Skip to contentSkip to conversation

Revert "drm/i915: Getter/setter for object attributes"

PATCH In review Ben Widawsky 2 participants 10 messages Jul 5, 2013

Subsystems (3)
lore
Share & tools
lore
#0 lore raw

PATCH 1/9 Revert "drm/i915: Getter/setter for object attributes"

This reverts commit 3c7354329d77c333dab8647676c3de342f022dc9.

---
 drivers/gpu/drm/i915/i915_debugfs.c        | 26 ++++-----
 drivers/gpu/drm/i915/i915_drv.h            | 31 -----------
 drivers/gpu/drm/i915/i915_gem.c            | 89 +++++++++++++++---------------
 drivers/gpu/drm/i915/i915_gem_context.c    |  2 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 19 +++----
 drivers/gpu/drm/i915/i915_gem_gtt.c        | 14 ++---
 drivers/gpu/drm/i915/i915_gem_tiling.c     | 14 ++---
 drivers/gpu/drm/i915/i915_irq.c            | 15 ++---
 drivers/gpu/drm/i915/i915_trace.h          |  8 +--
 drivers/gpu/drm/i915/intel_display.c       | 28 +++++-----
 drivers/gpu/drm/i915/intel_fb.c            |  8 +--
 drivers/gpu/drm/i915/intel_overlay.c       | 14 ++---
 drivers/gpu/drm/i915/intel_pm.c            |  8 +--
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 12 ++--
 drivers/gpu/drm/i915/intel_sprite.c        |  8 +--
 15 files changed, 129 insertions(+), 167 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +12 -14
index 396387e..3e36756 100644
@@ -122,9 +122,9 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (pinned x %d)", obj->pin_count);
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
-	if (i915_gem_obj_ggtt_bound(obj))
-		seq_printf(m, " (gtt offset: %08lx, size: %08x)",
-			   i915_gem_obj_ggtt_offset(obj), (unsigned int)i915_gem_obj_ggtt_size(obj));
+	if (obj->gtt_space != NULL)
+		seq_printf(m, " (gtt offset: %08x, size: %08x)",
+			   obj->gtt_offset, (unsigned int)obj->gtt_space->size);
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08lx)", obj->stolen->start);
 	if (obj->pin_mappable || obj->fault_mappable) {
@@ -175,7 +175,7 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += i915_gem_obj_ggtt_size(obj);
+		total_gtt_size += obj->gtt_space->size;
 		count++;
 	}
 	mutex_unlock(&dev->struct_mutex);
@@ -187,10 +187,10 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 
 #define count_objects(list, member) do { \
 	list_for_each_entry(obj, list, member) { \
-		size += i915_gem_obj_ggtt_size(obj); \
+		size += obj->gtt_space->size; \
 		++count; \
 		if (obj->map_and_fenceable) { \
-			mappable_size += i915_gem_obj_ggtt_size(obj); \
+			mappable_size += obj->gtt_space->size; \
 			++mappable_count; \
 		} \
 	} \
@@ -209,7 +209,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 	stats->count++;
 	stats->total += obj->base.size;
 
-	if (i915_gem_obj_ggtt_bound(obj)) {
+	if (obj->gtt_space) {
 		if (!list_empty(&obj->ring_list))
 			stats->active += obj->base.size;
 		else
@@ -267,11 +267,11 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 	size = count = mappable_size = mappable_count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if (obj->fault_mappable) {
-			size += i915_gem_obj_ggtt_size(obj);
+			size += obj->gtt_space->size;
 			++count;
 		}
 		if (obj->pin_mappable) {
-			mappable_size += i915_gem_obj_ggtt_size(obj);
+			mappable_size += obj->gtt_space->size;
 			++mappable_count;
 		}
 		if (obj->madv == I915_MADV_DONTNEED) {
@@ -333,7 +333,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += i915_gem_obj_ggtt_size(obj);
+		total_gtt_size += obj->gtt_space->size;
 		count++;
 	}
 
@@ -379,14 +379,12 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 			if (work->old_fb_obj) {
 				struct drm_i915_gem_object *obj = work->old_fb_obj;
 				if (obj)
-					seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n",
-						   i915_gem_obj_ggtt_offset(obj));
+					seq_printf(m, "Old framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
 			}
 			if (work->pending_flip_obj) {
 				struct drm_i915_gem_object *obj = work->pending_flip_obj;
 				if (obj)
-					seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n",
-						   i915_gem_obj_ggtt_offset(obj));
+					seq_printf(m, "New framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
 			}
 		}
 		spin_unlock_irqrestore(&dev->event_lock, flags);
drivers/gpu/drm/i915/i915_drv.h +0 -31
index ea86ad6..c80521c 100644
@@ -1354,37 +1354,6 @@ struct drm_i915_gem_object {
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
-/* Offset of the first PTE pointing to this object */
-static inline unsigned long
-i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
-{
-	return o->gtt_space->start;
-}
-
-/* Whether or not this object is currently mapped by the translation tables */
-static inline bool
-i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
-{
-	return o->gtt_space != NULL;
-}
-
-/* The size used in the translation tables may be larger than the actual size of
- * the object on GEN2/GEN3 because of the way tiling is handled. See
- * i915_gem_get_gtt_size() for more details.
- */
-static inline unsigned long
-i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
-{
-	return o->gtt_space->size;
-}
-
-static inline void
-i915_gem_obj_ggtt_set_color(struct drm_i915_gem_object *o,
-			    enum i915_cache_level color)
-{
-	o->gtt_space->color = color;
-}
-
 /**
  * Request queue structure.
  *
drivers/gpu/drm/i915/i915_gem.c +44 -45

253 lines not on this page · raw message

drivers/gpu/drm/i915/i915_gem_context.c +1 -1
index 2074544..51b7a21 100644
@@ -377,7 +377,7 @@ mi_set_context(struct intel_ring_buffer *ring,
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->obj) |
+	intel_ring_emit(ring, new_context->obj->gtt_offset |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
drivers/gpu/drm/i915/i915_gem_execbuffer.c +9 -10
index 5aeb447..87a3227 100644
@@ -188,7 +188,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -ENOENT;
 
 	target_i915_obj = to_intel_bo(target_obj);
-	target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
+	target_offset = target_i915_obj->gtt_offset;
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -280,7 +280,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			return ret;
 
 		/* Map the page containing the relocation we're going to perform.  */
-		reloc->offset += i915_gem_obj_ggtt_offset(obj);
+		reloc->offset += obj->gtt_offset;
 		reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
 						      reloc->offset & PAGE_MASK);
 		reloc_entry = (uint32_t __iomem *)
@@ -436,8 +436,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->has_aliasing_ppgtt_mapping = 1;
 	}
 
-	if (entry->offset != i915_gem_obj_ggtt_offset(obj)) {
-		entry->offset = i915_gem_obj_ggtt_offset(obj);
+	if (entry->offset != obj->gtt_offset) {
+		entry->offset = obj->gtt_offset;
 		*need_reloc = true;
 	}
 
@@ -458,7 +458,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_gem_exec_object2 *entry;
 
-	if (!i915_gem_obj_ggtt_bound(obj))
+	if (!obj->gtt_space)
 		return;
 
 	entry = obj->exec_entry;
@@ -530,7 +530,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 			bool need_fence, need_mappable;
 
-			if (!i915_gem_obj_ggtt_bound(obj))
+			if (!obj->gtt_space)
 				continue;
 
 			need_fence =
@@ -539,8 +539,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 				obj->tiling_mode != I915_TILING_NONE;
 			need_mappable = need_fence || need_reloc_mappable(obj);
 
-			if ((entry->alignment &&
-			     i915_gem_obj_ggtt_offset(obj) & (entry->alignment - 1)) ||
+			if ((entry->alignment && obj->gtt_offset & (entry->alignment - 1)) ||
 			    (need_mappable && !obj->map_and_fenceable))
 				ret = i915_gem_object_unbind(obj);
 			else
@@ -551,7 +550,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 
 		/* Bind fresh objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			if (i915_gem_obj_ggtt_bound(obj))
+			if (obj->gtt_space)
 				continue;
 
 			ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
@@ -1059,7 +1058,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 	}
 
-	exec_start = i915_gem_obj_ggtt_offset(batch_obj) + args->batch_start_offset;
+	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
 	exec_len = args->batch_len;
 	if (cliprects) {
 		for (i = 0; i < args->num_cliprects; i++) {
drivers/gpu/drm/i915/i915_gem_gtt.c +7 -7
index f075831..7f85d6f 100644
@@ -378,7 +378,7 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
 			    enum i915_cache_level cache_level)
 {
 	ppgtt->insert_entries(ppgtt, obj->pages,
-			      i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
+			      obj->gtt_space->start >> PAGE_SHIFT,
 			      cache_level);
 }
 
@@ -386,7 +386,7 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			      struct drm_i915_gem_object *obj)
 {
 	ppgtt->clear_range(ppgtt,
-			   i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
+			   obj->gtt_space->start >> PAGE_SHIFT,
 			   obj->base.size >> PAGE_SHIFT);
 }
 
@@ -551,7 +551,7 @@ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	dev_priv->gtt.gtt_insert_entries(dev, obj->pages,
-					 i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
+					 obj->gtt_space->start >> PAGE_SHIFT,
 					 cache_level);
 
 	obj->has_global_gtt_mapping = 1;
@@ -563,7 +563,7 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	dev_priv->gtt.gtt_clear_range(obj->base.dev,
-				      i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
+				      obj->gtt_space->start >> PAGE_SHIFT,
 				      obj->base.size >> PAGE_SHIFT);
 
 	obj->has_global_gtt_mapping = 0;
@@ -629,12 +629,12 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
-			      i915_gem_obj_ggtt_offset(obj), obj->base.size);
+		DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
+			      obj->gtt_offset, obj->base.size);
 
 		BUG_ON(obj->gtt_space->start != I915_GTT_RESERVED);
 		obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space,
-						     i915_gem_obj_ggtt_offset(obj),
+						     obj->gtt_offset,
 						     obj->base.size,
 						     false);
 		obj->has_global_gtt_mapping = 1;
drivers/gpu/drm/i915/i915_gem_tiling.c +7 -7
index 92a8d27..537545b 100644
@@ -268,18 +268,18 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 		return true;
 
 	if (INTEL_INFO(obj->base.dev)->gen == 3) {
-		if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK)
+		if (obj->gtt_offset & ~I915_FENCE_START_MASK)
 			return false;
 	} else {
-		if (i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK)
+		if (obj->gtt_offset & ~I830_FENCE_START_MASK)
 			return false;
 	}
 
 	size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode);
-	if (i915_gem_obj_ggtt_size(obj) != size)
+	if (obj->gtt_space->size != size)
 		return false;
 
-	if (i915_gem_obj_ggtt_offset(obj) & (size - 1))
+	if (obj->gtt_offset & (size - 1))
 		return false;
 
 	return true;
@@ -359,8 +359,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 */
 
 		obj->map_and_fenceable =
-			!i915_gem_obj_ggtt_bound(obj) ||
-			(i915_gem_obj_ggtt_offset(obj) + obj->base.size <= dev_priv->gtt.mappable_end &&
+			obj->gtt_space == NULL ||
+			(obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end &&
 			 i915_gem_object_fence_ok(obj, args->tiling_mode));
 
 		/* Rebind if we need a change of alignment */
@@ -369,7 +369,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 				i915_gem_get_gtt_alignment(dev, obj->base.size,
 							    args->tiling_mode,
 							    false);
-			if (i915_gem_obj_ggtt_offset(obj) & (unfenced_alignment - 1))
+			if (obj->gtt_offset & (unfenced_alignment - 1))
 				ret = i915_gem_object_unbind(obj);
 		}
 
drivers/gpu/drm/i915/i915_irq.c +8 -7
index 4aedd38..c2e11a0 100644
@@ -1520,7 +1520,7 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 	if (dst == NULL)
 		return NULL;
 
-	reloc_offset = dst->gtt_offset = i915_gem_obj_ggtt_offset(src);
+	reloc_offset = src->gtt_offset;
 	for (i = 0; i < num_pages; i++) {
 		unsigned long flags;
 		void *d;
@@ -1572,6 +1572,7 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 		reloc_offset += PAGE_SIZE;
 	}
 	dst->page_count = num_pages;
+	dst->gtt_offset = src->gtt_offset;
 
 	return dst;
 
@@ -1625,7 +1626,7 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->name = obj->base.name;
 	err->rseqno = obj->last_read_seqno;
 	err->wseqno = obj->last_write_seqno;
-	err->gtt_offset = i915_gem_obj_ggtt_offset(obj);
+	err->gtt_offset = obj->gtt_offset;
 	err->read_domains = obj->base.read_domains;
 	err->write_domain = obj->base.write_domain;
 	err->fence_reg = obj->fence_reg;
@@ -1723,8 +1724,8 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 			return NULL;
 
 		obj = ring->private;
-		if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
-		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
+		if (acthd >= obj->gtt_offset &&
+		    acthd < obj->gtt_offset + obj->base.size)
 			return i915_error_object_create(dev_priv, obj);
 	}
 
@@ -1805,7 +1806,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
 		return;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) {
+		if ((error->ccid & PAGE_MASK) == obj->gtt_offset) {
 			ering->ctx = i915_error_object_create_sized(dev_priv,
 								    obj, 1);
 			break;
@@ -2159,10 +2160,10 @@ static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, in
 	if (INTEL_INFO(dev)->gen >= 4) {
 		int dspsurf = DSPSURF(intel_crtc->plane);
 		stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) ==
-					i915_gem_obj_ggtt_offset(obj);
+					obj->gtt_offset;
 	} else {
 		int dspaddr = DSPADDR(intel_crtc->plane);
-		stall_detected = I915_READ(dspaddr) == (i915_gem_obj_ggtt_offset(obj) +
+		stall_detected = I915_READ(dspaddr) == (obj->gtt_offset +
 							crtc->y * crtc->fb->pitches[0] +
 							crtc->x * crtc->fb->bits_per_pixel/8);
 	}
drivers/gpu/drm/i915/i915_trace.h +4 -4
index 7d283b5..3db4a68 100644
@@ -46,8 +46,8 @@ TRACE_EVENT(i915_gem_object_bind,
 
