Re: [PATCH v2 03/14] ASoC: hdac_hdmi - Use list to add pins and converters

Re: [PATCH v2 03/14] ASoC: hdac_hdmi - Use list to add pins and converters

[Takashi Iwai]

On Thu, 03 Dec 2015 22:08:51 +0100,
Subhransu S. Prusty wrote:
>  static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
>  {
> +	struct hdac_hdmi_priv *hdmi = edev->private_data;
> +	struct hdac_hdmi_pin *pin;
> +	struct hdac_hdmi_cvt *cvt;
> +
>  	snd_soc_unregister_codec(&edev->hdac.dev);
>  
> +	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
> +		list_del(&cvt->head);
> +		kfree(cvt);
> +	}
> +
> +	list_for_each_entry(pin, &hdmi->pin_list, head) {
> +		list_del(&pin->head);
> +		kfree(pin);
> +	}

These must be list_for_each_entry_safe().


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 04/14] ASoC: hdac_hdmi: Add hotplug notification and read eld

[Takashi Iwai]

On Thu, 03 Dec 2015 22:08:52 +0100,
Subhransu S. Prusty wrote:
> 
> This patch uses i915 component framework to register for hotplug
> notification. And once it identifies valid pin sense and valid eld,
> reads the eld into the corresponding pin map buffer. For now it
> directly sends the verbs and reads the eld. Later this will use
> the i915 framework to populate ELD buffer once available.
> 
> The eld reading APIs in legacy hda are required for ASoC skylake
> hdmi driver as well. So keeping a copy here and will remove once
> component ops for reading ELD are merged in hda core.
> 
> Also read the monitor present sense during resume and ignore the
> ELD notify from graphics during PM as is done in legacy hda.
> Reference commits:
> 
> git: git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
> 
> commit 33d58f2bb446 ("ALSA: hda - Skip ELD notification during PM
> process")

This one isn't merged yet, so the commit ID may be wrong.
Maybe I'm going to merge this one at first to for-next branch,
irrelevant from test/hdmi-jack branch.  So drop it from the
description for now.

> commit 8ae743e82f0b ("ALSA: hda - Skip ELD notification during
> system suspend")

This one is already solid.


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Takashi Iwai]

On Thu, 03 Dec 2015 22:08:53 +0100,
Subhransu S. Prusty wrote:
> 
> Setting the constraint format based on ELD was missing bit in
> the sound/core pcm drm. Added with this patch.

No, you can't define these here.  The format really depends on the
hardware, while the rate and the channels are independent.
How do you know it's little-endian?  And why it must be S24_LE for
24bit, not S32_LE?


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 08/14] ASoC: hdac_hdmi - create dais based on number of streams

[Takashi Iwai]

On Thu, 03 Dec 2015 22:08:56 +0100,
Subhransu S. Prusty wrote:
> 
> A stream is mapped to a converter. So based on the converters
> queried, dais are created.
> 
> The streams can be dynamically routed to any converter. For
> now it is mapped statically. The dynamic mapping of stream
> to converter will be added when required.
> 
> Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
> Signed-off-by: Vinod Koul <vinod.koul@intel.com>
> ---
>  sound/soc/codecs/hdac_hdmi.c | 124 ++++++++++++++++++++++++++++++++-----------
>  1 file changed, 92 insertions(+), 32 deletions(-)
> 
> diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
> index 325d22b..83248ad 100644
> --- a/sound/soc/codecs/hdac_hdmi.c
> +++ b/sound/soc/codecs/hdac_hdmi.c
> @@ -29,6 +29,8 @@
>  #include <sound/pcm_drm_eld.h>
>  #include "../../hda/local.h"
>  
> +#define NAME_SIZE	32
> +
>  #define AMP_OUT_MUTE		0xb080
>  #define AMP_OUT_UNMUTE		0xb000
>  #define PIN_OUT			(AC_PINCTL_OUT_EN)
> @@ -640,11 +642,84 @@ static void hdac_hdmi_skl_enable_dp12(struct hdac_device *hdac)
>  
>  }
>  
> +static struct snd_soc_dai_ops hdmi_dai_ops = {
> +	.startup = hdac_hdmi_pcm_open,
> +	.shutdown = hdac_hdmi_pcm_close,
> +	.hw_params = hdac_hdmi_set_hw_params,
> +	.prepare = hdac_hdmi_playback_prepare,
> +	.hw_free = hdac_hdmi_playback_cleanup,
> +};
> +
> +static int hdac_hdmi_create_dais(struct hdac_device *hdac,
> +		struct snd_soc_dai_driver **dais,
> +		struct hdac_hdmi_priv *hdmi, int num_dais)
> +{
> +	struct snd_soc_dai_driver *hdmi_dais;
> +	struct hdac_hdmi_cvt *cvt;
> +	char name[NAME_SIZE], dai_name[NAME_SIZE];
> +	int i = 0, j;
> +	u32 rates, bps;
> +	unsigned int rate_max = 384000, rate_min = 8000;
> +	u64 formats;
> +	int ret;
> +	static unsigned int rate_pcm[] = {
> +		8000, 11025, 16000, 22050, 32000, 44100, 48000, 88200,
> +		96000, 176400, 192000, 384000
> +	};
> +
> +	hdmi_dais = devm_kzalloc(&hdac->dev, (sizeof(*hdmi_dais) * num_dais),
> +			GFP_KERNEL);
> +	if (!hdmi_dais)
> +		return -ENOMEM;
> +
> +	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
> +		ret = snd_hdac_query_supported_pcm(hdac, cvt->nid, &rates,
> +			&formats, &bps);
> +		if (ret)
> +			return ret;
> +		for (j = 0; j < ARRAY_SIZE(rate_pcm); j++) {
> +			if (rates & (1 << j)) {
> +				rate_min = rate_pcm[j];
> +				break;
> +			}
> +		}
> +
> +		for (j = ARRAY_SIZE(rate_pcm) - 1; j >= 0; j--) {
> +			if (rates & (1 << j)) {
> +				rate_max = rate_pcm[j];
> +				break;
> +			}
> +		}

This is ugly...  Can't we just set rate_min/max with the fixed numbers
that cover the all possible ranges?  The refinement is done by the
rates bitmap and hw_constraint in anyway.


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 11/14] drm/edid: Add API to help find connection type

[Takashi Iwai]

On Thu, 03 Dec 2015 22:08:59 +0100,
Subhransu S. Prusty wrote:
> 
> To fill the audio infoframe it is required to identify the
> connection type as DP or HDMI. This patch adds an API which
> parses ELD and returns the display type of connected.
> 
> Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
> Signed-off-by: Vinod Koul <vinod.koul@intel.com>
> Cc: David Airlie <airlied@linux.ie>
> Cc: dri-devel@lists.freedesktop.org
> Cc: Daniel Vetter <daniel.vetter@intel.com>
> ---
>  include/drm/drm_edid.h | 12 ++++++++++++
>  1 file changed, 12 insertions(+)
> 
> diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
> index 2af9769..072de90 100644
> --- a/include/drm/drm_edid.h
> +++ b/include/drm/drm_edid.h
> @@ -403,6 +403,18 @@ static inline int drm_eld_size(const uint8_t *eld)
>  	return DRM_ELD_HEADER_BLOCK_SIZE + eld[DRM_ELD_BASELINE_ELD_LEN] * 4;
>  }
>  
> +/**
> + * drm_eld_get_conn_type - Get device type hdmi/dp connected
> + * @eld: pointer to an eld memory structure
> + *
> + * The caller need to use DRM_ELD_CONN_TYPE_HDMI or DRM_ELD_CONN_TYPE_DP to
> + * identify the display type connected.

Constants should be marked with '%'.


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 12/14] ASoC: hdac_hdmi: Add infoframe support for dp audio

[Daniel Stone]

Hi Subhransu,

On 3 December 2015 at 21:09, Subhransu S. Prusty
<subhransu.s.prusty@intel.com> wrote:
> +       if (conn_type == DRM_ELD_CONN_TYPE_HDMI) {
> +               hdmi_audio_infoframe_init(&frame);
> +
> +               /* Default stereo for now */
> +               frame.channels = channels;
> +
> +               ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
> +               if (ret < 0)
> +                       return ret;
> +
> +               dip = (u8 *)&frame;
> +
> +       } else if (conn_type == DRM_ELD_CONN_TYPE_DP) {
> +               memset(&dp_ai, 0, sizeof(dp_ai));
> +               dp_ai.type      = 0x84;
> +               dp_ai.len       = 0x1b;
> +               dp_ai.ver       = 0x11 << 2;
> +               dp_ai.CC02_CT47 = channels - 1;
> +               dp_ai.CA        = 0;
> +
> +               dip = (u8 *)&dip;

Surely this should be dip = (u8 *) &dp_ai, instead of pointing to itself?

Cheers,
Daniel

On 3 December 2015 at 21:09, Subhransu S. Prusty
<subhransu.s.prusty@intel.com> wrote:
> This uses the get_conn_type API added in the previous patch to
> identify the type of display connected and fills the infoframe
> accordingly.
>
> Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
> Signed-off-by: Vinod Koul <vinod.koul@intel.com>
> ---
>  sound/soc/codecs/hdac_hdmi.c | 68 ++++++++++++++++++++++++++++++++++++++------
>  1 file changed, 59 insertions(+), 9 deletions(-)
>
> diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
> index 3ac3498..d963d92 100644
> --- a/sound/soc/codecs/hdac_hdmi.c
> +++ b/sound/soc/codecs/hdac_hdmi.c
> @@ -22,6 +22,7 @@
>  #include <linux/module.h>
>  #include <linux/pm_runtime.h>
>  #include <linux/hdmi.h>
> +#include <drm/drm_edid.h>
>  #include <sound/pcm_params.h>
>  #include <sound/soc.h>
>  #include <sound/hdaudio_ext.h>
> @@ -201,27 +202,70 @@ hdac_hdmi_set_dip_index(struct hdac_ext_device *hdac, hda_nid_t pin_nid,
>                                 AC_VERB_SET_HDMI_DIP_INDEX, val);
>  }
>
> +struct dp_audio_infoframe {
> +       u8 type; /* 0x84 */
> +       u8 len;  /* 0x1b */
> +       u8 ver;  /* 0x11 << 2 */
> +
> +       u8 CC02_CT47;   /* match with HDMI infoframe from this on */
> +       u8 SS01_SF24;
> +       u8 CXT04;
> +       u8 CA;
> +       u8 LFEPBL01_LSV36_DM_INH7;
> +};
> +
>  static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *hdac,
>                                 hda_nid_t cvt_nid, hda_nid_t pin_nid)
>  {
>         uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE];
>         struct hdmi_audio_infoframe frame;
> +       struct dp_audio_infoframe dp_ai;
> +       struct hdac_hdmi_priv *hdmi = hdac->private_data;
> +       struct hdac_hdmi_pin *pin;
>         u8 *dip = (u8 *)&frame;
>         int ret;
>         int i;
> +       const u8 *eld_buf;
> +       u8 conn_type;
> +       int channels = 2;
>
> -       hdmi_audio_infoframe_init(&frame);
> +       list_for_each_entry(pin, &hdmi->pin_list, head) {
> +               if (pin->nid == pin_nid)
> +                       break;
> +       }
>
> -       /* Default stereo for now */
> -       frame.channels = 2;
> +       eld_buf = pin->eld.eld_buffer;
> +       conn_type = drm_eld_get_conn_type(eld_buf);
>
>         /* setup channel count */
>         snd_hdac_codec_write(&hdac->hdac, cvt_nid, 0,
> -                           AC_VERB_SET_CVT_CHAN_COUNT, frame.channels - 1);
> +                           AC_VERB_SET_CVT_CHAN_COUNT, channels - 1);
>
> -       ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
> -       if (ret < 0)
> -               return ret;
> +       if (conn_type == DRM_ELD_CONN_TYPE_HDMI) {
> +               hdmi_audio_infoframe_init(&frame);
> +
> +               /* Default stereo for now */
> +               frame.channels = channels;
> +
> +               ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
> +               if (ret < 0)
> +                       return ret;
> +
> +               dip = (u8 *)&frame;
> +
> +       } else if (conn_type == DRM_ELD_CONN_TYPE_DP) {
> +               memset(&dp_ai, 0, sizeof(dp_ai));
> +               dp_ai.type      = 0x84;
> +               dp_ai.len       = 0x1b;
> +               dp_ai.ver       = 0x11 << 2;
> +               dp_ai.CC02_CT47 = channels - 1;
> +               dp_ai.CA        = 0;
> +
> +               dip = (u8 *)&dip;
> +       } else {
> +               dev_err(&hdac->hdac.dev, "Invalid connection type: %d\n", conn_type);
> +               return -EIO;
> +       }
>
>         /* stop infoframe transmission */
>         hdac_hdmi_set_dip_index(hdac, pin_nid, 0x0, 0x0);
> @@ -231,9 +275,15 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *hdac,
>
>         /*  Fill infoframe. Index auto-incremented */
>         hdac_hdmi_set_dip_index(hdac, pin_nid, 0x0, 0x0);
> -       for (i = 0; i < sizeof(frame); i++)
> -               snd_hdac_codec_write(&hdac->hdac, pin_nid, 0,
> +       if (conn_type == 0) {
> +               for (i = 0; i < sizeof(frame); i++)
> +                       snd_hdac_codec_write(&hdac->hdac, pin_nid, 0,
>                                 AC_VERB_SET_HDMI_DIP_DATA, dip[i]);
> +       } else {
> +               for (i = 0; i < sizeof(dp_ai); i++)
> +                       snd_hdac_codec_write(&hdac->hdac, pin_nid, 0,
> +                               AC_VERB_SET_HDMI_DIP_DATA, dip[i]);
> +       }
>
>         /* Start infoframe */
>         hdac_hdmi_set_dip_index(hdac, pin_nid, 0x0, 0x0);
> --
> 1.9.1
>
> _______________________________________________
> dri-devel mailing list
> dri-devel@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/dri-devel
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 00/14] ASoC: hdac_hdmi: Add DP & notification support

[Subhransu S. Prusty]

This patch series adds DP audio and hotplug notification
support.

On Skylake two DP ports are available and to enable DP on both
ports all pins need to be enabled.

