From fb3db6dfc686405fc9fb37ecdf99e3b2ba138d6e Mon Sep 17 00:00:00 2001 From: Arthur Hanson Rasmusson Date: Sun, 18 Oct 2026 15:40:56 -0400 Subject: vgsp: fail4 r233 - budgeted REC-DUMP + READ-DIVERGE-WIT (fill vs copy-path vs ledger) r231/r232: the probe-class launches produced zero REC-DUMP lines while the transformer's 8+2 appeared - the per-line pr_info_ratelimited was suppressed wholesale during the probe's post-stall logging burst. REC-DUMP now uses plain pr_info under a boot-wide 512-line budget, so a <=64-rec launch always dumps its full rec table. READ-DIVERGE-WIT (sema service, rec-build loop): for small launches the three resolutions of each VA are compared side by side - the fill's dg->pa (the page whose content the copy-in stages; exactly what the engine reads), svc_op_translate (the H2D/D2H copy path's resolver) and the ledger's write landing. A page-level split is logged with op_src/op_rc and an op-miss token. Bounded: first 8 recs, boot budget 128. Static permutation check (negative): reloc_va is assigned sequentially in fill order (svc_gr_data_fill), copy-in/out iterate recs in order, the engine reads reloc-base + linear offset, and the per-page copy loop folds in-page offsets correctly on every resolver path; no sort/rotate/LIFO order found in the page-table or copy paths. The remaining split suspect is the m171/m180 ledger DIVERGE preference - exactly what READ-DIVERGE-WIT compares. Build green. (cherry picked from commit 59e50207d60067b5d1e3a0546f20e9b22c92e112) --- kernel/gsp_sema_service.c | 36 ++++++++++++++++++++++++++++++++++++ 1 file changed, 36 insertions(+) (limited to 'kernel/gsp_sema_service.c') diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index 02c100f..d9f5895 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -12666,6 +12666,7 @@ static unsigned long svc_fwd_state; static u64 svc_fwd_requests; static u64 svc_fwd_dropped; static u32 svc_grvaudit_launches; /* GRVAUDIT: per-launch audit counter */ +static u32 svc_readdiv_log; /* r233 READ-DIVERGE-WIT budget */ /* * Pause gate shared by the pump's request path and the backend release path: * quiesce takes this lock, sets paused and waits for the in-flight work item; @@ -14387,6 +14388,41 @@ static void svc_fwd_gr_work(void) } } } + /* + * r233 READ-DIVERGE-WIT: the engine's read of this VA uses + * exactly what the fill resolved (dg->pa: the page whose + * content was copied into the bounce). The copy paths (H2D + * writes, D2H reads) resolve independently through + * svc_op_translate/ledger. For small launches (the probe + * class) compare the three for the first recs and flag any + * page-level split - the direct witness for a read/write + * permutation. Bounded: first 8 recs, 4 lines per launch, + * boot budget 128. + */ + if (svc_fwd_req.gr_n_data <= 64u && i < 8u && + svc_readdiv_log < 128u) { + u64 opa = 0, lpa2 = 0; + u32 oap = 0, lap2 = 0; + bool op_miss, have_led; + + op_miss = svc_op_translate(svc_fwd_req.vgpu, dg->va, + &opa, &oap) != 0; + have_led = !svc_ledger_lookup(dg->va, &lpa2, &lap2); + if (op_miss || (!op_miss && + (opa & ~(u64)(SEMA_PAGE_SIZE - 1)) != + (dg->pa & ~(u64)(SEMA_PAGE_SIZE - 1))) || + (have_led && + (lpa2 & ~(u64)(SEMA_PAGE_SIZE - 1)) != + (dg->pa & ~(u64)(SEMA_PAGE_SIZE - 1)))) { + svc_readdiv_log++; + pr_info("vgsp-gr: READ-DIVERGE-WIT va=0x%llx fill_pa=0x%llx op_pa=0x%llx op_src=%u op_rc=%d ledger_pa=0x%llx%s\n", + dg->va, dg->pa, opa, + op_miss ? 0xffffffffu : svc.op_tr_src, + op_miss ? -ENOENT : 0, + have_led ? lpa2 : 0, + op_miss ? " (op-miss)" : ""); + } + } /* * C3 (data class): after the run the backend copies this * page's results back to dg->pa (gsp_phys_booter.c copy-out). -- cgit v1.2.3