If cs_automic is called twice (like it is during init) while the mic
is present, it will over-write the last_input with the new one,
causing it to switch back to the automic input when the mic is
unplugged. This leaves the driver in a state (cur_input, last_input,
and automix_idx the same) where the internal mic can not be selected
until it is rebooted without the mic attached.

Check that the mic hasn't already been switched to before setting
last_input.

Signed-off-by: Dylan Reid <dgreid@chromium.org>
Cc: <stable@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The user reports that model=auto works better than current handling
on a 3.2 based kernel (with jack detection patches backported).
Since model=auto is what we prefer these days anyway, the quirk
should be removed.

Alsa-info for the relevant machine:
https://bugs.launchpad.net/ubuntu/+source/linux/+bug/923316/+attachment/2702812/+files/alsa-info.txt.Pbfno2x7bp

BugLink: https://bugs.launchpad.net/bugs/923316


Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

If a codec has both a front and a rear Line In, two controls both
named "Line Jack" will be created, which causes parsing to fail.
While a long term solution might be to name the jacks differently,
this extra check is consistent with what is already being done in many
auto-parsers, and will also protect against other cases when two
inputs have the same label.

BugLink: https://bugs.launchpad.net/bugs/923409


Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

It turned out that other ASUS laptops require the similar fix to
enable the VREF on the pin 0x0f for the secret output amp, not only
ASUS A6Rp.  Moreover, it's required even when the pin is being used
as the output.  Thus, writing a fixed value doesn't work always.

This patch applies the VREF-fix for all ASUS laptops with ALC861/660
in a fixup function that checks the current value and turns on only
the VREF value no matter whether input or output direction is set.

The automute function is modified as well to keep the pin VREF upon
muting/unmuting via pin-control; otherwise the pin VREF is reset at
plugging/unplugging a jack.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42588



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

A bunch of small driver specific fixes - nothing terribly exciting here,
all of this will only affect people using particular devices and then
usually only in some use cases.

The Openmoko GTA01 machine has been removed from the machine ID database,
  so we need to remove references to it as well.

Without that fix we have:
  sound/soc/samsung/neo1973_wm8753.c: In function ‘neo1973_wm8753_init’:
  sound/soc/samsung/neo1973_wm8753.c:325:2: error: implicit declaration of function ‘machine_is_neo1973_gta01’

Signed-off-by: Denis 'GNUtoo' Carikli <GNUtoo@no-log.org>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

This fixes below build warning when CONFIG_PCI is not set.

CC      sound/sound_core.o
In file included from sound/sound_core.c:15:
include/sound/core.h:454: warning: 'struct pci_dev' declared inside parameter list
include/sound/core.h:454: warning: its scope is only this definition or declaration, which is probably not what you want

Signed-off-by: Axel Lin <axel.lin@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Signed-off-by: UK KIM <w0806.kim@samsung.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@vger.kernel.org

The user reports that he needs to add model=auto for audio to
work properly. In fact, since node 0x15 is not even a pin node,
the existing fixup is definitely wrong. Relevant information can
be found in the buglink below.

Cc: stable@kernel.org (3.2+)
BugLink: https://bugs.launchpad.net/bugs/918254


Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

For optimal performance the single ended line outputs require that the
line output VMID buffer be enabled.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@vger.kernel.org

The very same problem is seen on Haier W18 laptop with ALC861 as seen
on ASUS A6Rp, which was fixed by the commit 3b25eb69.
Now we just need to add a new SSID entry pointing to the same fixup.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42656



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

Otherwise we won't resync later.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

Otherwise we won't resync later.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

Otherwise we won't resync later.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

We need to write the configuration for each microphone to a different
register.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@vger.kernel.org

When we have identified an accessory make sure we've flagged that we've
done so in order to make sure we always report buttons and don't continue
to polarity flip.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

HP laptop models with buggy BIOS are apparently frequent, including
machines with different codecs. Set the polarity of the mute led based
on the SSID and include an entry for the HP Mini 110-3100.

