RPCSX/rpcsx
1
0
Fork 0
mirror of https://github.com/RPCSX/rpcsx.git synced 2026-02-10 17:54:23 +01:00
Code Issues Actions Packages Projects Releases Wiki Activity
11379 commits 5 branches 1 tag 150 MiB
Commit graph

9667 commits

Author SHA1 Message Date
Nekotekina bd90e3e37f atomic.cpp: shrink and simplify main hashtable 
Reduce collision detection to 1 or 0 for now.
I think it should be offloaded to notifiers.
 2020-11-26 20:11:26 +03:00
Nekotekina 8b6d615aa6 atomic.hpp: remove/deprecate incomplete notify features 
Notification with "phantom value" could be useful in theory.
As an alternative way of sending signal from the notifier.
But current implementation is just useless.
Also fixed slow_mutex (not used anywhere).
 2020-11-26 06:31:36 +03:00
Megamouse 9e352da052 Handle some undefined behavior regarding null pads 2020-11-26 00:45:49 +01:00
Nekotekina 95b8467a76 perf_meter.hpp: move logic to noinline function 
May improve performance if perf meter is disabled.
 2020-11-25 10:41:17 +03:00
Nekotekina 2b674d4d8c utils::shm: allow 2M hugepages on demand 2020-11-25 10:41:17 +03:00
Nekotekina 487b572aa6 Linux: remove assertions on MADV_HUGEPAGE 
It's a hint and is allowed to fail.
 2020-11-25 10:41:17 +03:00
Nekotekina 600c0ea5ba atomic.cpp: fix windows/std path 
Always check condition after rearming internal semaphore.
 2020-11-25 10:41:17 +03:00
Nekotekina 00e64920c8 Implement "slow mutex" without spin-waiting. 
Benefits: only 1 byte.
Testing atomic wait.
 2020-11-25 10:41:17 +03:00
Megamouse 9efedbe76a Minor changes related to Emu.Stop() 2020-11-25 00:11:07 +01:00
Nekotekina d8e9382573 asm.hpp: constexpr refactoring 
Removed asm (what an irony), made many functions constexpr.
Removed some unused function, readding them should be trivial.
 2020-11-24 13:20:40 +03:00
Nekotekina ab248e170c vm_native.cpp: add MADV_HUGEPAGE 
It enables Transparend Huge Pages for some regions on Linux.
Although it can't be actively useful, it seems to do something.
Maybe it's even harmful for recompilers.
 2020-11-24 12:31:11 +03:00
Nekotekina 27097cbcfe atomic.hpp: alter atomic_storage<>::store a bit 
Always fallback to exchange. May improve codegen on gcc.
 2020-11-24 12:31:11 +03:00
Nekotekina 43952e18e2 Implement prefetch_write() and prefetch_exec() wrappers 
Do some refactoring to prefetch_read() in util/asm.hpp as well.
Make all these function constexpr because they are no-ops.
 2020-11-24 12:31:11 +03:00
Megamouse 5076da8f77 Fix auto exit 
- Don't quit on stop if force boot was set
- Don't stop the emulator on gs_frame close when it was already stopped. This would remove the force boot flag by mistake.
 2020-11-24 11:17:03 +03:00
kd-11 8228a4adcd gl: Disable depth test before rendering text to the backbuffer which does have a Z buffer 2020-11-24 11:10:43 +03:00
Eladash 3f028fbb83 Fix SPU LS MMIO 2020-11-24 03:44:30 +03:00
Nekotekina f0cba1371c vm: adjustments 
Increase max range lock size (less than 512 MiB)
Remove "range_executable" flag, make it reserved.
 2020-11-24 01:09:04 +03:00
Nekotekina 14fa96fdef atomic.cpp: don't use empty notify callback 
Instead, allow setting it to null and check for null.
Similar could be done for wait cb, but it's set for all named threads.
 2020-11-24 01:09:04 +03:00
kd-11 f1c65dcefc vk: Improve support for RDNA 
- Add support for RDNA2
- Add RDNA MSAA workaround
 2020-11-23 19:20:00 +03:00
Nekotekina 16cc88dd0e atomic.hpp: fix atomic_wait::list regression 
Typo-regressions. Also improve static asserts.
 2020-11-23 09:26:25 +03:00
Nekotekina 280f5f0b54 atomic.hpp: redefine op::ne to actually mean "not equal" 
WTF is "native endianness", it's native by default.
 2020-11-23 09:24:16 +03:00
Nekotekina f85c8584b0 Attempt to fix #9316 2020-11-22 12:57:50 +03:00
Nekotekina 6cf50f8f6c Second attempt to fix hanging RPCS3 process 
Now fix exit logic a bit.
Remove Init() call from Stop().
Remove Stop() call from Quit().
