Mirrors canary's `XObject::StashHandle` (xobject.h:253-256): on first
adoption of a guest dispatcher header, stamp +0x08 with the
kXObjSignature fourcc 'X','E','N','\0' and +0x0C with the stash handle
(here the guest pointer itself, since our shadow table is keyed by ptr).
Audit-023/024A documented divergence at addresses such as 0x828F4838
where canary stores "XEN\0" + handle but we left zeros. Lands as
canary-correctness restoration; cascade impact at -n 500M is nil per
the discipline gate (no sharp prediction tied to the writeback).
Lockstep determinism preserved: instructions=100000003,
imports=987516, swaps=2, draws=0 across 2 reruns.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds an opt-in diagnostic that emits one tracing line per guest store
overlapping any armed byte address, naming the writer (tid, pc, lr)
plus old/new u32 lanes. Mirrors the --pc-probe / --branch-probe shape;
pc/lr are stamped from worker_prologue via a thread-local Cell, so
default runs (empty watch set) take a single is_empty() check on each
write. Lockstep digest preserved (instructions=100000003 across reruns,
sylpheed_n50m.json golden byte-identical).
Diagnostic infra only; no functional change. Used to identify producers
of dispatch-state writes for the audit-017 / audit-019 hunt.
Replace the no-op cookie-returner with a real impl per canary
xenia-canary/src/xenia/kernel/xboxkrnl/xboxkrnl_threading.cc:216-227
(XObject::GetNativeObject<XThread>()->Resume()). Mirrors
nt_resume_thread plumbing two functions below:
resolve_pseudo_handle -> scheduler.find_by_handle -> resume_ref.
Returns STATUS_SUCCESS if the KTHREAD-pointer-as-handle resolves,
STATUS_INVALID_HANDLE otherwise — matches canary's Resume()/!thread
return semantics.
Cascade-prediction scorecard (audit-018 -> post-fix):
- A PASS: tids 9 (entry=0x824D2878) and 10 (entry=0x824D2940)
leave Suspended -> run prologue -> park on audio buffer-completion
semaphores 0x828A3254 / 0x828A3230.
- B PARTIAL FAIL: NtSetEvent 667->3334; KeReleaseSemaphore=0;
XAudioSubmitRenderDriverFrame=0.
- C FAIL (predicted 2->1, actual 2->2): both ExTerminateThread +
KeReleaseSemaphore still canary-only.
- D FAIL: gamma-cluster blocker unchanged — pc-probe at
0x82184318/0x82184374 no fires; dump-addr 0x828F4070 no DUMP;
signal_attempts on 0x1004/0x100c/0x1020/0x15e4 still 0.
Necessary-but-not-sufficient: workers unsuspend but park on a
downstream gate that's part of the audit-009/-016/-017 gamma cluster.
Tests 600 -> 601 (+ke_resume_thread_unblocks_suspended_worker).
Lockstep instructions=100000003 imports=987516 deterministic x2.
Goldens re-baselined: sylpheed_n50m.json instructions
50000003->50000011, imports 407255->407247.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Mirrors canary xam_user.cc:90-101. User 0 returns 1 (SignedInLocally),
all other indices return 0. Replaces stub_return_zero registration that
was reaching guest-side branches looking up signin state.
Tests: 599 -> 600.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
audit-findings.md: full IO-004 entry with cascade-prediction scorecard.
audit-runs/audit-006/canary_export_queue.md: post-IO-004 status note
(7 -> 3 canary-only; 4 reclassified RE-FIRES).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Captures two consecutive read-only diagnostic sessions:
AUDIT-008 (2026-05-05): IO-003 model reset. The 0x100c / 0x1004 / 0x15e0
workers ARE spawned post-IO-003; the IO-003 prediction-scorecard's
"UNCREATED" markers were misclassifications (handle audit already showed
the workers parked on lifecycle events, just unlinked from dispatcher
addresses). Hypothesized the gate among the 5 non-create-chain callers
of sub_821800D8 whose parents live in 0x82287000-0x82292FFF.
AUDIT-009 (2026-05-05): falsifies AUDIT-008's β-hypothesis. A 21-PC
--branch-probe (6 parents + 5 shims + dispatcher + 9 audit-005
producer-callsites) shows 0/21 firings at -n 500M — the entire
0x82287000-0x82294000 cluster is unreached. Static analysis confirms
the cluster's level-1 roots have zero non-call xrefs in sylpheed.db.
The gate is structurally above the cluster (vtable / function-pointer
that's never written). Stop condition 1 triggered; discipline gate
fails on box 1 + box 3; no fix this session.
