diff options
Diffstat (limited to 'STATE-CURRENT.md')
| -rw-r--r-- | STATE-CURRENT.md | 14 |
1 files changed, 12 insertions, 2 deletions
diff --git a/STATE-CURRENT.md b/STATE-CURRENT.md index 93ae38f..38017d5 100644 --- a/STATE-CURRENT.md +++ b/STATE-CURRENT.md @@ -65,8 +65,18 @@ isolation, performance, portability). compute-object alloc) wedges the server; three further cycles closed the client-promote shape space on the default external VAS with a soft `NV_ERR_INVALID_STATE` (0x40) each. The V5 commit assert `0x52a8b04` is a - secondary failure. Next routes: name the soft-0x40 check, root-cause the - V5 first failure, or rehost the promote flow in risc-v-gsp-rm-debugger. + secondary failure. Offline (2026-10-05): the promote control handler and its + commit chain are decompiled; the external-VAS branch is confirmed in + `kchannelMapEngineCtxBuf_IMPL` (a externally-owned VAS requires the engine + context VA to be booked in the server's `vaList`, which a raw-PTE client map + never creates, while a non-external VAS is mapped and booked by the server); + the V6 soft-0x40 is the known rec-677 message emitted through the promote + error machinery. The rec-677 format text lives in runtime-inflated metadata + (not in the shipped image), so naming it needs a live-GSP metadata dump. + Next routes: name the soft-0x40 record from live metadata, root-cause the V5 + first failure (the log call site before the assert is now identified), or + root-cause the shared-management `TURING_COMPUTE_A` wedge; physical cycles + only with a named hypothesis and supervision. 2. **Hardening the accepted no-claim path.** The first green guest CUDA acceptance has landed and is holding across repeats; what remains is the intermittent guest-side corruption flake (intermittent guest boot |