Commit Graph

14188 Commits

Author SHA1 Message Date
Axel Dörfler
f3bb653937 Simplified sigsuspend() a bit.
Minor cleanup.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14460 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 18:38:30 +00:00
Axel Dörfler
7d9e0897ed Implemented sigsuspend() - not tested, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14459 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 18:09:50 +00:00
Axel Dörfler
e4d36dd1f4 Implemented sigpending().
Forgot to atomically get some thread_debug_info values.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14458 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 17:19:46 +00:00
Axel Dörfler
50374cbdca Changed the signal handling code so that handle_signals() can be called without
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
2005-10-20 16:56:04 +00:00
Axel Dörfler
7121425eb5 Turns out we could remove a mount point...
Under BeOS remove_vnode() is failing in this case, which looks like a good idea to imitate.
Also, pipefs/rootfs didn't handle that case - they even removed the entry before calling
remove_vnode() - they now behave correctly. And also BFS now returns the actual error code
received from remove_vnode() instead of B_ERROR.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14456 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 16:34:18 +00:00
Rudolf Cornelissen
195828c401 checked CX25871 on wstv: all modes OK. So only a 'comments update' here.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14455 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 15:37:28 +00:00
Rudolf Cornelissen
5cadaa5f63 verified CX25871 on NV11 working OK. Tweaked it's horizontal TVpicture position for PAL VCD and NTSC DVD to be indeed overscanning on all sides on a 4:3 TV. Enabled TVout upto/including NV15, still assuming TVout is on primary head for dualhead cards (will fix that asap I hope). Newer cards with BT/CX still only display the testimage if TVout is enabled. Fixed 'random horizontal position of TVout picture' on NV11.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14454 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 15:06:29 +00:00
Axel Dörfler
4daad1792e You shall compile before you commit - I must have forgotten to save the file
on the previous try (I definitely built mountvolume & mount after the changes).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14453 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 13:21:10 +00:00
Stephan Aßmus
09b3f55cb1 replaced the NOTES files in each subfolder with a single NOTES file in the parent folder, and updates the NOTES to the current information
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14452 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 13:17:18 +00:00
Stephan Aßmus
dd79576b10 * fixed scrolling for the current clipping code, it brings
up a new problem, maybe Adi has an idea for the fix, see
  comment in the code


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14451 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 13:06:38 +00:00
Axel Dörfler
da6d1a7022 fs_mount_volume() now returns a dev_t as well - changed mount/mountvolume to take
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
2005-10-20 13:03:50 +00:00
Stephan Aßmus
9949213a25 removed the redundant "translator" from the folder names, fixed some warnings in the JPEG2000Translator
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14449 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 12:15:56 +00:00
Stephan Aßmus
a405a49e82 * cleaned up and applied coding style to FontStyle
* 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
2005-10-20 10:01:49 +00:00
Stephan Aßmus
2b8347c0d8 don't use potentially stall freetype font face handles. The code is
more correct now, but it doesn't actually fix anything, since FT_Face
handles are nowhere freed in the app_server code.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14447 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:51:56 +00:00
Stephan Aßmus
00e0821ffd Use a ServerFont instance which is assigned to the currently
used font, so that the FontStyle reference count reflects the
fact that the AGG engine might still use the font
-> I think this "fix" is valid, but I have still seen crashes
in the freetype code.



git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14446 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:44:46 +00:00
Stephan Aßmus
ccdfe4055f Jerome is encoded in UTF8
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14445 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:39:12 +00:00
Stephan Aßmus
c0a539ccec Jerome is encoded in UTF8
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14444 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:37:40 +00:00
Stephan Aßmus
c8292991d2 applied coding style
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14443 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:37:04 +00:00
Axel Dörfler
9ebc6e3c2d Added a comment on what kind of functionality we need from the caching layer one day.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14442 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:29:40 +00:00
Rudolf Cornelissen
10aea461cc oops. Now only uninstalling INT handler if it was previously installed.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14441 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:10:32 +00:00
Rudolf Cornelissen
e68584fa18 added shared_info flag for 'no-INT-assigned' stuff.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14440 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:02:37 +00:00
Rudolf Cornelissen
52c8d6219d added no-INT-assigned capability to kerneldriver. Updated docs.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14439 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:01:54 +00:00
Rudolf Cornelissen
ce3fc95ee4 added capability to driver to run without an INT assigned. Driver now autodisables 'Sync_to_Retrace' functionality if it finds no INT assigned, instead of not loading/running the driver at all. This should enable some users outthere to finally run the nVidia driver on their systems. Bumped version to 0.56. Note: While driver has been tested with INT assigned, it has not yet been tested without it. (got to find a system which has the option or fixed disabled BIOS setting).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14438 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-20 09:00:38 +00:00
Axel Dörfler
1c88c851ad Turned off debug output again - also temporarily removed the file cache warning
about our block_io module not honouring the total length in read_pages().
Removed drops into the debugger when there is a block without an "original"
data buffer - that's completely normal and happens when someone asks for
a cleared block that is not yet in the cache.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14437 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 23:01:57 +00:00
Axel Dörfler
d7f0a6f215 If register_preloaded_module_image() fails, a warning is printed.
get_next_loaded_module_name() no longer prints anything if tracing is enabled.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14436 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 22:45:13 +00:00
Axel Dörfler
8c20600d12 Looks like some BIOS don't bother filling in cylinder/head/sectors_per_track information
for extended drive parameters.
This should fix eventual "no boot disk" messages of the boot loader.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14435 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 22:43:50 +00:00
Axel Dörfler
cb6d675cf4 Aborting transactions doesn't change the number of unwritten transactions - that
counter does not take the current transaction into account.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14434 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 22:26:49 +00:00
Axel Dörfler
944278d7ed Fix the build - Stack.h is now gone from the BFS directory.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14433 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 17:43:45 +00:00
Axel Dörfler
9a99234b1a Implemented basic sub transaction support - seems to work so far, but I haven't
tested it heavily yet.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14432 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 16:49:01 +00:00
Axel Dörfler
ca7c5a9e13 Implemented cache_detach_sub_transaction() - not tested yet, though.
Added and implemented new functions cache_blocks_in_[sub_]transaction().


