drm/i915: Move obj->active:5 to obj->flags

We are motivated to avoid using a bitfield for obj->active for a couple
of reasons. Firstly, we wish to document our lockless read of obj->active
using READ_ONCE inside i915_gem_busy_ioctl() and that requires an
integral type (i.e. not a bitfield). Secondly, gcc produces abysmal code
when presented with a bitfield and that shows up high on the profiles of
request tracking (mainly due to excess memory traffic as it converts
the bitfield to a register and back and generates frequent AGI in the
process).

v2: BIT, break up a long line in compute the other engines, new paint
for i915_gem_object_is_active (now i915_gem_object_get_active).
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1470324762-2545-23-git-send-email-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_debugfs.c

@@ -91,7 +91,7 @@ static int i915_capabilities(struct seq_file *m, void *data)
 
 static char get_active_flag(struct drm_i915_gem_object *obj)
 {
-	return obj->active ? '*' : ' ';
+	return i915_gem_object_is_active(obj) ? '*' : ' ';
 }
 
 static char get_pin_flag(struct drm_i915_gem_object *obj)

drivers/gpu/drm/i915/i915_drv.h

@@ -2155,12 +2155,16 @@ struct drm_i915_gem_object {
 
 	struct list_head batch_pool_link;
 
+	unsigned long flags;
 	/**
 	 * This is set if the object is on the active lists (has pending
 	 * rendering and so a non-zero seqno), and is not set if it i s on
 	 * inactive (ready to be unbound) list.
 	 */
-	unsigned int active:I915_NUM_ENGINES;
+#define I915_BO_ACTIVE_SHIFT 0
+#define I915_BO_ACTIVE_MASK ((1 << I915_NUM_ENGINES) - 1)
+#define __I915_BO_ACTIVE(bo) \
+	((READ_ONCE((bo)->flags) >> I915_BO_ACTIVE_SHIFT) & I915_BO_ACTIVE_MASK)
 
 	/**
 	 * This is set if the object has been written to since last bound
@@ -2325,6 +2329,37 @@ i915_gem_object_has_struct_page(const struct drm_i915_gem_object *obj)
 	return obj->ops->flags & I915_GEM_OBJECT_HAS_STRUCT_PAGE;
 }
 
+static inline unsigned long
+i915_gem_object_get_active(const struct drm_i915_gem_object *obj)
+{
+	return (obj->flags >> I915_BO_ACTIVE_SHIFT) & I915_BO_ACTIVE_MASK;
+}
+
+static inline bool
+i915_gem_object_is_active(const struct drm_i915_gem_object *obj)
+{
+	return i915_gem_object_get_active(obj);
+}
+
+static inline void
+i915_gem_object_set_active(struct drm_i915_gem_object *obj, int engine)
+{
+	obj->flags |= BIT(engine + I915_BO_ACTIVE_SHIFT);
+}
+
+static inline void
+i915_gem_object_clear_active(struct drm_i915_gem_object *obj, int engine)
+{
+	obj->flags &= ~BIT(engine + I915_BO_ACTIVE_SHIFT);
+}
+
+static inline bool
+i915_gem_object_has_active_engine(const struct drm_i915_gem_object *obj,
+				  int engine)
+{
+	return obj->flags & BIT(engine + I915_BO_ACTIVE_SHIFT);
+}
+
 /*
  * Optimised SGL iterator for GEM objects
  */

drivers/gpu/drm/i915/i915_gem.c

@@ -1358,7 +1358,7 @@ i915_gem_object_wait_rendering(struct drm_i915_gem_object *obj,
 
 	if (!readonly) {
 		active = obj->last_read;
-		active_mask = obj->active;
+		active_mask = i915_gem_object_get_active(obj);
 	} else {
 		active_mask = 1;
 		active = &obj->last_write;
@@ -1402,7 +1402,7 @@ i915_gem_object_wait_rendering__nonblocking(struct drm_i915_gem_object *obj,
 	BUG_ON(!mutex_is_locked(&dev->struct_mutex));
 	BUG_ON(!dev_priv->mm.interruptible);
 
-	active_mask = obj->active;
+	active_mask = i915_gem_object_get_active(obj);
 	if (!active_mask)
 		return 0;
 
@@ -2365,10 +2365,10 @@ i915_gem_object_retire__read(struct i915_gem_active *active,
 	struct drm_i915_gem_object *obj =
 		container_of(active, struct drm_i915_gem_object, last_read[idx]);
 
-	GEM_BUG_ON((obj->active & (1 << idx)) == 0);
+	GEM_BUG_ON(!i915_gem_object_has_active_engine(obj, idx));
 
