* Use Linux timers for sleeps up to 1ms (v3)
The current sleep timer implementation basically offers two variants. Either
wait the specified time exactly with a condition variable (as host) or use a
combination of it with a thread yielding busy loop afterwards (usleep timer).
While the second one is very precise it consumes CPU loops for each wait call
below 50us. Games like Bomberman Ultra spam 30us waits and the emulator hogs
low power CPUs. Switching to host mode reduces CPU consumption but gives a
~50us penalty for each wait call. Thus extending all sleeps by a factor of
more than two.
The following bugfix tries to improve the system timer for Linux by using
Linux native timers for small wait calls below 1ms. This has two effects.
- Host wait setting has much less wait overhead
- usleep wait setting produces lower CPU overhead
* sys_cond fixes
sys_cond_wait is now signaled atomically (regression fix)
Fix a corner case with sys_cond_wait and sys_cond_destroy EBSUY check (waiter count was inaccurate if thread is not the owner of mutex)
Add not about EBUSY corner case (TODO)
* Fix inconcistency in sys_cond_destroy and ETIMEDOUT
.. event at sys_cond_wait regarding waiters count.
Now waiters count is properly connected to the mutex owner actions after ETIMEDOUT in sys_cond_wait.
Possibly fixes sys_fs_rmdir and other cases of directory removal.
Make sure the directory with deleted files always becomes empty.
For this purpose, temp files are moved to the root of the device.
- Add an explicit frame scope marker tied in with the queue_prepare command
Since queue_prepare is emitted at the end of a frame, it can be used as end-of-frame in games that emit this
- If this command is not emitted, fifo flatenner and frameskip will not work
With the option enabled GET commands are blocked until the current PUTLLC/PUTLLUC executer on that address finishes
Additional improvements:
- Minor race fix of sys_ppu_thread_exit (wait until the writer finishes)
- Max number of ppu threads bumped to 8