drm/i915: Move GEM activity tracking into a common struct reservation…

…_object

In preparation to support many distinct timelines, we need to expand the
activity tracking on the GEM object to handle more than just a request
per engine. We already use the struct reservation_object on the dma-buf
to handle many fence contexts, so integrating that into the GEM object
itself is the preferred solution. (For example, we can now share the same
reservation_object between every consumer/producer using this buffer and
skip the manual import/export via dma-buf.)

v2: Reimplement busy-ioctl (by walking the reservation object), postpone
the ABI change for another day. Similarly use the reservation object to
find the last_write request (if active and from i915) for choosing
display CS flips.

Caveats:

 * busy-ioctl: busy-ioctl only reports on the native fences, it will not
warn of stalls (in set-domain-ioctl, pread/pwrite etc) if the object is
being rendered to by external fences. It also will not report the same
busy state as wait-ioctl (or polling on the dma-buf) in the same
circumstances. On the plus side, it does retain reporting of which
*i915* engines are engaged with this object.

 * non-blocking atomic modesets take a step backwards as the wait for
render completion blocks the ioctl. This is fixed in a subsequent
patch to use a fence instead for awaiting on the rendering, see
"drm/i915: Restore nonblocking awaits for modesetting"

 * dynamic array manipulation for shared-fences in reservation is slower
than the previous lockless static assignment (e.g. gem_exec_lut_handle
runtime on ivb goes from 42s to 66s), mainly due to atomic operations
(maintaining the fence refcounts).

 * loss of object-level retirement callbacks, emulated by VMA retirement
tracking.

 * minor loss of object-level last activity information from debugfs,
could be replaced with per-vma information if desired

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/20161028125858.23563-21-chris@chris-wilson.co.uk

drivers/gpu/drm/i915/i915_debugfs.c

@@ -136,11 +136,10 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	struct i915_vma *vma;
 	unsigned int frontbuffer_bits;
 	int pin_count = 0;
-	enum intel_engine_id id;
 
 	lockdep_assert_held(&obj->base.dev->struct_mutex);
 
-	seq_printf(m, "%pK: %c%c%c%c%c %8zdKiB %02x %02x [ ",
+	seq_printf(m, "%pK: %c%c%c%c%c %8zdKiB %02x %02x %s%s%s",
 		   &obj->base,
 		   get_active_flag(obj),
 		   get_pin_flag(obj),
@@ -149,14 +148,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		   get_pin_mapped_flag(obj),
 		   obj->base.size / 1024,
 		   obj->base.read_domains,
-		   obj->base.write_domain);
-	for_each_engine(engine, dev_priv, id)
-		seq_printf(m, "%x ",
-			   i915_gem_active_get_seqno(&obj->last_read[id],
-						     &obj->base.dev->struct_mutex));
-	seq_printf(m, "] %x %s%s%s",
-		   i915_gem_active_get_seqno(&obj->last_write,
-					     &obj->base.dev->struct_mutex),
+		   obj->base.write_domain,
 		   i915_cache_level_str(dev_priv, obj->cache_level),
 		   obj->mm.dirty ? " dirty" : "",
 		   obj->mm.madv == I915_MADV_DONTNEED ? " purgeable" : "");
@@ -187,8 +179,7 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08llx)", obj->stolen->start);
 
-	engine = i915_gem_active_get_engine(&obj->last_write,
-					    &dev_priv->drm.struct_mutex);
+	engine = i915_gem_object_last_write_engine(obj);
 	if (engine)
 		seq_printf(m, " (%s)", engine->name);
 

drivers/gpu/drm/i915/i915_drv.h

@@ -41,6 +41,7 @@
 #include <linux/intel-iommu.h>
 #include <linux/kref.h>
 #include <linux/pm_qos.h>
+#include <linux/reservation.h>
 #include <linux/shmem_fs.h>
 
 #include <drm/drmP.h>
@@ -2246,21 +2247,12 @@ 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.
-	 */
-#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)
 
 	/**
 	 * Have we taken a reference for the object for incomplete GPU
 	 * activity?
 	 */
-#define I915_BO_ACTIVE_REF (I915_BO_ACTIVE_SHIFT + I915_NUM_ENGINES)
+#define I915_BO_ACTIVE_REF 0
 
 	/*
 	 * Is the object to be mapped as read-only to the GPU
@@ -2281,6 +2273,7 @@ struct drm_i915_gem_object {
 
 	/** Count of VMA actually bound by this object */
 	unsigned int bind_count;
+	unsigned int active_count;
 	unsigned int pin_display;
 
 	struct {
@@ -2320,8 +2313,7 @@ struct drm_i915_gem_object {
 	 * read request. This allows for the CPU to read from an active
 	 * buffer by only waiting for the write to complete.
 	 */
-	struct i915_gem_active last_read[I915_NUM_ENGINES];
-	struct i915_gem_active last_write;
+	struct reservation_object *resv;
 
 	/** References from framebuffers, locks out tiling changes. */
 	unsigned long framebuffer_references;
@@ -2340,6 +2332,8 @@ struct drm_i915_gem_object {
 
 	/** for phys allocated objects */
 	struct drm_dma_handle *phys_handle;
+
+	struct reservation_object __builtin_resv;
 };
 
 static inline struct drm_i915_gem_object *
@@ -2425,35 +2419,10 @@ 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);
+	return obj->active_count;
 }
 
 static inline bool
@@ -2496,6 +2465,23 @@ i915_gem_object_get_stride(struct drm_i915_gem_object *obj)
 	return obj->tiling_and_stride & STRIDE_MASK;
 }
 
+static inline struct intel_engine_cs *
+i915_gem_object_last_write_engine(struct drm_i915_gem_object *obj)
+{
+	struct intel_engine_cs *engine = NULL;
+	struct dma_fence *fence;
+
+	rcu_read_lock();
+	fence = reservation_object_get_excl_rcu(obj->resv);
+	rcu_read_unlock();
+
+	if (fence && dma_fence_is_i915(fence) && !dma_fence_is_signaled(fence))
+		engine = to_request(fence)->engine;
+	dma_fence_put(fence);
+
+	return engine;
+}
+
 static inline struct i915_vma *i915_vma_get(struct i915_vma *vma)
 {
 	i915_gem_object_get(vma->obj);