commit c02f77d32d2c45cfb1b2bb99eabd8a78f5ecc7db upstream.

A long-time problem on the recent AMD chip (X370, X470, B450, etc with
PCI ID 1022:1457) with Realtek codecs is the crackled or distorted
sound for capture streams, as well as occasional playback hiccups.
After lengthy debugging sessions, the workarounds we've found are like
the following:

- Set up the proper driver caps for this controller, similar as the
  other AMD controller.

- Correct the DMA position reporting with the fixed FIFO size, which
  is similar like as workaround used for VIA chip set.

- Even after the position correction, PulseAudio still shows
  mysterious stalls of playback streams when a capture is triggered in
  timer-scheduled mode.  Since we have no clear way to eliminate the
  stall, pass the BATCH PCM flag for PA to suppress the tsched mode as
  a temporary workaround.

This patch implements the workarounds.  For the driver caps, it
defines a new preset, AXZ_DCAPS_PRESET_AMD_SB.  It enables the FIFO-
corrected position reporting (corresponding to the new position_fix=6)
and enforces the SNDRV_PCM_INFO_BATCH flag.

Note that the current implementation is merely a workaround.
Hopefully we'll find a better alternative in future, especially about
removing the BATCH flag hack again.

BugLink: https://bugzilla.kernel.org/show_bug.cgi?id=195303
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

[ Upstream commit 78c9be61c3a5cd9e2439fd27a5ffad73a81958c7 ]

Introduce a new flag, uc_buffer, to indicate that the controller
requires the non-cached pages for stream buffers, either as a
chip-specific requirement or specified via snoop=0 option.
This improves the code-readability.

Also, this patch fixes the incorrect behavior for C-Media chip where
the stream buffers were never handled as non-cached due to the check
of driver_type even if you pass snoop=0 option.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NSasha Levin <sashal@kernel.org>
Signed-off-by: NGreg Kroah-Hartman <gregkh@linuxfoundation.org>

In the commit fcc88d91 ("ALSA: hda - Bind with i915 component
before codec binding"), the binding with i915 audio component is moved
to be performed always at probing the controller.  This fixed the
potential problems on IVB, but now it brought another issue on HSW and
BDW.  These two platforms give two individual HD-audio controllers,
one for the analog codec on PCH and another for HDMI over gfx.  Since
I decided to take a lazy path to check only AZX_DRIVER_PCH type in the
commit above, now both controllers try to bind with i915, and you see
a kernel WARNING.

This patch tries to address it again properly.  Now a new DCAPS bit,
AZX_DCAPS_I915_COMPONENT, is introduced for indicating the binding
with i915 component in addition to the existing I915_POWERWELL bit
flag.  Each PCI entry has to give this new flag if it requires the
binding with i915 component.  For HSW/BDW PCH (i.e. the ones defined
by AZX_DCAPS_INTEL_PCH) doesn't contain AZX_DCAPS_I915_COMPONENT bit
while others have it.

While we're at it, add parentheses around the bit flag check for
avoiding possible compiler warnings, too.

The bug was spotted by Intel CI tests.

Fixes: fcc88d91 ("ALSA: hda - Bind with i915 component before codec binding")
Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=196219Reported-by: NMartin Peres <martin.peres@free.fr>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

HD-audio driver has a mechanism to fall back to the single cmd mode as
a last resort if the CORB/RIRB communication goes wrong even after
switching to the polling mode.  The switching has worked in the past
well, but Enrico Mioso reported that his system crashes when this
happens.

Although the actual cause of the crash isn't still fully analyzed yet,
it'd be in anyway good to provide an option to turn off the fallback
mode.  Now this patch extends the behavior of the existing single_cmd
option for that.  Namely,

- The option is changed from bool to bint.
- As default, it is the mode allowing the fallback to single cmd.
- Once when either true/false value is given to the option, the driver
  explicitly turns on/off the single cmd mode, but without the
  fallback.