 	    TP_fast_assign(
 			   __entry->obj = obj;
-			   __entry->offset = i915_gem_obj_ggtt_offset(obj);
-			   __entry->size = i915_gem_obj_ggtt_size(obj);
+			   __entry->offset = obj->gtt_space->start;
+			   __entry->size = obj->gtt_space->size;
 			   __entry->mappable = mappable;
 			   ),
 
@@ -68,8 +68,8 @@ TRACE_EVENT(i915_gem_object_unbind,
 
 	    TP_fast_assign(
 			   __entry->obj = obj;
-			   __entry->offset = i915_gem_obj_ggtt_offset(obj);
-			   __entry->size = i915_gem_obj_ggtt_size(obj);
+			   __entry->offset = obj->gtt_space->start;
+			   __entry->size = obj->gtt_space->size;
 			   ),
 
 	    TP_printk("obj=%p, offset=%08x size=%x",
drivers/gpu/drm/i915/intel_display.c +13 -15
index a45bb92..aaa9a75 100644
@@ -1980,17 +1980,16 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		intel_crtc->dspaddr_offset = linear_offset;
 	}
 
-	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
-		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
-		      fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
+		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	if (INTEL_INFO(dev)->gen >= 4) {
 		I915_MODIFY_DISPBASE(DSPSURF(plane),
-				     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+				     obj->gtt_offset + intel_crtc->dspaddr_offset);
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else
-		I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset);
+		I915_WRITE(DSPADDR(plane), obj->gtt_offset + linear_offset);
 	POSTING_READ(reg);
 
 	return 0;
@@ -2070,12 +2069,11 @@ static int ironlake_update_plane(struct drm_crtc *crtc,
 					       fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
 
-	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
-		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
-		      fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
+		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	I915_MODIFY_DISPBASE(DSPSURF(plane),
-			     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+			     obj->gtt_offset + intel_crtc->dspaddr_offset);
 	if (IS_HASWELL(dev)) {
 		I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
 	} else {
@@ -6569,7 +6567,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 			goto fail_unpin;
 		}
 
-		addr = i915_gem_obj_ggtt_offset(obj);
+		addr = obj->gtt_offset;
 	} else {
 		int align = IS_I830(dev) ? 16 * 1024 : 256;
 		ret = i915_gem_attach_phys_object(dev, obj,
@@ -7341,7 +7339,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7382,7 +7380,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7422,7 +7420,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
 	intel_ring_emit(ring,
-			(i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) |
+			(obj->gtt_offset + intel_crtc->dspaddr_offset) |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -7465,7 +7463,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -7530,7 +7528,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
 	intel_mark_page_flip_active(intel_crtc);
drivers/gpu/drm/i915/intel_fb.c +4 -4
index f3c97e0..dff669e 100644
@@ -139,11 +139,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = dev_priv->gtt.mappable_end;
 
-	info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj);
+	info->fix.smem_start = dev->mode_config.fb_base + obj->gtt_offset;
 	info->fix.smem_len = size;
 
 	info->screen_base =
-		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
+		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
 			   size);
 	if (!info->screen_base) {
 		ret = -ENOSPC;
@@ -166,9 +166,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n",
+	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x, bo %p\n",
 		      fb->width, fb->height,
-		      i915_gem_obj_ggtt_offset(obj), obj);
+		      obj->gtt_offset, obj);
 
 
 	mutex_unlock(&dev->struct_mutex);
drivers/gpu/drm/i915/intel_overlay.c +7 -7
index 81c3ca1..a369881 100644
@@ -196,7 +196,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay)
 		regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_wc(dev_priv->gtt.mappable,
-					 i915_gem_obj_ggtt_offset(overlay->reg_bo));
+					 overlay->reg_bo->gtt_offset);
 
 	return regs;
 }
@@ -740,7 +740,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	swidth = params->src_w;
 	swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width);
 	sheight = params->src_h;
-	iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, &regs->OBUF_0Y);
+	iowrite32(new_bo->gtt_offset + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
 
 	if (params->format & I915_OVERLAY_YUV_PLANAR) {
@@ -754,8 +754,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
-		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_U, &regs->OBUF_0U);
-		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_V, &regs->OBUF_0V);
+		iowrite32(new_bo->gtt_offset + params->offset_U, &regs->OBUF_0U);
+		iowrite32(new_bo->gtt_offset + params->offset_V, &regs->OBUF_0V);
 		ostride |= params->stride_UV << 16;
 	}
 
@@ -1355,7 +1355,7 @@ void intel_setup_overlay(struct drm_device *dev)
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
 		}
-		overlay->flip_addr = i915_gem_obj_ggtt_offset(reg_bo);
+		overlay->flip_addr = reg_bo->gtt_offset;
 
 		ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
 		if (ret) {
@@ -1435,7 +1435,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay)
 			overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						i915_gem_obj_ggtt_offset(overlay->reg_bo));
+						overlay->reg_bo->gtt_offset);
 
 	return regs;
 }
@@ -1468,7 +1468,7 @@ intel_overlay_capture_error_state(struct drm_device *dev)
 	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
 		error->base = (__force long)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
-		error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo);
+		error->base = overlay->reg_bo->gtt_offset;
 
 	regs = intel_overlay_map_regs_atomic(overlay);
 	if (!regs)
drivers/gpu/drm/i915/intel_pm.c +4 -4
index 125a741..0eed35d 100644
@@ -218,7 +218,7 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 		   (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) |
 		   (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT));
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y);
-	I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID);
+	I915_WRITE(ILK_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -275,7 +275,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj));
+	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset);
 
 	I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X |
 		   IVB_DPFC_CTL_FENCE_EN |
@@ -3700,7 +3700,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 
 	intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
+	intel_ring_emit(ring, dev_priv->ips.renderctx->gtt_offset |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
@@ -3723,7 +3723,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 		return;
 	}
 
-	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
+	I915_WRITE(PWRCTXA, dev_priv->ips.pwrctx->gtt_offset | PWRCTX_EN);
 	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
 }
 
drivers/gpu/drm/i915/intel_ringbuffer.c +6 -6
index 5b647eb..18ca76e 100644
@@ -440,14 +440,14 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
-	I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj));
+	I915_WRITE_START(ring, obj->gtt_offset);
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
 
 	/* If the head is still not zero, the ring is dead */
 	if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 &&
-		     I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) &&
+		     I915_READ_START(ring) == obj->gtt_offset &&
 		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
 				"ctl %08x head %08x tail %08x start %08x\n",
@@ -505,7 +505,7 @@ init_pipe_control(struct intel_ring_buffer *ring)
 	if (ret)
 		goto err_unref;
 
-	pc->gtt_offset = i915_gem_obj_ggtt_offset(obj);
+	pc->gtt_offset = obj->gtt_offset;
 	pc->cpu_page = kmap(sg_page(obj->pages->sgl));
 	if (pc->cpu_page == NULL) {
 		ret = -ENOMEM;
@@ -1145,7 +1145,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 		intel_ring_advance(ring);
 	} else {
 		struct drm_i915_gem_object *obj = ring->private;
-		u32 cs_offset = i915_gem_obj_ggtt_offset(obj);
+		u32 cs_offset = obj->gtt_offset;
 
 		if (len > I830_BATCH_LIMIT)
 			return -ENOSPC;
@@ -1230,7 +1230,7 @@ static int init_status_page(struct intel_ring_buffer *ring)
 		goto err_unref;
 	}
 
-	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
+	ring->status_page.gfx_addr = obj->gtt_offset;
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
 	if (ring->status_page.page_addr == NULL) {
 		ret = -ENOMEM;
@@ -1317,7 +1317,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		goto err_unpin;
 
 	ring->virtual_start =
-		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
+		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
 			   ring->size);
 	if (ring->virtual_start == NULL) {
 		DRM_ERROR("Failed to map ringbuffer.\n");
drivers/gpu/drm/i915/intel_sprite.c +3 -5
index 55bdf70..1fa5612 100644
@@ -133,7 +133,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 
 	I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
-	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
+	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), obj->gtt_offset +
 			     sprsurf_offset);
 	POSTING_READ(SPSURF(pipe, plane));
 }
@@ -308,8 +308,7 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), sprscale);
 	I915_WRITE(SPRCTL(pipe), sprctl);
-	I915_MODIFY_DISPBASE(SPRSURF(pipe),
-			     i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
+	I915_MODIFY_DISPBASE(SPRSURF(pipe), obj->gtt_offset + sprsurf_offset);
 	POSTING_READ(SPRSURF(pipe));
 
 	/* potentially re-enable LP watermarks */
@@ -479,8 +478,7 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	I915_WRITE(DVSSIZE(pipe), (crtc_h << 16) | crtc_w);
 	I915_WRITE(DVSSCALE(pipe), dvsscale);
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
-	I915_MODIFY_DISPBASE(DVSSURF(pipe),
-			     i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
+	I915_MODIFY_DISPBASE(DVSSURF(pipe), obj->gtt_offset + dvssurf_offset);
 	POSTING_READ(DVSSURF(pipe));
 }
 
Signature · 1 line
1.8.3.2
#1 lore raw

PATCH 2/9 Revert "drm/i915: Kill obj->gtt_offset"

This reverts commit a6b27b42fbb01a6b6523ff1ab6a6d440d0eba1ae.

---
 drivers/gpu/drm/i915/i915_drv.h        | 7 +++++++
 drivers/gpu/drm/i915/i915_gem.c        | 2 ++
 drivers/gpu/drm/i915/i915_gem_stolen.c | 1 +
 3 files changed, 10 insertions(+)
drivers/gpu/drm/i915/i915_drv.h +7 -0
index c80521c..bd676df 100644
@@ -1329,6 +1329,13 @@ struct drm_i915_gem_object {
 	unsigned long exec_handle;
 	struct drm_i915_gem_exec_object2 *exec_entry;
 
+	/**
+	 * Current offset of the object in GTT space.
+	 *
+	 * This is the same as gtt_space->start
+	 */
+	uint32_t gtt_offset;
+
 	struct intel_ring_buffer *ring;
 
 	/** Breadcrumb of last rendering to the buffer. */
drivers/gpu/drm/i915/i915_gem.c +2 -0
index e298f17..ef0b650 100644
@@ -2622,6 +2622,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 
 	drm_mm_put_block(obj->gtt_space);
 	obj->gtt_space = NULL;
+	obj->gtt_offset = 0;
 
 	return 0;
 }
@@ -3151,6 +3152,7 @@ search_free:
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
 	obj->gtt_space = node;
+	obj->gtt_offset = node->start;
 
 	fenceable =
 		node->size == fence_size &&
drivers/gpu/drm/i915/i915_gem_stolen.c +1 -0
index c6b70312..4bb2ccd 100644
@@ -400,6 +400,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	} else
 		obj->gtt_space->start = I915_GTT_RESERVED;
 
+	obj->gtt_offset = gtt_offset;
 	obj->has_global_gtt_mapping = 1;
 
 	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
Signature · 1 line
1.8.3.2
#2 lore raw

PATCH 3/9 Revert "drm/i915: Use gtt_space->start for stolen reservation"

In reply to Ben Widawsky

This reverts commit 7dedae28b41000539b6c18bcf72107c97e4937e4.

Conflicts:

	drivers/gpu/drm/i915/i915_drv.h
---
 drivers/gpu/drm/i915/i915_drv.h        | 2 +-
 drivers/gpu/drm/i915/i915_gem_gtt.c    | 2 +-
 drivers/gpu/drm/i915/i915_gem_stolen.c | 2 +-
 3 files changed, 3 insertions(+), 3 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +1 -1
index bd676df..c2d2f90 100644
@@ -1201,7 +1201,7 @@ enum hdmi_force_audio {
 	HDMI_AUDIO_ON,			/* force turn on HDMI audio */
 };
 
-#define I915_GTT_RESERVED (ULONG_MAX)
+#define I915_GTT_RESERVED ((struct drm_mm_node *)0x1)
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
drivers/gpu/drm/i915/i915_gem_gtt.c +1 -1
index 7f85d6f..66929ea 100644
@@ -632,7 +632,7 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 		DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
 			      obj->gtt_offset, obj->base.size);
 
-		BUG_ON(obj->gtt_space->start != I915_GTT_RESERVED);
+		BUG_ON(obj->gtt_space != I915_GTT_RESERVED);
 		obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space,
 						     obj->gtt_offset,
 						     obj->base.size,
drivers/gpu/drm/i915/i915_gem_stolen.c +1 -1
index 4bb2ccd..aea6221 100644
@@ -398,7 +398,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 			return NULL;
 		}
 	} else
-		obj->gtt_space->start = I915_GTT_RESERVED;
+		obj->gtt_space = I915_GTT_RESERVED;
 
 	obj->gtt_offset = gtt_offset;
 	obj->has_global_gtt_mapping = 1;
Signature · 1 line
1.8.3.2
#3 lore raw

PATCH 4/9 drm: pre allocate node for create_block

In reply to Ben Widawsky

For an upcoming patch where we introduce the i915 VMA, it's ideal to have the drm_mm_node as part of the VMA struct (ie. it's pre-allocated). Part of the conversion to VMAs is to kill off obj->gtt_space. Doing this will break a bunch of code, but amongst them are 2 callers of drm_mm_create_block(), both related to stolen memory.