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14431 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 16:46:17 +00:00
Jérôme Duval
6ded062819 updated third party tool: bison-2.1
removed unused dirs to be lighter


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14430 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 15:07:54 +00:00
Axel Dörfler
94752292dd First go at an implementation of sub transactions - code is not yet tested, though.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14429 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 14:37:29 +00:00
Axel Dörfler
bd0b075c13 Now takes the off-by-one error in Be's BFS implemenation into account, too.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14428 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 14:36:21 +00:00
Axel Dörfler
3a7c99e12d Oops, this one did only work for my test case...
The last log entry was never added to the list (if there were more than one), and
thus, it's blocks were never unlocked nor written back (after some minutes of
makehdimage an empty image would greet you).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14427 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 14:32:25 +00:00
Jérôme Duval
f7b4a08237 updated bzip2 version info
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14426 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 13:57:02 +00:00
Jérôme Duval
6c21682df5 updated third party tool: bzip2-1.0.3
added man pages


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14425 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 13:54:56 +00:00
Jérôme Duval
1a8f53bbf7 added a SourceVisitor and a TargetVisitor to go through BDiskDevice and BPartition objects
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14424 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 13:11:11 +00:00
Axel Dörfler
8047f0a02d Ported the new logging structure over to the old R5 BFS version - doesn't optimize it,
though, so it's not really ready to be used in a real file system.
Found an off-by-one/some error in Be's BFS implementation: it doesn't use the log
array to its full extent.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14423 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 12:59:04 +00:00
Jérôme Duval
94fa227876 update third party lib : libiconv-1.10
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14422 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 08:42:03 +00:00
Jérôme Duval
42f724a7f3 update third party lib : zlib-1.2.3
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14421 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 08:31:31 +00:00
Jérôme Duval
9b85b132da update third party lib : libpng-1.2.8
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14420 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-19 08:29:54 +00:00
Jérôme Duval
b461fb1d4b added a haiku logo from stippi, thanks!
enlarged the window
improves widget placement


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14419 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 23:10:27 +00:00
Axel Dörfler
e620c9328c Argl, turns out Be's replay log routine cannot handle block_runs with a size unequal
1 - IOW using block_runs here is completely bogus.
Crippled our code to not create longer block_runs - at least, a dirty BFS image is
now a dirty BFS image - you can mount a dirty image on either system and it will
work :-)
The R5 version of our BFS is still incompatible though - ie. running bfs_shell or
copy_to_bfs_image on a dirty image will still potentially corrupt it. Maybe I'll
even port the changes over one day...


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14418 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 20:52:15 +00:00
Axel Dörfler
b68efdcaa7 We now use the kernel's Stack class instead of our own copy.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14417 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 20:03:00 +00:00
Axel Dörfler
0bf62ebece The BlockArray class is now longer used, and strlcpy() is part of the Haiku kernel anyway.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14416 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 20:02:16 +00:00
Axel Dörfler
a59b9afff0 Rewrote the log entry writing so that it should be BFS compatible - not yet tested for
compatibility, though!
Writing is now combined into a few writev_pos() function calls to speed up log writing.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14415 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 20:01:42 +00:00
Axel Dörfler
636d40373d Moved the "reopen when read-only" logic into the DeviceOpener class.
Since CD-ROMs let open themselves read/write, it now also checks the device
geometry, and will make sure the device is opened read-only if the geometry
structure says so - this should reduce the number of write errors you get
during boot :-)
Volume::fFlags is now always correctly maintained.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14414 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 19:58:19 +00:00
Axel Dörfler
0fc0129604 Fixed another stupid bug in all readv()/writev() versions: the position of
the read/write access was only correct for the first entry in the iovec.
These functions should be updated to use read_pages()/write_pages() where
possible, anyway - right now, they only save some kernel calls, while they
could be processed by the device at once.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14413 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 19:51:47 +00:00
Axel Dörfler
28953e6c2b Fixed two stupid bugs in _kern_writev() and _kern_readv() - they accidently
tried to write from/read to the userland file descriptor instead of the one
of the kernel.


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14412 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 19:11:07 +00:00
Waldemar Kornewald
e50616872e We should not forget to stop the etherq (was not sure if the stack does
it for us, but seems that we had a lock/memory-leak, here).


git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@14411 a95241bf-73f2-0310-859d-f6bbb57e9c96
2005-10-18 18:46:45 +00:00