drm/i915/bdw: collect semaphore error state

Since the semaphore information is in an object, just dump it, and let
the user parse it later.

NOTE: The page being used for the semaphores are incoherent with the
CPU. No matter what I do, I cannot figure out a way to read anything but
0s. Note that the semaphore waits are indeed working.

v2: Don't print signal, and wait (they should be the same). Instead,
print sync_seqno (Chris)

v3: Free the semaphore error object (Chris)

v4: Fix semaphore offset calculation during error state collection
(Ville)

v5: VCS2 rebase
Make semaphore object error capture coding style consistent (Ville)
Do the proper math for the signal offset (Ville)

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>

3 files changed, 55 insertions, 11 deletions

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 1ede81863d5c..c82b593780e5 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -328,6 +328,7 @@ struct drm_i915_error_state {
 	u64 fence[I915_MAX_NUM_FENCES];
 	struct intel_overlay_error_state *overlay;
 	struct intel_display_error_state *display;
+	struct drm_i915_error_object *semaphore_obj;
 
 	struct drm_i915_error_ring {
 		bool valid;
diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index a7eaab20eddc..50d2af8c0e4f 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -326,6 +326,7 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 	struct drm_device *dev = error_priv->dev;
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_error_state *error = error_priv->error;
+	struct drm_i915_error_object *obj;
 	int i, j, offset, elt;
 	int max_hangcheck_score;
 
@@ -394,8 +395,6 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 				    error->pinned_bo_count[0]);
 
 	for (i = 0; i < ARRAY_SIZE(error->ring); i++) {
-		struct drm_i915_error_object *obj;
-
 		obj = error->ring[i].batchbuffer;
 		if (obj) {
 			err_puts(m, dev_priv->ring[i].name);
@@ -458,6 +457,18 @@ int i915_error_state_to_str(struct drm_i915_error_state_buf *m,
 		}
 	}
 
+	if ((obj = error->semaphore_obj)) {
+		err_printf(m, "Semaphore page = 0x%08x\n", obj->gtt_offset);
+		for (elt = 0; elt < PAGE_SIZE/16; elt += 4) {
+			err_printf(m, "[%04x] %08x %08x %08x %08x\n",
+				   elt * 4,
+				   obj->pages[0][elt],
+				   obj->pages[0][elt+1],
+				   obj->pages[0][elt+2],
+				   obj->pages[0][elt+3]);
+		}
+	}
+
 	if (error->overlay)
 		intel_overlay_print_error_state(m, error->overlay);
 
@@ -528,6 +539,7 @@ static void i915_error_state_free(struct kref *error_ref)
 		kfree(error->ring[i].requests);
 	}
 
+	i915_error_object_free(error->semaphore_obj);
 	kfree(error->active_bo);
 	kfree(error->overlay);
 	kfree(error->display);
@@ -745,6 +757,33 @@ static void i915_gem_record_fences(struct drm_device *dev,
 }
 
 
+static void gen8_record_semaphore_state(struct drm_i915_private *dev_priv,
+					struct drm_i915_error_state *error,
+					struct intel_ring_buffer *ring,
+					struct drm_i915_error_ring *ering)
+{
+	struct intel_ring_buffer *useless;
+	int i;
+
+	if (!i915_semaphore_is_enabled(dev_priv->dev))
+		return;
+
+	if (!error->semaphore_obj)
+		error->semaphore_obj =
+			i915_error_object_create(dev_priv,
+						 dev_priv->semaphore_obj,
+						 &dev_priv->gtt.base);
+
+	for_each_ring(useless, dev_priv, i) {
+		u16 signal_offset =
+			(GEN8_SIGNAL_OFFSET(ring, i) & PAGE_MASK) / 4;
+		u32 *tmp = error->semaphore_obj->pages[0];
+
+		ering->semaphore_mboxes[i] = tmp[signal_offset];
+		ering->semaphore_seqno[i] = ring->semaphore.sync_seqno[i];
+	}
+}
+
 static void gen6_record_semaphore_state(struct drm_i915_private *dev_priv,
 					struct intel_ring_buffer *ring,
 					struct drm_i915_error_ring *ering)
@@ -762,6 +801,7 @@ static void gen6_record_semaphore_state(struct drm_i915_private *dev_priv,
 }
 
 static void i915_record_ring_state(struct drm_device *dev,
+				   struct drm_i915_error_state *error,
 				   struct intel_ring_buffer *ring,
 				   struct drm_i915_error_ring *ering)
 {
@@ -770,7 +810,10 @@ static void i915_record_ring_state(struct drm_device *dev,
 	if (INTEL_INFO(dev)->gen >= 6) {
 		ering->rc_psmi = I915_READ(ring->mmio_base + 0x50);
 		ering->fault_reg = I915_READ(RING_FAULT_REG(ring));
-		gen6_record_semaphore_state(dev_priv, ring, ering);
+		if (INTEL_INFO(dev)->gen >= 8)
+			gen8_record_semaphore_state(dev_priv, error, ring, ering);
+		else
+			gen6_record_semaphore_state(dev_priv, ring, ering);
 	}
 
 	if (INTEL_INFO(dev)->gen >= 4) {
@@ -897,7 +940,7 @@ static void i915_gem_record_rings(struct drm_device *dev,
 
 		error->ring[i].valid = true;
 
-		i915_record_ring_state(dev, ring, &error->ring[i]);
+		i915_record_ring_state(dev, error, ring, &error->ring[i]);
 
 		error->ring[i].pid = -1;
 		request = i915_gem_find_active_request(ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ff20d11e82af..3cafdbcd415d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -40,9 +40,9 @@ struct  intel_hw_status_page {
  * do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
  */
 #define i915_semaphore_seqno_size sizeof(uint64_t)
-#define GEN8_SIGNAL_OFFSET(to) \
+#define GEN8_SIGNAL_OFFSET(__ring, to) \
 	(i915_gem_obj_ggtt_offset(dev_priv->semaphore_obj) + \
-	(ring->id * I915_NUM_RINGS * i915_semaphore_seqno_size) + \
+	((__ring)->id * I915_NUM_RINGS * i915_semaphore_seqno_size) + \
 	(i915_semaphore_seqno_size * (to)))
 
 #define GEN8_WAIT_OFFSET(__ring, from) \
@@ -54,11 +54,11 @@ struct  intel_hw_status_page {
 	if (!dev_priv->semaphore_obj) { \
 		break; \
 	} \
-	ring->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET(RCS); \
-	ring->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET(VCS); \
-	ring->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET(BCS); \
-	ring->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET(VECS); \
-	ring->semaphore.signal_ggtt[VCS2] = GEN8_SIGNAL_OFFSET(VCS2); \
+	ring->semaphore.signal_ggtt[RCS] = GEN8_SIGNAL_OFFSET(ring, RCS); \
+	ring->semaphore.signal_ggtt[VCS] = GEN8_SIGNAL_OFFSET(ring, VCS); \
+	ring->semaphore.signal_ggtt[BCS] = GEN8_SIGNAL_OFFSET(ring, BCS); \
+	ring->semaphore.signal_ggtt[VECS] = GEN8_SIGNAL_OFFSET(ring, VECS); \
+	ring->semaphore.signal_ggtt[VCS2] = GEN8_SIGNAL_OFFSET(ring, VCS2); \
 	ring->semaphore.signal_ggtt[ring->id] = MI_SEMAPHORE_SYNC_INVALID; \
 	} while(0)