When BIOS is damn crazy and gives no pin-config at all, the driver might
lead to a NULL dereference.  Let's add a NULL check for such a case.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Similarly in patch_via.c, parse the active analog-loopback connections
and create a list dynamically rather than static arrays.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Resitance is futile.  The remaining static model quirks for Apple
machines with ALC882-compatible codecs are converted to the auto-parser
now.  We can remove all alc*_quirks.c finally.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

If anyone wants to debug the driver and avoid the existing fix-ups,
pass model=nofixup option.  Then the driver will skip to pick up the
fixup list.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Finally the all static quirks for ALC880 are converted to the
auto-parser.  Since we are never sure whether the BIOS on so many old
machines are really correct, the quirk table entries are copied as
they are, but just providing the proper pin-config values
accordingly.

Since alc880_quirks.c is removed, alc882_quirks.c has to be adjusted
slightly to be built again.  There might be some compile warnings due
to the remaining alc882 quirks, but these shall be killed sooner or
later, I don't care it much at this point.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

It turned out that BIOS on most of ASUS mobo's set the pin-config tables
reasonably well for the auto-parser.  We'd need GPIO setups, but should
work as is other than that.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

ASUS W1V has a sane pin-config table set by BIOS.  The only missing piece
is the setup of GPIO1.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

ASUS Z71V has a totally broken BIOS setup (at least the info I got),
thus we need to override the whole pin-config table to make the
auto-parser working correctly.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

ALC880 model=uniwill-dig requires the fix-up of bogus BIOS pin default
configurations.  Other than that, it's pretty normal.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The model=uniwill would work almost as is, but a couple of adjustments
are needed to make the mutli-io working correctly.  The headphone and
speaker pins have to be marked properly in pin configs.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Uniwill p53 has a sane BIOS setup but just needs the volume-knob handling
like Fujitsu laptops with ALC880.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Similar as the previous patch for model=fujitsu, we can now move the
static quirk for F1734 to the auto-parser.  The only difference is the
default pin configurations: F1734 has less pins than Amilo's.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Now adding the support for the volume-knob widget, we can move the static
quirk for ALC880 model=fujitsu to the auto-parser completely.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Move the call of alc_apply_fixup() with ALC_FIXUP_ACT_PROBE after the
whole setups of patch_ops & co, so that the fix-up function may override
the default setup.  This will be needed for installing the own unsol
event handler (e.g. for volume-knob controls).
Signed-off-by: Takashi Iwai <tiwai@suse.de>

It needs a few extra setups for EAPD, but others look fairly
straightforward.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Clevo machines with ALC880 are all well with proper BIOS setup.
It seems still requiring the additional COEF setup for the EAPD.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Refactor the DAC filling function to be used for both the primary
line outputs and extra outputs using the individual badness tables.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The Medion W810 with ALC880 has a typical BIOS bug, copying the
pin-defaults without disabling the unused pins.  At least, the pin
0x17 must be disabled.  Also, it requires GPIO-2 setup.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

ALC880 model=lg could work fine with the auto-parser due to the recent
rewrite, but it still needs the manual adjustment; namely, the BIOS leaves
unused pins as some real active jacks.  This confuses the parser.
Thus we just cover these pins and override the pin-configs as a fix-up.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Try harder to fit the multi-io pins also by checking the hard-wired
connections for multi-ios.  Also, the badness values are adjusted to
prioritize the multi-ios as more valuable.  These changes will enable
the multi-io on some machines without losing the current capability.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Signed-off-by: Takashi Iwai <tiwai@suse.de>

So far, the Realtek driver tires to assign the single-connected routes
for all pins only once at the beginning.  However, since some DACs have
been already mapped, the rest pins might have also single conections.

In this patch, the driver does the single-connection assignment in a
loop until all possbile single-connections are checked.  This will
improve the DAC assignment, e.g. for ASUS G72.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

This patch improves the Realtek auto-parser for assigning the DACs and
mixers in more suitable ways by evaluating the assignment with "badness"
calculations.

When assigning a DAC hinders the assignment of individual DACs for
other pins, some badness point is given.  Similarly, when it blocks the
assignment of unique mixer controls, another badness point is added.
Also, if no DAC, even shared DAC, can be assigned, more badness is
pointed.  Finally, comparing the accumulated badness, the best route is
chosen among several trials.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

When the connections from the pin selector contain only two
widgets, a route to DAC and the aa-mixer, it's certainly a
single connection.  In such a case, get_dac_if_single() should
return the connected DAC, too.

