Re: [PATCH v2 0/6] Intel Integrated Sensor Hub Support (ISH)

From
Srinivas Pandruvada <srinivas.pandruvada@linux.intel.com>
Date
2016-08-31 14:35:29
Also in
linux-iio, lkml
Reply to
Grant Likely, 2016-08-31
On Wed, 2016-08-31 at 15:19 +0100, Grant Likely wrote:
On Wed, Aug 24, 2016 at 10:23 PM, Jonathan Cameron [off-list ref]
wrote:
quoted
On 24/08/16 22:14, Jiri Kosina wrote:
quoted
On Wed, 24 Aug 2016, Grant Likely wrote:
quoted
quoted
quoted
v2:
- Overview in documentation show analogy with usbhid
implementation
- sparse errors for statics. Also pointed by Jiri
- Clearly marking exported function header file. Clean up
all exports
unused inteface functions
- Changed to tristate from boolean as pointed by Jiri:
this required remove/unload functions
- Prevent crash when ISH enabled on non supported platform
- Break client.c to smaller part by seprating buffer
allocations
- move bus register/unregister to ishtp module
- There is only one config symbol INTEL_ISH_HID, removed
silent
config for TRANSPORT and IPC
Tested-by: Grant Likely <redacted>

On an HP Spectre x360 laptop using v4.7-rc5.
Hey Srinivas. Any progress on this patch series?
The HID part (with patch #5 omitted) should be in linux-next
through
hid.git already.
The one IIO patch was pulled by Greg KH last night so hit linux
next
today.  Hence all on it's way by the sound of it!
Nice!

Unfortunately, I've just hit a new bug after updating to v4.8-rc4.
4.7.0-rc6 works fine.

The kernel boots, and the driver loads, but the orientations are
wrong. It appears that the X/Y is getting swapped:

Normal orientation: display rotated 90 degrees CW
Rotated 90 degrees CW: display normal orientation
Rotated 180 degrees (upside down): display rotated 90 degrees CCW
Rotated 90 degrees CCW: display rotated 180 degrees
This is  also observed in all non ISH platforms too. I bisected it to
some commit, which I don't know how this impacts. Yesterday I sent
email to the list. Try reverting this, you should be fine.

 commit 703b5faf22fbddf984a361e6555f3a03fdba63d9
Author: George Spelvin [off-list ref]
Date:   Fri Jun 10 00:22:12 2016 -0400

    fs/dcache.c: Save one 32-bit multiply in dcache lookup

    Noe that we're mixing in the parent pointer earlier, we
    don't need to use hash_32() to mix its bits.  Instead, we can
    just take the msbits of the hash value directly.

    For those applications which use the partial_name_hash(),
    move the multiply to end_name_hash.

    Signed-off-by: George Spelvin [off-list ref]
    Signed-off-by: Linus Torvalds [off-list ref]

Thanks,
Srinivas

Cheers,
g.
Thread (17 messages) 17 messages, 4 authors, last reply 2016-08-31
Keyboard shortcuts
hback out one level
jnext message in thread / next series-diff position
kprevious message in thread / previous series-diff position
ldrill in
Escclose help / fold thread tree
?toggle this help