drm/i915: WA for platforms with double buffered address update enable bit

In Gen 9 and Gen 10 platforms, async address update enable bit is
double buffered. Due to this, during the transition from async flip
to sync flip we have to wait until this bit is updated before continuing
with the normal commit for sync flip.

v9: -Rename skl_toggle_async_sync() to skl_disable_async_flip_wa(). (Ville)
    -Place the declarations appropriately as per need. (Ville)
    -Take the lock before the reg read. (Ville)
    -Fix comment and formatting. (Ville)
    -Use IS_GEN_RANGE() for gen check. (Ville)
    -Move skl_disable_async_flip_wa() to intel_pre_plane_update(). (Ville)

v10: -Rebased.
Signed-off-by: Karthik B S <karthik.b.s@intel.com>
Signed-off-by: Vandita Kulkarni <vandita.kulkarni@intel.com>
Reviewed-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: Ville Syrjälä <ville.syrjala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200921110210.21182-7-karthik.b.s@intel.com

drivers/gpu/drm/i915/display/intel_display.c

@@ -6562,6 +6562,43 @@ static void intel_post_plane_update(struct intel_atomic_state *state,
 		icl_wa_scalerclkgating(dev_priv, pipe, false);
 }
 
+static void skl_disable_async_flip_wa(struct intel_atomic_state *state,
+				      struct intel_crtc *crtc,
+				      const struct intel_crtc_state *new_crtc_state)
+{
+	struct drm_i915_private *dev_priv = to_i915(state->base.dev);
+	struct intel_plane *plane;
+	struct intel_plane_state *new_plane_state;
+	int i;
+
+	for_each_new_intel_plane_in_state(state, plane, new_plane_state, i) {
+		u32 update_mask = new_crtc_state->update_planes;
+		u32 plane_ctl, surf_addr;
+		enum plane_id plane_id;
+		unsigned long irqflags;
+		enum pipe pipe;
+
+		if (crtc->pipe != plane->pipe ||
+		    !(update_mask & BIT(plane->id)))
+			continue;
+
+		plane_id = plane->id;
+		pipe = plane->pipe;
+
+		spin_lock_irqsave(&dev_priv->uncore.lock, irqflags);
+		plane_ctl = intel_de_read_fw(dev_priv, PLANE_CTL(pipe, plane_id));
+		surf_addr = intel_de_read_fw(dev_priv, PLANE_SURF(pipe, plane_id));
+
+		plane_ctl &= ~PLANE_CTL_ASYNC_FLIP;
+
+		intel_de_write_fw(dev_priv, PLANE_CTL(pipe, plane_id), plane_ctl);
+		intel_de_write_fw(dev_priv, PLANE_SURF(pipe, plane_id), surf_addr);
+		spin_unlock_irqrestore(&dev_priv->uncore.lock, irqflags);
+	}
+
+	intel_wait_for_vblank(dev_priv, crtc->pipe);
+}
+
 static void intel_pre_plane_update(struct intel_atomic_state *state,
 				   struct intel_crtc *crtc)
 {
@@ -6647,6 +6684,15 @@ static void intel_pre_plane_update(struct intel_atomic_state *state,
 	 */
 	if (IS_GEN(dev_priv, 2) && planes_disabling(old_crtc_state, new_crtc_state))
 		intel_set_cpu_fifo_underrun_reporting(dev_priv, pipe, false);
+
+	/*
+	 * WA for platforms where async address update enable bit
+	 * is double buffered and only latched at start of vblank.
+	 */
+	if (old_crtc_state->uapi.async_flip &&
+	    !new_crtc_state->uapi.async_flip &&
+	    IS_GEN_RANGE(dev_priv, 9, 10))
+		skl_disable_async_flip_wa(state, crtc, new_crtc_state);
 }
 
 static void intel_crtc_disable_planes(struct intel_atomic_state *state,