intel_extreme: change i2c_send_receive to a hook

common: i2c/ddc uses a 7-bit address for EDID.

Change-Id: Ic1bba2a23174c671bd7374104596c22433bd343a
Reviewed-on: https://review.haiku-os.org/c/haiku/+/5171
Tested-by: Commit checker robot <no-reply+buildbot@haiku-os.org>
Reviewed-by: Adrien Destugues <pulkomandy@gmail.com>

accelerants common: fix crash on x86 i2c tracing

PVS V564: use of bitwise operators on booleans

Change-Id: I0a0cd7ddba0abaef27700f1ba05bf99bb8c7a400
Reviewed-on: https://review.haiku-os.org/c/1607
Reviewed-by: waddlesplash <waddlesplash@gmail.com>

* small bit of common i2c / ddc white space cleanup
* small bit of tracing cleanup
* no functional change


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42794 a95241bf-73f2-0310-859d-f6bbb57e9c96

* there's one 'l' in Philips
* no functional change


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42778 a95241bf-73f2-0310-859d-f6bbb57e9c96

* reading through i2c specs, little comment cleanup
* add a few notes for future i2c bit-bangers
* cleanup of tracing
* no real functional change


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42777 a95241bf-73f2-0310-859d-f6bbb57e9c96

Better watch your bools in C code. In C99, the bool type of the argument to
send_bit() causes a type conversion from the value handed in to 0 or 1. This
clashed with the usage in send_byte(), that hands over a shifted byte. The
argument was converted to true when it had any value other than 0, whereas
before (where a bool simply was an int) it would have just handed over the value
directly. Therefore the logic in send_bit() that simply masked off the lowest
bit of the value would now not work anymore.
This fixes EDID failing on GCC4 and therefore fixes #2275, the last issue of
#4084 and may also affect #2780.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32593 a95241bf-73f2-0310-859d-f6bbb57e9c96

modified the 100kHz timing inside the DDC common accelerant code. If delays with values near the timer resolution are required, the values should always have one resolution step added since otherwise the minimum delay isn't quaranteed. the 400khz timing needs fixing as well I guess... This modification fixes at least ticket #4084 where a DDC monitor isn't detected otherwise.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32540 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix I2C tracing, style cleanups.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25749 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Separated I2C from DDC a bit more.
* i2c_bus now contains a i2c_timing structure, so that you don't need
both to talk to the I2C bus.
* Therefore, there is now a void ddc2_init_timing() function to get the
the timing DDC needs.
* Cleanup in radeon's monitor_detection.c, and updated it to work with
the DDC/I2C changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22265 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Vasilis Kaoutsis - thanks!:
* Fixed some warnings.
* Style cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@21774 a95241bf-73f2-0310-859d-f6bbb57e9c96

Upgrade to version 4.1 of radeon driver.
Includes some common routines which can be used by other accelerants.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@8406 a95241bf-73f2-0310-859d-f6bbb57e9c96

* small bit of common i2c / ddc white space cleanup
* small bit of tracing cleanup
* no functional change


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42794 a95241bf-73f2-0310-859d-f6bbb57e9c96

* there's one 'l' in Philips
* no functional change


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42778 a95241bf-73f2-0310-859d-f6bbb57e9c96

* reading through i2c specs, little comment cleanup
* add a few notes for future i2c bit-bangers
* cleanup of tracing
* no real functional change


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@42777 a95241bf-73f2-0310-859d-f6bbb57e9c96

Better watch your bools in C code. In C99, the bool type of the argument to
send_bit() causes a type conversion from the value handed in to 0 or 1. This
clashed with the usage in send_byte(), that hands over a shifted byte. The
argument was converted to true when it had any value other than 0, whereas
before (where a bool simply was an int) it would have just handed over the value
directly. Therefore the logic in send_bit() that simply masked off the lowest
bit of the value would now not work anymore.
This fixes EDID failing on GCC4 and therefore fixes #2275, the last issue of
#4084 and may also affect #2780.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32593 a95241bf-73f2-0310-859d-f6bbb57e9c96

modified the 100kHz timing inside the DDC common accelerant code. If delays with values near the timer resolution are required, the values should always have one resolution step added since otherwise the minimum delay isn't quaranteed. the 400khz timing needs fixing as well I guess... This modification fixes at least ticket #4084 where a DDC monitor isn't detected otherwise.

git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@32540 a95241bf-73f2-0310-859d-f6bbb57e9c96

Fix I2C tracing, style cleanups.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@25749 a95241bf-73f2-0310-859d-f6bbb57e9c96

* Separated I2C from DDC a bit more.
* i2c_bus now contains a i2c_timing structure, so that you don't need
both to talk to the I2C bus.
* Therefore, there is now a void ddc2_init_timing() function to get the
the timing DDC needs.
* Cleanup in radeon's monitor_detection.c, and updated it to work with
the DDC/I2C changes.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@22265 a95241bf-73f2-0310-859d-f6bbb57e9c96

Patch by Vasilis Kaoutsis - thanks!:
* Fixed some warnings.
* Style cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@21774 a95241bf-73f2-0310-859d-f6bbb57e9c96

Upgrade to version 4.1 of radeon driver.
Includes some common routines which can be used by other accelerants.


git-svn-id: file:///srv/svn/repos/haiku/trunk/current@8406 a95241bf-73f2-0310-859d-f6bbb57e9c96