The stack & tile feature developement & fixes would be done in
branches/features/stack-and-tile branch, until it's ready enough to be merge
into trunk.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33840 a95241bf-73f2-0310-859d-f6bbb57e9c96
before, st_ctim was never updated; since you cannot change st_ctim via an API,
'0' cannot ever be set, either.
* Inode::WriteAttribute(), and Attribute::Write() now return whether they
created an attribute or not, and thus B_ATTR_CREATED is now correctly set.
* Moved status_change update from bfs_write_attr() into Inode::WriteAttribute()
where it can be handled more efficiently.
* Likewise, Inode::RemoveAttribute() now updates the status_change time as well,
I simply forgot this before.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33832 a95241bf-73f2-0310-859d-f6bbb57e9c96
survives a reboot.
* The target directory is now created if needed.
* Relocated/renamed the settings file to
~/config/settings/system/registrar/RosterSettings.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33827 a95241bf-73f2-0310-859d-f6bbb57e9c96
* While Ingo already convinced me to use the modified time for this instead
(see People files, for example), I did not do so for two reasons:
1) The file modification date is important to the user; more or less hidden
attribute changes shouldn't have an effect on this.
2) Efficiency: the last_modified field is indexed whereas status_change is
not. Speed would suffer noticeably else.
* We might want to think about a new "stat::st_attrtim" field, though, instead.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33825 a95241bf-73f2-0310-859d-f6bbb57e9c96
Ukrainian locale catalog files for Media and Keymap preflets added.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33820 a95241bf-73f2-0310-859d-f6bbb57e9c96
Hope "Yang" is actually your lastname!
Feel free to correct me.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33817 a95241bf-73f2-0310-859d-f6bbb57e9c96
(reported by Axel):
* _AutoResize() can no longer check the difference between the textrect and
the maximum line width, as the textrect is no being adjusted earlier during
the line-calculation code - instead, it needs to measure the difference
between the bounds and the textrect width plus the insets.
* MakeResizable(true) needs to reset the right inset, as otherwise the auto-
resizing would get confused about how large the textview needs to be
(seems to be an artefact of how Tracker creates the textview).
* GetInsets() doesn't need to compute the insets, as they're maintained in
fLayoutData.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33813 a95241bf-73f2-0310-859d-f6bbb57e9c96
debug_output().
* Added a second buffer to be used when interrupts are turned off, otherwise
dprintf_args() will now use a mutex guarded buffer to fill with vfprintf() -
the actual sending to the outputs still needs the spinlock, so things only
slightly improved.
* Moved private functions into the private section of the source file.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33809 a95241bf-73f2-0310-859d-f6bbb57e9c96
were initialized, causing Keymap to lose the current map.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33808 a95241bf-73f2-0310-859d-f6bbb57e9c96
should improve the kernel latencies, as things like
vm_page_allocate_page_run() is very expensive.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33807 a95241bf-73f2-0310-859d-f6bbb57e9c96
Rework ContainerWindow's B_REFS_RECEIVED to use CheckDevicesEqual to decide move vs copy as is done elsewhere.
Fixes ticket #4850.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33803 a95241bf-73f2-0310-859d-f6bbb57e9c96
Welcome onboard!
And, look, what a coincidence: you're my new upper neighbour in that list!
:-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33796 a95241bf-73f2-0310-859d-f6bbb57e9c96
The previous code used kill_thread() and then destroyed the common RingBuffer.
This wasn't working, and as Axel notes it's not really working on kernel side.
* Added RingBuffer::DestroyLock
* Changed the thread to exit gracefully on RingBuffer semaphore destruction.
* Changed close function to destroy RingBuffer sem, wait_for_thread and then destroy resources.
* Minor code style fixes.
(And also my first commit.)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33795 a95241bf-73f2-0310-859d-f6bbb57e9c96
really something to play with without knowing the outcome.
* Fixed indentation/coding style violations introduced with r33783. Please take
more care when accepting patches!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33787 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Copyright style fixes.
* Implemented FreeBSD hardclock subsystem, which is needed to update the ticks
variable. The previous usage of "#define ticks system_time()" wasn't
sufficient anymore, as there are drivers using the ticks name for local
scoped variables.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33785 a95241bf-73f2-0310-859d-f6bbb57e9c96
Closing usb_midi now wake up midi_server port reader, as expected.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33782 a95241bf-73f2-0310-859d-f6bbb57e9c96
Global lock/unlock assembly code was broken, reworked based on
what FreeBSD does.