It also allows us to embed the drm_mm_node into the object currently which provides a nice transition over to the new code.

v2: Reordered to do before ripping out obj->gtt_offset. Some minor cleanups made available because of reordering.

v3: s/continue/break on failed stolen node allocation (David) Set obj->gtt_space on failed node allocation (David) Only unref stolen (fix double free) on failed create_stolen (David) Free node, and NULL it in failed create_stolen (David) Add back accidentally removed newline (David)

---
 drivers/gpu/drm/drm_mm.c               | 16 +++++----------
 drivers/gpu/drm/i915/i915_gem_gtt.c    | 20 ++++++++++++++----
 drivers/gpu/drm/i915/i915_gem_stolen.c | 37 +++++++++++++++++++++++++---------
 include/drm/drm_mm.h                   |  9 +++++----
 4 files changed, 53 insertions(+), 29 deletions(-)
drivers/gpu/drm/drm_mm.c +5 -11
index 543b9b3..94d48c5 100644
@@ -147,12 +147,10 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 	}
 }
 
-struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm,
-					unsigned long start,
-					unsigned long size,
-					bool atomic)
+int drm_mm_create_block(struct drm_mm *mm, struct drm_mm_node *node,
+			unsigned long start, unsigned long size)
 {
-	struct drm_mm_node *hole, *node;
+	struct drm_mm_node *hole;
 	unsigned long end = start + size;
 	unsigned long hole_start;
 	unsigned long hole_end;
@@ -161,10 +159,6 @@ struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm,
 		if (hole_start > start || hole_end < end)
 			continue;
 
-		node = drm_mm_kmalloc(mm, atomic);
-		if (unlikely(node == NULL))
-			return NULL;
-
 		node->start = start;
 		node->size = size;
 		node->mm = mm;
@@ -184,11 +178,11 @@ struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm,
 			node->hole_follows = 1;
 		}
 
-		return node;
+		return 0;
 	}
 
 	WARN(1, "no hole found for block 0x%lx + 0x%lx\n", start, size);
-	return NULL;
+	return -ENOSPC;
 }
 EXPORT_SYMBOL(drm_mm_create_block);
 
drivers/gpu/drm/i915/i915_gem_gtt.c +16 -4
index 66929ea..88180a5 100644
@@ -629,14 +629,26 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		int ret;
 		DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
 			      obj->gtt_offset, obj->base.size);
 
 		BUG_ON(obj->gtt_space != I915_GTT_RESERVED);
-		obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space,
-						     obj->gtt_offset,
-						     obj->base.size,
-						     false);
+		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
+		if (!obj->gtt_space) {
+			DRM_ERROR("Failed to preserve object at offset %x\n",
+				  obj->gtt_offset);
+			continue;
+		}
+		ret = drm_mm_create_block(&dev_priv->mm.gtt_space,
+					  obj->gtt_space,
+					  obj->gtt_offset,
+					  obj->base.size);
+		if (ret) {
+			DRM_DEBUG_KMS("Reservation failed\n");
+			kfree(obj->gtt_space);
+			obj->gtt_space = NULL;
+		}
 		obj->has_global_gtt_mapping = 1;
 	}
 
drivers/gpu/drm/i915/i915_gem_stolen.c +27 -10
index aea6221..c1b726c 100644
@@ -319,6 +319,7 @@ i915_gem_object_create_stolen(struct drm_device *dev, u32 size)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
+	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
@@ -364,11 +365,15 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	if (WARN_ON(size == 0))
 		return NULL;
 
-	stolen = drm_mm_create_block(&dev_priv->mm.stolen,
-				     stolen_offset, size,
-				     false);
-	if (stolen == NULL) {
+	stolen = kzalloc(sizeof(*stolen), GFP_KERNEL);
+	if (!stolen)
+		return NULL;
+
+	ret = drm_mm_create_block(&dev_priv->mm.stolen, stolen, stolen_offset,
+				  size);
+	if (ret) {
 		DRM_DEBUG_KMS("failed to allocate stolen space\n");
+		kfree(stolen);
 		return NULL;
 	}
 
@@ -389,13 +394,18 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	 * later.
 	 */
 	if (drm_mm_initialized(&dev_priv->mm.gtt_space)) {
-		obj->gtt_space = drm_mm_create_block(&dev_priv->mm.gtt_space,
-						     gtt_offset, size,
-						     false);
-		if (obj->gtt_space == NULL) {
+		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
+		if (!obj->gtt_space) {
+			DRM_DEBUG_KMS("-ENOMEM stolen GTT space\n");
+			goto unref_out;
+		}
+
+		ret = drm_mm_create_block(&dev_priv->mm.gtt_space,
+					  obj->gtt_space,
+					  gtt_offset, size);
+		if (ret) {
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
-			drm_gem_object_unreference(&obj->base);
-			return NULL;
+			goto free_out;
 		}
 	} else
 		obj->gtt_space = I915_GTT_RESERVED;
@@ -407,6 +417,13 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
 	return obj;
+
+free_out:
+	kfree(obj->gtt_space);
+	obj->gtt_space = NULL;
+unref_out:
+	drm_gem_object_unreference(&obj->base);
+	return NULL;
 }
 
 void
include/drm/drm_mm.h +5 -4
index 4d06edb..6ac218d 100644
@@ -138,10 +138,10 @@ static inline unsigned long drm_mm_hole_node_end(struct drm_mm_node *hole_node)
 /*
  * Basic range manager support (drm_mm.c)
  */
-extern struct drm_mm_node *drm_mm_create_block(struct drm_mm *mm,
-					       unsigned long start,
-					       unsigned long size,
-					       bool atomic);
+extern int drm_mm_create_block(struct drm_mm *mm,
+			       struct drm_mm_node *node,
+			       unsigned long start,
+			       unsigned long size);
 extern struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *node,
 						    unsigned long size,
 						    unsigned alignment,
@@ -155,6 +155,7 @@ extern struct drm_mm_node *drm_mm_get_block_range_generic(
 						unsigned long start,
 						unsigned long end,
 						int atomic);
+
 static inline struct drm_mm_node *drm_mm_get_block(struct drm_mm_node *parent,
 						   unsigned long size,
 						   unsigned alignment)
Signature · 1 line
1.8.3.2
#4 lore raw

PATCH 5/9 drm: Change create block to reserve node

In reply to Ben Widawsky

With the previous patch we no longer actually create a node, we simply find the correct hole and occupy it. This very well could have been squashed with the last patch, but since I already had David's review, I figured it's easiest to keep it distinct.

Also update the users in i915. Conveniently this is the only user of the interface.

---
 drivers/gpu/drm/drm_mm.c               | 19 ++++++++++---------
 drivers/gpu/drm/i915/i915_gem_gtt.c    |  8 ++++----
 drivers/gpu/drm/i915/i915_gem_stolen.c | 14 ++++++++------
 include/drm/drm_mm.h                   |  5 +----
 4 files changed, 23 insertions(+), 23 deletions(-)
drivers/gpu/drm/drm_mm.c +10 -9
index 94d48c5..fe304f9 100644
@@ -147,27 +147,27 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 	}
 }
 
-int drm_mm_create_block(struct drm_mm *mm, struct drm_mm_node *node,
-			unsigned long start, unsigned long size)
+int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node)
 {
 	struct drm_mm_node *hole;
-	unsigned long end = start + size;
+	unsigned long end = node->start + node->size;
 	unsigned long hole_start;
 	unsigned long hole_end;
 
+	BUG_ON(node == NULL);
+
+	/* Find the relevant hole to add our node to */
 	drm_mm_for_each_hole(hole, mm, hole_start, hole_end) {
-		if (hole_start > start || hole_end < end)
+		if (hole_start > node->start || hole_end < end)
 			continue;
 
-		node->start = start;
-		node->size = size;
 		node->mm = mm;
 		node->allocated = 1;
 
 		INIT_LIST_HEAD(&node->hole_stack);
 		list_add(&node->node_list, &hole->node_list);
 
-		if (start == hole_start) {
+		if (node->start == hole_start) {
 			hole->hole_follows = 0;
 			list_del_init(&hole->hole_stack);
 		}
@@ -181,10 +181,11 @@ int drm_mm_create_block(struct drm_mm *mm, struct drm_mm_node *node,
 		return 0;
 	}
 
-	WARN(1, "no hole found for block 0x%lx + 0x%lx\n", start, size);
+	WARN(1, "no hole found for node 0x%lx + 0x%lx\n",
+	     node->start, node->size);
 	return -ENOSPC;
 }
-EXPORT_SYMBOL(drm_mm_create_block);
+EXPORT_SYMBOL(drm_mm_reserve_node);
 
 struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *hole_node,
 					     unsigned long size,
drivers/gpu/drm/i915/i915_gem_gtt.c +4 -4
index 88180a5..afba7e5 100644
@@ -640,10 +640,10 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 				  obj->gtt_offset);
 			continue;
 		}
-		ret = drm_mm_create_block(&dev_priv->mm.gtt_space,
-					  obj->gtt_space,
-					  obj->gtt_offset,
-					  obj->base.size);
+		obj->gtt_space->start = obj->gtt_offset;
+		obj->gtt_space->size = obj->base.size;
+		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
+					  obj->gtt_space);
 		if (ret) {
 			DRM_DEBUG_KMS("Reservation failed\n");
 			kfree(obj->gtt_space);
drivers/gpu/drm/i915/i915_gem_stolen.c +8 -6
index c1b726c..95c3836 100644
@@ -319,7 +319,6 @@ i915_gem_object_create_stolen(struct drm_device *dev, u32 size)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
-	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
@@ -351,6 +350,7 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_gem_object *obj;
 	struct drm_mm_node *stolen;
+	int ret;
 
 	if (!drm_mm_initialized(&dev_priv->mm.stolen))
 		return NULL;
@@ -369,8 +369,9 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	if (!stolen)
 		return NULL;
 
-	ret = drm_mm_create_block(&dev_priv->mm.stolen, stolen, stolen_offset,
-				  size);
+	stolen->start = stolen_offset;
+	stolen->size = size;
+	ret = drm_mm_reserve_node(&dev_priv->mm.stolen, stolen);
 	if (ret) {
 		DRM_DEBUG_KMS("failed to allocate stolen space\n");
 		kfree(stolen);
@@ -400,9 +401,10 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 			goto unref_out;
 		}
 
-		ret = drm_mm_create_block(&dev_priv->mm.gtt_space,
-					  obj->gtt_space,
-					  gtt_offset, size);
+		obj->gtt_space->start = gtt_offset;
+		obj->gtt_space->size = size;
+		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
+					  obj->gtt_space);
 		if (ret) {
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
 			goto free_out;
include/drm/drm_mm.h +1 -4
index 6ac218d..b87d05e 100644
@@ -138,10 +138,7 @@ static inline unsigned long drm_mm_hole_node_end(struct drm_mm_node *hole_node)
 /*
  * Basic range manager support (drm_mm.c)
  */
-extern int drm_mm_create_block(struct drm_mm *mm,
-			       struct drm_mm_node *node,
-			       unsigned long start,
-			       unsigned long size);
+extern int drm_mm_reserve_node(struct drm_mm *mm, struct drm_mm_node *node);
 extern struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *node,
 						    unsigned long size,
 						    unsigned alignment,
Signature · 1 line
1.8.3.2
#5 lore raw

PATCH 6/9 drm/i915: Getter/setter for object attributes

In reply to Ben Widawsky

Soon we want to gut a lot of our existing assumptions how many address spaces an object can live in, and in doing so, embed the drm_mm_node in the object (and later the VMA).

It's possible in the future we'll want to add more getter/setter methods, but for now this is enough to enable the VMAs.

v2: Reworked commit message (Ben)
Added comments to the main functions (Ben)
sed -i "s/i915_gem_obj_set_color/i915_gem_obj_ggtt_set_color/" drivers/gpu/drm/i915/*.[ch] sed -i "s/i915_gem_obj_bound/i915_gem_obj_ggtt_bound/" drivers/gpu/drm/i915/*.[ch] sed -i "s/i915_gem_obj_size/i915_gem_obj_ggtt_size/" drivers/gpu/drm/i915/*.[ch] sed -i "s/i915_gem_obj_offset/i915_gem_obj_ggtt_offset/" drivers/gpu/drm/i915/*.[ch] (Daniel)

v3: Rebased on new reserve_node patch
Changed DRM_DEBUG_KMS to actually work (will need fixing later)

---
 drivers/gpu/drm/i915/i915_debugfs.c        | 26 +++++----
 drivers/gpu/drm/i915/i915_drv.h            | 31 +++++++++++
 drivers/gpu/drm/i915/i915_gem.c            | 89 +++++++++++++++---------------
 drivers/gpu/drm/i915/i915_gem_context.c    |  2 +-
 drivers/gpu/drm/i915/i915_gem_execbuffer.c | 19 ++++---
 drivers/gpu/drm/i915/i915_gem_gtt.c        |  8 +--
 drivers/gpu/drm/i915/i915_gem_tiling.c     | 14 ++---
 drivers/gpu/drm/i915/i915_irq.c            | 15 +++--
 drivers/gpu/drm/i915/i915_trace.h          |  8 +--
 drivers/gpu/drm/i915/intel_display.c       | 28 +++++-----
 drivers/gpu/drm/i915/intel_fb.c            |  8 +--
 drivers/gpu/drm/i915/intel_overlay.c       | 14 ++---
 drivers/gpu/drm/i915/intel_pm.c            |  8 +--
 drivers/gpu/drm/i915/intel_ringbuffer.c    | 12 ++--
 drivers/gpu/drm/i915/intel_sprite.c        |  8 ++-
 15 files changed, 164 insertions(+), 126 deletions(-)
drivers/gpu/drm/i915/i915_debugfs.c +14 -12
index 3e36756..396387e 100644
@@ -122,9 +122,9 @@ describe_obj(struct seq_file *m, struct drm_i915_gem_object *obj)
 		seq_printf(m, " (pinned x %d)", obj->pin_count);
 	if (obj->fence_reg != I915_FENCE_REG_NONE)
 		seq_printf(m, " (fence: %d)", obj->fence_reg);
-	if (obj->gtt_space != NULL)
-		seq_printf(m, " (gtt offset: %08x, size: %08x)",
-			   obj->gtt_offset, (unsigned int)obj->gtt_space->size);
+	if (i915_gem_obj_ggtt_bound(obj))
+		seq_printf(m, " (gtt offset: %08lx, size: %08x)",
+			   i915_gem_obj_ggtt_offset(obj), (unsigned int)i915_gem_obj_ggtt_size(obj));
 	if (obj->stolen)
 		seq_printf(m, " (stolen: %08lx)", obj->stolen->start);
 	if (obj->pin_mappable || obj->fault_mappable) {
@@ -175,7 +175,7 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += obj->gtt_space->size;
+		total_gtt_size += i915_gem_obj_ggtt_size(obj);
 		count++;
 	}
 	mutex_unlock(&dev->struct_mutex);
@@ -187,10 +187,10 @@ static int i915_gem_object_list_info(struct seq_file *m, void *data)
 