There is a special vendor widget which need to be programmed to
enable all pins and converters. This series adds hotplug
notification, read/set constraint based on ELD, enable all
pin/cvts, DP1.2, programs the audio infoframe for DP. There is
a one to one mapping between converter and stream, so the dais
are created based on the no of streams supported on hdmi codec.
Even though cvts can be mapped dynamically to the streams,
currently it is statically mapped as simultaneous playback on
both DP and HDMI is not supported as of now.

Pin muxes and controls are created dynamically to map converter
to pin widget. So at run time specific pin is mapped to the dai
based on the control selected (based on the display type DP/HDMI
connected).

Finally the DP audio infoframe programming is added to support
the DP feature. 

Also with hotplug notification support, ELD is read and
capabilities are set for rate, formats and channels. drm_eld
sound/core framework is updated to limit the formats based on
ELD.

There are few fixes one fixing the static checker warning and
other one not to fail if no connection list is found for a pin
widget.

Pls note, the 11th patch is adding a small macro for getting
connection type in drm header, we have CCed drm folks on that and
this one. Pls ack so that we can have this series merged thru
sound trees

changes in v2:
	- Address review comments
	- Dropped devm_xxx for cvt and pin memory allocation.
	- Dropped the ELD helper APIs from core and copied to driver.
	- Updated notification patch to add PM fixes from legacy hda.
	- commit message and change log updated for display power fix.
	- Updated DRM helper APIs and the caller

Jeeja KP (1):
  ASoC: hdac_hdmi: Add codec suspend/resume handler

Ramesh Babu (1):
  ASoC: hdac_hdmi: Fix to keep display active while enumerating codec

Subhransu S. Prusty (12):
  ASoC: hdac_hdmi: Fix to check num nodes correctly
  ASoC: hdac_hdmi: Fix to warn instead of err for no connected nids
  ASoC: hdac_hdmi - Use list to add pins and converters
  ASoC: hdac_hdmi: Add hotplug notification and read eld
  ALSA: pcm: Add DRM helper to set constraint for format
  ASoC: hdac_hdmi: Apply constraints based on ELD
  ASoC: hdac_hdmi: Enable DP1.2 and all converters/pins
  ASoC: hdac_hdmi - create dais based on number of streams
  ASoC: hdac_hdmi: Create widget/route based on nodes enumerated
  ASoC: hdac_hdmi: Assign pin for stream based on dapm connection
  drm/edid: Add API to help find connection type
  ASoC: hdac_hdmi: Add infoframe support for dp audio

 include/drm/drm_edid.h       |   12 +
 sound/core/pcm_drm_eld.c     |   42 +-
 sound/soc/codecs/Kconfig     |    1 +
 sound/soc/codecs/hdac_hdmi.c | 1019 ++++++++++++++++++++++++++++++++++++------
 4 files changed, 925 insertions(+), 149 deletions(-)

-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 01/14] ASoC: hdac_hdmi: Fix to check num nodes correctly

[Subhransu S. Prusty]

commit 3c83ac23253c ("ASoC: hdac_hdmi: check error return") fixes
the static checker warning reported by Dan Carpenter:

	sound/soc/codecs/hdac_hdmi.c:416 hdac_hdmi_parse_and_map_nid()
	warn: unsigned 'hdac->num_nodes' is never less than zero.

But it doesn't fix the issue completely.

It's also a failure if no sub nodes found for an afg node. So modify
the return condition appropriately.

Cc: Dan Carpenter <dan.carpenter@oracle.com>
Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 1a2f33b..929f27b 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -415,7 +415,7 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	int cvt_nid = 0, pin_nid = 0;
 
 	num_nodes = snd_hdac_get_sub_nodes(hdac, hdac->afg, &nid);
-	if (!nid || num_nodes < 0) {
+	if (!nid || num_nodes <= 0) {
 		dev_warn(&hdac->dev, "HDMI: failed to get afg sub nodes\n");
 		return -EINVAL;
 	}
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 02/14] ASoC: hdac_hdmi: Fix to warn instead of err for no connected nids

[Subhransu S. Prusty]

It is possible that some pin widget may return with no converter
connected. So don't throw error if none are found to be connected.
Instead print a warning and continue.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 10 ++++++----
 1 file changed, 6 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 929f27b..429fa14 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -316,10 +316,12 @@ static int hdac_hdmi_query_pin_connlist(struct hdac_ext_device *hdac,
 
 	pin->num_mux_nids = snd_hdac_get_connections(&hdac->hdac, pin->nid,
 			pin->mux_nids, HDA_MAX_CONNECTIONS);
-	if (pin->num_mux_nids == 0) {
-		dev_err(&hdac->hdac.dev, "No connections found\n");
-		return -ENODEV;
-	}
+	if (pin->num_mux_nids == 0)
+		dev_warn(&hdac->hdac.dev, "No connections found for pin: %d\n",
+								pin->nid);
+
+	dev_dbg(&hdac->hdac.dev, "num_mux_nids %d for pin: %d\n",
+			pin->num_mux_nids, pin->nid);
 
 	return pin->num_mux_nids;
 }
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 03/14] ASoC: hdac_hdmi - Use list to add pins and converters

[Subhransu S. Prusty]

Future platforms may have a different set of pins/converters.
So use lists to add pins and converters based on enumeration.

Also it may be required to connect any converter to any pin
dynamically as per different use cases (for example DP is
connected to pin 6 on skylake board). So this will help in
dynamically select and route.

Fix the dai map as well to use the pin/cvt from list. Not
enabling all dai maps for now.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 154 +++++++++++++++++++++++++++++--------------
 1 file changed, 106 insertions(+), 48 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 429fa14..31ab37b 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -43,11 +43,13 @@ struct hdac_hdmi_cvt_params {
 };
 
 struct hdac_hdmi_cvt {
+	struct list_head head;
 	hda_nid_t nid;
 	struct hdac_hdmi_cvt_params params;
 };
 
 struct hdac_hdmi_pin {
+	struct list_head head;
 	hda_nid_t nid;
 	int num_mux_nids;
 	hda_nid_t mux_nids[HDA_MAX_CONNECTIONS];
@@ -55,14 +57,16 @@ struct hdac_hdmi_pin {
 
 struct hdac_hdmi_dai_pin_map {
 	int dai_id;
-	struct hdac_hdmi_pin pin;
-	struct hdac_hdmi_cvt cvt;
+	struct hdac_hdmi_pin *pin;
+	struct hdac_hdmi_cvt *cvt;
 };
 
 struct hdac_hdmi_priv {
-	hda_nid_t pin_nid[3];
-	hda_nid_t cvt_nid[3];
 	struct hdac_hdmi_dai_pin_map dai_map[3];
+	struct list_head pin_list;
+	struct list_head cvt_list;
+	int num_pin;
+	int num_cvt;
 };
 
 static inline struct hdac_ext_device *to_hda_ext_device(struct device *dev)
@@ -149,13 +153,15 @@ static void hdac_hdmi_set_power_state(struct hdac_ext_device *edev,
 		struct hdac_hdmi_dai_pin_map *dai_map, unsigned int pwr_state)
 {
 	/* Power up pin widget */
-	if (!snd_hdac_check_power_state(&edev->hdac, dai_map->pin.nid, pwr_state))
-		snd_hdac_codec_write(&edev->hdac, dai_map->pin.nid, 0,
+	if (!snd_hdac_check_power_state(&edev->hdac, dai_map->pin->nid,
+						pwr_state))
+		snd_hdac_codec_write(&edev->hdac, dai_map->pin->nid, 0,
 			AC_VERB_SET_POWER_STATE, pwr_state);
 
 	/* Power up converter */
-	if (!snd_hdac_check_power_state(&edev->hdac, dai_map->cvt.nid, pwr_state))
-		snd_hdac_codec_write(&edev->hdac, dai_map->cvt.nid, 0,
+	if (!snd_hdac_check_power_state(&edev->hdac, dai_map->cvt->nid,
+						pwr_state))
+		snd_hdac_codec_write(&edev->hdac, dai_map->cvt->nid, 0,
 			AC_VERB_SET_POWER_STATE, pwr_state);
 }
 
@@ -179,13 +185,13 @@ static int hdac_hdmi_playback_prepare(struct snd_pcm_substream *substream,
 	dev_dbg(&hdac->hdac.dev, "stream tag from cpu dai %d format in cvt 0x%x\n",
 			dd->stream_tag,	dd->format);
 
-	ret = hdac_hdmi_setup_audio_infoframe(hdac, dai_map->cvt.nid,
-						dai_map->pin.nid);
+	ret = hdac_hdmi_setup_audio_infoframe(hdac, dai_map->cvt->nid,
+						dai_map->pin->nid);
 	if (ret < 0)
 		return ret;
 
-	return hdac_hdmi_setup_stream(hdac, dai_map->cvt.nid, dai_map->pin.nid,
-					dd->stream_tag, dd->format);
+	return hdac_hdmi_setup_stream(hdac, dai_map->cvt->nid,
+			dai_map->pin->nid, dd->stream_tag, dd->format);
 }
 
 static int hdac_hdmi_set_hw_params(struct snd_pcm_substream *substream,
@@ -221,9 +227,9 @@ static int hdac_hdmi_playback_cleanup(struct snd_pcm_substream *substream,
 
 	dai_map = &hdmi->dai_map[dai->id];
 
-	snd_hdac_codec_write(&edev->hdac, dai_map->cvt.nid, 0,
+	snd_hdac_codec_write(&edev->hdac, dai_map->cvt->nid, 0,
 				AC_VERB_SET_CHANNEL_STREAMID, 0);
-	snd_hdac_codec_write(&edev->hdac, dai_map->cvt.nid, 0,
+	snd_hdac_codec_write(&edev->hdac, dai_map->cvt->nid, 0,
 				AC_VERB_SET_STREAM_FORMAT, 0);
 
 	dd = (struct hdac_ext_dma_params *)snd_soc_dai_get_dma_data(dai, substream);
@@ -249,7 +255,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 
 	dai_map = &hdmi->dai_map[dai->id];
 
-	val = snd_hdac_codec_read(&hdac->hdac, dai_map->pin.nid, 0,
+	val = snd_hdac_codec_read(&hdac->hdac, dai_map->pin->nid, 0,
 					AC_VERB_GET_PIN_SENSE, 0);
 	dev_info(&hdac->hdac.dev, "Val for AC_VERB_GET_PIN_SENSE: %x\n", val);
 
@@ -260,7 +266,7 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 
 	hdac_hdmi_set_power_state(hdac, dai_map, AC_PWRST_D0);
 
-	snd_hdac_codec_write(&hdac->hdac, dai_map->pin.nid, 0,
+	snd_hdac_codec_write(&hdac->hdac, dai_map->pin->nid, 0,
 			AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
 
 	snd_pcm_hw_constraint_step(substream->runtime, 0,
@@ -280,7 +286,7 @@ static void hdac_hdmi_pcm_close(struct snd_pcm_substream *substream,
 
 	hdac_hdmi_set_power_state(hdac, dai_map, AC_PWRST_D3);
 
-	snd_hdac_codec_write(&hdac->hdac, dai_map->pin.nid, 0,
+	snd_hdac_codec_write(&hdac->hdac, dai_map->pin->nid, 0,
 			AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
 }
 
@@ -368,40 +374,79 @@ static void create_fill_widget_route_map(struct snd_soc_dapm_context *dapm,
 	snd_soc_dapm_add_routes(dapm, route, ARRAY_SIZE(route));
 }
 
-static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev,
-			struct hdac_hdmi_dai_pin_map *dai_map,
-			hda_nid_t pin_nid, hda_nid_t cvt_nid, int dai_id)
+static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
 {
-	int ret;
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_dai_pin_map *dai_map = &hdmi->dai_map[0];
+	struct hdac_hdmi_cvt *cvt;
+	struct hdac_hdmi_pin *pin;
 
-	dai_map->dai_id = dai_id;
-	dai_map->pin.nid = pin_nid;
+	if (list_empty(&hdmi->cvt_list) || list_empty(&hdmi->pin_list))
+		return -EINVAL;
 
-	ret = hdac_hdmi_query_pin_connlist(edev, &dai_map->pin);
-	if (ret < 0) {
-		dev_err(&edev->hdac.dev,
-			"Error querying connection list: %d\n", ret);
-		return ret;
-	}
+	/*
+	 * Currently on board only 1 pin and 1 converter is enabled for
+	 * simplification, more will be added eventually
+	 * So using fixed map for dai_id:pin:cvt
+	 */
+	cvt = list_first_entry(&hdmi->cvt_list, struct hdac_hdmi_cvt, head);
+	pin = list_first_entry(&hdmi->pin_list, struct hdac_hdmi_pin, head);
+
+	dai_map->dai_id = 0;
+	dai_map->pin = pin;
 
-	dai_map->cvt.nid = cvt_nid;
+	dai_map->cvt = cvt;
 
 	/* Enable out path for this pin widget */
-	snd_hdac_codec_write(&edev->hdac, pin_nid, 0,
+	snd_hdac_codec_write(&edev->hdac, pin->nid, 0,
 			AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
 
 	/* Enable transmission */
-	snd_hdac_codec_write(&edev->hdac, cvt_nid, 0,
+	snd_hdac_codec_write(&edev->hdac, cvt->nid, 0,
 			AC_VERB_SET_DIGI_CONVERT_1, 1);
 
 	/* Category Code (CC) to zero */
-	snd_hdac_codec_write(&edev->hdac, cvt_nid, 0,
+	snd_hdac_codec_write(&edev->hdac, cvt->nid, 0,
 			AC_VERB_SET_DIGI_CONVERT_2, 0);
 
-	snd_hdac_codec_write(&edev->hdac, pin_nid, 0,
+	snd_hdac_codec_write(&edev->hdac, pin->nid, 0,
 			AC_VERB_SET_CONNECT_SEL, 0);
 
-	return hdac_hdmi_query_cvt_params(&edev->hdac, &dai_map->cvt);
+	return 0;
+}
+
+static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid)
+{
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_cvt *cvt;
+
+	cvt = kzalloc(sizeof(*cvt), GFP_KERNEL);
+	if (!cvt)
+		return -ENOMEM;
+
+	cvt->nid = nid;
+
+	list_add_tail(&cvt->head, &hdmi->cvt_list);
+	hdmi->num_cvt++;
+
+	return hdac_hdmi_query_cvt_params(&edev->hdac, cvt);
+}
+
+static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
+{
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_pin *pin;
+
+	pin = kzalloc(sizeof(*pin), GFP_KERNEL);
+	if (!pin)
+		return -ENOMEM;
+
+	pin->nid = nid;
+
+	list_add_tail(&pin->head, &hdmi->pin_list);
+	hdmi->num_pin++;
+
+	return 0;
 }
 
