values. The implementation needs to sum up fractional movement, not
truncate to zero. Before this change, the mouse would be pretty much unusable
at lower speeds/acceleration. Now it is guaranteed to move.
* No need to memset() before ioctl(), the driver does that anyways.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28669 a95241bf-73f2-0310-859d-f6bbb57e9c96
DataTranslations list view. This should fix it. MessageReceived() was not
forwarding to the immediate inherited class.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28665 a95241bf-73f2-0310-859d-f6bbb57e9c96
a message.
* The DesktopSettings class is now using that to send the new
AS_SYSTEM_FONT_CHANGED message to all windows.
* The ServerWindow now propagates font changes to its decorator, causing it
to update its drawing. That means changing the bold font in the "Fonts"
preferences application will instantly change all window titles.
* Factored out a _RebuildAndRedrawAfterWindowChange() out of several Desktop
methods, simplifying some code.
* The DefaultDecorator no longer calls _DoLayout() twice (through SetLook()),
but instead calls the new _UpdateFont() method now also called by
FontsChanged(), and SetLook().
* BWindow::GetDecoratorSettings() now also includes "tab frame" BRect with the
exact footprint of the tab, allowing apps to know the size of the tab to
position itself accordingly.
* Automatic white space cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28664 a95241bf-73f2-0310-859d-f6bbb57e9c96
it to the stream. This caused Read()/Write() to need two syscalls for nothing
(this only caused the actual stream to share the same position with the
BBufferIO, something you just cannot rely on when using buffered I/O).
* Anyway, this reduces the time VirtualBox needs to open some RAW test images
from over 4 minutes to less than 15 seconds...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28662 a95241bf-73f2-0310-859d-f6bbb57e9c96
be used.
* Added tty::ref_count. Each cookie keeps a reference. Only when a
cookie is freed the reference is surrendered. A tty is considered used
as long as it is still referenced. This allows to access a tty through
the cookie, even if it already has been closed.
* Fixed tty_deselect(). It was keeping registered select events when
called after the cookie has been closed. The referenced select_sync
structure would become invalid and later attempts to send select
notifications for the tty could crash. Fixes#3126.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28651 a95241bf-73f2-0310-859d-f6bbb57e9c96
window being the focus window that is a subset of the specified window.
* This is now used to bring the window to front belonging to a floating
or modal window (if on another workspace), ie. Desktop::ActivateWindow()
should now work with modal and floating windows.
* Fixed typo (in Window.cpp).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28649 a95241bf-73f2-0310-859d-f6bbb57e9c96
will now accepted and regarded as sparse file data. FileMap::_Add() also
correctly joins multiple vecs with that offset together, FileMap::Translate()
will always report offset -1 even for offsets into that extent.
* read_file_io_vec_pages() (or rather, its backend common_file_io_vec_pages())
now supports sparse files, and will just clear the memory it should read from
offset -1 instead of passing a request to the vnode.
* ext2 now correctly reports sparse files. This should close bug #2889, as well
as #975.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28648 a95241bf-73f2-0310-859d-f6bbb57e9c96
code duplication and will make maintaining it much easier.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28647 a95241bf-73f2-0310-859d-f6bbb57e9c96
classes (BView, BWindow, BAlert, BButton - BTextView should be part of this,
too, to make BAlerts work).
* However, it's not that simple, because there is often no way to return an
error. Most of that code obviously assumes to be able to throw exceptions
(it's just not communicated to the caller). Maybe we should just start
documenting exceptions for R1 (and properly use exceptions later on).
* Automatic white space cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28646 a95241bf-73f2-0310-859d-f6bbb57e9c96
memory to free was empty, but didn't check the list with objects to
delete. So those were queued until someone used deferred_free().
Should fix#3128.
