- has_signals_pending() is not declared in Be headers, and it isn't declared in
our KernelExport.h anymore, too
- removed snooze_etc() from KernelExport.h, as it's already defined in OS.h
(and really exported by libroot.so).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12506 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fixed a small glitch in drawing.
Removed an unneeded Sync() in Draw().
Removed some unnecessary virtual method calls.
Improved drawing of the current slider's value.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12505 a95241bf-73f2-0310-859d-f6bbb57e9c96
The properties are now the same as in the Be version - there is no reason (IMO) for usage
comments like these; it's a public class, and its scripting usage should be documented in
the BeBook, if anywhere.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12503 a95241bf-73f2-0310-859d-f6bbb57e9c96
keyboard and mouse part), since for some reason, the app_server refuses to work
with the input_server for me now):
- keyboards are now actually detected, the keyboard device is only published if
there actually is a keyboard
- keyboard_close() no longer calls put_module() for the ISA bus manager; it's
sharing that resource with the mouse driver.
- rewrote the keyboard command handshake; now, the acknowledge byte is always
considered, and it's now also safe to call keyboard commands with the interrupt
handler installed (bytes read are now safely routed through the handler).
- keyboard_open() now also sets the PS/2 command byte to enable keyboard
interrupts (this may actually have been the source of all evil - ie. keyboard
not working after having touched the mouse)
- many commands now try again several times if they failed
- ps2_get_command_byte() is now safe to be called when the keyboard driver
is up and running, too (it's now locally buffered)
- more and better error checks
- possibly more I forgot about...
- general cleanup.
Note, there is still some functionality missing from the keyboard driver:
- ctrl/alt/del handling
- key repeat (delay, time, non-repeating)
Repeat stuff might better be moved to the input_server add-on, anyway, for
more flexibility and better performance.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12498 a95241bf-73f2-0310-859d-f6bbb57e9c96
- Only the active channel slider is highlighted now, unlike Beos's version. I like this more.
- Added an (experimental) feature: when changing a slider's value with the mouse, its value is displayed (requested by Axel, can you check if it's what you wanted ? http://burton666.neoni.net/shots/channelslider.png ).
There are still some problems with the calculations of coordinates, I'd like someone to review my code.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12496 a95241bf-73f2-0310-859d-f6bbb57e9c96
Uncomment in Jamfile "#APPSERVER_TEST_MODE = 1 ;" to test app_server with input_server
Uncomment in InputServer.h "//#define R5_CURSOR_COMM" to enable cursor comm when appserver BPortlink comm is used
Default mode is R5 comm if TARGET != haiku
and appserver BPortLink comm when TARGET = haiku
For APPSERVER_TEST_MODE, make sure to change the ViewInputDevice path in AddOnManager.cpp
To test with app_server, enable LaunchCursorThread() in AppServer.cpp and uncomment "#define INPUTSERVER_TEST_MODE 1" in ViewHWInterface.cpp
Also make sure to change the input_server path in AppServer.cpp
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12493 a95241bf-73f2-0310-859d-f6bbb57e9c96
we write view events to a port so that the ViewInputDevice gets them and have them processed by input_server, and then app_server
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12489 a95241bf-73f2-0310-859d-f6bbb57e9c96
Lots of cleanup:
- moved B_NO_ENABLE_COUNTER flag definition out of int.h to KernelExport.h, as it's
described in the BeBook (although it's probably not really used that often :))
- int.c no longer has any platform dependent code (+ 0x20 on interrupt numbers is gone);
it's now entirely handled in the arch/x86/ section.
- the io_vectors[] is now statically initialized, instead of allocated from the heap
- removed {install|remove}_interrupt_handler(); they weren't that useful, arch_smp_init()
is now calling install_io_interrupt_handler() correctly instead
- introduced a new arch_int.h header file that currently contains NUM_IO_VECTORS only
(though on x86, it also has ARCH_INTERRUPT_BASE == 0x20).
- changed the return type from {install|remove}_io_interrupt_handler() from "long" to
"status_t"
- rearranged and cleaned the PIC initialization code, made the PIC code more prominent
- changed comments that talk about a non existing 8239 (the PIC chip is actually 8259)
- moved arch/x86/interrupts.h to the source directory, as it's not used outside
- added BeOS compatible interrupts_enabled() function, that should replace our
equivalent (and private) are_interrupts_enabled()
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12477 a95241bf-73f2-0310-859d-f6bbb57e9c96
so we shouldn't overwrite it with zero...
I must have tested an older version of the driver by accident; now it
actually works again under R5.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12475 a95241bf-73f2-0310-859d-f6bbb57e9c96
Apparently, the net_server does not use read()/write() but the kernel
syscalls directly. Even worse, it obviously ignores error values like
B_WOULD_BLOCK - the return length has to be set even in case of error.
The driver did not work at all under R5 net_server since then...
Some other minor changes.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12474 a95241bf-73f2-0310-859d-f6bbb57e9c96
