having the thread lock held and interrupts disabled.
Cleaned up the signal handling code, and fixed some minor bugs with blockable
vs. non-blockable signals.
thread_debug_info was using uint64 for signals sets instead of sigset_t.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14457 a95241bf-73f2-0310-859d-f6bbb57e9c96
that into account as well (they were reporting an error even though everything
went fine).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14450 a95241bf-73f2-0310-859d-f6bbb57e9c96
* got rid of bogus member variables in FontStyle (which were
already flags in the underlying FT_Face structure)
* disabled using the FreeType font cache -> I think from
my earlier tests, I can conclude that the cache was not
actually working. At least not giving any speed improvements.
The AGG engine contains a caching system, for now, it works ok.
I have no idea if this has anything to do with crashes in the
freetype code, but at least I have not seen any since this
change. But I have not tested much...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14448 a95241bf-73f2-0310-859d-f6bbb57e9c96
some heuristic: when you booted from a CD, CDs are preferred; else, volumes with
names like "Haiku" or "System" are preferred - if someone has better ideas, please
shout.
Note, this heuristic will only come into play if the boot loader was loaded from
an image (ie. floppy/CD/network), and you didn't choose any boot device.
Added evil methods to the Stack class that come in handy (you can now directly
access the array) for this.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14410 a95241bf-73f2-0310-859d-f6bbb57e9c96
and into its own file vfs_boot.cpp.
Added basic support for booting from CD - it doesn't give CDs a higher priority,
so you could end up booting from HD when you didn't explicetly select "CD-ROM"
in the boot loader. Eventually, it should only boot from HD in this case, if
booting from CD failed (because of a missing boot partition or whatever).
fs_mount(), _kern_mount(), and _user_mount() will now return the dev_t of the
mounted device, and not just B_OK. Maybe we should have fs_unmount() work on
a dev_t instead of a path as well...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14403 a95241bf-73f2-0310-859d-f6bbb57e9c96
"booted_from_image" in the kernel_args' boot_disk structure.
Also, added fields "cd" and "user_selected".
A CHOICE_MENU menu can now have a choice text - this is automatically updated
as entries in the menu get selected.
The boot volume menu now has the initial choice text "CD-ROM or hard drive"
in case the boot loader was loaded from an image. The "Rescan volumes" item
is no longer selected by default (only if there was no boot volume found) - but
it's still functionless anyway.
The TAR fs will now appear as "Boot from CD-ROM" in the boot volume menu.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14388 a95241bf-73f2-0310-859d-f6bbb57e9c96
like floppy or CD boot.
This allows it to reduce the number of scans needed to identify the boot
partition - when booted from a real floppy, this speeds up the boot
process by a magnitude.
Also, the loader now has a fall back in case there were no "boot" links
on the disk - the current boot floppy script doesn't create them.
With these changes, I was able to boot into a HD based Haiku installation
from a floppy disk. It's not yet enough to boot from CD (as the boot
device selection is a bit too simplistic right now), but it will eventually
come next. Testing is a lot slower here, though, as neither qemu nor
Bochs support multi-session CDs (at least I have no idea how to get them
to do this).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14380 a95241bf-73f2-0310-859d-f6bbb57e9c96
per file descriptor (a descriptor can be shared among several slots). There is now a
second table in the io_context structure that contains that information in a bitmap.
There are now two new (private) functions to control the close-on-exec flag, fd_close_on_exec(),
and fd_set_close_on_exec().
F_DUPFD, dup(), and dup2() are supposed to clear the close-on-exec flag on the duplicated
slot - this fixes bug #57 (no output after a redirect of a shell builtin).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14313 a95241bf-73f2-0310-859d-f6bbb57e9c96
socketpair() in the network stack is empty and still to be implemented for real
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14267 a95241bf-73f2-0310-859d-f6bbb57e9c96
improved GetBoundingBoxesAsString (just for fun, keep in mind we'll use AGGTextRenderer in the end :) )
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14091 a95241bf-73f2-0310-859d-f6bbb57e9c96
removed the locking it did, as that doesn't work anymore in the kernel debugger.
The function was not thought to be used outside the debugger, anyway.
Improved usage message from debugger command "ls".