 /*
@@ -414,7 +459,7 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	int i, num_nodes;
 	struct hdac_device *hdac = &edev->hdac;
 	struct hdac_hdmi_priv *hdmi = edev->private_data;
-	int cvt_nid = 0, pin_nid = 0;
+	int ret;
 
 	num_nodes = snd_hdac_get_sub_nodes(hdac, hdac->afg, &nid);
 	if (!nid || num_nodes <= 0) {
@@ -438,29 +483,25 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 		switch (type) {
 
 		case AC_WID_AUD_OUT:
-			hdmi->cvt_nid[cvt_nid] = nid;
-			cvt_nid++;
+			ret = hdac_hdmi_add_cvt(edev, nid);
+			if (ret < 0)
+				return ret;
 			break;
 
 		case AC_WID_PIN:
-			hdmi->pin_nid[pin_nid] = nid;
-			pin_nid++;
+			ret = hdac_hdmi_add_pin(edev, nid);
+			if (ret < 0)
+				return ret;
 			break;
 		}
 	}
 
 	hdac->end_nid = nid;
 
-	if (!pin_nid || !cvt_nid)
+	if (!hdmi->num_pin || !hdmi->num_cvt)
 		return -EIO;
 
-	/*
-	 * Currently on board only 1 pin and 1 converter is enabled for
-	 * simplification, more will be added eventually
-	 * So using fixed map for dai_id:pin:cvt
-	 */
-	return hdac_hdmi_init_dai_map(edev, &hdmi->dai_map[0], hdmi->pin_nid[0],
-			hdmi->cvt_nid[0], 0);
+	return hdac_hdmi_init_dai_map(edev);
 }
 
 static int hdmi_codec_probe(struct snd_soc_codec *codec)
@@ -544,6 +585,9 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 
 	dev_set_drvdata(&codec->dev, edev);
 
+	INIT_LIST_HEAD(&hdmi_priv->pin_list);
+	INIT_LIST_HEAD(&hdmi_priv->cvt_list);
+
 	ret = hdac_hdmi_parse_and_map_nid(edev);
 	if (ret < 0)
 		return ret;
@@ -555,8 +599,22 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 
 static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
 {
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_pin *pin;
+	struct hdac_hdmi_cvt *cvt;
+
 	snd_soc_unregister_codec(&edev->hdac.dev);
 
+	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
+		list_del(&cvt->head);
+		kfree(cvt);
+	}
+
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		list_del(&pin->head);
+		kfree(pin);
+	}
+
 	return 0;
 }
 
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 04/14] ASoC: hdac_hdmi: Add hotplug notification and read eld

[Subhransu S. Prusty]

This patch uses i915 component framework to register for hotplug
notification. And once it identifies valid pin sense and valid eld,
reads the eld into the corresponding pin map buffer. For now it
directly sends the verbs and reads the eld. Later this will use
the i915 framework to populate ELD buffer once available.

The eld reading APIs in legacy hda are required for ASoC skylake
hdmi driver as well. So keeping a copy here and will remove once
component ops for reading ELD are merged in hda core.

Also read the monitor present sense during resume and ignore the
ELD notify from graphics during PM as is done in legacy hda.
Reference commits:

git: git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git

commit 33d58f2bb446 ("ALSA: hda - Skip ELD notification during PM
process")
commit 8ae743e82f0b ("ALSA: hda - Skip ELD notification during
system suspend")

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 214 +++++++++++++++++++++++++++++++++++++++++--
 1 file changed, 207 insertions(+), 7 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 31ab37b..65796ce 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -34,6 +34,9 @@
 
 #define HDA_MAX_CONNECTIONS     32
 
+#define ELD_MAX_SIZE    256
+#define ELD_FIXED_BYTES	20
+
 struct hdac_hdmi_cvt_params {
 	unsigned int channels_min;
 	unsigned int channels_max;
@@ -48,11 +51,22 @@ struct hdac_hdmi_cvt {
 	struct hdac_hdmi_cvt_params params;
 };
 
+struct hdmi_eld {
+	bool	monitor_present;
+	bool	eld_valid;
+	int	eld_size;
+	char    eld_buffer[ELD_MAX_SIZE];
+};
+
 struct hdac_hdmi_pin {
 	struct list_head head;
 	hda_nid_t nid;
 	int num_mux_nids;
 	hda_nid_t mux_nids[HDA_MAX_CONNECTIONS];
+	struct hdmi_eld eld;
+	struct hdac_ext_device *edev;
+	int repoll_count;
+	struct delayed_work work;
 };
 
 struct hdac_hdmi_dai_pin_map {
@@ -76,6 +90,81 @@ static inline struct hdac_ext_device *to_hda_ext_device(struct device *dev)
 	return container_of(hdac, struct hdac_ext_device, hdac);
 }
 
+ /* HDMI Eld routines */
+static unsigned int hdac_hdmi_get_eld_data(struct hdac_device *codec,
+				hda_nid_t nid, int byte_index)
+{
+	unsigned int val;
+
+	val = snd_hdac_codec_read(codec, nid, 0, AC_VERB_GET_HDMI_ELDD,
+							byte_index);
+
+	dev_dbg(&codec->dev, "HDMI: ELD data byte %d: 0x%x\n",
+			byte_index, val);
+
+	return val;
+}
+
+static int hdac_hdmi_get_eld_size(struct hdac_device *codec, hda_nid_t nid)
+{
+	return snd_hdac_codec_read(codec, nid, 0, AC_VERB_GET_HDMI_DIP_SIZE,
+						 AC_DIPSIZE_ELD_BUF);
+}
+
+/*
+ * This function queries the eld size and eld data and fills in the buffer
+ * passed by user
+ */
+int hdac_hdmi_get_eld(struct hdac_device *codec, hda_nid_t nid,
+		     unsigned char *buf, int *eld_size)
+{
+	int i;
+	int ret = 0;
+	int size;
+
+	/*
+	 * ELD size is initialized to zero in caller function. If no errors and
+	 * ELD is valid, actual eld_size is assigned.
+	 */
+
+	size = hdac_hdmi_get_eld_size(codec, nid);
+	if (size < ELD_FIXED_BYTES || size > ELD_MAX_SIZE) {
+		dev_info(&codec->dev, "HDMI: invalid ELD buf size %d\n", size);
+		return -ERANGE;
+	}
+
+	/* set ELD buffer */
+	for (i = 0; i < size; i++) {
+		unsigned int val = hdac_hdmi_get_eld_data(codec, nid, i);
+		/*
+		 * Graphics driver might be writing to ELD buffer right now.
+		 * Just abort. The caller will repoll after a while.
+		 */
+		if (!(val & AC_ELDD_ELD_VALID)) {
+			dev_info(&codec->dev, "HDMI: invalid ELD data byte %d\n", i);
+			ret = -EINVAL;
+			goto error;
+		}
+		val &= AC_ELDD_ELD_DATA;
+		/*
+		 * The first byte cannot be zero. This can happen on some DVI
+		 * connections. Some Intel chips may also need some 250ms delay
+		 * to return non-zero ELD data, even when the graphics driver
+		 * correctly writes ELD content before setting ELD_valid bit.
+		 */
+		if (!val && !i) {
+			dev_dbg(&codec->dev, "HDMI: 0 ELD data\n");
+			ret = -EINVAL;
+			goto error;
+		}
+		buf[i] = val;
+	}
+
+	*eld_size = size;
+error:
+	return ret;
+}
+
 static int hdac_hdmi_setup_stream(struct hdac_ext_device *hdac,
 				hda_nid_t cvt_nid, hda_nid_t pin_nid,
 				u32 stream_tag, int format)
@@ -246,7 +335,6 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 	struct hdac_ext_device *hdac = snd_soc_dai_get_drvdata(dai);
 	struct hdac_hdmi_priv *hdmi = hdac->private_data;
 	struct hdac_hdmi_dai_pin_map *dai_map;
-	int val;
 
 	if (dai->id > 0) {
 		dev_err(&hdac->hdac.dev, "Only one dai supported as of now\n");
@@ -255,12 +343,11 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 
 	dai_map = &hdmi->dai_map[dai->id];
 
-	val = snd_hdac_codec_read(&hdac->hdac, dai_map->pin->nid, 0,
-					AC_VERB_GET_PIN_SENSE, 0);
-	dev_info(&hdac->hdac.dev, "Val for AC_VERB_GET_PIN_SENSE: %x\n", val);
-
-	if ((!(val & AC_PINSENSE_PRESENCE)) || (!(val & AC_PINSENSE_ELDV))) {
-		dev_err(&hdac->hdac.dev, "Monitor presence invalid with val: %x\n", val);
+	if ((!dai_map->pin->eld.monitor_present) ||
+		(!dai_map->pin->eld.eld_valid)) {
+		dev_err(&hdac->hdac.dev, "Failed: montior present? %d eld valid?: %d\n",
+				dai_map->pin->eld.monitor_present,
+				dai_map->pin->eld.eld_valid);
 		return -ENODEV;
 	}
 
@@ -432,6 +519,68 @@ static int hdac_hdmi_add_cvt(struct hdac_ext_device *edev, hda_nid_t nid)
 	return hdac_hdmi_query_cvt_params(&edev->hdac, cvt);
 }
 
+static void hdac_hdmi_present_sense(struct hdac_hdmi_pin *pin, int repoll)
+{
+	struct hdac_ext_device *edev = pin->edev;
+	int val;
+
+	if (!edev)
+		return;
+
+	pin->repoll_count = repoll;
+
+	pm_runtime_get_sync(&edev->hdac.dev);
+	val = snd_hdac_codec_read(&edev->hdac, pin->nid, 0,
+					AC_VERB_GET_PIN_SENSE, 0);
+
+	dev_dbg(&edev->hdac.dev, "Pin sense val %x for pin: %d\n",
+			val, pin->nid);
+	pin->eld.monitor_present = !!(val & AC_PINSENSE_PRESENCE);
+	pin->eld.eld_valid = !!(val & AC_PINSENSE_ELDV);
+
+	if (!pin->eld.monitor_present || !pin->eld.eld_valid) {
+		dev_info(&edev->hdac.dev, "%s: disconnect or eld_invalid\n",
+				__func__);
+		goto put_hdac_device;
+	}
+
+	if (pin->eld.monitor_present && pin->eld.eld_valid) {
+		/* TODO: Use i915 cmpnt framework when available */
+		if (hdac_hdmi_get_eld(&edev->hdac, pin->nid,
+				pin->eld.eld_buffer,
+				&pin->eld.eld_size) == 0) {
+			print_hex_dump_bytes("Eld: ", DUMP_PREFIX_OFFSET,
+					pin->eld.eld_buffer, pin->eld.eld_size);
+		} else {
+			dev_err(&edev->hdac.dev, "ELD invalid\n");
+			pin->eld.monitor_present = false;
+			pin->eld.eld_valid = false;
+		}
+
+	}
+
+	/*
+	 * Sometimes the pin_sense may present invalid monitor
+	 * present and eld_valid. If eld data is not valid loop, few
+	 * more times to get correct pin sense and valid eld.
+	 */
+	if ((!pin->eld.monitor_present || !pin->eld.eld_valid) && repoll)
+		schedule_delayed_work(&pin->work, msecs_to_jiffies(300));
+
+put_hdac_device:
+	pm_runtime_put_sync(&edev->hdac.dev);
+}
+static void hdac_hdmi_repoll_eld(struct work_struct *work)
+{
+	struct hdac_hdmi_pin *pin =
+		container_of(to_delayed_work(work), struct hdac_hdmi_pin, work);
+
+	/* picked from legacy */
+	if (pin->repoll_count++ > 6)
+		pin->repoll_count = 0;
+
+	hdac_hdmi_present_sense(pin, pin->repoll_count);
+}
 static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
 {
 	struct hdac_hdmi_priv *hdmi = edev->private_data;
@@ -446,6 +595,9 @@ static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
 	list_add_tail(&pin->head, &hdmi->pin_list);
 	hdmi->num_pin++;
 
+	pin->edev = edev;
+	INIT_DELAYED_WORK(&pin->work, hdac_hdmi_repoll_eld);
+
 	return 0;
 }
 
@@ -504,17 +656,64 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	return hdac_hdmi_init_dai_map(edev);
 }
 
+static void hdac_hdmi_eld_notify_cb(void *aptr, int port)
+{
+	struct hdac_ext_device *edev = aptr;
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_pin *pin;
+	struct snd_soc_codec *codec = edev->scodec;
+	/* Don't know how this mapping is derived */
+	hda_nid_t pin_nid = port + 0x04;
+
+	dev_dbg(&edev->hdac.dev, "%s: for pin: %d\n", __func__, pin_nid);
+
+	/*
+	 * skip notification during system suspend (but not in runtime PM);
+	 * the state will be updated at resume. Also since the ELD and
+	 * connection states are updated in anyway at the end of the resume,
+	 * we can skip it when received during PM process.
+	 */
+	if (snd_power_get_state(codec->component.card->snd_card) !=
+			SNDRV_CTL_POWER_D0)
+		return;
+
+	if (atomic_read(&edev->hdac.in_pm))
+		return;
+
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		if (pin->nid == pin_nid)
+			hdac_hdmi_present_sense(pin, 1);
+	}
+}
+
+static struct i915_audio_component_audio_ops aops = {
+	.pin_eld_notify	= hdac_hdmi_eld_notify_cb,
+};
+
 static int hdmi_codec_probe(struct snd_soc_codec *codec)
 {
 	struct hdac_ext_device *edev = snd_soc_codec_get_drvdata(codec);
 	struct hdac_hdmi_priv *hdmi = edev->private_data;
 	struct snd_soc_dapm_context *dapm =
 		snd_soc_component_get_dapm(&codec->component);
+	struct hdac_hdmi_pin *pin;
+	int ret;
 
 	edev->scodec = codec;
 
 	create_fill_widget_route_map(dapm, &hdmi->dai_map[0]);
 
+	aops.audio_ptr = edev;
+	ret = snd_hdac_i915_register_notifier(&aops);
+	if (ret < 0) {
+		dev_err(&edev->hdac.dev, "notifier register failed: err: %d\n",
+				ret);
+		return ret;
+	}
+
+	list_for_each_entry(pin, &hdmi->pin_list, head)
+		hdac_hdmi_eld_notify_cb(edev, (pin->nid - 0x04));
+
 	/* Imp: Store the card pointer in hda_codec */
 	edev->card = dapm->card->snd_card;
 