That is, if you want to disable the fallback, just pass single_cmd=0
option.  Passing single_cmd=1 will keep working like before.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Skylake onwards HDA controller supports new capabilities like
Global Time Stamping (GTS) capability. So add support to parse
these new capabilities.
Signed-off-by: NGuneshwor Singh <guneshwor.o.singh@intel.com>
Signed-off-by: NHardik T Shah <hardik.t.shah@intel.com>
Signed-off-by: NVinod Koul <vinod.koul@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

AZX_DCAPS_REVERSE_ASSIGN is no longer referred by any code.
Let's drop it.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

AZX_DCAPS_POSFIX_VIA is coupled always with AZX_DRIVER_VIA type, so we
don't have to keep this bit in dcaps.  Save one more!
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

AZX_DCAPS_RIRB_DELAY is dedicated only for Nvidia and its purpose is
just to set a flag in bus.  So it's better to be set in the toplevel
driver, either hda_intel.c or hda_tegra.c, instead of the common
hda_controller.c.  This also allows us to strip this flag from dcaps,
so save one more bit there.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

AZX_DCAPS_RIRB_PRE_DELAY is always tied with AZX_DCAPS_CTX_WORKAROUND,
which is Creative's XFi specific.  So, we can replace it and reduce
one more bit free for DCAPS.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Just a minor cleanup; instead of passing an array, pass the assigned
bdl_pos_adj option value directory in struct azx.  Also split the code
to get the default bdl_pos_adj value for the change that will follow
after this.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

snd-hda-intel driver tries to bind with i915 audio component always
when AZX_DCAPS_I915_POWERWELL is set in the driver caps.  This was
mostly OK in the past, as the flag was applied only to a limited set
of devices, namely, Haswell and Broadwell.  On these machines, i915
graphics is almost mandatory as long as HDMI/DP is concerned.

Recently the application of i915 binding was widened to more Intel
chips.  On these chips, the chance of a kernel without i915 graphics
is much higher, and such user would hit an error like:

 snd_hda_intel 0000:00:1b.0: failed to add i915 component master (-19)

Although the error itself is harmless, it's certainly superfluous even
to try binding with i915, if we already know that there isn't any.

This patch fixes it by simply defining AZX_DCAPS_I915_POWERWELL as 0
in the case without i915.  Then all codes referring to this flag will
be optimized out by the compiler.

Fixes: 6603249d ('ALSA: hda - Enable audio component for old Intel PCH devices')
Reported-by: Nkernel test robot <ying.huang@linux.intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Currently everyone and their dog has their own favourite spelling
for vga_switcheroo. This makes it hard to grep dmesg for log entries
relating to vga_switcheroo. It also makes it hard to find related
source files in the tree.

vga_switcheroo.c uses pr_fmt "vga_switcheroo". Use that everywhere.
Signed-off-by: NLukas Wunner <lukas@wunner.de>
Reviewed-by: NTakashi Iwai <tiwai@suse.de>
Link: http://patchwork.freedesktop.org/patch/msgid/9b0175319ce78d831acfcf11e4c6c760f826b0e3.1444663039.git.lukas@wunner.deSigned-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This patch implements the bus link_power ops to request/release i915 display
power well. It can be used by the display codec which shares this power well
with GPU on Intel platforms.
Signed-off-by: NMengdong Lin <mengdong.lin@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This flag seems used commonly, so deserves to be located there.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

They are no longer used (only one place which can be replaced with a
proper helper function).  Let's drop.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Because AZX_DCAPS_PM_RUNTIME is always defined as non-zero, the
initial part of the expression can be skipped.
Signed-off-by: NDavid Henningsson <david.henningsson@canonical.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

... and replace with the existing hda-core helper codes.
This reduces lots of lines, finally.

Since struct hda_bus is now embedded into struct azx,
snd_hda_bus_new() is moved and expanded from hda_codec.c to
hda_controller.c, accordingly.  Also private_free bus ops and
private_data field are removed because we no longer need to point azx
object from bus (we can use container_of())

The spin locks are consolidated into the single one, bus->reg_lock.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Embed hdac_stream object into azx_dev, and use a few basic helper
functions.  The most of helper codes for hdac_stream aren't still used
yet.

