[Intel-gfx] [PATCH 2/2] drm/i915: Capture current context on error

[Ben Widawsky]

On error, this represents the state of the currently running context at
the time it was loaded.

Unfortunately, since we're hung and can't switch out the context this
may not tell us too much about the most current state of the context,
but does give clues about what has happened since loading.

Thanks to recent doc updates, we have a little more confidence regarding
what is actually in this memory, and perhaps it will help us gain more
insight into certain bugs. AFAICT, the most interesting info is in the
first page. To save space, we only capture the first page. In the
future, we might want to dump more.

Sample of the relevant part of error state:
--- HW Context = 0x01b20000
00000000 :  00000000 1100105f 00002028 ffff0880
00000010 :  0000209c feff4040 000020c0 efdf0080
00000020 :  00002178 00000001 0000217c 00145855
00000030 :  00002310 00000000 00002314 00000000
00000040 :  00002318 00000000 0000231c 00000000

References: https://bugs.freedesktop.org/show_bug.cgi?id=55845
Cc: Chris Wilson <chris at chris-wilson.co.uk>
Signed-off-by: Ben Widawsky <ben at bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_debugfs.c | 16 ++++++++++++++++
 drivers/gpu/drm/i915/i915_drv.h     |  1 +
 drivers/gpu/drm/i915/i915_irq.c     |  8 ++++++++
 3 files changed, 25 insertions(+)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 7c65ab8..b71d0ac 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -774,6 +774,22 @@ static int i915_error_state(struct seq_file *m, void *unused)
 		}
 	}
 
+	if (error->ctx_obj) {
+		struct drm_i915_error_object *obj = error->ctx_obj;
+		seq_printf(m, "--- HW Context = 0x%08x\n",
+			   obj->gtt_offset);
+		offset = 0;
+		for (elt = 0; elt < PAGE_SIZE/16; elt+=4) {
+			seq_printf(m, "%08x :  %08x %08x %08x %08x\n",
+				   offset,
+				   obj->pages[0][elt],
+				   obj->pages[0][elt+1],
+				   obj->pages[0][elt+2],
+				   obj->pages[0][elt+3]);
+				offset += 16;
+		}
+	}
+
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
 
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index e95337c..ab88620 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -209,6 +209,7 @@ struct drm_i915_error_state {
 	u32 pgtbl_er;
 	u32 ier;
 	u32 ccid;
+	struct drm_i915_error_object *ctx_obj;
 	u32 derrmr;
 	u32 forcewake;
 	bool waiting[I915_NUM_RINGS];
diff --git a/drivers/gpu/drm/i915/i915_irq.c b/drivers/gpu/drm/i915/i915_irq.c
index ebaf558..7f7d241 100644
--- a/drivers/gpu/drm/i915/i915_irq.c
+++ b/drivers/gpu/drm/i915/i915_irq.c
@@ -1321,6 +1321,14 @@ static void i915_capture_error_state(struct drm_device *dev)
 	error->pgtbl_er = I915_READ(PGTBL_ER);
 	error->ccid = I915_READ(CCID);
 
+	if (error->ccid && !dev_priv->hw_contexts_disabled) {
+		list_for_each_entry(obj, &dev_priv->mm.active_list, mm_list)
+			if ((error->ccid & PAGE_MASK) == obj->gtt_offset)
+				error->ctx_obj =
+					i915_error_object_create_sized(dev_priv,
+								       obj, 1);
+	}
+
 	if (HAS_PCH_SPLIT(dev))
 		error->ier = I915_READ(DEIER) | I915_READ(GTIER);
 	else if (IS_VALLEYVIEW(dev))
-- 
1.8.1.4