@@ -659,6 +858,7 @@ static int hdac_hdmi_runtime_resume(struct device *dev)
 	if (!bus)
 		return 0;
 
+
 	err = snd_hdac_display_power(bus, true);
 	if (err < 0) {
 		dev_err(bus->dev, "Cannot turn on display power on i915\n");
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Subhransu S. Prusty]

Setting the constraint format based on ELD was missing bit in
the sound/core pcm drm. Added with this patch.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/core/pcm_drm_eld.c | 42 +++++++++++++++++++++++++++++++++++++++++-
 1 file changed, 41 insertions(+), 1 deletion(-)

diff --git a/sound/core/pcm_drm_eld.c b/sound/core/pcm_drm_eld.c
index e70379f..0c5653e 100644
--- a/sound/core/pcm_drm_eld.c
+++ b/sound/core/pcm_drm_eld.c
@@ -20,11 +20,49 @@ static const unsigned int eld_rates[] = {
 	192000,
 };
 
+static unsigned int sad_format(const u8 *sad)
+{
+	return ((sad[0] >> 0x3) & 0x1f);
+}
+
+static unsigned int sad_sample_bits_lpcm(const u8 *sad)
+{
+	return (sad[2] & 7);
+}
+
 static unsigned int sad_max_channels(const u8 *sad)
 {
 	return 1 + (sad[0] & 7);
 }
 
+static int eld_limit_formats(struct snd_pcm_runtime *runtime, void *eld)
+{
+	u64 formats = SNDRV_PCM_FMTBIT_S16_LE;
+	int i;
+	const u8 *sad, *eld_buf = eld;
+
+	sad = drm_eld_sad(eld_buf);
+	if (!sad)
+		goto format_constraint;
+
+	for (i = drm_eld_sad_count(eld_buf); i > 0; i--, sad += 3) {
+		if (sad_format(sad) == 1) { /* AUDIO_CODING_TYPE_LPCM */
+
+			/* 20 bit */
+			if (sad_sample_bits_lpcm(sad) & 0x2)
+				formats |= SNDRV_PCM_FMTBIT_S32_LE;
+
+			/* 24 bit */
+			if (sad_sample_bits_lpcm(sad) & 0x4)
+				formats |= SNDRV_PCM_FMTBIT_S24_LE;
+		}
+	}
+
+format_constraint:
+	return snd_pcm_hw_constraint_mask64(runtime, SNDRV_PCM_HW_PARAM_FORMAT,
+				formats);
+}
+
 static int eld_limit_rates(struct snd_pcm_hw_params *params,
 			   struct snd_pcm_hw_rule *rule)
 {
@@ -93,7 +131,9 @@ int snd_pcm_hw_constraint_eld(struct snd_pcm_runtime *runtime, void *eld)
 	ret = snd_pcm_hw_rule_add(runtime, 0, SNDRV_PCM_HW_PARAM_CHANNELS,
 				  eld_limit_channels, eld,
 				  SNDRV_PCM_HW_PARAM_RATE, -1);
+	if (ret < 0)
+		return ret;
 
-	return ret;
+	return eld_limit_formats(runtime, eld);
 }
 EXPORT_SYMBOL_GPL(snd_pcm_hw_constraint_eld);
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 06/14] ASoC: hdac_hdmi: Apply constraints based on ELD

[Subhransu S. Prusty]

Uses the drm eld core framework to apply rate, channel and
format constraint.

Even though the channel constraint is based on ELD, infoframe
is set with stereo only. Multichannel support will be added
later.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/Kconfig     | 1 +
 sound/soc/codecs/hdac_hdmi.c | 7 +++----
 2 files changed, 4 insertions(+), 4 deletions(-)

diff --git a/sound/soc/codecs/Kconfig b/sound/soc/codecs/Kconfig
index c0c5c8e..f805cb6 100644
--- a/sound/soc/codecs/Kconfig
+++ b/sound/soc/codecs/Kconfig
@@ -486,6 +486,7 @@ config SND_SOC_GTM601
 config SND_SOC_HDAC_HDMI
 	tristate
 	select SND_HDA_EXT_CORE
+	select SND_PCM_ELD
 	select HDMI
 
 config SND_SOC_ICS43432
diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 65796ce..d891ad7 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -26,6 +26,7 @@
 #include <sound/soc.h>
 #include <sound/hdaudio_ext.h>
 #include <sound/hda_i915.h>
+#include <sound/pcm_drm_eld.h>
 #include "../../hda/local.h"
 
 #define AMP_OUT_MUTE		0xb080
@@ -356,10 +357,8 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 	snd_hdac_codec_write(&hdac->hdac, dai_map->pin->nid, 0,
 			AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
 
-	snd_pcm_hw_constraint_step(substream->runtime, 0,
-				   SNDRV_PCM_HW_PARAM_CHANNELS, 2);
-
-	return 0;
+	return snd_pcm_hw_constraint_eld(substream->runtime,
+			dai_map->pin->eld.eld_buffer);
 }
 
 static void hdac_hdmi_pcm_close(struct snd_pcm_substream *substream,
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 07/14] ASoC: hdac_hdmi: Enable DP1.2 and all converters/pins

[Subhransu S. Prusty]

By default only one converter and pin widget are enabled. A vendor
widget required to be configured to enable all the widgets of the
codec.

As we are enabling the DP support enable the DP1.2 feature as well.

The changes below are copied from patch_hdmi.c

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index d891ad7..325d22b 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -600,6 +600,46 @@ static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
 	return 0;
 }
 
+#define INTEL_VENDOR_NID 0x08
+#define INTEL_GET_VENDOR_VERB 0xf81
+#define INTEL_SET_VENDOR_VERB 0x781
+#define INTEL_EN_DP12			0x02 /* enable DP 1.2 features */
+#define INTEL_EN_ALL_PIN_CVTS	0x01 /* enable 2nd & 3rd pins and convertors */
+
+static void hdac_hdmi_skl_enable_all_pins(struct hdac_device *hdac)
+{
+	unsigned int vendor_param;
+
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_GET_VENDOR_VERB, 0);
+	if (vendor_param == -1 || vendor_param & INTEL_EN_ALL_PIN_CVTS)
+		return;
+
+	vendor_param |= INTEL_EN_ALL_PIN_CVTS;
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_SET_VENDOR_VERB, vendor_param);
+	if (vendor_param == -1)
+		return;
+}
+
+static void hdac_hdmi_skl_enable_dp12(struct hdac_device *hdac)
+{
+	unsigned int vendor_param;
+
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_GET_VENDOR_VERB, 0);
+	if (vendor_param == -1 || vendor_param & INTEL_EN_DP12)
+		return;
+
+	/* enable DP1.2 mode */
+	vendor_param |= INTEL_EN_DP12;
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_SET_VENDOR_VERB, vendor_param);
+	if (vendor_param == -1)
+		return;
+
+}
+
 /*
  * Parse all nodes and store the cvt/pin nids in array
  * Add one time initialization for pin and cvt widgets
@@ -612,6 +652,9 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	struct hdac_hdmi_priv *hdmi = edev->private_data;
 	int ret;
 
+	hdac_hdmi_skl_enable_all_pins(hdac);
+	hdac_hdmi_skl_enable_dp12(hdac);
+
 	num_nodes = snd_hdac_get_sub_nodes(hdac, hdac->afg, &nid);
 	if (!nid || num_nodes <= 0) {
 		dev_warn(&hdac->dev, "HDMI: failed to get afg sub nodes\n");
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 08/14] ASoC: hdac_hdmi - create dais based on number of streams

[Subhransu S. Prusty]

A stream is mapped to a converter. So based on the converters
queried, dais are created.

The streams can be dynamically routed to any converter. For
now it is mapped statically. The dynamic mapping of stream
to converter will be added when required.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 124 ++++++++++++++++++++++++++++++++-----------
 1 file changed, 92 insertions(+), 32 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 325d22b..83248ad 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -29,6 +29,8 @@
 #include <sound/pcm_drm_eld.h>
 #include "../../hda/local.h"
 
+#define NAME_SIZE	32
+
 #define AMP_OUT_MUTE		0xb080
 #define AMP_OUT_UNMUTE		0xb000
 #define PIN_OUT			(AC_PINCTL_OUT_EN)
@@ -640,11 +642,84 @@ static void hdac_hdmi_skl_enable_dp12(struct hdac_device *hdac)
 
 }
 
+static struct snd_soc_dai_ops hdmi_dai_ops = {
+	.startup = hdac_hdmi_pcm_open,
+	.shutdown = hdac_hdmi_pcm_close,
+	.hw_params = hdac_hdmi_set_hw_params,
+	.prepare = hdac_hdmi_playback_prepare,
+	.hw_free = hdac_hdmi_playback_cleanup,
+};
+
+static int hdac_hdmi_create_dais(struct hdac_device *hdac,
+		struct snd_soc_dai_driver **dais,
+		struct hdac_hdmi_priv *hdmi, int num_dais)
+{
+	struct snd_soc_dai_driver *hdmi_dais;
+	struct hdac_hdmi_cvt *cvt;
+	char name[NAME_SIZE], dai_name[NAME_SIZE];
+	int i = 0, j;
+	u32 rates, bps;
+	unsigned int rate_max = 384000, rate_min = 8000;
+	u64 formats;
+	int ret;
+	static unsigned int rate_pcm[] = {
+		8000, 11025, 16000, 22050, 32000, 44100, 48000, 88200,
+		96000, 176400, 192000, 384000
+	};
+
+	hdmi_dais = devm_kzalloc(&hdac->dev, (sizeof(*hdmi_dais) * num_dais),
+			GFP_KERNEL);
+	if (!hdmi_dais)
+		return -ENOMEM;
+
+	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
+		ret = snd_hdac_query_supported_pcm(hdac, cvt->nid, &rates,
+			&formats, &bps);
+		if (ret)
+			return ret;
+		for (j = 0; j < ARRAY_SIZE(rate_pcm); j++) {
+			if (rates & (1 << j)) {
+				rate_min = rate_pcm[j];
+				break;
+			}
+		}
+
+		for (j = ARRAY_SIZE(rate_pcm) - 1; j >= 0; j--) {
+			if (rates & (1 << j)) {
+				rate_max = rate_pcm[j];
+				break;
+			}
+		}
+
+		sprintf(dai_name, "intel-hdmi-hifi%d", i+1);
+		hdmi_dais[i].name = devm_kstrdup(&hdac->dev, dai_name,
+						GFP_KERNEL);
+
+		snprintf(name, sizeof(name), "hifi%d", i+1);
+		hdmi_dais[i].playback.stream_name =
+				devm_kstrdup(&hdac->dev, name, GFP_KERNEL);
+		hdmi_dais[i].playback.formats = formats;
+		hdmi_dais[i].playback.rates = rates;
+		hdmi_dais[i].playback.rate_max = rate_max;
+		hdmi_dais[i].playback.rate_min = rate_min;
+		hdmi_dais[i].playback.channels_min = 2;
+		hdmi_dais[i].playback.channels_max = 2;
+		hdmi_dais[i].ops = &hdmi_dai_ops;
+
+		i++;
+	}
+
+	*dais = hdmi_dais;
+
+	return 0;
+}
+
 /*
  * Parse all nodes and store the cvt/pin nids in array
  * Add one time initialization for pin and cvt widgets
  */
-static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
+static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev,
+		struct snd_soc_dai_driver **dais, int *num_dais)
 {
 	hda_nid_t nid;
 	int i, num_nodes;
@@ -695,6 +770,15 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	if (!hdmi->num_pin || !hdmi->num_cvt)
 		return -EIO;
 
+	ret = hdac_hdmi_create_dais(hdac, dais, hdmi, hdmi->num_cvt);
+	if (ret) {
+		dev_err(&hdac->dev, "Failed to create dais with err: %d\n",
+							ret);
+		return ret;
+	}
+
+	*num_dais = hdmi->num_cvt;
+
 	return hdac_hdmi_init_dai_map(edev);
 }
 
@@ -784,38 +868,12 @@ static struct snd_soc_codec_driver hdmi_hda_codec = {
 	.idle_bias_off	= true,
 };
 
-static struct snd_soc_dai_ops hdmi_dai_ops = {
-	.startup = hdac_hdmi_pcm_open,
-	.shutdown = hdac_hdmi_pcm_close,
-	.hw_params = hdac_hdmi_set_hw_params,
-	.prepare = hdac_hdmi_playback_prepare,
-	.hw_free = hdac_hdmi_playback_cleanup,
-};
-
-static struct snd_soc_dai_driver hdmi_dais[] = {
-	{	.name = "intel-hdmi-hif1",
-		.playback = {
-			.stream_name = "hif1",
-			.channels_min = 2,
-			.channels_max = 2,
-			.rates = SNDRV_PCM_RATE_32000 |
-				SNDRV_PCM_RATE_44100 | SNDRV_PCM_RATE_48000 |
-				SNDRV_PCM_RATE_88200 | SNDRV_PCM_RATE_96000 |
-				SNDRV_PCM_RATE_176400 | SNDRV_PCM_RATE_192000,
-			.formats = SNDRV_PCM_FMTBIT_S16_LE |
-				SNDRV_PCM_FMTBIT_S20_3LE |
-				SNDRV_PCM_FMTBIT_S24_LE |
-				SNDRV_PCM_FMTBIT_S32_LE,
-
-		},
-		.ops = &hdmi_dai_ops,
-	},
-};
-
 static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 {
 	struct hdac_device *codec = &edev->hdac;
 	struct hdac_hdmi_priv *hdmi_priv;
+	struct snd_soc_dai_driver *hdmi_dais = NULL;
+	int num_dais = 0;
 	int ret = 0;
 
 	hdmi_priv = devm_kzalloc(&codec->dev, sizeof(*hdmi_priv), GFP_KERNEL);
@@ -829,13 +887,15 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	INIT_LIST_HEAD(&hdmi_priv->pin_list);
 	INIT_LIST_HEAD(&hdmi_priv->cvt_list);
 
-	ret = hdac_hdmi_parse_and_map_nid(edev);
-	if (ret < 0)
+	ret = hdac_hdmi_parse_and_map_nid(edev, &hdmi_dais, &num_dais);
+	if (ret < 0) {
+		dev_err(&codec->dev, "Failed in parse and map nid with err: %d\n", ret);
 		return ret;
+	}
 
 	/* ASoC specific initialization */
 	return snd_soc_register_codec(&codec->dev, &hdmi_hda_codec,
-			hdmi_dais, ARRAY_SIZE(hdmi_dais));
+			hdmi_dais, num_dais);
 }
 
 static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 09/14] ASoC: hdac_hdmi: Create widget/route based on nodes enumerated

[Subhransu S. Prusty]

Instead of direct mapping between converter and pin, Muxes are
added between them to support any converter connection to any pin.