 2020-11-22 12:45:19 +03:00
Nekotekina d70ab11477 atomic.cpp: remove redundant constexpr 
Static initialization is all-zeros anyway.
But constexpr was killing my intellisense.
And probably also affected compile time.

Also make some internal structures hidden ("static").
 2020-11-22 12:07:49 +03:00
kd-11 cab4c78b7b rsx: Some shader compiler threads tuning 
- Allow more threads for wide CPUs
- Simplify 'auto' selection a bit
 2020-11-21 20:43:15 +03:00
kd-11 14358d5e84 qt: Add shader compiler threads to GUI 2020-11-21 20:43:15 +03:00
kd-11 7553429130 gl: Thread shader source compilation dispatch 
- glCompileShader is in itself much slower than anticipated
 2020-11-21 20:43:15 +03:00
kd-11 3ddfa288cf rsx: Use multithreaded shader compiler backend 2020-11-21 20:43:15 +03:00
Nekotekina e89a568765 Attempt to fix Emu.Quit() 
There was some kind of "initialization order fiasco" of g_fxo.
Not only should it be used after main, but also destroyed before exit.
 2020-11-21 18:27:16 +03:00
Nekotekina 71f1021648 Fix thread pool entry point and get_cycles() 
Fix possible race between thread handle availability.
Don't treat zero thread as invalid one.
Now entry point is full is assembly.
Attempt to fix #9282
Also fix some TLS.
 2020-11-21 17:18:42 +03:00
Nekotekina 60cff6f3d4 Attempt to fix #9271 2020-11-21 07:09:48 +03:00
Nekotekina 5f010c2f4c atomic.cpp: optimize "cond" allocation with TLS 
Billions of events can reduce to thousands, saving CPU time a few s.
Only 4 slots are available (arbitrarily), and only 1 is usually used.
Other slots are used only for waiting on multiple atomics.
 2020-11-20 19:13:22 +03:00
Nekotekina 6c18e00977 atomic.cpp: use deterministic "cond" allocation 
Takes ~80 ns instead of ~40 ns, same about deallocation.
Loops don't exist here, only 4-level semaphore tree.
Worst case only happens with concurrence, not from looping.
This optimization is not really necessary at current state of RPCS3.
This is more like to test C++ compilers and MSVC u128 implementation.
 2020-11-20 15:04:17 +03:00
Nekotekina 72ac1aa537 atomic.cpp: use some actual hash for hashtable (std::minstd_rand) 
Should only take about 5ns for initialization.
Should also make collisions almost impossible.

I also suspect I fixed some bad bug in process...
 2020-11-20 15:04:17 +03:00
Nekotekina 5bcaa25c02 CPU: remove descheduled threads from suspend_all list 2020-11-20 13:53:34 +03:00
Eladash 85880ffded
SPU: Log STOP full opcode (#9292) 
Co-authored-by: Ani <ani-leo@outlook.com>
 2020-11-20 13:53:16 +03:00
Megamouse 5b207c3b95 hotfix for infinite loop when booting game data 2020-11-19 23:53:10 +01:00
Megamouse 3087f15dd8
Update disc boot detection and hope it works 2020-11-19 21:55:06 +01:00
Nekotekina 292af1e4cd CPU: use u128 in bit counter 
Apparently, u64 was not enough.
 2020-11-19 16:05:08 +03:00
Nekotekina d4d5dc99f3 Fix perf_meter<> after adding thread pool. 
Print and reset sorted information after emulation stop/pause.
Print useless average value.
 2020-11-19 14:44:58 +03:00
Nekotekina 3e1344e4e4 vm.cpp: minor optimization for filling stack guards 
Use REP STOSQ on all compilers.
 2020-11-19 14:44:58 +03:00
Nekotekina 6d37bc62a5 CPU: remove cpu_counter from g_fxo 
Convert it to a namespace, simplify add/remove functions.
Don't add() threads just creates, they are trapped in check_state() anyway.
Don't add() threads which are leaving check_state() because stopped.
 2020-11-19 09:46:22 +03:00
Nekotekina e9f7c100a0 CPU: update suspend interface (dummy) 2020-11-18 19:15:56 +03:00
Nekotekina 190676c982 CPU: Fix g_suspend_counter waiting logic 2020-11-18 14:38:01 +03:00
Eladash 28cbba5a7d
SPU LLVM: fix AND instruction family (#9290) 
Incorrect immediate test (looks like copypasta)
 2020-11-18 14:36:26 +03:00
kd-11 0e7a705254 rsx: Resolution scaling overhaul 
- Enforce square pixels instead of per-axis scaling
 2020-11-18 09:29:34 +03:00
Nekotekina 68931b4c43 Debugger: fill stack guard with STACKGRD 2020-11-17 16:32:59 +03:00
Nekotekina 65c81c5e83 Fix memory viewer for SPU LS 2020-11-17 15:22:04 +03:00
Nekotekina ccd0d2046d SPU: increase max SPU count 
According to max SPU TG count.
