summaryrefslogtreecommitdiffstats
path: root/tools
Commit message (Collapse)AuthorAge
* vgsp: eng89f - RT-ADMIT-BLOCK receipt; cap the mission waitArthur Hanson Rasmusson5 hours
| | | | | | | | The receipt prints state_push/rt_valid/rt0_first/rtp/mask/pchan/has_draw at the beef draw-synth reject, so the next boot names which of the five conjoined admission predicates failed. Runner: wait at most GZ_SECS+120 for mission-done (the mission itself writes it by GZ_SECS+30 when the guest is alive; a dead boot no longer costs 7.5 minutes).
* vgsp: eng89e - RT-SCAN candidate witness + streamed dmesg captureArthur Hanson Rasmusson5 hours
| | | | | | | | | | | | | c918-c921 had no RT-PERSIST and every beef draw was rejected on the missing colour-target bind, while c910 had the bind on the X/2D channel. RT-SCAN logs the last A/B/W/H candidates and seen flags for every beef channel push (bounded to 32) so the next boot answers whether the bind is absent from the push, filtered by the surface-class checks, or never authored. The batch runner also streams the kernel log with 'dmesg -w' per cycle and merges it into the per-cycle evidence; the ring wraps in under four minutes at this debug volume and had truncated c921's key receipts.
* vgsp: eng89c - fix the live GS map, draw anchor, prelude budget, RT persistenceArthur Hanson Rasmusson6 hours
| | | | | | | | | | | | | | | | | | | | | | | | | Four fixes from a code audit of eng89/eng89b, each of which could have made the maps=6 experiment unobservable or harmful: - Draw-move anchor: use the FIRST 0x3810 run only. The 247-word window also carries its own 0x3810 later; the old code moved the draw to the last one, i.e. behind the setup calls it must precede. Removed the post-scan promotion. - Prelude/stage budget: the raster-enable words (8) pushed the prelude toward the 96-word cap and could skip the whole stage-bind block (SPH-BIND-STAGE-SKIP reason=budget), hiding the GS bind. Array and gates grown to 128. - RT persistence: require B/W/H only (A optional, matching the existing first-valid check), store the channel and require it for admission, require a real draw marker (0x1618/0xd78/0x3910) in the window, and clear the state in svc_session_flush so a recycled channel cannot inherit a dead session's target. - GS live map: moved out of the SPH-AUTHOR copy branch and derived from the family page's actual VTG image at +0x900 (not the source record), so an overlap skip no longer makes maps=6 inert. New gs_addr=0 parameter set (GS at 0x780) keeps the GS header clear of the VTG copy. Test matrix: params-r1624-maps6-780.txt (maps=6, gs_addr=0).
* sdl_cap: capture-mode and file-ownership fixes for the GZDoom video runArthur Hanson Rasmusson6 hours
| | | | | | | | | | | | | | | | | | - GZCAP_SYNC=1: synchronous readback path for software GL (the async PBO+fence path never signals under Mesa llvmpipe, so 0 frames were recorded; the GPU path keeps the async path). - GZCAP_READBUF=back: read GL_BACK on a double-buffered X11 window (Xvfb); the default GL_FRONT is correct only for the single-buffered GPU pbuffer. Without it every Xvfb frame was black. - File gate: only an SDL renderer process opens the capture, and an existing non-empty capture is appended, never truncated. The old 'wb' open in every LD_PRELOAD child turned a 288-frame capture into a 4108-byte file; a helper without SDL also opened it via the glReadPixels fallback. - Log the read buffer in the async arm line. Validated by the 2026-11-16 GZDoom video runs: 2200-frame captures, clean_end=1, corrupt=0, 30 fps encodes, delivered via files.vgpu.io.
* vgsp: eng89b - persist the colour-target bind across pushesArthur Hanson Rasmusson8 hours
| | | | | | | | | | | | Most beef draw pushes carry no colour-target bind of their own (the client binds the target once per context/target switch in an earlier state push), so the per-window admission refused the real frame pushes on most boots ('beef draw-synth: no valid last colour-target bind', the shallow-boot lottery). Track the last complete, plausible bind seen on a trusted push (same surface-class validity as the first-bind check; an invalid later write never overwrites a valid state) and admit a beef draw window on it: RT-PERSIST + '3D mark admitted (persisted colour-target bind)' receipts. Knob sema_gl_win_rt_persist, default 1.
