[PATCH v4 31/31] accel: ethosu: Support U85 IFM upscaling

[Rob Herring (Arm)]

Track the U85 IFM upscaling mode while validating command streams and
adjust feature-map bounds for its 2x resampling modes.

Resize operations require no IFM upscaling, so reject a non-default
mode there.

Signed-off-by: Rob Herring (Arm) <robh@xxxxxxxxxx>
---
v4:
 - New patch
---
 drivers/accel/ethosu/ethosu_device.h |  7 +++++++
 drivers/accel/ethosu/ethosu_gem.c    | 30 ++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/drivers/accel/ethosu/ethosu_device.h b/drivers/accel/ethosu/ethosu_device.h
index f41a8e0e1e1b..1fec33d9917c 100644
--- a/drivers/accel/ethosu/ethosu_device.h
+++ b/drivers/accel/ethosu/ethosu_device.h
@@ -97,6 +97,12 @@ struct gen_pool;
 
 #define NPU_CMD_CTRL_CMD1		BIT(14)
 
+enum ethosu_ifm_upscale_mode {
+	NPU_IFM_UPSCALE_NONE,
+	NPU_IFM_UPSCALE_NEAREST,
+	NPU_IFM_UPSCALE_TRANSPOSE,
+};
+
 enum ethosu_cmds {
 	NPU_OP_STOP = 0x0,
 	NPU_OP_CONV = 0x2,
@@ -113,6 +119,7 @@ enum ethosu_cmds {
 	NPU_SET_IFM_PAD_BOTTOM = 0x103,
 	NPU_SET_IFM_DEPTH_M1 = 0x104,
 	NPU_SET_IFM_PRECISION = 0x105,
+	NPU_SET_IFM_UPSCALE = 0x107, // U85 only
 	NPU_SET_IFM_BROADCAST = 0x108,
 	NPU_SET_IFM_WIDTH0_M1 = 0x10a,
 	NPU_SET_IFM_HEIGHT0_M1 = 0x10b,
diff --git a/drivers/accel/ethosu/ethosu_gem.c b/drivers/accel/ethosu/ethosu_gem.c
index 21458aacfcad..d82c9540e82a 100644
--- a/drivers/accel/ethosu/ethosu_gem.c
+++ b/drivers/accel/ethosu/ethosu_gem.c
@@ -165,6 +165,7 @@ struct cmd_state {
 	DECLARE_BITMAP(cmd0, NPU_CMD0_REGS);
 	DECLARE_BITMAP(cmd1, NPU_CMD1_REGS);
 	bool acc_input_ifm2;
+	u8 ifm_upscale;
 	u8 parallel_mode;
 	struct dma_state dma;
 	struct buffer scale[2];
@@ -718,6 +719,11 @@ static int calc_sizes_resize(struct drm_device *ddev,
 	u64 len;
 	int ret;
 
+	if (st->ifm_upscale != NPU_IFM_UPSCALE_NONE ||
+	    feat_matrix_chained(edev, &st->ofm) ||
+	    FIELD_GET(NPU_OFM_TRANSPOSE_MASK, st->ofm.precision))
+		return -EINVAL;
+
 	if (!cmd_state_reg_is_set(st, NPU_SET_KERNEL_WIDTH_M1) ||
 	    !cmd_state_reg_is_set(st, NPU_SET_KERNEL_HEIGHT_M1) ||
 	    !cmd_state_reg_is_set(st, NPU_SET_OFM_BLK_WIDTH_M1) ||
@@ -790,6 +796,20 @@ static int weight_streams(struct ethosu_device *edev, struct cmd_state *st,
 	return 0;
 }
 
+static u32 ifm_upscale_coord(u32 coord, u8 mode)
+{
+	switch (mode) {
+	case NPU_IFM_UPSCALE_NONE:
+		return coord;
+	case NPU_IFM_UPSCALE_NEAREST:
+		return coord / 2;
+	case NPU_IFM_UPSCALE_TRANSPOSE:
+		return coord / 2;
+	}
+
+	return 0;
+}
+
 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 can_omit)
@@ -856,6 +876,8 @@ static int calc_sizes(struct drm_device *ddev,
 
 		if (ifm_height < 0 || ifm_width < 0)
 			return -EINVAL;
+		ifm_height = ifm_upscale_coord(ifm_height, st->ifm_upscale);
+		ifm_width = ifm_upscale_coord(ifm_width, st->ifm_upscale);
 
 		ret = feat_matrix_size(edev, info, st, &st->ifm, FEAT_MATRIX_IFM,
 				       ifm_width, ifm_height, st->ifm.depth, false,
@@ -952,6 +974,8 @@ static int calc_sizes_elemwise(struct drm_device *ddev,
 		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;
+		height = ifm_upscale_coord(height, st->ifm_upscale);
+		width = ifm_upscale_coord(width, st->ifm_upscale);
 
 		ret = feat_matrix_size(edev, info, st, &st->ifm, FEAT_MATRIX_IFM,
 				       width, height, depth, false, &len);
@@ -1168,6 +1192,12 @@ static int ethosu_gem_cmdstream_copy_and_validate(struct drm_device *ddev,
 				return -EINVAL;
 			st.ifm.precision = param;
 			break;
+		case NPU_SET_IFM_UPSCALE:
+			if (ethosu_is_u65(edev) ||
+			    param > NPU_IFM_UPSCALE_TRANSPOSE)
+				return -EINVAL;
+			st.ifm_upscale = param;
+			break;
 		case NPU_SET_IFM_BROADCAST:
 			st.ifm.broadcast = param;
 			break;

-- 
2.53.0