diff options
Diffstat (limited to 'kernel/gsp_sema_service.c')
| -rw-r--r-- | kernel/gsp_sema_service.c | 56 |
1 files changed, 56 insertions, 0 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index 1cb771a..ccccfec 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -4794,6 +4794,7 @@ static u32 svc_ledger_n; static u64 svc_ledger_diverges; static u64 svc_ledger_stores; static u64 svc_ledger_rewrites; +static u64 svc_ledger_reloc_diverges; static u32 svc_ledger_store_log; static inline u32 svc_ledger_home(u64 page) @@ -4881,6 +4882,7 @@ static void svc_ledger_clear(void) memset(svc_ledger, 0, sizeof(svc_ledger)); svc_ledger_n = 0; svc_ledger_rewrites = 0; + svc_ledger_reloc_diverges = 0; } static int svc_copy(struct nv_vgpu_device *vgpu, u64 dst, u64 src, size_t total, @@ -13962,6 +13964,8 @@ static void svc_fwd_relay_select(struct svc_fwd_req *req) * svc_gr_req_fill from its QMD pointer association and the captured inline * bytes. Overflow is a failure (fail-closed), not a silent drop. */ +static const char *svc_gr_src_probe(struct nv_vgpu_device *vgpu, u64 va, + u64 *pa_out, u32 *ap_out); static void svc_gr_page_note(struct nv_vgpu_device *vgpu, u64 va, u32 qmd_word) { u64 page = va & ~(u64)(SEMA_PAGE_SIZE - 1); @@ -13986,6 +13990,58 @@ static void svc_gr_page_note(struct nv_vgpu_device *vgpu, u64 va, u32 qmd_word) i = svc_fwd_req.gr_n_pages++; svc_fwd_req.gr_pages[i].va = page; svc_fwd_req.gr_pages[i].qmd_word = qmd_word; + /* + * m181 (relocation/ledger unification): the unified landing table is + * the authority for a page a host write already landed on. The CE + * inline writes that author these launch pages (param, program, + * constant banks, inline destinations) go through + * svc_grce_inline_write(), which records its landing. The backend's + * QMD relocation reads the page content through pg->pa (win0 shadow + * copy) and the m129 mirror patches that same page, so resolving + * independently here could hand the engine a stale page whose + * pointer values are not this launch's VAs: the relocation then + * matches nothing, the engine executes against unrelocated guest VAs + * it cannot walk, and the grid aborts silently (zero stores, ack + * still delivered) - the cross-session zero-write class - or runs on + * the previous client's parameters (the multi-page wrongness). + * Resolve once, from the table, and record the independent answer as + * stale when it differs. + */ + { + u64 lpa = 0; + u32 lap = 0; + + if (!svc_ledger_lookup(page, &lpa, &lap)) { + u64 rpa = 0; + u32 rap = 0; + const char *rsrc = svc_gr_src_probe(vgpu, page, &rpa, + &rap); + + if (rpa && + ((lpa & ~(u64)(SEMA_PAGE_SIZE - 1)) != + (rpa & ~(u64)(SEMA_PAGE_SIZE - 1)) || + (u32)lap != (u32)rap)) { + svc_ledger_reloc_diverges++; + if (svc_ledger_reloc_diverges <= 16) + pr_info("sema-ledger: RELOC-DIVERGE va=0x%llx ledger_pa=0x%llx %s_pa=0x%llx (ledger wins)\n", + page, + lpa & ~(u64)(SEMA_PAGE_SIZE - 1), + rsrc, rpa & + ~(u64)(SEMA_PAGE_SIZE - 1)); + } + svc_fwd_req.gr_pages[i].pa = + lpa & ~(u64)(SEMA_PAGE_SIZE - 1); + svc_fwd_req.gr_pages[i].ap = (u8)lap; + /* + * Keep the pin table consistent with the authority so + * the win0 copy path and later resolves agree (and no + * stale self-pin is planted for this VA). + */ + svc_pin_store(page, lpa & ~(u64)(SEMA_PAGE_SIZE - 1), + (int)lap); + return; + } + } if (svc_resolve_va(vgpu, page, &pa, &ap)) return; svc_fwd_req.gr_pages[i].pa = pa & ~(u64)(SEMA_PAGE_SIZE - 1); |