This will improve the detection of the individual DAC
assignment for each pin.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The fix for bitmap-overflow in Realtek codec driver is needed for the
further development of the auto-parser with badness evaluation.

The bitmap introduced in the commit [527e4d73: ALSA: hda/realtek - Fix
missing volume controls with ALC260] is too narrow for some codecs,
which may have more NIDs than 0x20, thus it may overflow the bitmap
array on them.

Just double the number to cover all and also add a sanity-check code
to be safer.

Cc: <stable@kernel.org> [v3.2+]
Signed-off-by: Takashi Iwai <tiwai@suse.de>

We've enabled the static fixups for ASUS machines with ALC269 codec,
just for making things compatible during the transition to the auto-
parser.  However, it seems that the static configurations do more harmful
than good, as some of entries don't match with the actual hardware setups.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Now we can clean up all static quirks for ALC260.
Also many codes in alc_quirks.c can be ripped off since they have been
used only by ALC260 static quirks.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The model works with the auto-parser as is, thus now good to drop.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

It's working with the auto-parser just with the standard GPIO 1 setup.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

HP Presario B1900 needs a similar hack like Replacer, toggling GPIO1
per the jack state, in addition to the COEF setup used for other Acer
laptops.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The support for Replacer 627V in the auto-parser needs the unique unsol
event handling: although the machine has a single output pin 0x0f, it's
used for both the headphone and the speaker, and the driver needs to
toggle the output route via GPIO 1.

In addition, it needs a special COEF setup with 0x3050.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The ALC260 model=acer needs GPIO1 setup.  It could be selected well
if the codec SSID is set properly by BIOS, but to make sure, enable it
forcibly.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The model=will for ALC260 requires the pin 0x0f to be a headphone and
some special verbs for the COEF to turn on the amp.  Now added these as
fixup entries and removed the static model quirk.
Signed-off-by: Takashi Iwai <tiwai@suse.de>

A malicious USB device could feed in a large nr_rates value.  This would
cause the subsequent call to kmemdup() to allocate a smaller buffer than
expected, leading to out-of-bounds access.

This patch validates the nr_rates value and reuses the limit introduced
in commit 4fa0e81b ("ALSA: usb-audio: fix possible hang and overflow
in parse_uac2_sample_rate_range()").
Signed-off-by: Xi Wang <xi.wang@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

BugLink: https://bugs.launchpad.net/bugs/930842

The reporter states that audio is inaudible by default without muting
'External Amplifier'. Add a quirk to handle his SSID so that changing
the control is not necessary.
Reported-and-tested-by: Benjamin Carlson <elderbubba0810@gmail.com>
Cc: <stable@kernel.org>
Signed-off-by: Daniel T Chen <crimsun@ubuntu.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

A simple fix from Morimoto-san for the pointer() operation in the FSI
driver.

Conflicts:
	sound/pci/hda/patch_realtek.c

Merged back the fix for Acer Aspire 6935 with ALC889 codec.
The fix commit was based on 3.2 kernel so that it can be applied to
stable kernel cleanly.

Since 3.2 kernel, the driver starts trying to assign the multi-io DACs
before the speaker, thus it assigns DAC2/3 for multi-io and DAC4 for
the speaker for a standard laptop setup like a HP, a speaker, a mic-in
and a line-in.  However, on Acer Aspire 6935, it seems that the
speaker pin 0x14 must be connected with either DAC1 or 2; otherwise it
results in silence by some reason, although the codec itself allows
the routing to DAC3/4.

As a workaround, the connection list of each pin is reduced to be
mapped to either only DAC1/2 or DAC3/4, so that the compatible
assignment as in kernel 3.1 is achieved.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42740

Cc: <stable@kernel.org> [v3.2+]
Signed-off-by: Takashi Iwai <tiwai@suse.de>

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

The fix is simply to check the existence of MUX for secondary ADCs in
the initialization code.
Tested-by: Anisse Astier <anisse@astier.eu>
Cc: <stable@kernel.org> [v3.1+]
Signed-off-by: Takashi Iwai <tiwai@suse.de>