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14050 a95241bf-73f2-0310-859d-f6bbb57e9c96
even if "kernel_startup" was "true". Page faults are now no longer allowed
during kernel startup (and could be easily avoided). The only situation where
we accept page faults with interrupts turned off now is during a kernel debugger
session.
Added a command debug_debugger_running() to test for that situation.
kernel_debugger() no longer sets kernel_startup while it's running; there should
be no situation when this could be helpful.
Interrupts are no longer enabled when a page fault happens in the kernel
debugger.
This potentially fixes all sorts of problems, and not only in the kernel debugger,
it could also have affected SMP (will test later).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14045 a95241bf-73f2-0310-859d-f6bbb57e9c96
Moved the scanning of individual font folders to FontServer
Implemented server-side code for update_font_families
Removed ClientFontList from the build
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13938 a95241bf-73f2-0310-859d-f6bbb57e9c96
working directory (instead of the full path).
Cleanup of some remaining "int" status variables (where it should have
been a "status_t").
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13924 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also cleaned up Message3.h revert it if you think its a binary compatibility issue.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13920 a95241bf-73f2-0310-859d-f6bbb57e9c96
Sorry to pollute the repository with all those extra files, they will be (re-)moved when the decision about which implementation to use is made.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13916 a95241bf-73f2-0310-859d-f6bbb57e9c96
prevents the system to allocate caches for files that don't use or have
a file cache (ie. only those can be mmap()ed!).
Therefore, cache_prefetch() no longer crashes when trying to prefetch
files without a file cache.
read_into_cache() no longer does anything if the requested size is 0.
Fixed a bug in cache_prefetch_vnode(): if the cache couldn't be retrieved,
it put the vnode, but didn't own it (the caller does).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13904 a95241bf-73f2-0310-859d-f6bbb57e9c96
device becomes available.
Currently, it opens the "launch_speedup" module (if available), later it
should consult a settings file for what to do.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13894 a95241bf-73f2-0310-859d-f6bbb57e9c96
(dprintf() locks using acquire_spinlock() which can itself drop into the
kernel debugger, causing an endless loop (until the stack was full).
Removed debug_putchar().
The gdb interface is now calling arch_debug_serial_*() directly.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13882 a95241bf-73f2-0310-859d-f6bbb57e9c96
Removed vfs_vnode_release_ref(), as vfs_put_vnode() already does the same thing.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13867 a95241bf-73f2-0310-859d-f6bbb57e9c96
the other one with usual device/inode ID pair.
Both versions now accept an offset/size pair to specify the region of the
file to be prefetched - this may be turned into a file_vec_io array later on.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13866 a95241bf-73f2-0310-859d-f6bbb57e9c96
changed the way prefs is stored, so that we have default settings
general cleanup
time sliders are now linked together as on R5
password window is centered onscreen
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13849 a95241bf-73f2-0310-859d-f6bbb57e9c96
added ScreenSaver.cpp to ScreenSaver preferences to have Matrix working
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13828 a95241bf-73f2-0310-859d-f6bbb57e9c96
creation/deletion (and management) over to that class.
ServerApp now gets a desktop pointer, and no longer uses gDesktop.
Converted private MessageLooper::_MessagePort() to a public method MessagePort()
so that the looper can be addressed from elsewhere without using PostMessage().
Added a real basic message loop to MessageLooper::_MessageLoop().
BApplication now only asks the app_server to get its desktop object which should
now be used for everything that's not in the realm of the application.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13824 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
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
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
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
* Moved setting the default cursor from ServerScreen to Desktop
* Getting the default cursor is now done using the CursorManager
* Removed outdated setcursor from SysCursor.cpp (we have a new implementation by now)
* Renamed SysCursor.cpp to CursorSet.cpp as that's what it is
* Moved headers/private/app/SysCursor.h to headers/private/servers/app/CursorSet.h
* Removed some unneeded header includes along the way
There remains {set|get}_syscursor now in CursorSet.cpp. Serverside for these are not implemented
and they are obvious hacks. Do we need to keep them?