Also updates audit-runs/audit-006/canary_export_queue.md to reflect
the AUDIT-009 evidence: 3 canary-only exports remain REAL_BUT_UNREACHED
(ExTerminateThread, KeReleaseSemaphore, XamUserReadProfileSettings) —
none is the immediate gate.
No code changes; --branch-probe machinery from AUDIT-007 sufficed.
Trace artifacts left untracked under audit-runs/audit-008/ +
audit-runs/audit-009/ (consistent with prior audit-runs/* convention).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replace the stub_success registration of NtDeviceIoControlFile at
exports.rs:90 with a real handler for FsCtlCodes 0x70000 (drive
geometry) and 0x74004 (partition info), mirroring xenia-canary
xboxkrnl_io.cc:645-678 + null_device.{h,cc}. The 16-byte 0x74004
response with cache_size=0xFF000 at OUT+8 is the gate that lets
sub_824ABD88 return SUCCESS and sub_824A9710 reach the priv-11
XexCheckExecutablePrivilege site identified by KRNBUG-AUDIT-007.
Stack args 9-10 (OutputBuffer, OutputBufferLength) read from the
caller's parameter save area at [sp+0x54] / [sp+0x5C] per the Xbox
360 PowerPC EABI (linkage area sp+0..sp+8, 8-quadword spill area
sp+0x14..sp+0x54, then stack args every 8 bytes). First HLE export
in the codebase to need 9+ args.
Cascade vs. KRNBUG-AUDIT-007 prediction (5/8 held):
- XexCheckExecutablePrivilege count 1 → 2 (priv=0xA + priv=0xB) ✓
- XamTaskSchedule count 0 → 1 ✓
- canary-only exports 7 → 3 (audit predicted ≤3) ✓
- 0x15e0 semaphore signal_attempts 0 → 1 (bonus)
- 0x100c worker spawn DID NOT fire (still UNCREATED) ✗
- 0x1004 signal_attempts unchanged ✗
- Worker spawn count unchanged at 19 ✗
Tests: 592 → 594. Lockstep deterministic at -n 100M (run1 ≡ run2 ≡
run3, byte-identical). instructions=100000010 → 100000019, imports
407417 → 987524 (+2.4×). swaps=2 draws=0 plateau persists.
sylpheed_n50m golden re-baselined instructions=50000004→50000003,
imports=407362→407255. sylpheed_n2m unchanged.
Still canary-only after this fix: ExTerminateThread,
KeReleaseSemaphore, XamUserReadProfileSettings. The next downstream
gate is somewhere past XamTaskSchedule's completion path.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Sister to --pc-probe / --ctor-probe but emits a single compact one-line
BRANCH-PROBE record per fire (pc, tid, hw, cycle, r3, lr, cr0/cr6 flags)
with no back-chain. Designed for tracing every conditional-branch fire
inside a candidate-gate function so the last PC reached before the
function epilogue identifies the exit branch.
Runtime trace at audit-runs/audit-007/sub_824A9710-trace.log decisively
identifies the priv-11 gate:
- Exit branch: 0x824a9944 (post bl sub_824ABD88 first call)
- Responsible kernel call: NtDeviceIoControlFile, FsCtlCode=0x74004
(registered as stub_success at exports.rs:90)
- Mechanical chain: stub returns 0/SUCCESS without writing OUT, game
reads [out_buf+8], finds zero, assigns hardcoded 0xC0000034
(STATUS_OBJECT_NAME_NOT_FOUND) at sub_824ABD88:0x824abea8-ac, exits
via 0x824a9944's lt branch before priv-11 site at 0x824a99a0.
592→592 tests; lockstep instructions=100000010, swaps=2, draws=0
deterministic across reruns. Read-only diagnostic — no fix this session.
Next session: KRNBUG-IO-003 (real NtDeviceIoControlFile per canary
NullDevice::IoControl for FsCtlCodes 0x70000 + 0x74004).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Volume-info class-3 alloc unit 2048 → 0x10000 (canary NullDevice
byte-identical). Tests 591 → 592, lockstep deterministic.
Audit-006-predicted 7→0 cascade FALSIFIED (7→7, no movement).
Vol-info is not the priv-11 gate. See KRNBUG-IO-002 entry in
audit-findings.md for the full diagnostic and next-session leads.
`nt_query_volume_information_file` class-3 (`FileFsSizeInformation`)
was returning sectors_per_unit=1, bytes_per_sector=2048 (alloc unit
2048). Replaced with canary's NullDevice byte-identical values
sectors=0x80, bps=0x200 (alloc unit 0x10000), with total /
available allocation units lowered to 0x10 / 0x10 to match.
Reference: xenia-canary/src/xenia/vfs/devices/null_device.h:38-46
(`NullDevice::sectors_per_allocation_unit()` and
`bytes_per_sector()`); consumed by canary's
`NtQueryVolumeInformationFile_entry` at
xenia-canary/src/xenia/kernel/xboxkrnl/xboxkrnl_io_info.cc:355-365.
