| Commit message (Collapse) | Author | Age |
|---|
| |
|
|
|
|
|
|
|
|
| |
Document the corrected GR context-buffer query ABI (80-byte entries, 5136
byte params), the new gsp_phys_rmcall_srv_ctxcommit / gsp_phys_rmcall_channel
/ gsp_phys_gr_forward parameters, and the live 2026-10-05 findings: PA-only
never commits the engine context pointer; on the shared VAS the server
pre-books MAIN as managed so a client VA-only promote returns 0x40 at the
vaListSetManaged gate; EVICT_CTX does not release it; the external-VAS
VA-promote shape wedged the device and must not be repeated.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
content-hash once gate)
The grace-expiry fake path consumed a held CE entry without marking its
GPFIFO slot as consumed for the put epoch, and the replay guard only ran
while the channel was not deferring. A later pin-batch rewind then
re-read the slot, found no recorded identity, and executed the push's
copies against a staging buffer the client had refilled after the faked
release - a deterministic vadd input shift (a[k] == h_a[k + 2 MB]).
- grace-fake consume path now calls svc_replay_note() before advancing;
- the svc_replay_seen() replay skip is evaluated unconditionally: a slot
consumed in the current epoch is skipped on every replay, deferral or
not, until a put wrap clears the mark;
- the once-only identity gate gains a content witness (FNV-1a hash of the
recorded push bytes): the same entry words with different push content
is a new push (clients rewrite push buffers in place) and runs its ops
with a cleared done bitmap; suppression requires identical content;
- snapshot write-back persists the hash array; new drain counter
reident= counts content-mismatch cancellations;
- the grace window stays at 8 s: a faked entry's work is never run, so
the hold is that work's only chance (a 2.5 s experiment made red-class
runs complete with corrupt data instead of timing out).
Verified: module 8e90fc7e..., three consecutive end-to-end acceptance
runs (MAIL + VADD bad=0 checksum=392344090.500000 + STATUS OK).
|
| |
|
|
|
|
| |
A later supervised cycle reproduced the held-entry retry over a
refilled staging buffer, the completed operation was skipped, and the
end-to-end transfer verified byte-for-byte (bad=0, expected checksum).
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The pump's operand-targeted-scan hold decodes a push, runs every op that
translates, then leaves the entry pending for a retry. The retry
re-decoded the whole push and re-ran the operations that had already
completed. A CE copy reads a client staging buffer the client refills
per chunk, so the retry overwrote a finished chunk with the following
chunk's data (observed: the bridge's vadd input half replaced by the
next 1 MB chunk, first half of the device buffer byte-identical to the
source shifted by exactly 2 MB; the same 1 MB copy logged twice with
different staging contents).
The service now records, per GPFIFO slot, the entry identity plus a
bitmap of the decoded operation indexes whose work has executed for
that identity, and a complete flag for a pass that ended with no
operand pending. svc_run_ops skips already-executed ops on a retry and
marks the rest as they succeed; the pump stores the record
immediately after decode, before any hold path can break, so the
pending path can no longer lose it. A replay of a complete identity
suppresses all ops; a partial identity retries only what is owed.
Also carries the ops_once diagnostic counter in the service snapshot
line and documents the operation-granularity rule in the architecture
doc.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The no-claim emulation path now runs a stock CUDA program end to end:
device properties, cudaMalloc, a GPU-authored string kernel read back
byte-for-byte, two 4 MB host-to-device copies, a 1 M-element vectorAdd
executed on the physical GPU through the host bridge, and the
device-to-host copy-back verified element by element. Three consecutive
supervised cycles report MAIL + VADD bad=0 checksum=392344090.500000 +
STATUS OK with identical input/output hashes.
Two data-path correctness fixes make the transfers sound:
- Once-only op execution per GPFIFO entry. The pump replays recently
consumed ring entries when translation batches are injected so missed
releases can land; re-executing a CE copy is not idempotent because
its source is a client staging buffer that may have been refilled.
Slots now record their raw entry words and a replayed entry matching
that identity suppresses operations while still processing releases.
- Per-page translation of virtual operands. svc_copy resolved only the
first page of a VA range and walked the PA linearly; client staging
ranges are frequently split (observed 195 + 61 pages), so the tail of
alternating chunks was read from unrelated memory. Multi-page copies
now re-resolve each 4 KB page through the trusted resolver.
