[PATCH v4 20/31] accel: ethosu: Validate all feature map tiles

["Rob Herring (Arm)" <robh@kernel.org>]

The command-stream validator checked only the final feature-map
coordinate. For tiled tensors, this can leave an earlier tile base
address unchecked even though the operation accesses it.

Check the final coordinate of every tile touched by an operation. Also
treat U65 feature maps as 2x2 tiled: its precision rounding bits are not
the U85 storage encoding.

Fixes: 5a5e9c0228e6 ("accel: Add Arm Ethos-U NPU driver")
Cc: stable@vger.kernel.org
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
---
v4:
 - NHCWB16 feature maps may be vertically tiled. Account for tile 0's
   maximum Y coordinate when calculating the feature map bounds.

v3:
 - Fix for storage mode 0 intermediate tile calculations

v2:
 - no changes
---
 drivers/accel/ethosu/ethosu_gem.c | 147 ++++++++++++++++++++++++++++++--------
 1 file changed, 119 insertions(+), 28 deletions(-)

diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c
index 74ef86848a2d..3333477bf2e5 100644
--- a/drivers/accel/ethosu/ethosu_gem.c
+++ b/drivers/accel/ethosu/ethosu_gem.c
@@ -444,6 +444,96 @@ static u64 feat_matrix_length(struct ethosu_device *edev,
 	return addr;
 }
 
+static int feat_matrix_check_location(struct ethosu_device *edev,
+				      struct ethosu_validated_cmdstream_info *info,
+				      struct cmd_state *st, struct feat_matrix *fm,
+				      enum feat_matrix_type type, u32 x, u32 y,
+				      u32 c, bool ofm, u64 *max_len)
+{
+	u64 len;
+
+	len = feat_matrix_length(edev, info, st, fm, type, x, y, c, ofm);
+	if (len == U64_MAX)
+		return -EINVAL;
+
+	*max_len = max(*max_len, len);
+	return 0;
+}
+
+static int feat_matrix_size(struct ethosu_device *edev,
+			    struct ethosu_validated_cmdstream_info *info,
+			    struct cmd_state *st, struct feat_matrix *fm,
+			    enum feat_matrix_type type,
+			    u32 x, u32 y, u32 c, bool ofm, u64 *max_len)
+{
+	u32 storage = ethosu_is_u65(edev) ? 0 : fm->precision >> 14;
+	int ret;
+
+	*max_len = 0;
+
+	if (storage == 0) {
+		ret = feat_matrix_check_location(edev, info, st, fm, type, 0, 0,
+						 c, ofm, max_len);
+		if (ret)
+			return ret;
+
+		ret = feat_matrix_check_location(edev, info, st, fm, type,
+						 min(x, (u32)fm->width0),
+						 min(y, (u32)fm->height[0]), c, ofm,
+						 max_len);
+		if (ret)
+			return ret;
+
+		if (fm->width0 < x) {
+			ret = feat_matrix_check_location(edev, info, st, fm, type, x,
+							 min(y, (u32)fm->height[1]), c,
+							 ofm, max_len);
+			if (ret)
+				return ret;
+		}
+
+		if (fm->height[0] < y) {
+			ret = feat_matrix_check_location(edev, info, st, fm, type,
+							 min(x, (u32)fm->width0), y, c,
+							 ofm, max_len);
+			if (ret)
+				return ret;
+		}
+
+		if (fm->width0 < x && fm->height[1] < y)
+			return feat_matrix_check_location(edev, info, st, fm, type,
+							  x, y, c, ofm, max_len);
+
+		return 0;
+	}
+
+	if (storage == 1) {
+		ret = feat_matrix_check_location(edev, info, st, fm, type, x,
+						 min3(y, (u32)fm->height[0],
+						      (u32)fm->height[1]), c, ofm,
+						 max_len);
+		if (ret)
+			return ret;
+		if (fm->height[0] < fm->height[1] && fm->height[1] <= y) {
+			ret = feat_matrix_check_location(edev, info, st, fm, type, x,
+							 fm->height[1], c, ofm,
+							 max_len);
+			if (ret)
+				return ret;
+		}
+		if (fm->height[1] < y) {
+			ret = feat_matrix_check_location(edev, info, st, fm, type, x,
+							 fm->height[1] + 1, c, ofm,
+							 max_len);
+			if (ret)
+				return ret;
+		}
+	}
+
+	return feat_matrix_check_location(edev, info, st, fm, type, x, y, c, ofm,
+					  max_len);
+}
+
 static int buffer_size(struct ethosu_validated_cmdstream_info *info,
 		       struct cmd_state *st, struct buffer *buf, s8 region,
 		       u16 region_cmd, u16 base_cmd, u16 length_cmd, bool optional)
@@ -474,6 +564,7 @@ static int calc_sizes(struct drm_device *ddev,
 {
 	struct ethosu_device *edev = to_ethosu_device(ddev);
 	u64 len;
+	int ret;
 
 	if (ifm) {
 		if (!cmd_state_reg_is_set(st, NPU_SET_KERNEL_WIDTH_M1) ||
@@ -496,23 +587,22 @@ static int calc_sizes(struct drm_device *ddev,
 		if (ifm_height < 0 || ifm_width < 0)
 			return -EINVAL;
 
