diff options
Diffstat (limited to 'wiki/Graphics-Execution.md')
| -rw-r--r-- | wiki/Graphics-Execution.md | 83 |
1 files changed, 43 insertions, 40 deletions
diff --git a/wiki/Graphics-Execution.md b/wiki/Graphics-Execution.md index 7771d6a..ca04b8f 100644 --- a/wiki/Graphics-Execution.md +++ b/wiki/Graphics-Execution.md @@ -12,7 +12,7 @@ > [`../docs/04-implementation/04-real-render-walls.md`](../docs/04-implementation/04-real-render-walls.md) > (the measured walls); the docs tree wins on disagreement. -Status: 2026-11-09, tree `master @ cb8e822b`. Tags: `[live]` observed end to +Status: 2026-11-09, tree `master @ bb802909`. Tags: `[live]` observed end to end; `[wip]` partially built; `[wall]` current blocker; `[target]` defined success state; `[planned]` designed, not built. @@ -92,9 +92,10 @@ fidelity: applied), forcing GLX selects `libnvidia-glcore`, and the event-IRQ fix (`a478f0b4`) lets the guest service the completion, so glxgears completes swaps and the guest's real GL draws now forward and execute on the - physical GPU (`work_gr backend_ok=9`). What remains is the constant-buffer - (MVP) content, the MME front-end defer and GR stale-wedge, and the DDX - get-word/notifier completion (§6). + physical GPU (`work_gr backend_ok=5-7`, `backend_timeout=0`) and X is + reliable, but the draw still writes 0 pages. What remains is the beef GR + ring resolution race, the fixed-CB image's zero MVP block, and the + render-target bind (§6). ## 4. The channel and object picture @@ -144,9 +145,11 @@ host-side levers now, and a diagnostic write of the get word released the DDX's reserve loop. For a windowed GL client the present is a kick; the GSP event-IRQ fix now sets the RISC-V SWGEN0 IRQSTAT/IRQMASK/IRQDEST and latches the CPU-tree leaf, so the guest services the event and glxgears completes -swaps. The next completion step is the constant buffer: the draw's CB page -must be resolved and copied into the seed page so the engine produces -fragments. +swaps, and the GR backend no longer times out (the pair-close/pair-safe +replay fixes are default ON; draws retire in 3-2400 ms). The next completion +step is the beef GR ring (so the fixed-CB scan runs on every cycle) and the +CB image (its `0x80` MVP block is zero even when the scan runs), then the +render-target bind. During bring-up the module also carries a **diagnostics-only mirror** for apps that spin on a shared progress word; it exists so a run can proceed while the @@ -155,35 +158,33 @@ requires it switched off, along with any external poke. ## 6. Where the frontier is (ranked walls) -1. **The constant buffer (MVP) content** `[wall]`. The guest's GL draws now - execute on the physical GPU, but the engine writes 0 pages. The draw's - constant-buffer source is forced to the seed page because - `cb-copy src=0x0cd70000 ... first8=00000000 ... src=synthetic-id` reads all - zeros; a guest-RAM scan found no MVP matrix and the `0x3f800000` vidmem - hits are shader microcode immediates. With a zero MVP every vertex - collapses to the origin, so there are no fragments. Decode the CB-bind - method on the beef channel, resolve that VA through the channel VAS, and - copy the real page into the seed page. -2. **Execution stability** `[wall]`. The MME front-end is busy/deferred - (`MME-FE-DEFER` then forced loads) and the GR channel stale-wedges - (`GR-STALL-stale-wedge`, recovered), so the pipeline restarts mid-frame. - Fixing the CB page may unstick the MME; the wedge recovery needs a durable - fix. -3. **The X DDX push-buffer completion** `[wall]`. The DDX's 2D reserve loop - exits only when the GPU-written engine get word advances (`get <= put`) and - the kick requires the notifier to be recycled to `0xffff` after completion. - `sema_vas_cand_ms=1` makes X green on attempt 1, but X can still die after a - few forward frames into the RM-degraded state. +1. **Beef GR ring resolution** `[wall]`. `0xbeef0100` (the GL client GR + channel) registers with `vas=0` before its CE siblings publish + `0xbeef0300`; the shared VAS is then registered UNVERIFIED by the 1 ms + age-out, so the ring at `0x4020000` stays `ring_pa=0` and the fixed-CB scan + (gated to the `0xbeef0000` family) never runs. The next fix is to gate the + candidate promote on *verified* rather than *known* and retry every pump + turn. +2. **The fixed-CB image MVP block** `[wall]`. Even on a cycle where the scan + runs (`r1687`), it decodes 1492 `0x3800` offsets plus 1497 `0x39c8` data + runs (1092 words) but the image's `0x80` MVP block is zero. Identified + parser bugs (subchannel bits 15:13, `0x238c` ONE_INC inline data, selector + B/C swap) are not yet applied; the MVP may live at an offset >= `0x1000` or + a selector B/C binding. With a zero MVP every vertex collapses to the + origin, so there are no fragments. +3. **The render-target bind** `[wall]`. Confirm that the replayed draw's + render target is the page `bounce copy-out` compares + (`svc_surf_prelude_capture` currently picks the last trusted bind + globally). 