vgsp: service the guest RC watchdog channel (Volta GPFIFO class + class2d notifier ack)

The guest kernel's krcWatchdog posts a notifier cycle on its own channel
(object 0x31415900) every second and declares 'GPU is probably locked'
when the zeroed notification never comes back within 7 s. Observed as
the sustained-GL-load wedge: once a GL client (GZDOOM) enabled robust
channels the errors started and Xorg eventually stalled on screen
readback.

- rm: register the Volta GPFIFO class 0xc36f (plus the later
  generations) as a channel class. The watchdog's channel allocates
  0xc36f on this device - the driver picks the first class the gpu
  reports supported - and without it the channel never reached the
  progress service. It now registers and latches (put visible, entries
  walked).
- sema: decode the class2d notifier cycle on subchannel 3
  (SET_NOTIFY_A/B name the notifier VA, NOTIFY WRITE_ONLY writes the
  zeroed NvNotification) and author the write, like svc_notify_complete
  does for the work-submit token. Proven live: 'sema-notify2d: va=...
  zeroed (RC watchdog acked)'.
- sema: also ack on every pass that sees the channel's put != get, so
  the ack does not depend on the ring reads (its VA is known from the
  first decode); idempotent.
- sema: never consume a zero-length/zero-VA GPFIFO entry as empty work.
  Two bogus zero entries consumed through a mis-resolved ring page
  pushed the watchdog userd's GPGet past the driver's own GPPut and
  every later userd probe then read get>put, permanently rejecting the
  channel's real userd. Hold such entries (bounded, per-channel
  counter persists through the pass snapshot).
- sema: a registered userd value that is a real guest PA (the
  watchdog's own block) outranks the ring+0x2000 convention guess the
  ring auto-pin applies for the CUDA GR layout.
- rm: log channel-class allocs whose params are too short for
  registration instead of skipping silently.

Remaining (next): under heavy GL traffic the watchdog ring's
translation can go stale for stretches (content-scanned map answering
where a pin used to), which starves the ack; pin the push/notifier
pages when the first real decode delivers them. The frame capture
(xshm_pub -> XShmGetImage) still stalls while that starvation is
active.

1 files changed, 177 insertions, 6 deletions

diff --git a/kernel/gsp_sema_service.c b/kernel/gsp_sema_service.c
index 1fa09d0..9d3697f 100644
--- a/kernel/gsp_sema_service.c
+++ b/kernel/gsp_sema_service.c
@@ -506,6 +506,20 @@ struct svc_channel {
 	 */
 	u8	userd_scans;
 	/*
+	 * r828: the RC watchdog's notifier VA, captured from the class2d
+	 * SET_NOTIFY_A/B methods on subchannel 3 and zeroed at the NOTIFY
+	 * (see svc_notify2d_write). Survives the pass snapshot via the
+	 * write-back list.
+	 */
+	u64	notify2d_va;
+	/* r829: bounded count of zero-entry (bad-translation) holds; see the
+	 * zero-entry hold in svc_pump_channels. Persists via the write-back. */
+	u32	zero_held;
+	/* r831: the registered userd value is a real guest PA (the driver's
+	 * own declaration; e.g. the RC watchdog channel). The ring auto-pin's
+	 * ring+0x2000 convention must not overwrite it. */
+	bool	userd_reg;
+	/*
 	 * r471: the completion-counter publish must never advance the
 	 * guest's word past a push whose content was still unwritten when
 	 * the entry was consumed (the streams_events staging-reuse
@@ -1562,6 +1576,16 @@ void gsp_sema_service_channel_add(const struct sema_channel_desc *desc)
 		ch->gpfifo_entries = desc->gpfifo_entries;
 		ch->userd_pa = desc->userd_pa;
 		ch->userd_as = desc->userd_as ? desc->userd_as : SVC_APERTURE_SYS;
+		/*
+		 * r831: a registered userd value that looks like a real guest
+		 * PA (the RC watchdog's channel carries its own userd block)
+		 * is the driver's own declaration and outranks the ring+0x2000
+		 * convention guess the ring auto-pin applies (that guess is
+		 * right for the CUDA GR layout, where the registered value is
+		 * pool-relative - observed 0x10000). Tiny registered values
+		 * stay guesses.
+		 */
+		ch->userd_reg = desc->userd_pa >= 0x10000000ULL;
 		ch->instance_pa = desc->instance_pa;
 		ch->notifier_pa = desc->notifier_pa;
 		ch->notifier_as = desc->notifier_as ? desc->notifier_as
@@ -3227,6 +3251,8 @@ static u32 svc_rdw_log;
  * appeared. Each scan reports its decision, a scan that found nothing
  * reportable logs a sweep summary. */
 static u32 svc_userdp_log;
+/* r829: bounded witness for the zero-entry holds (bad ring translations). */
+static u32 svc_zero_entry_log;
 static u8 svc_read_last_src;
 /* r715: PA the winning source of the last push read resolved to. */
 static u64 svc_read_last_pa;
@@ -10742,6 +10768,54 @@ static void svc_push_raw_dump(const u8 *buf, u32 len, u64 push_va,
 		h_object, push_va, off, len);
 }
 
