diff options
Diffstat (limited to 'kernel')
| -rw-r--r-- | kernel/gsp_sema_service.c | 89 |
1 files changed, 74 insertions, 15 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index ff95598..d3ac29c 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -878,6 +878,18 @@ struct sema_svc { u64 sem256_log; /* 256-byte op trace budget */ u64 op_tr_log; /* operand targeted-resolve budget */ u32 op_tr_pending; /* an operand's targeted scan is in progress */ + u32 op_owed; /* r540: a denied transfer op + * was never re-run because the + * per-slot pend cap was hit; the + * slot must stay INCOMPLETE so a + * later trusted/injected pass + * runs it (the r539 5-minute + * device-init stall class: the + * client's GRCE H2D was denied + * while untrusted, capped, then + * replay-suppressed forever and + * the copy never executed) */ + u64 op_owed_log; /* r540: bounded owe witness */ u64 copy_watch_log; /* sema_copy_watch log budget */ u64 copy_dst_hold; /* m169: device-dst copies held for * want of a pin (stale-table guard) */ @@ -11140,20 +11152,54 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, * channel in 10 s hold cycles. */ if (entry_idx != SVC_ENTRY_NONE && - entry_idx < SVC_GPFIFO_MAX_BITS && - ch->slot_pend_tries[entry_idx] < 4) { - ch->slot_pend_tries[entry_idx]++; - svc.op_tr_pending = 1; - if (gsp_sema_dbg && - svc.pend_dbg_log < 512) { - svc.pend_dbg_log++; - pr_info("sema-pend: h=0x%x push=0x%llx idx=%u out=0x%llx in=0x%llx line=%u replay=%d trusted=%d tries=%u -> op_tr_pending\n", - ch->h_object, push_va, - entry_idx, st.offset_out, - st.offset_in, - st.line_length, - replay, trusted, - ch->slot_pend_tries[entry_idx]); + entry_idx < SVC_GPFIFO_MAX_BITS) { + if (ch->slot_pend_tries[entry_idx] < 4) { + ch->slot_pend_tries[entry_idx]++; + svc.op_tr_pending = 1; + if (gsp_sema_dbg && + svc.pend_dbg_log < 512) { + svc.pend_dbg_log++; + pr_info("sema-pend: h=0x%x push=0x%llx idx=%u out=0x%llx in=0x%llx line=%u replay=%d trusted=%d tries=%u -> op_tr_pending\n", + ch->h_object, push_va, + entry_idx, st.offset_out, + st.offset_in, + st.line_length, + replay, trusted, + ch->slot_pend_tries[entry_idx]); + } + } else { + /* + * r540: the cap stopped the + * re-hold, but the op is still + * owed. Leaving the slot + * complete would classify every + * later pass as a replay and + * suppress the copy forever - + * the client waits on a copy + * that never ran (the r539 + * ~5-minute device-init stall: + * a GRCE H2D denied while + * untrusted, capped at 4 tries, + * then replay-suppressed after + * the pin arrived). Mark the + * pass owed so the slot stays + * INCOMPLETE and the next + * fresh pass (injected or + * translated) executes the + * copy. No hold is armed, so a + * slot whose trust never arrives + * still cannot wedge the pump. + */ + svc.op_owed = 1; + if (svc.op_owed_log < 64) { + svc.op_owed_log++; + pr_info("sema-pend: OWED h=0x%x push=0x%llx idx=%u out=0x%llx in=0x%llx line=%u trusted=%d (cap hit; slot stays incomplete for a fresh retry)\n", + ch->h_object, push_va, + entry_idx, st.offset_out, + st.offset_in, + st.line_length, + trusted); + } } } } @@ -22049,6 +22095,7 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu) svc_entry_outcome("decode", ch, idx, va, len); svc.op_tr_pending = 0; + svc.op_owed = 0; svc_decode_stream(vgpu, pb, len, 0, (allow_ops || injected) && @@ -22083,8 +22130,20 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu) entry_ident; ch->slot_ops_done[idx] = entry_done; + /* + * r540: an owed + * denied op keeps + * the slot + * incomplete too - + * otherwise every + * later pass is a + * replay and the + * op can never run + * (see op_owed). + */ ch->slot_ops_complete[idx] = - svc.op_tr_pending ? + (svc.op_tr_pending || + svc.op_owed) ? 0 : 1; ch->slot_ops_hash[idx] = svc_push_hash(pb, |