* Run the daemon once a second instead of every five seconds, so memory
is recycled a little quicker.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28644 a95241bf-73f2-0310-859d-f6bbb57e9c96
* I feel the Synaptics driver is now good enough to give it more exposure
and turned it on again. If it gives you trouble for some reason, you can
turn it off again in ps2_dev.c, line 105.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28643 a95241bf-73f2-0310-859d-f6bbb57e9c96
won't be called, the control thread will remove the device anyways.
* Turned off the debug output I left on accidentally in KeyboardInputDevice.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28642 a95241bf-73f2-0310-859d-f6bbb57e9c96
in Send(), which uses SaveAsDraft(). This fixes#1020. Thanks to kaoutsis and
ksmith for their investigation!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28641 a95241bf-73f2-0310-859d-f6bbb57e9c96
* removed superfluous #include <config.h> which was protected by an #ifdef
that evaluated to false - so the file never got included, but jam tried
to locate it and usually failed, unless there happens to be a config.h
in the current working directory.
This fixes a spurious dependency from regex.c to the config.h in
src/libs/iconv.h if you invoked jam from there.
* fixed two warnings by always including stdlib.h
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28639 a95241bf-73f2-0310-859d-f6bbb57e9c96
* adjusted libtextencoding's Jamfile
* added libiconv.so to image
* added iconv headers to optional package Development (under 3rdparty)
* removed old private version of libiconv from textencoding
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28631 a95241bf-73f2-0310-859d-f6bbb57e9c96
the libiconv that was available for R5
* cleaned up iconv.h
* moved public libiconv headers (iconv.h and localcharset.h) into a
specific folder in headers/libs
* renamed config.h to libiconv_config.h in order to circumvent strange
problems with regex.c from glibc picking it up
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28630 a95241bf-73f2-0310-859d-f6bbb57e9c96
(config.h, iconv.h and localcharset.h were created by running 'configure'
on haiku)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28629 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Shuffled functions around to separate command functions from their support
functions.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28624 a95241bf-73f2-0310-859d-f6bbb57e9c96
Taken from ftp://mir1.ovh.net/lv0/ftp.kernel.org/pub/scm/linux/kernel/git/jejb/merge-tree/arch/powerpc/boot/hack-coff.c
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28618 a95241bf-73f2-0310-859d-f6bbb57e9c96
the fixes applied to the kernel version of it (most notably a correctly
working block_cache_discard(), and cache_detach_sub_transaction()).
Also switched to the new notification functions, even though it still works
synchronously in the fs_shell.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28617 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Whatever is the cause of #2733, this should at least not make it crash.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28615 a95241bf-73f2-0310-859d-f6bbb57e9c96
first chunk of a possibly multi-buffer mbuf. This fixes#2840, thanks a lot!
* Fixed warning in _bus_dmamap_load_buffer().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28599 a95241bf-73f2-0310-859d-f6bbb57e9c96
I just added a check in bmtphy_probe() as ENXIO is negative on Haiku.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28597 a95241bf-73f2-0310-859d-f6bbb57e9c96
sure that you can have an old style mouse without scroll wheel and one with attached at the
same time. For example, when I hot-plug my PS/2 mouse with wheel, the IBM trackpoint will
otherwise already use up the "PS/2 Mouse 1" name.
Unfortunately, hot-plugging the PS/2 mouse on my T60 docking station still does not work
quite right. The PS/2 driver detects everything correctly, the node monitoring works and I end
up with the correct device threads in the input_server. (The notebook is automatically removing
the touchpad and trackpoint devices in this event, which cannot be turned off in the BIOS.)
However, the mouse does not move. In the syslog, I see one message
"ps2: strange mouse data, x/y overflow, trying resync" after the the output from the add-on
manager in the input_server that it has added the new device. When I restart the input_server,
it works fine, even though the same devices are detected and polling threads are running.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28591 a95241bf-73f2-0310-859d-f6bbb57e9c96
functions private and moved them accordingly in the file.
* I forgot to initialize the BObjectList to own the items in
TouchpadInputDevice.