+/*
+ * r828: the guest kernel's RC watchdog (krcWatchdog_IMPL, 7 s notify
+ * timeout) posts a notifier cycle on its own channel (object 0x31415900)
+ * through the class2d subchannel (NVA06F_SUBCHANNEL_2D = 3): SET_NOTIFY_A/B
+ * name the notifier VA, NOTIFY (WRITE_ONLY) is the GPU's "write a zeroed
+ * NvNotification" - the driver set the status word to 0xFFFF and declares
+ * "GPU is probably locked" when it never comes back as 0. Observed: robust
+ * channels enabled by the GL client (GZDOOM), then NVRM krcWatchdog every
+ * 8 s and Xorg dead on its screen readback. The emulation must author the
+ * notification write, exactly like svc_notify_complete does for the
+ * work-submit token.
+ */
+#define SVC_2D_SUBCH		3	/* NVA06F_SUBCHANNEL_2D */
+#define SVC_2D_SET_NOTIFY_A	0x0104	/* payload: addr bits [56:32] */
+#define SVC_2D_SET_NOTIFY_B	0x0108	/* payload: addr bits [31:0] */
+#define SVC_2D_NOTIFY		0x010c	/* payload: 0 = WRITE_ONLY */
+
+static u64 svc_notify2d_done;
+static u32 svc_notify2d_log;
+
+static void svc_notify2d_write(struct nv_vgpu_device *vgpu,
+			       struct svc_channel *ch)
+{
+	/* 16 bytes = the NvNotification (status word at +14). */
+	u8 zero[16] = { 0 };
+	u64 pa = 0;
+	int ap = SVC_APERTURE_SYS;
+
+	if (!ch->notify2d_va)
+		return;
+	if (svc_lookup(vgpu, ch->notify2d_va, &pa, &ap)) {
+		if (gsp_sema_dbg && svc_notify2d_log < 16) {
+			svc_notify2d_log++;
+			pr_info("sema-notify2d: h=0x%x va=0x%llx unresolved (RC watchdog notifier; guest re-posts every second)\n",
+				ch->h_object, ch->notify2d_va);
+		}
+		return;
+	}
+	if (svc_write_ap(vgpu, pa, svc_ap_of(ap), zero, sizeof(zero)))
+		return;
+	svc_notify2d_done++;
+	if (gsp_sema_dbg && svc_notify2d_log < 16) {
+		svc_notify2d_log++;
+		pr_info("sema-notify2d: h=0x%x va=0x%llx -> pa=0x%llx zeroed (RC watchdog acked)\n",
+			ch->h_object, ch->notify2d_va, pa);
+	}
+}
+
 static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf,
 			      u32 len, u64 page_pa, bool allow_ops,
 			      struct svc_channel *ch, u32 entry_idx,
@@ -11292,6 +11366,33 @@ static void svc_decode_stream(struct nv_vgpu_device *vgpu, const u8 *buf,
 			continue;
 		}
 
+		if (subch == SVC_2D_SUBCH && count >= 1 && addr >= 0x0100 &&
+		    addr <= 0x010c) {
+			/*
+			 * r828: the RC watchdog's notifier cycle (class2d
+			 * methods on subchannel 3). See svc_notify2d_write:
+			 * without the zeroed notification the guest's
+			 * krcWatchdog declares the GPU locked after 7 s and
+			 * the X/GL stack wedges on screen readback.
+			 */
+			switch (addr) {
+			case SVC_2D_SET_NOTIFY_A:
+				ch->notify2d_va = (u64)(v0 & 0x1ffffff) << 32;
+				break;
+			case SVC_2D_SET_NOTIFY_B:
+				ch->notify2d_va |= (u64)v0;
+				break;
+			case SVC_2D_NOTIFY:
+				if (count == 1 && v0 == 0)	/* WRITE_ONLY */
+					svc_notify2d_write(vgpu, ch);
+				break;
+			default:
+				break;
+			}
+			off += 4 + count * 4;
+			continue;
+		}
+
 		if (subch == 0 && addr == 0) {
 			/* SET_OBJECT on the channel subchannel: a push starts */
 			n_ops = 0;
@@ -16997,9 +17098,15 @@ static void svc_gr_ring_autopin(struct nv_vgpu_device *vgpu,
 						      &get);
 				svc_pin_store(ch->gpfifo_va, pin_pa, pin_ap);
 				svc_lat_store(ch->gpfifo_va, pin_pa, pin_ap);
-				ch->userd_pa = pin_pa + SVC_GR_USERD_OFF;
-				ch->userd_as = svc_ap_of(pin_ap);
-				ch->userd_ok = true;
+				/* r831: keep a registered real-PA userd. */
+				if (ch->userd_reg) {
+					ch->userd_ok = true;
+				} else {
+					ch->userd_pa =
+						pin_pa + SVC_GR_USERD_OFF;
+					ch->userd_as = svc_ap_of(pin_ap);
+					ch->userd_ok = true;
+				}
 				svc_gr_ring_base = base;
 				if (svc_ap_of(pin_ap) == SVC_APERTURE_FB)
 					svc_fb_claim_add(ch->h_object, pin_pa,
@@ -17036,9 +17143,19 @@ static void svc_gr_ring_autopin(struct nv_vgpu_device *vgpu,
 					  &get)) {
 			svc_pin_store(ch->gpfifo_va, wpa, wap);
 			svc_lat_store(ch->gpfifo_va, wpa, wap);
-			ch->userd_pa = wpa + SVC_GR_USERD_OFF;
-			ch->userd_as = wap;
-			ch->userd_ok = true;
+			/*
+			 * r831: the ring+0x2000 userd convention is a guess
+			 * for the CUDA GR layout; a channel whose REGISTERED
+			 * userd is a real PA (the RC watchdog) keeps its own
+			 * (the candidate gate above probes it as fallback).
+			 */
+			if (ch->userd_reg) {
+				ch->userd_ok = true;
+			} else {
+				ch->userd_pa = wpa + SVC_GR_USERD_OFF;
+				ch->userd_as = wap;
+				ch->userd_ok = true;
+			}
 			svc_gr_ring_base = wpa;
 			if (wap == SVC_APERTURE_FB)
 				svc_fb_claim_add(ch->h_object, wpa,
@@ -26782,6 +26899,23 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu)
 		}
 