Tests 591 → 592 (added
`nt_query_volume_information_file_class3_returns_64k_alloc_unit`).
Lockstep `instructions=100000010, swaps=2, draws=0` deterministic
across two `--stable-digest -n 100M` reruns. sylpheed_n50m oracle
still matches its existing golden — observably a no-op at -n 50M.
The audit-006-predicted 7→0 cascade did NOT fire (canary-only
exports still 7, identical set; XexCheckExecutablePrivilege still
priv=0xA only; XamTaskSchedule still 0). All 16
NtQueryVolumeInformationFile calls in our 500M trace originate
from a single LR 0x82611f38 and complete successfully — vol-info
is therefore not the priv-11 gate. The fix value is correct
(canary-byte-identical) but is not load-bearing for the gate;
landing it anyway because it's the right value and unblocks no
regression. Stop condition triggered per the IO-002 task brief —
no second fix this session.
Next-session: --pc-probe on sub_824A9710 entry to find the actual
upstream gate. See `audit-findings.md` (KRNBUG-IO-002 entry) and
`audit-runs/post-IO-002/` for the full diagnostic trail.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
AUDIT-005's static attribution to sub_824ABA98 was wrong. The 0xC0000011
(STATUS_END_OF_FILE) at lr=0x824a97e4 traces to the NtReadFile call at
0x824a9810 inside sub_824A9710 — the cache-loader reads 1024 B from
offset 2048 of `\Device\Harddisk0\partition0`. Our synth-empty fallback
returned EOF (start_pos 2048 > size 0), so the function bailed via
RtlNtStatusToDosError before sub_824ABA98 was ever called.
Canary mounts partition0 to a NullDevice; `NullFile::ReadSync`
([null_file.cc:24-31](xenia-canary/src/xenia/vfs/devices/null_file.cc))
returns X_STATUS_SUCCESS with bytes_read=0 and never touches the
buffer. Sylpheed's caller pre-zeroes the 1024-byte stack buffer
(`memset(sp+208, 0, 1024)` at sub_824A9710 prologue), validates a
"Josh" magic on the first read, and falls back to the cache-recreate
path when the magic doesn't match.
The fix mirrors NullFile semantics: when the open synthesized a
zero-length file (`data.is_empty() && size == 0`), NtReadFile returns
SUCCESS with information=0 and the buffer untouched.
Effects (chain-of-effects verification at -n 500M):
- tests: 590 → 591 (added regression covering NullDevice semantics)
- lockstep: deterministic across 3 reruns (same instructions=100000010,
swaps=2)
- sylpheed_n50m golden re-baselined: instructions 50000004→50000000,
imports 407416→407362
- canary kernel-call diff: 10 → 7 missing exports
(XeCryptSha + XeKeysConsolePrivateKeySign + NtDeviceIoControlFile
now run; the cache-recreate path executes through to NtWriteFile)
- boot reaches silph::Silph::Impl::OnInit: 19 worker threads spawn
(was 6 before the fix)
- parked-handle 0x1004 still signal_attempts=0; the original 0x100c
and 0x15e0 are now <UNCREATED> because cascade walked past them and
the handle assignments shifted; new parked sites: 0x12fc/0x1600/
0x1040/0x10b8/0x15e8/0x1014/0x101c/0x10bc/0x1044
- draws=0 plateau persists; renderer is multi-causal blocked
Next blocker: per the canary-only diff, XamTaskSchedule + the cluster
of XAM exports (XamTaskCloseHandle, XamUserReadProfileSettings,
ObCreateSymbolicLink) and the post-thread-exit chain (ExTerminateThread,
KeReleaseSemaphore, KeResetEvent) are the next-up frontier.
Mirrors canary's cvars::avpack default (xam_info.cc:35) and Sylpheed's
accepted set {3,4,6,8} (xam_info.cc:250-251). With KRNBUG-XEX-001 having
flipped the priv-10 gate, XGetAVPack now reaches its caller in
sub_824AB578; returning 0x16 caused Sylpheed to abort the AV/crypto
block before XeCryptSha. Cascade walks one step (canary-only export
list 11 → 10); sub_824ABA98 is the next candidate.
Tests: 589 → 590. Goldens re-baselined (n50m: 50000005→50000004,
imports 407417→407416). Lockstep deterministic across 3 reruns at
-n 100M (instructions=100000010, import_calls=987686 +2.4×, swaps=2).
