vgsp-sema: scrub-pass diagnostics - stash bind/MISS logs (4096+-entry channels that fail the userd/va condition were silent), pass idle/read-fail/junk-put logs; the r697 session proved the direct authoring works (fin/host sema advance unblocks scrubCheckAndWaitForSize permanently) but the in-service pass never fired

1 files changed, 38 insertions, 3 deletions

diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c
index 993e507..e7c55d2 100644
--- a/kernel/gsp_sema_service.c
+++ b/kernel/gsp_sema_service.c
@@ -1592,6 +1592,9 @@ void gsp_sema_service_channel_add(const struct sema_channel_desc *desc)
 
 			if (!s)
 				goto scrub_done;	/* table full: max guests */
+			pr_info("sema-svc: scrub stash bind vgpu=%px slot=%d h=0x%x entries=%u\n",
+				(void *)desc->vgpu, (int)(s - svc_scrubs),
+				desc->h_object, desc->gpfifo_entries);
 			/* Re-seed the counting on a fresh scrubber object or a
 			 * new client session (m176: the counter/submitted state
 			 * is per-session; a recycled scrubber handle after a
@@ -1616,6 +1619,14 @@ void gsp_sema_service_channel_add(const struct sema_channel_desc *desc)
 				desc->h_object, desc->gpfifo_va,
 				desc->gpfifo_entries, desc->userd_pa,
 				s->userd_as);
+		} else if (desc->gpfifo_entries >= 4096) {
+			/* m112b: a 4096+-entry channel that fails the stash
+			 * condition (missing VA or USERD PA) never becomes a
+			 * scrub object - log it so a silent no-authoring
+			 * boot is diagnosable. */
+			pr_info_ratelimited("sema-svc: scrubber-stash MISS h=0x%x entries=%u va=0x%llx userd_pa=0x%llx\n",
+				desc->h_object, desc->gpfifo_entries,
+				desc->gpfifo_va, desc->userd_pa);
 		}
 scrub_done:
 		pr_info("sema-svc: channel 0x%x registered gpfifo=0x%llx entries=%u userd=0x%llx eng=%u cid=%u notif=0x%llx\n",
@@ -26992,19 +27003,43 @@ static void svc_scrub_pass(struct nv_vgpu_device *vgpu)
 	u32 put = 0;
 	u64 delta;
 
-	if (!s || !s->userd_ok || !s->pa_ok || !s->entries)
+	if (!s)
+		return;
+	if (!s->userd_ok || !s->pa_ok || !s->entries) {
+		/* m112b: silent-return diagnostic (bounded per boot). */
+		if (s->log_budget < 8) {
+			s->log_budget++;
+			pr_info("sema-svc: scrub pass idle vgpu=%px slot=%d userd_ok=%d pa_ok=%d entries=%u gen=%u\n",
+				(void *)vgpu, (int)(s - svc_scrubs),
+				s->userd_ok, s->pa_ok, s->entries,
+				s->session_gen);
+		}
 		return;
+	}
 	if (svc_read_ap(vgpu, s->userd_pa + SVC_USERD_GP_PUT, s->userd_as,
 			&put, sizeof(put))) {
 		/* Retry through the alternate aperture (as registration did). */
 		if (svc_read_ap(vgpu, s->userd_pa + SVC_USERD_GP_PUT,
 				s->userd_as == SVC_APERTURE_FB ?
 				SVC_APERTURE_SYS : SVC_APERTURE_FB,
-				&put, sizeof(put)))
+				&put, sizeof(put))) {
+			if (s->log_budget < 12) {
+				s->log_budget++;
+				pr_info("sema-svc: scrub pass read-fail userd=0x%llx as=%u\n",
+					s->userd_pa, s->userd_as);
+			}
 			return;
+		}
 	}
-	if (put >= s->entries)
+	if (put >= s->entries) {
+		/* m112b: junk-translation diagnostic (bounded). */
+		if (s->log_budget < 12) {
+			s->log_budget++;
+			pr_info("sema-svc: scrub pass junk put=%u entries=%u userd=0x%llx\n",
+				put, s->entries, s->userd_pa);
+		}
 		return;		/* junk translation; retry next pass */
+	}
 
 	if (!s->seeded) {
 		s->seeded = true;