* vgsp: eng89 - live-derived GS map, draw-move anchor, raster enables, async ↵Arthur Hanson Rasmusson8 hours
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | capture Kernel (deterministic fixes, each with an A/B knob): - sema_gl_sph_gs_maps=6: derive the whole 216-bit GS IMAP/OMAP blocks from the bound VTG image's OMAP and the PS image's IMAP at authoring time (SPH-GS-MAP receipt; SPH-GS-SKIP names ps-invalid/gs-invalid/ vtg-overlap/vtg-short). maps=4 stays as the fallback. - DS-MAP census line: dump stage-4/5 w5/w10/w13/w17 next to DS-IMAGE so the fetched maps are visible without a new probe. - MME pack carrier: reject maxa > 4096 (the IR pack array) instead of 64K, with MME-PACK-REJECT reason=bound. - MME-DRAW-MOVE: anchor the slot-34 move after a 0x3810 VERTEX_STREAM run. c848 moved CALL(34) to 0x204, ahead of the prepended stream bind, so the 8x3 fetch used stale stream state. - sema_gl_raster_enable=1: emit SET_RASTER_ENABLE=1 and SET_GLOBAL_RENDER_ENABLE MODE_TRUE in the raster prelude (fresh replay contexts may carry 0 for both, discarding every fragment). Guest tooling (unblocks the render loop and capture): - sdl_cap.c: asynchronous PBO+fence capture with a 5 s abandonment bound; no glFinish/blocking readback (c899 wedged gzdoom in an uninterruptible nv ioctl); clean sentinel from a destructor. - gz_pbuf.c: request depth 24/stencil 8, log GL_DEPTH_BITS, and swap with glFlush only. - mission-gz.sh: gl_frames probe off by default; GZDoom launched detached with a bounded wait, per-attempt X restart and retry; capture in /dev/shm with GZCAP_MAXF. - gzdoom_pbuf_run.sh: gl_pipeline_depth=2, gl_finishbeforeswap=0, GZCAP_MAXF default, rc-file support for the detached run. - run_cycles_long.sh: durable multi-cycle runner (the previous one lived in /tmp and was lost on reboot); pushes tools, runs the mission, grabs dmesg + guest logs + capture per cycle, stops on pixels. Test matrix: params-r1624-maps{4,6}.txt.
* tools: GS-map A/B - per-boot maps=0 (short 2-frame draw-carrying cycles)Arthur Hanson Rasmusson12 hours
|
* vgsp: eng85 - owner-channel MME pack continuation ↵Arthur Hanson Rasmusson12 hours
| | | | | | | | | | | | | | | | | | (sema_gl_mme_pack_carry_client) CONT.539: c858's split pack landed on the client channel h=0x1000013 and the continuation never armed because gsp_phys_gr_mme_carry_arm() required (h & 0xfffff000)==0xbeef0000. c848 only worked because the same bytes landed on h=0xbeef0100. New knob sema_gl_mme_pack_carry_client (default 0) relaxes the arm and take gates to the split's own owner channel; the synthetic windowless LOAD-ONLY launch still goes through that owner's forwarding candidate (the pump locates it by h_object), and the builder reads the global pack cursor so the continuation bytes are identical. The saved-window release carrier stays beef-only; its MME-CARRY-ARM mode=release fires once the pack becomes resident (the owner completion clears the pack-not-resident gate on the next pass). Params-r1624 enables it.
* tools: dedupe the raster-prelude param (it was already inline =1)Arthur Hanson Rasmusson13 hours
| | | | | | | The previous commit appended a duplicate; the inline line-1 params already carried sema_gl_raster_prelude=1, so c848 ran WITH the raster prelude and still saw the SPH18 DS with no stores - the scissor/depth is not the remaining gate; the GS SPH18 is.
* tools: enable the raster prelude (CT_WRITE + depth/stencil/scissor disables)Arthur Hanson Rasmusson13 hours
| | | | | | | | | | | Plan B from CONT.538: the 247 window carries 0x12cc/0x12e8/0x1380=0 (SET_DEPTH_TEST / SET_DEPTH_WRITE / SET_STENCIL_TEST, per the code comment at the knob) and no SET_CT_WRITE / SET_SCISSOR_ENABLE - those are client channel state. On a replayed 3D DRAW_IAB the replay channel keeps hardware defaults, so every fragment can be discarded (CT_WRITE=0). Enable the existing sema_gl_raster_prelude remedy (CT_WRITE(0..7)=0x1111, depth/stencil disable, SCISSOR_ENABLE(0)) alongside gs_img=1/maps=2/TCS-off.
* tools: GS-map A/B step 2 - sema_gl_sph_gs_maps=2 (PS-exact IMAP)Arthur Hanson Rasmusson13 hours
| | | | | | | | c850-c853 (maps=0, pass-through): the 247-window-class boot did not reproduce in these cycles (c850 no release, c851 poison 0xbadf1201, c852 a 730-page upload burst with no DRAW_IAB release lines), so the SPH18 read needs a maps=0 247 boot that did not occur. Step 2 of the A/B per the plan: maps=2 (IMAP PS-exact) with gs_img=1 and TCS off.
* tools: GS-map A/B step 1 - sema_gl_sph_gs_maps=0 (pass-through)Arthur Hanson Rasmusson13 hours
| | | | | | | | c848: with the correct VTG VB base the DRAW_IAB runs and the hardware DS now flags SPH18 (GS check2): DS-FAST ds 80000000->81040000. The header-only GS SPH (gs_img=1, family+0xe80) with maps=4 (the r1569 variant) still fails the GS attribute-map check. Step 1 of the A/B: maps=0 (pass-through IMAP/OMAP). Keep TCS off (stage_disable=0x04).