Also carries the earlier uncommitted emulation fixes that got the client
to the launch (QMD address-window gate, counter registration
persistence, 512 MiB emulated FB, bridge slot hygiene) and bounded
diagnostics (sema-bigop, sema-bigcopy, bridge-in/out hashes, daemon
INCHECK/OUTCHECK/dumps).
|
| |
|
|
|
|
|
|
| |
- kernel: gsp_cuda_bridge (QMD launch capture, debugfs job/out/done, param+output resolution cached from inline writes), sema drain fixes (never hold/starve a channel), GR ring autopin + counter autoreg, per-page push reads, counter-derive gate; module builds clean
- tools/cuda-bridge: CUDA driver-API daemon executing mail/vadd kernels on the physical GPU, CUBB2/CBD2 v2 protocol, layout check + self-tests
- tools/guest-diag + tools/cuda-ab: scanner/pin fixes, victory push-only mode
- debug/risc-v-gsp-rm-vm: Phase S simulator wave (GSP device model, boot ladder, triage/re-demo harnesses, docs 30-41), GPGPU-sim scaffolding
- STATE-CURRENT/docs updates
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
(guest-faithful 9-entry set)
- gsp_rm_emulation: dump every guest GPU_PROMOTE_CTX (0x2080012b) params and
entries so the real client's promote shape is observable (captured on the
emulation path: MAIN 2 MB PA+VA, PATCH, BUNDLE_CB/PAGEPOOL/ATTRIBUTE_CB/
RTV_CB_GLOBAL VA-only, FECS, PRIV, UNRESTRICTED)
- gsp_phys_booter: promote mode 19 replays that exact 9-entry shape on the V5
channel with host buffers (MAIN 2 MB + PDB map, small buffers, booking-only
VAs); clamp 0..19
- docs/eng-ops: mode-19 result recorded - the server never replied (fn76 -110)
and the release fail-safe held WPR2/GPU until an approved reboot; mode 19 is
known-wedging
|
| |
|
|
|
|
|
|
|
|
|
| |
- gsp_phys_booter: mode 18 allocates a FERMI_CONTEXT_SHARE_A (0x9067) on the
TSG with the ladder VAS and carries it as hContextShare on the V6 KMD
channel, so the share construct can allocate the GraphicsSubcontext the
single-MAIN promote needs; clamp 0..18
- docs/eng-ops: GR promote bisection row updated with the session-2 results
(modes 12-18: PA-only accepted but no ENG_CTX_VALID; PATCH/PM/FBMEM and
server-managed registry all leave the KMD promote at 0x40; wall is the
commit/RAMFC path)
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
registry variant; complete vgsp rename; docs/tooling refresh
- gsp_phys_booter: GR promote bisection modes 4-17 (two-phase zero-field VA,
batched entries, hVirtMemory, bare VA, KMD SKIP_CTXBUFFER_ALLOC channel,
old-interface GPU_INITIALIZE_CTX, FBMEM context buffer, UVM-faithful PA-only,
PATCH/PM auxiliary promotes, server-managed no-promote path); PATCH/PM
geometry queries and buffers; pre-boot SET_REGISTRY profile selection
- gsp_phys_gpu: gsp_phys_rmcall_gr_promote clamp 0..17 and gsp_phys_srv_ctxbuf
parameter; registry image variant with RMSetClientRMAllocatedCtxBuffer=0
- vgsp rename across kernel, scripts, tools and docs (module vgsp.ko,
/sys/kernel/debug/vgsp/, vgsp-<subsystem>: log prefixes)
- risc-v-gsp-rm-debugger user-facing rename and docs/CI refresh; guest-diag
tool updates; README/SBOM/install/Makefile sync
Live status: CE ladder and P6 guest-copy forwarding green; GR engine context
commit still open (all promote shapes accepted or cleanly refused; the channel
stays CTXNOTVALID) - see Handoff-vGPU-IO.md Addendum 21 (local).
|
| |
|
|
|
|
|
|
|
|
|
|
| |
complete rename, adversarial-review fixes
Remove the '# TOOL IN DEVELOPMENT - NOT READY YET!' notices from the tool docs/README/scripts and the project docs; record the removal (2026-10-02) against the tool audit (debug/risc-v-gsp-rm-vm/docs/27-TOOL-AUDIT.md), the 194-test suite and the value-validation demos (docs/25-VALUE-VALIDATION.md).
