diff options
| -rw-r--r-- | kernel/gsp_sema_service.c | 39 |
1 files changed, 37 insertions, 2 deletions
diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c index 1b86945..f55502b 100644 --- a/kernel/gsp_sema_service.c +++ b/kernel/gsp_sema_service.c @@ -7541,6 +7541,13 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, u64 *ops_done) { struct svc_push_state st; + + /* + * r316: pending releases record the channel they were decoded for; + * the verified pool resolver is channel-keyed (see svc_pending_add + * and the matmul r322 starved/hung note). + */ + svc.cur_ch = ch->h_object; /* * Static for the same reason as svc_handle_chan_dump: a 32-entry ops * array is a ~2 KB frame, and this is called from the single service @@ -9028,7 +9035,25 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf, * release through the pending * pass instead. */ - if (n_ops > 0) { + if (n_ops > 0 || + svc.op_tr_pending) { + /* + * r316 (CONT.60): + * op_tr_pending covers + * the denied pass - the + * pass built no op + * (allow=0) but a copy is + * still owed; applying + * the fence here (the old + * n_ops==0 path) let the + * driver refill the + * ping-pong staging before + * the copy ever ran - the + * cold-run capture gap + * (vector_add run 1 + * bad=157696/193536 vs + * bad=0 warm). + */ svc_pending_add(sem_va, st.sem_payload, inc ? 1u : 0u); @@ -9168,6 +9193,12 @@ struct svc_pending_release { u64 va; u32 payload; u32 op; /* 0 = RELEASE, 1 = REDUCTION (add payload) */ + u32 h; /* r316: channel the release was decoded for; the + * verified pool resolver is channel-keyed and h=0 + * never matches its per-channel entries (matmul + * r322: pool-rel cand resolved at decode (rrc=0, + * h=channel) while svc_apply_pending with h=0 + * starved forever and hung the client). */ /* * Resolution attempts that found no translation for this VA. * Telemetry for ISSUE-0001: a pending release that keeps failing to @@ -9244,6 +9275,7 @@ static void svc_pending_add(u64 va, u32 payload, u32 op) svc_pending[i].payload = payload; svc_pending[i].op = op; svc_pending[i].tries = 0; + svc_pending[i].h = svc.cur_ch; } /* @@ -9571,8 +9603,11 @@ static void svc_apply_pending(struct nv_vgpu_device *vgpu) * resolver: the learned map can answer with a stale * page whose value makes this release look already * delivered and drops it (see svc_sem_write). + * r316: resolve with the channel the release was + * decoded for (h=0 never matches the per-channel + * pool entries - matmul r322 starved/hung). */ - if (svc_pool_pa_resolve(vgpu, 0, p->va, &ppa, &pap, + if (svc_pool_pa_resolve(vgpu, p->h, p->va, &ppa, &pap, NULL)) { /* not translatable yet: keep (ISSUE-0001) */ p->tries++; |