* Changed the methods that read and apply settings in all three addons to be
executed from the control threads only, which fixes race conditions.
* The success of opening a device is no longer checked in the Start() method
of the *Devices. Instead, the control thread checks the device before it
enters the polling loop and cleans up if there was an error. This fixes
non-running devices in the input_server because the PS/2 driver publishes
devices which is has not checked yet for other reasons. It is important,
however, to open() the devices in the Start() hook and not the control
thread, otherwise there are unwanted race conditions in case node monitoring
events are received more than once for the same device. That's the case
for some reason on one of my computers for the AT 0 keyboard.
TODO:
* Combine the Touchpad and Mouse device addon into one, it's almost the
same code except the Touchpad knows more settings and one more control
message.
* Refactor a common base class for Keyboard and Mouse device addon.
* Fix the mouse speed/acceleration. If the speed is lowered from the default
in the preflet, the mouse becomes almost unusable. To fix this, the same
trick should be used as I used in the touchpad kernel driver, which is to
sum up previous mouse moved fractional offsets.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28590 a95241bf-73f2-0310-859d-f6bbb57e9c96
generic page mapping mechanism. This should fix#2902 (will test in a minute).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28584 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Replaced debug_printf() invocations by a macro, which is set to
ktrace_printf() by default.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28581 a95241bf-73f2-0310-859d-f6bbb57e9c96
the per-root-image breadth-first sorted image array. Instead we have a
per-image hook function to resolve the symbols. The default function
uses the sLoadedImages list directly, which is breadth-first sorted
anyway. There's also a BeOS function for old-style symbol resolution
and one for add-ons, which lacks a proper implementation yet (just
uses old-style ATM).
* Made the dl*() functions POSIX compliant:
- dlopen() does no longer use load_add_on(), but loads the object as a
library. It also properly supports a NULL name, now -- the previous
"_APP_" work-around did only work, if this soname was set on the
program (unlikely for programs using this API).
- Implemented RTLD_{GLOBAL,LOCAL}.
- dlsym() looks up symbols properly now, i.e. not just in the given
image, but breadth-first for an actual image or in load order for
the global scope. It also supports the not-quite POSIX RTLD_DEFAULT
and RTLD_NEXT extensions. Our RTLD_NEXT finds more symbols than in
Linux (also in later dlopen()ed libraries), but that should be fine.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28568 a95241bf-73f2-0310-859d-f6bbb57e9c96
OpenFile() now returns early when the format is unsupported (don't add the document to recent documents, don't allow to save the document) (bug #3072)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28565 a95241bf-73f2-0310-859d-f6bbb57e9c96
class/namespace. Renamed the B_GRADIENT_* types to TYPE_* as the context
is already given.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28564 a95241bf-73f2-0310-859d-f6bbb57e9c96
* fStyleMap could be deleted more than once in certain situations.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28563 a95241bf-73f2-0310-859d-f6bbb57e9c96
license was nowhere mentioned. I added an explaination to the copyrights section
and also mentioned that clicking a license name will open the respective
license for reading.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28557 a95241bf-73f2-0310-859d-f6bbb57e9c96
to succeed on Linux. FreeBSD fails some tests since it seems to have a
different load order (depth-first instead of breadth-first). Haiku fails
a lot of tests due to its POSIX non-compliant dlopen().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28556 a95241bf-73f2-0310-859d-f6bbb57e9c96
lock held - that was a relict of the past.
* This fixes bug #2535.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28551 a95241bf-73f2-0310-859d-f6bbb57e9c96
bug #3082.
* Also, it now allows to remove daemons in their hook function.
* Added a "daemons" KDL command that dumps all registered kernel daemons, and
resource resizers.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28550 a95241bf-73f2-0310-859d-f6bbb57e9c96
consider the workspaces in the configured count.