As the possible mux inputs can only be identified during runtime,
all possible routes are created to connect all converters to all
pin muxes. The user should enable appropriate mux inputs to enable
correct port.

In the process to support the above changes widget/route fill APIs
are updated to take all required parameters.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 224 ++++++++++++++++++++++++++++++++++++++-----
 1 file changed, 202 insertions(+), 22 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 83248ad..cded3d7 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -420,46 +420,224 @@ static int hdac_hdmi_query_pin_connlist(struct hdac_ext_device *hdac,
 	return pin->num_mux_nids;
 }
 
-static void hdac_hdmi_fill_widget_info(struct snd_soc_dapm_widget *w,
-				enum snd_soc_dapm_type id,
-				const char *wname, const char *stream)
+static void hdac_hdmi_fill_widget_info(struct device *dev,
+				struct snd_soc_dapm_widget *w,
+				enum snd_soc_dapm_type id, void *priv,
+				const char *wname, const char *stream,
+				struct snd_kcontrol_new *wc, int numkc)
 {
 	w->id = id;
-	w->name = wname;
+	w->name = devm_kstrdup(dev, wname, GFP_KERNEL);
 	w->sname = stream;
 	w->reg = SND_SOC_NOPM;
 	w->shift = 0;
-	w->kcontrol_news = NULL;
-	w->num_kcontrols = 0;
-	w->priv = NULL;
+	w->kcontrol_news = wc;
+	w->num_kcontrols = numkc;
+	w->priv = priv;
 }
 
 static void hdac_hdmi_fill_route(struct snd_soc_dapm_route *route,
-		const char *sink, const char *control, const char *src)
+		const char *sink, const char *control, const char *src,
+		int (*handler)(struct snd_soc_dapm_widget *sr,
+			struct snd_soc_dapm_widget *snk))
 {
 	route->sink = sink;
 	route->source = src;
 	route->control = control;
-	route->connected = NULL;
+	route->connected = handler;
 }
 
-static void create_fill_widget_route_map(struct snd_soc_dapm_context *dapm,
-					struct hdac_hdmi_dai_pin_map *dai_map)
+/*
+ * Ideally the Mux inputs should be based on the num_muxs enumerated, but
+ * the display driver seem to be programming the connection list for the pin
+ * widget runtime.
+ *
+ * So programming all the possible inputs for the mux, the user has to take
+ * care of selecting the right one and leaving all other inputs selected to
+ * "NONE"
+ */
+static int hdac_hdmi_create_pin_muxs(struct hdac_ext_device *edev,
+				struct hdac_hdmi_pin *pin,
+				struct snd_soc_dapm_widget *widget,
+				const char *widget_name)
 {
-	struct snd_soc_dapm_route route[1];
-	struct snd_soc_dapm_widget widgets[2] = { {0} };
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct snd_kcontrol_new *kc;
+	struct hdac_hdmi_cvt *cvt;
+	struct soc_enum *se;
+	char kc_name[NAME_SIZE];
+	char mux_items[NAME_SIZE];
+	/* To hold inputs to the Pin mux */
+	char *items[HDA_MAX_CONNECTIONS];
+	int i = 0;
+	int num_items = hdmi->num_cvt + 1;
+
+	kc = devm_kzalloc(&edev->hdac.dev, sizeof(*kc), GFP_KERNEL);
+	if (!kc)
+		return -ENOMEM;
+
+	se = devm_kzalloc(&edev->hdac.dev, sizeof(*se), GFP_KERNEL);
+	if (!se)
+		return -ENOMEM;
+
+	sprintf(kc_name, "Pin %d Input", pin->nid);
+	kc->name = devm_kstrdup(&edev->hdac.dev, kc_name, GFP_KERNEL);
+	kc->private_value = (long)se;
+	kc->iface = SNDRV_CTL_ELEM_IFACE_MIXER;
+	kc->access = 0;
+	kc->info = snd_soc_info_enum_double;
+	kc->put = snd_soc_dapm_put_enum_double;
+	kc->get = snd_soc_dapm_get_enum_double;
 
-	memset(&route, 0, sizeof(route));
+	se->reg = SND_SOC_NOPM;
 
-	hdac_hdmi_fill_widget_info(&widgets[0], snd_soc_dapm_output,
-			"hif1 Output", NULL);
-	hdac_hdmi_fill_widget_info(&widgets[1], snd_soc_dapm_aif_in,
-			"Coverter 1", "hif1");
+	/* enum texts: ["NONE", "cvt #", "cvt #", ...] */
+	se->items = num_items;
+	se->mask = roundup_pow_of_two(se->items) - 1;
+
+	sprintf(mux_items, "NONE");
+	items[i] = devm_kstrdup(&edev->hdac.dev, mux_items, GFP_KERNEL);
+
+	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
+		i++;
+		sprintf(mux_items, "cvt %d", cvt->nid);
+		items[i] = devm_kstrdup(&edev->hdac.dev, mux_items, GFP_KERNEL);
+	}
+
+	se->texts = devm_kmemdup(&edev->hdac.dev, items,
+			(num_items  * sizeof(char *)), GFP_KERNEL);
+
+	hdac_hdmi_fill_widget_info(&edev->hdac.dev, widget, snd_soc_dapm_mux,
+				&pin->nid, widget_name, NULL, kc, 1);
+
+	return 0;
+}
 
-	hdac_hdmi_fill_route(&route[0], "hif1 Output", NULL, "Coverter 1");
+/* Add cvt <- input <- mux route map */
+static void hdac_hdmi_add_pinmux_cvt_route(struct hdac_ext_device *edev,
+		struct snd_soc_dapm_widget *widgets,
+		struct snd_soc_dapm_route *route, int rindex)
+{
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	const struct snd_kcontrol_new *kc;
+	struct soc_enum *se;
+	int mux_index = hdmi->num_cvt + hdmi->num_pin;
+	int i, j;
+
+	for (i = 0; i < hdmi->num_pin; i++) {
+		kc = widgets[mux_index].kcontrol_news;
+		se = (struct soc_enum *)kc->private_value;
+		for (j = 0; j < hdmi->num_cvt; j++) {
+			hdac_hdmi_fill_route(&route[rindex],
+					widgets[mux_index].name,
+					se->texts[j + 1],
+					widgets[j].name, NULL);
+
+			rindex++;
+		}
+
+		mux_index++;
+	}
+}
+
+/*
+ * Widgets are added in the below sequence
+ *	Converter widgets for num converters enumerated
+ *	Pin widgets for num pins enumerated
+ *	Pin mux widgets to represent connenction list of pin widget
+ *
+ * Total widgets elements = num_cvt + num_pin + num_pin;
+ *
+ * Routes are added as below:
+ *	pin mux -> pin (based on num_pins)
+ *	cvt -> "Input sel control" -> pin_mux
+ *
+ * Total route elements:
+ *	num_pins + (pin_muxes * num_cvt)
+ */
+static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
+{
+	struct snd_soc_dapm_widget *widgets;
+	struct snd_soc_dapm_route *route;
+	struct hdac_ext_device *edev = to_hda_ext_device(dapm->dev);
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct snd_soc_dai_driver *dai_drv = dapm->component->dai_drv;
+	char widget_name[NAME_SIZE];
+	struct hdac_hdmi_cvt *cvt;
+	struct hdac_hdmi_pin *pin;
+	int i = 0;
+	int ret;
+	int num_routes = 0;
+
+	if (list_empty(&hdmi->cvt_list) || list_empty(&hdmi->pin_list))
+		return -EINVAL;
+
+	widgets = devm_kzalloc(dapm->dev,
+			(sizeof(*widgets) * ((2 * hdmi->num_pin) + hdmi->num_cvt)),
+			GFP_KERNEL);
+	if (!widgets)
+		return -ENOMEM;
+
+	/* DAPM widgets to represent each converter widget */
+	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
+		sprintf(widget_name, "Converter %d", cvt->nid);
+		hdac_hdmi_fill_widget_info(dapm->dev, &widgets[i],
+			snd_soc_dapm_aif_in, &cvt->nid,
+			widget_name, dai_drv[i].playback.stream_name, NULL, 0);
+		i++;
+	}
+
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		sprintf(widget_name, "hif%d Output", pin->nid);
+		hdac_hdmi_fill_widget_info(dapm->dev, &widgets[i],
+				snd_soc_dapm_output, &pin->nid,
+				widget_name, NULL, NULL, 0);
+		i++;
+	}
+
+	/* DAPM widgets to represent the connection list to pin widget */
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		sprintf(widget_name, "Pin %d Mux", pin->nid);
+		ret = hdac_hdmi_create_pin_muxs(edev, pin, &widgets[i],
+							widget_name);
+		if (ret < 0)
+			return ret;
+		i++;
+
+		/* For cvt to pin_mux mapping */
+		num_routes += hdmi->num_cvt;
+
+		/* For pin_mux to pin mapping */
+		num_routes++;
+	}
+
+	route = devm_kzalloc(dapm->dev, (sizeof(*route) * num_routes),
+							GFP_KERNEL);
+	if (!route)
+		return -ENOMEM;
+
+	i = 0;
+	/* Add pin <- NULL <- mux route map */
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		int sink_index = i + hdmi->num_cvt;
+		int src_index = sink_index + hdmi->num_pin;
+
+		hdac_hdmi_fill_route(&route[i], widgets[sink_index].name,
+				NULL, widgets[src_index].name,
+				NULL);
+		i++;
+
+	}
+
+	hdac_hdmi_add_pinmux_cvt_route(edev, widgets, route, i);
+
+	snd_soc_dapm_new_controls(dapm, widgets,
+		((2 * hdmi->num_pin) + hdmi->num_cvt));
+	snd_soc_dapm_add_routes(dapm, route, num_routes);
+	snd_soc_dapm_new_widgets(dapm->card);
+
+	return 0;
 
-	snd_soc_dapm_new_controls(dapm, widgets, ARRAY_SIZE(widgets));
-	snd_soc_dapm_add_routes(dapm, route, ARRAY_SIZE(route));
 }
 
 static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
@@ -827,7 +1005,9 @@ static int hdmi_codec_probe(struct snd_soc_codec *codec)
 
 	edev->scodec = codec;
 
-	create_fill_widget_route_map(dapm, &hdmi->dai_map[0]);
+	ret = create_fill_widget_route_map(dapm);
+	if (ret < 0)
+		return ret;
 
 	aops.audio_ptr = edev;
 	ret = snd_hdac_i915_register_notifier(&aops);
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 10/14] ASoC: hdac_hdmi: Assign pin for stream based on dapm connection

[Subhransu S. Prusty]

Now that we have all the widgets enumerated we can route the stream
to any pin widget based on Mux connection. So map the pin to stream
accordingly.

Also seems the connection list to the pin widgets are not static
and is updated runtime based on type of display attached to the port.
This looks to be a hardware behavior.

So querying of the connection list is removed from pin initialization
and used in selecting the pin for a dai map.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 208 +++++++++++++++++++++++++++++++------------
 1 file changed, 151 insertions(+), 57 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index cded3d7..3ac3498 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -37,6 +37,8 @@
 
 #define HDA_MAX_CONNECTIONS     32
 
+#define HDA_MAX_CVTS		3
+
 #define ELD_MAX_SIZE    256
 #define ELD_FIXED_BYTES	20
 
@@ -79,7 +81,7 @@ struct hdac_hdmi_dai_pin_map {
 };
 
 struct hdac_hdmi_priv {
-	struct hdac_hdmi_dai_pin_map dai_map[3];
+	struct hdac_hdmi_dai_pin_map dai_map[HDA_MAX_CVTS];
 	struct list_head pin_list;
 	struct list_head cvt_list;
 	int num_pin;
@@ -332,12 +334,126 @@ static int hdac_hdmi_playback_cleanup(struct snd_pcm_substream *substream,
 	return 0;
 }
 