-	obj->active &= ~(1 << idx);
-	if (obj->active)
+	i915_gem_object_clear_active(obj, idx);
+	if (i915_gem_object_is_active(obj))
 		return;
 
 	/* Bump our place on the bound list to keep it roughly in LRU order
@@ -2672,7 +2672,7 @@ i915_gem_wait_ioctl(struct drm_device *dev, void *data, struct drm_file *file)
 		return -ENOENT;
 	}
 
-	if (!obj->active)
+	if (!i915_gem_object_is_active(obj))
 		goto out;
 
 	for (i = 0; i < I915_NUM_ENGINES; i++) {
@@ -2760,7 +2760,7 @@ i915_gem_object_sync(struct drm_i915_gem_object *obj,
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
-	active_mask = obj->active;
+	active_mask = i915_gem_object_get_active(obj);
 	if (!active_mask)
 		return 0;
 
@@ -3811,7 +3811,7 @@ i915_gem_busy_ioctl(struct drm_device *dev, void *data,
 	 * become non-busy without any further actions.
 	 */
 	args->busy = 0;
-	if (obj->active) {
+	if (i915_gem_object_is_active(obj)) {
 		struct drm_i915_gem_request *req;
 		int i;
 

drivers/gpu/drm/i915/i915_gem_execbuffer.c

@@ -434,7 +434,7 @@ relocate_entry_clflush(struct drm_i915_gem_object *obj,
 
 static bool object_is_idle(struct drm_i915_gem_object *obj)
 {
-	unsigned long active = obj->active;
+	unsigned long active = i915_gem_object_get_active(obj);
 	int idx;
 
 	for_each_active(active, idx) {
@@ -990,11 +990,21 @@ i915_gem_execbuffer_relocate_slow(struct drm_device *dev,
 	return ret;
 }
 
+static unsigned int eb_other_engines(struct drm_i915_gem_request *req)
+{
+	unsigned int mask;
+
+	mask = ~intel_engine_flag(req->engine) & I915_BO_ACTIVE_MASK;
+	mask <<= I915_BO_ACTIVE_SHIFT;
+
+	return mask;
+}
+
 static int
 i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 				struct list_head *vmas)
 {
-	const unsigned other_rings = ~intel_engine_flag(req->engine);
+	const unsigned int other_rings = eb_other_engines(req);
 	struct i915_vma *vma;
 	uint32_t flush_domains = 0;
 	bool flush_chipset = false;
@@ -1003,7 +1013,7 @@ i915_gem_execbuffer_move_to_gpu(struct drm_i915_gem_request *req,
 	list_for_each_entry(vma, vmas, exec_list) {
 		struct drm_i915_gem_object *obj = vma->obj;
 
-		if (obj->active & other_rings) {
+		if (obj->flags & other_rings) {
 			ret = i915_gem_object_sync(obj, req);
 			if (ret)
 				return ret;
@@ -1166,9 +1176,9 @@ void i915_vma_move_to_active(struct i915_vma *vma,
 	 * add the active reference first and queue for it to be dropped
 	 * *last*.
 	 */
-	if (obj->active == 0)
+	if (!i915_gem_object_is_active(obj))
 		i915_gem_object_get(obj);
-	obj->active |= 1 << idx;
+	i915_gem_object_set_active(obj, idx);
 	i915_gem_active_set(&obj->last_read[idx], req);
 
 	if (flags & EXEC_OBJECT_WRITE) {

drivers/gpu/drm/i915/i915_gem_shrinker.c

@@ -182,7 +182,8 @@ i915_gem_shrink(struct drm_i915_private *dev_priv,
 			    !is_vmalloc_addr(obj->mapping))
 				continue;
 
-			if ((flags & I915_SHRINK_ACTIVE) == 0 && obj->active)
+			if ((flags & I915_SHRINK_ACTIVE) == 0 &&
+			    i915_gem_object_is_active(obj))
 				continue;
 
 			if (!can_release_pages(obj))
@@ -267,7 +268,7 @@ i915_gem_shrinker_count(struct shrinker *shrinker, struct shrink_control *sc)
 			count += obj->base.size >> PAGE_SHIFT;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if (!obj->active && can_release_pages(obj))
+		if (!i915_gem_object_is_active(obj) && can_release_pages(obj))
 			count += obj->base.size >> PAGE_SHIFT;
 	}
 

drivers/gpu/drm/i915/i915_gem_userptr.c

@@ -67,7 +67,7 @@ static void wait_rendering(struct drm_i915_gem_object *obj)
 	struct drm_i915_gem_request *requests[I915_NUM_ENGINES];
 	int i, n;
 
-	if (!obj->active)
+	if (!i915_gem_object_is_active(obj))
 		return;
 
 	n = 0;