Complete the cosmetic rename to risc-v-gsp-rm-debugger in user-facing prose and commands (launcher, roadmap, docs); internal greeneye package and code identifiers unchanged.
Adversarial-review fixes: deterministic control-discovery sweep (flaky test root-caused), UUID session dirs + atomic JSON writes for concurrent runs, Ghidra bridge loopback enforcement and clean shutdown, fp register restore in Session.call, version_diff --dry-run, 30 s interrupt budget, dry-run non-destructiveness verified.
Docs: flag-removal records, link fixes, command/flag corrections (fdematch arity, port_new_device --out, trace filename), F2 orchestration note in future-eng-ops; STATE-CURRENT status refreshed.
|
| |
|
|
| |
docs, CLI, launcher and CI workflow; internal greeneye package/module identifiers unchanged (includes in-flight greeneye module edits present in the tree)
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- docs/eng-ops.md gains Part II, live physical-backend engineering
operations: hard rules, the full module-parameter matrix, the routine
supervised cycle and clean-release checklist, the debugfs inventory,
how to read gsp-phys-state, a debugging scenario catalogue
(CTXNOTVALID/promote wedge, fail-safe WPR2, unload hangs, guest wedges,
MMU/PTE and PBDMA faults, relay symptoms), a hazard register (crash
causes and debugging side effects), the physical-backend OODA loop, and
the work-context map with porting flows
- architecture, implementation, operations, orientation, getting-started,
portability, ecosystem and reference docs corrected to the current
state: CUDA driver-API smoke green, CE-class work forwarding and
engine-authored releases plus fault relay in place (default off), GR
execution blocked on engine-context validity, the promote wedge and
designed locked fail-safe, and P5 wave-2 subsumed
- internal-reference cleanup in tracked docs (no analysis-source or
local-archive references); historical architecture document bannered
- README reading list and STATE-CURRENT frontier refreshed; new pages
(runbook, green-eye user guide, porting sequence, porting/packaging
notes) linked from the tree
Link check: scripts/check-docs-links.py passes (56 files, no broken links).
|
| |
|
|
| |
plugin, value-validation demos, CI pipeline, toolchain docs; add host RM tools rmtool/rmtop
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
bridge, long-term docs
Adds to debug/risc-v-gsp-rm-vm/:
- Session.call / run_until: Frida-like remote function calls and run-to-cursor,
with register restoration; verified live (rpc_ping -> 0xaffe).
- symbol+offset target resolution (gsp_ctrl+0x10) across all APIs and the REPL.
- Injection SDK (sdk/) and 'greeneye inject': position-independent RV64 service
blobs (verified zero relocations), loaded into RAM, registered in the demo
handler table, and invoked either directly or through the firmware mailbox
dispatcher. Demo ABI extended: mailbox 16..23 selects slots, arg0 carries the
service command, arg2 added (struct now 0x190; schema updated).
- Ghidra control bridge (greeneye ghidra + GreenEyeControl.java): run-until-here,
breakpoints, memory/register access, remote calls, hit export; verified
end-to-end with Ghidra headless (run_until reached rpc_sum from a GhidraScript).
- MarkGreenEyeHits.java fixed for the Ghidra 12 createBookmark API; verified
headless together with ExportForGreenEye.java.
- Analyzer renders a QEMU first-fault table for probe sessions (fault count,
epc with firmware vaddr translation, access address/size, reason).
- Tests now 35 green, including injection, Ghidra bridge, remote call, run-until
and REPL command smoke tests.
- Documentation: docs/11-16 (GSP RM service developer guide, injection SDK
specification, Ghidra control, adversarial interoperability guide, agentic
GSP IDE, custom simulator design) and GREEN-EYE-ROADMAP.md (long-term H1-H7
program); doc maps and the project RISC-V VM doc updated.
|
| |
|
|
|
|
|
|
|
|
| |
Adds open-iov/debug/risc-v-gsp-rm-vm: a GDB-free instrumentation stack that boots uproc/GSP firmware in qemu-system-riscv64 and provides Frida-like hooks, breakpoints, watchpoints, memory dumps, structure decoding, snapshot diffs, recorded sessions, declarative probes, a plugin API and a Ghidra symbol/hit bridge.