Also this commit _would_ break Appearance, but 1) all the related code is currently commented out
with the comment "cursor set management belongs in another app" and 2) it is already broken
because of ColorSet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13726 a95241bf-73f2-0310-859d-f6bbb57e9c96
Deskbar to initiate the shutdown process asynchronously. Couldn't test it,
because opening the Be menu doesn't work:
***PANIC: BW: Can't find view with ID: 19 !***
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13722 a95241bf-73f2-0310-859d-f6bbb57e9c96
the desktop's settings, you have to do something like this:
DesktopSettings settings(desktop);
settings.SetMouseMode(mode);
The advantage of this is that this object is fully locked, and cannot lead to
corrupted settings anymore. Also, the settings will stay the same until you
delete the object again.
Updated all accesses to use this new API.
Removed no longer used FFM messages.
Implemented AS_{GET|SET}_MENU_INFO for future use.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13719 a95241bf-73f2-0310-859d-f6bbb57e9c96
debug_server uses this feature to print stack traces with symbols.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13698 a95241bf-73f2-0310-859d-f6bbb57e9c96
allocating a buffer and copying your data into it, when you have data to
send in several chunks (for example, this could be used by BMessage, as
suggested by Ingo Weinhold).
Code is untested, but should work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13667 a95241bf-73f2-0310-859d-f6bbb57e9c96
last commit was wrong as easily noticed by Jack Burton :)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13636 a95241bf-73f2-0310-859d-f6bbb57e9c96
Forgot to adapt the limit to switch to "GHz" in AboutHaiku.
Both bugs were reported by Herve W a.k.a. "V" - whatever
that means :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13571 a95241bf-73f2-0310-859d-f6bbb57e9c96
someone with app server insight wants to do that. :-)
* Simplified main_thread_for() for Haiku.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13538 a95241bf-73f2-0310-859d-f6bbb57e9c96
Basic support for the desktop window feel: WinBorder will now resize
a window with kDesktopWindowFeel to span over the whole screen.
Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13462 a95241bf-73f2-0310-859d-f6bbb57e9c96
Fixed handling in ServerWindow as stippi's latest commit broke it.
It's now properly done with a separate ServerWindow::SetTitle() method,
that will also take care to rename the window's thread.
Changed naming the window thread in the app_server to "w:<team>:<title>".
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13461 a95241bf-73f2-0310-859d-f6bbb57e9c96
(we can still remove it later if needed).
Added B_SERVER_TOKEN type.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13451 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Adjusted the shutdown command to use BRoster::ShutDown(). Removed
the alert.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13416 a95241bf-73f2-0310-859d-f6bbb57e9c96
time of the idle thread. IOW Pulse now works :-)
Renamed the idle thread/stack to start with 1 instead of 0 (first idle thread will
be called "idle thread 1").
Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13373 a95241bf-73f2-0310-859d-f6bbb57e9c96
We now use "const" for the chunk buffer pointer returned by GetNextChunk,
because the buffer is not supposed to be modified by the codec.
size_t is used for the size where applicable. This matches BMediaDecoder.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13361 a95241bf-73f2-0310-859d-f6bbb57e9c96
- it now seems to work finally correctly
- renamed ViewAttr to ViewState and put it into the BPrivate namespace
- some refactoring (moved some private BView methods to ViewState)
- renamed AS_LAYER_MOVETO/RESIZETO to *_TO (note the underscore)
- exchanged BView::originX/Y with fParentOffset (BPoint)
- divided AS_LAYER_GET_COLORS into separate ones for high/low/view color
- BView::SetPattern() now actually works as expected (ie. updates
only if necessary)
- exchanged the ViewAttr::flags with ViewState::valid_flags which inverses
the previous logic (which wasn't even used consistently)
- fState was initialized twice (incorrectly by the ViewAttr constructor,
and then again correctly by initCachedState()) - now the ViewState
constructor does the job alone, but correctly
- BView::PushState() no longer resets the state (it did so only locally
anyway...)
- cleanup
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13325 a95241bf-73f2-0310-859d-f6bbb57e9c96
for servers, that don't have a GUI or want to control when the app server
connection is established.
* BServer is necessarily a friend of BApplication, for it uses a private
constructor. Hence BApplication::Private::InitGUIContext() is no longer
needed.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13315 a95241bf-73f2-0310-859d-f6bbb57e9c96
BApplication::Private class for accessing relevant parts.
* Pulled the app server connection and IK initialization out of
InitData() into a new method _InitGUIContext() and introduced a private
constructor that allows to avoid this initialization. This will be used
for servers that don't have GUI respectively want to init the app server
connection later.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13312 a95241bf-73f2-0310-859d-f6bbb57e9c96
used for new area.
