summaryrefslogtreecommitdiffstats
Commit message (Collapse)AuthorAge
...
* vgsp: m81 - map the PM ctx-buffer booking VA before the engine context loadArthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | The m80 window shows PGRAPH_INTR=0x00000010 (ILLEGAL_METHOD, the reserved-SW prelude methods, same as the real driver) clearing, then 0x00200002 (SEMAPHORE|EXCEPTION) pending exactly when the QMD activates, followed by the FECS save/unload. The real driver's launch transient carries the same ILLEGAL_METHOD without ever setting EXCEPTION, so the exception is the ctx-restore difference. The one R1-booked ctx VA with no PTE is PM (0x2370000): the golden9 range mapping covers PATCH/FECS/PRIV/UNR and the four globals (windows 17..22 after the golden9k 1->6 extension) but never PM, and R1-before-F2 makes the image carry that VA as the PM pointer. Map it through the ctx PT window right after the mode-35 PM FBMEM allocation, before any engine context load and before the PTE line's first fetch.
* gr-regs/vgsp: sample PGRAPH_INTR + PGRAPH_INTR_EN at the dispatch windowArthur Hanson Rasmusson5 days
| | | | | | | | | | The m75/m78/m79 launch windows show FECS_CTXSW_STATUS_FE_0.GR_INTR_REQ (bit17) asserted through the SKED CWD ACTIVE state and a following CTXSW_REQ (bit0) that results in the context save/unload. The real driver carries GR_INTR only transiently during its context load and clears it before ACTIVE. The PGRAPH interrupt latch (0x400100) names what the engine is signaling (e.g. ILLEGAL_METHOD bit4, SEMAPHORE bit1, NOTIFY); sampled by the external sampler and dumped in the launch post-mortem.
* vgsp: m78 - lane-enable skip mask + best-effort lane tail (#1063 no longer ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | aborts it) gsp_phys_rmcall_gr_lane_skip: bit0 skips #1059 CILP mode, bit1 skips #1061 timeslice, bit2 skips #1063 device-sched. Used to bisect which lane-enable control arms the forwarded QMD enqueue and which one leaves the scheduling state that ends in the dispatch-time context save. Also makes the m76 lane tail independent of #1063 (always refused 0x1f by the server).
* vgsp: m76 - R2 lane tail (TSG PREEMPT bWait + device-sched off + perf boost)Arthur Hanson Rasmusson5 days
| | | | | | | | | | | The real client's context-creation tail after the lane-enable trio is #1073 NVA06C_CTRL_CMD_PREEMPT on the TSG with bWait=1, #1075 NV0080 device-sched disable, #1077 PERF_BOOST_SET_2X. The explicit preempt makes the RM perform a clean context save/switch-out at setup time so the first dispatch loads the context normally; without it our lane's context sits loaded from the ladder and task activation ends in a save/unload instead of execution (m72/m73/m75 signature). Gated by gsp_phys_rmcall_gr_lane_tail (default 0).
* gr-regs: sampler reads CWD_FS, CWD_PARTITION_CTL/DATA, HWW_INFO/EN, SKED ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | caches/tasktables The dispatch-time comparison against the live driver needs the GR context's floor-sweep state (CWD_FS expected 0x1806 on TU104) and the SKED debug interiors (HWW_INFO_1/2/3, CWD_T2, CACHE_0/1, L15_CACHE_0, TASKTABLE_0/1/2). Recorded 2026-10-07: the distro driver's executing steady state shows CWD_FS=0x1806, CWD_T0=0x3f002400 (VEID 63), SKED_ACTIVITY=0x600000c0, PGRAPH_STATUS=0x01242001, FECS_CURRENT valid and frozen for the kernel's lifetime, TASKTABLE zero.