Signed-off-by: Gustavo Maciel Dias Vieira <gustavo@sagui.org>
Tested-by: Predrag Ivanovic <predivan@open.telekom.rs>
Cc: <stable@kernel.org> [v3.2+]
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The refactoring of Realtek codec driver in 3.2 kernel caused a
regression for ASUS A6Rp laptop; it doesn't give any output.
The reason was that this machine has a secret master mute (or EAPD)
control via NID 0x0f VREF.  Setting VREF50 on this node makes the
sound working again.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42588



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

If copy_from_user() does not return 0 we'll leak the memory we
allocated for 'params' when that variable goes out of scope.

Also a small CodingStyle cleanup: Use braces on both branches of
if/else when one branch needs it.

Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Acked-by: Vinod Koul <vinod.koul@linux.intel.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

- check SDAC bit of AC97 primary codec when create "rear" device 3,
  "4ch" device 2 and "4ch Duplication" switch as the card need a four channels
  AC97 codec to support surround40.

Signed-off-by: Raymond Yau <superquad.vortex2@gmail.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

In wm2000_i2c_probe(), if we take the true branch in

"
  ret = snd_soc_register_codec(&i2c->dev, &soc_codec_dev_wm2000,
                               NULL, 0);
  if (ret != 0)
          goto err_fw;
"

then we'll release_firmware(fw) at the 'err_fw' label. But we've already
done that just a few lines above. That's a use-after-free bug.

This patch restructures the code so that we always call
release_firmware(fw) before leaving the function, but only ever call
it once.
This means that we have to initialize 'fw' to NULL since some paths
may now end up calling it without having called request_firmware(),
but since request_firmware() deals gracefully with NULL pointers, we
are fine if we just NULL initialize it.

Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

To print a value of type size_t one should use %zd, not %d.

Signed-off-by: Jesper Juhl <jj@chaosbits.net>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

The recent change of the power-widget handling for IDT codecs caused
the silent output from the docking-station line-out jack.  This was
partially fixed by the commit f2cbba76
"ALSA: hda - Fix the lost power-setup of seconary pins after PM resume".
But the line-out on the docking-station is still silent when booted
with the jack plugged even by this fix.

The remainig bug is that the power-widget is set off in stac92xx_init()
because the pins in cfg->line_out_pins[] aren't checked there properly
but only hp_pins[] are checked in is_nid_hp_pin().

This patch fixes the problem by checking both HP and line-out pins
and leaving the power-map correctly.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42637



Cc: <stable@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The user reports that model=auto works fine for him. Using
model=auto bring in new features such as jack detection notification
to userspace.

Alsa info is available at http://paste.ubuntu.com/805351/



Signed-off-by: David Henningsson <david.henningsson@canonical.com>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

The commit 2ae66c26
    ALSA: hda: option to enable arbitrary buffer/period sizes
introduced a regression on machines with Intel controller and Nvidia
HDMI.  The reason is that the driver modifies the global variable
align_buffer_size when an Intel controller is found, and the Nvidia
HDMI controller is probed after Intel although Nvidia chips require
the aligned buffers.

This patch fixes the problem by moving the flag into the local struct
so that it's not affected by other controllers.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=42567



Cc: <stable@kernel.org>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

We should be allowing a 5ms delay after the charge pump is started in
order to ensure it has finished ramping.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

On a mx28evk board the following errors happens on mxs-sgtl5000 probe:

[    0.660000] saif0_clk_set_rate: divider writing timeout
[    0.670000] mxs-sgtl5000: probe of mxs-sgtl5000.0 failed with error -110
[    0.670000] ALSA device list:
[    0.680000]   No soundcards found.

This timeout happens because clk_set_rate will result in writing to the DIV bits
of register HW_CLKCTRL_SAIF0 with the saif clock gated (CLKGATE bit set to one).

MX28 Reference states the following about CLKGATE:

"The DIV field can change ONLY when this clock gate bit field is low."

So call clk_prepare_enable prior to clk_set_rate to fix this problem.

After this change the mxs-saif driver can be correctly probed and audio is functional.