MemPool::AddToPool() now gracefully deals with NULL pointers (or a size of 0).
BitmapManager was deleting the area it transferred to AreaPool before - it
no longer needs an extra area, though.
Minor other cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13260 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also applied our style guide on that class.
Renamed some public globals to match our style guide.
Made BitmapManager inherit from BLocker instead of duplicating its
functionality (incorrectly, did not check for B_INTERRUPTED) locally.
Some more cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13259 a95241bf-73f2-0310-859d-f6bbb57e9c96
to LinkReceiver, LinkMsgSender to LinkSender, and put everything into the
BPrivate namespace.
Made AppServerLink a cheap object - it will use the applications receiver/sender
and not create its own buffers.
Fixed broken communication stuff here and there (mostly Font.cpp).
Put the newly introduced set|get_system_colors() into the BPrivate namespace -
please don't introduce private functions into the public namespace!!!
Also fixed their broken communication use, as Darkwyrm obviously forgot about
it again: the sequence Flush(); GetNextMessage() without error checking is
purely wrong and can make the app hang and/or crash! :-)
Other minor cleanup.
The input_server used some test mode with the haiku build target which is
probably wrong.
Hopefully I did not forget anything this time.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13128 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also, when the line is too long, E2BIG is returned.
Thanks to Korli who pointed me to this: http://homepages.cwi.nl/~aeb/std/shebang/
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13114 a95241bf-73f2-0310-859d-f6bbb57e9c96
now as well.
Also, both functions will now test if the executable exists and is valid; that
way, load_image()/exec*() can catch many errors without having to create a new
team (or erase the current one - an exec*("my invalid app") might now return
with an error).
The runtime linker now exports a function to test executables that is aware
of the search paths, and will also check user permissions upfront.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13113 a95241bf-73f2-0310-859d-f6bbb57e9c96
no items can be removed from that list - nevertheless, it's wrong.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13088 a95241bf-73f2-0310-859d-f6bbb57e9c96
can now only happen if the thread is killed.
_user_receive_data() will now longer pass B_CAN_INTERRUPT to receive_data(),
but B_KILL_CAN_INTERRUPT - this should fix the problem Stefano experienced
with this function, even if I couldn't reproduce it.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13075 a95241bf-73f2-0310-859d-f6bbb57e9c96
(Incorrectly) implemented AS_GET_DESKTOP_COLOR - works for now.
Minor cleanup.
Is AS_SET_SCREEN_MODE used at all?
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13010 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added LinkMsgReader::NeedsReply() method.
Completely redone ServerApp messaging: no more "replyport" from BAppServerLink; instead,
the registered client reply port is used. Fixed some more weak messaging stuff.
ServerApp now recognizes if an unknown message needs a reply, and sends it - for example,
the "Screen" preferences app no longer hangs, but crashes on start :)
Made LinkMsgReader::Read() virtual again, since it's needed by RAMLinkMsgReader.cpp.
Renamed BPortLink::GetNextReply() to GetNextMessage().
Some more cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@13004 a95241bf-73f2-0310-859d-f6bbb57e9c96
BPortLink::AttachString() now accepts a length argument, and will no longer
send a terminating null byte; LinkMsgReader::ReadString(), however, will
make sure the string read is null terminated.
Changed client communication code to use FlushWithReply() instead of Flush()
and GetNextReply() - there were many bugs and shortcomings in the code, I
hope I've fixed them all.
Converted ClientFontList.cpp to our coding style (but not completely, the
class members are missing).
Some more cleanup - I hope Adi will adopt our coding style one day!
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12998 a95241bf-73f2-0310-859d-f6bbb57e9c96
- StartMessage() can now get a size to make sure there is enough free space
- if StartMessage() is called with the current message behind a certain
watermark, the buffer is flushed in order to prevent moving around messages
in the buffer. The actual value should be tested in real life, though.
- enlarged maximum buffer size to 64k
- fixed bug: could use memcpy() to move overlapping memory around
- added a flag to Flush() that marks messages as needing a reply - the other
way would be to mark the message "code" to contain this information
Some cleanup in LinkMsgReader.
BPortLink now has most methods as inlines.