* vgsp: m74 - R1 booking before F2 image init (context-image aux pointers) + ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | CWD_FS readback The one-shot GR context-image initializer (0x52a94f8, pEngCtx+0x135) runs in F2's mapped-MAIN promote and consumes the per-VAS vaLists at that moment. With R1 after F2 the image carries zero PATCH/PM/priv-map/global pointers; the m72/m73 sampler signature (QMD ACTIVE then freed, FECS unloads exactly at dispatch, no fault) is consistent with the engine context restore failing on the empty image. gsp_phys_rmcall_gr_r1_first=1 sends R1 before F2 (default 0 = legacy order). Post-mortem now also reads CWD_FS (0x405b00).
* vgsp: m72/m73 - local-memory context block (SKEDCHECK05 fix), SKED ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | | | | | | | | | | transition recorder, sysmem instance selector m72: append the vendor turingLocalMemUpdate block (SET_SHADER_LOCAL_MEMORY_A/B 0x790/0x794, NON_THROTTLED_A/B 0x2e4/0x2e8, WINDOW_A/B 0x7b0/0x7b4) to the forwarded GR launch prelude; without it the channel local-memory state is zero and the m64-m69 sampler shows SKED_HWW_ESR bit12 = SKEDCHECK05 LOCAL_MEMORY_TOTAL_SIZE latching while the CWD entry is allocated then deallocated. Base/per-TPC size are module params for A/B. m72: change-detecting SKED transition recorder in the launch poll (CWD_T0/1/2, HWW_INFO_1/2, ACTIVITY, HWW_ESR, GRFIFO, FECS current/new/ctxsw status) and extended post-mortem readbacks (HWW_ESR_EN, INFO_1/2/3, CWD_T2, watermarks). m72-r2 sampler result: the QMD enters SKED (CWD_T0=0x11300 STATUS=ACTIVE, CWD_T1=0x1070) and HWW_ESR stays 0 with the lmem block, but the FECS context load never completes: NEW_CTX=0x001f42b0 (V7 FBMEM instance, VALID=0) then CURRENT=0; the task frees (CWD_T0=0x12000 DEP=PENDING_TASK_COMPLETE). m63 (sysmem instance) had VALID=1 on the same load. m73 adds the sysmem instance/RAMFC selector (gsp_phys_rmcall_gr_inst_sys; default 0 = FBMEM capture shape) for the A/B.
* STATE-CURRENT: 2026-10-07 ~01:15 snapshot - 0xc5c0 construct GREEN + ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | | | | | forwarded QMD enqueues/schedules; engine-core execution is the remaining wall (a) The TSG+share lane's compute-object construct returns success after a 10-entry VA-only booking promote books the server's per-VAS ctx-buffer maps (a mapped MAIN promote alone leaves them unbooked because the construct skips its own mapping once MAIN is initialized). (b) The forwarded guest QMD now enqueues and is scheduled: the missing real-client step was the lane-enable tail (CILP preemption mode, timeslice 0x800, device scheduling enable); the front-end deposit, the scheduler CWD entry (QMD id) and the engine-context load (VALID) all appear. Register ground truth from the working distribution driver during live CUDA plus the read-only sampler/analyzer are committed under tools/gr-regs/. Remaining wall: the GR engine core does not execute the scheduled QMD (no release written anywhere, no visible fault); ranked next moves in the local handoff. Host clean, GPU green, no reboots.
* vgsp: m70 - restore the capture-exact FBMEM instance/ramfc (revert the m62 ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | readback deviation) The m62 sysmem-chunk instance/ramfc made the server's writes host-readable (job done: FECS showed V7's instance loaded with VALID=1, TARGET=3 sysmem), but the captured real lane uses FBMEM slices and the GR engine core's context restore may require VIDMEM instance/RAMFC. Keep every fix (R1/E2/m68 prefetch/m69 win0) and restore the capture shape.