 #define count_objects(list, member) do { \
 	list_for_each_entry(obj, list, member) { \
-		size += obj->gtt_space->size; \
+		size += i915_gem_obj_ggtt_size(obj); \
 		++count; \
 		if (obj->map_and_fenceable) { \
-			mappable_size += obj->gtt_space->size; \
+			mappable_size += i915_gem_obj_ggtt_size(obj); \
 			++mappable_count; \
 		} \
 	} \
@@ -209,7 +209,7 @@ static int per_file_stats(int id, void *ptr, void *data)
 	stats->count++;
 	stats->total += obj->base.size;
 
-	if (obj->gtt_space) {
+	if (i915_gem_obj_ggtt_bound(obj)) {
 		if (!list_empty(&obj->ring_list))
 			stats->active += obj->base.size;
 		else
@@ -267,11 +267,11 @@ static int i915_gem_object_info(struct seq_file *m, void *data)
 	size = count = mappable_size = mappable_count = 0;
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
 		if (obj->fault_mappable) {
-			size += obj->gtt_space->size;
+			size += i915_gem_obj_ggtt_size(obj);
 			++count;
 		}
 		if (obj->pin_mappable) {
-			mappable_size += obj->gtt_space->size;
+			mappable_size += i915_gem_obj_ggtt_size(obj);
 			++mappable_count;
 		}
 		if (obj->madv == I915_MADV_DONTNEED) {
@@ -333,7 +333,7 @@ static int i915_gem_gtt_info(struct seq_file *m, void *data)
 		describe_obj(m, obj);
 		seq_putc(m, '\n');
 		total_obj_size += obj->base.size;
-		total_gtt_size += obj->gtt_space->size;
+		total_gtt_size += i915_gem_obj_ggtt_size(obj);
 		count++;
 	}
 
@@ -379,12 +379,14 @@ static int i915_gem_pageflip_info(struct seq_file *m, void *data)
 			if (work->old_fb_obj) {
 				struct drm_i915_gem_object *obj = work->old_fb_obj;
 				if (obj)
-					seq_printf(m, "Old framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
+					seq_printf(m, "Old framebuffer gtt_offset 0x%08lx\n",
+						   i915_gem_obj_ggtt_offset(obj));
 			}
 			if (work->pending_flip_obj) {
 				struct drm_i915_gem_object *obj = work->pending_flip_obj;
 				if (obj)
-					seq_printf(m, "New framebuffer gtt_offset 0x%08x\n", obj->gtt_offset);
+					seq_printf(m, "New framebuffer gtt_offset 0x%08lx\n",
+						   i915_gem_obj_ggtt_offset(obj));
 			}
 		}
 		spin_unlock_irqrestore(&dev->event_lock, flags);
drivers/gpu/drm/i915/i915_drv.h +31 -0
index c2d2f90..626cff5 100644
@@ -1361,6 +1361,37 @@ struct drm_i915_gem_object {
 
 #define to_intel_bo(x) container_of(x, struct drm_i915_gem_object, base)
 
+/* Offset of the first PTE pointing to this object */
+static inline unsigned long
+i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
+{
+	return o->gtt_space->start;
+}
+
+/* Whether or not this object is currently mapped by the translation tables */
+static inline bool
+i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
+{
+	return o->gtt_space != NULL;
+}
+
+/* The size used in the translation tables may be larger than the actual size of
+ * the object on GEN2/GEN3 because of the way tiling is handled. See
+ * i915_gem_get_gtt_size() for more details.
+ */
+static inline unsigned long
+i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
+{
+	return o->gtt_space->size;
+}
+
+static inline void
+i915_gem_obj_ggtt_set_color(struct drm_i915_gem_object *o,
+			    enum i915_cache_level color)
+{
+	o->gtt_space->color = color;
+}
+
 /**
  * Request queue structure.
  *
drivers/gpu/drm/i915/i915_gem.c +45 -44

253 lines not on this page · raw message

drivers/gpu/drm/i915/i915_gem_context.c +1 -1
index 51b7a21..2074544 100644
@@ -377,7 +377,7 @@ mi_set_context(struct intel_ring_buffer *ring,
 
 	intel_ring_emit(ring, MI_NOOP);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, new_context->obj->gtt_offset |
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(new_context->obj) |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
drivers/gpu/drm/i915/i915_gem_execbuffer.c +10 -9
index 87a3227..5aeb447 100644
@@ -188,7 +188,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 		return -ENOENT;
 
 	target_i915_obj = to_intel_bo(target_obj);
-	target_offset = target_i915_obj->gtt_offset;
+	target_offset = i915_gem_obj_ggtt_offset(target_i915_obj);
 
 	/* Sandybridge PPGTT errata: We need a global gtt mapping for MI and
 	 * pipe_control writes because the gpu doesn't properly redirect them
@@ -280,7 +280,7 @@ i915_gem_execbuffer_relocate_entry(struct drm_i915_gem_object *obj,
 			return ret;
 
 		/* Map the page containing the relocation we're going to perform.  */
-		reloc->offset += obj->gtt_offset;
+		reloc->offset += i915_gem_obj_ggtt_offset(obj);
 		reloc_page = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
 						      reloc->offset & PAGE_MASK);
 		reloc_entry = (uint32_t __iomem *)
@@ -436,8 +436,8 @@ i915_gem_execbuffer_reserve_object(struct drm_i915_gem_object *obj,
 		obj->has_aliasing_ppgtt_mapping = 1;
 	}
 
-	if (entry->offset != obj->gtt_offset) {
-		entry->offset = obj->gtt_offset;
+	if (entry->offset != i915_gem_obj_ggtt_offset(obj)) {
+		entry->offset = i915_gem_obj_ggtt_offset(obj);
 		*need_reloc = true;
 	}
 
@@ -458,7 +458,7 @@ i915_gem_execbuffer_unreserve_object(struct drm_i915_gem_object *obj)
 {
 	struct drm_i915_gem_exec_object2 *entry;
 
-	if (!obj->gtt_space)
+	if (!i915_gem_obj_ggtt_bound(obj))
 		return;
 
 	entry = obj->exec_entry;
@@ -530,7 +530,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 			struct drm_i915_gem_exec_object2 *entry = obj->exec_entry;
 			bool need_fence, need_mappable;
 
-			if (!obj->gtt_space)
+			if (!i915_gem_obj_ggtt_bound(obj))
 				continue;
 
 			need_fence =
@@ -539,7 +539,8 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 				obj->tiling_mode != I915_TILING_NONE;
 			need_mappable = need_fence || need_reloc_mappable(obj);
 
-			if ((entry->alignment && obj->gtt_offset & (entry->alignment - 1)) ||
+			if ((entry->alignment &&
+			     i915_gem_obj_ggtt_offset(obj) & (entry->alignment - 1)) ||
 			    (need_mappable && !obj->map_and_fenceable))
 				ret = i915_gem_object_unbind(obj);
 			else
@@ -550,7 +551,7 @@ i915_gem_execbuffer_reserve(struct intel_ring_buffer *ring,
 
 		/* Bind fresh objects */
 		list_for_each_entry(obj, objects, exec_list) {
-			if (obj->gtt_space)
+			if (i915_gem_obj_ggtt_bound(obj))
 				continue;
 
 			ret = i915_gem_execbuffer_reserve_object(obj, ring, need_relocs);
@@ -1058,7 +1059,7 @@ i915_gem_do_execbuffer(struct drm_device *dev, void *data,
 			goto err;
 	}
 
-	exec_start = batch_obj->gtt_offset + args->batch_start_offset;
+	exec_start = i915_gem_obj_ggtt_offset(batch_obj) + args->batch_start_offset;
 	exec_len = args->batch_len;
 	if (cliprects) {
 		for (i = 0; i < args->num_cliprects; i++) {
drivers/gpu/drm/i915/i915_gem_gtt.c +4 -4
index afba7e5..6f0a4c0 100644
@@ -378,7 +378,7 @@ void i915_ppgtt_bind_object(struct i915_hw_ppgtt *ppgtt,
 			    enum i915_cache_level cache_level)
 {
 	ppgtt->insert_entries(ppgtt, obj->pages,
-			      obj->gtt_space->start >> PAGE_SHIFT,
+			      i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 			      cache_level);
 }
 
@@ -386,7 +386,7 @@ void i915_ppgtt_unbind_object(struct i915_hw_ppgtt *ppgtt,
 			      struct drm_i915_gem_object *obj)
 {
 	ppgtt->clear_range(ppgtt,
-			   obj->gtt_space->start >> PAGE_SHIFT,
+			   i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 			   obj->base.size >> PAGE_SHIFT);
 }
 
@@ -551,7 +551,7 @@ void i915_gem_gtt_bind_object(struct drm_i915_gem_object *obj,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	dev_priv->gtt.gtt_insert_entries(dev, obj->pages,
-					 obj->gtt_space->start >> PAGE_SHIFT,
+					 i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 					 cache_level);
 
 	obj->has_global_gtt_mapping = 1;
@@ -563,7 +563,7 @@ void i915_gem_gtt_unbind_object(struct drm_i915_gem_object *obj)
 	struct drm_i915_private *dev_priv = dev->dev_private;
 
 	dev_priv->gtt.gtt_clear_range(obj->base.dev,
-				      obj->gtt_space->start >> PAGE_SHIFT,
+				      i915_gem_obj_ggtt_offset(obj) >> PAGE_SHIFT,
 				      obj->base.size >> PAGE_SHIFT);
 
 	obj->has_global_gtt_mapping = 0;
drivers/gpu/drm/i915/i915_gem_tiling.c +7 -7
index 537545b..92a8d27 100644
@@ -268,18 +268,18 @@ i915_gem_object_fence_ok(struct drm_i915_gem_object *obj, int tiling_mode)
 		return true;
 
 	if (INTEL_INFO(obj->base.dev)->gen == 3) {
-		if (obj->gtt_offset & ~I915_FENCE_START_MASK)
+		if (i915_gem_obj_ggtt_offset(obj) & ~I915_FENCE_START_MASK)
 			return false;
 	} else {
-		if (obj->gtt_offset & ~I830_FENCE_START_MASK)
+		if (i915_gem_obj_ggtt_offset(obj) & ~I830_FENCE_START_MASK)
 			return false;
 	}
 
 	size = i915_gem_get_gtt_size(obj->base.dev, obj->base.size, tiling_mode);
-	if (obj->gtt_space->size != size)
+	if (i915_gem_obj_ggtt_size(obj) != size)
 		return false;
 
-	if (obj->gtt_offset & (size - 1))
+	if (i915_gem_obj_ggtt_offset(obj) & (size - 1))
 		return false;
 
 	return true;
@@ -359,8 +359,8 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 		 */
 
 		obj->map_and_fenceable =
-			obj->gtt_space == NULL ||
-			(obj->gtt_offset + obj->base.size <= dev_priv->gtt.mappable_end &&
+			!i915_gem_obj_ggtt_bound(obj) ||
+			(i915_gem_obj_ggtt_offset(obj) + obj->base.size <= dev_priv->gtt.mappable_end &&
 			 i915_gem_object_fence_ok(obj, args->tiling_mode));
 
 		/* Rebind if we need a change of alignment */
@@ -369,7 +369,7 @@ i915_gem_set_tiling(struct drm_device *dev, void *data,
 				i915_gem_get_gtt_alignment(dev, obj->base.size,
 							    args->tiling_mode,
 							    false);
-			if (obj->gtt_offset & (unfenced_alignment - 1))
+			if (i915_gem_obj_ggtt_offset(obj) & (unfenced_alignment - 1))
 				ret = i915_gem_object_unbind(obj);
 		}
 
drivers/gpu/drm/i915/i915_irq.c +7 -8
index c2e11a0..4aedd38 100644
@@ -1520,7 +1520,7 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 	if (dst == NULL)
 		return NULL;
 
-	reloc_offset = src->gtt_offset;
+	reloc_offset = dst->gtt_offset = i915_gem_obj_ggtt_offset(src);
 	for (i = 0; i < num_pages; i++) {
 		unsigned long flags;
 		void *d;
@@ -1572,7 +1572,6 @@ i915_error_object_create_sized(struct drm_i915_private *dev_priv,
 		reloc_offset += PAGE_SIZE;
 	}
 	dst->page_count = num_pages;
-	dst->gtt_offset = src->gtt_offset;
 
 	return dst;
 
@@ -1626,7 +1625,7 @@ static void capture_bo(struct drm_i915_error_buffer *err,
 	err->name = obj->base.name;
 	err->rseqno = obj->last_read_seqno;
 	err->wseqno = obj->last_write_seqno;
-	err->gtt_offset = obj->gtt_offset;
+	err->gtt_offset = i915_gem_obj_ggtt_offset(obj);
 	err->read_domains = obj->base.read_domains;
 	err->write_domain = obj->base.write_domain;
 	err->fence_reg = obj->fence_reg;
@@ -1724,8 +1723,8 @@ i915_error_first_batchbuffer(struct drm_i915_private *dev_priv,
 			return NULL;
 
 		obj = ring->private;
-		if (acthd >= obj->gtt_offset &&
-		    acthd < obj->gtt_offset + obj->base.size)
+		if (acthd >= i915_gem_obj_ggtt_offset(obj) &&
+		    acthd < i915_gem_obj_ggtt_offset(obj) + obj->base.size)
 			return i915_error_object_create(dev_priv, obj);
 	}
 
@@ -1806,7 +1805,7 @@ static void i915_gem_record_active_context(struct intel_ring_buffer *ring,
 		return;
 