 2020-11-17 15:22:04 +03:00
Nekotekina 0fec99e75b SPU: absolutely unacceptable hack for SPU LS 
Make normal threads inaccessible in PS3 memory.
 2020-11-17 15:22:04 +03:00
Nekotekina f8d1f070f5 sys_memory: HORRIBLE HACK for sys_memory_get_page_attributes 2020-11-17 15:22:04 +03:00
Nekotekina 3dd48a24ce atomic.cpp: remove tiny redundancy 2020-11-17 15:22:04 +03:00
Nekotekina 984e97cbdc Potential fix for Linux compilation 2020-11-17 15:22:04 +03:00
Eladash 50ea1a12c9 Debugger: Fix scrolling in first registers panel 2020-11-17 09:39:39 +01:00
Eladash 992a372fc7 cellGame fixes 2020-11-17 09:04:35 +01:00
Nekotekina d7e1cf7dd2 vm: respect initial protection for allocation mapping 
Unused yet.
 2020-11-17 05:33:46 +03:00
Nekotekina ea5f5aea5f vm: memory locking rewritten 
Added vm::lock_sudo method (wrapper for utils::memory_lock).
Put locking outside of vm::g_mutex scope.
Prelock sudo memory for RSX, vm::stack, vm::main.
Prelock sudo memory for shared memory objects.
Don't check for TSX path.
 2020-11-16 12:46:15 +03:00
Nekotekina eaf0bbc108 SPU: don't allocate SPU LS in vm::main 
Create its own shared memory object.
Use vm::spu to allocate all SPU types.
Use vm::writer_lock for shm::map_critical.
 2020-11-16 12:46:15 +03:00
Eladash b1710bb712
SPU Debugger: Implement float registers view + General debugger fixes (#9265) 
* SPU Debugger: Fix try_get_insert_mask_info
* Debugger: Always update thread state on context's data change
No longer needing to press on thread's instructions for actions to work!
 2020-11-15 08:45:28 +03:00
Nekotekina dfae7bd073 SPU: Fix some stat printing 2020-11-15 04:41:16 +03:00
Nekotekina 333fe9a561 atomic.cpp: fix notification on windows 2020-11-15 04:40:44 +03:00
Nekotekina badb3dc2dd atomic.cpp/threads: remove old wait callback 
Add new wait callback which simply collects statistics.
Shift workarounds towards actual problem detection.
 2020-11-14 18:16:27 +03:00
Nekotekina 3ac819ee70 atomic.cpp: fix waiting on multiple variables 
Silly bugs are so silly...
 2020-11-14 17:25:02 +03:00
Nekotekina 00f877e812 atomic.cpp: fix rare overload scenario 
If slot allocation fails, increase reference counter in every slot.
This prevents search routine from "losing" some slots.
 2020-11-14 13:56:23 +03:00
Nekotekina 1e269751bf Temporarily disable memory locking if TSX is not used 
It's a very heavy operation that could cause some problem under mutex lock.
 2020-11-14 11:12:58 +03:00
Nekotekina 5b69eda39a Fix suspend_all bug (TSX, TSX-FA) 
Could cause freezes.
 2020-11-14 10:56:05 +03:00
Nekotekina 71ca413067 Don't add lonely cpu_flag::memory on TSX path (bug) 2020-11-14 09:03:33 +03:00
Nekotekina ab365fe494 Fixed thread pool a bit 
Use 128-bit allocator instead of queue.
When pool is full (128), threads just terminate as before.
 2020-11-13 13:32:44 +03:00
Nekotekina e48f160a29 atomic.cpp: continuation of fixing all-ones masks 
Also added missing const noexcept.
 2020-11-13 12:40:02 +03:00
Nekotekina cfda4d0ade atomic.cpp: optimize raw_notify() for unspecified pointer mode 
Remove unnecessary optimization from cond_alloc().
Optimistic case was absolutely dominating anyway.
Although the whole function is a dirty hack.
Now scanning through all threads is faster.
 2020-11-13 07:05:33 +03:00
RipleyTom debfae06a8 Improve disconnected state handling of dns queries 2020-11-13 07:05:06 +03:00
RipleyTom e6f2f8ad0d Add some error checking in sceNp2.cpp 2020-11-13 05:28:00 +03:00
Nekotekina 67785a918c Implement simple thread pool 2020-11-13 03:32:24 +03:00
Nekotekina 3888b0429c atomic.cpp: print some stats on stop 2020-11-12 05:52:22 +03:00
Nekotekina 70761a4ef0 atomic.cpp: fix notification bug from few commits before 
Make sure forced notification ignores mask comparison.
