[Intel-gfx] [PATCH] drm/i915/gem: Don't try to map and fence large scanout buffers

[Vivek Kasireddy]

On platforms capable of allowing 8K (7680 x 4320) modes, pinning 2 or
more framebuffers/scanout buffers results in only one that is mappable/
fenceable. Therefore, pageflipping between these 2 FBs where only one
is mappable/fenceable creates latencies large enough to miss alternate
vblanks thereby producing less optimal framerate.

This mainly happens because when i915_gem_object_pin_to_display_plane()
is called to pin one of the FB objs, the associated vma is identified
as misplaced and therefore i915_vma_unbind() is called which unbinds and
evicts it. This misplaced vma gets subseqently pinned only when
i915_gem_object_ggtt_pin_ww() is called without the mappable flag. This
results in a latency of ~10ms and happens every other vblank/repaint cycle.

Testcase:
Running Weston and weston-simple-egl on an Alderlake_S (ADLS) platform
with a 8K at 60 mode results in only ~40 FPS. Since upstream Weston submits
a frame ~7ms before the next vblank, the latencies seen between atomic
commit and flip event are 7, 24 (7 + 16.66), 7, 24..... suggesting that
it misses the vblank every other frame.

Here is the ftrace snippet that shows the source of the ~10ms latency:
              i915_gem_object_pin_to_display_plane() {
0.102 us   |    i915_gem_object_set_cache_level();
                i915_gem_object_ggtt_pin_ww() {
0.390 us   |      i915_vma_instance();
0.178 us   |      i915_vma_misplaced();
                  i915_vma_unbind() {
                  __i915_active_wait() {
0.082 us   |        i915_active_acquire_if_busy();
0.475 us   |      }
                  intel_runtime_pm_get() {
0.087 us   |        intel_runtime_pm_acquire();
0.259 us   |      }
                  __i915_active_wait() {
0.085 us   |        i915_active_acquire_if_busy();
0.240 us   |      }
                  __i915_vma_evict() {
                    ggtt_unbind_vma() {
                      gen8_ggtt_clear_range() {
10507.255 us |        }
10507.689 us |      }
10508.516 us |   }

v2: Instead of using bigjoiner checks, determine whether a scanout
    buffer is too big by checking to see if it is possible to map
    two of them into the ggtt.

Cc: Ville Syrjälä <ville.syrjala at linux.intel.com>
Cc: Maarten Lankhorst <maarten.lankhorst at linux.intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin at linux.intel.com>
Cc: Manasi Navare <manasi.d.navare at intel.com>
Signed-off-by: Vivek Kasireddy <vivek.kasireddy at intel.com>
---
 drivers/gpu/drm/i915/i915_gem.c | 48 ++++++++++++++++++++++++++-------
 drivers/gpu/drm/i915/i915_vma.c |  2 +-
 2 files changed, 40 insertions(+), 10 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_gem.c b/drivers/gpu/drm/i915/i915_gem.c
index 981e383d1a5d..0050c7e4bb51 100644
--- a/drivers/gpu/drm/i915/i915_gem.c
+++ b/drivers/gpu/drm/i915/i915_gem.c
@@ -866,6 +866,44 @@ static void discard_ggtt_vma(struct i915_vma *vma)
 	spin_unlock(&obj->vma.lock);
 }
 
+static bool i915_gem_obj_too_big(struct drm_i915_gem_object *obj)
+{
+	struct drm_i915_private *i915 = to_i915(obj->base.dev);
+	struct i915_ggtt *ggtt = &i915->ggtt;
+	struct drm_mm_node *hole;
+	u64 hole_start, hole_end;
+	u64 fence_size;
+
+	/*
+	 * If the required space is larger than the available
+	 * aperture, we will not able to find a slot for the
+	 * object and unbinding the object now will be in
+	 * vain. Worse, doing so may cause us to ping-pong
+	 * the object in and out of the Global GTT and
+	 * waste a lot of cycles under the mutex.
+	 */
+	if (obj->base.size > ggtt->mappable_end)
+		return true;
+
+	fence_size = i915_gem_fence_size(i915, obj->base.size,
+					 i915_gem_object_get_tiling(obj),
+					 i915_gem_object_get_stride(obj));
+
+	/*
+	 * Assuming this object is a large scanout buffer, we try to find
+	 * out if there is room to map at-least two of them. There could
+	 * be space available to map one but to be consistent, we try to
+	 * avoid mapping/fencing any of them.
+	 */
+	drm_mm_for_each_hole(hole, &ggtt->vm.mm, hole_start, hole_end) {
+		if (hole_end - hole_start > 2 * fence_size &&
+		    hole_start + 2 * fence_size < ggtt->mappable_end)
+			return false;
+	}
+
+	return true;
+}
+
 struct i915_vma *
 i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
 			    struct i915_gem_ww_ctx *ww,
@@ -879,15 +917,7 @@ i915_gem_object_ggtt_pin_ww(struct drm_i915_gem_object *obj,
 
 	if (flags & PIN_MAPPABLE &&
 	    (!view || view->type == I915_GGTT_VIEW_NORMAL)) {
-		/*
-		 * If the required space is larger than the available
-		 * aperture, we will not able to find a slot for the
-		 * object and unbinding the object now will be in
-		 * vain. Worse, doing so may cause us to ping-pong
-		 * the object in and out of the Global GTT and
-		 * waste a lot of cycles under the mutex.
-		 */
-		if (obj->base.size > ggtt->mappable_end)
+		if (i915_gem_obj_too_big(obj))
 			return ERR_PTR(-E2BIG);
 
 		/*
diff --git a/drivers/gpu/drm/i915/i915_vma.c b/drivers/gpu/drm/i915/i915_vma.c
index 90546fa58fc1..551644dbfa8a 100644
--- a/drivers/gpu/drm/i915/i915_vma.c
+++ b/drivers/gpu/drm/i915/i915_vma.c
@@ -977,7 +977,7 @@ int i915_vma_pin_ww(struct i915_vma *vma, struct i915_gem_ww_ctx *ww,
 		if (err)
 			goto err_active;
 
-		if (i915_is_ggtt(vma->vm))
+		if (i915_is_ggtt(vma->vm) && flags & PIN_MAPPABLE)
 			__i915_vma_set_map_and_fenceable(vma);
 	}
 
-- 
2.31.1