The buffer sizes are now declared in a shared header, so that receiver and
sender are always equipped equally.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12997 a95241bf-73f2-0310-859d-f6bbb57e9c96
(ab)using the BApplication lock to synchronize messaging.
Also, it now has one global reply port, that is created on demand,
but never freed - hope this doesn't cause any other trouble.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12957 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added new devfs_add_driver() function that the device manager will now call
to register new drivers.
Devfs will now keep a list of known drivers and remembers, if they have
been initialized already - a driver can now safely scan the directory it's
in while being scanned itself without having its hooks called twice.
Devfs is now using a recursive lock instead of a mutex (that's not really
a requirement right now, but would allow us to keep the fs lock during
scanning).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12933 a95241bf-73f2-0310-859d-f6bbb57e9c96
called by debug_init_post_vm().
Since the availability of a blue screen specific getchar() is static anyway, there
is no need for the sBlueScreenGetChar variable (only the message "only serial input
available" gets lost, but since that is platform specific anyway...).
Hello blue screen! We now have an on-screen KDL, to be enabled by the kernel
setting "bluescreen", just like on BeOS.
The blue screen does not yet support any cursor actions or backspace, though (need
to grab some stuff from our console driver).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12896 a95241bf-73f2-0310-859d-f6bbb57e9c96
kernel_debugger() didn't do enough before; panic() did all the work - but
since the former is a public function as well, I moved all the functionality
to it. Also fixed a possible buffer overrun in panic().
Renamed dbg_* to debug_*.
"serial_debug_port" setting did not ignore negative values.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12889 a95241bf-73f2-0310-859d-f6bbb57e9c96
- extended libdebug.so functionality to be able to get stack frames,
current instruction pointer, etc.
- changed the debug_server to be able to run as a simple BLooper - this
saves some trouble when the app_server dies
- the debug_server now prints out a stack crawl for the crashed team
(without symbols, though - for that data to be helpful you should
have a look at the loaded images (ie. where they start))
- the debug_server now also prints the team name when it kills it
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12882 a95241bf-73f2-0310-859d-f6bbb57e9c96
has to care about refresh rates. Also changed Screen::GetMode() (formerly
Resolution()) to return all interesting values, so that hopefully no one
will call it anymore like RootLayer::SetScreens() did.
Greatly improved the horrible RootLayer::SetScreens().
The app_server is now able to deal with failing HWInterface::SetMode() calls;
in this case, it will fall back to the hardware's current mode. This now
also works correctly in combination with the vesa driver, so that you don't
have to compile the app_server with the same resolution you boot in anymore.
SetMode() now always returns if it succeeded or not.
Renamed RootLayer::fScreenXYResolution to fScreenWidth/Height respectively.
Removed the useless DisplayDriver::DisplayMode() method.
Added B_GET_DISPLAY_MODE to the required accelerant hooks.
Some minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12831 a95241bf-73f2-0310-859d-f6bbb57e9c96
This will keep it alive longer until a) the block cache no longer
uses the heap, and b) we get a better heap without a fixed size.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12830 a95241bf-73f2-0310-859d-f6bbb57e9c96
VFS's interface, so that a file system only has to implement one interface.
As a side effect, the automatic file system detection may now work (not yet
tested, though).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12786 a95241bf-73f2-0310-859d-f6bbb57e9c96
following 1152 MB - that area only guarantees that the heap can grow this much before
the application need the memory for something else. And even then, the heap range
is reused from top-to-bottom, allowing for maximum heap usage. Of course, if the
memory after the heap range is not claimed yet, it can still be claimed by the heap,
too. Added new syscall to create the reserved range.
Fixed a bug in vm_delete_areas(): when it removed reserved areas, the area list
could get messed up.
Fixed a bug in resize_area(): resized areas could never be deleted (missing vm_put_area())!
resize_area() now supports reserved regions (but not perfectly yet, see ToDo items).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12692 a95241bf-73f2-0310-859d-f6bbb57e9c96
only if memory becomes tight, and then the range is used from end to
start.
This is useful to reserve heap address ranges.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12675 a95241bf-73f2-0310-859d-f6bbb57e9c96
along the protection flags).
Changed the handling of B_STACK_AREA types and anonymous vm_areas: now
every area can overcommit if B_OVERCOMMITTING_AREA was specified.
