  * @flags:		Connection flags (attributes, not events)
  */
@@ -218,8 +217,7 @@ struct tcp_splice_conn {
 	int s[SIDES];
 	int pipe[SIDES][2];
 
-	uint32_t read[SIDES];
-	uint32_t written[SIDES];
+	uint32_t pending[SIDES];
 
 	uint8_t events;
 #define SPLICE_CLOSED			0
diff --git a/tcp_splice.c b/tcp_splice.c
index ae92bbd..af50e71 100644
--- a/tcp_splice.c
+++ b/tcp_splice.c
@@ -292,7 +292,7 @@ bool tcp_splice_flow_defer(struct tcp_splice_conn *conn)
 			conn->s[sidei] = -1;
 		}
 
-		conn->read[sidei] = conn->written[sidei] = 0;
+		conn->pending[sidei] = 0;
 	}
 
 	conn->events = SPLICE_CLOSED;
@@ -494,7 +494,7 @@ static int tcp_splice_forward(struct ctx *c,
 	int eof = 0;
 
 	while (1) {
-		ssize_t readlen, written, pending;
+		ssize_t readlen, written;
 		int more = 0;
 
 retry:
@@ -543,7 +543,7 @@ retry:
 		flow_trace(conn, "%zi from write-side call (passed %zi)",
 			   written, c->tcp.pipe_size);
 
-		/* Most common case: skip updating counters. */
+		/* Most common case: skip updating count of pending bytes */
 		if (readlen > 0 && readlen == written) {
 			if (readlen >= (long)c->tcp.pipe_size * 10 / 100)
 				continue;
@@ -567,11 +567,11 @@ retry:
 			continue;
 		}
 
-		conn->read[fromsidei]    += readlen > 0 ? readlen : 0;
-		conn->written[fromsidei] += written > 0 ? written : 0;
+		conn->pending[fromsidei] += readlen > 0 ? readlen : 0;
+		conn->pending[fromsidei] -= written > 0 ? written : 0;
 
 		if (written < 0) {
-			if (conn->read[fromsidei] == conn->written[fromsidei])
+			if (!conn->pending[fromsidei])
 				break;
 
 			conn_event(conn, OUT_WAIT(!fromsidei));
@@ -581,15 +581,15 @@ retry:
 		if (never_read && written == (long)(c->tcp.pipe_size))
 			goto retry;
 
-		pending = conn->read[fromsidei] - conn->written[fromsidei];
-		if (!never_read && written > 0 && written < pending)
+		if (!never_read && written > 0 &&
+		    written < conn->pending[fromsidei])
 			goto retry;
 
 		if (eof)
 			break;
 	}
 
-	if (conn->read[fromsidei] == conn->written[fromsidei] && eof) {
+	if (!conn->pending[fromsidei] && eof) {
 		unsigned sidei;
 
 		flow_foreach_sidei(sidei) {