Socket waits now block in select() on the socket plus a wake or cancel
socket (Common/Net/Cancel), so a stop or cancel ends them at once.
- HTTP: cancel flags become net::CancelToken; Connect waits once on all
addresses, receives wait instead of spinning, no DNS retry sleep.
- Adhoc: the friend finder and adhoc server block on their sockets with
a wake socket and a deadline; matching runs on a CoreTiming tick
instead of two threads (savestate section bumped).
- sceNetInet select/poll check without blocking and park the HLE thread,
re-checked from a CoreTiming event until ready or the emulated
timeout.
- Vendor the aemu_postoffice client (was a submodule) with no sleeps:
waits on the socket, close via shutdown and an eventcount, cancelable
connects, and lock-free session slot claims.
- PortManager waits without a timeout; PSP_InitWait replaces the
headless boot poll.
- TimeUtil: sleep_us/sleep_ms only outside the core; sleep_precise,
sleep_random, yield and the Windows timer period are gone.
- Unit test for the socket waits.
We haven't activated it for a long time, and nowadays PPSSPP has a completely
different level of compatibility and performance compared to back when
we added the upgrade reminder.
Also I'm no longer a fan of HTTP requests on startup, even if only every
10 times like we did.
So, away it goes.
Moved the potentially useful translation strings into [Dialog].
sleep_ms() should generally be avoided when possible. This can be used to try
to track down unnecessary sleeps by adding some logging.
This commit on its own doesn't actually add any logging.
* Rename LogType to Log
* Explicitly use the Log:: enum when logging. Allows for autocomplete when editing.
* Mac/ARM64 buildfix
* Do the same with the hle result log macros
* Rename the log names to mixed case while at it.
* iOS buildfix
* Qt buildfix attempt, ARM32 buildfix
It seems to be possible for a user to back out of a screen before
receiving the "dialog completed" callback on Android, in which case
things pointed to by the callback might be gone.
In this case, it's better to simply not call the callback, rather than
crashing.
This is accomplished by assigning "Tokens" to screens that cause
requests, and in ~Screen, invalidate any pending requests belonging to
that token.
libretroadmin