open-iov.git/tools/test, branch gr-forwarding

gsp-phys: P6a - real copy engine reads/writes guest RAM pages

2026-10-02T07:31:06+00:00

- file-backed guest RAM (launcher memory-backend-file share=on) and in-kernel GPA->HPA translation through the shared file page cache (read_cache_page + page_to_phys + pfn_valid), opened O_LARGEFILE; new default-off gsp_phys_guest_mem parameter - debugfs gsp-phys-guest-ram (path + gpa/off/size ranges) and gsp-phys-guest-gpa (one pinned GPA per boot); rm-call triggers 6/7 run host->guest and guest->host 4 KiB CE copies; trigger 8 is a PTE self-test through a fresh slot - guest page-table slots are pre-built during ladder stage 3: runtime PTE writes into an already-walked page-table line are not observed without a TLB invalidate - guest RAM layout (q35 4.2, 4 GiB): below-4G GPA == file offset, above-4G offset = GPA - 0x80000000 (2 GiB PCI hole) - tests: tools/test/gpage_test.c guest probe; docs + STATE-CURRENT record the live green (G2H/W2G with semaphore release, guest observed the write, smoke ALL OK 64/64, clean latched release)

guest-diag: cdt2 mapping scan is opt-in (CDT_SCAN=1); it can wedge the client

2026-09-30T12:40:17+00:00

guest-diag: cdt2 payload scan limited to anon mappings (device-mapping reads can block)

2026-09-30T12:25:49+00:00

guest-diag: cdt2 payload scan only touches anon/device mappings (avoid SIGBUS on truncated file maps)

2026-09-30T12:08:32+00:00

guest-diag: cdt2 scans its own mappings for the payload after HtoD (DtoH mechanism probe)

2026-09-30T11:25:45+00:00

sema-svc: decode GRCE inline-data DMA (small HtoD path)

2026-09-30T10:13:26+00:00

The 256-byte cuMemcpyHtoD payload never appears in any CE push: CUDA submits it on the compute channel as a compute-class DMA whose source is the push's own inline data (LINE_LENGTH_IN=256, OFFSET_OUT=, LAUNCH_DMA=0x41, LOAD_INLINE_DATA 64 dwords, then the channel's SET_REPORT_SEMAPHORE release). The CE-shaped decoder skipped the data run (opcode 3) and no GR work ran at all. - Decode NVC5C0 GRCE methods on subchannel 1 (LINE_LENGTH_IN, LINE_COUNT, OFFSET_OUT/UPPER, LAUNCH_DMA) and the opcode-3 LOAD_INLINE_DATA run. - svc_grce_inline_write resolves the destination VA through trusted sources (pins, map, published page directories, targeted rm_mem resolve), pins the page and writes into vidmem or guest RAM; budgeted sema-grce logs name the target or report UNRESOLVED. - cdt2 test binary gains CDT_CP_PAUSE / CDT_HP_PAUSE for live inspection of the copy path; pushed by push_guest_tools.sh.

guest-diag: cdt CDT_WAIT park-at-end (live memory inspection); run_cycle CDT_WAIT passthrough

2026-09-30T09:38:31+00:00

guest-diag: run_cycle SKIP_OPS knob + cdt output on serial; cdt richer roundtrip diagnostics

2026-09-30T08:41:06+00:00

gsprm: reply-latency logging + param dump cap; guest-diag: CDT_PAUSE, watcher reaping, wider CE stream window

2026-09-30T04:06:42+00:00

guest-diag: adaptive miss-driven pinner; cdt holds on failure for inspection

2026-09-28T17:14:16+00:00

pin_miss_pages.sh watches the host journal for release-miss VAs, resolves each page for the live cdt pid through the guest pagemap and injects it (the injection rewinds the pump so releases consumed under a stale pin are re-read); it re-pins when a new cdt pid appears. cuda_drv_test prints cuGetErrorName/String on failure and, with CDT_HOLD=, stays alive so the RM error record and tracker state can be inspected after cuCtxCreate has given up.