Signed-off-by: Fabio Estevam <fabio.estevam@freescale.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

With a low frequency SYSCLK and a fast I2C clock register synchronisation
may occasionally take too long to take effect, causing I/O issues. Disable
synchronisation in order to avoid any issues.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

These are all to either uncached registers or fixes to register defaults,
in the former case the cache won't do anything and in the latter case
we're fixing things so the cache sync will do the right thing.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

Writing to the registers won't work if we do actually manage to hit a fully
powered off state.

Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>
Cc: stable@kernel.org

Register LDOCTLEN must always be initialized to clear the analog power
control bit, otherwise the analog block will stay deactivated.

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Javier Martin <javier.martin@vista-silicon.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

Dividers (such as MDAC) are always needed, independent of the codec
being I2S master or slave. Needed on a custom board where the codec has
to be slave.

Signed-off-by: Wolfram Sang <w.sang@pengutronix.de>
Acked-by: Javier Martin <javier.martin@vista-silicon.com>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

Correct SGTL5000_CHIP_CLK_CTRL to SGTL5000_CHIP_REF_CTRL in
sgtl5000_restore_regs(), and add comment to explain the
restore order.

Reported-by: Julia Lawall <julia.lawall@lip6.fr>
Signed-off-by: Zeng Zhaoming <zengzm.kernel@gmail.com>
Acked-by: Dong Aisheng <dong.aisheng@linaro.org>
Signed-off-by: Mark Brown <broonie@opensource.wolfsonmicro.com>

Just overlooked.

sound/pci/hda/patch_realtek.c: In function ‘alc_sku_unsol_event’:
sound/pci/hda/patch_realtek.c:643:19: warning: unused variable ‘spec’ [-Wunused-variable]

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

I have been told that this way the rear headphone connector is
working as well; with model=alienware only laptop speakers work.
The subsystem of both controller and codec is 1028:0490.

Signed-off-by: Albert Pool <albertpool@solcon.nl>
Signed-off-by: Takashi Iwai <tiwai@suse.de>

Merge branches 'sched-urgent-for-linus', 'perf-urgent-for-linus' and 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

* 'sched-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/accounting, proc: Fix /proc/stat interrupts sum

* 'perf-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  tracepoints/module: Fix disabling tracepoints with taint CRAP or OOT
  x86/kprobes: Add arch/x86/tools/insn_sanity to .gitignore
  x86/kprobes: Fix typo transferred from Intel manual

* 'x86-urgent-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86, syscall: Need __ARCH_WANT_SYS_IPC for 32 bits
  x86, tsc: Fix SMI induced variation in quick_pit_calibrate()
  x86, opcode: ANDN and Group 17 in x86-opcode-map.txt
  x86/kconfig: Move the ZONE_DMA entry under a menu
  x86/UV2: Add accounting for BAU strong nacks
  x86/UV2: Ack BAU interrupt earlier
  x86/UV2: Remove stale no-resources test for UV2 BAU
  x86/UV2: Work around BAU bug
  x86/UV2: Fix BAU destination timeout initialization
  x86/UV2: Fix new UV2 hardware by using native UV2 broadcast mode
  x86: Get rid of dubious one-bit signed bitfield

gpio bug fixes for v3.3

* tag 'gpio-for-linus' of git://git.secretlab.ca/git/linux-2.6:
  gpio: tps65910: Use correct offset for gpio initialization
  gpio/it8761e: Restrict it8761e gpio driver to x86.
  gpio-ml-ioh: cleanup __iomem annotation usage
  gpio-ml-ioh: cleanup NULL pointer checking
  gpio-pch: cleanup __iomem annotation usage
  gpio-pch: cleanup NULL pointer checking

* 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/viro/vfs:
  qnx4: don't leak ->BitMap on late failure exits
  qnx4: reduce the insane nesting in qnx4_checkroot()
  qnx4: di_fname is an array, for crying out loud...
  vfs: remove printk from set_nlink()
  wake up s_wait_unfrozen when ->freeze_fs fails