B_STACK_AREA areas are still automatically overcommitting, but
B_KERNEL_STACK_AREA areas no longer.
vm_store_anonymous_noswap.c now only tests for guard pages if there were
any specified which is only done for B_STACK_AREA areas.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12673 a95241bf-73f2-0310-859d-f6bbb57e9c96
(right now, it's still malloc/free, just encapsulated in an allocator class).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12662 a95241bf-73f2-0310-859d-f6bbb57e9c96
- 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
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
Adds latests IDs from Intel docs
Adds some Sempron IDs
Renamed Athlon 64 to be consistent with Intel names
Adds IDs in cpu_type.h
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12429 a95241bf-73f2-0310-859d-f6bbb57e9c96
it doesn't really do anything, it just passes the initial frame buffer
on to the app_server).
While it seems to work on real hardware (if you set the video mode to
640x480x32, app_server restriction), under Bochs, the app_server crashes.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12273 a95241bf-73f2-0310-859d-f6bbb57e9c96
Also changed readlink() to be POSIX compliant with those changes.
"ls -l" does now resolve links properly again (the new coreutils version outlined the problems).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12263 a95241bf-73f2-0310-859d-f6bbb57e9c96
create_area() and friends should fail if it's not supported.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12248 a95241bf-73f2-0310-859d-f6bbb57e9c96
for these changes. I was mostly just staring in amazement at the screen
while Axel and Thomas were discussing IA32 internals. A particularly
fascinating moment was when Thomas produced the cause of a bug we had
been trying to track down for hours off the top of his head (of course
iret behaves specially when the NT bit is set :-). His slowness must be
excused though, since he hadn't slept for more then 30 hours. ;-)
The code doesn't wholeheartedly deal with multi-processor machines yet.
Axel will certainly do some cleanup...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12239 a95241bf-73f2-0310-859d-f6bbb57e9c96
flag. Now, it will choose how to set the granularity by evaluating the
limit.
This call was actually already used this way in the kernel, so that
the TLS and TSS segments were much too large (harmless but incorrect).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12231 a95241bf-73f2-0310-859d-f6bbb57e9c96
Introduced a gBootFrameStack that is used until the first thread structure
is available - this allows stack crawls and useful register dumps during
early startup. Could also be solved differently by making sure there is
always a thread structure installed in %dr3 (ie. the boot thread would
get a static thread structure instead of a static iframe stack only).
This might be a better solution as i386_handle_trap() would no longer
need to check for an existing thread structure.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12230 a95241bf-73f2-0310-859d-f6bbb57e9c96
Moved ptentry/pdentry to arch_vm_translation_map.c and renamed them to
page_table_entry and page_directory_entry.
Fixed a race condition that happened when memory was remapped (which
can currently happen because lock_memory() does not work correctly, and
there might be other conditions as well, like certain vm_store fault
handlers). Now, page table and directory entries are updated atomically.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12229 a95241bf-73f2-0310-859d-f6bbb57e9c96
the APM driver to see it at work).
The frame buffer console now creates such a boot item to give a potential
VESA driver access to the boot frame buffer configuration.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12221 a95241bf-73f2-0310-859d-f6bbb57e9c96
Probably only works under Haiku due to the new area flags.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12219 a95241bf-73f2-0310-859d-f6bbb57e9c96
Added a ToDo comment about the forgotten find_directory().
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12201 a95241bf-73f2-0310-859d-f6bbb57e9c96
MenuItem::SetData() now asks for a const parameter.
The safemode menu options now set their MenuItem::Data() to the safemode option string.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12191 a95241bf-73f2-0310-859d-f6bbb57e9c96
instead B_KERNEL_PROTECTION and B_USER_PROTECTION.
Unlike before, B_USER_CLONEABLE_AREA is now only in B_KERNEL_AREA_FLAGS,
but no longer in B_KERNEL_PROTECTION. This fixes a couple of problems
when B_USER_CLONEABLE_AREA was defined without specifing read/write
access.
PAGE_PRESENT|MODIFIED|ACCESSED are in the same "namespace" as the
protection flags, and therefore, shouldn't overlap.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@12154 a95241bf-73f2-0310-859d-f6bbb57e9c96
with the bit number, not the respective mask).