* vgsp: m69 - window-0 shadow pool for the QMD program/param pagesArthur Hanson Rasmusson5 days
| | | | | | | | | | | | | m68 proved the program page's shadow copy contains real SASS (SASS_version 0x75) and the prefetch pair is fixed, yet the engine still never completes and never writes its release anywhere - including a window-0 module sem. Best remaining suspect: the window-1 scratch VA range (PT chain installed by DMA_UPDATE_PDE_2 pdeIndex=1) has never been proven readable by the GR engine core, unlike the window-0 GPFIFO/PB/QMDWIN small-PT line. m69 plants 8 module pages at VAs 0x108000..0x10f000 (slots 0x108..0x10f, same 128 B PT fetch line, planted before first fetch like qmdwin), copies the resolved program/param page content into them at launch and rewrites the QMD pointer pairs there (param=32, program=48). Param: gsp_phys_rmcall_gr_shadow_win0.
* vgsp: m68 - rewrite the QMD program-prefetch pair to the shadow copy + dump ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | the program target m67 decoded the QMD (v02_03, SASS_version 0x75, block 64x1x1, grid 1x1x1) and showed the host rewrote PROGRAM_ADDRESS (w48/49) to a Tier-2 shadow copy but left PROGRAM_PREFETCH_ADDR (w8 = LO32(prefetch>>8), w31[8:0] = HI32(prefetch>>8)) pointing at the guest VA 0x7a90ed44c800 - unmapped in the execution VAS. Rewrite the prefetch pair to the same shadow copy when the prefetch lies in the shadowed page (preserving prefetch size and SASS_VERSION), and dump the program target's 16 instruction words in the post-mortem to prove the SASS landed.
* vgsp: m67 diagnostics - post-mortem page table, QMD w16..w31, shadow page ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | contents m66's forced sysmem fault buffers were refused by the server (ALLOC_MEMORY 0x1f, assert 0x5ab0214), so the engine-fault path stays FBMEM. Instead dump everything that decides whether the engine can execute the scheduled QMD: the resolved page table (guest VA -> HPA per QMD pointer), the QMD's w16..w31 (QMD/SASS version, thread dimensions, register count) and the first words of every Tier-2 shadow page the QMD's param/program pointers were rewritten to (proves whether the SASS/params actually landed there).
* vgsp: m66 - host-readable TSG fault buffers + post-mortem dumpArthur Hanson Rasmusson5 days
| | | | | | | | | m65 proved the scheduled QMD never writes its release anywhere (module sem stays 0, guest page stays 5) - the engine dies or is cancelled before completion. The TSG fault-method buffers (0xa06c010a) are the hardware's record of why; force them to host sysmem (the captured aperture, param gsp_phys_rmcall_faultbuf_sys=1) and dump both buffers' first 8 words in the post-mortem so an engine fault entry (faulting address/engine) is visible.
* vgsp: m64 fix - keep the module-sem fallback observable via sem_va (not ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | chunk DMA __va) The forward's poll already falls back to the SEM chunk kernel VA when qmd_rel_hpa is 0; the m64 change set qmd_rel_hpa to the chunk DMA address, whose __va() alias is not the chunk mapping, so the m64 poll read garbage. Revert to qmd_rel_hpa=0 for the module-release fallback and read the SEM chunk via sem_va in the post-mortem relw (plus the release word at rel_off in the release-page dump).
* vgsp: mode 35 m64 - forced module-sem release discriminant + fallback poll ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | | fix + post-mortem dumps m63 (E2 lane enable) got the forwarded QMD into SKED: CWD_TABLE_0 left the cold value, CWD_TABLE_1 carried the QMD id (0x1070), SKED_ACTIVITY fired, FECS_CURRENT_CTX showed V7's instance with VALID=1 - but the release write never landed (relw=5) and no engine fault is logged. m64 discriminates 'engine completed but the shadow release was lost' from 'engine never completed': param gsp_phys_rmcall_gr_rel_mod=1 forces QMD release0 to the module window-0 semaphore with a distinct payload (0x600df00d) and polls the SEM chunk. Also fixes the latent fallback (it set no poll source, so a module-sem release could never complete) and dumps the full QMD w2..w15 + the guest release page words in the post-mortem.
