drm/i915/gen9: fix the WaWmMemoryReadLatency implementation

Bspec says:
  "The mailbox response data may not account for memory read latency.
   If the mailbox response data for level 0 is 0us, add 2 microseconds
   to the result for each valid level."

This means we should only do the +2 in case wm[0] == 0, not always.

So split the sanitizing implementation from the WA implementation and
fix the WA implementation.

v2: Add Fixes tag (Maarten).

Fixes: 367294be ("drm/i915/gen9: Add 2us read latency to WM level")
Cc: stable@vger.kernel.org
Cc: Vandana Kannan <vandana.kannan@intel.com>
Reviewed-by: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Signed-off-by: Paulo Zanoni <paulo.r.zanoni@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/1474578035-424-5-git-send-email-paulo.r.zanoni@intel.com
(cherry picked from commit 0727e40a)
Signed-off-by: Jani Nikula <jani.nikula@intel.com>

drivers/gpu/drm/i915/intel_pm.c

@@ -2126,33 +2126,35 @@ static void intel_read_wm_latency(struct drm_device *dev, uint16_t wm[8])
 		wm[7] = (val >> GEN9_MEM_LATENCY_LEVEL_3_7_SHIFT) &
 				GEN9_MEM_LATENCY_LEVEL_MASK;
 
+		/*
+		 * If a level n (n > 1) has a 0us latency, all levels m (m >= n)
+		 * need to be disabled. We make sure to sanitize the values out
+		 * of the punit to satisfy this requirement.
+		 */
+		for (level = 1; level <= max_level; level++) {
+			if (wm[level] == 0) {
+				for (i = level + 1; i <= max_level; i++)
+					wm[i] = 0;
+				break;
+			}
+		}
+
 		/*
 		 * WaWmMemoryReadLatency:skl
 		 *
 		 * punit doesn't take into account the read latency so we need
-		 * to add 2us to the various latency levels we retrieve from
-		 * the punit.
-		 *   - W0 is a bit special in that it's the only level that
-		 *   can't be disabled if we want to have display working, so
-		 *   we always add 2us there.
-		 *   - For levels >=1, punit returns 0us latency when they are
-		 *   disabled, so we respect that and don't add 2us then
-		 *
-		 * Additionally, if a level n (n > 1) has a 0us latency, all
-		 * levels m (m >= n) need to be disabled. We make sure to
-		 * sanitize the values out of the punit to satisfy this
-		 * requirement.
+		 * to add 2us to the various latency levels we retrieve from the
+		 * punit when level 0 response data us 0us.
 		 */
-		wm[0] += 2;
-		for (level = 1; level <= max_level; level++)
-			if (wm[level] != 0)
+		if (wm[0] == 0) {
+			wm[0] += 2;
+			for (level = 1; level <= max_level; level++) {
+				if (wm[level] == 0)
+					break;
 				wm[level] += 2;
-			else {
-				for (i = level + 1; i <= max_level; i++)
-					wm[i] = 0;
-
-				break;
 			}
+		}
+
 	} else if (IS_HASWELL(dev) || IS_BROADWELL(dev)) {
 		uint64_t sskpd = I915_READ64(MCH_SSKPD);