Also fix masks provided by smaller types to correct ones.
 2020-11-12 05:01:44 +03:00
Nekotekina e37df998e9 atomic.cpp: minor optimization 
Silly MSVC emits unnecessary initialize-on-first-use code guards.
Didn't check other compiler. But workaround just works anyway.
 2020-11-12 03:41:19 +03:00
Nekotekina c30cdfb3a7 atomic.cpp: merge more atomic variables for simplicity 
Compress 16-bit ref counter and two 48+64 bit slot allocators.
This allowed to remove some weird unnecessary logic paths.
Adjust hashtable size to keep it the same.
 2020-11-12 03:39:05 +03:00
Nekotekina 350b704cd7 atomic.cpp: combine two atomics (ref ctr and wait ptr) 
Should fit into cache line perfectly.
Also makes ptr check more robust.
 2020-11-12 01:06:12 +03:00
Nekotekina ad013d59f4 atomic.cpp: don't load actual memory on empty mask 
It's not an optimization. It just allows some tricks safely.
 2020-11-11 23:59:09 +03:00
Nekotekina d391133524 atomic.cpp: minor notification improvement 
Check mask before locking the reference.
Can help to not bother non-eligible waiters.
 2020-11-11 23:51:41 +03:00
Nekotekina 4b823469f7 atomic.cpp: restore notify_all() behaviour 
Restore batch notification with non-blocking attempts.
 2020-11-11 22:43:13 +03:00
Nekotekina 7cd1e767be atomic.cpp: implement some atomic wait operations. 
Instead of plain waiting while equal to some value,
it can be something like less, or greater, or even bitcount.
But it's a draft and untested. Hopefully doesn't break anything.
 2020-11-11 20:46:37 +03:00
Eladash fefab50e06 Fix vm::range_lock, imporve vm::check_addr 2020-11-11 10:30:09 +03:00
Eladash 6e27ab60ca Registers Editor: Implement SPU/PPU register value broadcast 2020-11-11 10:27:45 +03:00
Eladash 74274f6d77 Debugger: Improve SPU/PPU vector registers 2020-11-11 10:27:45 +03:00
RipleyTom 908b2703f3 Fix missing controller mapping 2020-11-11 07:16:45 +03:00
Nekotekina c047ab6147 atomic.cpp: waitable atomics got brutally rewritten 
Hashtable increased and flatten, tree-alike extensions removed.
Some things simplified, so it can actually decrease perf a bit.
But most platforms shouldn't be affected.
Removed limit of 56 waiters per pointer.
Real limit now is about 65535.
 2020-11-11 05:35:27 +03:00
Eladash 52fa69d93d SPU Debugger: Improve registers panel 2020-11-10 22:51:52 +03:00
RipleyTom a83df01bfd
rpcn 0.3.5 (#9227) 2020-11-10 08:55:49 +00:00
Eladash b32d989a10 Fix PPU stack contents on allocation 2020-11-10 06:30:35 +03:00
Nekotekina d1ee7c651f Make memory locking optional (mlock, VirtualLock). 
Fix desired locking operation (to fix "sudo" memory).
It was discovered that some systems have outdated configuration.
With too tight limit, it's almost impossible to lock anything in memory.
 2020-11-10 06:05:37 +03:00
Nekotekina dcbe8ef5f4 Import VirtualAlloc2 if available (Win10+) 
Import MapViewOfFile3 as well.
Unused, this crap is tricky.
 2020-11-10 03:04:38 +03:00
Nekotekina bd5253047b Improve DYNAMIC_IMPORT 
Don't call get_proc_address every time if if failed.
Also rename Utilities/dynamic_library.h to util/dyn_lib.hpp
 2020-11-10 01:44:31 +03:00
Nekotekina cdaa8cb5c4 CPU: Improve suspend_all g_suspend_counter handling 
Increase in two stages, giving more chances to use it.
Second stage is when all wait flags have been seen.
 2020-11-09 23:54:36 +03:00
Nekotekina 083397a555 vm: lock memory under "sudo" addr 
Remove memory touching from transactions.
 2020-11-09 23:54:36 +03:00
Nekotekina e98eb4659e Implement utils::memory_lock 2020-11-09 22:57:36 +03:00
Nekotekina d1988d384c vm: remove unnecessary memset() on stop 2020-11-09 22:57:36 +03:00
Nekotekina bc61835d97 CPU: use unsigned (u8) priority in suspend_all 2020-11-09 22:57:36 +03:00
RipleyTom 8a50880613 Fix path not being saved on install pkgs 2020-11-09 14:23:54 +03:00
Nekotekina b05d12df0e Hotfix for shm->map_self() 
Make sure mmap returns 64K-aligned results, as on Windows.
 2020-11-08 22:15:59 +03:00