* tools: durable BAR0 GR register sampler + analyzer (gr-regs/)Arthur Hanson Rasmusson5 days
| | | | | | | | | | | reg_sampler.py: high-rate read-only MMIO sampler for the physical GPU's PGRAPH/FECS/SKED/PFIFO registers (FECS current-context valid + pointer, SKED CWD table occupancy/activity, GRFIFO, FE QMD-virt, PMC_ENABLE) with analyze_regs.py for value distributions and transition timelines. Recorded ground truth and register semantics in tools/gr-regs/README.md. Used to capture the live distro-driver CUDA reference (FECS VALID=1, CWD table 0x3f002000 while running) and to observe the ladder's forwarded launch (CWD entry + SKED processing after the mode-35 lane enable).
* vgsp: mode 35 m62 readback + m63 E2 lane-enable tailArthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | | m62 diagnostic: V7 instance/ramfc on host-visible sysmem chunks so the server's WFI-pointer/TARGET-bit writes are decodable (captured lane uses unreadable FBMEM slices); decode calls post-promotes and post-construct. m63 E2: send the real CUDA lane-enable tail after stage-4 schedules (R2 #1059 NV2080_CTRL_CMD_GR_SET_CTXSW_PREEMPTION_MODE flags=CILP_SET hChannelGroup=TSG cilp=CILP on the subdevice, #1061 NVA06C_CTRL_CMD_SET_TIMESLICE 0x800 on the TSG, #1063 NV01 device 0x00802009 enable=1). Ground truth: live real CUDA runs with FECS_CURRENT_CTX VALID=1; our m61 snapshots show V7's context never valid, and the SKED CWD table never leaves the cold value. Best-effort, mode-35 only.
* vgsp: mode 35 R1 - VA-only ctx-buffer booking promote on V7 (R2 #879 shape); ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | 0xc5c0 construct now returns 0x0 The construct's internal vaListFindVa (0x52cf9c0, KGC shared +0x370) needs the channel VAS present in the per-context ctx-buffer VA maps; F2's mapped MAIN promote only wrote the per-TSG ENGINE_CTX_DESCRIPTOR vaList. Send the capture's #879-shaped 10-entry VA-only promote {5,11,9,10,4,6,0,3,1,2} (va only, pa/size/attr/init/non all zero) after F2 and before the TURING_COMPUTE_A construct. m61: promote accepted status=0x0; TURING_COMPUTE_A on V7 alloc returns status=0x0 (hObject=0xcaf000a8); REAL GR SEM now fires on V7. Forwarded guest QMD still does not schedule (qmd_rel=5, relw=5).
* vgsp: ctxshare_force probe - keep the commit carrier A share-less (share on ↵Arthur Hanson Rasmusson5 days
| | | | V6 only; m59 A+share promote rejected)
* vgsp: ctxshare_force probe - share on the proven mode-31 execution channel ↵Arthur Hanson Rasmusson5 days
| | | | (V6+sibling A attach via params init)
* vgsp: mode 35 - revert the m56 SKIP flags (SKIP channels cannot promote); ↵Arthur Hanson Rasmusson5 days
| | | | keep the F3 KGR queries
* vgsp: mode 35 F3 - send the real client's KGR static ctx-buffer query set ↵Arthur Hanson Rasmusson5 days
| | | | before the channel batch (capture #388-402; a2a/a32 may prepare the server per-context tables the 0x57 companion needs)
* vgsp: mode 35 m56 probe - add SKIP_SCRUBBER|SKIP_CTXBUFFER_ALLOC to V7 flags ↵Arthur Hanson Rasmusson5 days
| | | | (V6-proven construct path while the share stays attached)
* vgsp: mode 35 F2c - hObjectError as a real class-0x40 FBMEM memory object ↵Arthur Hanson Rasmusson5 days
| | | | (registered list object failed the promote resolver lookup 0x57)
* vgsp: mode 35 F2b - register the USERD chunk as a memory object and pass ↵Arthur Hanson Rasmusson5 days
| | | | hUserdMemory[0] (server construct worker looked one up; 0x57 without it)
* vgsp: mode 35 F2 - MAIN mapped promote (pa+va, nonmapped=0) after the lane ↵Arthur Hanson Rasmusson5 days