Verified: 25 tests green (including a live QEMU smoke test); the demo uproc boots with correct hook/leave/watch/schema/snapshot/fault evidence; the optional TCG trace plugin builds and recorded 15M trace lines in 3 s; the TU104 570.144 fwimage probe reports its first exception (load access fault at firmware vaddr 0x4009014 reading 0x2000000000000A00).
Documentation: lean tool docs under debug/risc-v-gsp-rm-vm/docs/00-10, a new docs/05-operations/03-risc-v-gsp-rm-vm.md debugging document, and '# TOOL IN DEVELOPMENT - NOT READY YET!' markers in docs/README.md, the onboarding tooling table and the debugging workflows doc.
Vendors qemu-plugin.h from QEMU v8.2.2 (GPL-2.0-or-later), with its license header intact, so the optional TCG plugin builds without a QEMU source tree.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
copies
- new default-off gsp_phys_work_defer_release: a forwarded guest push's
releases are recorded and its GPFIFO entry is held (no consume, no
GP_GET write, no counter publish/stall) until the work item publishes
completion; the service thread then delivers the releases, with a
fallback on failure/timeout (500 ms cap enforced every pump pass)/
pause/quiesce/channel-delete
- new default-off gsp_phys_work_hw_primary: the software copy is skipped
for forwarded ops, so the physical engine authors the data; a once-only
software copy runs before the releases on any hardware failure or when
the request cannot be queued
- release-apply helpers extracted; exactly-once latches; channel-delete
and teardown handling; counters and a work_guard state line
- live: deferred-release run engaged=75 applied=75 timeouts=0 with the
full smoke green; hardware-primary run req=100 ok=100 verify_ok=100
fallback=0 copy_skipped=119 copy_fail=0, smoke ALL OK 64/64 (guest read
data the engine authored), with 19 fail-closed inline software
fallbacks under single-inflight contention; a range-unregistered run
proved the fallback (121 skipped copies, all recovered, smoke green)
- defaults off; the software path and all existing guards unchanged
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- the sema service captures the first eligible copy per push from the
software resolver's own operands (the real push shape mixes guest RAM
with emulated-VRAM shadow addresses, including physical destinations)
- HPA resolution: guest RAM through the shared guest-RAM file page cache,
emulated VRAM through the mapping of its kernel shadow
- new scratch page-table pool: 16 zeroed page-table pages with their
page-directory entries built before any engine access, handing out one
whole 128-byte GMMU PTE fetch line per copy pair (16 PTEs, 512 pairs
per boot, never reused; a PTE written into an already-fetched line is
not observed and there is no invalidate path)
- the backend submits the copy on the module-owned channel and verifies
the result host-side; every miss falls back to the ladder shadow copy,
and the software pump remains authoritative
- live (full smoke, both parameters on): req=42 ok=42 verify_ok=42
verify_fail=0 fallback=0, guest payload roundtrip ALL OK 64/64,
clean latched release; defaults stay off
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- file-backed guest RAM (launcher memory-backend-file share=on) and
in-kernel GPA->HPA translation through the shared file page cache
(read_cache_page + page_to_phys + pfn_valid), opened O_LARGEFILE;
new default-off gsp_phys_guest_mem parameter
- debugfs gsp-phys-guest-ram (path + gpa/off/size ranges) and
gsp-phys-guest-gpa (one pinned GPA per boot); rm-call triggers 6/7 run
host->guest and guest->host 4 KiB CE copies; trigger 8 is a PTE
self-test through a fresh slot
- guest page-table slots are pre-built during ladder stage 3: runtime
PTE writes into an already-walked page-table line are not observed
without a TLB invalidate
- guest RAM layout (q35 4.2, 4 GiB): below-4G GPA == file offset,
above-4G offset = GPA - 0x80000000 (2 GiB PCI hole)
- tests: tools/test/gpage_test.c guest probe; docs + STATE-CURRENT
record the live green (G2H/W2G with semaphore release, guest observed
the write, smoke ALL OK 64/64, clean latched release)
|
| |
|
|
| |
third-party references
|
| |
|
|
| |
P5 wave-1 shadow execution
|
| |
|
|
|
|
|
|
| |
- STATE-CURRENT snapshot moves to the P3 frontier: the host-freeze latch
and readiness gates are validated, the static identity overlay and the
read-only control forwarding are landed and live-verified
- the physical-backend guest-wiring design is now marked P0-P3 implemented
with the P2/P3 acceptance results
|
| |
|
|
|
|
|
|
|
|
| |
Clarify in the post-1.0 record and the public status page that host-native
acceleration / host display is a stretch goal we are only considering:
do not block on it, pursue it, or design around it. It is never reached
automatically, requires an explicit human decision after all baseline goals
are complete (and only once there is no known risk), and may be scrapped on
architectural grounds. No aspect of the baseline software may be designed
toward it. No baseline design or code changes.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The host-VF design is reverted. Independent adversarial, soundness and
VM-support reviews falsified its load-bearing mechanisms: RAM-backed BARs
cannot be ioremapped or claimed by the stock driver on x86_64 or aarch64;
trap-free windows cannot observe edge-triggered writes or read side
effects; multi-client GSP-RM is unproven; the MSI and bridge bring-up
plans were incorrect; and the isolation and performance claims were
overstated for the mechanism.
