steam-frame/FEX-Emu--FEX
1
0 Fork 0
mirror of https://github.com/FEX-Emu/FEX.git synced 2026-10-09 06:00:15 +02:00
Code Issues Packages Projects Releases 67 Wiki Activity
15,192 Commits 11 Branches 71 Tags
08f451d3bce62a68aa6307dced5a8eaeb85c39bc
Commit Graph
591 Commits
Author SHA1 Message Date
Ryan Houdek 82040bae3e CPUInfo: Adds new AVX extensions 2026-09-19 13:51:30 -07:00
Ryan Houdek 91bbce5a96 FEXCore/OpcodeDispatcher: Fixes syscall instruction on Linux 
I forgot on Linux by default we didn't have the syscall instructions
count as block end. Change this so that it counts as block end now.

This has the additional benefit that now the frontend needs to modify
the RIP manually as well which is fine as it's what arm64ec and wow64
does.

Also add back the UnimplementedOp in RDPID that accidentally got caught
up. Also increment DiskCache version as both changes will change
codegen.

Fixes #5942
 2026-09-10 09:50:07 -07:00
Pierre-Loup A. Griffais b5ac608fc5 DiskCache: allow relocations within the same ELF image 
We would check the FileID of mapped sections, but BSS is an anonymous mapping.
Grab the ELF image extents when we parse the file, and add an additional check
to the relocation filter to bail out additional relocs if we know that size.
 2026-09-09 22:39:50 -07:00
Ryan Houdek 516ce6b15c Threads: Support setting thread names through creation 
Gives the DiskCache a thread name so it's easier to find.
 2026-09-08 19:11:52 -07:00
Ryan Houdek 66cad978c3 FEXCore: Removes syscall optimization 
The JIT was doing a bunch of additional work where it was saving and
restoring registers and then juggling the arguments back in to a stack
frame. All of this is nonsensical without the optimization where we
could call syscalls inline without a stack frame.

Instead remove this optimization entirely and behave like a "generic"
syscall path always. The Linux syscall handler now pulls the arguments
out of the CPU context directly and stores the result back in to RAX
directly as well.

This has knock-on effects where technically syscalls are
going to be slightly faster because no stack frame setup for the
arguments, but additionally we are going to be able to have syscalls be
proper serialization points where we can interrupt the syscall and
long-jump out without problems.

Bumps the DiskCache version again because it causes codegen to change.
 2026-08-31 19:23:18 -07:00
Pierre-Loup A. Griffais c0b24b2f2e DiskCache: on Linux, block signals in Writer thread 
Clean up thread flags while we're at it.
 2026-08-30 22:27:05 -07:00
Ryan Houdek b83dd97762 FEXCore/Context: Removes InitialRIP/RSP from CreateThread 
We actually never use this anymore, we instead always pass zero for
both, and then rely on the thread inheritance model or setting the
values manually. Now that we expose visibility of the
InternalThreadState to the frontend they just access it directly.

Just a smidge of cleanup, NFC.
 2026-08-24 18:32:35 -07:00
Pierre-Loup A. Griffais c3fb6ccaaa DiskCache: make Writer thread low-priority 2026-08-23 14:01:32 -07:00
Ryan Houdek a312347589 Thunks: Adds some new PV paths 
Slight PV behaviour changes meant we missed this.
 2026-08-12 16:54:01 -07:00
Iaying 7629323548 Fix an XMM register bug in SpillSRA, along with adding a test that reproduces the bug 2026-08-03 15:15:41 -07:00
LC e8b5cd18bd SignalDelegator: Remove unused Required parameter in handler setting 
The required flag is set by the subsequent frontend functions that
follow the calls to these functions.
 2026-07-27 15:06:24 -04:00
FrontMage 35518a5fa0 FEXCore: Ignore inactive JIT guard ranges 2026-07-24 07:57:48 +08:00
Ryan Houdek 99b8df4e6f Merge pull request #5773 from lioncash/fdres 
ThreadManager: Fix error return values in FrontendAllocateSlots()
 2026-07-19 16:14:50 -07:00
LC 331655182d ThreadManager: Fix error return values in FrontendAllocateSlots() 
If ftruncate or the mmap ever fail for whatever reason, then we need to
return the current size, rather than the new size.
 2026-07-21 15:12:41 -04:00
Ryan Houdek ec95330dcd Merge pull request #5765 from lioncash/signal 
SignalDelegator: Group members together
 2026-07-19 16:13:26 -07:00
LC 3959863462 SignalDelegator: Group members together 
Hides all public members and situates all of them together to make for
an easier overview.
 2026-07-19 21:10:35 -04:00
LC 6e37dca566 LinuxAllocator: Reduce MemAllocator32Bit size by 16 bytes 
These constants don't need to be member vars.
 2026-07-19 18:37:38 -04:00
LC a3d0b67777 LinuxEmulation: Resolve missing prototype warnings 
Ensures all functions are marked whether they're intended to be
internally linked or not.
 2026-07-17 00:12:28 -04:00
LC 2943b87c83 VDSO_Emulation: Mark relevant members as internally linked 
Silences missing prototype warnings and makes it obvious they're only
used within the translation unit.
 2026-07-16 07:28:50 -04:00
Ryan Houdek 50c75d1f43 Move Linux version calculation to common code 2026-07-14 20:06:37 -07:00
LC 23402bf31b x32/Semaphore: Fix storing of message type in msgrcv 
This was previously storing into the local compat handler, not the
actual managed message.
 2026-07-13 17:30:27 -04:00
LC 50be718b72 x32/Semaphore: Mark _ipc as static 
This isn't used outside of the translation unit.
 2026-07-13 17:30:24 -04:00
Ryan Houdek f2b679f602 Merge pull request #5728 from lioncash/halves 
x32/FD: Combine offset halves directly
 2026-07-12 11:15:10 -07:00
Ryan Houdek b9d97dffe7 Merge pull request #5727 from lioncash/vmsplice 
x32/FD: Make use of SanitizeIOCount for vector construction in vmsplice
 2026-07-12 11:14:31 -07:00
LC a6c8f0d300 x32/FD: Combine offset halves directly 
Shortens these up a little.
 2026-07-12 13:31:48 -04:00
LC 046750354e x32/FD: Make use of SanitizeIOCount for vector construction in vmsplice 
Makes this consistent with the other fd syscalls that make temporary
buffers.
 2026-07-12 13:01:58 -04:00
LC ca2d2520d2 Signals: Preprocessor disable intentional dead code in userfaultfd 
Noticed this when going through the syscalls. Avoids potential warnings.
 2026-07-12 12:16:07 -04:00
LC 7d149ebec4 GdbServer: Add missing log format argument 2026-07-12 00:28:29 -04:00
Ryan Houdek 341a5196ba Merge pull request #5701 from lioncash/thread 
Thread: Amend new thread handling in HandleNewClone()
 2026-07-11 17:09:59 -07:00
Ryan Houdek 48ce5bf6e6 Merge pull request #5714 from lioncash/readahead 
x32/FD: Fix readahead upper offset type
 2026-07-11 11:20:49 -07:00
Ryan Houdek 617a518714 Merge pull request #5713 from lioncash/select 
x32/FD: Correct total word calculation in select() variants
 2026-07-11 11:19:29 -07:00
Ryan Houdek 480f45f2f3 Merge pull request #5712 from lioncash/bpf 
BPFEmitter: Amend instruction class checking in HandleStore()
 2026-07-11 11:08:58 -07:00
Ryan Houdek 0e8b01c1b5 Merge pull request #5711 from lioncash/fault 
x64/Thread: Amend faulting copy handling related to LDTs
 2026-07-11 11:04:47 -07:00
LC a90a7dbec7 x32/FD: Fix readahead upper offset type 
This should be a uint32_t
 2026-07-11 13:33:11 -04:00
LC 2250bd58a2 x32/FD: Deduplicate guest and host fd set management 
Same behavior, but less copy pastey
 2026-07-11 13:23:19 -04:00
LC 126be45ed1 x32/FD: Correct total word calculation in select() variants 
Previously this would result in a larger amount of words specified than
necessary.

