[Nouveau] [PATCH 01/10] drm/nv50: decode PGRAPH status registers on TLB flush fail

[Marcin Slusarz]

On Mon, Aug 20, 2012 at 07:02:46PM +0200, Marcin Slusarz wrote:
> On Mon, Aug 20, 2012 at 04:27:18PM +1000, Ben Skeggs wrote:
> > On Sun, Aug 19, 2012 at 10:59:56PM +0200, Marcin Slusarz wrote:
> > > Now it outputs:
> > > nouveau E[  PGRAPH][0000:02:00.0] PGRAPH TLB flush idle timeout fail
> > > nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_STATUS: BUSY DISPATCH VFETCH CCACHE_UNK4 STRMOUT_GSCHED_UNK5 UNK14XX UNK1CXX CLIPID ZCULL ENG2D UNK34XX TPRAST TPROP ROP (0x011fde03)
> > > nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_VSTATUS_0: CCACHE (0x00145b4d)
> > > nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_VSTATUS_1: (0x0000002d)
> > > nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_VSTATUS_2: ENG2D ROP (0x0034db40)
> > > 
> > > instead of:
> > > [drm] nouveau 0000:02:00.0: PGRAPH TLB flush idle timeout fail: 0x011fde03 0x00145b4d 0x0000002d 0x0034db40
> > 
> > I didn't push these first few patches yet as I have a couple of thoughts on it.
> > 
> > Mostly I was thinking we should probably have a:
> > 
> > nv_printf(obj, lvl, fmt, args...)
> > 
> > to replace the printk's which just does a continued print while still obeying
> > the debug level?
> 
> Well, this patch does not use nv_printk_enabled, so these concerns should
> not apply to it, right? I'll fix up bitfield list and resend it.

---
From: Marcin Slusarz <marcin.slusarz at gmail.com>
Subject: [PATCH] drm/nv50: decode PGRAPH status registers on TLB flush fail

Now it outputs:
nouveau E[  PGRAPH][0000:02:00.0] PGRAPH TLB flush idle timeout fail
nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_STATUS: BUSY DISPATCH VFETCH CCACHE_UNK4 STRMOUT_GSCHED_UNK5 UNK14XX UNK1CXX CLIPID ZCULL ENG2D UNK34XX TPRAST TPROP ROP (0x011fde03)
nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_VSTATUS_0: CCACHE (0x00145b4d)
nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_VSTATUS_1: (0x0000002d)
nouveau E[  PGRAPH][0000:02:00.0] PGRAPH_VSTATUS_2: ENG2D ROP (0x0034db40)

instead of:
[drm] nouveau 0000:02:00.0: PGRAPH TLB flush idle timeout fail: 0x011fde03 0x00145b4d 0x0000002d 0x0034db40

Based on envytools docs.

Signed-off-by: Marcin Slusarz <marcin.slusarz at gmail.com>
---
 drivers/gpu/drm/nouveau/core/engine/graph/nv50.c |   78 ++++++++++++++++++++-
 1 files changed, 74 insertions(+), 4 deletions(-)

diff --git a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
index c93b525..3789bd2 100644
--- a/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
+++ b/drivers/gpu/drm/nouveau/core/engine/graph/nv50.c
@@ -184,6 +184,62 @@ nv50_graph_tlb_flush(struct nouveau_engine *engine)
 	return 0;
 }
 
+static const struct nouveau_bitfield nv50_pgraph_status[] = {
+	{ 0x00000001, "BUSY" }, /* set when any bit is set */
+	{ 0x00000002, "DISPATCH" },
+	{ 0x00000004, "UNK2" },
+	{ 0x00000008, "UNK3" },
+	{ 0x00000010, "UNK4" },
+	{ 0x00000020, "UNK5" },
+	{ 0x00000040, "M2MF" },
+	{ 0x00000080, "UNK7" },
+	{ 0x00000100, "CTXPROG" },
+	{ 0x00000200, "VFETCH" },
+	{ 0x00000400, "CCACHE_UNK4" },
+	{ 0x00000800, "STRMOUT_GSCHED_UNK5" },
+	{ 0x00001000, "UNK14XX" },
+	{ 0x00002000, "UNK24XX_CSCHED" },
+	{ 0x00004000, "UNK1CXX" },
+	{ 0x00008000, "CLIPID" },
+	{ 0x00010000, "ZCULL" },
+	{ 0x00020000, "ENG2D" },
+	{ 0x00040000, "UNK34XX" },
+	{ 0x00080000, "TPRAST" },
+	{ 0x00100000, "TPROP" },
+	{ 0x00200000, "TEX" },
+	{ 0x00400000, "TPVP" },
+	{ 0x00800000, "MP" },
+	{ 0x01000000, "ROP" },
+	{}
+};
+
+static const char *const nv50_pgraph_vstatus_0[] = {
+	"VFETCH", "CCACHE", "UNK4", "UNK5", "GSCHED", "STRMOUT", "UNK14XX", NULL
+};
+
+static const char *const nv50_pgraph_vstatus_1[] = {
+	"TPRAST", "TPROP", "TEXTURE", "TPVP", "MP", NULL
+};
+
+static const char *const nv50_pgraph_vstatus_2[] = {
+	"UNK24XX", "CSCHED", "UNK1CXX", "CLIPID", "ZCULL", "ENG2D", "UNK34XX",
+	"ROP", NULL
+};
+
+static void nouveau_pgraph_vstatus_print(const char *const units[], u32 status)
+{
+	int i;
+	u32 tmp = status;
+	for (i = 0; units[i] && tmp; i++) {
+		if ((tmp & 7) == 1)
+			pr_cont("%s ", units[i]);
+		tmp >>= 3;
+	}
+	if (tmp)
+		pr_cont("invalid: %x ", tmp);
+	pr_cont("(0x%08x)\n", status);
+}
+
 static int
 nv84_graph_tlb_flush(struct nouveau_engine *engine)
 {
@@ -219,10 +275,24 @@ nv84_graph_tlb_flush(struct nouveau_engine *engine)
 		 !(timeout = ptimer->read(ptimer) - start > 2000000000));
 
 	if (timeout) {
-		nv_error(priv, "PGRAPH TLB flush idle timeout fail: "
-			      "0x%08x 0x%08x 0x%08x 0x%08x\n",
-			 nv_rd32(priv, 0x400700), nv_rd32(priv, 0x400380),
-			 nv_rd32(priv, 0x400384), nv_rd32(priv, 0x400388));
+		nv_error(priv, "PGRAPH TLB flush idle timeout fail\n");
+
+		nv_error(priv, "PGRAPH_STATUS: ");
+		tmp = nv_rd32(priv, 0x400700);
+		nouveau_bitfield_print(nv50_pgraph_status, tmp);
+		pr_cont(" (0x%08x)\n", tmp);
+
+		nv_error(priv, "PGRAPH_VSTATUS_0: ");
+		nouveau_pgraph_vstatus_print(nv50_pgraph_vstatus_0,
+				nv_rd32(priv, 0x400380));
+
+		nv_error(priv, "PGRAPH_VSTATUS_1: ");
+		nouveau_pgraph_vstatus_print(nv50_pgraph_vstatus_1,
+				nv_rd32(priv, 0x400384));
+
+		nv_error(priv, "PGRAPH_VSTATUS_2: ");
+		nouveau_pgraph_vstatus_print(nv50_pgraph_vstatus_2,
+				nv_rd32(priv, 0x400388));
 	}
 
 	nv50_vm_flush_engine(&engine->base, 0x00);
-- 
1.7.8.6