sema-svc: learn GR counter PA from pinned release VA (auto-register, publish puts)

1 files changed, 41 insertions, 0 deletions

diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c
index e21c997..d4cab22 100644
--- a/kernel/gsp_sema_service.c
+++ b/kernel/gsp_sema_service.c
@@ -2111,6 +2111,39 @@ static void svc_counter_release_apply(struct nv_vgpu_device *vgpu, u32 h,
 			    h, pa, payload, cur);
 }
 
+/*
+ * Learn a GR channel's completion-counter guest PA from a release VA the
+ * push carried, so the publish path can advance the exact slot the client
+ * polls without any guest-side enumeration. Only a host-verified translation
+ * (pin/ipin) is trusted; the release VA of a GR push is the counter slot
+ * itself (0x20400fXX observed). No-op once registered.
+ */
+static void svc_counter_learn(u32 h, u64 sem_va)
+{
+	unsigned long flags;
+	u64 pa = 0;
+	int ap = SVC_APERTURE_SYS;
+	int i;
+
+	if (!h || sem_va < 0x204000000ULL || sem_va >= 0x204100000ULL)
+		return;
+	if (svc_pin_lookup_any(sem_va, &pa, &ap) || ap != SVC_APERTURE_SYS)
+		return;
+
+	spin_lock_irqsave(&svc.chan_lock, flags);
+	for (i = 0; i < SVC_MAX_CHANNELS; i++) {
+		if (svc.chan[i].valid && svc.chan[i].h_object == h) {
+			if (!svc.chan[i].counter_pa) {
+				svc.chan[i].counter_pa = pa & ~0x3ULL;
+				pr_info("sema-chan: counter learned h=0x%x pa=0x%llx (from release va=0x%llx)\n",
+					h, pa & ~0x3ULL, sem_va);
+			}
+			break;
+		}
+	}
+	spin_unlock_irqrestore(&svc.chan_lock, flags);
+}
+
 static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf,
 			      u32 len, u64 page_pa, bool allow_ops,
 			      u32 ch_h, u32 ch_eng, u64 push_va,
@@ -2557,6 +2590,14 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf,
 				 * translation. Same forward-only guard as the
 				 * VA path.
 				 */
+				/*
+				 * GR pushes release the per-channel completion
+				 * counter; learn its guest PA from the (pinned)
+				 * release VA so the publish path can advance the
+				 * exact slot the client polls.
+				 */
+				if (ch_eng == 0)
+					svc_counter_learn(ch_h, sem_va);
 				svc_counter_release_apply(vgpu, ch_h,
 							  st.sem_payload);
 				/* release ends the push */