vgsp-sema: SESSION 130 zero-payload application + tail-arbitration witness - a zero-headed tail-served payload is now applied under a variant once-key (h | 1) instead of being refused forever (the destination is empty, so authoring zeros is idempotent and correct for the driver's internal zero buffer, whose 256 B i2m equals GF100_ZERO_BUFFER_SIZE exactly), while a later non-zero payload for the same entry still matches its own (h) key and lands; the utildec witness now carries alt=success/tries so a walk-read that fails is distinguishable from one that returns zero

1 files changed, 36 insertions, 2 deletions

diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c
index 4984a8c..1a844cb 100644
--- a/kernel/gsp_sema_service.c
+++ b/kernel/gsp_sema_service.c
@@ -24455,7 +24455,37 @@ static u32 svc_gr_ahead_push(struct nv_vgpu_device *vgpu, struct svc_channel *ch
 					svc_util_wit.zero = true;
 			}
 			if (refuse_zero) {
+				/*
+				 * SESSION 130: a zero-headed tail-served
+				 * payload is applied under a VARIANT once-key
+				 * (h | 1) instead of being refused forever:
+				 * the destination is currently empty, so
+				 * authoring zeros is idempotent and correct
+				 * for the driver's internal zero buffer (the
+				 * observed 256 B utility i2m = exactly
+				 * GF100_ZERO_BUFFER_SIZE), while a later
+				 * non-zero payload for the same entry still
+				 * matches its own (h) key and lands - the
+				 * refusal can no longer stall the arm
+				 * (r737/r739: `writes=0` with the payload
+				 * page stably zero).
+				 */
 				svc_util_pending_zero++;
+				if (bytes && !svc_inline_once_seen(push_va,
+								   h | 1,
+								   off_out,
+								   bytes)) {
+					svc_inline_once_store(push_va, h | 1,
+							      off_out, bytes);
+					svc_gr_ahead_inline_writes++;
+					if (inline_only)
+						svc_util_wit.fired = true;
+					(void)svc_grce_inline_write(vgpu,
+								    off_out,
+								    svc_ahead_inline_buf,
+								    bytes,
+								    ch->h_object);
+				}
 			} else if (bytes && !svc_inline_once_seen(push_va, h,
 								  off_out,
 								  bytes)) {
@@ -24872,6 +24902,8 @@ static void svc_gr_util_sweep(struct nv_vgpu_device *vgpu,
 	static u64 svc_util_tail_alt;	/* SESSION 130: tails re-read through
 					 * the direct walk because the
 					 * channel read was zero-headed */
+	static u64 svc_util_tail_try;	/* ... and the walk attempts (alt is
+					 * the subset that yielded non-zero) */
 	u32 i, maxent = min_t(u32, gsp_sema_gr_util_scan, 64);
 	u32 swept = 0, nmade = 0;
 
@@ -24994,6 +25026,7 @@ static void svc_gr_util_sweep(struct nv_vgpu_device *vgpu,
 			    !memchr_inv(nbuf, 0, min_t(u32, tl_a, 16))) {
 				u32 want = tl_a;
 
+				svc_util_tail_try++;
 				if (!svc_util_walk_read(vgpu, nva, tbuf,
 							want) &&
 				    memchr_inv(tbuf, 0,
@@ -25035,11 +25068,12 @@ static void svc_gr_util_sweep(struct nv_vgpu_device *vgpu,
 			svc_util_dec_keys[slot].va = va;
 			svc_util_dec_keys[slot].h = hkey;
 			svc_util_dec_log++;
-			pr_info("sema-utildec: h=0x%x i=%u va=0x%llx len=0x%x p_src=%u pa=%u pb=%u tail_va=0x%llx tail=0x%x t8=%08x %08x alt=%llu lidn=%u subch=%u saw=%d fired=%d zero=%d dst=0x%x ll=%u lc=%u f8=%08x %08x\n",
+			pr_info("sema-utildec: h=0x%x i=%u va=0x%llx len=0x%x p_src=%u pa=%u pb=%u tail_va=0x%llx tail=0x%x t8=%08x %08x alt=%llu/%llu lidn=%u subch=%u saw=%d fired=%d zero=%d dst=0x%x ll=%u lc=%u f8=%08x %08x\n",
 				ch->h_object, i, va, rlen,
 				pbuf == bbuf ? 1u : 0u, parse_a, parse_b,
 				nva, tl_a, svc_util_wit.t0, svc_util_wit.t1,
-				svc_util_tail_alt, lidn, lidsc,
+				svc_util_tail_alt, svc_util_tail_try,
+				lidn, lidsc,
 				svc_util_wit.saw_lid ? 1 : 0,
 				svc_util_wit.fired ? 1 : 0,
 				svc_util_wit.zero ? 1 : 0,