* If the window is not on the current workspace after the workspace check,
always move it to the current instead. This lets windows on workspaces
outside of the ones currently configured show up on the current workspace
as if they had the B_NOT_ANCHORED_ON_ACTIVATE flag set.
* This fixes bug #3003.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28549 a95241bf-73f2-0310-859d-f6bbb57e9c96
These were copied from the same code that originally was used for libjpeg
(jpegsrc.v6b.tar.gz) in the JPEGTranslator with a few small changes.
This will be used to implement JPEG lossless transformations in ShowImage in
the way suggested by Michael Lotz in the email linked from the bug.
Next up is changes to ShowImage.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28544 a95241bf-73f2-0310-859d-f6bbb57e9c96
slightly strange redrawing, including scrolling the offscreen view
that it uses in "flicker free" mode (which is the default). Invalidation
does not work in offscreen windows, since the client thread is not running
and certainly won't redraw anything. But that will leave a non-drawable
region on the app_server side of things. Simply don't invalidate in
this case. From what I have seen, redrawing in NetPositive seems to
work fine now.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28538 a95241bf-73f2-0310-859d-f6bbb57e9c96
for most messages, use debug_printf(), cleanup line breaks
* check return code of last link method in a lot more places
* changed some printf() and fprintf() into debug_printf()
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28537 a95241bf-73f2-0310-859d-f6bbb57e9c96
on uninitialized accelerant, but that's what AS_GET_DRIVER_PATH is for.
* This should fix#2847.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28534 a95241bf-73f2-0310-859d-f6bbb57e9c96
in AutoMounter::InitialMountVisitor::Visit(), otherwise restoring
mount options, like read-only mounting, would never work. This
kind of mixes the options of the mount settings, since it partially
remembers the settings even if the option is not "only previously
mounted disks", but it should not hurt anyways. As a side effect,
this should also fix the mount notification sent to Tracker, as
the path should only have been correct for the "mount previous disks"
setting.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28533 a95241bf-73f2-0310-859d-f6bbb57e9c96
gWidthBuffer.
* Tracker PoseView now uses BPrivate::gWidthBuffer instead of it's own
instance.
* TextView.h and PoseView.h are now a little cleaner.
* InterfaceDefs.cpp now deletes gWidthBuffer in _fini_interface_kit_().
* Added binary compatibility support for NetPositive in WidthBuffer.h and .cpp.
Obviously it kind of defeats the purpose of having WidthBuffer neatly tucked
away in the BPrivate namespace, but Haiku should run NetPositive, I guess.
Fixes#2879.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28532 a95241bf-73f2-0310-859d-f6bbb57e9c96
and wcrtomb() functions. I worked around the issue, and added a build
warning so that we don't forget to change it back once we have working
versions of those.
* This lets apps like "ftp", and "sftp" work again.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28531 a95241bf-73f2-0310-859d-f6bbb57e9c96
* fix _SetTime(), was using the wrong * operator, resulting in
an overflow at some point that lead to the mentioned jumping
fixes 2878 and 3057
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28524 a95241bf-73f2-0310-859d-f6bbb57e9c96
as public defines. They are now called THREAD_{MIN|MAX}_SET_PRIORITY to
better reflect what they are for. Minimum priority is now 1, ie. you no
longer can set another thread to the idle priority. This fixes part of
ticket #2959.
* set_thread_priority() will no longer allow to change the priority of the
idle thread to something else. This fixes the rest of ticket #2959.
* Automatic whitespace cleanup in OS.h.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28521 a95241bf-73f2-0310-859d-f6bbb57e9c96
icon in the MediaPlayer Info window. I changed it a bit, so that the
icon retrieval only happens at the file change notification (quite
important, since the info window receives playback position notifications).
I also changed it to take the icon from the file first, if there is one.
Thanks!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28520 a95241bf-73f2-0310-859d-f6bbb57e9c96
and the block cache don't interfere when working on the same blocks.
