sceKernelGetProcessTime and sceKernelGetProcessTimeCounter subtracted
GetStartNanos() from GetMonotonicNanos() in one expression. GCC reads the
clock first, so on the first call in a process the start was captured
after it and the result wrapped to about 2^64.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
#1372 adds its test after the vop1 decode tests and #1314 its debt entry after s_setkill, the places where this branch added its own. The wave control decode test now precedes the vop1 decode tests and the s_sethalt entry follows sceRtcParseDateTime, so either pull request can merge first without a conflict.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
The test is added to ctest in its own BUILD_TESTING block, as agc_vop1_sdwa_move_decode is, instead of in the shared test list that #1187 also extends.
s_sethalt with SIMM16[0] clear is a no-op; s_sethalt 1, s_sendmsghalt, a reached s_code_end, s_rfe_b64, the ds_gws_* instructions and ds_ordered_count throw with the reason at translation. Linear decoding stops at s_code_end like at s_endpgm, so code padded with s_code_end after a final backward branch decodes. Encodings from LLVM SOPInstructions.td and DSInstructions.td, checked against the gfx10 MC tests; semantics from the RDNA 2 ISA guide.
DecodeState and the draw precheck rejected DB_SHADER_CONTROL bit 16,
PRIMITIVE_ORDERED_PIXEL_SHADER (POPS), which runs the ordered section
of overlapping pixels' shaders in primitive order. The bit now reaches
the recompiler as a pixel stage field, and such a pixel shader declares
PixelInterlockOrderedEXT and runs its whole body between
OpBeginInvocationInterlockEXT and OpEndInvocationInterlockEXT; an
invocation that a BDA read fault kills ends the interlock first. The
POPS collision SGPRs read 0, so a title skips its POPS wait and runs
its per-collision loop once. An image_load still reads a sampled
binding, which misses an earlier overlapping primitive's image_store in
the same draw. The device enables VK_EXT_fragment_shader_interlock when
it has fragmentShaderPixelInterlock; without it the recompile throws,
as does a nonzero POPS_OVERLAP_NUM_SAMPLES. The field is part of the
recompile cache key, the draw key and the serialized request (version 10).
FindPending returned the first pending storage image at a texture's
address that is at least as long as the surface. When transient
surfaces alias (a 2-mip 1424x800 chain and, after it, a 1-mip
1424x800 surface at the same address, each with its own DCC keys),
a sampled lookup of the newer single-mip surface could be served by
the older chain: the chain's view was refreshed under its own keys,
which the title had re-filled with a fast-clear code, so whole blocks
read as the clear value instead of what the GPU had just written.
An image whose length equals the surface's now wins; a longer chain
still serves a descriptor of its first mips when no exact image is
pending.
Engines alias transient render targets, so a texture can sit at the
address of a depth surface after the memory has been handed to a color
image: a 384x384 R11G11B10 texture over a 384x384 D32S8 surface, say.
Sampling it threw "sampling the depth plane ... is not implemented"
and the draw was skipped.
A view with another extent, or a depth-plane view in a format that
cannot hold the plane (neither the plane's own R32F / R16 unorm nor a
T# that reads the raw depth bits), is now treated as memory reuse: the
lookup falls through to the ordinary texture path instead of the depth
surface. Stencil-plane views keep their current handling.
Use the shared atomic bounds check instead of wrapping at 64 KiB.
Expect zero returns and unchanged LDS for aligned out-of-range accesses,
and record the gfx1035 hardware measurements.
No request reaches the network, so sceHttpsSetSslVersion has no TLS
connection to configure, sceHttpSetRedirectCallback and
sceHttpSetCookieRecvCallback register callbacks that are never called,
and sceHttpsGetSslError reports error 0 with detail 0. A null errNum or
detail returns SCE_HTTP_ERROR_INVALID_VALUE like sceHttpGetLastErrno.
Signatures follow shadPS4.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
scePthreadMutexDestroy threw when the mutex was locked. FreeBSD libthr,
which the console's libkernel follows, returns EBUSY and leaves the
mutex usable; PPSA28997 destroys a locked mutex during its intro and
was aborted.
