drm/i915: add support for 5/6 data buffer partitioning on Haswell

Now we compute the results for both 1/2 and 5/6 partitioning and then
use hsw_find_best_result to choose which one to use.

With this patch, Haswell watermarks support should be in good shape.
The only improvement we're missing is the case where the primary plane
is disabled: we always assume it's enabled, so we take it into
consideration when calculating the watermarks.

v2: - Check the latency when finding the best result
Signed-off-by: NPaulo Zanoni <paulo.r.zanoni@intel.com>
Reviewed-by: NVille Syrjälä <ville.syrjala@linux.intel.com>
Signed-off-by: NDaniel Vetter <daniel.vetter@ffwll.ch>

drivers/gpu/drm/i915/intel_pm.c

@@ -2335,7 +2335,8 @@ hsw_compute_linetime_wm(struct drm_device *dev, struct drm_crtc *crtc)
 static void hsw_compute_wm_parameters(struct drm_device *dev,
 				      struct hsw_pipe_wm_parameters *params,
 				      uint32_t *wm,
-				      struct hsw_wm_maximums *lp_max_1_2)
+				      struct hsw_wm_maximums *lp_max_1_2,
+				      struct hsw_wm_maximums *lp_max_5_6)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_crtc *crtc;
@@ -2391,15 +2392,17 @@ static void hsw_compute_wm_parameters(struct drm_device *dev,
 	}
 
 	if (pipes_active > 1) {
-		lp_max_1_2->pri = sprites_enabled ? 128 : 256;
-		lp_max_1_2->spr = 128;
-		lp_max_1_2->cur = 64;
+		lp_max_1_2->pri = lp_max_5_6->pri = sprites_enabled ? 128 : 256;
+		lp_max_1_2->spr = lp_max_5_6->spr = 128;
+		lp_max_1_2->cur = lp_max_5_6->cur = 64;
 	} else {
 		lp_max_1_2->pri = sprites_enabled ? 384 : 768;
+		lp_max_5_6->pri = sprites_enabled ? 128 : 768;
 		lp_max_1_2->spr = 384;
-		lp_max_1_2->cur = 255;
+		lp_max_5_6->spr = 640;
+		lp_max_1_2->cur = lp_max_5_6->cur = 255;
 	}
-	lp_max_1_2->fbc = 15;
+	lp_max_1_2->fbc = lp_max_5_6->fbc = 15;
 }
 
 static void hsw_compute_wm_results(struct drm_device *dev,
@@ -2457,6 +2460,32 @@ static void hsw_compute_wm_results(struct drm_device *dev,
 	}
 }
 
+/* Find the result with the highest level enabled. Check for enable_fbc_wm in
+ * case both are at the same level. Prefer r1 in case they're the same. */
+struct hsw_wm_values *hsw_find_best_result(struct hsw_wm_values *r1,
+					   struct hsw_wm_values *r2)
+{
+	int i, val_r1 = 0, val_r2 = 0;
+
+	for (i = 0; i < 3; i++) {
+		if (r1->wm_lp[i] & WM3_LP_EN)
+			val_r1 = r1->wm_lp[i] & WM1_LP_LATENCY_MASK;
+		if (r2->wm_lp[i] & WM3_LP_EN)
+			val_r2 = r2->wm_lp[i] & WM1_LP_LATENCY_MASK;
+	}
+
+	if (val_r1 == val_r2) {
+		if (r2->enable_fbc_wm && !r1->enable_fbc_wm)
+			return r2;
+		else
+			return r1;
+	} else if (val_r1 > val_r2) {
+		return r1;
+	} else {
+		return r2;
+	}
+}
+
 /*
  * The spec says we shouldn't write when we don't need, because every write
  * causes WMs to be re-evaluated, expending some power.
@@ -2557,14 +2586,27 @@ static void hsw_write_wm_values(struct drm_i915_private *dev_priv,
 static void haswell_update_wm(struct drm_device *dev)
 {
 	struct drm_i915_private *dev_priv = dev->dev_private;
-	struct hsw_wm_maximums lp_max_1_2;
+	struct hsw_wm_maximums lp_max_1_2, lp_max_5_6;
 	struct hsw_pipe_wm_parameters params[3];
-	struct hsw_wm_values results;
+	struct hsw_wm_values results_1_2, results_5_6, *best_results;
 	uint32_t wm[5];
+	enum hsw_data_buf_partitioning partitioning;
+
+	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2, &lp_max_5_6);
+
+	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results_1_2);
+	if (lp_max_1_2.pri != lp_max_5_6.pri) {
+		hsw_compute_wm_results(dev, params, wm, &lp_max_5_6,
+				       &results_5_6);
+		best_results = hsw_find_best_result(&results_1_2, &results_5_6);
+	} else {
+		best_results = &results_1_2;
+	}
+
+	partitioning = (best_results == &results_1_2) ?
+		       HSW_DATA_BUF_PART_1_2 : HSW_DATA_BUF_PART_5_6;
 
-	hsw_compute_wm_parameters(dev, params, wm, &lp_max_1_2);
-	hsw_compute_wm_results(dev, params, wm, &lp_max_1_2, &results);
-	hsw_write_wm_values(dev_priv, &results, HSW_DATA_BUF_PART_1_2);
+	hsw_write_wm_values(dev_priv, best_results, partitioning);
 }
 
 static void haswell_update_sprite_wm(struct drm_device *dev, int pipe,