install interrupt handlers in init_driver().
The downside of this is that you can now only use F12 to drop into
the debugger when the console appeared (not before).
This way, the driver no longer causes ps2_hid to not be able to
disable or enable the keyboard (which means you can keep them both
installed without worries).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12732 a95241bf-73f2-0310-859d-f6bbb57e9c96
- there can only be one _UPDATE_ message at a time in the queue so we
can stop searching after we hit the first one
- mouse coordinates are always send in screen coordinates (unlike R5,
which means this is a compatibility problem), so we need to convert
them even for the current view.
Apps should now work with the old synchronous controls method (even
though their drawing updates look clumsy and are slow compared to
asynchronous controls for whatever reason).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12730 a95241bf-73f2-0310-859d-f6bbb57e9c96
Not yet used, though - we probably need to rearrange the source files a bit.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12727 a95241bf-73f2-0310-859d-f6bbb57e9c96
myriad of small bugs here and there, as well as some very odd coding techniques:
- the "Minimize" property was not handled
- the "Minimize" property was not settable
- the property/scripting stuff was horrible, anyway
- there are more and better error codes than B_ERROR (could someone tell the
app_server guys? :))
- added some ToDo items here and there
- and much more I don't remember
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12723 a95241bf-73f2-0310-859d-f6bbb57e9c96
messages from the port.
BView::GetMouse() now calls this function if it was called from the window's
thread and thus blocking the message loop.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12716 a95241bf-73f2-0310-859d-f6bbb57e9c96
just those before the first mouse message.
This should be more correct and look better.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12715 a95241bf-73f2-0310-859d-f6bbb57e9c96
- it returned on _UPDATE_ messages without a mouse position
- it no longer calls DispatchMessage() for everything anymore,
however, it will still call BWindow::DispatchMessage() directly
for _UPDATE_ messages
- it didn't care for B_MOUSE_DOWN messages
- it didn't unlock the queue in case it found a message.
(this message actually reflects the differences to r12683 of this
file, but the newer one r12705 was even more broken, but in other
ways)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12714 a95241bf-73f2-0310-859d-f6bbb57e9c96
Looks like that, when called with "true" as third parameter,
it "eats" all the input messages like B_MOUSE_UP/B_MOUSE_MOVED. That means our implementation isn't correct.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12699 a95241bf-73f2-0310-859d-f6bbb57e9c96
will return true in the former case).
vm_delete_areas() is now using this information to print out a warning
in this case (so that a missing vm_put_area() can now be found easier).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12693 a95241bf-73f2-0310-859d-f6bbb57e9c96
following 1152 MB - that area only guarantees that the heap can grow this much before
the application need the memory for something else. And even then, the heap range
is reused from top-to-bottom, allowing for maximum heap usage. Of course, if the
memory after the heap range is not claimed yet, it can still be claimed by the heap,
too. Added new syscall to create the reserved range.
Fixed a bug in vm_delete_areas(): when it removed reserved areas, the area list
could get messed up.
Fixed a bug in resize_area(): resized areas could never be deleted (missing vm_put_area())!
resize_area() now supports reserved regions (but not perfectly yet, see ToDo items).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12692 a95241bf-73f2-0310-859d-f6bbb57e9c96
Jérôme Duval