[Intel-gfx] [PATCH] drm/i915: dump even more into the error_state

[Daniel Vetter]

Chris Wilson and me have again stared at funny error states and it's
been pretty clear from the start that something was seriously amiss.
The seqnos last seen by the cpu were a few hundred behind those that
the gpu could have possibly emitted last before it died ...

Chris now tracked it down (hopefully, definit verdict's still out),
but in hindsight we'd have found the bug by simply dumping the cpu
side tracking of the ring head and tail registers.

Fix this and prevent an identical time-waster in the future.

Because the hangs always involved semaphores in one way or another,
we've tried to dump the mbox registers, but couldn't find any
inconsistencies. Still, dump them too.

Signed-Off-by: Daniel Vetter <daniel.vetter at ffwll.ch>
---
 drivers/gpu/drm/i915/i915_debugfs.c |    6 ++++++
 drivers/gpu/drm/i915/i915_drv.h     |    4 ++++
 drivers/gpu/drm/i915/i915_irq.c     |    7 +++++++
 3 files changed, 17 insertions(+), 0 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 681cbe4..e9eeacb 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -721,8 +721,14 @@ static void i915_ring_error_state(struct seq_file *m,
 	if (INTEL_INFO(dev)->gen >= 6) {
 		seq_printf(m, "  FADDR: 0x%08x\n", error->faddr[ring]);
 		seq_printf(m, "  FAULT_REG: 0x%08x\n", error->fault_reg[ring]);
+		seq_printf(m, "  SYNC_0: 0x%08x\n",
+			   error->semaphore_mboxes[ring][0]);
+		seq_printf(m, "  SYNC_1: 0x%08x\n",
+			   error->semaphore_mboxes[ring][1]);
 	}
 	seq_printf(m, "  seqno: 0x%08x\n", error->seqno[ring]);
+	seq_printf(m, "  ring->head: 0x%08x\n", error->cpu_ring_head[ring]);
+	seq_printf(m, "  ring->tail: 0x%08x\n", error->cpu_ring_tail[ring]);
 }
 
 static int i915_error_state(struct seq_file *m, void *unused)
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 865de80..1eb3b9a 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -159,6 +159,10 @@ struct drm_i915_error_state {
 	u32 ipehr[I915_NUM_RINGS];
 	u32 instdone[I915_NUM_RINGS];
 	u32 acthd[I915_NUM_RINGS];
+	u32 semaphore_mboxes[I915_NUM_RINGS][I915_NUM_RINGS - 1];
+	/* our own tracking of ring head and tail */
+	u32 cpu_ring_head[I915_NUM_RINGS];
+	u32 cpu_ring_tail[I915_NUM_RINGS];
 	u32 error; /* gen6+ */
 	u32 instpm[I915_NUM_RINGS];
 	u32 instps[I915_NUM_RINGS];
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index 8ea1ca4..cde1ce9 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -903,6 +903,10 @@ static void i915_record_ring_state(struct drm_device *dev,
 	if (INTEL_INFO(dev)->gen >= 6) {
 		error->faddr[ring->id] = I915_READ(RING_DMA_FADD(ring->mmio_base));
 		error->fault_reg[ring->id] = I915_READ(RING_FAULT_REG(ring));
+		error->semaphore_mboxes[ring->id][0]
+			= I915_READ(RING_SYNC_0(ring->mmio_base));
+		error->semaphore_mboxes[ring->id][1]
+			= I915_READ(RING_SYNC_1(ring->mmio_base));
 	}
 
 	if (INTEL_INFO(dev)->gen >= 4) {
@@ -925,6 +929,9 @@ static void i915_record_ring_state(struct drm_device *dev,
 	error->acthd[ring->id] = intel_ring_get_active_head(ring);
 	error->head[ring->id] = I915_READ_HEAD(ring);
 	error->tail[ring->id] = I915_READ_TAIL(ring);
+
+	error->cpu_ring_head[ring->id] = ring->head;
+	error->cpu_ring_tail[ring->id] = ring->tail;
 }
 
 /**
-- 
1.7.8.3