[PATCH 1/2] ALSA: hda - fix Lewisburg audio issue

[PATCH 1/2] ALSA: hda - fix Lewisburg audio issue

[Jaroslav Kysela]

Like for Sunrise Point, the total stream number of Lewisburg's
input and output stream exceeds 15 (GCAP is 0x9701), which will
cause some streams do not work because of the overflow on
SDxCTL.STRM field if using the legacy stream tag allocation method.

Signed-off-by: Jaroslav Kysela <perex@perex.cz>
---
 sound/pci/hda/hda_intel.c | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index faf99cc..7d77bb5 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -2214,9 +2214,9 @@ static const struct pci_device_id azx_ids[] = {
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
 	/* Lewisburg */
 	{ PCI_DEVICE(0x8086, 0xa1f0),
-	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	{ PCI_DEVICE(0x8086, 0xa270),
-	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
+	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_SKYLAKE },
 	/* Lynx Point-LP */
 	{ PCI_DEVICE(0x8086, 0x9c20),
 	  .driver_data = AZX_DRIVER_PCH | AZX_DCAPS_INTEL_PCH },
-- 
2.9.3

[PATCH 2/2] ALSA: hda - add sanity check to force the separate stream tags

[Jaroslav Kysela]

It seems that newer Intel chipsets have more than 15 I/O streams (total).
This patch forces the separate stream tags, when this hardware is detected
to avoid SDxCTL.STRM field overflow and an unexpected behaviour.

Signed-off-by: Jaroslav Kysela <perex@perex.cz>
---
 sound/pci/hda/hda_intel.c | 8 ++++++++
 1 file changed, 8 insertions(+)

diff --git a/sound/pci/hda/hda_intel.c b/sound/pci/hda/hda_intel.c
index 7d77bb5..16108f0e 100644
--- a/sound/pci/hda/hda_intel.c
+++ b/sound/pci/hda/hda_intel.c
@@ -1778,6 +1778,14 @@ static int azx_first_init(struct azx *chip)
 	chip->playback_index_offset = chip->capture_streams;
 	chip->num_streams = chip->playback_streams + chip->capture_streams;
 
+	/* sanity check for the SDxCTL.STRM field overflow */
+	if (chip->num_streams > 15 &&
+	    (chip->driver_caps & AZX_DCAPS_SEPARATE_STREAM_TAG) == 0) {
+		dev_warn(chip->card->dev, "number of I/O streams is %d, "
+			 "forcing separate stream tags", chip->num_streams);
+		chip->driver_caps |= AZX_DCAPS_SEPARATE_STREAM_TAG;
+	}
+
 	/* initialize streams */
 	err = azx_init_streams(chip);
 	if (err < 0)
-- 
2.9.3

Re: [PATCH 2/2] ALSA: hda - add sanity check to force the separate stream tags

[Takashi Iwai]

On Wed, 15 Feb 2017 17:09:43 +0100,
Jaroslav Kysela wrote:
> 
> It seems that newer Intel chipsets have more than 15 I/O streams (total).
> This patch forces the separate stream tags, when this hardware is detected
> to avoid SDxCTL.STRM field overflow and an unexpected behaviour.
> 
> Signed-off-by: Jaroslav Kysela <perex@perex.cz>

It's a good idea.  Applied now.


thanks,

Takashi

Re: [PATCH 1/2] ALSA: hda - fix Lewisburg audio issue

[Takashi Iwai]

On Wed, 15 Feb 2017 17:09:42 +0100,
Jaroslav Kysela wrote:
> 
> Like for Sunrise Point, the total stream number of Lewisburg's
> input and output stream exceeds 15 (GCAP is 0x9701), which will
> cause some streams do not work because of the overflow on
> SDxCTL.STRM field if using the legacy stream tag allocation method.
> 
> Signed-off-by: Jaroslav Kysela <perex@perex.cz>

Applied (with Cc to stable) now.  Thanks.


Takashi