Replace it with one self-contained post-1.0 document recording the
findings, corrected candidate approaches and trade-offs, a minimal-risk
future architecture, the compile-time + module-load experimental gating
policy, a phased plan with abort gates, and the revisit criteria. No
baseline design or code path is changed; all earlier doc edits are
reverted.
|
| | |
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
physical-backend guest-wiring design
- STATE-CURRENT snapshot 2026-10-01 21:05: the host RM-client ladder now
allocates VAS+PDB+TSG+channel and executes a real 4 KiB VA-mode CE copy
(semaphore released, dst==src) on the physical engine; next is wiring the
live session into the guest-facing mdev/vfio path.
- docs/03-architecture/11-physical-backend-guest-wiring.md: phased design
(P0-P6) for bridging the physical backend into the guest-facing emulation,
with the seam table, lifecycle changes and static-config flow.
- docs/README.md: reading order updated for the new document; execution
status refreshed.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
Fill the GspSystemInfo chipset fields the production client syncs before
the GSP boot instead of leaving them zero:
- clPdbProperties (bitmask in the client's clSyncWithGsp order): bit 0
(config space accessible, from the OS MCFG/ECAM availability), bit 7
and bit 21 (Intel Skylake-family upstream-port setup: ASPM POR list,
root-port nosnoop WAR), bit 13 (upstream port ASPM L1 capable), bit 27
(LTR supported+enabled up to the root port) and bit 32 (IO coherent).
PDB_PROP_CL_UNSUPPORTED_CHIPSET is never assigned by the client, so the
faithful unmatched-chipset value is 0.
- Chipset = 0 (CS_UNKNOWN) for a host bridge with no chipsetInfo[] entry,
the reference's no-match fallback.
- FHBBusInfo/chipsetIDInfo: 10-byte BUSINFO blobs of the first host
bridge of the GPU's domain (device, vendor, subdevice, subvendor,
revision), with the subsystem-capability fallback on chipsetIDInfo.
acpiMethodData is intentionally sent all-zero (bValid=0): no ACPI/AML
calls are made and every consumer tolerates the no-data encoding. All
device lookups use refcounted pci_get_device()/pci_dev_put().
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
The real-GSP boot path staged the message queue but never queued the two
fire-and-forget init RPCs the production client places in it before the
booter starts. GSP-RM therefore created its GPU object without any system
information and aborted RM init (live GSP_INIT_DONE rpc_result=0x59), with
the resource-manager's object-database lookups asserting from the first
journal record.
