Permalink
Commits on Oct 13, 2015
  1. gproj: Use mpdecision as default

    EmmanuelU authored and tkawajir committed Sep 24, 2015
  2. cpufreq: Update interactive

    EmmanuelU authored and tkawajir committed Sep 8, 2015
  3. block: deadline: Optimize for non-rotational

    myfluxi authored and tkawajir committed Oct 18, 2013
    Change-Id: Ib36df79cf0cab0aff5e0a67fd92265ff29fda39e
  4. deadline: Allow 0ms deadline latency, increase the read speed

    tuxiaobing authored and tkawajir committed Dec 9, 2012
    Change a timer compare from after to after-equals, thus allowing
    0 timeout and making deadline schedule FIFO.
    
    Signed-off-by: xiaobing tu <xiaobing.tu@intel.com>
    Signed-off-by: Jens Axboe <axboe@kernel.dk>
  5. Revert "block: Add URGENT request notification support to CFQ scheduler"

    Tatyana Brokhman authored and tkawajir committed Sep 4, 2013
    This reverts commit b410a82118cdaa1dc92759e7995c20dcce0d1f1a.
    The reverted commit was identified as the cause of the FS error
    mentioned in the CR bellow.
    It's reverted till further annalists of the root cause of FS error.
    
    Change-Id: Ia75216de8012a2491b87f33e8c21f75592d87c80
    CRs-fixed: 531257
    Signed-off-by: Tatyana Brokhman <tlinder@codeaurora.org>
  6. cfq-iosched: fix the setting of IOPS mode on SSDs

    axboe authored and tkawajir committed Jun 10, 2015
    A previous commit wanted to make CFQ default to IOPS mode on
    non-rotational storage, however it did so when the queue was
    initialized and the non-rotational flag is only set later on
    in the probe.
    
    Add an elevator hook that gets called off the add_disk() path,
    at that point we know that feature probing has finished, and
    we can reliably check for the various flags that drivers can
    set.
    
    Change-Id: Ieaf0beed1efc0ace7e61766e725647c6509e9852
    Fixes: 41c0126b ("block: Make CFQ default to IOPS mode on SSDs")
    Tested-by: Romain Francoise <romain@orebokech.com>
    Signed-off-by: Jens Axboe <axboe@fb.com>
  7. block: Make CFQ default to IOPS mode on SSDs

    Tahsin Erdogan authored and tkawajir committed May 19, 2015
    CFQ idling causes reduced IOPS throughput on non-rotational disks.
    Since disk head seeking is not applicable to SSDs, it doesn't really
    help performance by anticipating future near-by IO requests.
    
    By turning off idling (and switching to IOPS mode), we allow other
    processes to dispatch IO requests down to the driver and so increase IO
    throughput.
    
    Following FIO benchmark results were taken on a cloud SSD offering with
    idling on and off:
    
    Idling     iops    avg-lat(ms)    stddev            bw
    ------------------------------------------------------
        On     7054    90.107         38.697     28217KB/s
       Off    29255    21.836         11.730    117022KB/s
    
    fio --name=temp --size=100G --time_based --ioengine=libaio \
        --randrepeat=0 --direct=1 --invalidate=1 --verify=0 \
        --verify_fatal=0 --rw=randread --blocksize=4k --group_reporting=1 \
        --filename=/dev/sdb --runtime=10 --iodepth=64 --numjobs=10
    
    And the following is from a local SSD run:
    
    Idling     iops    avg-lat(ms)    stddev            bw
    ------------------------------------------------------
        On    19320    33.043         14.068     77281KB/s
       Off    21626    29.465         12.662     86507KB/s
    
    fio --name=temp --size=5G --time_based --ioengine=libaio \
        --randrepeat=0 --direct=1 --invalidate=1 --verify=0 \
        --verify_fatal=0 --rw=randread --blocksize=4k --group_reporting=1 \
        --filename=/fio_data --runtime=10 --iodepth=64 --numjobs=10
    
    Change-Id: I2311c1b349092d5d6afe5200037f6aeccf506e04
    Reviewed-by: Nauman Rafique <nauman@google.com>
    Signed-off-by: Tahsin Erdogan <tahsin@google.com>
    Signed-off-by: Jens Axboe <axboe@fb.com>
  8. acpu: CPU Underclock

    tkawajir committed Sep 21, 2015
  9. lge_touch_core: Fix logic

    EmmanuelU authored and tkawajir committed Aug 15, 2015
    There can be a case where the IRQ wake is never disabled, as DT2W/S2W was disabled while the screen was on.
  10. lge_touch_core: Prevent unbalanced IRQ

    EmmanuelU authored and tkawajir committed Aug 13, 2015
    ts->client->irq has the potential of being disabled before it is enabled if the user attempts to wake screen using s2w/dt2w before using the power button at least once (before early_suspend is called).
  11. dt2w: Check screen on state

    jollaman999 authored and tkawajir committed Aug 3, 2015
    This will prevent screen state go back to suspend state after screen turned on.
  12. Revert "dt2w: Add spinlock to 'detect_doubletap2wake'"

    jollaman999 authored and tkawajir committed May 9, 2015
    This reverts commit d49c9c18be35a06286dc80b4b5ec2a89414d20e4.
    
    Conflicts:
    	drivers/input/touchscreen/doubletap2wake.c
  13. dt2w: Remove 3 taps wake solution and optimize codes

    jollaman999 authored and tkawajir committed May 5, 2015
    Conflicts:
    	drivers/video/msm/mipi_lgit.c
  14. dt2w: Fix initializing

    jollaman999 authored and tkawajir committed Apr 28, 2015
  15. gproj: Enable S2W and DT2W

    EmmanuelU authored and tkawajir committed Aug 12, 2015
  16. DoubleTap2Wake and Sweep2Wake Fixes

    jollaman999 authored and tkawajir committed Jul 17, 2015
  17. DoubleTap2Wake and Sweep2Wake

    showp1984 authored and tkawajir committed Jul 17, 2015
  18. sound: Port over FauxSound

    tkawajir committed Sep 13, 2015
  19. cpu_input_boost: Implement IDLE boost state

    EmmanuelU authored and tkawajir committed Jun 11, 2015
    Previously, there were only two states (boost and unboost). They are handled in a CPU notifier, meaning that they will boost/unboost everytime there is a policy update, rather than when there is a boost queued. So introducing this intermediary state will prevent events from occuring when they weren't called.
    
    In my edit of this driver, this also prevents the stored user minfreq from being overwritten by the current boost freq (because multiple boosts may be called right after each other before an unboost).
  20. gproj: Enable Intelliplug

    EmmanuelU authored and tkawajir committed Jun 11, 2015
    Still testing stability
  21. arch: Implement Faux's Intelliplug

    EmmanuelU authored and tkawajir committed Jun 11, 2015
    As much as I despise shying away from QC's mpdecision, I was faced with a decision. My CPU toggle features piss off mpdecision, which goes hectic in the logs because it doesn't know what to do. Atleast if I use Intelliplug, I can tweak the source to add in my own conditions for when a CPU is disabled. Blame QC being closed source for whatever reason
  22. gproj: Enable more govenors

    EmmanuelU authored and tkawajir committed Jun 9, 2015
  23. cpufreq: smartass2: Implement suspend notifiers

    EmmanuelU authored and tkawajir committed Jun 9, 2015
    Also tweak some dbs
  24. cpufreq: Add a few govenors

    EmmanuelU authored and tkawajir committed Jun 9, 2015
    Adaptive, Intellidemand, Lionheart, Smartass V2, and Wheatley