A condition wait on a recursive mutex locked more than once unlocked the
native mutex only once, so the thread that should signal blocked forever
on it. Unlock the remaining levels before the wait and lock them again
after it, as FreeBSD libthr does in _mutex_cv_unlock and _mutex_cv_lock.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01HeC9bA3n74TzJRYv9AgBE8
A thread that sceKernelRaiseException redirects resumes through
RtlRestoreContext with a CONTEXT that has no XSTATE, so the upper halves
of ymm0-ymm15 came back as the handler and the delivery path left them.
A handler or host routine that runs vzeroupper or any VEX instruction
(Zen 2 guest code, the CRT's memcpy) cleared the upper lanes of a thread
interrupted in the middle of AVX code. The entry stub now stores
ymm0-ymm15 next to the delivery when the CPU and the OS enable AVX, and
the exit loads them back right before RtlRestoreContext, which restores
only the low halves.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01HeC9bA3n74TzJRYv9AgBE8
sceKernelGetCurrentCpu returned the raw host CPU index. Guest affinities
are bookkeeping only and sceKernelGetAvailableCpumask advertises CPUs 0
to 12, so on a host with more than 13 logical CPUs a title could get 13
or higher, and a thread pinned to one CPU could get another one.
The host index now selects a CPU of the calling thread's affinity
clipped to the available mask, so the result is always an advertised
CPU and a thread pinned to one CPU reports that CPU.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01HeC9bA3n74TzJRYv9AgBE8
A thread had one TimedWait waiter for every wait. When
sceKernelRaiseException reached a thread blocked in a TimedWait
condition, its handler ran as an APC inside that wait, and a wait in
the handler queued the same waiter on a second condition while it was
still linked into the first. The links of the first queue were
overwritten, so waiters behind it were never woken, and a wake of the
outer wait set the shared event and was consumed by the inner wait.
A wait now takes the thread's first waiter that is not in use, and
creates a deeper one for a wait nested inside another.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01HeC9bA3n74TzJRYv9AgBE8
On Windows each AIO request seeked a _dup of the descriptor and then read
or wrote through it. A duplicated descriptor shares the file position, and
the seek and the transfer are separate calls, so two threads submitting
requests on one descriptor could transfer at each other's offset. Each
request is now a single ReadFile/WriteFile with an OVERLAPPED offset on
the OS handle, as pread and pwrite already do in Stdio.cpp.
GuestAio reads four distinct blocks of one descriptor from four threads
and checks every result.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01HeC9bA3n74TzJRYv9AgBE8
An idle queue worker with completions pending waited on its condition
variable for 1 ms before each reap. With MinGW that wait goes through
winpthreads, which ends a timed wait on a 15.6 ms GetTickCount64 step,
so deferred end-of-pipe interrupts reached the guest about 15 ms after
the GPU had finished. On Windows the worker now sleeps with PollSleep
between reaps, and so does the wait for a wait-free submission's order
release.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
On Windows the vblank thread's condition_variable::wait_until went
through winpthreads, which ends a timed wait on a 15.6 ms
GetTickCount64 step even with the scheduler tick raised to 0.5 ms.
Vblank intervals ranged from 2 ms to 34 ms instead of 16.68 ms. The
thread now sleeps to each deadline with PreciseSleepUs and checks for
a stop or a presentation failure after each sleep.
Co-Authored-By: Claude Opus 5.5 <[email protected]>
Opening a volume needs administrator rights, so the volume flush skipped
every volume in a normal user session. The libc, libkernel, save data and
app content file functions now record each host file and directory they
change. On Windows sceKernelSync flushes the recorded paths that changed
since the previous call, plus their changed parent directories, through
handles a normal user can open. Linux still calls sync().
wcstod, wcstof, wcstold, wcstol, wcstoll, wcstoul, wcstoull, wcscoll and wcsxfrm still forwarded to the host's wchar_t functions, which use 32-bit units on Linux. The wcsto* functions now parse the ASCII prefix of the guest string with the narrow parsers, as the C locale accepts only ASCII white space and digits. wcscoll compares like wcscmp and wcsxfrm copies, as strcoll and strxfrm do in the C locale.
Adrià