Submit function 72 (GSP_SET_SYSTEM_INFO, 928-byte v17_00 payload carrying
the BAR physical bases, domain/bus/slot, PCI IDs, the BAR0 config-mirror
offset, link/FLR capabilities and upstream-port flags read from the
pci_dev) and function 73 (SET_REGISTRY, header-only empty table, which the
server explicitly accepts) through the existing submit-only queue producer
after all stage-3d preconditions and before the GSP falcon reset/Booter
Load kick. The wire layouts are re-declared in the module with per-field
static asserts against the reference ABI; payloads are heap-allocated, so
no new stack frames are introduced.
|
| |
|
|
| |
STATE-CURRENT and the integration page reflect the implemented sequencer, clean-shutdown RPC and static-info probe awaiting the next supervised live cycle.
|
| |
|
|
| |
Adds a minimal msgq producer on the command queue (element layout, checksum, sequence, dma_wmb before writePtr, doorbell) and submits the UNLOADING_GUEST_DRIVER RPC so GSP-RM shuts down and sets the scratch14 handoff bit the Booter Unload gate needs. Release attempts the RPC once before quiescing when a boot ran; on-demand testing is available through the debugfs file gsp-phys-unload-rpc while the module owns the GPU. GSP-RM processor suspend is polled on the GSP mailbox.
|
| |
|
|
| |
STATE-CURRENT and the architecture docs now describe the observed order (FWSEC -> Booter Load -> RISC-V active -> event 0x1002 run-sequencer -> 0x1001 init-done), the four-handoff-bit clean-release constraint, and the --boot/--keep harness contract.
|
| |
|
|
| |
physical-backend lock
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
physical backend
- New 4.2: describe behaviourally how the option-D claim path can
power-gate the board on driver release (platform power resource behind
the root port, off/on sequence via the embedded controller), the two
observed host freezes (no crash record), and the D0 lock now applied
across release -> claim -> rebind: runtime-PM forbid + D3cold disable on
the GPU, its board companion functions and the root port, config-space
verification while claimed and again before rebind, abort with the locks
held on any power-loss signature, runtime-PM restore after the
distribution driver's probe.
- 4.1/4.3: the lock is a required ownership step; returning to the normal
driver is conditional, not assumed; real GSP boot not started.
- 2/3(A): fresh no-unbind evidence - no exported RM/vGPU symbols and no
manager daemon in the stock distribution build.
- 6: driver-API baseline re-verified 64/64; ownership + firmware staging
verified; power-domain lock implemented pending supervised verification.
- 7/8: residual out-of-band power-cut risk, supervised-test requirement,
and the gsp_phys_gpu + gsp_phys_hazard_ack operating constraint.
|
| |
|
|
| |
verified, real boot next
|
| |
|
|
|
|
|
| |
- remove the superseded flat state page; current state lives in
STATE-CURRENT.md and the docs tree
- update the historical-material note in docs/README and the STATE-CURRENT
header/see-also references
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
| |
- new 03-architecture/09-full-system-picture.md: end-state map, GSP boot,
guest init, RPC lifecycle, memory model, work path (bridge and end state),
scheduling, isolation levels, KVM/mdev/VFIO, BAR/engine/channel/GMMU,
portability, performance model, implementation/test status
- new 03-architecture/10-interaction-and-scheduling.md: interaction inventory,
control-plane call path, msgq element lifecycle, channel pump, concurrency,
timing budgets, multi-tenant scheduling, teardown ordering, versioning
- README: mermaid system diagram replaces the ASCII block; reading list
extended and renumbered
- component docs: GSP boot sequence, mdev/VFIO lifecycle, end-state
interaction sequence; STATE-CURRENT links
|
| |
|
|
|
|
|
|
|
|
|
| |
- add docs/03-architecture/08-physical-gpu-integration.md: interfaces that
exist, mechanism options A-E, chosen path (module-owned GPU driven through
its real GSP firmware), sharing policy, decision record
- update 06-host-module-and-hybrid-model, 02-practical-challenges, system
overview, known-knowns, docs/README reading order and CUDA-side docs to
match
- correct stale engine-topology/COPY14 blocker claims across the tree
- add STATE-CURRENT.md as the dated public status snapshot
|
| |
|
|
| |
pitfall
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
- admit {GPU VA -> PA} pairs only when the preceding bytes form a valid
client memory descriptor header (type 0/1, CPU+GPU mapped bits), prefer
validated pairs over headerless candidates under first-wins dedup, and
invalidate the translation cache on every rebuild; fixes stale identity
entries shadowing live pool pages and lets the guest UVM channel
bring-up complete on its own
- capture OS event allocations (class 0x79) and post event records
(function 0x1003) into the guest status queue when a channel's busy
notification is consumed, with a broadcast fallback, serialized with
replies via a queue lock
- add BAR0 shadow introspection (dump_bar0/scan_bar0) and guest-side
diagnostic scripts for the VM cycle
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Merge and remove the pre-reboot flat documents, preserving their still-useful
material in the structured tree: debugging workflows and the EPT-livelock
case study (05-operations/02), performance microbenchmarks and A/B
methodology (05-operations/01), the version-upgrade runbook
(05-operations/02 section 4, with corrected host/guest framing), kernel-code
pitfalls (07-developers) and the OpenRM build/load order
(03-architecture/06 section 7). The remaining legacy files were verified
redundant and removed.
