3.2-stable review patch.  If anyone has any objections, please let me know.

------------------

From: Takashi Iwai <redacted>

commit fc1156c0b0f7ad45ec03d919866349eeca2bf18c upstream.

VT1705 codec has two ADCs where the secondary ADC has no MUX but only
a fixed connection to the mic pin.  This confused the driver and it
tries always overriding the input-source selection by assumption of
the existing MUX for the secondary ADC, resulted in resetting the
input-source at each time PM (including power-saving) occurs.

The fix is simply to check the existence of MUX for secondary ADCs in
the initialization code.

Tested-by: Anisse Astier <redacted>
Signed-off-by: Takashi Iwai <redacted>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>

---
 sound/pci/hda/patch_via.c |    3 +++
 1 file changed, 3 insertions(+)

--- a/sound/pci/hda/patch_via.c
+++ b/sound/pci/hda/patch_via.c

@@ -665,6 +665,9 @@ static void via_auto_init_analog_input(s
 	/* init input-src */
 	for (i = 0; i < spec->num_adc_nids; i++) {
 		int adc_idx = spec->inputs[spec->cur_mux[i]].adc_idx;
+		/* secondary ADCs must have the unique MUX */
+		if (i > 0 && !spec->mux_nids[i])
+			break;
 		if (spec->mux_nids[adc_idx]) {
 			int mux_idx = spec->inputs[spec->cur_mux[i]].mux_idx;
 			snd_hda_codec_write(codec, spec->mux_nids[adc_idx], 0,