vgsp-sema: every-pass VAS candidate verify with the last-good ring pair (r707e) - the r710 boot shows the host content-located trigger registers the user VAS and the walk resolves (walk_probe va=0x4ca0000: vas[3] h=0xfade0002 pdb=0x101d63000 -> rc=0 pa=0x11fa20000), while the pump's own svc_lookup pair only registered the three internal VASes (all rc=-2); the working order is: content-located trigger FIRST (registers the user VAS), then sema_chan_rewind so the replay re-reads the entries with the working VAS

1 files changed, 25 insertions, 0 deletions

diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c
index 25fd408..21a39a2 100644
--- a/kernel/gsp_sema_service.c
+++ b/kernel/gsp_sema_service.c
@@ -13922,6 +13922,18 @@ static u32 svc_pushpg_split_log;
  */
 /* r707d: bounded push-read failure witness (see below). */
 static u32 svc_pushfail_log;
+/*
+ * r707e: last content-backed ring pair resolved by any channel. The VAS
+ * candidate verify is retried with it on EVERY pump pass: the parked
+ * COPY_SERVER_PDES candidate for the client's user VAS parks at
+ * device-create and must register before the submit's first push read
+ * (a failed GR entry read is never retried with a fresh VAS), but the ring
+ * resolution and the park race within one pass - the every-pass retry
+ * closes that race in a single boot.
+ */
+static u64 svc_lastgood_ring_va;
+static u64 svc_lastgood_ring_pa;
+
 
 static int svc_read_va_push_ex(struct nv_vgpu_device *vgpu,
 			       struct svc_channel *ch, u64 va, void *buf,
@@ -23669,6 +23681,15 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu)
 		}
 	}
 	/*
+	 * r707e: every-pass candidate verify with the last-good ring pair.
+	 * Cheap (<=16 parked candidates, one walk each) and idempotent; the
+	 * first pass after the user-VAS candidate parks registers it, so the
+	 * client's very first push reads resolve.
+	 */
+	if (svc_lastgood_ring_pa)
+		svc_vas_candidates_verify(vgpu, svc_lastgood_ring_va,
+					  svc_lastgood_ring_pa);
+	/*
 	 * r507o stream-order: walk the CE channels BEFORE the GR channels.
 	 * The client's stream order places its H2D copies before the kernel
 	 * that consumes them, but the channels register in handle order (the
@@ -23885,6 +23906,10 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu)
 
 		if (!rrc)
 			svc_pb_pair(vgpu, ch);
+		if (!rrc && ring_pa) {
+			svc_lastgood_ring_va = ch->gpfifo_va;
+			svc_lastgood_ring_pa = ring_pa;
+		}
 		/*
 		 * r707f (FOLD): the moment ANY channel's ring resolves through
 		 * the channel object, verify the parked COPY_SERVER_PDES VAS