e.g. Given nfds = 1:

With AlignUp(1, 32) / 4, we'd end up with supposedly eight words, when it
should only be one word.

On the other extreme, given a full fd set of 1024 fds, then we'd end up
with 256 words, when it should only be 32.
 2026-07-11 12:53:08 -04:00
LC e021a55abd BPFEmitter: Amend instruction class checking in HandleStore() 
This was previously checking for a load class, which would result in ST
clobbering the index register.
 2026-07-11 12:26:11 -04:00
LC 2ad6254894 x64/Thread: Amend faulting copy handling related to LDTs 
CopyToUser doesn't return the number of bytes copied, but rather returns
0 to indicate success, otherwise a fault has occurred (and the SIGSEGV
handler has set X0 to EFAULT)
 2026-07-11 11:57:38 -04:00
LC f16bc12b7d SignalDelegator: Remove odd double negation in GuestSigProcMask 
We can just reduce it to normal null comparisons.
 2026-07-11 05:42:48 -04:00
Ryan Houdek d2f096187c Merge pull request #5705 from lioncash/thread3 2026-07-10 22:34:04 -07:00
LC 8b0f07b2dc Syscalls: Remove unnecessary usages of namespace FEXCore::IR 
These aren't necessary.
 2026-07-10 21:02:12 -04:00
LC 017c898ed0 x64/Signals: Amend set size in rt_sigtimedwait 
We should be checking the size passed in, not the sizeof of it.
 2026-07-10 19:40:05 -04:00
LC 85b8e91b57 Thread: Amend new thread handling in HandleNewClone() 
Ensures that newly cloned threads get tracked properly.
 2026-07-10 18:35:58 -04:00
Ryan Houdek 0bdf15977f Merge pull request #5697 from lioncash/thread 
x32/Thread: Move writability check around in waitpid
 2026-07-10 10:34:56 -07:00
Ryan Houdek 8a844f9cca Merge pull request #5695 from lioncash/socket 
Socket: Pass size by reference in getsockopt
 2026-07-10 10:34:33 -07:00
Ryan Houdek 8fbde84380 Merge pull request #5696 from lioncash/time 
x32/Time: Correct sizeof expression in utimensat
 2026-07-10 10:31:47 -07:00
Ryan Houdek 00826d3327 Merge pull request #5694 from lioncash/rlimit 
x32/Info: Only modify output in getrlimit/ugetrlimit if successful
 2026-07-10 10:27:51 -07:00
Ryan Houdek 5dd0477440 Merge pull request #5689 from lioncash/msg 
x32/Msg: Fix result comparison in mq_getsetattr
 2026-07-10 10:15:15 -07:00
Ryan Houdek c6f823f855 Merge pull request #5688 from lioncash/pidfd 
Thread: Amend pidfd_open check
 2026-07-10 10:14:49 -07:00
Ryan Houdek 2af7c24e79 Merge pull request #5687 from lioncash/limit 
x32/Thread: Fix off-by-one in get_thread_area
 2026-07-10 10:14:29 -07:00