Thanks!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33781 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Now, killing a team shut properly cause the app_server to close the windows
of that team, too.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33777 a95241bf-73f2-0310-859d-f6bbb57e9c96
posixtestsuite into our repository.
* A few of the latter ones actually fail on Haiku.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33776 a95241bf-73f2-0310-859d-f6bbb57e9c96
pthread_create 2-1 interface conformance test to pass.
* Also fixed return values to be in the POSIX error range in case we ever switch
them by default.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33775 a95241bf-73f2-0310-859d-f6bbb57e9c96
ID.
* Accidently, this should also fix bug #4839.
* Optimized _get_next_sem_info() a whole lot by iterating over the team's
semaphore list.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33773 a95241bf-73f2-0310-859d-f6bbb57e9c96
to the owning team.
* Instead, the team now maintains a list containing the ports it owns.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33771 a95241bf-73f2-0310-859d-f6bbb57e9c96
renamed files. After more investigation i found out that the problem was
caused by a non usual use of the zombie list in r31307. In the conditions
to reproduce #4130 it would call AttrChanged() or StatChanged() on zombie
poses which by convention should always be invalid models, ie: null node.
The logic would potentially create other problems too as it wasn't only
adding refFiltered models to the zombies.
I reverted part of r31307, clarified the logic and updated the comments.
I'd prefer another implementation for this as reusing the zombie list
here is only calling for future mysterious problems. #4131, #4271, #4610
and #4831 are still closed, but i'm reopening #1717 which is more of an
enhancement btw.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33769 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Brecht, is it possible your line break column is one character too short? At
least you broke some lines without need.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33766 a95241bf-73f2-0310-859d-f6bbb57e9c96
This changeset correct usage of this language abbreviation and restore normal function of the localized preflets.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33765 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Instead, they should call the protected virtual ExpandOrCollapse(), this makes
one of my apps work again under Haiku (where the list view contents are
filled on demand).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33760 a95241bf-73f2-0310-859d-f6bbb57e9c96
I thought there was a ticket about this bug, but couldn't find it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33750 a95241bf-73f2-0310-859d-f6bbb57e9c96
* added header for dealing with binary numbers and bitmasks (C++ templates)
these "macro's" might not work well for long words, though
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33749 a95241bf-73f2-0310-859d-f6bbb57e9c96
returns valid data. Since the data is still valid in the copy, we don't need
to clear the corresponding flag when copying a message. This is most probably
the same behaviour as in R5 as Tracker seems to expect that in the case where
a drop is done after a menu was displayed as in #4757. Thanks to aldeck for
tracking that one down inside Tracker, should fix#4757.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33746 a95241bf-73f2-0310-859d-f6bbb57e9c96
Using macro nonnull which actually resolves to an attribute doesn't work
on inline functions.
Thx to mmlr for helping out.
Eitherway it should have worked in the first place, because the compiler
has all the information it needs.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33745 a95241bf-73f2-0310-859d-f6bbb57e9c96
busy processing other things, the file could be gone by the time we processed
the fs notification message of the entry creation. This case wasn't handled
properly and would cause #4130 and most certainly duplicate #4831, #4610 and
also possibly #4271.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33744 a95241bf-73f2-0310-859d-f6bbb57e9c96
* This makes sem_delete_owned_sems() a lot more efficient; before it would need
to scan the entire semaphore table.
* This speeds up the test build of the kernel by another 2 seconds (with
KDEBUG=2) on my laptop.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33743 a95241bf-73f2-0310-859d-f6bbb57e9c96
the network drivers needed to be adjusted to the header reordering, too
sorry
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33740 a95241bf-73f2-0310-859d-f6bbb57e9c96
ordering.
this makes porting driver (especially wifi ones) more
convinient
* based on FreeBSD svn revision 196691
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33739 a95241bf-73f2-0310-859d-f6bbb57e9c96
iterated over all known thread *IDs* with interrupts disabled.
Now it iterates over the team's thread list (going from back to front, since
new threads are added at the front of the singly linked queue).
* Alexandre restarted Tracker quite a lot, and let the shell script run to
reproduce a certain bug - and then wondered why ProcessController would
take several seconds to open its windows until it passed through more than
8 million IDs... :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33737 a95241bf-73f2-0310-859d-f6bbb57e9c96
(hopefully) correct place.
* It seems to be even harder to understand basic locking primitives: when you
think about it, it shouldn't surprise you that conditional variables never
return B_WOULD_BLOCK. This fixes gdb again.