* vgsp: eng75 - A/B: point the SURF prelude/RT0 at the big-surface aliasArthur Hanson Rasmusson16 hours
| | | | | | | | | | | | | | c824/c825: the release RT0/RT1 target is 0xa000000 (the data-rec bounce base from gsp_phys_gr_surf_launch_target's rec-over-alias preference) while the aliased 1920x1080 X-screen surface is 0x15d0000 (2025 pages). The changed pages (0x120700000/0x120704000/0x120705000) are inside the screen range but the draw's RT offsets are computed against the bounce base. sema_gl_surf_alias_pref (default 0; params=1): after the SURF prelude patch, rewrite its target words to gsp_phys_gr_surf[].alias so the prelude and the RT0 copy (r1483) both name the contiguous surface alias. SURF-ALIAS-PREF receipt.
* tools: revert sema_gl_raster_extra (poisoned before the release in c794/c829)Arthur Hanson Rasmusson17 hours
| | | | | | | The raster-kill A/B never reached a release: c794 and c829 both hit the badf1201 held-window poison before the release. Revert the param to the known-good TCS-off + vs_autobind configuration; the raster_extra hypothesis stays open for a clean-boot A/B.
* tools: enable sema_gl_raster_extra for the raster-kill A/B (eng74 build)Arthur Hanson Rasmusson17 hours
| | | | | | | | The release now binds VS0/SZ0 (scanned float2 vertex data), viewport and RT, runs the DRAW_IAB, but no surface page changes. The neutral blend/alpha/cull/point/ZCULL state is the untested fragment-kill lever (c794 poisoned before the release); re-enable it in params for the c828+ A/B.
* vgsp: eng74 - dump the scanned VS candidate and witness the surface alias pagesArthur Hanson Rasmusson17 hours
| | | | | | | | | | | | | | 1. VS-BLOB: on a VS-SCAN candidate, print the 16 words at the winning block and the DRAW range (starts 0,3,..,21 * stride 20 + 8), so the CB-page heuristic candidate can be validated/rejected against the Mesa DRAW_IAB shape. 2. Surface alias WIT: gsp_phys_gr_surface_alias_locked records every RT guest page (VA+HPA) it maps in a persistent table; the launch WIT capture notes them, so a render-target store through the 0xa/0xc alias becomes a GUEST-WIT changed line. This fixes the eng73 gap (the surface alias does not use the pair alias cache). params: sema_gl_wit_shown=40 so the RT page is not hidden by the 4-line budget.
* vgsp: eng71 - scan the tracked data pages for the vertex payload and bind VS0Arthur Hanson Rasmusson23 hours
| | | | | | | | | | | | | | | | c812/c813: the 151-word DRAW-window release has VS0=VS1=VS3=0 and SZ0=SZ1=SZ3=0; the DRAW_IAB emits its 8x3-vertex draws (VA=0xd74=0x15) against no vertex stream, so nothing rasterizes. The client's vertex payload is a 24-vertex, 20-byte-stride float2 buffer (FORMAT 0x1014, ATTR(0) float2 offset 0) written into the launch's tracked data pages. sema_gl_vs_autobind (0=off, 1=scan+log, 2=bind; params=2): scan the 0x120400000..0x120800000 data pages for a 512-byte block of 24 plausible float2 vertices (score>=8 nice values), then prepend to the saved release window: VS0 location [fmt=0x1014, upper, lower=reloc_va +off], and the Turing stream SIZE pair (0x600<-0, 0x604<-0x100000). VS-SCAN/MME-VS-BIND/MME-VS-SIZE receipts; the starts 0..21 x stride 20 resolve inside the 1 MB bound.
* vgsp: eng67 - synthesize a full-RT viewport for replayed beef 3D windowsArthur Hanson Rasmusson24 hours
| | | | | | | | | | | | | | | | | c797 (engine ef2e68b9) DRAW-STATE on the release launch: RT0/RT1 = alias 0xa000000, 1920x1080, fmt 0xe6; VS0 address 0x1e305dc bound; DRAW_IAB emitted its last vertex-array start (0xd74=0x15); but the viewport SCALE/OFFSET methods 0xa00..0xa14 read 0 on the replay context (they are client channel state the per-frame window never carries). Every vertex maps to (0,0), so the 8x3-vertex draws rasterize nothing and the 1025 tracked RT pages stay 0. sema_gl_viewport (default 0; params=1) emits a full-color-target viewport before beef 3D windows: SCALE_X=+W/2, SCALE_Y=-H/2, SCALE_Z=0.5, OFFSET_X=W/2, OFFSET_Y=H/2, OFFSET_Z=0.5 (IEEE bits computed without FP; W/H from the RT0 method shadow, fallback 1920x1080). VIEWPORT receipt carries the emitted bit patterns.