* docs/README now records where each migrated topic lives.
* Portability: the config YAML files are called out as design targets that no
code reads yet, with what adding support actually requires today.
* Getting started: the OpenRM step is marked optional (native vGPU-management
workflows only; the emulated path uses the distro driver).
* tools docs: rmtool/rmtop marked as planned, pointing at the implemented
tools/rmq subset.
* wiki: new CUDA-Userspace-Driver deep-dive page (public-safe, links the
canonical userspace/cuda analysis) and index update.
* scripts/check-docs-links.py plus a CI step so relative links cannot rot.
* STATE.md references to removed documents repointed.
|
| |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| |
* Status now matches the live state: guest driver probe and nvidia-smi work;
cuInit/device queries work; cuCtxCreate returns 999 because the emulated
engine list is missing the async copy engine (COPY14). The userspace
libcuda segfault is recorded as solved, with its mechanism (an RM
allocation reply must echo request parameters; zeroing them corrupted the
caller's saved frame pointer).
* Correct the emulation claims: only a subset of RM controls are
special-cased; the rest return a success reply with zeroed parameters whose
consumed fields are still being corrected; allocation replies are coherent
but no server-side object model exists.
* Add the eight-point emulation checklist and reply-fidelity ladder as
explicit gates, documented in userspace/cuda and linked from the
architecture, implementation and operations docs.
* Fix operational errors: build/test commands, module load order, mdev type
names, LFS references, debugfs claims, in-repo firmware claims, CI claims,
portability matrix (guest status, config layout, userspace driver facts).
* Mark historical material: one superseded banner per legacy document with a
pointer to its replacement; STATE.md marked as a 2026-09-21 snapshot.
* Wiki: fix the index, add status banners and in-place factual corrections
(msgq transport vs legacy mailbox, BAR definitions, error statuses,
migration, glossary), and note the archived 2023 imports.
|
| |
|
|
|
|
|
|
|
| |
- patches/ -> legacy-patches/ (gitignored)
- legacy-driver-guest/ (old guest vGPU driver, gitignored)
- docs/old/ (superseded architecture write-up, gitignored)
- docs that only reference the legacy components stay tracked; their path
references now point at legacy-patches/
- install.sh PATCH_DIR updated
|
|
|
Open-IOV virtualizes NVIDIA GPUs so that unmodified guest drivers run with
real GPU functionality - CUDA first, 3D and video to follow - on unmodified
hosts, without a proprietary vGPU license and without patching any driver,
firmware or hypervisor.
Core principle: emulate the interface, pass through the work.
kernel/ open-iov-vfio.ko - host VFIO mdev driver: virtual GPU device
(PCI config space, BAR shadows, MSI-X), GSP boot emulation,
GSP-RM message-queue/RPC emulation, memory model (GPU-VA to
guest-PA discovery) and the semaphore-completion service that
advances guest UVM progress.
userspace/ libiov.so management API and examples.
tools/ guest diagnostics, firmware analysis wrappers, RM probes.
scripts/ stack manager, VM harness, build/load/test automation.
config/ hardware/version profiles (the portability surface).
docs/ documentation tree - start at docs/README.md.
wiki/ long-form firmware and protocol deep dives.
Status: initialization works end to end for a stock 570.144 Linux guest on
Turing (TU104): driver probe, nvidia-smi, the full GSP-RM control battery,
object creation and the early CUDA/UVM start-up path. GPU work forwarding -
the step that makes CUDA kernels execute on real hardware - is the active
work item; see docs/04-implementation/01-known-knowns-and-unknowns.md.
License: BSD-3-Clause for the project; GPL-2.0 for kernel modules that link
GPL-only kernel interfaces. See LICENSE and docs/09-reference/legal-and-licensing.md.
|