+static int hdac_hdmi_enable_pin(struct hdac_ext_device *hdac,
+		struct hdac_hdmi_dai_pin_map *dai_map)
+{
+	int mux_idx;
+	struct hdac_hdmi_pin *pin = dai_map->pin;
+
+	for (mux_idx = 0; mux_idx < pin->num_mux_nids; mux_idx++) {
+		if (pin->mux_nids[mux_idx] == dai_map->cvt->nid) {
+			snd_hdac_codec_write(&hdac->hdac, pin->nid, 0,
+					AC_VERB_SET_CONNECT_SEL, mux_idx);
+			break;
+		}
+	}
+
+	if (mux_idx == pin->num_mux_nids)
+		return -EIO;
+
+	/* Enable out path for this pin widget */
+	snd_hdac_codec_write(&hdac->hdac, pin->nid, 0,
+			AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+
+	hdac_hdmi_set_power_state(hdac, dai_map, AC_PWRST_D0);
+
+	snd_hdac_codec_write(&hdac->hdac, pin->nid, 0,
+			AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+
+	return 0;
+}
+
+static int hdac_hdmi_query_pin_connlist(struct hdac_ext_device *hdac,
+					struct hdac_hdmi_pin *pin)
+{
+	if (!(get_wcaps(&hdac->hdac, pin->nid) & AC_WCAP_CONN_LIST)) {
+		dev_warn(&hdac->hdac.dev,
+			"HDMI: pin %d wcaps %#x does not support connection list\n",
+			pin->nid, get_wcaps(&hdac->hdac, pin->nid));
+		return -EINVAL;
+	}
+
+	pin->num_mux_nids = snd_hdac_get_connections(&hdac->hdac, pin->nid,
+			pin->mux_nids, HDA_MAX_CONNECTIONS);
+	if (pin->num_mux_nids == 0)
+		dev_warn(&hdac->hdac.dev, "No connections found for pin: %d\n", pin->nid);
+
+	dev_dbg(&hdac->hdac.dev, "num_mux_nids %d for pin: %d\n",
+			pin->num_mux_nids, pin->nid);
+
+	return pin->num_mux_nids;
+}
+
+static inline struct hdac_hdmi_pin *hdac_hdmi_get_pin(
+			struct hdac_ext_device *edev,
+			struct snd_soc_dapm_path *p,
+			struct hdac_hdmi_cvt *cvt)
+{
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_pin *pin;
+	hda_nid_t *nid;
+	int ret, i;
+
+	nid = (hda_nid_t *)p->sink->priv;
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		if (pin->nid == *nid) {
+			ret = hdac_hdmi_query_pin_connlist(edev, pin);
+			if (ret < 0)
+				continue;
+
+			for (i = 0; i < pin->num_mux_nids; i++) {
+				if (pin->mux_nids[i] == cvt->nid)
+					return pin;
+			}
+		}
+	}
+
+	return NULL;
+}
+
+/*
+ * This queries mux widgets in each sink path of the dai widget and returns
+ * a matching pin widget to which the stream may be routed.
+ *
+ * The converter may be input to multiple pin muxes. So each
+ * pin mux (basically each pin widget) is queried to identify if
+ * the converter as one of the input, then the first pin match
+ * is selected for rendering.
+ *
+ * Same stream rendering to multiple pins simultaneously can be done
+ * possibly, but not supported for now.
+ *
+ * So return the first pin connected
+ */
+static struct hdac_hdmi_pin *hdac_hdmi_get_pin_from_daistream(
+			struct hdac_ext_device *edev,
+			struct snd_soc_dapm_widget *strm_w,
+			struct hdac_hdmi_cvt *cvt)
+{
+	struct snd_soc_dapm_path *p;
+
+	snd_soc_dapm_widget_for_each_sink_path(strm_w, p) {
+		if (!p->connect)
+			continue;
+
+		if (strstr(p->sink->name, "Mux"))
+			return hdac_hdmi_get_pin(edev, p, cvt);
+		else
+			return hdac_hdmi_get_pin_from_daistream(edev, p->sink, cvt);
+	}
+
+	return NULL;
+}
+
 static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 			struct snd_soc_dai *dai)
 {
 	struct hdac_ext_device *hdac = snd_soc_dai_get_drvdata(dai);
 	struct hdac_hdmi_priv *hdmi = hdac->private_data;
 	struct hdac_hdmi_dai_pin_map *dai_map;
+	struct hdac_hdmi_cvt *cvt;
+	struct hdac_hdmi_pin *pin;
+	int ret;
 
 	if (dai->id > 0) {
 		dev_err(&hdac->hdac.dev, "Only one dai supported as of now\n");
@@ -346,18 +462,23 @@ static int hdac_hdmi_pcm_open(struct snd_pcm_substream *substream,
 
 	dai_map = &hdmi->dai_map[dai->id];
 
-	if ((!dai_map->pin->eld.monitor_present) ||
-		(!dai_map->pin->eld.eld_valid)) {
+	cvt = dai_map->cvt;
+	pin = hdac_hdmi_get_pin_from_daistream(hdac, dai->playback_widget, cvt);
+	if (!pin)
+		return -EIO;
+
+	if ((!pin->eld.monitor_present) ||
+		(!pin->eld.eld_valid)) {
 		dev_err(&hdac->hdac.dev, "Failed: montior present? %d eld valid?: %d\n",
-				dai_map->pin->eld.monitor_present,
-				dai_map->pin->eld.eld_valid);
-		return -ENODEV;
+				pin->eld.monitor_present, pin->eld.eld_valid);
+		return -EINVAL;
 	}
 
-	hdac_hdmi_set_power_state(hdac, dai_map, AC_PWRST_D0);
+	dai_map->pin = pin;
 
-	snd_hdac_codec_write(&hdac->hdac, dai_map->pin->nid, 0,
-			AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_UNMUTE);
+	ret = hdac_hdmi_enable_pin(hdac, dai_map);
+	if (ret < 0)
+		return ret;
 
 	return snd_pcm_hw_constraint_eld(substream->runtime,
 			dai_map->pin->eld.eld_buffer);
@@ -376,6 +497,8 @@ static void hdac_hdmi_pcm_close(struct snd_pcm_substream *substream,
 
 	snd_hdac_codec_write(&hdac->hdac, dai_map->pin->nid, 0,
 			AC_VERB_SET_AMP_GAIN_MUTE, AMP_OUT_MUTE);
+
+	dai_map->pin = NULL;
 }
 
 static int
@@ -398,28 +521,6 @@ hdac_hdmi_query_cvt_params(struct hdac_device *hdac, struct hdac_hdmi_cvt *cvt)
 	return err;
 }
 
-static int hdac_hdmi_query_pin_connlist(struct hdac_ext_device *hdac,
-					struct hdac_hdmi_pin *pin)
-{
-	if (!(get_wcaps(&hdac->hdac, pin->nid) & AC_WCAP_CONN_LIST)) {
-		dev_warn(&hdac->hdac.dev,
-			"HDMI: pin %d wcaps %#x does not support connection list\n",
-			pin->nid, get_wcaps(&hdac->hdac, pin->nid));
-		return -EINVAL;
-	}
-
-	pin->num_mux_nids = snd_hdac_get_connections(&hdac->hdac, pin->nid,
-			pin->mux_nids, HDA_MAX_CONNECTIONS);
-	if (pin->num_mux_nids == 0)
-		dev_warn(&hdac->hdac.dev, "No connections found for pin: %d\n",
-								pin->nid);
-
-	dev_dbg(&hdac->hdac.dev, "num_mux_nids %d for pin: %d\n",
-			pin->num_mux_nids, pin->nid);
-
-	return pin->num_mux_nids;
-}
-
 static void hdac_hdmi_fill_widget_info(struct device *dev,
 				struct snd_soc_dapm_widget *w,
 				enum snd_soc_dapm_type id, void *priv,
@@ -643,40 +744,33 @@ static int create_fill_widget_route_map(struct snd_soc_dapm_context *dapm)
 static int hdac_hdmi_init_dai_map(struct hdac_ext_device *edev)
 {
 	struct hdac_hdmi_priv *hdmi = edev->private_data;
-	struct hdac_hdmi_dai_pin_map *dai_map = &hdmi->dai_map[0];
+	struct hdac_hdmi_dai_pin_map *dai_map;
 	struct hdac_hdmi_cvt *cvt;
-	struct hdac_hdmi_pin *pin;
+	int dai_id = 0;
 
-	if (list_empty(&hdmi->cvt_list) || list_empty(&hdmi->pin_list))
+	if (list_empty(&hdmi->cvt_list))
 		return -EINVAL;
 
-	/*
-	 * Currently on board only 1 pin and 1 converter is enabled for
-	 * simplification, more will be added eventually
-	 * So using fixed map for dai_id:pin:cvt
-	 */
-	cvt = list_first_entry(&hdmi->cvt_list, struct hdac_hdmi_cvt, head);
-	pin = list_first_entry(&hdmi->pin_list, struct hdac_hdmi_pin, head);
-
-	dai_map->dai_id = 0;
-	dai_map->pin = pin;
-
-	dai_map->cvt = cvt;
+	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
+		dai_map = &hdmi->dai_map[dai_id];
+		dai_map->dai_id = dai_id;
+		dai_map->cvt = cvt;
 
-	/* Enable out path for this pin widget */
-	snd_hdac_codec_write(&edev->hdac, pin->nid, 0,
-			AC_VERB_SET_PIN_WIDGET_CONTROL, PIN_OUT);
+		/* Enable transmission */
+		snd_hdac_codec_write(&edev->hdac, cvt->nid, 0,
+				AC_VERB_SET_DIGI_CONVERT_1, 1);
 
-	/* Enable transmission */
-	snd_hdac_codec_write(&edev->hdac, cvt->nid, 0,
-			AC_VERB_SET_DIGI_CONVERT_1, 1);
+		/* Category Code (CC) to zero */
+		snd_hdac_codec_write(&edev->hdac, cvt->nid, 0,
+				AC_VERB_SET_DIGI_CONVERT_2, 0);
 
-	/* Category Code (CC) to zero */
-	snd_hdac_codec_write(&edev->hdac, cvt->nid, 0,
-			AC_VERB_SET_DIGI_CONVERT_2, 0);
+		dai_id++;
 
-	snd_hdac_codec_write(&edev->hdac, pin->nid, 0,
-			AC_VERB_SET_CONNECT_SEL, 0);
+		if (dai_id == HDA_MAX_CVTS) {
+			dev_warn(&edev->hdac.dev, "Max dais supported: %d\n", dai_id);
+			break;
+		}
+	}
 
 	return 0;
 }
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 11/14] drm/edid: Add API to help find connection type

[Subhransu S. Prusty]

To fill the audio infoframe it is required to identify the
connection type as DP or HDMI. This patch adds an API which
parses ELD and returns the display type of connected.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Cc: David Airlie <airlied@linux.ie>
Cc: dri-devel@lists.freedesktop.org
Cc: Daniel Vetter <daniel.vetter@intel.com>
---
 include/drm/drm_edid.h | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
index 2af9769..072de90 100644
--- a/include/drm/drm_edid.h
+++ b/include/drm/drm_edid.h
@@ -403,6 +403,18 @@ static inline int drm_eld_size(const uint8_t *eld)
 	return DRM_ELD_HEADER_BLOCK_SIZE + eld[DRM_ELD_BASELINE_ELD_LEN] * 4;
 }
 
+/**
+ * drm_eld_get_conn_type - Get device type hdmi/dp connected
+ * @eld: pointer to an eld memory structure
+ *
+ * The caller need to use DRM_ELD_CONN_TYPE_HDMI or DRM_ELD_CONN_TYPE_DP to
+ * identify the display type connected.
+ */
+static inline u8 drm_eld_get_conn_type(const uint8_t *eld)
+{
+	return eld[DRM_ELD_SAD_COUNT_CONN_TYPE] & DRM_ELD_CONN_TYPE_MASK;
+}
+
 struct edid *drm_do_get_edid(struct drm_connector *connector,
 	int (*get_edid_block)(void *data, u8 *buf, unsigned int block,
 			      size_t len),
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 12/14] ASoC: hdac_hdmi: Add infoframe support for dp audio

[Subhransu S. Prusty]

This uses the get_conn_type API added in the previous patch to
identify the type of display connected and fills the infoframe
accordingly.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 68 ++++++++++++++++++++++++++++++++++++++------
 1 file changed, 59 insertions(+), 9 deletions(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 3ac3498..d963d92 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -22,6 +22,7 @@
 #include <linux/module.h>
 #include <linux/pm_runtime.h>
 #include <linux/hdmi.h>
+#include <drm/drm_edid.h>
 #include <sound/pcm_params.h>
 #include <sound/soc.h>
 #include <sound/hdaudio_ext.h>
@@ -201,27 +202,70 @@ hdac_hdmi_set_dip_index(struct hdac_ext_device *hdac, hda_nid_t pin_nid,
 				AC_VERB_SET_HDMI_DIP_INDEX, val);
 }
 
+struct dp_audio_infoframe {
+	u8 type; /* 0x84 */
+	u8 len;  /* 0x1b */
+	u8 ver;  /* 0x11 << 2 */
+
+	u8 CC02_CT47;	/* match with HDMI infoframe from this on */
+	u8 SS01_SF24;
+	u8 CXT04;
+	u8 CA;
+	u8 LFEPBL01_LSV36_DM_INH7;
+};
+
 static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *hdac,
 				hda_nid_t cvt_nid, hda_nid_t pin_nid)
 {
 	uint8_t buffer[HDMI_INFOFRAME_HEADER_SIZE + HDMI_AUDIO_INFOFRAME_SIZE];
 	struct hdmi_audio_infoframe frame;
+	struct dp_audio_infoframe dp_ai;
+	struct hdac_hdmi_priv *hdmi = hdac->private_data;
+	struct hdac_hdmi_pin *pin;
 	u8 *dip = (u8 *)&frame;
 	int ret;
 	int i;
+	const u8 *eld_buf;
+	u8 conn_type;
+	int channels = 2;
 
-	hdmi_audio_infoframe_init(&frame);
+	list_for_each_entry(pin, &hdmi->pin_list, head) {
+		if (pin->nid == pin_nid)
+			break;
+	}
 
-	/* Default stereo for now */
-	frame.channels = 2;
+	eld_buf = pin->eld.eld_buffer;
+	conn_type = drm_eld_get_conn_type(eld_buf);
 
 	/* setup channel count */
 	snd_hdac_codec_write(&hdac->hdac, cvt_nid, 0,
-			    AC_VERB_SET_CVT_CHAN_COUNT, frame.channels - 1);
+			    AC_VERB_SET_CVT_CHAN_COUNT, channels - 1);
 
-	ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
-	if (ret < 0)
-		return ret;
+	if (conn_type == DRM_ELD_CONN_TYPE_HDMI) {
+		hdmi_audio_infoframe_init(&frame);
+
+		/* Default stereo for now */
+		frame.channels = channels;
+
+		ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
+		if (ret < 0)
+			return ret;
+
+		dip = (u8 *)&frame;
+
+	} else if (conn_type == DRM_ELD_CONN_TYPE_DP) {
+		memset(&dp_ai, 0, sizeof(dp_ai));
+		dp_ai.type	= 0x84;
+		dp_ai.len	= 0x1b;
+		dp_ai.ver	= 0x11 << 2;
+		dp_ai.CC02_CT47	= channels - 1;
+		dp_ai.CA	= 0;
+
+		dip = (u8 *)&dip;
+	} else {
+		dev_err(&hdac->hdac.dev, "Invalid connection type: %d\n", conn_type);
+		return -EIO;
+	}
 
 	/* stop infoframe transmission */
 	hdac_hdmi_set_dip_index(hdac, pin_nid, 0x0, 0x0);
@@ -231,9 +275,15 @@ static int hdac_hdmi_setup_audio_infoframe(struct hdac_ext_device *hdac,
 
 	/*  Fill infoframe. Index auto-incremented */
 	hdac_hdmi_set_dip_index(hdac, pin_nid, 0x0, 0x0);
-	for (i = 0; i < sizeof(frame); i++)
-		snd_hdac_codec_write(&hdac->hdac, pin_nid, 0,
+	if (conn_type == 0) {
+		for (i = 0; i < sizeof(frame); i++)
+			snd_hdac_codec_write(&hdac->hdac, pin_nid, 0,
 				AC_VERB_SET_HDMI_DIP_DATA, dip[i]);
+	} else {
+		for (i = 0; i < sizeof(dp_ai); i++)
+			snd_hdac_codec_write(&hdac->hdac, pin_nid, 0,
+				AC_VERB_SET_HDMI_DIP_DATA, dip[i]);
+	}
 
 	/* Start infoframe */
 	hdac_hdmi_set_dip_index(hdac, pin_nid, 0x0, 0x0);
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 13/14] ASoC: hdac_hdmi: Add codec suspend/resume handler

[Subhransu S. Prusty]

From: Jeeja KP <jeeja.kp@intel.com>

Need to add enabling of all pins and DP1.2 feature again after
resume. Also during the device in suspended state ELD notify
callback is not processed. So add ELD check for all pins here.

