Skip to content

K
Kernel

openeuler / Kernel
接近 2 年 前同步成功

通知 8
Star 0
Fork 0
K
Kernel
切换分支/标签
  1. 11 9月, 2018 1 次提交
  3. 30 8月, 2018 2 次提交
  5. 28 8月, 2018 3 次提交
    • T
      ALSA: hda: Remove substream allocation/free ops · 193c7e14
      由 Takashi Iwai 提交于 
      Since we dropped the memory page fiddling in the own allocators in
hda_intel.c, the substream allocation and free ops in both hda_intel.c
and hda_tegra.c became nothing but the simple calls of the standard
snd_pcm_lib helpers.  As both are identical, there is no longer need
for indirect calls via ops; it's a good opportunity for removing ops
and simplifying the codes.
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
      193c7e14
    • T
      ALSA: hda: Use new non-cached allocation for non-snoop mode · fc478143
      由 Takashi Iwai 提交于 
      Now the ALSA memory allocator helper supports the new non-cached
pages, let's use the new type, SNDRV_DMA_TYPE_DEV_UC_SG, for HD-audio
driver.  This allows us to reduce lots of codes.

As another positive side-effect by this patch, the long-standing issue
with non-snoop mode playing in the non-mmap mode is fixed.  The core
memalloc helper does the proper pgprot setup for non-cached pages for
vmap(), which was missing in the past.
Reported-and-tested-by: NHans Hu <HansHu@zhaoxin.com>
Signed-off-by: NTakashi Iwai <tiwai@suse.de>
      fc478143
    • T
      ALSA: hda: Check the non-cached stream buffers more explicitly · 78c9be61
      由 Takashi Iwai 提交于 
      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>
      78c9be61
  7. 30 6月, 2017 1 次提交
    • T
      ALSA: hda - Fix doubly initialization of i915 component · dba9b7b6
      由 Takashi Iwai 提交于 
      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>
      dba9b7b6
  9. 15 1月, 2017 1 次提交
    • T
      ALSA: hda - Make single_cmd option to stop the fallback mechanism · 41438f13
      由 Takashi Iwai 提交于 
      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>
      41438f13
  11. 09 8月, 2016 1 次提交
  13. 17 12月, 2015 4 次提交
  15. 15 12月, 2015 1 次提交
  17. 09 12月, 2015 1 次提交
    • T
      ALSA: hda - Don't try to bind i915 unless CONFIG_SND_HDA_I915 is set · fbaf9f9f
      由 Takashi Iwai 提交于 
      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>
      fbaf9f9f
  19. 19 10月, 2015 1 次提交
  21. 29 4月, 2015 1 次提交
  23. 17 4月, 2015 1 次提交
  25. 16 4月, 2015 6 次提交
  27. 13 3月, 2015 1 次提交
  29. 26 2月, 2015 2 次提交
    • T
      ALSA: hda - Clear pcm pointer assigned to hda_pcm at device removal · 820cc6cf
      由 Takashi Iwai 提交于 
      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>
      820cc6cf
    • T
      ALSA: hda - Drop power_save value indirection in hda_bus · bb573928
      由 Takashi Iwai 提交于 
      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>
      bb573928
  31. 20 2月, 2015 3 次提交
  33. 27 6月, 2014 2 次提交
  35. 09 4月, 2014 1 次提交
  37. 01 3月, 2014 7 次提交