The total stream number of Sunrise Point's input and output stream
exceeds 15, which will cause some streams do not work because
of the overflow on SDxCTL.STRM field if using the legacy
stream tag allocation method.

This patch uses the new stream tag allocation method by add
the flag AZX_DCAPS_SEPARATE_STREAM_TAG for Skylake platform.
Signed-off-by: NLibin Yang <libin.yang@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This is essentially a partial revert of the commit [b1920c21:
'ALSA: hda - Enable runtime PM on Panther Point'].  There was a bug
report showing the HD-audio bus hang during runtime PM on HP Spectre
XT.
Reported-by: NDang Sananikone <dang.sananikone@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Register a component master to be used to interface with the i915
driver. This is meant to replace the current interface which is based on
module symbol lookups.

Note that currently we keep the existing behavior and pin the i915
module while the hda driver is loaded. Using the component interface
allows us to remove this dependency once support for dynamically
enabling / disabling the HDMI functionality is added to the driver.

v2:
- change roles between the hda and i915 components (Daniel)
v3:
- rename display_component to audio_component (Daniel)
v4:
- move removal of i915_powerwell.h from this patch to the next (Takashi)
- request_module fails if module support isn't enabled, so ignore
  any error it returns and depend on the following NULL check of the
  component ops (Takashi)
- change over to using dev_* instead of pr_* (Takashi)
Signed-off-by: NImre Deak <imre.deak@intel.com>
Reviewed-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

chip is already passed to most of the i915 interface functions. Unify
the interface by passing intel_hda instead of chip and passing it to all
functions. Passing intel_hda instead of chip makes more sense since this
is an intel specific interface. Also in an upcoming patch we will use
intel_hda in all of these functions so by passing intel_hda we can save
on some pointer casts from chip to intel_hda.

This will be needed by an upcoming patch adding component support.

No functional change.

v2-3: unchanged
v4:
- pass intel_hda instead of chip
Signed-off-by: NImre Deak <imre.deak@intel.com>
Reviewed-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This struct will be needed by the component code added in an upcoming
patch, so export it into a new hda_intel.h file. At the same time also
merge hda_i915.h into this new header, there is no reason to keep two
separate intel specific header file.
Suggested-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NImre Deak <imre.deak@intel.com>
Reviewed-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

This is a similar cleanup like the commit [3db084fd: ALSA: fm801:
PCI core handles power state for us].

Since pci_set_power_state(), pci_save_state() and pci_restore_state()
are already done in the PCI core side, so we don't need to it doubly.

Also, pci_enable_device(), pci_disable_device() and pci_set_master()
calls in PM callbacks are superfluous nowadays, too, so get rid of
them as well.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The iounmap() function performs also input parameter validation.
Thus the test around the call is not needed.

This issue was detected by using the Coccinelle software.
Signed-off-by: NMarkus Elfring <elfring@users.sourceforge.net>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The total stream number of Skylake's input and output stream
exceeds 15, which will cause some streams do not work because
of the overflow on SDxCTL.STRM field if using the legacy
stream tag allocation method.

This patch uses the new stream tag allocation method by add
the flag AZX_DCAPS_SEPARATE_STREAM_TAG for Skylake platform.
Signed-off-by: NLibin Yang <libin.yang@intel.com>
Reviewed-by: NVinod Koul <vinod.koul@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

After commit b2b49ccb (PM: Kconfig: Set PM_RUNTIME if PM_SLEEP is
selected) PM_RUNTIME is always set if PM is set, so #ifdef blocks
depending on CONFIG_PM_RUNTIME may now be changed to depend on
CONFIG_PM.

Replace CONFIG_PM_RUNTIME with CONFIG_PM everywhere under sound/.
Signed-off-by: NRafael J. Wysocki <rafael.j.wysocki@intel.com>
Acked-by: NTakashi Iwai <tiwai@suse.de>
Acked-by: NNicolin Chen <nicoleotsuka@gmail.com>
Acked-by: NBrian Austin <brian.austin@cirrus.com>
Acked-by: NMark Brown <broonie@kernel.org>

We introduced AZX_DCAPS_ALIGN_BUFSIZE to explicity show that the
controller needs the alignment, with a slight hope that the buffer
size alignment will be disabled as default in future.  But the reality
tells that most chips need the buffer size alignment, and it'll be
likely enabled in future, too.

This patch drops AZX_DCAPS_ALIGN_BUFSIZE to give back one more
precious DCAPS bit for future use.  At the same time, rename
AZX_DCAPS_BUFSIZE with AZX_DCAPS_NO_ALIGN_BUFSIZE for avoiding
confusion.