* vgsp: eng65 - allow per-stage SPH disable on the all-slots bind boot ↵Arthur Hanson Rasmusson25 hours
| | | | | | | | | | | | | | | | | (TCS-off DS A/B) c788 achieved DRAW_IAB (MME-FAST macro-status=00122266 mpc=614 mac=0x22 run=1 via MME-DRAW-MOVE) but the draw latched DS 0x84000420 (SPH5 VSB c1, SPH10 TCS c2, M_PIPE_STAGE TI) and stores stayed 0 (NOWRITE-CONFIRMED wrote=0). The DS-ESR post-clear=84000420 then the retire reads ds=80000000, so the pending validation error is the draw's. The per-stage disable mask was only honoured with sema_gl_sph_bind=0, so the all-slots boot could not disable TCS while keeping the window's own VSB bind and the other synth slots. Read the mask unconditionally; default 0 keeps the emitted bytes identical. params-r1624 sets sema_gl_sph_stage_disable=0x04 (TCS disable record 0x2080<-0x20, synth j2 bind skipped) for the next A/B.
* vgsp: eng63 - held-CALL target census, DRAW-window preference, and ↵Arthur Hanson Rasmusson26 hours
| | | | | | | | | | | | | | | | | | | | | | | | release-launch SA re-arm c776 proved the saved-window release replay carries the slot-34 CALL_MME_MACRO run (MME-WINRUN off=340 op=5 cnt=10 mthd=3910) but the macros ran 0x33/0x0/0x39: the release launch sets emit_prelude=0, and the client capture had no slot 34 (c774 fill published golden entry 0x265 host-side only), so the stale engine SA[34] resolved the call to IR 0 (mac=0x0). - MME-CALL-CENSUS/MME-CALL-TARGET: decode the held window's CALL runs with the hold/drop run grammar (op 1/3 walk method+4k, op 5 only the header method, op 4 one method) and print targets + slot34 with the client/golden/used entry. - release_save: among DRAW_IAB-bearing windows prefer the smaller raw DRAW stream (324 B/81 words, the c716 mac=0x22 shape) over the 728 B state window; keep=draw-win receipt. - sema_gl_mme_release_sa_arm (default 0; params-r1624 enables it): run the SA re-arm + golden fill on the release launch so CALL_MME_MACRO(34) points at the golden DRAW_IAB body (IR 0x265). Pack-carry/release receipts unchanged; release carrier still default 0.
* tools/guest-diag: tag BGRA capture records as GZF2 fmt 33Arthur Hanson Rasmusson26 hours
| | | | | | | | | | | | | | | sdl_cap.c wrote the same 32 in the GZF2 record format field for every capture path, so gzf2_video.py's auto mode decoded ARGB8888/X-surface frames (BGRA byte order on little-endian) as RGBA and swapped red and blue. Make the field the documented pixel-order tag: 32 = RGBA8 from the GL swap path (glReadPixels GL_RGBA), 33 = BGRA8 from SDL_RenderReadPixels(ARGB8888) and X window surfaces; xgrab.c tags its ZPixmap BGRA records 33 as well. gzf2_video.py continues to accept both tags (and old all-32 captures via --pix-fmt bgra), checks ffmpeg/ffprobe before indexing, and keeps the final resampled endpoint so a 90-frame 60 fps capture encodes as 90 frames instead of 88.
* vgsp: eng62 - fill missing golden SA entries (slot 34 DRAW_IAB = IR 0x265), ↵Arthur Hanson Rasmusson26 hours
| | | | | | | | | | | | | | | | | | | | default off The golden overlay writes all 55 slot bodies, but the CALL_MME_MACRO(34) DRAW_IAB run targets SA[34]; the client's captured SA table only covered slots 0-11 (c772), so slot 34 resolved to IR 0 (the slot-0 body) and the macro never produced mac=0x22. Add sema_gl_mme_sa_golden_fill (bool, 0): for every slot whose client SA entry is missing/zero and whose golden body exists (kernel/golden-mme-tu104.h golden_mme_tu104_sa[64]), set the SA entry to the golden body's IR entry (slot 34 = 0x265, 75 words) and mark it present. Nonzero client entries are never overwritten. Fill runs in the golden overlay, in the submit path before the stub/call-drop walk, and in the SA re-arm (the release-carrier path); the release path re-fetches and emits the filled 0x11c pairs. New MME-GOLDEN sa-fill/sa-census receipts. c774 proves the fill: `MME-GOLDEN sa-fill slot=34 entry=0x265 (client=missing)`. Enable in params-r1624. Build rc 0; the mac=0x22 validation needs a c772-class release boot.