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		if ((error->ccid & PAGE_MASK) == obj->gtt_offset) {
+		if ((error->ccid & PAGE_MASK) == i915_gem_obj_ggtt_offset(obj)) {
 			ering->ctx = i915_error_object_create_sized(dev_priv,
 								    obj, 1);
 			break;
@@ -2160,10 +2159,10 @@ static void __always_unused i915_pageflip_stall_check(struct drm_device *dev, in
 	if (INTEL_INFO(dev)->gen >= 4) {
 		int dspsurf = DSPSURF(intel_crtc->plane);
 		stall_detected = I915_HI_DISPBASE(I915_READ(dspsurf)) ==
-					obj->gtt_offset;
+					i915_gem_obj_ggtt_offset(obj);
 	} else {
 		int dspaddr = DSPADDR(intel_crtc->plane);
-		stall_detected = I915_READ(dspaddr) == (obj->gtt_offset +
+		stall_detected = I915_READ(dspaddr) == (i915_gem_obj_ggtt_offset(obj) +
 							crtc->y * crtc->fb->pitches[0] +
 							crtc->x * crtc->fb->bits_per_pixel/8);
 	}
drivers/gpu/drm/i915/i915_trace.h +4 -4
index 3db4a68..7d283b5 100644
@@ -46,8 +46,8 @@ TRACE_EVENT(i915_gem_object_bind,
 
 	    TP_fast_assign(
 			   __entry->obj = obj;
-			   __entry->offset = obj->gtt_space->start;
-			   __entry->size = obj->gtt_space->size;
+			   __entry->offset = i915_gem_obj_ggtt_offset(obj);
+			   __entry->size = i915_gem_obj_ggtt_size(obj);
 			   __entry->mappable = mappable;
 			   ),
 
@@ -68,8 +68,8 @@ TRACE_EVENT(i915_gem_object_unbind,
 
 	    TP_fast_assign(
 			   __entry->obj = obj;
-			   __entry->offset = obj->gtt_space->start;
-			   __entry->size = obj->gtt_space->size;
+			   __entry->offset = i915_gem_obj_ggtt_offset(obj);
+			   __entry->size = i915_gem_obj_ggtt_size(obj);
 			   ),
 
 	    TP_printk("obj=%p, offset=%08x size=%x",
drivers/gpu/drm/i915/intel_display.c +15 -13
index aaa9a75..a45bb92 100644
@@ -1980,16 +1980,17 @@ static int i9xx_update_plane(struct drm_crtc *crtc, struct drm_framebuffer *fb,
 		intel_crtc->dspaddr_offset = linear_offset;
 	}
 
-	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
-		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
+		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
+		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	if (INTEL_INFO(dev)->gen >= 4) {
 		I915_MODIFY_DISPBASE(DSPSURF(plane),
-				     obj->gtt_offset + intel_crtc->dspaddr_offset);
+				     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 		I915_WRITE(DSPTILEOFF(plane), (y << 16) | x);
 		I915_WRITE(DSPLINOFF(plane), linear_offset);
 	} else
-		I915_WRITE(DSPADDR(plane), obj->gtt_offset + linear_offset);
+		I915_WRITE(DSPADDR(plane), i915_gem_obj_ggtt_offset(obj) + linear_offset);
 	POSTING_READ(reg);
 
 	return 0;
@@ -2069,11 +2070,12 @@ static int ironlake_update_plane(struct drm_crtc *crtc,
 					       fb->pitches[0]);
 	linear_offset -= intel_crtc->dspaddr_offset;
 
-	DRM_DEBUG_KMS("Writing base %08X %08lX %d %d %d\n",
-		      obj->gtt_offset, linear_offset, x, y, fb->pitches[0]);
+	DRM_DEBUG_KMS("Writing base %08lX %08lX %d %d %d\n",
+		      i915_gem_obj_ggtt_offset(obj), linear_offset, x, y,
+		      fb->pitches[0]);
 	I915_WRITE(DSPSTRIDE(plane), fb->pitches[0]);
 	I915_MODIFY_DISPBASE(DSPSURF(plane),
-			     obj->gtt_offset + intel_crtc->dspaddr_offset);
+			     i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	if (IS_HASWELL(dev)) {
 		I915_WRITE(DSPOFFSET(plane), (y << 16) | x);
 	} else {
@@ -6567,7 +6569,7 @@ static int intel_crtc_cursor_set(struct drm_crtc *crtc,
 			goto fail_unpin;
 		}
 
-		addr = obj->gtt_offset;
+		addr = i915_gem_obj_ggtt_offset(obj);
 	} else {
 		int align = IS_I830(dev) ? 16 * 1024 : 256;
 		ret = i915_gem_attach_phys_object(dev, obj,
@@ -7339,7 +7341,7 @@ static int intel_gen2_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, 0); /* aux display base address, unused */
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7380,7 +7382,7 @@ static int intel_gen3_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, MI_NOOP);
 
 	intel_mark_page_flip_active(intel_crtc);
@@ -7420,7 +7422,7 @@ static int intel_gen4_queue_flip(struct drm_device *dev,
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0]);
 	intel_ring_emit(ring,
-			(obj->gtt_offset + intel_crtc->dspaddr_offset) |
+			(i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset) |
 			obj->tiling_mode);
 
 	/* XXX Enabling the panel-fitter across page-flip is so far
@@ -7463,7 +7465,7 @@ static int intel_gen6_queue_flip(struct drm_device *dev,
 	intel_ring_emit(ring, MI_DISPLAY_FLIP |
 			MI_DISPLAY_FLIP_PLANE(intel_crtc->plane));
 	intel_ring_emit(ring, fb->pitches[0] | obj->tiling_mode);
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 
 	/* Contrary to the suggestions in the documentation,
 	 * "Enable Panel Fitter" does not seem to be required when page
@@ -7528,7 +7530,7 @@ static int intel_gen7_queue_flip(struct drm_device *dev,
 
 	intel_ring_emit(ring, MI_DISPLAY_FLIP_I915 | plane_bit);
 	intel_ring_emit(ring, (fb->pitches[0] | obj->tiling_mode));
-	intel_ring_emit(ring, obj->gtt_offset + intel_crtc->dspaddr_offset);
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(obj) + intel_crtc->dspaddr_offset);
 	intel_ring_emit(ring, (MI_NOOP));
 
 	intel_mark_page_flip_active(intel_crtc);
drivers/gpu/drm/i915/intel_fb.c +4 -4
index dff669e..f3c97e0 100644
@@ -139,11 +139,11 @@ static int intelfb_create(struct drm_fb_helper *helper,
 	info->apertures->ranges[0].base = dev->mode_config.fb_base;
 	info->apertures->ranges[0].size = dev_priv->gtt.mappable_end;
 
-	info->fix.smem_start = dev->mode_config.fb_base + obj->gtt_offset;
+	info->fix.smem_start = dev->mode_config.fb_base + i915_gem_obj_ggtt_offset(obj);
 	info->fix.smem_len = size;
 
 	info->screen_base =
-		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
+		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   size);
 	if (!info->screen_base) {
 		ret = -ENOSPC;
@@ -166,9 +166,9 @@ static int intelfb_create(struct drm_fb_helper *helper,
 
 	/* Use default scratch pixmap (info->pixmap.flags = FB_PIXMAP_SYSTEM) */
 
-	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08x, bo %p\n",
+	DRM_DEBUG_KMS("allocated %dx%d fb: 0x%08lx, bo %p\n",
 		      fb->width, fb->height,
-		      obj->gtt_offset, obj);
+		      i915_gem_obj_ggtt_offset(obj), obj);
 
 
 	mutex_unlock(&dev->struct_mutex);
drivers/gpu/drm/i915/intel_overlay.c +7 -7
index a369881..81c3ca1 100644
@@ -196,7 +196,7 @@ intel_overlay_map_regs(struct intel_overlay *overlay)
 		regs = (struct overlay_registers __iomem *)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_wc(dev_priv->gtt.mappable,
-					 overlay->reg_bo->gtt_offset);
+					 i915_gem_obj_ggtt_offset(overlay->reg_bo));
 
 	return regs;
 }
@@ -740,7 +740,7 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 	swidth = params->src_w;
 	swidthsw = calc_swidthsw(overlay->dev, params->offset_Y, tmp_width);
 	sheight = params->src_h;
-	iowrite32(new_bo->gtt_offset + params->offset_Y, &regs->OBUF_0Y);
+	iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_Y, &regs->OBUF_0Y);
 	ostride = params->stride_Y;
 
 	if (params->format & I915_OVERLAY_YUV_PLANAR) {
@@ -754,8 +754,8 @@ static int intel_overlay_do_put_image(struct intel_overlay *overlay,
 				      params->src_w/uv_hscale);
 		swidthsw |= max_t(u32, tmp_U, tmp_V) << 16;
 		sheight |= (params->src_h/uv_vscale) << 16;
-		iowrite32(new_bo->gtt_offset + params->offset_U, &regs->OBUF_0U);
-		iowrite32(new_bo->gtt_offset + params->offset_V, &regs->OBUF_0V);
+		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_U, &regs->OBUF_0U);
+		iowrite32(i915_gem_obj_ggtt_offset(new_bo) + params->offset_V, &regs->OBUF_0V);
 		ostride |= params->stride_UV << 16;
 	}
 
@@ -1355,7 +1355,7 @@ void intel_setup_overlay(struct drm_device *dev)
 			DRM_ERROR("failed to pin overlay register bo\n");
 			goto out_free_bo;
 		}
-		overlay->flip_addr = reg_bo->gtt_offset;
+		overlay->flip_addr = i915_gem_obj_ggtt_offset(reg_bo);
 
 		ret = i915_gem_object_set_to_gtt_domain(reg_bo, true);
 		if (ret) {
@@ -1435,7 +1435,7 @@ intel_overlay_map_regs_atomic(struct intel_overlay *overlay)
 			overlay->reg_bo->phys_obj->handle->vaddr;
 	else
 		regs = io_mapping_map_atomic_wc(dev_priv->gtt.mappable,
-						overlay->reg_bo->gtt_offset);
+						i915_gem_obj_ggtt_offset(overlay->reg_bo));
 
 	return regs;
 }
@@ -1468,7 +1468,7 @@ intel_overlay_capture_error_state(struct drm_device *dev)
 	if (OVERLAY_NEEDS_PHYSICAL(overlay->dev))
 		error->base = (__force long)overlay->reg_bo->phys_obj->handle->vaddr;
 	else
-		error->base = overlay->reg_bo->gtt_offset;
+		error->base = i915_gem_obj_ggtt_offset(overlay->reg_bo);
 
 	regs = intel_overlay_map_regs_atomic(overlay);
 	if (!regs)
drivers/gpu/drm/i915/intel_pm.c +4 -4
index 0eed35d..125a741 100644
@@ -218,7 +218,7 @@ static void ironlake_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 		   (stall_watermark << DPFC_RECOMP_STALL_WM_SHIFT) |
 		   (interval << DPFC_RECOMP_TIMER_COUNT_SHIFT));
 	I915_WRITE(ILK_DPFC_FENCE_YOFF, crtc->y);
-	I915_WRITE(ILK_FBC_RT_BASE, obj->gtt_offset | ILK_FBC_RT_VALID);
+	I915_WRITE(ILK_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj) | ILK_FBC_RT_VALID);
 	/* enable it... */
 	I915_WRITE(ILK_DPFC_CONTROL, dpfc_ctl | DPFC_CTL_EN);
 
@@ -275,7 +275,7 @@ static void gen7_enable_fbc(struct drm_crtc *crtc, unsigned long interval)
 	struct drm_i915_gem_object *obj = intel_fb->obj;
 	struct intel_crtc *intel_crtc = to_intel_crtc(crtc);
 
-	I915_WRITE(IVB_FBC_RT_BASE, obj->gtt_offset);
+	I915_WRITE(IVB_FBC_RT_BASE, i915_gem_obj_ggtt_offset(obj));
 
 	I915_WRITE(ILK_DPFC_CONTROL, DPFC_CTL_EN | DPFC_CTL_LIMIT_1X |
 		   IVB_DPFC_CTL_FENCE_EN |
@@ -3700,7 +3700,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 
 	intel_ring_emit(ring, MI_SUSPEND_FLUSH | MI_SUSPEND_FLUSH_EN);
 	intel_ring_emit(ring, MI_SET_CONTEXT);
-	intel_ring_emit(ring, dev_priv->ips.renderctx->gtt_offset |
+	intel_ring_emit(ring, i915_gem_obj_ggtt_offset(dev_priv->ips.renderctx) |
 			MI_MM_SPACE_GTT |
 			MI_SAVE_EXT_STATE_EN |
 			MI_RESTORE_EXT_STATE_EN |
@@ -3723,7 +3723,7 @@ static void ironlake_enable_rc6(struct drm_device *dev)
 		return;
 	}
 
-	I915_WRITE(PWRCTXA, dev_priv->ips.pwrctx->gtt_offset | PWRCTX_EN);
+	I915_WRITE(PWRCTXA, i915_gem_obj_ggtt_offset(dev_priv->ips.pwrctx) | PWRCTX_EN);
 	I915_WRITE(RSTDBYCTL, I915_READ(RSTDBYCTL) & ~RCX_SW_EXIT);
 }
 
drivers/gpu/drm/i915/intel_ringbuffer.c +6 -6
index 18ca76e..5b647eb 100644
@@ -440,14 +440,14 @@ static int init_ring_common(struct intel_ring_buffer *ring)
 	 * registers with the above sequence (the readback of the HEAD registers
 	 * also enforces ordering), otherwise the hw might lose the new ring
 	 * register values. */
-	I915_WRITE_START(ring, obj->gtt_offset);
+	I915_WRITE_START(ring, i915_gem_obj_ggtt_offset(obj));
 	I915_WRITE_CTL(ring,
 			((ring->size - PAGE_SIZE) & RING_NR_PAGES)
 			| RING_VALID);
 
 	/* If the head is still not zero, the ring is dead */
 	if (wait_for((I915_READ_CTL(ring) & RING_VALID) != 0 &&
-		     I915_READ_START(ring) == obj->gtt_offset &&
+		     I915_READ_START(ring) == i915_gem_obj_ggtt_offset(obj) &&
 		     (I915_READ_HEAD(ring) & HEAD_ADDR) == 0, 50)) {
 		DRM_ERROR("%s initialization failed "
 				"ctl %08x head %08x tail %08x start %08x\n",
@@ -505,7 +505,7 @@ init_pipe_control(struct intel_ring_buffer *ring)
 	if (ret)
 		goto err_unref;
 