AZX_DCAPS_ALIGN_BUFSIZE are still kept (but commented out) in each
DCAPS presets for a purpose as markers.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Just for improving readability.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

User can pass snoop option to enable/disable the snoop behavior, but
currently azx_check_snoop_available() always turns it off for some
devices.  For better debuggability, change the parameter as bint, and
allow user to enable/disable forcibly the snoop when specified via the
module option.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Add a new driver_caps bit, AZX_DCAPS_SNOOP_OFF, to set the snoop off
as default.  This new bit is used for the checks in
azx_check_snoop_available().  Most of case-switches are replaced with
the new dcaps in each entry.

While working on it, for avoiding to spend more bits, combine three
bits AZX_DCAPS_SNOOP_SCH, AZX_DCAPS_SNOOP_ATI and
AZX_DCAPS_SNOOP_NVIDIA bits into a flat type of two bits.  This
reduces the bits usages, and assign AZX_DCAPS_OFF to this empty bit
now.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

A number of radeon cards have a HW limitation causing them to be
unable to generate the full 64-bit of address bits for MSIs. This
breaks MSIs on some platforms such as POWER machines.

We used to have a powerpc specific quirk to address that on a
single card, but this doesn't scale very well, this is better
put under control of the drivers who know precisely what a given
HW revision can do.

We now have a generic quirk in the PCI code. We should set it
appropriately for all radeon's from the audio driver.
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
Reviewed-by: NTakashi Iwai <tiwai@suse.de>
Reviewed-by: NAlex Deucher <alexander.deucher@amd.com>
CC: <stable@vger.kernel.org>

AMD/ATI HDMI controller chip models, we already have a filter to lower
to 32bit DMA, but the rest are supposed to be working with 64bit
although the hardware doesn't really work with 63bit but only with 40
or 48bit DMA.  In this patch, we take 40bit DMA for safety for the
AMD/ATI controllers as the graphics drivers does.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
Signed-off-by: NBenjamin Herrenschmidt <benh@kernel.crashing.org>
CC: <stable@vger.kernel.org>

The functions kfree() and release_firmware() test whether their argument
is NULL and then return immediately. Thus the test around the call
is not needed.

This issue was detected by using the Coccinelle software.
Signed-off-by: NMarkus Elfring <elfring@users.sourceforge.net>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch adds DeviceIDs for Sunrise Point-LP
Signed-off-by: NDevin Ryles <devin.ryles@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

CMI8888 shows the stuttering playback when the snooping is disabled
on the audio buffer.  Meanwhile, we've got reports that CORB/RIRB
doesn't work in the snooped mode.  So, as a compromise, disable the
snoop only for CORB/RIRB and enable the snoop for the stream buffers.

The resultant patch became a bit ugly, unfortunately, but we still can
live with it.
Reported-and-tested-by: NGeoffrey McRae <geoff@spacevs.com>
Cc: <stable@vger.kernel.org> # 3.17+
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This patch adds the HD Audio Device IDs for the Intel Sunrise Point PCH.

[the item position rearranged by tiwai]
Signed-off-by: NJames Ralston <james.d.ralston@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

ASUS Phoebus with CMI8888 HD-audio chip (PCI id 13f6:5011) doesn't
work with HD-audio driver as is because of some weird nature.  For
making DMA properly working, we need to disable MSI.  The position
report buffer doesn't work, thus we need to force reading LPIB
instead.  And yet, the codec CORB/RIRB communication gives errors
unless we disable the snooping (caching).

In this patch, all these workarounds are added as a quirk for the
device.  The HD-audio *codec* chip needs yet another workaround, but
it'll be provided in the succeeding patch.
Reported-and-tested-by: NVincent Lejeune <vljn@ovi.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Add HD Audio Device PCI ID for the Intel Braswell platform.
It is an HDA Intel PCH controller.

AZX_DCAPS_ALIGN_BUFSIZE is not necessary for this controller.
Signed-off-by: NLibin Yang <libin.yang@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Since devptr can be NULL due to asynchronous probe, all PM ops should
have NULL checks at the beginning.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When the initialization of Intel HDMI controller fails due to missing
i915 kernel symbols (e.g. HD-audio is built in while i915 is module),
the driver discontinues the probe.  However, since the probe was done
asynchronously, the driver object still remains, thus the relevant PM
ops are still called at suspend/resume. This results in the bad access
to the incomplete audio card object, eventually leads to Oops or stall
at PM.

This patch adds the missing checks of chip->init_failed flag at each
PM callback in order to fix the problem above.

Bugzilla: https://bugzilla.kernel.org/show_bug.cgi?id=79561
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

We got a regression report for 3.15.x kernels, and this turned out to
be triggered by the fix for stream assignment order.  On reporter's
machine with Intel controller (8086:1e20) + VIA VT1802 codec, the
first playback slot can't work with speaker outputs.

But the original commit was actually a fix for AMD controllers where
no proper GCAP value is returned, we shouldn't revert the whole
commit.  Instead, in this patch, a new flag is introduced to determine
the stream assignment order, and follow the old behavior for Intel
controllers.