9-PC producer probe still 0×; parked handles 0x1004/0x100c/0x15e0
still signal_attempts=0.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Extends `--ctor-probe` machinery into `--pc-probe` (clap alias) with
the optional `PC@DISPATCHER:OFFSET` token form: on a hit, the helper
additionally logs `[disp+off]` — what the producer's
`lwz r3, OFFSET(r3)` is about to read. Reuses `parse_hex_u32`; both
flags share parser + storage.
Read-only diagnostic. Lockstep digest preserved (`run digest matches
golden` at -n 50M `--stable-digest`). 588 tests green.
Decisive findings (full deliverable in `audit-findings.md` /
`audit-runs/audit-005/`):
- Failure mode α confirmed for KRNBUG-AUDIT-004: all 9 producer call
sites for handles 0x100c (5 sites) and 0x15e0 (4 sites) fire 0x at
-n 500M. The producer code path is not reached.
- Set-diff of kernel-call sequences (canary.log oracle vs ours.log
at -n 500M) identifies 11 exports canary calls and we don't:
XGetAVPack, XeCryptSha, XeKeysConsolePrivateKeySign,
ObCreateSymbolicLink, NtDeviceIoControlFile (×2),
XamUserReadProfileSettings (×2), XamTaskSchedule, XamTaskCloseHandle,
KeReleaseSemaphore (×268), KeResetEvent, ExTerminateThread (×2).
- XGetAVPack has exactly one caller (sub_824AB578 at 0x824AB5A0).
The 4 instructions immediately preceding it are:
addi r3, r0, 10 ; privilege bit 10
bl XexCheckExecutablePrivilege
cmpli 0, r3, 0
bc 12, eq, 0x824AB724 ; if r3==0, skip whole block
- exports.rs:193 registers XexCheckExecutablePrivilege as
stub_return_zero. Always returning 0 -> guest takes the branch
and skips the entire AV/crypto/save-data init block.
- The other call site (sub_824A9710 at 0x824A99A0) queries privilege
11 with opposite polarity (bne) -> gates XamTaskSchedule on the
privilege-NOT-set arm. With both stubs returning 0, the guest
walks the wrong arm of every privilege-gated branch.
- This explains why the dispatcher fields read zero
([0x828F3D08+0x50]=0, [0x828F4070+0x24]=0 from AUDIT-004 dumps):
the ctors run, but the producers that would populate those fields
with a non-zero handle never execute.
Next session: replace XexCheckExecutablePrivilege stub with real
priv-bit lookup from XEX header. See audit-findings.md
KRNBUG-AUDIT-005 for the validation matrix.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Diagnostic-only, read-only. Lockstep `instructions=100000002`
preserved bit-exact at -n 100M --stable-digest. 586 → 588 tests.
Adds two read-only diagnostics for the parked-waiter producer hunt:
* `--ctor-probe=0x8217C850,0x...` — at every interpreter step,
if `ctx.pc` is in the configured set, print one `CTOR-PROBE`
line capturing live r3 (= `this` in MSVC PPC ctors), lr
(= return site), sp, plus an 8-frame back-chain with
saved-r31/r30 per frame. Fires once per hit, exactly what the
8-instance-pool probe needed.
* `--dump-addr=0x828F3D08,0x828F4070,0x828F3EC0,...` — at end of
run (after the FOCUS report in `dump_thread_diagnostic`), each
address gets a 128-byte hex + be32 + ASCII dump. Used to
inspect the static dispatcher / job-queue struct layouts
AUDIT-003 identified.
Both gated default-off; empty set is a single `is_empty()` test on
the hot path. No guest state is mutated, so the
`sylpheed_n*m.json` lockstep digest is preserved.
KRNBUG-AUDIT-004 findings (corrects KRNBUG-AUDIT-002/003):
1. **The "8-instance pool" hypothesis for handle 0x1004 is FALSE.**
Probing the inner per-instance ctors `[0x821783D8, 0x82181750,
0x821701C8]` at -n 50M shows each fires EXACTLY ONCE with
r3 = `[0x828F3EC0, 0x828F3D08, 0x828F4070]` respectively. All
three handles are Meyers-style singletons with one dispatcher
each. The "called 8 times" claim came from miscounting raw
entries to the OUTER getter sub_8217C850 — but that getter is
itself a Meyers-singleton-getter; only the FIRST entry cascades
through to bl 0x821783D8 (gated on `[0x828F48D8] bit 0`).
2. **The producer indirection layer is the singleton-getter
itself.** Static byte-scan of .rdata / .data shows 0 hits for
the dispatcher addresses — no static registry table holds them.
But the xrefs table for the OUTER getters reveals 5–6 callers
each, MOSTLY non-create-chain, sharing the canonical producer
pattern: `bl outer_singleton_getter; lwz r3, OFFSET(r3); bl
0x824AA1D8` (with OFFSET=80 for 0x100c, =36 for 0x15e0). So the
AUDIT-003 xref audit was necessary but not sufficient — it
correctly saw "no direct producer references" but missed the
singleton-getter indirection layer.