* Added a small hack to allow single stepping to work in qemu.
Apparently the BS bit in DR6 is not set when the debug exception
is handled. So we always assume that a single step event occurred,
when we couldn't recognize any other event, if the hack is enabled.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11998 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added initialization function. Currently only need to init the
single step hack for qemu.
* Fixed a deadlock when the nub thread destroyed the debug info. It was
waiting for itself.
* Moved the filling in the origin info of the debug messages into
thread_hit_debug_event_internal(). No need for code duplication.
* Writing to user memory can now be partial. We also change the area
protection, if it wasn't writable. Necessary for setting software
breakpoints.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11996 a95241bf-73f2-0310-859d-f6bbb57e9c96
that we no longer need an initialize_after().
Put the architecture dependent hoard functions into the BPrivate namespace
as well. Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11956 a95241bf-73f2-0310-859d-f6bbb57e9c96
Entirely implemented on top of the public <debugger.h> API, but more
convenient to use. Lives in a separate library libdebug.so.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11925 a95241bf-73f2-0310-859d-f6bbb57e9c96
removed unused headers. Adapted sources to still compile with the new
header locations.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11913 a95241bf-73f2-0310-859d-f6bbb57e9c96
team boundaries; if you didn't actually call close() from within the
application, the close-hook of the file system was never called.
Also, you could close files of other teams (ie. invoke close on a
shared file descriptor).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11892 a95241bf-73f2-0310-859d-f6bbb57e9c96
they are public now, they might become private later on.
It's almost the same as acquire_sem() but allows you to release another semaphore
atomically. This makes condvar implementations and the like very simple to do.
Added B_CHECK_PERMISSION flags to the user calls, although it's not honored yet.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11887 a95241bf-73f2-0310-859d-f6bbb57e9c96
and drivers that need to provide special select() support with
managing select notification information.
* Renamed vfs_select.c to *.cpp and fixed the resulting C++ compiler
errors. Added tracing macros.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11886 a95241bf-73f2-0310-859d-f6bbb57e9c96
and free_*_cookie() hooks of the underlying FS were always called
together when the reference count of the FD dropped to zero. When
blocking operations (reading/writing) on the FD were still in progress
this would never happen, though. Now we additionally maintain an open
count and call the close_*() hook when it drops to zero.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11882 a95241bf-73f2-0310-859d-f6bbb57e9c96
is perfectly okay on x86 anyway, but should be moved into the arch stuff).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@11869 a95241bf-73f2-0310-859d-f6bbb57e9c96
* user_debug_break_or_watchpoint_hit() into separate functions for
break- and watchpoints. The one for breakpoints gets another parameter
which indicates whether the breakpoint was a soft- or hardware
breakpoint. This info is also sent to the debugger.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11714 a95241bf-73f2-0310-859d-f6bbb57e9c96
of a signal.
* Added sigaction_etc(). It's just a sigaction() for which the thread
in question can be specified.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11704 a95241bf-73f2-0310-859d-f6bbb57e9c96
not to be notified.
* Added debugger commands for setting/getting of thread signal ignore
masks and signal handlers.
* Renamed user_debug_fault_occurred() to a more correct
user_debug_exception_occurred(). It no longer sends a `stopped' message,
but the new one dedicated to exceptions. Additionally the number of the
signal is supplied that will be sent, when the thread continues (without
indicating to ignore the event).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11703 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added _kern_image_relocated() and _kern_loading_app_failed(), which
are invoked by the loader to provide the kernel with more info.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11689 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Implemented _user_wait_for_debugger().
* Reworked a few bits to ensure that after a remove_team_debugger() or
after requesting a debugger handover the debugger doesn't get any more
messages.
* When the debugger is removed or dies, the debugged threads should now
cleanup their debug info and continue, instead of waiting at their
debug port forever.
All the new features are not tested. Will happen, when gdb will be
debugged.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11664 a95241bf-73f2-0310-859d-f6bbb57e9c96
threadID parameter to spawn_kernel_thread_etc(). It's now possible to
set the ID of a new thread. Used in team.c to make team ID and the ID of
the main thread equal.
Fascinatingly the two added functions prompt my compiler to issue
`missing prototype' warnings, although those are obviously there. It would
be nice if someone could solve that riddle.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11621 a95241bf-73f2-0310-859d-f6bbb57e9c96
we only have 3 debug registers available for break-/watchpoints.
