* Continue working in the _FinishTransfer thread
* added next_done_descriptor in ohci_[general|isochronous]_td structure in order to handle
collisions.
* added next_logical_descriptor to ohci_isochronous_td structure
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23594 a95241bf-73f2-0310-859d-f6bbb57e9c96
of the descriptor from its physical address returned by the controller.
NOTE: As stated in the commented code, when the controller has finished processing
some descriptors, it returns the first element physical address of an heterogeneous list
(general + isochronous) and there is not way to tell the descriptor type.
This solution, which implementes two hash tables (one for generic descriptors and
one for isochronous) is the one adopted from *BSD.
If somebody has better idea, please let me know. :)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23589 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Removed ID 0x0141 for the FX 6600 as well until it's fixed, see ticket #1530
for details.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23579 a95241bf-73f2-0310-859d-f6bbb57e9c96
in the critical error handler. In the high level function, the jmp_buf is
now allocated on the stack and placed in the "cinfo->err" structure. This
should make the mechanism thread-safe. Unfortunately, we don't use the
original libjpeg anymore as is, but this seems to be frozen code since a
few years anyways. If you have any better suggestions, please don't
hesitate to mention them! :-)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23560 a95241bf-73f2-0310-859d-f6bbb57e9c96
that only loads bitmaps and is supposed to return a status_t error from
the Translate() function, especially for people using this in mission
critical applications.
The requirements on the error handler that is
to be installed for the jpeg library are not to return to the calling
function for critical errors. C++ exceptions seem like the
natural solution to the problem, but unfortunately, they simply don't
seem to work, possibly because we are inside an add-on. Ingo had the idea
to use setjmp() and longjmp() to go directly from the error handler back
to the top level code and this works. I have implemented this from what
I understand from reading the opengroup spec, but the compiler currently
issues a warning. Feel free to fix. The desired effects are achieved though,
the translator recovers correctly from broken jpg files now.
Also, I don't know if the translator should somehow "uninstall" the
breakpoint. Again, feel free to fix or tell me.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23559 a95241bf-73f2-0310-859d-f6bbb57e9c96
compute the bit offsets correctly if the last block of the whole
bitmap was only a partial block.
* Added new bfs_allocator KDL command.
* Renamed the KDL command bfsinode to bfs_inode.
* Added "--help" argument to bfs_inode and bfs KDL commands.
* Added more tracing in the block allocator.
* Turned on the ASSERT() macro in non-debug builds.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23534 a95241bf-73f2-0310-859d-f6bbb57e9c96
transaction ends or has been aborted.
* BFS now listens for transactions when it created an inode to see if
the transaction will be aborted without freeing the inode (in which
case it will panic for now).
* Started implementing tracing support, but it's not working yet.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23492 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Added function to allocate space in the buffer.
* Dump() now fills a buffer instead of printing its data directly.
* This allows the new "#pattern" argument of the "traced" command to
work. When you're using that, the index of the trace entry is printed
out, too, so that you can then get a full dump around the hits.
* Added an AddDump() method to the AbstractTraceEntry class so that
there is no need to call the inherited function anymore.
* Minor cleanup.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23479 a95241bf-73f2-0310-859d-f6bbb57e9c96
DEBUG macro; they are now added only if BFS_DEBUGGER_COMMANDS is
defined (which is now done by default in the Jamfile).
* Added "bfs" KDL command which dumps volume information and the super
block.
* Made use of the new tracing API to trace block and inode actions
(and the new AbstractTraceEntry class I forgot to mention in the last
commit). Is compiled in only when BFS_TRACING is enabled (defaults to
off in the standard builds).
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23464 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Removed now unnecessary devfs calls again
* Add an explanation in device_removed()
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23442 a95241bf-73f2-0310-859d-f6bbb57e9c96
B_MOUSE_MOVED message does not already contain the same buttons as a
following B_MOUSE_DOWN message... fixes mouse clicks being ignored
when you are moving the mouse at the same time when clicking
(using Haiku's mouse input_server device on BeOS or ZETA)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23421 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Beginnings of devfs interaction to properly publish/unpublish under Haiku
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23412 a95241bf-73f2-0310-859d-f6bbb57e9c96
* handle one more allocation failure in device_added
* improved style consistency in a few places
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23409 a95241bf-73f2-0310-859d-f6bbb57e9c96
and you never pressed any key on the usb keyboard, you could suddenly
be flooded with a random key...
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23403 a95241bf-73f2-0310-859d-f6bbb57e9c96
should fix detection of Audigy2 Value (it was trying to check the revision id instead of the device id)
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23399 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Some restructuring and cleanup
This keeps the input_server from polling a removed device continuously.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23388 a95241bf-73f2-0310-859d-f6bbb57e9c96
* Actually enable the periodic schedule so that any interrupts work over EHCI
For those who wait for OHCI: You can now attach your USB 1.1 mouse or keyboard
to a USB 2.0 hub and it should work.
git-svn-id: file:///srv/svn/repos/haiku/haiku/trunk@23382 a95241bf-73f2-0310-859d-f6bbb57e9c96