4. **The X DDX footprint** `[wall]`. The DDX allocates 4 GB of system pages at startup; an 8 GB guest has no headroom once GZDoom's own footprint lands and both are OOM-killed. Current runs use a 12 GB guest; the allocation is a suspected emulation gap (a 512 MiB emulated VRAM falling back to a 4 GB sysmem allocation) to fix. -5. **Non-black frames and sustained rate** `[wall]`/`[target]`. Once the - constant buffer, the MME/wedge stability and the DDX get-word/notifier - completion land, the capture must show motion, then 60 fps in one VM with - no forcing, then two VMs on two mediated devices with non-black frames in - both. +5. **Non-black frames and sustained rate** `[wall]`/`[target]`. Once the beef + ring, the CB image and the render-target bind land, the capture must show + motion, then 60 fps in one VM with no forcing, then two VMs on two mediated + devices with non-black frames in both. ## 7. What is proven today @@ -193,18 +194,20 @@ requires it switched off, along with any external poke. | Display engine serves the modeset push buffers; notifier plus `UPDATE -> FINISHED` | `[live]` (campaign configuration) | | nvidia-modeset/NvKms registers (`/dev/dri/card0`, `renderD128`, `fb0`); `nvidia-smi -L` enumerates | `[live]` | | `glxinfo` reports the emulated GPU with the NVIDIA renderer (OpenGL 4.6.0, direct rendering) | `[live]` | -| X server green with `sema_vas_cand_ms=1`; glxinfo 4.6.0 direct | `[live]` | +| X green on attempt 1 in three consecutive cycles (`ebf3130f`) | `[live]` | | GSP event-IRQ fix wakes the guest poll; glxgears completes swaps | `[live]` | | 2D path end-to-end: accelerated X fills read back via `xwd` | `[live]` | -| Guest's real GL draws forward and execute on the physical GPU (`work_gr backend_ok=9`) | `[live]` | +| Guest's real GL draws forward and execute on the physical GPU (`work_gr backend_ok=5-7`) | `[live]` | +| GR backend timeouts fixed (`backend_timeout=0`; draws retire in 3-2400 ms) | `[live]` | +| CB-DIAG decodes the draw's fixed-CB stream (1492 `0x3800` offsets, 1092 words) | `[live]` | | Beef GR channel `0xbeef0100` captures real GL draw sections | `[live]` | | GL section capture: the X channel's `0xC597` stream decoded | `[live]` | | Verbatim 3D method-stream replay retired by the engine (no MMU fault) | `[live]` | | Synthesized launch executes real `sm_75` SASS; Turing `V3` program header accepted | `[live]` | | X server survives the run on a 12 GB guest (the DDX's 4 GB sysmem allocation forces the size) | `[live]` | -| Constant-buffer (MVP) page resolves and the draw writes render-target pixels | `[wall]` | -| MME front-end defer / GR stale-wedge stability | `[wall]` | -| DDX push-buffer get-word publish and notifier recycle | `[wall]` | +| Beef GR ring resolves deterministically; fixed-CB scan runs every cycle | `[wall]` | +| Fixed-CB image's `0x80` MVP block becomes non-zero | `[wall]` | +| Render-target bind matches the copy-out page | `[wall]` | | NVIDIA Vulkan ICD creates a device | `[wall]` | | Non-black pixels from the emulated vGPU's 3D pipeline | `[wall]` | | Windows/DirectX guests | `[planned]` | @@ -213,10 +216,10 @@ requires it switched off, along with any external poke. * No non-black pixel has been produced by the emulated vGPU's 3D pipeline yet. * Display/KMS bring-up (NvKms, `/dev/dri`, X, a real GL context) is not a - rendered-frame claim; the guest's GL draws now execute on the physical GPU - and glxgears completes swaps, but the frames are black. The constant-buffer - (MVP) content, the MME/wedge stability and the DDX get-word/notifier - completion are the current walls. + rendered-frame claim; the guest's GL draws now execute on the physical GPU, + X is reliable and glxgears completes swaps, but the frames are black. The + beef GR ring resolution, the fixed-CB image's zero MVP block and the + render-target bind are the current walls. * No frame-rate or latency numbers: the scheduled measurement is defined (60 fps over 60 s, no forcing) but not yet met. * The `virgl`-based demo videos are a different, labelled path — not this one. |