[Intel-gfx] [PATCH] drm/i915: Per-process stats work better when evaluated per-process

[Chris Wilson]

The idea of printing objects used by each process is to judge how each
process is using them. This means that we need to evaluate whether the
object is bound for that particular process, rather than just whether it
is bound into the global GTT.

Signed-off-by: Chris Wilson <chris at chris-wilson.co.uk>
Cc: Ben Widawsky <benjamin.widawsky at intel.com>
---
 drivers/gpu/drm/i915/i915_debugfs.c     | 34 ++++++++++++++++++++++++++-------
 drivers/gpu/drm/i915/i915_drv.h         |  2 ++
 drivers/gpu/drm/i915/i915_gem_context.c |  1 +
 3 files changed, 30 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_debugfs.c b/drivers/gpu/drm/i915/i915_debugfs.c
index 95a97ef45a3e..ab7b6f3b15df 100644
--- a/drivers/gpu/drm/i915/i915_debugfs.c
+++ b/drivers/gpu/drm/i915/i915_debugfs.c
@@ -299,28 +299,46 @@ static int i915_gem_stolen_list_info(struct seq_file *m, void *data)
 } while (0)
 
 struct file_stats {
+	struct drm_i915_file_private *file_priv;
 	int count;
-	size_t total, active, inactive, unbound;
+	size_t total, global, active, inactive, unbound;
 };
 
 static int per_file_stats(int id, void *ptr, void *data)
 {
 	struct drm_i915_gem_object *obj = ptr;
 	struct file_stats *stats = data;
+	struct i915_vma *vma;
 
 	stats->count++;
 	stats->total += obj->base.size;
 
-	if (i915_gem_obj_ggtt_bound(obj)) {
-		if (!list_empty(&obj->ring_list))
+	list_for_each_entry(vma, &obj->vma_list, vma_link) {
+		struct i915_hw_ppgtt *ppgtt;
+
+		if (!drm_mm_node_allocated(&vma->node))
+			continue;
+
+		ppgtt = container_of(vma->vm, struct i915_hw_ppgtt, base);
+		if (ppgtt->ctx == NULL) {
+			stats->global += obj->base.size;
+			continue;
+		}
+
+		if (ppgtt->ctx->file_priv != stats->file_priv)
+			continue;
+
+		if (obj->ring) /* XXX per-vma statistic */
 			stats->active += obj->base.size;
 		else
 			stats->inactive += obj->base.size;
-	} else {
-		if (!list_empty(&obj->global_list))
-			stats->unbound += obj->base.size;
+
+		return 0;
 	}
 
+	if (!list_empty(&obj->global_list))
+		stats->unbound += obj->base.size;
+
 	return 0;
 }
 
@@ -411,6 +429,7 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		struct task_struct *task;
 
 		memset(&stats, 0, sizeof(stats));
+		stats.file_priv = file->driver_priv;
 		idr_for_each(&file->object_idr, per_file_stats, &stats);
 		/*
 		 * Although we have a valid reference on file->pid, that does
@@ -420,12 +439,13 @@ static int i915_gem_object_info(struct seq_file *m, void* data)
 		 */
 		rcu_read_lock();
 		task = pid_task(file->pid, PIDTYPE_PID);
-		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu unbound)\n",
+		seq_printf(m, "%s: %u objects, %zu bytes (%zu active, %zu inactive, %zu global, %zu unbound)\n",
 			   task ? task->comm : "<unknown>",
 			   stats.count,
 			   stats.total,
 			   stats.active,
 			   stats.inactive,
+			   stats.global,
 			   stats.unbound);
 		rcu_read_unlock();
 	}
diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index 49f5ce77ef21..c4aa3f8c0ba4 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -684,6 +684,8 @@ struct i915_hw_ppgtt {
 		dma_addr_t *gen8_pt_dma_addr[4];
 	};
 
+	struct i915_hw_context *ctx;
+
 	int (*enable)(struct i915_hw_ppgtt *ppgtt);
 	int (*switch_mm)(struct i915_hw_ppgtt *ppgtt,
 			 struct intel_ring_buffer *ring,
diff --git a/drivers/gpu/drm/i915/i915_gem_context.c b/drivers/gpu/drm/i915/i915_gem_context.c
index 6bbf0654b9b5..a1692227b55b 100644
--- a/drivers/gpu/drm/i915/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/i915_gem_context.c
@@ -174,6 +174,7 @@ create_vm_for_ctx(struct drm_device *dev, struct i915_hw_context *ctx)
 		return ERR_PTR(ret);
 	}
 
+	ppgtt->ctx = ctx;
 	return ppgtt;
 }
 
-- 
1.9.rc1