| | | | promote to reach the per-buffer commit (sets pEngCtx+0x135; gate for the 0xc5c0 construct)
* vgsp: mode 35 - V7 gpFifoEntries 1024 (captured #825; one-variable fidelity ↵Arthur Hanson Rasmusson5 days
| | | | pass)
* vgsp: mode 35 - best-effort V7 construct + promote gate exemption (m50 ↵Arthur Hanson Rasmusson5 days
| | | | stage-3 -22 fix; lane continues to stage 4/forward)
* vgsp: mode 35 - V7 USERD index 4 (free fixed slot; index 3 collided with ↵Arthur Hanson Rasmusson5 days
| | | | golden D, NV_ERR_NO_MEMORY 0x51)
* vgsp: mode 35 - real-client user lane (TSG fault buffers, share, V7 channel, ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | | | | | | | | | | | | 3-entry PA-only promote, V7 execution swap; compile-verified, untested) Replays the decoded real 570.144 GSP client compute-context sequence on the ladder, additive to modes 0-34: - TSG fault-method buffers: one 0xa06c010a on the ladder TSG with two 0x2000 {base,size,alignment=1,addressSpace,cache} descriptors + zero bar2Addr words + numValidEntries=2; server FBMEM first, registered host sysmem fallback (capture order TSG -> faults -> share -> channel). - FERMI_CONTEXT_SHARE_A (0x9067) reuse of the mode-34 helper (ladder TSG, SHARED_MANAGEMENT VAS, flags SYNC -> VEID 0). - V7 channel 0xcaf000a0: class 0xc46f, TSG parent, hVASpace=0, hContextShare, captured flags 0x00201320 and internalFlags 0x1d, engineType 0, sysmem hObjectError/errorNotifierMem, FBMEM instance/ramfc, sysmem USERD. - One atomic 3-entry GPU_PROMOTE_CTX on V7 (MAIN/PM/PATCH, PA-only, physAttr 4, bInitialize=1, bNonmapped=1) before any 0xc5c0 construct. - TURING_COMPUTE_A (0xc5c0) on V7 after the accepted promote; execution channel swapped to V7 for stage 4 BIND/SCHEDULE/token/GR-sem and forwarding (V6 allocated but unscheduled; its promote suppressed). - Mode-35-only golden9 entry refresh: FECS_EVENT attr=5 with the ctx-window VA in the physAddr field, PRIV_ACCESS_MAP va=0/bNonmapped=1. - gr_promote clamp/param doc extended to 0..35.
* risc-v-gsp-rm-debugger: B5 two-task attach + aggregate-state decode + docs ↵Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | | 51/53 status - sim/libos_port.py: port-role model + two-task network (extintr handoff, cross-task send/reply, TASK_STATE_QUERY trap state) - sim/msgq_attach.py: image task discovery, bounded two-task schedule, second-task-frontier divergence fields (first ring poll still blocked on post-init resume + GSP_ARGUMENTS_CACHED handoff; no fabricated polls) - harness/state_decode.py: aggregate 'group: key=value' state parsing (20-gsp-phys-state-* dumps) + kv diff classification - tests: 127 green across the five observability modules - docs/51/53: status and changelog updates
* vgsp: mode 34 - add GOLDEN_CTXSHARE to the GR ctx FBMEM MAIN selector (m46 ↵Arthur Hanson Rasmusson5 days
| | | | sysmem MAIN hang class)
* vgsp: add read-only gsp-phys-reg-probe debugfs register snapshotArthur Hanson Rasmusson5 days
| | | | | | | | | | | | Add a read-only BAR0 register-liveness probe at /sys/kernel/debug/vgsp/gsp-phys-reg-probe that prints "name addr value" for the PMC chip-id/clock gate, PGRAPH status/fault, SKED/HWW and FECS/GPCCS falcon state, the front-end QMD virtual-window controls and the GSP context registers, followed by decoded field lines. Read-only (readl only); additive to gsp_phys_boot_debugfs_init(); no ladder logic changed. Used to distinguish a clock/power-gated engine from a halted or running one during a physical cycle.