3. **Dispatcher struct layouts** (128-byte dumps captured at -n
50M --halt-on-deadlock):
- 0x828F3D08 (handle 0x100c): event_handle at +0x4C (0x100c),
thread_handle at +0x48 (0x1010), self-pointer at +0x74,
capacity 7 at +0x28, queue empty (+0/+3C = -1).
- 0x828F4070 (handle 0x15e0): event_handle at +0x20 (0x15e0),
sibling-handle 0x15E4 at +0x1C, queue empty (+0x10 = -1).
- 0x828F3EC0 (handle 0x1004): event_handle at +0x78 (0x1004),
4 guest-heap sub-buffers at +0x20/+0x3C/+0x44/+0x50 in
0x4xxxxxxx range — noticeably different layout from the
other two pure POD job queues.
Files:
crates/xenia-kernel/src/state.rs ctor_probe_pcs / dump_addrs +
fire_ctor_probe_if_match + 2 tests
crates/xenia-app/src/main.rs Exec --ctor-probe / --dump-addr
CLI parsing, prologue hook,
end-of-run struct dumper
audit-findings.md KRNBUG-AUDIT-004 entry
audit-runs/audit-004/ 50M probe runs (v1 outer-getter
hits, v2 inner-ctor hits proving
the singleton hypothesis)
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
vtable/RTTI class probe at handle creation + wait. Read-only
diagnostic; lockstep determinism preserved.
Tests 581 → 586 green. --stable-digest -n 100M instructions=100000002.
Identifies handle 0x100c dispatcher at 0x828F3D08 and handle 0x15e0
dispatcher at 0x828F4070 — both POD job queues, not C++ classes
(`[this+0]=-1` sentinel, no vtable). Decisive xref audit shows every
reference to either base is in a ctor or the CRT — NO producer code
exists in static analysis. Producer hunt deliverable: confirms
unreachable-producer, not broken-producer.
Master HEAD prior: 6440261.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a read-only MSVC RTTI traversal helper (`read_class_at_this`)
and a `probe_create_stack_classes` integration that walks each
captured back-chain frame for handle creates in `--trace-handles-focus`
and probes each frame's most-likely `this` candidate (live r31/r30/r3
for frame 0; saved-r31/r30 from the prologue spill area at [fp-12]/
[fp-16] for deeper frames). False-positive guard rejects the CRT
static-init iterator pattern (vtable's first two slots must be image-
range function pointers — PPC instruction words like `mflr r12` are
not in 0x82xxxxxx).
`dump_thread_diagnostic` now takes `&GuestMemory` so the FOCUS report
prints, for each parked waiter, a WAIT-THREAD block with full back-
chain frames and per-slot saved-register dump for offline lookup.
End-to-end finding (-n 500M producer-trace):
* Handle 0x100c dispatcher = 0x828F3D08 (image rdata; verified by
sub_82181750 disasm + xref table). [this+0] = -1 sentinel — POD
job queue, NOT a C++ polymorphic class.
* Handle 0x15e0 dispatcher = 0x828F4070 (same shape).
* Handle 0x1004's 8-instance pool members still TBD (MSVC ctors
didn't preserve `this` in r31).
* 0x42450b5c is a separate audit class (heap-allocated, parks via
non-`do_wait_single` path).
Decisive xref audit: every reference to 0x828F3D08 / 0x828F4070 in
the static analysis is in a ctor or the CRT init driver. NO producer
code references either dispatcher base. Confirms `signal_attempts=0`
is unreachable-producer, not broken-producer.
Tests: 581 → 586 green (+5: RTTI-intact / RTTI-stripped / non-object
/ cstring / probe_create_stack integration). `--stable-digest -n
100M` instructions=100000002 unchanged. Master HEAD prior: 6440261.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Multi-frame back-chain capture at NtCreateEvent / NtCreateSemaphore /
NtCreateTimer / XamTaskSchedule, gated on --trace-handles-focus. Read-
only diagnostic; lockstep determinism unaffected.
Tests 576 → 581 green. --stable-digest -n 100M instructions=100000002.
Identifies: 0x1004 = 8-instance pool via static ctor at 0x8280F810;
0x100c = singleton inside main(); 0x15e0 = singleton in distinct
cluster. All three are silph-framework dispatchers; producer hunt
continues with vtable/RTTI readout next session.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds `walk_guest_back_chain` (PPC EABI back-chain walker) and a
`record_create_with_stack` audit hook gated on `--trace-handles-focus`.
