add-on) we create a breadth-first sorted image list and use that to
search for symbols.
* Added support for preloading libraries. The environment variable
LD_PRELOAD can contain a whitespace-separated list of shared objects
that will be loaded before the program. This allows to replace
symbols without changing the executable or libraries.
* Resolved TODO in load_program() regarding the order of remapping the
images and initializing the dependencies (problem fixed in r28453).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28455 a95241bf-73f2-0310-859d-f6bbb57e9c96
used into the file name. This makes it easier to find the thread(s) one
is looking for.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28446 a95241bf-73f2-0310-859d-f6bbb57e9c96
- code is disabled yet as the bootloader doesn't have add_boot_item.. will need to pass via kernel args
- add a GetFileMap() method to the vfs, and implement it in FAT code.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28445 a95241bf-73f2-0310-859d-f6bbb57e9c96
I am also not happy with the acceleration yet and as reported
by others, there are problems with real mice as well (now wheel
support anymore). With the plain PS/2 driver, I can slide my
finger slowly over the touchpad and the cursor would react/follow
precisely the movement. In Synaptics mode however, there are
unexpected pauses in the movement of the cursor. In any case, the
patch is finally in and I or anyone else can continue to work
on it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28443 a95241bf-73f2-0310-859d-f6bbb57e9c96
added, if their creation event was now or in the future. Obviously we're
only interested in images that do already exist, though. Also get rid of
"new" images that already have been deleted in the meantime.
Fixes problem that for some threads (almost) no images were added and
thus no functions could be resolved.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28441 a95241bf-73f2-0310-859d-f6bbb57e9c96
1) If a view contained the point, but had children, that view would never be returned as a result, even if none of the children matched.
2) When converting coordinates to the child's coordinate space, it was using the bounds rectangle rather than the frame. This in most cases had the result that the coordinate was unchanged, and thus messed up the search completely.
This fixes ticket #3000.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28440 a95241bf-73f2-0310-859d-f6bbb57e9c96
fix a potential deadlock.
* Journal::Lock() now accepts another parameter that specified whether child
transactions should be split - this is nothing you would want in normal
operation unless the parent transaction is only there to prevent others from
writing (such as with the block allocator check stuff).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28438 a95241bf-73f2-0310-859d-f6bbb57e9c96
the old bfs_shell. This is probably not how Ingo anticipated this to be
used :-)
* It still seems to work, though, haven't yet tested on a partition with harder
errors.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28437 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Implemented a small app "checkfs" to check partitions and put it on the image.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28435 a95241bf-73f2-0310-859d-f6bbb57e9c96
also for error check mutexes, otherwise the next pthread_mutex_lock()
will fail.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28428 a95241bf-73f2-0310-859d-f6bbb57e9c96
patch wrongly. This should hopefully fix it. Only my coding style cleanup
history should be "lost" this way.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28426 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Hopefully fixed most of the coding style violations
* ps2_trackpoint.h had the wrong header guard
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28425 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Applied the changes that were done to MouseInputDevice:
- use BObjectList,
- take adventage of BPathMonitor node monitor message fieds
- remove the device in the polling thread upon ioctl() error
* Added TODOs about refactoring the code together with MouseInputDevice.
Untested, but the code is so similar, I am pretty confident it still works.
(famous last words... will test soon anyways)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28421 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added myself to Mouse and Keyboard add-ons for my recent work on them.
* Small cleanup in KeyboardInputDevice.h-
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28420 a95241bf-73f2-0310-859d-f6bbb57e9c96
random SHA hashes.
* Moved AdaptiveBuffering into its own file.
* Fixed updating a hash file.
* Implemented the "consistency_check" app that checks if a file has changed,
and prints warnings if there are any.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28419 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Implemented Synaptics touchpad support in the PS2 bus_manager by
refactoring/splitting the structure some and adding touchpad device
handling.
* Implemented Touchpad input_server device add-on
* Created Touchpad preflet for configuring advances Synaptics touchpad
options like scroll region (both horizontal and vertical) as well
as other neat stuff
Thanks a lot, Clemens!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28416 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Unfortunately, there still seems to be a problem in the hash generation...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28412 a95241bf-73f2-0310-859d-f6bbb57e9c96
problem in TextSearch. After the change, the scrollbar and child view layout
would be messed up there. The reason is that TextSearch calls
scrollview->ResizeToPreferred() prior to adding it to the window. In this
situation, the child views (scrollbars, target view) do not follow the parent
view. Before r28258, ResizeToPreferred() would not change the size of the
view (calling it in TextSearch is stupid anyways, since it is layouted later
in the code). I have thought about how to best fix this. I know 100% that there
is code out there that will mess with scrollbar layout. So it wouldn't be a
good option to refactor the layout out of BScrollView::DoLayout() and calling
that method from AttachedToWindow(), although that seems like the cleanest
option. Instead, I opted to simply reject resizing in ResizeToPreferred()
when the scroll view is not yet attached to a window. What do others think?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28409 a95241bf-73f2-0310-859d-f6bbb57e9c96
acquire_sem_etc(), but treat it as an error instead. This allows
to kill device polling threads in the input_server and prevents
a busy loop in the kernel then. Before the input_server was shutting
down devices upon quit (happens only when restarting it), this
busy loop could also be observed, since then polling threads would
be quit on exit of the team.
* Supply B_INFINITE_TIMEOUT for the MouseDevice instead of 0. Does not
change anything, but was probably not intended.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28407 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Started a file consistency checker; right now, it will just compute a SHA256
hash value for every file, and dump it to stdout.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28406 a95241bf-73f2-0310-859d-f6bbb57e9c96