Signed-off-by: Jeeja KP <jeeja.kp@intel.com>
Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 25 +++++++++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index d963d92..73f5612 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1186,9 +1186,34 @@ static int hdmi_codec_remove(struct snd_soc_codec *codec)
 	return 0;
 }
 
+#ifdef CONFIG_PM
+static int hdmi_codec_resume(struct snd_soc_codec *codec)
+{
+	struct hdac_ext_device *edev = snd_soc_codec_get_drvdata(codec);
+	struct hdac_hdmi_priv *hdmi = edev->private_data;
+	struct hdac_hdmi_pin *pin;
+
+	hdac_hdmi_skl_enable_all_pins(&edev->hdac);
+	hdac_hdmi_skl_enable_dp12(&edev->hdac);
+
+	/*
+	 * As the ELD notify callback request is not entertained while the
+	 * device is in suspend state. Need to manually check detection of
+	 * all pins here.
+	 */
+	list_for_each_entry(pin, &hdmi->pin_list, head)
+		hdac_hdmi_present_sense(pin, 1);
+
+	return 0;
+}
+#else
+#define hdmi_codec_resume NULL
+#endif
+
 static struct snd_soc_codec_driver hdmi_hda_codec = {
 	.probe		= hdmi_codec_probe,
 	.remove		= hdmi_codec_remove,
+	.resume		= hdmi_codec_resume,
 	.idle_bias_off	= true,
 };
 
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

[PATCH v2 14/14] ASoC: hdac_hdmi: Fix to keep display active while enumerating codec

[Subhransu S. Prusty]

From: Ramesh Babu <ramesh.babu@intel.com>

The display power reference count is decremented with the first
explicit call to pm_runtime_suspend. Otherwise the display power
reference count is balanced with runtime resume/suspend. Rest
of the time it is kept off.

Signed-off-by: Ramesh Babu <ramesh.babu@intel.com>
Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
---
 sound/soc/codecs/hdac_hdmi.c | 12 ++++++++++++
 1 file changed, 12 insertions(+)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index 73f5612..fb43461 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -1236,6 +1236,18 @@ static int hdac_hdmi_dev_probe(struct hdac_ext_device *edev)
 	INIT_LIST_HEAD(&hdmi_priv->pin_list);
 	INIT_LIST_HEAD(&hdmi_priv->cvt_list);
 
+	/*
+	 * Turned off in the runtime_suspend during the first explicit
+	 * pm_runtime_suspend call.
+	 */
+	ret = snd_hdac_display_power(edev->hdac.bus, true);
+	if (ret < 0) {
+		dev_err(&edev->hdac.dev,
+			"Cannot turn on display power on i915 err: %d\n",
+			ret);
+		return ret;
+	}
+
 	ret = hdac_hdmi_parse_and_map_nid(edev, &hdmi_dais, &num_dais);
 	if (ret < 0) {
 		dev_err(&codec->dev, "Failed in parse and map nid with err: %d\n", ret);
-- 
1.9.1

_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Takashi Iwai]

On Fri, 04 Dec 2015 12:08:26 +0100,
Subhransu S. Prusty wrote:
> 
> On Thu, Dec 03, 2015 at 04:57:14PM +0100, Takashi Iwai wrote:
> > On Thu, 03 Dec 2015 22:08:53 +0100,
> > Subhransu S. Prusty wrote:
> > > 
> > > Setting the constraint format based on ELD was missing bit in
> > > the sound/core pcm drm. Added with this patch.
> > 
> > No, you can't define these here.  The format really depends on the
> > hardware, while the rate and the channels are independent.
> 
> Probably then I will move this definition to driver.
> 
> > How do you know it's little-endian?  And why it must be S24_LE for
> > 24bit, not S32_LE?
> 
> Regarding the little-endian, In the driver I think I should set the
> constraint for both LE and BE. And the platform as it only supports LE alone
> it will set the constraint accordingly and edianness will be taken care of.
> 
> Regarding the sample size, from short audio descriptor, the samples can be
> one of 16/20/24 bit. I could use the format bits for 16 and 24 bits but
> don't know which format bits macro is suitable for 20bits. So kept it as
> S32_LE for 20bits. Should I fix the format bits for 20bits to use S24?

No you seem misunderstanding the concept...


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 03/14] ASoC: hdac_hdmi - Use list to add pins and converters

[Subhransu S. Prusty]

On Thu, Dec 03, 2015 at 04:44:55PM +0100, Takashi Iwai wrote:
> On Thu, 03 Dec 2015 22:08:51 +0100,
> Subhransu S. Prusty wrote:
> >  static int hdac_hdmi_dev_remove(struct hdac_ext_device *edev)
> >  {
> > +	struct hdac_hdmi_priv *hdmi = edev->private_data;
> > +	struct hdac_hdmi_pin *pin;
> > +	struct hdac_hdmi_cvt *cvt;
> > +
> >  	snd_soc_unregister_codec(&edev->hdac.dev);
> >  
> > +	list_for_each_entry(cvt, &hdmi->cvt_list, head) {
> > +		list_del(&cvt->head);
> > +		kfree(cvt);
> > +	}
> > +
> > +	list_for_each_entry(pin, &hdmi->pin_list, head) {
> > +		list_del(&pin->head);
> > +		kfree(pin);
> > +	}
> 
> These must be list_for_each_entry_safe().

Sure. Will change it.

Regards,
Subhransu
> 
> 
> Takashi

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 04/14] ASoC: hdac_hdmi: Add hotplug notification and read eld

[Subhransu S. Prusty]

On Thu, Dec 03, 2015 at 04:51:37PM +0100, Takashi Iwai wrote:
> On Thu, 03 Dec 2015 22:08:52 +0100,
> Subhransu S. Prusty wrote:
> > 
> > This patch uses i915 component framework to register for hotplug
> > notification. And once it identifies valid pin sense and valid eld,
> > reads the eld into the corresponding pin map buffer. For now it
> > directly sends the verbs and reads the eld. Later this will use
> > the i915 framework to populate ELD buffer once available.
> > 
> > The eld reading APIs in legacy hda are required for ASoC skylake
> > hdmi driver as well. So keeping a copy here and will remove once
> > component ops for reading ELD are merged in hda core.
> > 
> > Also read the monitor present sense during resume and ignore the
> > ELD notify from graphics during PM as is done in legacy hda.
> > Reference commits:
> > 
> > git: git://git.kernel.org/pub/scm/linux/kernel/git/tiwai/sound.git
> > 
> > commit 33d58f2bb446 ("ALSA: hda - Skip ELD notification during PM
> > process")
> 
> This one isn't merged yet, so the commit ID may be wrong.
> Maybe I'm going to merge this one at first to for-next branch,
> irrelevant from test/hdmi-jack branch.  So drop it from the
> description for now.

Ok.

> 
> > commit 8ae743e82f0b ("ALSA: hda - Skip ELD notification during
> > system suspend")
> 
> This one is already solid.
> 
> 
> Takashi

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 11/14] drm/edid: Add API to help find connection type

[Subhransu S. Prusty]

On Thu, Dec 03, 2015 at 05:16:34PM +0100, Takashi Iwai wrote:
> On Thu, 03 Dec 2015 22:08:59 +0100,
> Subhransu S. Prusty wrote:
> > 
> > To fill the audio infoframe it is required to identify the
> > connection type as DP or HDMI. This patch adds an API which
> > parses ELD and returns the display type of connected.
> > 
> > Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
> > Signed-off-by: Vinod Koul <vinod.koul@intel.com>
> > Cc: David Airlie <airlied@linux.ie>
> > Cc: dri-devel@lists.freedesktop.org
> > Cc: Daniel Vetter <daniel.vetter@intel.com>
> > ---
> >  include/drm/drm_edid.h | 12 ++++++++++++
> >  1 file changed, 12 insertions(+)
> > 
> > diff --git a/include/drm/drm_edid.h b/include/drm/drm_edid.h
> > index 2af9769..072de90 100644
> > --- a/include/drm/drm_edid.h
> > +++ b/include/drm/drm_edid.h
> > @@ -403,6 +403,18 @@ static inline int drm_eld_size(const uint8_t *eld)
> >  	return DRM_ELD_HEADER_BLOCK_SIZE + eld[DRM_ELD_BASELINE_ELD_LEN] * 4;
> >  }
> >  
> > +/**
> > + * drm_eld_get_conn_type - Get device type hdmi/dp connected
> > + * @eld: pointer to an eld memory structure
> > + *
> > + * The caller need to use DRM_ELD_CONN_TYPE_HDMI or DRM_ELD_CONN_TYPE_DP to
> > + * identify the display type connected.
> 
> Constants should be marked with '%'.

Sure will add it. 

Regards,
Subhransu
> 
> 
> Takashi

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 12/14] ASoC: hdac_hdmi: Add infoframe support for dp audio

[Subhransu S. Prusty]

On Thu, Dec 03, 2015 at 05:13:16PM +0000, Daniel Stone wrote:
> Hi Subhransu,
> 
> On 3 December 2015 at 21:09, Subhransu S. Prusty
> <subhransu.s.prusty@intel.com> wrote:
> > +       if (conn_type == DRM_ELD_CONN_TYPE_HDMI) {
> > +               hdmi_audio_infoframe_init(&frame);
> > +
> > +               /* Default stereo for now */
> > +               frame.channels = channels;
> > +
> > +               ret = hdmi_audio_infoframe_pack(&frame, buffer, sizeof(buffer));
> > +               if (ret < 0)
> > +                       return ret;
> > +
> > +               dip = (u8 *)&frame;
> > +
> > +       } else if (conn_type == DRM_ELD_CONN_TYPE_DP) {
> > +               memset(&dp_ai, 0, sizeof(dp_ai));
> > +               dp_ai.type      = 0x84;
> > +               dp_ai.len       = 0x1b;
> > +               dp_ai.ver       = 0x11 << 2;
> > +               dp_ai.CC02_CT47 = channels - 1;
> > +               dp_ai.CA        = 0;
> > +
> > +               dip = (u8 *)&dip;
> 
> Surely this should be dip = (u8 *) &dp_ai, instead of pointing to itself?

Thanks for pointing. It's a mistake, will fix it.

Regards,
Subhansu
> 
> Cheers,
> Daniel
> 

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Subhransu S. Prusty]

On Thu, Dec 03, 2015 at 04:57:14PM +0100, Takashi Iwai wrote:
> On Thu, 03 Dec 2015 22:08:53 +0100,
> Subhransu S. Prusty wrote:
> > 
> > Setting the constraint format based on ELD was missing bit in
> > the sound/core pcm drm. Added with this patch.
> 
> No, you can't define these here.  The format really depends on the
> hardware, while the rate and the channels are independent.

Probably then I will move this definition to driver.

> How do you know it's little-endian?  And why it must be S24_LE for
> 24bit, not S32_LE?

Regarding the little-endian, In the driver I think I should set the
constraint for both LE and BE. And the platform as it only supports LE alone
it will set the constraint accordingly and edianness will be taken care of.

Regarding the sample size, from short audio descriptor, the samples can be
one of 16/20/24 bit. I could use the format bits for 16 and 24 bits but
don't know which format bits macro is suitable for 20bits. So kept it as
S32_LE for 20bits. Should I fix the format bits for 20bits to use S24?

Regards,
Subhransu

> 
> 
> Takashi

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Takashi Iwai]

On Sat, 05 Dec 2015 12:27:03 +0100,
Subhransu S. Prusty wrote:
> 
> On Fri, Dec 04, 2015 at 06:59:19AM +0100, Takashi Iwai wrote:
> > On Fri, 04 Dec 2015 12:08:26 +0100,
> > Subhransu S. Prusty wrote:
> > > 
> > > On Thu, Dec 03, 2015 at 04:57:14PM +0100, Takashi Iwai wrote:
> > > > On Thu, 03 Dec 2015 22:08:53 +0100,
> > > > Subhransu S. Prusty wrote:
> > > > > 
> > > > > Setting the constraint format based on ELD was missing bit in
> > > > > the sound/core pcm drm. Added with this patch.
> > > > 
> > > > No, you can't define these here.  The format really depends on the
> > > > hardware, while the rate and the channels are independent.
> > > 
> > > Probably then I will move this definition to driver.
> > > 
> > > > How do you know it's little-endian?  And why it must be S24_LE for
> > > > 24bit, not S32_LE?
> > > 
> > > Regarding the little-endian, In the driver I think I should set the
> > > constraint for both LE and BE. And the platform as it only supports LE alone
> > > it will set the constraint accordingly and edianness will be taken care of.
> > > 
> > > Regarding the sample size, from short audio descriptor, the samples can be
> > > one of 16/20/24 bit. I could use the format bits for 16 and 24 bits but
> > > don't know which format bits macro is suitable for 20bits. So kept it as
> > > S32_LE for 20bits. Should I fix the format bits for 20bits to use S24?
> > 
> > No you seem misunderstanding the concept...
> 
> Sorry about that. 
> 
> I re-read the spec, it doesn't mention the container size for the samples.
> Assuming the container will be 32 bits, then I think we should use S24_LE
> for both 20 and 24 bits.

You can't limit easily from the supported bits.  In theory, all
formats that may fit with the given bit should be set.  For example, 
for a 20bit sample, S24, U24, S32, U32, S24_3, U24_3, S20_3, etc would
match, and even for both endianess.

The format type doesn't specify only the *max* bit it can pack, but
also only the position of bits to be packed.  For example, S24 packs
max 24 bits in the lower 24 bits in a 32bit container.  And, S24_3
packs max 24 bits in a 24bit container.  Most of Intel chips takes the
upper bits in a container, so usually they need S32 or S16 no matter
how many bits are used.


