1. 07 May, 2014 3 commits
  2. 02 May, 2014 1 commit
  3. 29 Apr, 2014 1 commit
    • Jarkko Nikula's avatar
      ASoC: core: Fix component_list corruption when unloading modules · 4da53393
      Jarkko Nikula authored
      This fixes module unload regressions introduced by commits 98e639fb
      ("ASoC: Track which components have been registered with
      snd_soc_register_component()") and b37f1d12 ("ASoC: Let snd_soc_platform
      subclass snd_soc_component").
      
      First commit causes component_list to be corrupted when removing codec and
      second when removing platform. Reason for both is that components associated
      with platform or codec are never removed from the list because for them
      registered_as_component field in struct snd_soc_component is always false.
      
      Now list becomes corrupted when snd_soc_unregister_platform() or
      snd_soc_unregister_codec() frees the platform or codec structure and where
      the associated struct snd_soc_component is embedded.
      
      Fix these by moving component unregistration and cleanup to a new local
      function __snd_soc_unregister_component() that takes component as its
      argument.
      
      Since component is known for platforms and codecs the
      __snd_soc_unregister_component() can be called directly and
      snd_soc_unregister_component() takes care to find and unregister only
      components that were registered using snd_soc_register_component().
      Signed-off-by: default avatarJarkko Nikula <jarkko.nikula@linux.intel.com>
      Acked-by: default avatarLars-Peter Clausen <lars@metafoo.de>
      Signed-off-by: default avatarMark Brown <broonie@linaro.org>
      4da53393
  4. 23 Apr, 2014 1 commit
    • Nicolin Chen's avatar
      ASoC: core: Don't break component searching if both id and num_dai are 0 · 3dcba280
      Nicolin Chen authored
      The commit e41975ed (ASoC: core: Fix the DAI name getting) added a break
      within the "if (id < 0 || id >= pos->num_dai)" while the original design
      of the search didn't break the loop if that condition contented but only
      mark the ret error and let it go on to search the next component.
      
      In a case like dmaengine which's not a dai but as a component sharing an
      identical name with a dai, both the id and pos->num_dai here could be 0.
      If we break the search, we may never find the dai we want as it might be
      placed behind its dmaengine in the component list.
      
      So this patch fixes the issue above by following the original design to
      let the search carry on.
      Signed-off-by: default avatarNicolin Chen <Guangyu.Chen@freescale.com>
      Signed-off-by: default avatarMark Brown <broonie@linaro.org>
      3dcba280
  5. 22 Apr, 2014 7 commits
  6. 21 Apr, 2014 2 commits
  7. 18 Apr, 2014 2 commits
  8. 15 Apr, 2014 1 commit
  9. 14 Apr, 2014 22 commits