is read one clock edge too late. This bit is driven low by
slave (as any other input data bits from slave) when the clock
is LOW. The current code did read the bit after the clock was
driven high again.
From OpenBSD (from FreeBSD).
Another small change
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13822 a95241bf-73f2-0310-859d-f6bbb57e9c96
The unflatten time is now reduced to about a third of the current BMessage implementation but it's still
about half as quick as R5 (we're talking about microseconds here).
A third version of BMessage that operates purely on a flat buffer is in the works. We'll see which one
will be faster for normal uses.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13821 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added the respective case statement in AppServer::DispatchMessage().
The code that actually activates the app is still missing.
* Removed the remnants of the old way of notifying the registrar about
what app got activated (the activated client window did that).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13820 a95241bf-73f2-0310-859d-f6bbb57e9c96
class runs it, too.
No real message processing is done yet, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13816 a95241bf-73f2-0310-859d-f6bbb57e9c96
the MessageLooper class - the other part is called from there as virtual
_PrepareQuit().
Moved the class documentation to the source file.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13815 a95241bf-73f2-0310-859d-f6bbb57e9c96
be improved a bit (Quit() and _MessageLooper() are empty right now).
Removed ServerApp::PingTarget().
Hopefully cleared some confusion about ServerApp::fClientLooperPort and fClientToken
(previously fHandlerToken), even if it's currently unused.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13807 a95241bf-73f2-0310-859d-f6bbb57e9c96
- when undoing the first change, any later change would make that first change reappear
- in hex mode editing, changes were not merged because they changed the same byte
Updated version info.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13801 a95241bf-73f2-0310-859d-f6bbb57e9c96
their path could be invalid in other contexts (e.g. the debug server might
be unabled to find them). This seems to be what BeOS does, too.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13796 a95241bf-73f2-0310-859d-f6bbb57e9c96
user application performs a division by zero or causes a general
protection fault. For some exceptions (e.g. machine check) I wasn't
quite sure whether they can be caused by user apps at all, so we panic()
in those cases. Wouldn't harm, if someone more knowledgable would check
this, though.
* Removed the unused fault handling stuff, respectively moved the little
that was used into x86/arch_int.c.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13795 a95241bf-73f2-0310-859d-f6bbb57e9c96
grist caused bfd to be compiled using gdb's config.h. This made it think
Haiku had no fcntl() and thus assumed shared objects were opened r/w instead
of read-only, which made it write back data when closing the files. So this
fixes the problem that gdb damages the shared objects it had loaded.
Basically two questions remain:
1) Why does BFD write something into the files that makes them invalid?
2) Why was it possible to write something into the read-only opened files?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13791 a95241bf-73f2-0310-859d-f6bbb57e9c96
Passes all unit tests now and works on Haiku too. Speed is not yet optimized and Message2.cpp is still not cleaned up.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13785 a95241bf-73f2-0310-859d-f6bbb57e9c96
It's currently really broken so don't even try to test it, but you can still review it ;-).
Message2.cpp is not yet cleaned - more to come...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13784 a95241bf-73f2-0310-859d-f6bbb57e9c96
CDDB data is written in R5 format with the exception of CD:key (still figuring out what to do about that)
Fixed some update notification problems with changing CDs
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13777 a95241bf-73f2-0310-859d-f6bbb57e9c96
use it. It is not (yet) included in the build and won't break anything.
As we now only have thin wrappers around the *Data() functions, the templatized implementation does
not make much sense anymore and wouldn't work either.
I started this new implementation to be as clean as possible. Instead of using a std::map and
BDataBuffer it uses BList and BMallocIO. It passes the unit tests and it even seems to be a bit quicker
in some tests (but not as quick as the R5 one).
Flattening/Unflattening does not work yet so you can't use it under Haiku right now. It's completely work in progress (I started it just 4 hours ago).
Shout if you see something completely broken, reviews welcome.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13776 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Print the debugger message in case the debugged team called debugger(),
and the description of an occurred exception respectively.
* Properly keep gdb's internal thread list up to date. This fixes the
problem that an attached debugger always resumed all threads of the
debugged team.
* A bit of cleanup of the attaching code.
Discovered an ugly bug: When invoking gdb with an executable -- regardless
of whether attaching gdb to a running process or just starting a debugger
session with the executable -- the executable is modified. I tested with
"crashing_app" and in the second debug session gdb fails to read the debug
info from the file and encounters a weird error when closing the file:
"No space left on device." I have the suspicion that this is another bug
in Axel's VM/file cache pet. :-P
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13775 a95241bf-73f2-0310-859d-f6bbb57e9c96
