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)

v6: Fix small conflicts on rebase and s/ring_buffer/engine_cs (Rodrigo)

Reviewed-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniel Vetter <daniel.vetter@ffwll.ch>

1 files changed, 47 insertions, 4 deletions

diff --git a/drivers/gpu/drm/i915/i915_gpu_error.c b/drivers/gpu/drm/i915/i915_gpu_error.c
index 9d42b6a8b545..45b6191efb58 100644
--- a/drivers/gpu/drm/i915/i915_gpu_error.c
+++ b/drivers/gpu/drm/i915/i915_gpu_error.c
@@ -327,6 +327,7 @@ 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;
 
@@ -395,8 +396,6 @@ 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);
@@ -459,6 +458,18 @@ 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);
 
@@ -529,6 +540,7 @@ 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);
@@ -747,6 +759,33 @@ 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_engine_cs *ring,
+                                        struct drm_i915_error_ring *ering)
+{
+        struct intel_engine_cs *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_engine_cs *ring,
                                         struct drm_i915_error_ring *ering)
@@ -764,6 +803,7 @@ 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_engine_cs *ring,
                                    struct drm_i915_error_ring *ering)
 {
@@ -772,7 +812,10 @@ 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) {
@@ -901,7 +944,7 @@ 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]);
 
                 request = i915_gem_find_active_request(ring);
                 if (request) {