1. 12 3月, 2011 1 次提交
  2. 20 10月, 2010 1 次提交
    • N
      arm: remove machine_desc.io_pg_offst and .phys_io · 6451d778
      Nicolas Pitre 提交于
      Since we're now using addruart to establish the debug mapping, we can
      remove the io_pg_offst and phys_io members of struct machine_desc.
      
      The various declarations were removed using the following script:
      
        grep -rl MACHINE_START arch/arm | xargs \
        sed -i '/MACHINE_START/,/MACHINE_END/ { /\.\(phys_io\|io_pg_offst\)/d }'
      
      [ Initial patch was from Jeremy Kerr, example script from Russell King ]
      Signed-off-by: NNicolas Pitre <nicolas.pitre@linaro.org>
      Acked-by: Eric Miao <eric.miao at canonical.com>
      6451d778
  3. 24 9月, 2010 4 次提交
  4. 06 8月, 2010 1 次提交
  5. 20 7月, 2010 1 次提交
    • S
      ASoC: davinci: let platform data define edma queue numbers · 48519f0a
      Sekhar Nori 提交于
      Currently the EDMA queue to be used by for servicing ASP through
      internal RAM is fixed to EDMAQ_0 and that to service internal RAM
      from external RAM is fixed to EDMAQ_1.
      
      This may not be the desirable configuration on all platforms. For
      example, on DM365, queue 0 has large fifo size and is more suitable
      for video transfers. Having audio and video transfers on the same
      queue may lead to starvation on audio side.
      
      platform data as defined currently passes a queue number to the driver
      but that remains unused inside the driver.
      
      Fix this by defining one queue each for ASP and RAM transfers in the
      platform data and using it inside the driver.
      
      Since EDMAQ_0 maps to 0, thats the queue that will be used if
      the asp queue number is not initialized. None of the platforms
      currently utilize ping-pong transfers through internal RAM so that
      functionality remains unchanged too.
      
      This patch has been tested on DM644x and OMAP-L138 EVMs.
      Signed-off-by: NSekhar Nori <nsekhar@ti.com>
      Acked-by: NLiam Girdwood <lrg@slimlogic.co.uk>
      Signed-off-by: NMark Brown <broonie@opensource.wolfsonmicro.com>
      48519f0a
  6. 14 5月, 2010 1 次提交
    • C
      Davinci: aintc/cpintc - use ioremap() · bd808947
      Cyril Chemparathy 提交于
      This patch implements the following:
      
       - interrupt initialization uses ioremap() instead of passing a virtual address
         via davinci_soc_info.
      
       - machine definitions directly point to cp_intc_init() or davinci_irq_init()
      
       - davinci_intc_type and davinci_intc_base now get initialized in controller
         specific init functions instead of davinci_common_init()
      
       - minor fix in davinci_irq_init() to use intc_irq_num instead of
         DAVINCI_N_AINTC_IRQ
      Signed-off-by: NCyril Chemparathy <cyril@ti.com>
      Signed-off-by: NKevin Hilman <khilman@deeprootsystems.com>
      bd808947
  7. 07 5月, 2010 5 次提交
  8. 05 2月, 2010 1 次提交
  9. 26 11月, 2009 17 次提交
  10. 26 8月, 2009 5 次提交