NtCreateEvent / NtCreateSemaphore / NtCreateTimer / XamTaskSchedule now
route through the new helper so focused handles capture up to 6 stack
frames at allocation time. Diagnostic-only, read-only memory access:
unfocused handles pay one HashSet lookup, focused ones pay six
back-chain dereferences. Lockstep determinism preserved.
End-to-end finding: handles 0x1004 (8-instance pool via static ctor at
0x8280F810), 0x100c (singleton built inside main()), 0x15e0 (singleton
in distinct cluster) are silph-framework dispatcher objects whose
producer code is unreached at -n 500M. The producer hunt now has class
ownership; vtable/RTTI readout is the next step.
Tests: 576 → 581 green. `--stable-digest -n 100M` instructions=100000002
unchanged. Master HEAD prior: 9d45efe.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds canary-faithful XAudioRegisterRenderDriverClient + Unregister + Submit
implementations and a default-off audio buffer-complete callback ticker
(`--xaudio-tick` / `XENIA_XAUDIO_TICK=1`).
Producer hypothesis FALSIFIED for handles 0x1004/0x100c/0x15e4 — all three
still show signal_attempts=0 at -n 500M with the ticker enabled.
Tests: 562 → 576 green. Lockstep goldens preserved at default settings
(instructions=100000002, swaps=2 unchanged).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replace the three XAudio kernel-export stubs (Register/Unregister/SubmitFrame)
with canary-faithful implementations and add a periodic buffer-complete
callback ticker reusing the existing SavedCallbackCtx injection machinery.
Canary parity:
- xboxkrnl_audio.cc:56-93 — read callback_ptr[0..1], wrap callback_arg in a
4-byte big-endian guest heap buffer (`wrapped_callback_arg`), write
`0x4155_xxxx` to *driver_ptr.
- audio_system.cc:139-141 — guest callback receives r3 = wrapped pointer,
not raw callback_arg.
- audio_driver.h:21-24 — frame rate 256 samples / 48 kHz ≈ 5.33 ms.
Implementation:
- New `crates/xenia-kernel/src/xaudio.rs` — `XAudioClient`, `XAudioState`
(8-slot table, pending FIFO, dual-mode ticker), `XAUDIO_INSTR_PERIOD =
48_000` (lockstep) and `XAUDIO_PERIOD = 5.333 ms` (--parallel), same
pattern as KRNBUG-D08 v-sync.
- `try_inject_audio_callback` in xenia-app mirrors `try_inject_graphics_interrupt`,
shares `interrupts.saved` slot for mutex with graphics callbacks.
Gating: ticker + injector run only when `--xaudio-tick` /
`XENIA_XAUDIO_TICK=1`. Default off because Sylpheed's audio callback
enters an infinite `KeWaitForSingleObject` loop on first invocation
(canary's host worker thread provides the buffer-completion fence we
don't model), which hijacks a guest HW thread and regresses
`swaps=2 → 1`. Default-off preserves the lockstep `sylpheed_n*m.json`
goldens exactly.
Producer hunt outcome (FALSIFIED for parked handles 0x1004/0x100c/0x15e4):
at `-n 500M --xaudio-tick` all 3 handles still show
`signal_attempts=0 (primary=0, ghost=0)`. Audio callback is not the
missing producer. Next candidate per audit-findings.md is Timer DPC
delivery (KeSetTimer / KeInsertQueueDpc).
Tests: 562 → 576 green (10 in `xaudio.rs`, 4 in `exports.rs`).
Lockstep `--stable-digest -n 100M` default-off: instructions=100000002,
swaps=2 (matches pre-change baseline byte-for-byte).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Replaces the no-op stub at xam.rs:204 with a canary-faithful
implementation mirroring xenia-canary/src/xenia/kernel/xam/xam_task.cc:43-80.
Allocates a ThreadImage, allocates a KernelObject::Thread handle, and
routes through Scheduler::spawn with entry=callback and
start_context=message_ptr (canary's third positional XThread ctor arg).
Stack size = max(0x4000, page-aligned 0x10_0000).
Producer-hypothesis outcome (500M --trace-handles-focus run): the call
site at 0x824a9a10 is never reached during this boot horizon, so
XamTaskSchedule cannot be the missing producer for the 3 parked
Event/Manual handles (0x1004, 0x100c, 0x15e4). The fix still lands —
the stub was a real correctness bug that would manifest the moment
the boot advances past the current deadlock. Next candidate per
audit-findings.md: XAudioRegisterRenderDriverClient.
- Workspace tests: 561 → 562 green (new test
xam::tests::xam_task_schedule_spawns_real_thread).
