ALSA: hda/realtek - Add a model for Thinkpad T570 without DAC workaround
PATCH 1/1 ALSA: hda/realtek - Add a model for Thinkpad T570 without DAC workaround
We fixed the regression of the speaker volume for some Thinkpad models (e.g. T570) by the commit 54947cd64c1b ("ALSA: hda/realtek - Fix speaker output regression on Thinkpad T570"). Essentially it fixes the DAC / pin pairing by a static table. It was confirmed and merged to stable kernel later.
Now, interestingly, we got another regression report for the very same model (T570) about the similar problem, and the commit above was the culprit. That is, by some reason, there are devices that prefer the DAC1, and another device DAC2!
Unfortunately those have the same ID and we have no idea what can differentiate, in this patch, a new fixup model "tpt470-dock-fix" is provided, so that users with such a machine can apply it manually. When model=tpt470-dock-fix option is passed to snd-hda-intel module, it avoids the fixed DAC pairing and the DAC1 is assigned to the speaker like the earlier versions.
--- sound/pci/hda/patch_realtek.c | 36 ++++++++++++++++++++++++++---------- 1 file changed, 26 insertions(+), 10 deletions(-)
sound/pci/hda/patch_realtek.c +26 -10
@@ -5484,18 +5484,9 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, { 0x19, 0x21a11010 }, /* dock mic */ { } }; -/* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise -* the speaker output becomes too low by some reason on Thinkpads with -* ALC298 codec -*/ -static const hda_nid_t preferred_pairs[] = { -0x14 ,0x03 ,0x17 ,0x02 ,0x21 ,0x02 , -0 - };struct alc_spec *spec = codec->spec;if (action ==HDA_FIXUP_ACT_PRE_PROBE ) { - spec->gen.preferred_dacs = preferred_pairs; spec->parse_flags =HDA_PINCFG_NO_HP_FIXUP ;snd_hda_apply_pincfgs (codec, pincfgs); }else if (action ==HDA_FIXUP_ACT_INIT ) {
@@ -5508,6 +5499,23 @@ static void alc_fixup_tpt470_dock(struct hda_codec *codec, } } +static void alc_fixup_tpt470_dacs (struct hda_codec *codec, +const struct hda_fixup *fix,int action) +{ +/* Assure the speaker pin to be coupled with DAC NID 0x03; otherwise +* the speaker output becomes too low by some reason on Thinkpads with +* ALC298 codec +*/ +static const hda_nid_t preferred_pairs[] = { +0x14 ,0x03 ,0x17 ,0x02 ,0x21 ,0x02 , +0 + }; +struct alc_spec *spec = codec->spec; + +if (action ==HDA_FIXUP_ACT_PRE_PROBE ) + spec->gen.preferred_dacs = preferred_pairs; +} +static void alc_shutup_dell_xps13 (struct hda_codec *codec) {struct alc_spec *spec = codec->spec;
@@ -6063,6 +6071,7 @@ enum {ALC700_FIXUP_INTEL_REFERENCE ,ALC274_FIXUP_DELL_BIND_DACS ,ALC274_FIXUP_DELL_AIO_LINEOUT_VERB , +ALC298_FIXUP_TPT470_DOCK_FIX ,ALC298_FIXUP_TPT470_DOCK ,ALC255_FIXUP_DUMMY_LINEOUT_VERB , ALC255_FIXUP_DELL_HEADSET_MIC,
@@ -6994,12 +7003,18 @@ static const struct hda_fixup alc269_fixups[] = { .chained = true, .chain_id =ALC274_FIXUP_DELL_BIND_DACS }, - [ALC298_FIXUP_TPT470_DOCK] = { + [ALC298_FIXUP_TPT470_DOCK_FIX] = { .type = HDA_FIXUP_FUNC, .v.func = alc_fixup_tpt470_dock, .chained = true, .chain_id =ALC293_FIXUP_LENOVO_SPK_NOISE }, + [ALC298_FIXUP_TPT470_DOCK] = { + .type = HDA_FIXUP_FUNC, + .v.func = alc_fixup_tpt470_dacs, + .chained = true, + .chain_id =ALC298_FIXUP_TPT470_DOCK_FIX + }, [ALC255_FIXUP_DUMMY_LINEOUT_VERB] = { .type = HDA_FIXUP_PINS, .v.pins = (const struct hda_pintbl []) {
@@ -7638,6 +7653,7 @@ static const struct hda_model_fixup alc269_fixup_models[] = { {.id = ALC292_FIXUP_TPT440_DOCK, .name = "tpt440-dock"}, {.id = ALC292_FIXUP_TPT440, .name = "tpt440"}, {.id = ALC292_FIXUP_TPT460, .name = "tpt460"}, + {.id = ALC298_FIXUP_TPT470_DOCK_FIX, .name = "tpt470-dock-fix"}, {.id = ALC298_FIXUP_TPT470_DOCK, .name = "tpt470-dock"}, {.id = ALC233_FIXUP_LENOVO_MULTI_CODECS, .name = "dual-codecs"}, {.id = ALC700_FIXUP_INTEL_REFERENCE, .name = "alc700-ref"},
Signature · 1 line
2.16.4
Hi
Quoted 16 lines
-----Original Message-----
From: Alsa-devel <[email protected]> On Behalf Of Takashi Iwai
Sent: Tuesday, May 26, 2020 2:24 AMWe fixed the regression of the speaker volume for some Thinkpad models (e.g. T570) by the commit
54947cd64c1b("ALSA: hda/realtek - Fix speaker output regression on Thinkpad T570"). Essentially it fixes the DAC / pin pairing by a static table. It was confirmed and merged to stable kernel later.Now, interestingly, we got another regression report for the very same model (T570) about the similar problem, and the commit above was the culprit. That is, by some reason, there are devices that prefer the DAC1, and another device DAC2!
Quoted 7 lines
Unfortunately those have the same ID and we have no idea what can differentiate, in this patch, a new fixup model "tpt470-dock-fix" is provided, so that users with such a machine can apply it manually. When model=tpt470-dock-fix option is passed to snd-hda-intel module, it avoids the fixed DAC pairing and the DAC1 is assigned to the speaker like the earlier versions.
That's interesting - let me follow up with the HW team and see if I can find out why this is. It would be nice to have something that works for all cases automatically.
Mark (Lenovo)
Quoted 26 lines · Mark Pearson
Hi
Quoted 16 lines
-----Original Message-----
From: Alsa-devel <[email protected]> On Behalf Of Takashi Iwai
Sent: Tuesday, May 26, 2020 2:24 AMWe fixed the regression of the speaker volume for some Thinkpad models (e.g. T570) by the commit
54947cd64c1b("ALSA: hda/realtek - Fix speaker output regression on Thinkpad T570"). Essentially it fixes the DAC / pin pairing by a static table. It was confirmed and merged to stable kernel later.Now, interestingly, we got another regression report for the very same model (T570) about the similar problem, and the commit above was the culprit. That is, by some reason, there are devices that prefer the DAC1, and another device DAC2!
Quoted 7 lines
Unfortunately those have the same ID and we have no idea what can differentiate, in this patch, a new fixup model "tpt470-dock-fix" is provided, so that users with such a machine can apply it manually. When model=tpt470-dock-fix option is passed to snd-hda-intel module, it avoids the fixed DAC pairing and the DAC1 is assigned to the speaker like the earlier versions.
Quoted 3 lines
That's interesting - let me follow up with the HW team and see if I can find out why this is. It would be nice to have something that works for all cases automatically.
That'd be appreciated, thanks!
Takashi