* Added definitions for debug status register DR6. Reordered DR7 defs to
ascending order. Added definitions for the EFLAGS flags we need.
* Added arch_thread_debug_info structure and related definitions.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11525 a95241bf-73f2-0310-859d-f6bbb57e9c96
needed to get the topmost user iframe. Added i386_get_user_iframe() for
exactly that purpose.
* Added reinitialization of user debugging for the new thread when
switching the context.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11523 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Made the parameter for restoring the FPU state const.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11522 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added event callbacks for break- and watchpoints and single stepping.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11520 a95241bf-73f2-0310-859d-f6bbb57e9c96
debug infos.
* Added function for setting the CPU state.
* Added functions for setting break-/watchpoints.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11507 a95241bf-73f2-0310-859d-f6bbb57e9c96
by the team lock, but by a lock in the structure. This is necessary
since we can't acquire the team lock while thread switching, for then the
thread lock is already held.
* Added support for single stepping and break-/watchpoints.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11503 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Removed SIGKILLTHR from BLOCKABLE_SIGS.
* Made header C++ safe.
* Added function is_kill_signal_pending(), returning true, if a
SIGKILL[THR] is pending for the current thread.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11487 a95241bf-73f2-0310-859d-f6bbb57e9c96
convenience.
* Added/implemented callbacks for almost all missing debug events (team,
thread, image creation/deletion, exceptions/faults, signals).
* The debugger can now specify how to deal with the event that stopped an
event (ignore or handle signals, exceptions/faults).
* Implemented B_DEBUGGED_THREAD_GET_WHY_STOPPED debugger message.
* The cpu_state is now passed to the debugger with
B_DEBUGGER_MESSAGE_THREAD_STOPPED notifications.
* Completed _user_debugger() implementation.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11474 a95241bf-73f2-0310-859d-f6bbb57e9c96
will also get syscall that the app_server has to call in order to update
the frame buffer configuration.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11352 a95241bf-73f2-0310-859d-f6bbb57e9c96
and thread_at_kernel_exit() are always called for userland threads at the appropriate
situation (note, I've renamed those from *_atkernel_*).
The timing should be more accurate this way, and the thread::last_time_type field
is no longer needed: all interrupts are now added to the kernel time (where the
time is actually spent).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11331 a95241bf-73f2-0310-859d-f6bbb57e9c96
Removed *_create() and *_create_entry_ref() syscalls - they are now handled by
*_open() and *_open_entry_ref() calls which get another parameter for the permissions.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11204 a95241bf-73f2-0310-859d-f6bbb57e9c96
link member in the element class. Usually more comfortable for structs.
* Added Add() method as synonym for Insert().
* Made fGetLink member static to save memory in objects using it.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11188 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added resolve_mount_point_to_volume_root() version for external use
(by the node monitor).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11159 a95241bf-73f2-0310-859d-f6bbb57e9c96
<disk_device_manager/KDiskDeviceUtils.h> into <util/AutoLock.h>.
Added instantiations for recursive locks (moved from vfs.cpp) and
mutexes.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11157 a95241bf-73f2-0310-859d-f6bbb57e9c96
proper private static BMessage members and made them accessible through
BMessage::Private. Got rid of unused _reconstruct_message_().
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@11106 a95241bf-73f2-0310-859d-f6bbb57e9c96
to userland applications. A userland server (probably the registrar) will
register as the server responsible for delivering the messages. The
messages are passed to it via shared memory.
The advantage over sending the messages directly will be, that they won't
need to be dropped, if the receiver port is temporarily full.
Currently only the kernel side is implemented. Completely untested yet.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10983 a95241bf-73f2-0310-859d-f6bbb57e9c96
append-only and hence has very compact storage and a comparatively small
footprint implementation. Can be used for kernel->userland messaging.
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10958 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Replaced the constant kRosterPortName by a function returning that name
(we need different port names under BeOS and Haiku, and already at
libbe init time).
* The settings directory is obtained via find_directory() (critized by
Axel :-).
git-svn-id: file:///srv/svn/repos/haiku/trunk/current@10812 a95241bf-73f2-0310-859d-f6bbb57e9c96