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Takashi Iwai]

On Sat, 05 Dec 2015 15:05:49 +0100,
Subhransu S. Prusty wrote:
> 
> On Sat, Dec 05, 2015 at 09:12:34AM +0100, Takashi Iwai wrote:
> > On Sat, 05 Dec 2015 12:27:03 +0100,
> > Subhransu S. Prusty wrote:
> > > 
> > > On Fri, Dec 04, 2015 at 06:59:19AM +0100, Takashi Iwai wrote:
> > > > On Fri, 04 Dec 2015 12:08:26 +0100,
> > > > Subhransu S. Prusty wrote:
> > > > > 
> > > > > On Thu, Dec 03, 2015 at 04:57:14PM +0100, Takashi Iwai wrote:
> > > > > > On Thu, 03 Dec 2015 22:08:53 +0100,
> > > > > > Subhransu S. Prusty wrote:
> > > > > > > 
> > > > > > > Setting the constraint format based on ELD was missing bit in
> > > > > > > the sound/core pcm drm. Added with this patch.
> > > > > > 
> > > > > > No, you can't define these here.  The format really depends on the
> > > > > > hardware, while the rate and the channels are independent.
> > > > > 
> > > > > Probably then I will move this definition to driver.
> > > > > 
> > > > > > How do you know it's little-endian?  And why it must be S24_LE for
> > > > > > 24bit, not S32_LE?
> > > > > 
> > > > > Regarding the little-endian, In the driver I think I should set the
> > > > > constraint for both LE and BE. And the platform as it only supports LE alone
> > > > > it will set the constraint accordingly and edianness will be taken care of.
> > > > > 
> > > > > Regarding the sample size, from short audio descriptor, the samples can be
> > > > > one of 16/20/24 bit. I could use the format bits for 16 and 24 bits but
> > > > > don't know which format bits macro is suitable for 20bits. So kept it as
> > > > > S32_LE for 20bits. Should I fix the format bits for 20bits to use S24?
> > > > 
> > > > No you seem misunderstanding the concept...
> > > 
> > > Sorry about that. 
> > > 
> > > I re-read the spec, it doesn't mention the container size for the samples.
> > > Assuming the container will be 32 bits, then I think we should use S24_LE
> > > for both 20 and 24 bits.
> > 
> > You can't limit easily from the supported bits.  In theory, all
> > formats that may fit with the given bit should be set.  For example, 
> > for a 20bit sample, S24, U24, S32, U32, S24_3, U24_3, S20_3, etc would
> > match, and even for both endianess.
> > 
> > The format type doesn't specify only the *max* bit it can pack, but
> > also only the position of bits to be packed.  For example, S24 packs
> > max 24 bits in the lower 24 bits in a 32bit container.  And, S24_3
> > packs max 24 bits in a 24bit container.  Most of Intel chips takes the
> > upper bits in a container, so usually they need S32 or S16 no matter
> > how many bits are used.
> 
> Thanks for the quick reply.
> 
> I am thinking to set the format as S16 for 16bits and S32 for 20/24bits.
> 
> But then we can set S32 for everything as well including 16bits.
> 
> What do you recommend?

In general it's better to use S16 for 16bits.

The problem is that you tried to put in the generic code where you
can't know the exact condition in the controller side.  Actually the
legacy HDA driver sets the formats constraint, too, but it at least
knows that the HDA controller may support only S16_LE and S32_LE.

That said, rather implement it locally instead of pcm_drm_eld.c.


Takashi
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Subhransu S. Prusty]

On Fri, Dec 04, 2015 at 06:59:19AM +0100, Takashi Iwai wrote:
> On Fri, 04 Dec 2015 12:08:26 +0100,
> Subhransu S. Prusty wrote:
> > 
> > On Thu, Dec 03, 2015 at 04:57:14PM +0100, Takashi Iwai wrote:
> > > On Thu, 03 Dec 2015 22:08:53 +0100,
> > > Subhransu S. Prusty wrote:
> > > > 
> > > > Setting the constraint format based on ELD was missing bit in
> > > > the sound/core pcm drm. Added with this patch.
> > > 
> > > No, you can't define these here.  The format really depends on the
> > > hardware, while the rate and the channels are independent.
> > 
> > Probably then I will move this definition to driver.
> > 
> > > How do you know it's little-endian?  And why it must be S24_LE for
> > > 24bit, not S32_LE?
> > 
> > Regarding the little-endian, In the driver I think I should set the
> > constraint for both LE and BE. And the platform as it only supports LE alone
> > it will set the constraint accordingly and edianness will be taken care of.
> > 
> > Regarding the sample size, from short audio descriptor, the samples can be
> > one of 16/20/24 bit. I could use the format bits for 16 and 24 bits but
> > don't know which format bits macro is suitable for 20bits. So kept it as
> > S32_LE for 20bits. Should I fix the format bits for 20bits to use S24?
> 
> No you seem misunderstanding the concept...

Sorry about that. 

I re-read the spec, it doesn't mention the container size for the samples.
Assuming the container will be 32 bits, then I think we should use S24_LE
for both 20 and 24 bits.

Can you please help to understand which concept I got wrong here.

Regards,
Subhransu
> 
> 
> Takashi

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Re: [PATCH v2 05/14] ALSA: pcm: Add DRM helper to set constraint for format

[Subhransu S. Prusty]

On Sat, Dec 05, 2015 at 09:12:34AM +0100, Takashi Iwai wrote:
> On Sat, 05 Dec 2015 12:27:03 +0100,
> Subhransu S. Prusty wrote:
> > 
> > On Fri, Dec 04, 2015 at 06:59:19AM +0100, Takashi Iwai wrote:
> > > On Fri, 04 Dec 2015 12:08:26 +0100,
> > > Subhransu S. Prusty wrote:
> > > > 
> > > > On Thu, Dec 03, 2015 at 04:57:14PM +0100, Takashi Iwai wrote:
> > > > > On Thu, 03 Dec 2015 22:08:53 +0100,
> > > > > Subhransu S. Prusty wrote:
> > > > > > 
> > > > > > Setting the constraint format based on ELD was missing bit in
> > > > > > the sound/core pcm drm. Added with this patch.
> > > > > 
> > > > > No, you can't define these here.  The format really depends on the
> > > > > hardware, while the rate and the channels are independent.
> > > > 
> > > > Probably then I will move this definition to driver.
> > > > 
> > > > > How do you know it's little-endian?  And why it must be S24_LE for
> > > > > 24bit, not S32_LE?
> > > > 
> > > > Regarding the little-endian, In the driver I think I should set the
> > > > constraint for both LE and BE. And the platform as it only supports LE alone
> > > > it will set the constraint accordingly and edianness will be taken care of.
> > > > 
> > > > Regarding the sample size, from short audio descriptor, the samples can be
> > > > one of 16/20/24 bit. I could use the format bits for 16 and 24 bits but
> > > > don't know which format bits macro is suitable for 20bits. So kept it as
> > > > S32_LE for 20bits. Should I fix the format bits for 20bits to use S24?
> > > 
> > > No you seem misunderstanding the concept...
> > 
> > Sorry about that. 
> > 
> > I re-read the spec, it doesn't mention the container size for the samples.
> > Assuming the container will be 32 bits, then I think we should use S24_LE
> > for both 20 and 24 bits.
> 
> You can't limit easily from the supported bits.  In theory, all
> formats that may fit with the given bit should be set.  For example, 
> for a 20bit sample, S24, U24, S32, U32, S24_3, U24_3, S20_3, etc would
> match, and even for both endianess.
> 
> The format type doesn't specify only the *max* bit it can pack, but
> also only the position of bits to be packed.  For example, S24 packs
> max 24 bits in the lower 24 bits in a 32bit container.  And, S24_3
> packs max 24 bits in a 24bit container.  Most of Intel chips takes the
> upper bits in a container, so usually they need S32 or S16 no matter
> how many bits are used.

Thanks for the quick reply.

I am thinking to set the format as S16 for 16bits and S32 for 20/24bits.

But then we can set S32 for everything as well including 16bits.

What do you recommend?


> 
> 
> Takashi

-- 
_______________________________________________
dri-devel mailing list
dri-devel@lists.freedesktop.org
http://lists.freedesktop.org/mailman/listinfo/dri-devel

Applied "ASoC: hdac_hdmi: Fix to check num nodes correctly" to the asoc tree

[Mark Brown]

The patch

   ASoC: hdac_hdmi: Fix to check num nodes correctly

has been applied to the asoc tree at

   git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git 

All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.  

You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.

If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.

Please add any relevant lists and maintainers to the CCs when replying
to this mail.

Thanks,
Mark

>From 541140d43046ccd4e7b511846d22b3d3ca7367f3 Mon Sep 17 00:00:00 2001
From: "Subhransu S. Prusty" <subhransu.s.prusty@intel.com>
Date: Wed, 9 Dec 2015 21:46:08 +0530
Subject: [PATCH] ASoC: hdac_hdmi: Fix to check num nodes correctly

commit 3c83ac23253c ("ASoC: hdac_hdmi: check error return") fixes
the static checker warning reported by Dan Carpenter:

	sound/soc/codecs/hdac_hdmi.c:416 hdac_hdmi_parse_and_map_nid()
	warn: unsigned 'hdac->num_nodes' is never less than zero.

But it doesn't fix the issue completely.

It's also a failure if no sub nodes found for an afg node. So modify
the return condition appropriately.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/hdac_hdmi.c | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index b999fb2a463b..e6dc4cd037d3 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -415,7 +415,7 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	int cvt_nid = 0, pin_nid = 0;
 
 	num_nodes = snd_hdac_get_sub_nodes(hdac, hdac->afg, &nid);
-	if (!nid || num_nodes < 0) {
+	if (!nid || num_nodes <= 0) {
 		dev_warn(&hdac->dev, "HDMI: failed to get afg sub nodes\n");
 		return -EINVAL;
 	}
-- 
2.7.0.rc3

Applied "ASoC: hdac_hdmi: Enable DP1.2 and all converters/pins" to the asoc tree

[Mark Brown]

The patch

   ASoC: hdac_hdmi: Enable DP1.2 and all converters/pins

has been applied to the asoc tree at

   git://git.kernel.org/pub/scm/linux/kernel/git/broonie/sound.git 

All being well this means that it will be integrated into the linux-next
tree (usually sometime in the next 24 hours) and sent to Linus during
the next merge window (or sooner if it is a bug fix), however if
problems are discovered then the patch may be dropped or reverted.  

You may get further e-mails resulting from automated or manual testing
and review of the tree, please engage with people reporting problems and
send followup patches addressing any issues that are reported if needed.

If any updates are required or you are submitting further changes they
should be sent as incremental updates against current git, existing
patches will not be replaced.

Please add any relevant lists and maintainers to the CCs when replying
to this mail.

Thanks,
Mark

>From 211caab73b20dcc91ac103db0f68fe2388120d59 Mon Sep 17 00:00:00 2001
From: "Subhransu S. Prusty" <subhransu.s.prusty@intel.com>
Date: Fri, 12 Feb 2016 07:46:03 +0530
Subject: [PATCH] ASoC: hdac_hdmi: Enable DP1.2 and all converters/pins

Skylake supports 3 pin and 3 converter widgets. But by default
only one converter and pin widget are enabled. In skylake
platform the DP port is on a different port which is not enabled
by default. To enable playback on DP port, enable all pin and
converter widget by sending a vendor VERB for a vendor widget to
set required bits.

As we are enabling the DP support enable the DP1.2 feature as well.

Enabling DP1.2 and all widget changes are copied from patch_hdmi.c.

Signed-off-by: Subhransu S. Prusty <subhransu.s.prusty@intel.com>
Signed-off-by: Vinod Koul <vinod.koul@intel.com>
Signed-off-by: Mark Brown <broonie@kernel.org>
---
 sound/soc/codecs/hdac_hdmi.c | 43 +++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 43 insertions(+)

diff --git a/sound/soc/codecs/hdac_hdmi.c b/sound/soc/codecs/hdac_hdmi.c
index d22fa6b..b2e5e54 100644
--- a/sound/soc/codecs/hdac_hdmi.c
+++ b/sound/soc/codecs/hdac_hdmi.c
@@ -629,6 +629,46 @@ static int hdac_hdmi_add_pin(struct hdac_ext_device *edev, hda_nid_t nid)
 	return 0;
 }
 
+#define INTEL_VENDOR_NID 0x08
+#define INTEL_GET_VENDOR_VERB 0xf81
+#define INTEL_SET_VENDOR_VERB 0x781
+#define INTEL_EN_DP12			0x02 /* enable DP 1.2 features */
+#define INTEL_EN_ALL_PIN_CVTS	0x01 /* enable 2nd & 3rd pins and convertors */
+
+static void hdac_hdmi_skl_enable_all_pins(struct hdac_device *hdac)
+{
+	unsigned int vendor_param;
+
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_GET_VENDOR_VERB, 0);
+	if (vendor_param == -1 || vendor_param & INTEL_EN_ALL_PIN_CVTS)
+		return;
+
+	vendor_param |= INTEL_EN_ALL_PIN_CVTS;
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_SET_VENDOR_VERB, vendor_param);
+	if (vendor_param == -1)
+		return;
+}
+
+static void hdac_hdmi_skl_enable_dp12(struct hdac_device *hdac)
+{
+	unsigned int vendor_param;
+
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_GET_VENDOR_VERB, 0);
+	if (vendor_param == -1 || vendor_param & INTEL_EN_DP12)
+		return;
+
+	/* enable DP1.2 mode */
+	vendor_param |= INTEL_EN_DP12;
+	vendor_param = snd_hdac_codec_read(hdac, INTEL_VENDOR_NID, 0,
+				INTEL_SET_VENDOR_VERB, vendor_param);
+	if (vendor_param == -1)
+		return;
+
+}
+
 /*
  * Parse all nodes and store the cvt/pin nids in array
  * Add one time initialization for pin and cvt widgets
@@ -641,6 +681,9 @@ static int hdac_hdmi_parse_and_map_nid(struct hdac_ext_device *edev)
 	struct hdac_hdmi_priv *hdmi = edev->private_data;
 	int ret;
 
+	hdac_hdmi_skl_enable_all_pins(hdac);
+	hdac_hdmi_skl_enable_dp12(hdac);
+
 	num_nodes = snd_hdac_get_sub_nodes(hdac, hdac->afg, &nid);
 	if (!nid || num_nodes <= 0) {
 		dev_warn(&hdac->dev, "HDMI: failed to get afg sub nodes\n");
-- 
2.7.0