1. 29 9月, 2012 5 次提交
  2. 25 9月, 2012 1 次提交
  3. 19 9月, 2012 1 次提交
  4. 12 9月, 2012 1 次提交
  5. 08 9月, 2012 2 次提交
  6. 07 8月, 2012 7 次提交
  7. 18 7月, 2012 3 次提交
  8. 12 7月, 2012 1 次提交
  9. 10 7月, 2012 1 次提交
  10. 29 6月, 2012 1 次提交
    • A
      mwifiex: wakeup main thread to handle command queued · 1a1fb970
      Amitkumar Karwar 提交于
      We miss to wakeup main thread after adding command to cmd pending
      queue at follwing places. These commands are handled later when
      main thread is woken up for handling an interrupt for sleep event
      from firmware. This adds worst case delay of 50msec.
      
      1) We don't wakeup main thread when asynchronous command is added
      to cmd pending queue. Move queue_work() call from
      mwifiex_wait_queue_complete() to mwifiex_send_cmd_async() to wakeup
      main thread for sync as well as async commands.
      
      2) Scan operation is triggered due to following reasons
         a) request from user (ex. "iw scan" command)
         b) Scan performed by driver internally.
         In first case main thread is woken up when first scan command is
      queued in cmd pending queue (we don't need to wakeup main thread for
      subsequent scan commands, because they are queued in scan command
      response handler), but it is not done for second case. queue_work()
      is moved inside mwifiex_scan_networks() to handle both the cases.
      Signed-off-by: NAmitkumar Karwar <akarwar@marvell.com>
      Signed-off-by: NAvinash Patil <patila@marvell.com>
      Signed-off-by: NBing Zhao <bzhao@marvell.com>
      Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
      1a1fb970
  11. 21 6月, 2012 2 次提交
  12. 12 6月, 2012 2 次提交
  13. 17 5月, 2012 11 次提交
  14. 24 4月, 2012 1 次提交
  15. 18 4月, 2012 1 次提交
    • A
      mwifiex: corrections in timestamp related code · b5abcf02
      Amitkumar Karwar 提交于
      We get two timing related fields for each bss from firmware in scan
      results.
      1) timestamp - Actual timestamp information in probe response/beacon
      2) network_tsf - firmware's TSF value at the time the beacon or probe
      response was received.
      Both are needed while associating by firmware.
      
      The patch takes care of following things.
      1) We should pass "timestamp" to cfg80211_inform_bss(), but currently
      "network_tsf" is being provided. This error is corrected here.
      2) Rename "network_tsf" to "fw_tsf"
      3) Make use of u64 variable instead of an array of u8/u32 to save
      parsed "timestamp" information.
      4) Use timestamp provided to stack in scan results using
      cfg80211_inform_bss() while associating. (bss->tsf)
      5) Allocate space to save fw_tsf in "priv" of cfg80211_bss
      and retrieve it while associating.
      Signed-off-by: NAmitkumar Karwar <akarwar@marvell.com>
      Signed-off-by: NBing Zhao <bzhao@marvell.com>
      Signed-off-by: NJohn W. Linville <linville@tuxdriver.com>
      b5abcf02