* tools: enable the pack continuation and saved-window release carriers in ↵Arthur Hanson Rasmusson26 hours
| | | | params-r1624 (c772: identity CARRY-FIRE mode=release -> synthetic push 0x6d6d6500 -> REARM gen=5 -> DS 0x84000420)
* vgsp: eng59 - saved-window release carrier for the held MME CALL runs ↵Arthur Hanson Rasmusson26 hours
| | | | | | | | | | | | | | | | | | | | | | | | (default off) When a 324 B draw window holds its CALL runs while the 2799-word pack is incomplete, the pack can complete later (X lane or a 728 B window) but the next client launch that would release the held calls is a per-frame lottery (c756: MME-CALL-HOLD 18, pack complete, no next launch -> no REARM/mac=0x22). Save the held window at MME-CALL-HOLD (raw pre-relocation stream + the launch capture fields) into module memory. When the pack is complete and resident and no client launch consumes the release within sema_gl_mme_pack_release_ms, re-submit the saved capture through the normal fill/build path with the held CALL runs KEPT (mme_hold_calls=false), no prelude emission, and gr_synthetic/no guest release. The released CALL(34) runs DRAW_IAB against the resident pack, the shape c716 proved. New: sema_gl_mme_pack_release (bool, 0) / _ms (uint, 100); MME-CARRY-SAVE / ARM/FIRE/COMPLETE/CANCEL/ABORT mode=release receipts. Beef-only, one fire per pack completion, fail-closed on context/handle changes or launch errors. The existing pack-continuation carrier is unchanged with its knob off. Build rc 0; validation pending.
* tools: enable sema_gl_sph_bind_pair_safe=1 in params-r1624 (synthesized ↵Arthur Hanson Rasmusson27 hours
| | | | stage TYPE/COUNT before the address pairs; DS A/B)
* vgsp: eng55 - VTG SPH authoring at family+0x900, DDX ring-head tracker ↵Arthur Hanson Rasmusson29 hours
| | | | | | | | | | | | | | | | | | | | | | | | | | decode, MME pack carrier, and the pump atomic-sleep hoist - gsp_phys_booter.c: sema_gl_sph_vtg_auth (default 1) authors the client's live VTG SPH image at family+0x900 and binds VSA/VSB there; new SPH-AUTHOR / SPH-ALIAS-auth receipts and a DS-IMAGE stage census at the DS latch (stage-start w0 + code word through the pair cache). - gsp_phys_booter.c: sema_gl_mme_pack_carry (default 0) + _ms (default 100) host-initiated windowless continuation carrier for a split MME pack; MME-CARRY-ARM/FIRE/COMPLETE/CANCEL/ABORT receipts, beef-only, bounded. - gsp_sema_service.c: sema_ddx_tracker_auth (default 0) ring-head decode for the DDX channel when the USERD is missing/reset (guest-authored C36F release applied verbatim); sema_gr_scan_top default raised to 0x300000000 for the 12 GiB campaign guest. - gsp_sema_service.c: hoist the r707e VAS candidate verify out of svc.chan_lock (its vfio_dma_rw path can sleep) and add in_atomic guards to svc_read/svc_write; fixes the gsp-sema-svc "scheduling while atomic" pump stall that lost the marked draw-window launch. - tools: enable sema_ddx_tracker_auth=1 in params-r1624; use timeout -k in the guest GL/GZDoom wrappers so a wedged GPU wait cannot hang a cycle. Validation: c741/c743 boots (VTG author byte readback, cross-lane and beef pack completion + REARM, DS-IMAGE census) and the c743 DS-FAST chain; A/B for the carrier and the tracker decode is still open.
* vgsp: eng51 - emit the SPH-BIND stage block (budget fix), admit RT0-bearing ↵Arthur Hanson Rasmusson30 hours
| | | | | | | | | | | | | | | | | | | | | | | draw-synth windows, preserve the last beef push, and default the DS stage-image A/B safe - gsp_phys_booter.c: the synthesized SPH-BIND stage-block guard double-counted the already-emitted raster words (101 > 96), silently skipping j0/j2/j4/j5; pre=29 -> pre=84 and the DS stage VAs populate. Add the SPH-BIND-STAGE-SKIP receipt. - gsp_sema_service.c: sema_gl_win_rt0_admit (default 1) admits a beef draw-synth window whose FIRST colour-target write is a usable surface-class bind (RT0-FIRST-MISS witness); preserve the most recent beef push (>=256 B) for the gsp-phys-last-push debugfs dump; skip the non-RAM windows in the linear ring scan; fix the MME shadow-RAM index shift to (mthd >> 2) & 0xfff. - gsp_phys_booter.c: sema_gl_sph_vtg600 (default 0) and sema_gl_sph_vtg_j1 (default 0) are the stage-image A/B: binding family+0x600 poisons the DS (the engine-visible alias shadow there is the client's SASS upload), so keep the historical +0x900 zero page until a real VTG SPH is authored at an engine-visible VA. - tools/guest-diag/params-r1624.txt: enable sema_gl_win_rt0_admit. - wiki/Project-Status.md: 2026-11-15 status (MME chain completes and executes DRAW_IAB; DS stage image is the named gate).