-	pc->gtt_offset = obj->gtt_offset;
+	pc->gtt_offset = i915_gem_obj_ggtt_offset(obj);
 	pc->cpu_page = kmap(sg_page(obj->pages->sgl));
 	if (pc->cpu_page == NULL) {
 		ret = -ENOMEM;
@@ -1145,7 +1145,7 @@ i830_dispatch_execbuffer(struct intel_ring_buffer *ring,
 		intel_ring_advance(ring);
 	} else {
 		struct drm_i915_gem_object *obj = ring->private;
-		u32 cs_offset = obj->gtt_offset;
+		u32 cs_offset = i915_gem_obj_ggtt_offset(obj);
 
 		if (len > I830_BATCH_LIMIT)
 			return -ENOSPC;
@@ -1230,7 +1230,7 @@ static int init_status_page(struct intel_ring_buffer *ring)
 		goto err_unref;
 	}
 
-	ring->status_page.gfx_addr = obj->gtt_offset;
+	ring->status_page.gfx_addr = i915_gem_obj_ggtt_offset(obj);
 	ring->status_page.page_addr = kmap(sg_page(obj->pages->sgl));
 	if (ring->status_page.page_addr == NULL) {
 		ret = -ENOMEM;
@@ -1317,7 +1317,7 @@ static int intel_init_ring_buffer(struct drm_device *dev,
 		goto err_unpin;
 
 	ring->virtual_start =
-		ioremap_wc(dev_priv->gtt.mappable_base + obj->gtt_offset,
+		ioremap_wc(dev_priv->gtt.mappable_base + i915_gem_obj_ggtt_offset(obj),
 			   ring->size);
 	if (ring->virtual_start == NULL) {
 		DRM_ERROR("Failed to map ringbuffer.\n");
drivers/gpu/drm/i915/intel_sprite.c +5 -3
index 1fa5612..55bdf70 100644
@@ -133,7 +133,7 @@ vlv_update_plane(struct drm_plane *dplane, struct drm_framebuffer *fb,
 
 	I915_WRITE(SPSIZE(pipe, plane), (crtc_h << 16) | crtc_w);
 	I915_WRITE(SPCNTR(pipe, plane), sprctl);
-	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), obj->gtt_offset +
+	I915_MODIFY_DISPBASE(SPSURF(pipe, plane), i915_gem_obj_ggtt_offset(obj) +
 			     sprsurf_offset);
 	POSTING_READ(SPSURF(pipe, plane));
 }
@@ -308,7 +308,8 @@ ivb_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	if (intel_plane->can_scale)
 		I915_WRITE(SPRSCALE(pipe), sprscale);
 	I915_WRITE(SPRCTL(pipe), sprctl);
-	I915_MODIFY_DISPBASE(SPRSURF(pipe), obj->gtt_offset + sprsurf_offset);
+	I915_MODIFY_DISPBASE(SPRSURF(pipe),
+			     i915_gem_obj_ggtt_offset(obj) + sprsurf_offset);
 	POSTING_READ(SPRSURF(pipe));
 
 	/* potentially re-enable LP watermarks */
@@ -478,7 +479,8 @@ ilk_update_plane(struct drm_plane *plane, struct drm_framebuffer *fb,
 	I915_WRITE(DVSSIZE(pipe), (crtc_h << 16) | crtc_w);
 	I915_WRITE(DVSSCALE(pipe), dvsscale);
 	I915_WRITE(DVSCNTR(pipe), dvscntr);
-	I915_MODIFY_DISPBASE(DVSSURF(pipe), obj->gtt_offset + dvssurf_offset);
+	I915_MODIFY_DISPBASE(DVSSURF(pipe),
+			     i915_gem_obj_ggtt_offset(obj) + dvssurf_offset);
 	POSTING_READ(DVSSURF(pipe));
 }
 
Signature · 1 line
1.8.3.2
#6 lore raw

PATCH 7/9 drm/i915: Kill obj->gtt_offset

In reply to Ben Widawsky

With the getters in place from the previous patch this members serves no purpose other than saving one spare pointer chase, which will be killed in the next patch anyway.

Moving to VMAs, this members adds unnecessary confusion since an object may exist at different offsets in different VMs.

v2: Properly preserve the stolen offset. This code is a bit hacky but it all goes away when we embed the drm_mm_node and removes the need for the incorrect patch I submitted previously: "Use gtt_space->start for stolen reservation"

---
 drivers/gpu/drm/i915/i915_drv.h        |  9 +--------
 drivers/gpu/drm/i915/i915_gem.c        |  2 --
 drivers/gpu/drm/i915/i915_gem_gtt.c    | 14 ++++++++------
 drivers/gpu/drm/i915/i915_gem_stolen.c |  9 ++++++---
 4 files changed, 15 insertions(+), 19 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +1 -8
index 626cff5..68cce56 100644
@@ -1201,7 +1201,7 @@ enum hdmi_force_audio {
 	HDMI_AUDIO_ON,			/* force turn on HDMI audio */
 };
 
-#define I915_GTT_RESERVED ((struct drm_mm_node *)0x1)
+#define I915_GTT_RESERVED (1<<0)
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
@@ -1329,13 +1329,6 @@ struct drm_i915_gem_object {
 	unsigned long exec_handle;
 	struct drm_i915_gem_exec_object2 *exec_entry;
 
-	/**
-	 * Current offset of the object in GTT space.
-	 *
-	 * This is the same as gtt_space->start
-	 */
-	uint32_t gtt_offset;
-
 	struct intel_ring_buffer *ring;
 
 	/** Breadcrumb of last rendering to the buffer. */
drivers/gpu/drm/i915/i915_gem.c +0 -2
index 4558059..13c0055 100644
@@ -2623,7 +2623,6 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 
 	drm_mm_put_block(obj->gtt_space);
 	obj->gtt_space = NULL;
-	obj->gtt_offset = 0;
 
 	return 0;
 }
@@ -3153,7 +3152,6 @@ search_free:
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
 	obj->gtt_space = node;
-	obj->gtt_offset = node->start;
 
 	fenceable =
 		node->size == fence_size &&
drivers/gpu/drm/i915/i915_gem_gtt.c +8 -6
index 6f0a4c0..76a4095 100644
@@ -629,18 +629,20 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
+		uintptr_t offset = (uintptr_t) obj->gtt_space;
 		int ret;
-		DRM_DEBUG_KMS("reserving preallocated space: %x + %zx\n",
-			      obj->gtt_offset, obj->base.size);
+		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
+			      offset, obj->base.size);
 
-		BUG_ON(obj->gtt_space != I915_GTT_RESERVED);
+		BUG_ON((offset & I915_GTT_RESERVED) != 0);
+		offset &= ~I915_GTT_RESERVED;
 		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
 		if (!obj->gtt_space) {
-			DRM_ERROR("Failed to preserve object at offset %x\n",
-				  obj->gtt_offset);
+			DRM_ERROR("Failed to preserve object at offset %lx\n",
+				  offset);
 			continue;
 		}
-		obj->gtt_space->start = obj->gtt_offset;
+		obj->gtt_space->start = (unsigned long)offset;
 		obj->gtt_space->size = obj->base.size;
 		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
 					  obj->gtt_space);
drivers/gpu/drm/i915/i915_gem_stolen.c +6 -3
index 95c3836..d70b9a9 100644
@@ -409,10 +409,13 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
 			goto free_out;
 		}
-	} else
-		obj->gtt_space = I915_GTT_RESERVED;
+	} else {
+		if (WARN_ON(gtt_offset & ~PAGE_MASK))
+			DRM_DEBUG_KMS("Cannot preserve non page aligned offset\n");
+		obj->gtt_space =
+			(struct drm_mm_node *)((uintptr_t)(I915_GTT_RESERVED | gtt_offset));
+	}
 
-	obj->gtt_offset = gtt_offset;
 	obj->has_global_gtt_mapping = 1;
 
 	list_add_tail(&obj->global_list, &dev_priv->mm.bound_list);
Signature · 1 line
1.8.3.2
#7 lore raw

PATCH 8/9 drm/i915: Embed drm_mm_node in i915 gem obj

In reply to Ben Widawsky

Embedding the node in the obj is more natural in the transition to VMAs which will also have embedded nodes. This change also helps transition away from put_block to remove node.

Though it's quite an uncommon occurrence, it's somewhat convenient to not fail at bind time because we cannot allocate the node. Though in practice there are other allocations (like the request structure) which would probably make this point not terribly useful.

Quoting Daniel:
Note that the only difference between put_block and remove_node is that the former fills up the preallocation cache. Which we don't need anyway and hence is just wasted space.

v2: Clean up the stolen preallocation code.
Rebased on the reserve_node patches
renames ggtt_ stuff to gtt_ stuff
WARN_ON if the object is already bound (which doesn't mean it's in the bound list, tricky)

Conflicts:

	drivers/gpu/drm/i915/i915_drv.h
	drivers/gpu/drm/i915/i915_gem.c
	drivers/gpu/drm/i915/i915_gem_evict.c
	drivers/gpu/drm/i915/i915_gem_gtt.c
	drivers/gpu/drm/i915/i915_gem_stolen.c
---
 drivers/gpu/drm/i915/i915_drv.h        | 11 +++++------
 drivers/gpu/drm/i915/i915_gem.c        | 31 +++++++++++--------------------
 drivers/gpu/drm/i915/i915_gem_evict.c  |  6 +++---
 drivers/gpu/drm/i915/i915_gem_gtt.c    | 23 +++++------------------
 drivers/gpu/drm/i915/i915_gem_stolen.c | 22 ++++------------------
 5 files changed, 28 insertions(+), 65 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +5 -6
index 68cce56..c8d6104 100644
@@ -1201,7 +1201,6 @@ enum hdmi_force_audio {
 	HDMI_AUDIO_ON,			/* force turn on HDMI audio */
 };
 
-#define I915_GTT_RESERVED (1<<0)
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
@@ -1228,7 +1227,7 @@ struct drm_i915_gem_object {
 	const struct drm_i915_gem_object_ops *ops;
 
 	/** Current space allocated to this object in the GTT, if any. */
-	struct drm_mm_node *gtt_space;
+	struct drm_mm_node gtt_space;
 	/** Stolen memory for this object, instead of being backed by shmem. */
 	struct drm_mm_node *stolen;
 	struct list_head global_list;
@@ -1358,14 +1357,14 @@ struct drm_i915_gem_object {
 static inline unsigned long
 i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
 {
-	return o->gtt_space->start;
+	return o->gtt_space.start;
 }
 
 /* Whether or not this object is currently mapped by the translation tables */
 static inline bool
 i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
 {
-	return o->gtt_space != NULL;
+	return drm_mm_node_allocated(&o->gtt_space);
 }
 
 /* The size used in the translation tables may be larger than the actual size of
@@ -1375,14 +1374,14 @@ i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
 static inline unsigned long
 i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
 {
-	return o->gtt_space->size;
+	return o->gtt_space.size;
 }
 
 static inline void
 i915_gem_obj_ggtt_set_color(struct drm_i915_gem_object *o,
 			    enum i915_cache_level color)
 {
-	o->gtt_space->color = color;
+	o->gtt_space.color = color;
 }
 
 /**
drivers/gpu/drm/i915/i915_gem.c +11 -20
index 13c0055..af61be8 100644
@@ -2621,8 +2621,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 	/* Avoid an unnecessary call to unbind on rebind. */
 	obj->map_and_fenceable = true;
 
-	drm_mm_put_block(obj->gtt_space);
-	obj->gtt_space = NULL;
+	drm_mm_remove_node(&obj->gtt_space);
 
 	return 0;
 }
@@ -3000,7 +2999,7 @@ static bool i915_gem_valid_gtt_space(struct drm_device *dev,
 	if (HAS_LLC(dev))
 		return true;
 
-	if (gtt_space == NULL)
+	if (!drm_mm_node_allocated(gtt_space))
 		return true;
 
 	if (list_empty(&gtt_space->node_list))
@@ -3068,7 +3067,6 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_mm_node *node;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
 	bool mappable, fenceable;
 	size_t gtt_max = map_and_fenceable ?
@@ -3113,14 +3111,9 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_pin_pages(obj);
 
-	node = kzalloc(sizeof(*node), GFP_KERNEL);
-	if (node == NULL) {
-		i915_gem_object_unpin_pages(obj);
-		return -ENOMEM;
-	}
-
 search_free:
-	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
+	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space,
+						  &obj->gtt_space,
 						  size, alignment,
 						  obj->cache_level, 0, gtt_max);
 	if (ret) {
@@ -3132,30 +3125,28 @@ search_free:
 			goto search_free;
 
 		i915_gem_object_unpin_pages(obj);
-		kfree(node);
 		return ret;
 	}
-	if (WARN_ON(!i915_gem_valid_gtt_space(dev, node, obj->cache_level))) {
+	if (WARN_ON(!i915_gem_valid_gtt_space(dev, &obj->gtt_space,
+					      obj->cache_level))) {
 		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(node);
+		drm_mm_remove_node(&obj->gtt_space);
 		return -EINVAL;
 	}
 
 	ret = i915_gem_gtt_prepare_object(obj);
 	if (ret) {
 		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(node);
+		drm_mm_remove_node(&obj->gtt_space);
 		return ret;
 	}
 
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
-	obj->gtt_space = node;
-
 	fenceable =
-		node->size == fence_size &&
-		(node->start & (fence_alignment - 1)) == 0;
+		i915_gem_obj_ggtt_size(obj) == fence_size &&
+		(i915_gem_obj_ggtt_offset(obj) & (fence_alignment - 1)) == 0;
 
 	mappable = i915_gem_obj_ggtt_offset(obj) + obj->base.size <=
 		dev_priv->gtt.mappable_end;
@@ -3319,7 +3310,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return -EBUSY;
 	}
 
-	if (!i915_gem_valid_gtt_space(dev, obj->gtt_space, cache_level)) {
+	if (!i915_gem_valid_gtt_space(dev, &obj->gtt_space, cache_level)) {
 		ret = i915_gem_object_unbind(obj);
 		if (ret)
 			return ret;
drivers/gpu/drm/i915/i915_gem_evict.c +3 -3
index c86d5d9..5f8afc4 100644
@@ -38,7 +38,7 @@ mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind)
 		return false;
 
 	list_add(&obj->exec_list, unwind);
-	return drm_mm_scan_add_block(obj->gtt_space);
+	return drm_mm_scan_add_block(&obj->gtt_space);
 }
 
 int
@@ -107,7 +107,7 @@ none:
 				       struct drm_i915_gem_object,
 				       exec_list);
 