- --stable-digest -n 100M: instructions=100000002 unchanged from
baseline; lockstep determinism preserved.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
3 IDs landed: GPUBUG-DRAIN-001, KRNBUG-AUDIT-001, KRNBUG-D08.
Tests 556 → 561. Lockstep digest BIT-IDENTICAL on stable fields.
draws=0 persists; parked-waiter producer-trace confirms hypothesis
(A) for 3 of 4 handles — guest code never calls Nt/KeSetEvent on
0x1004 / 0x100c / 0x15e4 — so the renderer plateau is a missing
kernel signal source, NOT a wake-eligibility bug or BST-paradox.
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The synthetic v-sync ticker used a per-instruction proxy
(VSYNC_INSTR_PERIOD = 150 k) tuned for ~10 MIPS lockstep
throughput → 60 Hz. Audit M11 observed this drifts under
`--parallel`: with 6 worker threads sharing the kernel mutex,
the dispatcher executes more PPC instructions per tick
callback, so the accumulator never crosses 150 k. Result:
~629 v-syncs/100M lockstep → ~2 v-syncs/100M --parallel.
Hybrid solution preserves lockstep determinism (which the
goldens depend on) while fixing --parallel:
* `tick_vsync_instr(instr_count)` — legacy instruction-count
ticker, used by lockstep. Bit-stable across runs.
* `tick_vsync_wallclock()` — new Instant-based ticker. Fires
`floor(elapsed / VSYNC_PERIOD)` v-syncs since the anchor
and advances the anchor by that many full periods (no
lazy backlog). Capped at INTERRUPT_QUEUE_CAP per call so a
forward-jumping clock can't overflow the FIFO.
* `KernelState.parallel_active` flag set at startup from
`--parallel` / `XENIA_PARALLEL=1`. Read by `coord_pre_round`
in main.rs to choose between the two tickers.
Verification:
* cargo test --workspace --release: 561 passing (+3 new
wall-clock tests vs prior 558 baseline).
* lockstep -n 100M --stable-digest: BIT-IDENTICAL to
pre-Phase-3 baseline. interrupts_delivered preserved at
~630 (was ~629 pre-fix).
* --parallel --reservations-table -n 30M: interrupts_delivered
rose from ~2 to 17. (FIFO INTERRUPT_QUEUE_CAP=4 still caps
burst delivery; that's a separate bottleneck — addressed
by raising cap when --parallel queue depth becomes the
next blocker.)
Trade-off: --parallel runs are non-deterministic at the
v-sync rate by design (per audit M05 PPCBUG-703 already).
Lockstep stays bit-identical, so the `sylpheed_n*m.json`
goldens are untouched.
Audit IDs: KRNBUG-D08 (closed).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
Adds a one-run diagnostic that distinguishes "guest never called
Nt/KeSetEvent on this handle" from "signal landed but waiter wasn't
woken", for any handle named via `--trace-handles-focus`.
Parked-waiter context (project_xenia_rs_sylpheed_stage3_2026_04_29):
four worker threads block Sylpheed past `draws=0` on handles
0x1004 / 0x100c / 0x15e4 / 0x42450b5c (mr=true, sig=false). The
pre-existing audit dropped signal-attempts that targeted handles
without a primary trail, so we couldn't tell whether the producer
was unreachable in the guest or whether the signal landed but missed
its waiter.
Three changes:
* audit.rs: `HandleAudit` gains `focus: HashSet<u32>` and
`ghost_trails: HashMap<u32, GhostTrail>`. `record_signal`
auto-falls-through to a new `record_signal_attempt_ghost` when no
primary trail exists AND the handle is in `focus`. Bounded by
AUDIT_RING_CAPACITY per handle. Two new tests cover the focus
ghost-trail and no-double-record invariants.
* main.rs: new `--trace-handles-focus=<LIST>` flag (hex 0x or decimal,
comma-separated) populates `kernel.audit.focus`. Implies
`--trace-handles`. New "=== Handle audit (focus) ===" section in
`dump_thread_diagnostic` emits per-handle:
- signal_attempts (primary + ghost), waits, wakes
- merged cycle-sorted timeline (last 16)
- GuestExport / KernelInternal classification
- <AUDIT_BLIND> marker when waiter_count > 0 but the audit
saw no waits (i.e. waiter parked via a non-audit path —
CS / spinlock / DPC).
- DIAGNOSIS conclusion that selects between five branches.
* `cmd_check` passes None for focus → goldens unaffected.
Empirical run output at -n 500M lockstep with
`--trace-handles-focus=0x1004,0x100c,0x15e4,0x42450b5c`:
handle=0x00001004 kind=Event/Manual waiters=1 signaled=false
signal_attempts=0 (primary=0, ghost=0)
waits=1 wakes=0
created cycle=0 tid=1 lr=0x824a9f6c src=NtCreateEvent
=> producer is a missing kernel signal source
(or BST-paradox upstream)
... (same shape for 0x100c, 0x15e4)
handle=0x42450b5c kind=<UNCREATED> waiters=1 signal_attempts=0
waits=0 wakes=0 <AUDIT_BLIND>
=> waiter parked via non-audited path
Conclusion: hypothesis (A) confirmed for all 4 handles. Producer is
NOT a wake/eligibility bug — it is a genuinely missing kernel signal
source. The 3 Event/Manual handles share a creator
(lr=0x824a9f6c, tid=1) and the same wait-call wrapper at
lr=0x824ac578 — these are 3 worker threads all parked on
"work-available" notifications that never come.