* tools: enable sema_mme_prelude_cap_any=1 in params-r1624 (eng48: X-lane ↵Arthur Hanson Rasmusson43 hours
| | | | prelude feed for the indirect replay chain; A/B pending)
* tools: enable sema_gl_mme_cb_alias=1 in params-r1624 (eng45: fixed-CB 7-page ↵Arthur Hanson Rasmusson46 hours
| | | | alias for the post-REARM macro path; A/B pending)
* tools: enable sema_gl_mme_keep_done_across_recycle=1 in params-r1624 (eng43: ↵Arthur Hanson Rasmusson47 hours
| | | | keep the MME pack completion record + cursor across the beef owner channel re-register so the first post-recycle prelude launch is non-emitting and MME-PACK-REARM fires; A/B pending)
* tools: enable sema_gl_mme_pack_keep_gen=1 in params-r1624 (eng39: the beef ↵Arthur Hanson Rasmusson2 days
| | | | multi-part pack restarts on prelude-generation churn between parts; keep the packed cursor across churn when golden_force=1; A/B pending)
* tools: enable sema_gl_mme_partial_keep_window=1 in params-r1624 (eng36/37: ↵Arthur Hanson Rasmusson2 days
| | | | let partial MME pack parts keep their windows so the multi-part beef program can complete and promote live_gen; A/B pending)
* tools: enable sema_gl_rt0_bind=1 in params-r1624 (eng34: the client clear ↵Arthur Hanson Rasmusson2 days
| | | | targets RT0 - MRT_SELECT=0 in CLEAR_SURFACE 0x3c - while the window binds RT1; bind RT0 to the same surface so the clear has a target)
* tools: add sema_gr_grace_ms=500 to params-r1624 (eng28/eng29: engine contact ↵Arthur Hanson Rasmusson3 days
| | | | for the beef state-push launches requires the shorter MME grace; 8000 showed no contact)
* tools: add sema_gl_draw_synth=1 to params-r1624 (eng23: required for the ↵Arthur Hanson Rasmusson3 days
| | | | direct-GL draw-section capture path)
* tools: add sema_gr_fb_push=1 to params-r1624 (eng21: required for the ↵Arthur Hanson Rasmusson3 days
| | | | FB-shadow push rescue at insmod)
* tools: cycle-r1780.sh arms the GR lane per boot (rm-call ladder + guest-ram ↵Arthur Hanson Rasmusson4 days
| | | | | | | | | | | | | | | | | | | | | | activation) Post-reboot cycles lost the pre-reboot 'arm the GR lane' steps, so gsp_phys_backend_gr_ready() stayed false (rmcall_gr_exec_ok=false) and every captured GL section died SILENTLY at svc_gr_request's first gate (c198: work_gr req=73 fallback=73 ok=0 refused=73 submitted=0 exec_ok=0; an ftrace run counted 2282 silent svc_gr_request calls). After 'guest agent up' the cycle now runs, with warnings only (never fails the cycle): echo 5; echo 3; echo 4 > gsp-phys-rm-call (order matters; 4 alone fails by design) echo '<mdev> /dev/shm/vgpu-guest-ram 0x80000000 0x0 0x300000000' > gsp-phys-guest-ram and logs both to <tag>-ladder.txt. Validated c203: 7x 'GR LAUNCH submitted' + 5x 'GUEST GR LAUNCH OK' from the captured GL sections (zero ever before), exec_ok=1, work_gr ok=4 backend_ok=4. Residual: gl_frames still black - GR-DEC n_data=0 dropped=24 (the section's data window resolves empty) and 'sema-grce: owner-vas h=0xbeef0100 ... dst=0x120700000 unmapped; cross-VAS walk refused (client-private page)' for the client copy-out operand - the old n_data/dstpend frontier, now with the forward live.
* vgsp: X-DMA wall witness for 0x1000013; add params-r1624.txt (rich bring-up set)Arthur Hanson Rasmusson4 days
| | | | | | | | | | | | | | | | One rate-limited (0.5 s) sema-xchan line per pass for the X DDX channel: rrc/uok/upa/uas/put/get/last/ring_pa/entry0 - names the decode-gate state independently of the shared userdp budget. Diagnostic only, no behaviour change. params-r1624.txt is the rich r1624 insmod set as a durable tools/guest-diag file (INSMOD_PARAMS=tools/guest-diag/params-r1624.txt). Context (c130/c131 with the rich set): the DDX DMA test now PASSES on most attempts (tracker release decoded + delivered); the remaining gap is the USERD speculative-latch lifetime (a latch that delivered the test kick is REJECTED 15 s later with no PUT advance; the next generation then adopts a stale VRAM block, put=2 get=0, and the retry window closes) plus a later 'Push buffer object allocation failed: 0x51 NV_ERR_NO_MEMORY' (emulated heap accounting; 1872 MiB free).
