ALSA: firewire-lib: Restrict calling flush_context_completion() when context exists

Currently, drivers can bring XRUN state for PCM substreams when error to
queue packets or detecting discontinuity of packet. The application may try to
recover this state by calling snd_pcm_prepare().

Depending on each driver, .prepare() includes restart streaming. Then there
is a state that PCM substreams are running but isochronous contexts are
stopped. In this case, when .pointer() is called, it refers to error pointer.

This commit is for a prevention of this bug.
Signed-off-by: NTakashi Sakamoto <o-takashi@sakamocchi.jp>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

sound/firewire/amdtp.c

@@ -898,7 +898,7 @@ EXPORT_SYMBOL(amdtp_stream_start);
 unsigned long amdtp_stream_pcm_pointer(struct amdtp_stream *s)
 {
 	/* this optimization is allowed to be racy */
-	if (s->pointer_flush)
+	if (s->pointer_flush && amdtp_stream_running(s))
 		fw_iso_context_flush_completions(s->context);
 	else
 		s->pointer_flush = true;