* Added tracing support to the ports subsystem.
* get_port_message() will now resize the port heap if needed (but will also
take timeouts into account while doing so, more or less). The initial port
space is 4MB (as before), the growth rate is the same, and the system wide
limit is arbitrarily set to 64 MB (all swappable). A team limit has been set
to 8 MB, but is not enforced yet. Since ports are using up address space in
the kernel, those seems to be proper limits.
* This also fixes a strange, and rare lockup where the mouse cursor would still
move, but everything else would basically hang, but look perfectly normal from
KDL on the first look. As recently happened on Brecht's laptop, and debugged
by mmlr and me: the cbuf space got used up when lots of windows wanted to
redraw after a workspace switch. The app_server wouldn't answer anymore to
client requests, but thought it would have done so, as LinkSender::Flush()
doesn't care if it got a B_NO_MEMORY (the ports will now block until memory
is available if possible, so that should not be a problem anymore).
* Improved "port" KDL command, it now also prints the messages in the port.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33735 a95241bf-73f2-0310-859d-f6bbb57e9c96
(might cause some regressions in FFM)
* made accept first click user configurable
* updated the Mouse preflet to use the layout kit
* removed the warp and instant warp modes from the Mouse preflet
* changed internal representation of mouse modes (warp modes moved)
* coding style fixes
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33732 a95241bf-73f2-0310-859d-f6bbb57e9c96
break the display for others. If that doesn't work out, there is probably a
bit more to it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33731 a95241bf-73f2-0310-859d-f6bbb57e9c96
was used this way in the debugger. Doing this later should be harmless,
AFAICT, but Ingo will probably know better.
* Beware, though, the debugger currently does not work anymore.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33730 a95241bf-73f2-0310-859d-f6bbb57e9c96
initialization to fail. This also caused a crash, as that wasn't checked for
before.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33729 a95241bf-73f2-0310-859d-f6bbb57e9c96
* its own heap allocator instead of cbuf - this makes cbuf superfluous, and I
therefore removed it from the kernel. The heap is swappable, so lifts the
kernel's resource usage a bit. In the future, the heap should grow as well;
right now it should be at least as good as before.
* it no longer uses spinlocks, but just mutexes now for better scalability - it
was not usable with interrupts turned off anyway (due to its semaphore usage).
* it no longer uses semaphores, but condition variables.
* Needed to move the port initialization to a later point, as swappable memory
wasn't usable that early.
* All ports test are still passing, hopefully I didn't mess anything up :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33728 a95241bf-73f2-0310-859d-f6bbb57e9c96
the bin sizes ensure that when hitting this case it always allocates multiple
pages. This makes it more flexible for other use cases though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33726 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Fixed some minor issues of heap_create_allocator() when it should use the
kernel heap to allocate its heap structure.
* Fixed an off by one error in the max bin check.
* Changed the KDL "heap" command to allow the "stats" for any heap as well.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33725 a95241bf-73f2-0310-859d-f6bbb57e9c96
fit into the existing area. In that case further reallocs could then assume the
wrong previous size and then not copy enough from the original buffer, leading
to lost bytes at the end of the new buffer.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33724 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Allow an allocator to be created on the heap to allow for non-locked
allocators to be created.
* Some cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33721 a95241bf-73f2-0310-859d-f6bbb57e9c96
read out in the ConditionVariableEntry::WaitStatus(). That way you can notify
with a specific status that can be read out on the other end.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33718 a95241bf-73f2-0310-859d-f6bbb57e9c96
* SetTextRect for non-wrapped textviews needs to update the insets,
as otherwise several misalignments occur within several apps - renaming
in Tracker was effected the worst, though
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33717 a95241bf-73f2-0310-859d-f6bbb57e9c96
during the width calculation
* used _TabExpandedStyledWidth() at all places that need to expand tabs,
fixing #4822
* removed _StyledWidthUTF8Safe() as it didn't make sense - we now perform
the same auto-scrolling horizontally as we do vertically
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33713 a95241bf-73f2-0310-859d-f6bbb57e9c96
actually works under Haiku (with a caveat, as there is apparently an
app_server bug that prevents that most of the time).
* Simplified ExpandoMenuBar::MouseDown().
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33708 a95241bf-73f2-0310-859d-f6bbb57e9c96
class.