-		len = feat_matrix_length(edev, info, st, &st->ifm,
-					 FEAT_MATRIX_IFM, ifm_width, ifm_height,
-					 st->ifm.depth, false);
+		ret = feat_matrix_size(edev, info, st, &st->ifm, FEAT_MATRIX_IFM,
+				       ifm_width, ifm_height, st->ifm.depth, false,
+				       &len);
 		dev_dbg(ddev->dev, "op %d: IFM:%d:0x%llx-0x%llx\n",
 			op, st->ifm.region, st->ifm.base[0], len);
-		if (len == U64_MAX)
-			return -EINVAL;
+		if (ret)
+			return ret;
 	}
 
 	if (ifm2) {
-		len = feat_matrix_length(edev, info, st, &st->ifm2,
-					 FEAT_MATRIX_IFM2, st->ifm.depth, 0,
-					 st->ofm.depth, false);
+		ret = feat_matrix_size(edev, info, st, &st->ifm2, FEAT_MATRIX_IFM2,
+				       st->ifm.depth, 0, st->ofm.depth, false, &len);
 		dev_dbg(ddev->dev, "op %d: IFM2:%d:0x%llx-0x%llx\n",
 			op, st->ifm2.region, st->ifm2.base[0], len);
-		if (len == U64_MAX)
-			return -EINVAL;
+		if (ret)
+			return ret;
 	}
 
 	if (weight) {
@@ -554,13 +644,13 @@ static int calc_sizes(struct drm_device *ddev,
 			return -EINVAL;
 	}
 
-	len = feat_matrix_length(edev, info, st, &st->ofm, FEAT_MATRIX_OFM,
-				 st->ofm.width, st->ofm.height[2], st->ofm.depth,
-				 true);
+	ret = feat_matrix_size(edev, info, st, &st->ofm, FEAT_MATRIX_OFM,
+			       st->ofm.width, st->ofm.height[2], st->ofm.depth,
+			       true, &len);
 	dev_dbg(ddev->dev, "op %d: OFM:%d:0x%llx-0x%llx\n",
 		op, st->ofm.region, st->ofm.base[0], len);
-	if (len == U64_MAX)
-		return -EINVAL;
+	if (ret)
+		return ret;
 	if (!feat_matrix_chained(edev, &st->ofm))
 		info->output_region[st->ofm.region] = true;
 
@@ -575,18 +665,19 @@ static int calc_sizes_elemwise(struct drm_device *ddev,
 	struct ethosu_device *edev = to_ethosu_device(ddev);
 	u32 height, width, depth;
 	u64 len;
+	int ret;
 
 	if (ifm) {
 		height = st->ifm.broadcast & 0x1 ? 0 : st->ofm.height[2];
 		width = st->ifm.broadcast & 0x2 ? 0 : st->ofm.width;
 		depth = st->ifm.broadcast & 0x4 ? 0 : st->ofm.depth;
 
-		len = feat_matrix_length(edev, info, st, &st->ifm,
-					 FEAT_MATRIX_IFM, width, height, depth, false);
+		ret = feat_matrix_size(edev, info, st, &st->ifm, FEAT_MATRIX_IFM,
+				       width, height, depth, false, &len);
 		dev_dbg(ddev->dev, "op %d: IFM:%d:0x%llx-0x%llx\n",
 			op, st->ifm.region, st->ifm.base[0], len);
-		if (len == U64_MAX)
-			return -EINVAL;
+		if (ret)
+			return ret;
 	}
 
 	if (ifm2) {
@@ -594,21 +685,21 @@ static int calc_sizes_elemwise(struct drm_device *ddev,
 		width = st->ifm2.broadcast & 0x2 ? 0 : st->ofm.width;
 		depth = st->ifm2.broadcast & 0x4 ? 0 : st->ofm.depth;
 
-		len = feat_matrix_length(edev, info, st, &st->ifm2,
-					 FEAT_MATRIX_IFM2, width, height, depth, false);
+		ret = feat_matrix_size(edev, info, st, &st->ifm2, FEAT_MATRIX_IFM2,
+				       width, height, depth, false, &len);
 		dev_dbg(ddev->dev, "op %d: IFM2:%d:0x%llx-0x%llx\n",
 			op, st->ifm2.region, st->ifm2.base[0], len);
-		if (len == U64_MAX)
-			return -EINVAL;
+		if (ret)
+			return ret;
 	}
 
-	len = feat_matrix_length(edev, info, st, &st->ofm, FEAT_MATRIX_OFM,
-				 st->ofm.width, st->ofm.height[2], st->ofm.depth,
-				 true);
+	ret = feat_matrix_size(edev, info, st, &st->ofm, FEAT_MATRIX_OFM,
+			       st->ofm.width, st->ofm.height[2], st->ofm.depth,
+			       true, &len);
 	dev_dbg(ddev->dev, "op %d: OFM:%d:0x%llx-0x%llx\n",
 		op, st->ofm.region, st->ofm.base[0], len);
-	if (len == U64_MAX)
-		return -EINVAL;
+	if (ret)
+		return ret;
 	if (!feat_matrix_chained(edev, &st->ofm))
 		info->output_region[st->ofm.region] = true;
 

-- 
2.53.0