* This has fixed all kinds of file corruptions I could reproduce before,
therefore likely also bug #3010.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28517 a95241bf-73f2-0310-859d-f6bbb57e9c96
in the cache is the same as in the condition variable. It now uses the
low-contention sCachesLock to accomplish this.
* Also added an ASSERT to make sure the notification is no longer part of the
list at this point.
* Improved KDL command output.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28516 a95241bf-73f2-0310-859d-f6bbb57e9c96
discarded blocks correctly as well.
* cache_detach_sub_transaction() left cached_block::original_data unchanged even
if the parent data was to become current (in case the sub transaction didn't
change the block yet). This could cause outdated blocks to be written back.
* cache_detach_sub_transaction() also set cached_block::previous_transaction
for all blocks, not just the ones with a previous transaction. This could
cause blocks to be written twice for no reason.
* cache_start_sub_transaction() did not change the num_blocks count for
discarded blocks.
* block_cache_discard() now panics if the block was already changed in the
current transaction.
* Improved test application, added more tests, revealing the above bugs in
cache_detach_sub_transaction().
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28514 a95241bf-73f2-0310-859d-f6bbb57e9c96
from the block notifier, the cache could be deleted before we have the chance
to lock it. We now lock the sCachesLock, and see if this cache is still valid.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28512 a95241bf-73f2-0310-859d-f6bbb57e9c96
mixer's controls, so I am removing it.
If someone disagrees, this code can be added back easily.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28509 a95241bf-73f2-0310-859d-f6bbb57e9c96
cache_end_transaction(), and cache_start_sub_transaction()).
* Further work on the test application, it's now actually usable, first test
passes.
* dump_block() did erroneously print 'B' for the dirty flag; now both dirty and
discard have the 'D' (3rd and 5th column).
* block_cache::LowMemoryHandler() is now private (and got an underscore prefix).
* Minor cleanup, shuffled some methods around.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28508 a95241bf-73f2-0310-859d-f6bbb57e9c96
license) and rebased the ExpressionParser from double on the MAPM data type.
Currently, the binary operators are not supported anymore, but the imprecise
calculations were getting on my nerves. I think a lot more neat functions
could now be supported, but I have not looked into it further. I also didn't
dare look closer at the C code of the library, but it seems to be well
tested. It's portable by all means, I guess even if the target platform has
8.3 char file names to hold the code... Luckily, the library inclused a C++
wrapper class for the data type (MAPM) which makes it fairly comfortable to
use and hides the ugly C stuff and messy memory management.
The result seems to be quite nice so far. Previously, I couldn't even calculate
my finances without eventually getting some rounding errors.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28506 a95241bf-73f2-0310-859d-f6bbb57e9c96
wrong check to see if the view was currently visible. This fixes the problem
that tool tips would popup for windows that are located on other workspaces.
* Removed commented out code that is no longer needed.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28498 a95241bf-73f2-0310-859d-f6bbb57e9c96
discarding their changes. This functionality currently only works correctly
when no transactions are used.
* Started test application for the block cache, doesn't do anything yet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28496 a95241bf-73f2-0310-859d-f6bbb57e9c96
* The function is not supposed to return hidden views.
* After iterating over the child views, the "view" variable was clobbered,
so it didn't work to return the current view if none of it's child views
were hit.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28494 a95241bf-73f2-0310-859d-f6bbb57e9c96
window this fixes the tool tip size/layout in apps that use BubbleHelper
(Beam, WonderBrush, ...). Thanks to Rene and Stefano for sending me a test
application.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28489 a95241bf-73f2-0310-859d-f6bbb57e9c96
several translators which used the incorrect MIME type for the base Be Bitmap
Format. Please when adding translators use image/x-be-bitmap, not just
x-be-bitmap. Though I suppose the if statement in ShowImage could be changed to
only look for x-be-bitmap at the end of the string when filtering, I think this
is the proper fix.