-		ret = drm_mm_scan_remove_block(obj->gtt_space);
+		ret = drm_mm_scan_remove_block(&obj->gtt_space);
 		BUG_ON(ret);
 
 		list_del_init(&obj->exec_list);
@@ -127,7 +127,7 @@ found:
 		obj = list_first_entry(&unwind_list,
 				       struct drm_i915_gem_object,
 				       exec_list);
-		if (drm_mm_scan_remove_block(obj->gtt_space)) {
+		if (drm_mm_scan_remove_block(&obj->gtt_space)) {
 			list_move(&obj->exec_list, &eviction_list);
 			drm_gem_object_reference(&obj->base);
 			continue;
drivers/gpu/drm/i915/i915_gem_gtt.c +5 -18
index 76a4095..242d0f9 100644
@@ -629,28 +629,15 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		uintptr_t offset = (uintptr_t) obj->gtt_space;
 		int ret;
 		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
-			      offset, obj->base.size);
-
-		BUG_ON((offset & I915_GTT_RESERVED) != 0);
-		offset &= ~I915_GTT_RESERVED;
-		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
-		if (!obj->gtt_space) {
-			DRM_ERROR("Failed to preserve object at offset %lx\n",
-				  offset);
-			continue;
-		}
-		obj->gtt_space->start = (unsigned long)offset;
-		obj->gtt_space->size = obj->base.size;
+			      i915_gem_obj_ggtt_offset(obj), obj->base.size);
+
+		WARN_ON(i915_gem_obj_ggtt_bound(obj));
 		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
-					  obj->gtt_space);
-		if (ret) {
+					  &obj->gtt_space);
+		if (ret)
 			DRM_DEBUG_KMS("Reservation failed\n");
-			kfree(obj->gtt_space);
-			obj->gtt_space = NULL;
-		}
 		obj->has_global_gtt_mapping = 1;
 	}
 
drivers/gpu/drm/i915/i915_gem_stolen.c +4 -18
index d70b9a9..7317606 100644
@@ -394,26 +394,15 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	 * setting up the GTT space. The actual reservation will occur
 	 * later.
 	 */
+	obj->gtt_space.start = gtt_offset;
+	obj->gtt_space.size = size;
 	if (drm_mm_initialized(&dev_priv->mm.gtt_space)) {
-		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
-		if (!obj->gtt_space) {
-			DRM_DEBUG_KMS("-ENOMEM stolen GTT space\n");
-			goto unref_out;
-		}
-
-		obj->gtt_space->start = gtt_offset;
-		obj->gtt_space->size = size;
 		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
-					  obj->gtt_space);
+					  &obj->gtt_space);
 		if (ret) {
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
-			goto free_out;
+			goto unref_out;
 		}
-	} else {
-		if (WARN_ON(gtt_offset & ~PAGE_MASK))
-			DRM_DEBUG_KMS("Cannot preserve non page aligned offset\n");
-		obj->gtt_space =
-			(struct drm_mm_node *)((uintptr_t)(I915_GTT_RESERVED | gtt_offset));
 	}
 
 	obj->has_global_gtt_mapping = 1;
@@ -423,9 +412,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 
 	return obj;
 
-free_out:
-	kfree(obj->gtt_space);
-	obj->gtt_space = NULL;
 unref_out:
 	drm_gem_object_unreference(&obj->base);
 	return NULL;
Signature · 1 line
1.8.3.2
#8 lore raw

Re: [PATCH 8/9] drm/i915: Embed drm_mm_node in i915 gem obj

Quoted 14 lines · Ben Widawsky

Embedding the node in the obj is more natural in the transition to VMAs which will also have embedded nodes. This change also helps transition away from put_block to remove node.

Though it's quite an uncommon occurrence, it's somewhat convenient to not fail at bind time because we cannot allocate the node. Though in practice there are other allocations (like the request structure) which would probably make this point not terribly useful.

Quoting Daniel:
Note that the only difference between put_block and remove_node is that the former fills up the preallocation cache. Which we don't need anyway and hence is just wasted space.

Quoted 7 lines

v2: Clean up the stolen preallocation code.
Rebased on the reserve_node patches
renames ggtt_ stuff to gtt_ stuff
WARN_ON if the object is already bound (which doesn't mean it's in the bound list, tricky)

Merged thus far with Dave's irc-ack on the two drm_mm patches. I think I'll wait for some good review on the top-down allocator first and maybe also for the actualy i915 users to show up before merging the last drm_mm patch.
-Daniel

Quoted 285 lines

Conflicts:

	drivers/gpu/drm/i915/i915_drv.h
	drivers/gpu/drm/i915/i915_gem.c
	drivers/gpu/drm/i915/i915_gem_evict.c
	drivers/gpu/drm/i915/i915_gem_gtt.c
	drivers/gpu/drm/i915/i915_gem_stolen.c
---
 drivers/gpu/drm/i915/i915_drv.h        | 11 +++++------
 drivers/gpu/drm/i915/i915_gem.c        | 31 +++++++++++--------------------
 drivers/gpu/drm/i915/i915_gem_evict.c  |  6 +++---
 drivers/gpu/drm/i915/i915_gem_gtt.c    | 23 +++++------------------
 drivers/gpu/drm/i915/i915_gem_stolen.c | 22 ++++------------------
 5 files changed, 28 insertions(+), 65 deletions(-)
drivers/gpu/drm/i915/i915_drv.h +5 -6
index 68cce56..c8d6104 100644
@@ -1201,7 +1201,6 @@ enum hdmi_force_audio {
 	HDMI_AUDIO_ON,			/* force turn on HDMI audio */
 };
 
-#define I915_GTT_RESERVED (1<<0)
 #define I915_GTT_OFFSET_NONE ((u32)-1)
 
 struct drm_i915_gem_object_ops {
@@ -1228,7 +1227,7 @@ struct drm_i915_gem_object {
 	const struct drm_i915_gem_object_ops *ops;
 
 	/** Current space allocated to this object in the GTT, if any. */
-	struct drm_mm_node *gtt_space;
+	struct drm_mm_node gtt_space;
 	/** Stolen memory for this object, instead of being backed by shmem. */
 	struct drm_mm_node *stolen;
 	struct list_head global_list;
@@ -1358,14 +1357,14 @@ struct drm_i915_gem_object {
 static inline unsigned long
 i915_gem_obj_ggtt_offset(struct drm_i915_gem_object *o)
 {
-	return o->gtt_space->start;
+	return o->gtt_space.start;
 }
 
 /* Whether or not this object is currently mapped by the translation tables */
 static inline bool
 i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
 {
-	return o->gtt_space != NULL;
+	return drm_mm_node_allocated(&o->gtt_space);
 }
 
 /* The size used in the translation tables may be larger than the actual size of
@@ -1375,14 +1374,14 @@ i915_gem_obj_ggtt_bound(struct drm_i915_gem_object *o)
 static inline unsigned long
 i915_gem_obj_ggtt_size(struct drm_i915_gem_object *o)
 {
-	return o->gtt_space->size;
+	return o->gtt_space.size;
 }
 
 static inline void
 i915_gem_obj_ggtt_set_color(struct drm_i915_gem_object *o,
 			    enum i915_cache_level color)
 {
-	o->gtt_space->color = color;
+	o->gtt_space.color = color;
 }
 
 /**
drivers/gpu/drm/i915/i915_gem.c +11 -20
index 13c0055..af61be8 100644
@@ -2621,8 +2621,7 @@ i915_gem_object_unbind(struct drm_i915_gem_object *obj)
 	/* Avoid an unnecessary call to unbind on rebind. */
 	obj->map_and_fenceable = true;
 
-	drm_mm_put_block(obj->gtt_space);
-	obj->gtt_space = NULL;
+	drm_mm_remove_node(&obj->gtt_space);
 
 	return 0;
 }
@@ -3000,7 +2999,7 @@ static bool i915_gem_valid_gtt_space(struct drm_device *dev,
 	if (HAS_LLC(dev))
 		return true;
 
-	if (gtt_space == NULL)
+	if (!drm_mm_node_allocated(gtt_space))
 		return true;
 
 	if (list_empty(&gtt_space->node_list))
@@ -3068,7 +3067,6 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 {
 	struct drm_device *dev = obj->base.dev;
 	drm_i915_private_t *dev_priv = dev->dev_private;
-	struct drm_mm_node *node;
 	u32 size, fence_size, fence_alignment, unfenced_alignment;
 	bool mappable, fenceable;
 	size_t gtt_max = map_and_fenceable ?
@@ -3113,14 +3111,9 @@ i915_gem_object_bind_to_gtt(struct drm_i915_gem_object *obj,
 
 	i915_gem_object_pin_pages(obj);
 
-	node = kzalloc(sizeof(*node), GFP_KERNEL);
-	if (node == NULL) {
-		i915_gem_object_unpin_pages(obj);
-		return -ENOMEM;
-	}
-
 search_free:
-	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space, node,
+	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space,
+						  &obj->gtt_space,
 						  size, alignment,
 						  obj->cache_level, 0, gtt_max);
 	if (ret) {
@@ -3132,30 +3125,28 @@ search_free:
 			goto search_free;
 
 		i915_gem_object_unpin_pages(obj);
-		kfree(node);
 		return ret;
 	}
-	if (WARN_ON(!i915_gem_valid_gtt_space(dev, node, obj->cache_level))) {
+	if (WARN_ON(!i915_gem_valid_gtt_space(dev, &obj->gtt_space,
+					      obj->cache_level))) {
 		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(node);
+		drm_mm_remove_node(&obj->gtt_space);
 		return -EINVAL;
 	}
 
 	ret = i915_gem_gtt_prepare_object(obj);
 	if (ret) {
 		i915_gem_object_unpin_pages(obj);
-		drm_mm_put_block(node);
+		drm_mm_remove_node(&obj->gtt_space);
 		return ret;
 	}
 
 	list_move_tail(&obj->global_list, &dev_priv->mm.bound_list);
 	list_add_tail(&obj->mm_list, &dev_priv->mm.inactive_list);
 
-	obj->gtt_space = node;
-
 	fenceable =
-		node->size == fence_size &&
-		(node->start & (fence_alignment - 1)) == 0;
+		i915_gem_obj_ggtt_size(obj) == fence_size &&
+		(i915_gem_obj_ggtt_offset(obj) & (fence_alignment - 1)) == 0;
 
 	mappable = i915_gem_obj_ggtt_offset(obj) + obj->base.size <=
 		dev_priv->gtt.mappable_end;
@@ -3319,7 +3310,7 @@ int i915_gem_object_set_cache_level(struct drm_i915_gem_object *obj,
 		return -EBUSY;
 	}
 
-	if (!i915_gem_valid_gtt_space(dev, obj->gtt_space, cache_level)) {
+	if (!i915_gem_valid_gtt_space(dev, &obj->gtt_space, cache_level)) {
 		ret = i915_gem_object_unbind(obj);
 		if (ret)
 			return ret;
drivers/gpu/drm/i915/i915_gem_evict.c +3 -3
index c86d5d9..5f8afc4 100644
@@ -38,7 +38,7 @@ mark_free(struct drm_i915_gem_object *obj, struct list_head *unwind)
 		return false;
 
 	list_add(&obj->exec_list, unwind);
-	return drm_mm_scan_add_block(obj->gtt_space);
+	return drm_mm_scan_add_block(&obj->gtt_space);
 }
 
 int
@@ -107,7 +107,7 @@ none:
 				       struct drm_i915_gem_object,
 				       exec_list);
 
-		ret = drm_mm_scan_remove_block(obj->gtt_space);
+		ret = drm_mm_scan_remove_block(&obj->gtt_space);
 		BUG_ON(ret);
 
 		list_del_init(&obj->exec_list);
@@ -127,7 +127,7 @@ found:
 		obj = list_first_entry(&unwind_list,
 				       struct drm_i915_gem_object,
 				       exec_list);
-		if (drm_mm_scan_remove_block(obj->gtt_space)) {
+		if (drm_mm_scan_remove_block(&obj->gtt_space)) {
 			list_move(&obj->exec_list, &eviction_list);
 			drm_gem_object_reference(&obj->base);
 			continue;
drivers/gpu/drm/i915/i915_gem_gtt.c +5 -18
index 76a4095..242d0f9 100644
@@ -629,28 +629,15 @@ void i915_gem_setup_global_gtt(struct drm_device *dev,
 