Verification:
* cargo test --workspace --release: 558 passing (+2 new ghost-trail
tests vs prior 556 baseline)
* lockstep -n 100M --stable-digest: bit-identical to master HEAD
Audit IDs: KRNBUG-AUDIT-001 (closed — diagnostic instrumentation).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
The Phase-C VdSwap PM4 ring path (commit 82f3d61) emits two
"PM4_XE_SWAP not consumed by drain" warnings when running:
exec sylpheed.iso --ui --quiet --halt-on-deadlock \
--parallel --reservations-table
Lockstep -n 100M never trips it. Two distinct race windows:
(a) Inline backend (--ui forces it): drain(mem, 4096) hit its
fixed packet cap before reaching the PM4_XE_SWAP we'd just
injected at the WPTR tail. With 6 CPU threads, the ring
accumulates >4096 packets between vd_swap callbacks.
(b) Threaded backend (--parallel without --ui): the worker's
DrainFence handler has a 900 ms deadline and game-batched
IBs (8-10 M packets observed) keep it from reaching the
tail in any reasonable budget. If the worker eventually
drained past the injected packet later, the safety-net
direct notify would double-count.
Three changes:
* gpu_system.rs: new `drain_until_wptr(target, time_budget)`
draining by the canary `WorkerThreadMain` predicate
(read_offset != target) instead of a fixed packet count.
900 ms deadline mirrors the threaded DrainFence handler.
* handle.rs: inline `drain_to_current_wptr` switches to
`drain_until_wptr`. DrainFence handler publishes the digest
mirror BEFORE replying so the CPU's post-drain
`digest_snapshot` sees fresh stats.
* exports.rs (vd_swap): skip the PM4 ring injection
unconditionally and route swap notification through
`notify_xe_swap` directly. Tail-injection is unreliable
under --parallel for both backends. The slot-0
fetch-constant patch is deferred (GPUBUG-FETCH-PATCH-001);
draws=0 today so a stale slot 0 has no observable effect.
Verification:
* cargo test --workspace --release: 556 passing (unchanged).
* Lockstep -n 100M --stable-digest: bit-identical to
pre-fix master HEAD aa3f1d3.
{instructions:100000002, imports:987685, unimpl:0, draws:0,
swaps:2, ...}
* check --parallel --reservations-table -n 30M: 0 warnings
(was 2). swaps=2.
* exec --gpu-inline --parallel --reservations-table -n 30M:
0 warnings (was 2 with drained=8M-10M observed). swaps=2.
Audit IDs: GPUBUG-DRAIN-001 (closed),
GPUBUG-FETCH-PATCH-001 (filed, deferred).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
`GuestMemory::write_bulk` did the bulk copy via raw `copy_nonoverlapping`
without bumping page_versions for any of the pages it touched. The
per-byte `write_u8/u16/u32` methods all bump page_versions after their
store; downstream caches (texture cache, shader cache) Acquire-load the
slot to invalidate stale entries on guest writes. Without the bulk
bump, a caller like `NtReadFile` writing a texture/shader resource into
guest memory would leave any cache that had already keyed on the prior
version handing back stale decoded bytes.
After the copy, walk every page the write touched and bump it. Cheap:
the typical bulk write spans a few pages (NtReadFile uses 64-128 KB
chunks → 16-32 pages).
Reservation-table invalidation for `lwarx`/`stwcx.` (XMODBUG-001's
sibling) is NOT addressed here — the reservation table lives on
KernelState, not GuestMemory, and plumbing it through requires a wider
change. Callers that bulk-write code-bearing or atomic-bearing memory
should call `kernel.reservations.invalidate_for_write(addr)`
themselves; XEX-loader and NtReadFile are doing data-bearing writes
that don't intersect lwarx targets, so this is acceptable for now.
Verification at -n 100M lockstep:
swaps: 2 → 2 (unchanged)
draws: 0 → 0
texture_cache_entries: 0 → 0 (Sylpheed hasn't issued IM_LOAD yet
— the bump is silent until a cache
keys on a touched page, which won't
happen until Phase F2/F3 unblocks
the resource-loader workers)
packets: ~59M (within noise)
Tests: 16 memory pass.
Closes XMODBUG-002 (P1).
Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