While I was editing the translators I also made the naming more consistant by
adding the translator name in parenthesis after Be Bitmap Format for those that
did not have it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28487 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added GNU M4 1.4.12 package to the Development optional package.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28486 a95241bf-73f2-0310-859d-f6bbb57e9c96
SetMouseEventMask() from within it's mouse hooks. Among other things,
scroll bars won't stop scrolling in FFM mode now if you accidentally
leave the window with the mouse, something which is very likely.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28481 a95241bf-73f2-0310-859d-f6bbb57e9c96
both double buffering and single buffering, Invalidate() needs to be
virtual and ViewHWInterface needs to decide where to invalidate it's host
window.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28480 a95241bf-73f2-0310-859d-f6bbb57e9c96
wait_for_thread() doesn't provide that; use waitpid() instead.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28479 a95241bf-73f2-0310-859d-f6bbb57e9c96
for the runtime loader add-on interface. There's a small library
(libltrace_stub.so) that when preloaded reroutes all library calls
through a stub that prints the function name and some of its arguments
to the debug output.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28476 a95241bf-73f2-0310-859d-f6bbb57e9c96
can export a structure containing callback hooks invoked by the
runtime loader when certain image events occur (image loaded,
relocated, initialized, etc.).
* Also added a mechanism to patch image symbols. For an image callback
functions can be installed that patch symbols exported or imported by
the image.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28475 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added new(mynothrow) operators which avoid clashes when also linking
against libgcc.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28474 a95241bf-73f2-0310-859d-f6bbb57e9c96
tool tips in WonderBrush. The reason was that the text rect is getting
smaller and smaller each time the tool tip is shown (even though there
is only one word), and the line break moves one char towards the beginning
each time. After four times, the busy loop would kick in reliably. I cannot
really say that I understand the code, though. But that's the spot anyways.
Stefano, could you have a look?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28471 a95241bf-73f2-0310-859d-f6bbb57e9c96
relative mouse movements. Removed the "history" and replaced it with a method
to accumulate the deltas. Very small deltas are somewhat suppressed, but still
accumulate. Overall, this improves the touchpad sensitivity for small movements
without introducing unwanted jitter. This also keeps the direction of slightly
"non-straight" movements better. I also changed the scale somewhat so that
the acceleration does not feel too little anymore.
These are the remaining problems I have:
* Tap-clicks are sometimes not recognized
* releasing the finger from the pad (which is pressure sensitive) sometimes
still injects unwanted mouse movement, which may be possible to be supressed
when looking at the pressure change and recognizing the release.
* scrolling has changed a bit due to my changes and feels a bit too sensitive
now
Please check it out if you like (ps2_dev.c:105) and tell me what you think.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28468 a95241bf-73f2-0310-859d-f6bbb57e9c96
worked, because the root scanning directory was declared without "/dev/".
This makes restarting the input_server work with the touchpad driver.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28464 a95241bf-73f2-0310-859d-f6bbb57e9c96
solution and replaced it by dumping output to the syslog. (Also
disabled debug output by default.)
* Fixed wrong header guard.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28463 a95241bf-73f2-0310-859d-f6bbb57e9c96
* ps2_dev.c - accidentally turned Synaptics support back on with my last commit. Sorry.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28460 a95241bf-73f2-0310-859d-f6bbb57e9c96
standard versus extended PS/2 mice by simplifying the naming
of the devices but forgetting to adapt this part of the code.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28458 a95241bf-73f2-0310-859d-f6bbb57e9c96
in UpdateSettings() to avoid a crash when there is no TouchPad at all.
Changes by myself: Adapted coding style and added a comment to ConnectToTouchPad()
on why the loop is not exited as soon as the device is found.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28457 a95241bf-73f2-0310-859d-f6bbb57e9c96
<runtime_loader.h>, since it isn't a kernel <-> userland interface.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@28456 a95241bf-73f2-0310-859d-f6bbb57e9c96
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