Also this commit disables the tracepoints temporarily due to build
problems.  It'll be enabled again later.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

One less redirection again.  This also requires the change of the call
order in the toplevel divers.  Namely, the bus has to be created at
first before other initializations since the memory allocation ops are
called through bus object now.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch adds the controller helper codes to hda-core library.
The I/O access ops are added to the bus ops.  The CORB/RIRB, the basic
attributes like irq# and iomap address, some locks and the list of
streams are added to the bus object, together with the stream object
and its helpers.

Currently the codes are just copied from the legacy driver, so you can
find duplicated codes in both directories.  Only constants are removed
from the original hda_controller.h.  More integration work will follow
in the later patches.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The driver shutdown ops is simpler than registering reboot notifier
manually.  There should be no functional change by this -- the codec
driver calls its own callback while the bus driver just calls
azx_stop() like before.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

We leave the pcm field of struct hda_pcm at removal of each device, so
far.  This hasn't been a problem since unbinding the codec driver
isn't supposed to happen and another route via snd_hda_codec_reset()
clears all the once.  However, for a proper unbind implementation, we
need to care about it.

This patch does the thing above properly:

- Include struct hda_pcm pointer instead of struct hda_pcm_stream
  pointers in struct azx_dev.  This allows us to point the hda_pcm
  object at dev_free callback.

- Introduce to_hda_pcm_stream() macro for better readability.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

We used to pass the power_save option value to hda_bus via a given
pointer.  This was needed to refer to the value from the HD-audio core
side.  However, after the transition to the runtime PM, this is no
longer needed.

This patch drops the power_save value indirection in hda_bus above,
and let the controller driver reprograms the autosuspend value
explicitly by a new helper, snd_hda_set_power_save().  Without this
call, the HD-audio core doesn't set up the autosuspend and flip the
runtime PM.  (User may still be able to set up via sysfs, though.)

Along with this change, the pointer argument of azx_bus_create() is
dropped as well.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

azx_create_codec() function does actually two things: create a bus and
probe codecs.  For the future work, split this to two logical
functions, azx_bus_create() and azx_probe_codecs().
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

It's just an indirection, so let the caller directly calling
snd_hda_build_controls().
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

There is no big reason to keep them separately.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The very same notifier code is used in both hda_intel.c and
hda_tegra.c.  Move it to the generic code.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

... and move most parts into hda_intel.c from the generic controller
code.  This is a clean up, and there should be no functional change by
this patch.

Now, struct azx obtains the generic callbacks for getting the position
and the delay.  As default NULL, posbuf is read.  These replace the
old position_fix[], and each is implemented as a callback.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The full_reset argument to azx_init_chip() carries boolean rather than
numerical information, so update the type to reflect that.
Signed-off-by: NThierry Reding <treding@nvidia.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Codec creation and stream initialization can be shared between
hda_intel and hda platform drivers.  Move it and the static functions
it depends on to hda_controller.c.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This code will be reused by an hda_platform driver as it has no PCI
dependencies.  This allows update_rirb to be static as all users are
now in hda_controller.c.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Share more code from hda_intel.  This moves the link control and
initialization to hda_controller.  The code will also be used by an
hda platform driver.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Combining the call to alloc_cmd_io with the allocate pages function
removes an extra interface between hda_intel and hda_controller.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This is done to allow an HDA platform driver to reuse the code.

A few of the interfaces added to hda_controller will disappear in
following commits as their users are also moved to hda_controller.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Moving the DSP loading functionality to hda_controller.c means that
the dsp lock doesn't need to be shared in hda_intel and
hda_controller.  The forthcoming platform driver doesn't need the DSP
loading code, but sharing it doesn't hurt.

Tested on Chromebook Pixel's ca0132 that uses the DSP loader.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Pull allocation from first_init to a new function in hda_controller.c.
Short term this will allow the dsp loader to be moved as well.  In
later commits it will allow the same allocation to be used by the
platform hda driver.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Pull the pcm_ops and the functions they use into a new hda_controller
file.  This is done to allow for other hda implementations besides PCI
to use the same ops.  The hda_controller file will house functionality
related to HDA but independent of the bus used to talk to the
controller.

This currently shares dsp locking across the two files.  This will be
remedied in a following commit.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>