Fixes: dcb32ecd ('ALSA: hda - Do not assign streams in reverse order')
Reported-and-tested-by: NSteven Newbury <steve@snewbury.org.uk>
Cc: <stable@vger.kernel.org> [v3.15+]
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

For HSW/BDW display HD-A controller, hda_set_bclk() is defined to set BCLK
by programming the M/N values as per the core display clock (CDCLK) queried from
i915 display driver.

And the audio driver will also set BCLK in azx_first_init() since the display
driver can turn off the shared power in boot phase if only eDP is connected
and M/N values will be lost and must be reprogrammed.
Signed-off-by: NMengdong Lin <mengdong.lin@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

ICH6_ prefix doesn't mean that it's specific to ICH6 chipset but
rather its generic for all HD-audio (or "Azalia") devices.
Use AZX_ prefix instead to align with other constants.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The defined numbers of SDs are specific to hda-intel, so move them to
there.
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>

Just move struct fields between struct azx and struct hda_intel, and
move some definitions from hda_priv.h to hda_intel.c.
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>

For Intel Haswell/Broadwell display HD-A controller, the 24MHz HD-A link BCLK
is converted from Core Display Clock (CDCLK): BCLK = CDCLK * M / N
And there are two registers EM4 and EM5 to program M, N value respectively.
The EM4/EM5 values will be lost and when the display power well is disabled.

BIOS programs CDCLK selected by OEM and EM4/EM5, but BIOS has no idea about
display power well on/off at runtime. So the M/N can be wrong if non-default
CDCLK is used when the audio controller resumes, which results in an invalid
BCLK and abnormal audio playback rate. So this patch saves and restores valid
M/N values on controller suspend/resume.

And 'struct hda_intel' is defined to contain standard HD-A 'struct azx' and
Intel specific fields, as Takashi suggested.
Signed-off-by: NMengdong Lin <mengdong.lin@intel.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

When a machine is booted with nomodeset option, i915 driver skips the
whole initialization.  Meanwhile, HD-audio tries to bind wth i915 just
by request_symbol() without knowing that the initialization was
skipped, and eventually it hits WARN_ON() in i915_request_power_well()
and i915_release_power_well() wrongly but still continues probing,
even though it doesn't work at all.

In this patch, both functions are changed to return an error in case
of uninitialized state instead of WARN_ON(), so that HD-audio driver
can give up HDMI controller initialization at the right time.
Acked-by: NDaniel Vetter <daniel.vetter@ffwll.ch>
Cc: <stable@vger.kernel.org> [3.15]
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

This reverts commit 7189eb9b.

It will use LPIB to get the DMA position on Broadwell HDMI Audio.
Signed-off-by: NLibin Yang <libin.yang@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Broadwell HDMI can't use position buffer reliably, force to use LPIB
Signed-off-by: NLibin Yang <libin.yang@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The recent Intel H97/Z97 chipsets need the similar setups like other
Intel chipsets for snooping, etc.  Especially without snooping, the
audio playback stutters or gets corrupted.  This fix patch just adds
the corresponding PCI ID entry with the proper flags.
Reported-and-tested-by: NArthur Borsboom <arthurborsboom@gmail.com>
Cc: <stable@vger.kernel.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

We should prefer `const struct pci_device_id` over
`DEFINE_PCI_DEVICE_TABLE` to meet kernel coding style guidelines.
This issue was reported by checkpatch.

A simplified version of the semantic patch that makes this change is as
follows (http://coccinelle.lip6.fr/):

// <smpl>

@@
identifier i;
declarer name DEFINE_PCI_DEVICE_TABLE;
initializer z;
@@

- DEFINE_PCI_DEVICE_TABLE(i)
+ const struct pci_device_id i[]
= z;

// </smpl>

It has been tested by compilation.
Signed-off-by: NBenoit Taine <benoit.taine@lip6.fr>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

Broadwell display controller has 3 stream DMA engines. DMA0 cannot update DMA
postion buffer properly while DMA1 and DMA2 can work well. So this patch masks
the buggy DMA0 by keeping it as opened.

This is a tentative workaround, so keep the change small as Takashi suggested.
Signed-off-by: NMengdong Lin <mengdong.lin@intel.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>

The recent commit (ca460f86) changed the CORB RP reset procedure to
follow the specification with a couple of sanity checks.
Unfortunately, Nvidia controller chips seem not following this way,
and spew the warning messages like:
  snd_hda_intel 0000:00:10.1: CORB reset timeout#1, CORBRP = 0

This patch adds the workaround for such chips.  It just skips the new
reset procedure for the known broken chips.
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>

The ops to read and write registers should take pointers labeled as
__iomem.  Thanks to the sparse bot for catching this.
Signed-off-by: NDylan Reid <dgreid@chromium.org>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>