ALSA: hda - Revert stream assignment order for Intel controllers

We got a regression report for 3.15.x kernels, and this turned out to
be triggered by the fix for stream assignment order.  On reporter's
machine with Intel controller (8086:1e20) + VIA VT1802 codec, the
first playback slot can't work with speaker outputs.

But the original commit was actually a fix for AMD controllers where
no proper GCAP value is returned, we shouldn't revert the whole
commit.  Instead, in this patch, a new flag is introduced to determine
the stream assignment order, and follow the old behavior for Intel
controllers.

Fixes: dcb32ecd9a ('ALSA: hda - Do not assign streams in reverse order')
Reported-and-tested-by: Steven Newbury <steve@snewbury.org.uk>
Cc: <stable@vger.kernel.org> [v3.15+]
Signed-off-by: Takashi Iwai <tiwai@suse.de>

sound/pci/hda/hda_controller.c

@@ -193,7 +193,8 @@ azx_assign_device(struct azx *chip, struct snd_pcm_substream *substream)
 				dsp_unlock(azx_dev);
 				return azx_dev;
 			}
-			if (!res)
+			if (!res ||
+			    (chip->driver_caps & AZX_DCAPS_REVERSE_ASSIGN))
 				res = azx_dev;
 		}
 		dsp_unlock(azx_dev);