* vgsp: mode 34 - context-share golden execution lane (compile-verified, untested)Arthur Hanson Rasmusson5 days
| | | | | | | | | | | | | Mode 34 allocates FERMI_CONTEXT_SHARE_A (0x9067) on the ladder TSG before the golden replay; the replay's golden channel A (0xcaf00054) attaches to the share with hVASpace=0 and keeps the captured unwired shape, runs its 9-entry promote and carries TURING_A (0xc597) plus a TURING_COMPUTE_A (0xc5c0, handle 0xcaf00090). V6 (0xcaf00034) attaches to the same share, constructs no class object of its own, and its FWCLIENT promote is suppressed; stage 4 and the forwarded launches run on V6 in A's shared VEID/subcontext. Default off; all paths gated by gsp_phys_rmcall_gr_promote=34. New pr_info cycle landmarks for the share alloc, A alloc/promote, A construct (rpc_result), V6 alloc and the instance/RAMFC decode. No hardware run.
* risc-v-gsp-rm-debugger: land docs 45-53 + harness/sim tool set with testsArthur Hanson Rasmusson5 days
| | | | | | | rm_capture (chunked decode), launch_audit, state_seed/state_decode, valprobe, rehost, contracts+run_contracts, host_traffic, gmmu_walk, msgq_attach, libos_port, log_decode, server_snapshot; doc index updates in the tool overview, operations pages and the repo README.
* STATE-CURRENT: 2026-10-06 evening snapshot - TSG commit lane + IQ2M deposit ↵Arthur Hanson Rasmusson5 days
| | | | proven, method space exhausted, structural levers next
* vgsp: mode 33 construct A object pre-promote (m43 post-promote 0x57)Arthur Hanson Rasmusson5 days
|
* vgsp: mode 33 - wired golden sibling A as execution channel ↵Arthur Hanson Rasmusson5 days
| | | | (compile-verified, untested)
* vgsp: SKED/FE readback + QMD w50..53 + two-step PCAS gate (m41 instrumentation)Arthur Hanson Rasmusson5 days
|
* vgsp: m37 pcas gate (window-only stock form) + QMD w48..50 post-mortemArthur Hanson Rasmusson5 days
|
* vgsp: preserve the pointer page offset in the shadow QMD rewrite (program ↵Arthur Hanson Rasmusson6 days
| | | | +0x800)
* vgsp: m32 rank-2 qmdwin - relocate the inline-QMD destination to a proven ↵Arthur Hanson Rasmusson6 days
| | | | ring-chunk page (compile-verified, untested)
* vgsp: mode 31 sibling A promote skips the one-shot FECS entry (m30: atomic 0x1f)Arthur Hanson Rasmusson6 days
|
* vgsp: mode 31 sibling A free ChID index (m29 decode: fixed index 3 collided ↵Arthur Hanson Rasmusson6 days
| | | | with D)
* vgsp: mode 31 sibling A userd memdesc (m28: TSG channel alloc rejected ↵Arthur Hanson Rasmusson6 days
| | | | without it)
* vgsp: mode 31 FBMEM ctx + pre-PDB aux prepare (m27: sysmem MAIN hung the ↵Arthur Hanson Rasmusson6 days
| | | | golden construct)
* vgsp: gate mode 31 on golden replay + physical backend (SA-CHK F1 fix)Arthur Hanson Rasmusson6 days
|
* vgsp: default the QMD-virt 0x29c pair off (m26 falsified it; non-vendor ↵Arthur Hanson Rasmusson6 days
| | | | without BASE)
* vgsp: mode 31 - D-golden-first TSG-sibling ordering (compile-verified, untested)Arthur Hanson Rasmusson6 days
|
* vgsp: m26 GR launch discriminator - rebuilt window (prelude off), QMD-virt ↵Arthur Hanson Rasmusson6 days
| | | | 0x29c, w63 sentinel
generated by cgit v1.2.3 (git 2.39.1) at 2026-10-12 08:48:36 +0000