From ce40bd872ea05776156a68afcc6d4571a0bbcad2 Mon Sep 17 00:00:00 2001 From: Arthur Hanson Rasmusson Date: Mon, 5 Oct 2026 13:06:39 -0400 Subject: vgsp: guest GR forwarding backend and capture (gsp_phys_gr_forward, default off) Add a default-off guest GR (compute) forwarding path so a guest CUDA launch submitted on its GR channel can be executed by the physical GR engine on the ladder channel, with fail-closed fallback to the host CUDA bridge and the unchanged software release path. - New module parameter gsp_phys_gr_forward (default 0) and accessor. - New GR execution gate: boot_stage.rmcall_gr_exec_ok, latched only after a real GR submission logs REAL GR SEM OK; the backend refuses while it is unset. - Sema capture: a completed 64-word inline QMD on a trusted, non-replay GR decode becomes an svc_gr_cand (push identity, decoded release0, parameter/program/pointer fields, up to 8 captured inline-write records); the CUDA bridge stays authoritative while the parameter is off and is reached in order forward -> bridge -> software release. - Backend: gsp_phys_backend_guest_gr_submit() maps pages at their own guest VAs through fresh Tier-1 small-PT pages/PDE installs or relocates inline-captured pages to ladder shadow pages (Tier 2), builds SET_OBJECT + the inline-QMD method run + REPORT_SEMAPHORE on the compute subchannel, reuses the shared GPFIFO/USERD/doorbell publish tail (extracted from the CE submit path, CE bytes unchanged) and polls the QMD release and/or module semaphore, draining the epoch-gated fault queue on timeout. - Sema wiring: GR requests reuse the INFLIGHT/hold/deferral machinery so the guest channel release applies only on the submit's success/failure edge; hold shims preserve the channel engine type. - Counters and a work_gr state line plus a stats accessor. - Bounds are fixed: 16 pages, 8 inline records, 64 QMD words; every pointer/size checked, pool exhaustion and stale mappings fail closed. - New ABI layouts pinned with static_asserts. Compile-only change: no device test performed. --- kernel/gsp_phys_gpu.h | 12 ++++++++++++ 1 file changed, 12 insertions(+) (limited to 'kernel/gsp_phys_gpu.h') diff --git a/kernel/gsp_phys_gpu.h b/kernel/gsp_phys_gpu.h index 74e3103..b204961 100644 --- a/kernel/gsp_phys_gpu.h +++ b/kernel/gsp_phys_gpu.h @@ -91,6 +91,18 @@ bool gsp_phys_srv_ctxbuf_value(void); */ bool gsp_phys_work_forward_enabled(void); +/* + * True when the gsp_phys_gr_forward module parameter is set (default 0: guest + * GR (compute) launches stay on the existing host CUDA bridge / software + * path). When set, the sema service captures a completed guest inline QMD and + * the booter submits it as real work on the ladder's physical GR channel, + * but only after boot_stage.rmcall_gr_exec_ok proved a real GR submission at + * boot (gsp_phys_backend_gr_ready() enforces the gate). Every forward + * refusal/failure falls back to the CUDA bridge (when enabled) and then the + * unchanged software release path. One-line rollback: gsp_phys_gr_forward=0. + */ +bool gsp_phys_gr_forward_enabled(void); + /* * True when the gsp_phys_guest_mem module parameter is set (default 0: the * debugfs rm-call ladder stays entirely on module-owned buffers, exactly as -- cgit v1.2.3