 		/*
+		 * r832: the RC watchdog's notifier ack must not depend on the
+		 * ring reads. Its VA is known from the channel's first decode
+		 * (ch->notify2d_va, captured from SET_NOTIFY_A/B) and the ack
+		 * is the same zeroed NvNotification the decode path writes:
+		 * the guest re-arms status=0xFFFF every cycle and checks it
+		 * back to 0 within 7 s. Under heavy GL traffic the watchdog
+		 * ring's translation can go stale for stretches (its entries
+		 * then read as zeros and are consumed as empty), which starved
+		 * exactly this write and wedged the guest with "GPU is
+		 * probably locked" while every other channel kept running.
+		 * Writing the ack on every pass that sees work pending is
+		 * idempotent.
+		 */
+		if (!ch->engine_type && ch->notify2d_va && put != get)
+			svc_notify2d_write(vgpu, ch);
+
+		/*
 		 * ISSUE-0002 diag: put snapshots for CE channels, bounded per
 		 * session. The throttle is indexed by rank (the channel struct
 		 * iterated here is a local copy, so a per-channel stamp never
@@ -27224,6 +27358,40 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu)
 			}
 
 			/*
+			 * r829: a zero-length / zero-VA entry is a bad read
+			 * (a stale or wrong translation), never work. The old
+			 * path consumed it as an empty push and advanced
+			 * GPGet; observed r830 on the RC watchdog channel:
+			 * two bogus zero entries consumed through a
+			 * mis-resolved ring page pushed the userd's GPGet past
+			 * the driver's own GPPut, every later userd probe then
+			 * read get>put and the channel's REAL userd was
+			 * rejected - the channel stopped being serviced and
+			 * the guest declared the GPU locked. Hold the entry
+			 * instead (bounded; the per-channel counter persists
+			 * through the pass snapshot); a corrected translation
+			 * (the ring auto-pin lands within seconds) re-reads
+			 * it. Past the cap the old consume-as-empty behavior
+			 * resumes so an unresolvable ring cannot livelock the
+			 * channel.
+			 */
+			if (va == 0 || len == 0) {
+				if (ch->zero_held < 512 && !svc_hold_bypass()) {
+					ch->zero_held++;
+					svc.gpfifo_held++;
+					if (gsp_sema_dbg &&
+					    svc_zero_entry_log < 16) {
+						svc_zero_entry_log++;
+						pr_info("sema-chan: zero-entry hold h=0x%x idx=%llu raw=%08x%08x (bad ring translation; not consumed)\n",
+							ch->h_object, idx,
+							e1, e0);
+					}
+					stalled = true;
+					continue;
+				}
+			}
+
+			/*
 			 * Cheap wait for an entry already inside its
 			 * expensive-wait window: read + rescue + hold were
 			 * already paid for this VA, and a pin-batch rewind
@@ -29270,6 +29438,9 @@ static void svc_pump_channels(struct nv_vgpu_device *vgpu)
 				svc.chan[k].gr_ram_logged = ch->gr_ram_logged;
 				svc.chan[k].gr_ram_ring = ch->gr_ram_ring;
 				svc.chan[k].userd_scans = ch->userd_scans;
+				svc.chan[k].notify2d_va = ch->notify2d_va;
+				svc.chan[k].zero_held = ch->zero_held;
+				svc.chan[k].userd_reg = ch->userd_reg;
 				svc.chan[k].logged = ch->logged;
 				svc.chan[k].logged_expected = ch->logged_expected;
 				svc.chan[k].notified = ch->notified;