* Changed ExpandoMenuBar to use that logic as well, so that your entries will
always keep the same sort order.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33704 a95241bf-73f2-0310-859d-f6bbb57e9c96
* switching from wrapping to non-wrapping mode triggers a recomputation of
the text rect
* non-wrapping mode now triggers updating of the data rect for the horizontal
scrollbar as needed, fixing #4705
* corrected a couple of width computations that confused bounds and text
rect width, leading to drawing artefacts at the end of a line
* unified computation of text rect width to always take all lines into
account (not just the first one)
* some cleanup
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33703 a95241bf-73f2-0310-859d-f6bbb57e9c96
defines - it's always in, and I don't think it makes any sense to make this
an option (since it just uses a system widget).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33699 a95241bf-73f2-0310-859d-f6bbb57e9c96
added to the window list without considering its frontmost window. That caused
problems with all feels that were always on top, like
B_ALL_WINDOW_FLOATING_FEEL. This was causing bug #4700.
* Disabled the "previous window keep keyboard focus" heuristic - it doesn't
really work that well. There should be a central mechanism that detects active
typing that could also be used to disable touchpads.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33697 a95241bf-73f2-0310-859d-f6bbb57e9c96
type if a file doesn't have one yet (and set it), instead of ignoring it
completely.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33694 a95241bf-73f2-0310-859d-f6bbb57e9c96
--Cette ligne, et les suivantes ci-dessous, seront ignorées--
M src/preferences/appearance/Jamfile
M src/preferences/locale/Jamfile
M src/preferences/bluetooth/Jamfile
M src/preferences/cpufrequency/Jamfile
A data/catalogs/preferences/appearance/ua.catkeys
A data/catalogs/preferences/locale/ua.catkeys
M data/catalogs/preferences/locale/fr.catkeys
A data/catalogs/preferences/bluetooth/ua.catkeys
A data/catalogs/preferences/cpufrequency/ua.catkeys
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33686 a95241bf-73f2-0310-859d-f6bbb57e9c96
must have been my very own stupid idea. It's removed now.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33685 a95241bf-73f2-0310-859d-f6bbb57e9c96
one or two remove messages were generated, as the query code produces
remove/create notifications on renames. Will check next if that also happens
on BeOS, as it doesn't really make much sense.
* This should fix the wrong mail count of the Deskbar replicant when you delete
mail.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33683 a95241bf-73f2-0310-859d-f6bbb57e9c96
wait status and therefore would return directly without actually blocking.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33681 a95241bf-73f2-0310-859d-f6bbb57e9c96
first I tried adding support for changing the format during running the node
connection, but later found out that this is not implemented in the system
mixer (it has this weird setting to allow input format changes, but if you
do this, the media_server will just crash, since the backend does not support
it yet). Also, the Media Kit documentation is extremely lacking in this regard.
I ended up re-establishing the node connection when the audio format is
supposed to change, just like it is already done for video. This means that
audio files now play with their native channel count and frame rate. But it
isn't so well tested yet, if 48 kHz for example introduce some clicks. The
channel count should not be a problem though, I've also tested that with some
movies and it works fine.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33678 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Unfortunately, there are remaining issues, but this is something I need to
discuss with Stippi: B_OP_COPY does not work as expected due to anti-aliasing
anymore, but there is no replacement one could possibly use to get the desired
effect without having to clear the background every time.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33676 a95241bf-73f2-0310-859d-f6bbb57e9c96
them more BeOS compatible while still keeping them somewhat flexible.
* _GrowStream() did actually not check if the double indirect region was already
filled up - this caused it to overwrite innocent memory. This fixes the bug
Rudolf showed me on this laptop that happened while copying a large file.
* Loosened file size restriction on a heavy fragmented disk: the indirect block
does not require a minimum array size anymore; before, you just couldn't let
a stream grow into the indirect range if it couldn't allocate NUM_ARRAY_BLOCKS
(4) blocks in a row. This considerably reduced the maximum file size in this
case.
* Removed no longer valid TODO.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33675 a95241bf-73f2-0310-859d-f6bbb57e9c96
to avoid recurring problems during migration of subversion checkouts
(restored binary files that were garbled by subversions during checkout)
* added appropriate svn:mime-type property for problematic (binary) files
* removed a single (mistyped) svn:mimetype property
* dropped svn:eol-style property for cleanup (they all contained 'native')
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33670 a95241bf-73f2-0310-859d-f6bbb57e9c96
a button or within the bar background within the timeout for the repeat-thread,
the thread would exit and there would be no repeating. I think there is still
a race condition somewhere since I managed to see it stall once again, probably
because it locks the looper twice in the loop...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@33666 a95241bf-73f2-0310-859d-f6bbb57e9c96