 	/* Mark any preallocated objects as occupied */
 	list_for_each_entry(obj, &dev_priv->mm.bound_list, global_list) {
-		uintptr_t offset = (uintptr_t) obj->gtt_space;
 		int ret;
 		DRM_DEBUG_KMS("reserving preallocated space: %lx + %zx\n",
-			      offset, obj->base.size);
-
-		BUG_ON((offset & I915_GTT_RESERVED) != 0);
-		offset &= ~I915_GTT_RESERVED;
-		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
-		if (!obj->gtt_space) {
-			DRM_ERROR("Failed to preserve object at offset %lx\n",
-				  offset);
-			continue;
-		}
-		obj->gtt_space->start = (unsigned long)offset;
-		obj->gtt_space->size = obj->base.size;
+			      i915_gem_obj_ggtt_offset(obj), obj->base.size);
+
+		WARN_ON(i915_gem_obj_ggtt_bound(obj));
 		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
-					  obj->gtt_space);
-		if (ret) {
+					  &obj->gtt_space);
+		if (ret)
 			DRM_DEBUG_KMS("Reservation failed\n");
-			kfree(obj->gtt_space);
-			obj->gtt_space = NULL;
-		}
 		obj->has_global_gtt_mapping = 1;
 	}
 
drivers/gpu/drm/i915/i915_gem_stolen.c +4 -18
index d70b9a9..7317606 100644
@@ -394,26 +394,15 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 	 * setting up the GTT space. The actual reservation will occur
 	 * later.
 	 */
+	obj->gtt_space.start = gtt_offset;
+	obj->gtt_space.size = size;
 	if (drm_mm_initialized(&dev_priv->mm.gtt_space)) {
-		obj->gtt_space = kzalloc(sizeof(*obj->gtt_space), GFP_KERNEL);
-		if (!obj->gtt_space) {
-			DRM_DEBUG_KMS("-ENOMEM stolen GTT space\n");
-			goto unref_out;
-		}
-
-		obj->gtt_space->start = gtt_offset;
-		obj->gtt_space->size = size;
 		ret = drm_mm_reserve_node(&dev_priv->mm.gtt_space,
-					  obj->gtt_space);
+					  &obj->gtt_space);
 		if (ret) {
 			DRM_DEBUG_KMS("failed to allocate stolen GTT space\n");
-			goto free_out;
+			goto unref_out;
 		}
-	} else {
-		if (WARN_ON(gtt_offset & ~PAGE_MASK))
-			DRM_DEBUG_KMS("Cannot preserve non page aligned offset\n");
-		obj->gtt_space =
-			(struct drm_mm_node *)((uintptr_t)(I915_GTT_RESERVED | gtt_offset));
 	}
 
 	obj->has_global_gtt_mapping = 1;
@@ -423,9 +412,6 @@ i915_gem_object_create_stolen_for_preallocated(struct drm_device *dev,
 
 	return obj;
 
-free_out:
-	kfree(obj->gtt_space);
-	obj->gtt_space = NULL;
 unref_out:
 	drm_gem_object_unreference(&obj->base);
 	return NULL;
Signature · 6 lines
1.8.3.2

_______________________________________________
Intel-gfx mailing list
[email protected]
http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Signature · 3 lines
Daniel Vetter
Software Engineer, Intel Corporation
+41 (0) 79 365 57 48 - http://blog.ffwll.ch
#9 lore raw

PATCH 9/9 drm: Optionally create mm blocks from top-to-bottom

In reply to Ben Widawsky

From: Chris Wilson <[email protected]>

Clients like i915 needs to segregate cache domains within the GTT which can lead to small amounts of fragmentation. By allocating the uncached buffers from the bottom and the cacheable buffers from the top, we can reduce the amount of wasted space and also optimize allocation of the mappable portion of the GTT to only those buffers that require CPU access through the GTT.

v2 by Ben:
Update callers in i915_gem_object_bind_to_gtt() Turn search flags and allocation flags into separate enums Make checkpatch happy where logical/easy

v3: by Ben:
Rebased on create_block removal

v4: by Ben:
Rebased on reserve_node addition.

Conflicts:
drivers/gpu/drm/drm_mm.c
include/drm/drm_mm.h

Conflicts:

	drivers/gpu/drm/drm_mm.c
	drivers/gpu/drm/i915/i915_gem_gtt.c
	drivers/gpu/drm/i915/i915_gem_stolen.c
	include/drm/drm_mm.h
---
 drivers/gpu/drm/drm_mm.c        | 118 +++++++++++++++++--------------
 drivers/gpu/drm/i915/i915_gem.c |   4 +-
 include/drm/drm_mm.h            | 149 +++++++++++++++++++++++++++-------------
 3 files changed, 169 insertions(+), 102 deletions(-)
drivers/gpu/drm/drm_mm.c +66 -52
index fe304f9..5037b1a 100644
@@ -49,7 +49,7 @@
 
 #define MM_UNUSED_TARGET 4
 
-static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, int atomic)
+static struct drm_mm_node *drm_mm_kmalloc(struct drm_mm *mm, bool atomic)
 {
 	struct drm_mm_node *child;
 
@@ -105,7 +105,8 @@ EXPORT_SYMBOL(drm_mm_pre_get);
 static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 				 struct drm_mm_node *node,
 				 unsigned long size, unsigned alignment,
-				 unsigned long color)
+				 unsigned long color,
+				 enum drm_mm_allocator_flags flags)
 {
 	struct drm_mm *mm = hole_node->mm;
 	unsigned long hole_start = drm_mm_hole_node_start(hole_node);
@@ -118,12 +119,22 @@ static void drm_mm_insert_helper(struct drm_mm_node *hole_node,
 	if (mm->color_adjust)
 		mm->color_adjust(hole_node, color, &adj_start, &adj_end);
 
+	if (flags & DRM_MM_CREATE_TOP)
+		adj_start = adj_end - size;
+
 	if (alignment) {
 		unsigned tmp = adj_start % alignment;
-		if (tmp)
-			adj_start += alignment - tmp;
+		if (tmp) {
+			if (flags & DRM_MM_CREATE_TOP)
+				adj_start -= tmp;
+			else
+				adj_start += alignment - tmp;
+		}
 	}
 
+	BUG_ON(adj_start < hole_start);
+	BUG_ON(adj_end > hole_end);
+
 	if (adj_start == hole_start) {
 		hole_node->hole_follows = 0;
 		list_del(&hole_node->hole_stack);
@@ -191,15 +202,15 @@ struct drm_mm_node *drm_mm_get_block_generic(struct drm_mm_node *hole_node,
 					     unsigned long size,
 					     unsigned alignment,
 					     unsigned long color,
-					     int atomic)
+					     enum drm_mm_allocator_flags flags)
 {
 	struct drm_mm_node *node;
 
-	node = drm_mm_kmalloc(hole_node->mm, atomic);
+	node = drm_mm_kmalloc(hole_node->mm, flags & DRM_MM_CREATE_ATOMIC);
 	if (unlikely(node == NULL))
 		return NULL;
 
-	drm_mm_insert_helper(hole_node, node, size, alignment, color);
+	drm_mm_insert_helper(hole_node, node, size, alignment, color, flags);
 
 	return node;
 }
@@ -212,32 +223,28 @@ EXPORT_SYMBOL(drm_mm_get_block_generic);
  */
 int drm_mm_insert_node_generic(struct drm_mm *mm, struct drm_mm_node *node,
 			       unsigned long size, unsigned alignment,
-			       unsigned long color)
+			       unsigned long color,
+			       enum drm_mm_allocator_flags aflags,
+			       enum drm_mm_search_flags sflags)
 {
 	struct drm_mm_node *hole_node;
 
 	hole_node = drm_mm_search_free_generic(mm, size, alignment,
-					       color, 0);
+					       color, sflags);
 	if (!hole_node)
 		return -ENOSPC;
 
-	drm_mm_insert_helper(hole_node, node, size, alignment, color);
+	drm_mm_insert_helper(hole_node, node, size, alignment, color, aflags);
 	return 0;
 }
 EXPORT_SYMBOL(drm_mm_insert_node_generic);
 
-int drm_mm_insert_node(struct drm_mm *mm, struct drm_mm_node *node,
-		       unsigned long size, unsigned alignment)
-{
-	return drm_mm_insert_node_generic(mm, node, size, alignment, 0);
-}
-EXPORT_SYMBOL(drm_mm_insert_node);
-
 static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 				       struct drm_mm_node *node,
 				       unsigned long size, unsigned alignment,
 				       unsigned long color,
-				       unsigned long start, unsigned long end)
+				       unsigned long start, unsigned long end,
+				       enum drm_mm_search_flags flags)
 {
 	struct drm_mm *mm = hole_node->mm;
 	unsigned long hole_start = drm_mm_hole_node_start(hole_node);
@@ -252,13 +259,20 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 	if (adj_end > end)
 		adj_end = end;
 
+	if (flags & DRM_MM_CREATE_TOP)
+		adj_start = adj_end - size;
+
 	if (mm->color_adjust)
 		mm->color_adjust(hole_node, color, &adj_start, &adj_end);
 
 	if (alignment) {
 		unsigned tmp = adj_start % alignment;
-		if (tmp)
-			adj_start += alignment - tmp;
+		if (tmp) {
+			if (flags & DRM_MM_CREATE_TOP)
+				adj_start -= tmp;
+			else
+				adj_start += alignment - tmp;
+		}
 	}
 
 	if (adj_start == hole_start) {
@@ -275,6 +289,8 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 	INIT_LIST_HEAD(&node->hole_stack);
 	list_add(&node->node_list, &hole_node->node_list);
 
+	BUG_ON(node->start < start);
+	BUG_ON(node->start < adj_start);
 	BUG_ON(node->start + node->size > adj_end);
 	BUG_ON(node->start + node->size > end);
 
@@ -285,22 +301,23 @@ static void drm_mm_insert_helper_range(struct drm_mm_node *hole_node,
 	}
 }
 
-struct drm_mm_node *drm_mm_get_block_range_generic(struct drm_mm_node *hole_node,
-						unsigned long size,
-						unsigned alignment,
-						unsigned long color,
-						unsigned long start,
-						unsigned long end,
-						int atomic)
+struct drm_mm_node *
+drm_mm_get_block_range_generic(struct drm_mm_node *hole_node,
+			       unsigned long size,
+			       unsigned alignment,
+			       unsigned long color,
+			       unsigned long start,
+			       unsigned long end,
+			       enum drm_mm_allocator_flags flags)
 {
 	struct drm_mm_node *node;
 
-	node = drm_mm_kmalloc(hole_node->mm, atomic);
+	node = drm_mm_kmalloc(hole_node->mm, flags & DRM_MM_CREATE_ATOMIC);
 	if (unlikely(node == NULL))
 		return NULL;
 
 	drm_mm_insert_helper_range(hole_node, node, size, alignment, color,
-				   start, end);
+				   start, end, flags);
 
 	return node;
 }
@@ -313,31 +330,25 @@ EXPORT_SYMBOL(drm_mm_get_block_range_generic);
  */
 int drm_mm_insert_node_in_range_generic(struct drm_mm *mm, struct drm_mm_node *node,
 					unsigned long size, unsigned alignment, unsigned long color,
-					unsigned long start, unsigned long end)
+					unsigned long start, unsigned long end,
+					enum drm_mm_allocator_flags aflags,
+					enum drm_mm_search_flags sflags)
 {
 	struct drm_mm_node *hole_node;
 
 	hole_node = drm_mm_search_free_in_range_generic(mm,
 							size, alignment, color,
-							start, end, 0);
+							start, end, sflags);
 	if (!hole_node)
 		return -ENOSPC;
 
 	drm_mm_insert_helper_range(hole_node, node,
 				   size, alignment, color,
-				   start, end);
+				   start, end, aflags);
 	return 0;
 }
 EXPORT_SYMBOL(drm_mm_insert_node_in_range_generic);
 
-int drm_mm_insert_node_in_range(struct drm_mm *mm, struct drm_mm_node *node,
-				unsigned long size, unsigned alignment,
-				unsigned long start, unsigned long end)
-{
-	return drm_mm_insert_node_in_range_generic(mm, node, size, alignment, 0, start, end);
-}
-EXPORT_SYMBOL(drm_mm_insert_node_in_range);
-
 /**
  * Remove a memory node from the allocator.
  */
@@ -413,7 +424,7 @@ struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 					       unsigned long size,
 					       unsigned alignment,
 					       unsigned long color,
-					       bool best_match)
+					       enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *entry;
 	struct drm_mm_node *best;
@@ -426,7 +437,8 @@ struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 	best = NULL;
 	best_size = ~0UL;
 
-	drm_mm_for_each_hole(entry, mm, adj_start, adj_end) {
+	__drm_mm_for_each_hole(entry, mm, adj_start, adj_end,
+			       flags & DRM_MM_SEARCH_BELOW) {
 		if (mm->color_adjust) {
 			mm->color_adjust(entry, color, &adj_start, &adj_end);
 			if (adj_end <= adj_start)
@@ -436,7 +448,7 @@ struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 		if (!check_free_hole(adj_start, adj_end, size, alignment))
 			continue;
 
-		if (!best_match)
+		if ((flags & DRM_MM_SEARCH_BEST) == 0)
 			return entry;
 
 		if (entry->size < best_size) {
@@ -449,13 +461,14 @@ struct drm_mm_node *drm_mm_search_free_generic(const struct drm_mm *mm,
 }
 EXPORT_SYMBOL(drm_mm_search_free_generic);
 
-struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
-							unsigned long size,
-							unsigned alignment,
-							unsigned long color,
-							unsigned long start,
-							unsigned long end,
-							bool best_match)
+struct drm_mm_node *
+drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
+				    unsigned long size,
+				    unsigned alignment,
+				    unsigned long color,
+				    unsigned long start,
+				    unsigned long end,
+				    enum drm_mm_search_flags flags)
 {
 	struct drm_mm_node *entry;
 	struct drm_mm_node *best;
@@ -468,7 +481,8 @@ struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
 	best = NULL;
 	best_size = ~0UL;
 
-	drm_mm_for_each_hole(entry, mm, adj_start, adj_end) {
+	__drm_mm_for_each_hole(entry, mm, adj_start, adj_end,
+			       flags & DRM_MM_SEARCH_BELOW) {
 		if (adj_start < start)
 			adj_start = start;
 		if (adj_end > end)
@@ -483,7 +497,7 @@ struct drm_mm_node *drm_mm_search_free_in_range_generic(const struct drm_mm *mm,
 		if (!check_free_hole(adj_start, adj_end, size, alignment))
 			continue;
 
-		if (!best_match)
+		if ((flags & DRM_MM_SEARCH_BEST) == 0)
 			return entry;
 
 		if (entry->size < best_size) {
drivers/gpu/drm/i915/i915_gem.c +3 -1
index af61be8..9275f90 100644
@@ -3115,7 +3115,9 @@ search_free:
 	ret = drm_mm_insert_node_in_range_generic(&dev_priv->mm.gtt_space,
 						  &obj->gtt_space,
 						  size, alignment,
-						  obj->cache_level, 0, gtt_max);
+						  obj->cache_level, 0, gtt_max,
+						  DRM_MM_CREATE_DEFAULT,
+						  DRM_MM_SEARCH_DEFAULT);
 	if (ret) {
 		ret = i915_gem_evict_something(dev, size, alignment,
 					       obj->cache_level,
include/drm/drm_mm.h +100 -49

204 lines not on this page · raw message

Signature · 1 line
1.8.3.2