* tools: fix cycle-r1780.sh env-var comment (INSMOD_PARAMS is what the code reads)Arthur Hanson Rasmusson4 days
|
* tools: mission-gz guest loop (X retry -> gl_frames probe -> GZDoom pbuffer ↵Arthur Hanson Rasmusson4 days
| | | | | | | | | | | capture); push/verify fixes mission-gz.sh runs the end-to-end guest pass in one shot (X bring-up with ScreenInit retries, GPU GL probe via gl_frames, GZDoom offscreen + gz_pbuf + sdl_cap under the tested wrapper, /tmp/mission-done result flag). push_gl_tools.sh runs vgpu_vm.py under sudo (QGA needs root); gl_verify.sh uses 'pkill -x Xorg' (the -f pattern self-matches the shell when the command line contains the Xorg invocation).
* vgsp: stop fabricating 0xFFFF into the nvPush error notifier; add r1780 GL ↵Arthur Hanson Rasmusson4 days
| | | | | | | | | | | | | | | | | | | | | ops tooling The uncommitted keep-alive change wrote 0xFFFF into slot 0's status field (u16 at notifier+0x0e) on the X DDX / GLX kick-idle channel families. Ground truth (570.144 reference sources + stock nvidia_drv.so disassembly): slot 0 of an nvPush notifier block is the ERROR notifier; nvPushCheckChannelError reads that status and 0xFFFF aborts every nvPushWaitForNotifier/idle wait as a channel error. There is no pb_kickIfIdle in 570.144 - the DDX DMA-idle test reads the progress-tracker semaphore word, not this slot. Leave slot 0 untouched; keep the 0x8000->0 completion ack for the remaining slots and the r864 0xFFFF/0x8000 completion on the RC-watchdog/beef families. Correct the CONT.408/409 comments accordingly. New host/guest tooling: gpa.py (QMP gva2gpa), tick_gen.py (guest-RM timer BO tick), guest_mode.sh (shared nvClip modeNum reader), gl_verify.sh (X/GLX bring-up with ScreenInit-lottery retries), push_gl_tools.sh, the gzdoom_pbuf_run.sh guest recipe and the test_tri SDL2 harness validation program; ignore tools/guest-diag/build/.
* tools: fix r1780 cycle prerequisites and add SDL GLX-pbuffer shimArthur Hanson Rasmusson4 days
| | | | | | | | | | | | | - cycle-r1780.sh: load vfio modules one per modprobe (the multi-module form was silently treating the extra names as parameters and never loading mdev); auto-detect the vgpu mdev type and prefer the 2 GiB type used by the campaign. - sdl_cap.c: gate capture-file creation to processes that can actually read GL pixels (a child was truncating the capture), and log the capture pid/pointers. - gz_pbuf.c: LD_PRELOAD shim that gives an SDL2 GL client a GLX pbuffer context on the guest's NVIDIA X server (the proven gl_frames path), with SDL_GL_GetDrawableSize/SwapWindow interception.
* vgsp: direct-GL ring/push rescue, VAS/pdb scanners and PTIMER tick; r1780 ↵Arthur Hanson Rasmusson4 days
| | | | cycle tooling
* tools/debug: add read-only GMMU/pdb scanners for live guest RAMArthur Hanson Rasmusson5 days
| | | | | | | | pdb_scan_gmmu walks the GP10X/VER2 GMMU page-table format (PD3/PD2/PD1/ PD0/PT, 16-byte dual PD0 entries, sys/vidmem apertures) and pdb_scan is the x86-64 index cross-check. Both map the QEMU pc.ram file correctly for the 2 GiB low + high-RAM q35 layout and are strictly read-only. Used to prove the ring page/VA and pdb chains in CONT.435/436.
* vgsp: all-ones scrub release for registered waits; walk-page registration; ↵Arthur Hanson Rasmusson6 days
| | | | | | | | | | | | | | | | | | | | | GL frame publisher (CONT.416-417) - gsp_sema_service: merge a scanner registration arriving after the stash record instead of dropping it (a dropped registration let the next authoring pass write the blocking pair into the page the guest was polling, so the wait never ended); author the finish word all-ones for every registered record while the sema word stays put-based once real submissions were observed (CONT.416/417). - scrub_pin_qmp (host scanner): accept an unstable-but-live wait page instead of skipping it, and register the walk-resolved scrubber channel page - first the walk summary, then the per-VAS kernel row (h=0xc) when the summary path fails - so the release is armed before the guest polls (r1762/r1764 evidence). - guest-diag: add gl_frames, the direct-GL (GLX pbuffer) frame publisher; with it the stack produced the first non-black GPU-rendered frames (40/40, 640x480, animated) through pbuffer -> sysmem -> ivshmem -> host frame_reader. - gsp_rm_emulation: log the display-shim request words for triage.
