diff --git a/drivers/gpu/drm/i915/intel_uncore.c b/drivers/gpu/drm/i915/intel_uncore.c
index a6d8a3ee7750adecb552415c8ffab06d599f46ff..260389acfb7752d01ce0ebd59597f06a671b2ea1 100644
--- a/drivers/gpu/drm/i915/intel_uncore.c
+++ b/drivers/gpu/drm/i915/intel_uncore.c
@@ -1274,10 +1274,12 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	struct drm_i915_private *dev_priv = dev->dev_private;
 	struct drm_i915_reg_read *reg = data;
 	struct register_whitelist const *entry = whitelist;
+	unsigned size;
+	u64 offset;
 	int i, ret = 0;
 
 	for (i = 0; i < ARRAY_SIZE(whitelist); i++, entry++) {
-		if (entry->offset == reg->offset &&
+		if (entry->offset == (reg->offset & -entry->size) &&
 		    (1 << INTEL_INFO(dev)->gen & entry->gen_bitmask))
 			break;
 	}
@@ -1285,23 +1287,33 @@ int i915_reg_read_ioctl(struct drm_device *dev,
 	if (i == ARRAY_SIZE(whitelist))
 		return -EINVAL;
 
+	/* We use the low bits to encode extra flags as the register should
+	 * be naturally aligned (and those that are not so aligned merely
+	 * limit the available flags for that register).
+	 */
+	offset = entry->offset;
+	size = entry->size;
+	size |= reg->offset ^ offset;
+
 	intel_runtime_pm_get(dev_priv);
 
-	switch (entry->size) {
+	switch (size) {
+	case 8 | 1:
+		reg->val = I915_READ64_2x32(offset, offset+4);
+		break;
 	case 8:
-		reg->val = I915_READ64(reg->offset);
+		reg->val = I915_READ64(offset);
 		break;
 	case 4:
-		reg->val = I915_READ(reg->offset);
+		reg->val = I915_READ(offset);
 		break;
 	case 2:
-		reg->val = I915_READ16(reg->offset);
+		reg->val = I915_READ16(offset);
 		break;
 	case 1:
-		reg->val = I915_READ8(reg->offset);
+		reg->val = I915_READ8(offset);
 		break;
 	default:
-		MISSING_CASE(entry->size);
 		ret = -EINVAL;
 		goto out;
 	}
diff --git a/include/uapi/drm/i915_drm.h b/include/uapi/drm/i915_drm.h
index 6e1a2ed116cb1410958f61631a7dc30839652738..db809b722985d3a1a03480cc1e3d36a656af2d2d 100644
--- a/include/uapi/drm/i915_drm.h
+++ b/include/uapi/drm/i915_drm.h
@@ -1070,6 +1070,14 @@ struct drm_i915_reg_read {
 	__u64 offset;
 	__u64 val; /* Return value */
 };
+/* Known registers:
+ *
+ * Render engine timestamp - 0x2358 + 64bit - gen7+
+ * - Note this register returns an invalid value if using the default
+ *   single instruction 8byte read, in order to workaround that use
+ *   offset (0x2538 | 1) instead.
+ *
+ */
 
 struct drm_i915_reset_stats {
 	__u32 ctx_id;