* wiki: 2026-11-10 afternoon refresh - first real GPU readback; ↵Arthur Hanson Rasmusson6 days
| | | | | | | | | | | direct-GL/window walls Refresh STATE-CURRENT, the Main Page and the status/frontier pages: the DDX 3D replay executes and a guest pbuffer glClear+glReadPixels returns a red pixel (ff0000ff); the RM write-lock holder (Xorg in the DDX scrub wait) is fixed in df6e71bb. The direct-GL client channel still emits only setup/notify kicks (ops_runs=0), a window draw wedges X, and X startup/RM stability plus the DDX 4 GB sysmem allocation remain. Published to open-iov.org.
* vgsp: USERD index/alias resolution, DDX kick-idle fix, completion-slot ↵Arthur Hanson Rasmusson6 days
| | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | | authorship (CONT.403-412) Ten debugging rounds against the direct-GL channel, each fixing the wall that blocked the previous one: - USERD index: honour USERD_INDEX_VALUE/PAGE_VALUE from NVOS04 flags (X idx=3, GL idx=4) instead of always reading the block at base+0. This fixed the X "Failed to initialize DMA" wall. - USERD alias: learn the BAR1-alias bias from the first ring-validated FB latch (wire 0x80600 -> live 0x910000) and prefer alias/wire-page candidates before falling back to the RAM scan, which previously adopted another channel's control page. - USERD latch: keep a ring-validated kick-family block across a transient put=0 instead of dropping it (bounded, per-channel log). - VAS alias: DUP_OBJECT copies pdb/entries/ap/verified so hVASpace 0xbfef0001 resolves to 0x10005 and its gpfifo VA stops re-resolving to a bogus FB PA. - Short-kick NOTIFY: complete a kick that has no armed class-2D target (release + event, no write) so the client proceeds past setup. - DDX kick-idle: slot 0 of the 0x01xxxxxx family is the pb_kickIfIdle gate and 0xFFFF is its IDLE value; the keepalive no longer zeroes it. Removes the GR-STALL-stale-wedge on the X channel. - Completion slots: register a per-channel completion on every successful kick and reuse it when a NOTIFY has no per-push SET_NOTIFY; prefer the channel's notifier page over the VA walk. - Empty/no-op submit: author the completion even when there is no push to replay, so a synchronous GL submit does not wait forever. - Scrub records: multi-record per guest, stash-first lookup, registered PA is authoritative against the GPU-VAS walk, scanner-only records author the proven 0xffffffff/0xffffffff pair. - GL attachment: accept a draw run whose own subchannel is the engine subchannel the channel uses (bind is subch 0, draws on subch 3), not only the bind subchannel. Measured: glxgears 427 -> 526 FPS sustained with no GR stall; X binds and renders its 2D path; 3D draw capture on the GL channel still does not occur (see CONT.412: the GL thread blocks on the NVRM RM write lock before it reaches any ioctl). Adds tools/guest-diag/scrub_pin_qmp.py to register guest channel-buffer vmap pages as scrub records from the host.
* wiki: 2026-11-10 morning refresh - X reliable, GR timeouts fixed; ↵Arthur Hanson Rasmusson6 days
| | | | | | | | | | | | beef-ring/CB/RT walls Refresh STATE-CURRENT, the Main Page and the status/frontier pages: ebf3130f fixes the X DMA-init path and flips the GR pair-close/pair-safe replay fixes default ON (X green on attempt 1 in three consecutive cycles, backend_timeout=0, draws retire in 3-2400 ms); bb802909 is committed. The replayed draw still writes 0 pages; the beef GR ring resolution, the fixed-CB image's zero 0x80 MVP block and the render-target bind are the named walls. Published to open-iov.org.
* wiki: 2026-11-10 status refresh - guest GL draws execute on the physical GPUArthur Hanson Rasmusson7 days
| | | | | | | | | | Refresh STATE-CURRENT, the Main Page and the status/frontier pages: the GSP event-IRQ fix completes swaps; the 2D path is green end-to-end; the guest's real GL draws now forward and execute on the physical GPU (work_gr backend_ok=9); the draw writes 0 pages because its constant-buffer (MVP) page is unresolved and forced to the seed page; the MME front-end defer, GR stale-wedge and the X DDX get-word/notifier completion remain. Published to open-iov.org.
* wiki: 2026-11-09 evening refresh 2 - forced GLX reaches glcore; windowed GL ↵Arthur Hanson Rasmusson7 days
| | | | | | | | | | | | waits on kernel kick completion Refresh STATE-CURRENT, the Main Page and the status/frontier pages: with SDL_VIDEO_X11_FORCE_EGL=0 the windowed GL path selects libnvidia-glcore, but the minimal glxgears hangs in the glcore kick wait (poll on the per-slot /dev/nvidia-modeset fd) while the host completes the beef notifier memory. The X DDX get-word/notifier completion, the DDX 4 GB sysmem footprint and physical dispatch of the GL draws remain. Published to open-iov.org.