drm/amd/display: Try RGB before YCbCr 4:4:4 in stream validationgrafted

amdgpu_dm_create_validate_stream_for_sink() walks encoding_order[] and
uses the first encoding that validates. YCbCr 4:4:4 is listed before
RGB, so an HDMI sink that advertises 4:4:4 gets YCbCr 4:4:4 whenever the
"color format" property is left at AUTO, even though RGB fits the same
link.

That contradicts the documented AUTO behaviour for HDMI in enum
drm_connector_color_format (RGB, falling back to YCbCr 4:2:0 only when
the bandwidth is not available or the mode is 4:2:0-only), which the
amdgpu implementation of the property also describes. It also leaves
the "Broadcast RGB" property without effect on such sinks, since the
quantization range it selects only applies to RGB output.

Try RGB first. The mask still holds every encoding the sink supports,
so a mode that cannot carry RGB falls back exactly as before.

For reference, v7.2 picked RGB here unless YCbCr 4:4:4 was forced
through debugfs, while earlier kernels picked YCbCr 4:4:4 for any HDMI
sink that advertised it.

Fixes: 0b0ff65d3ca1 ("drm/amd/display: Refactor stream validation")
Suggested-by: Adolfo Rodrigues <adolfotregosa@gmail.com>
Assisted-by: Claude Code:claude-fable-5-1
Signed-off-by: Adrian Betschart <adrian.betschart@cinemaone.ch>
Reviewed-by: Fangzhi Zuo <jerry.zuo@amd.com>
Tested-by: Adolfo Rodrigues <adolfotregosa@gmail.com>
Tested-by: Daniel Wheeler <daniel.wheeler@amd.com>
Signed-off-by: Alex Deucher <alexander.deucher@amd.com>
(cherry picked from commit 7de432bc753133764dc40d37f9388da56de251e7)

1 files changed, 128 insertions, 0 deletions

diff --git a/drivers/misc/altera-stapl/altera-comp.c b/drivers/misc/altera-stapl/altera-comp.c
new file mode 100644
index 000000000..4a63f51cc
--- /dev/null
+++ b/drivers/misc/altera-stapl/altera-comp.c
@@ -0,0 +1,128 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * altera-comp.c
+ *
+ * altera FPGA driver
+ *
+ * Copyright (C) Altera Corporation 1998-2001
+ * Copyright (C) 2010 NetUP Inc.
+ * Copyright (C) 2010 Igor M. Liplianin <liplianin@netup.ru>
+ */
+
+#include <linux/kernel.h>
+#include "altera-exprt.h"
+
+#define	SHORT_BITS		16
+#define	CHAR_BITS		8
+#define	DATA_BLOB_LENGTH	3
+#define	MATCH_DATA_LENGTH	8192
+#define ALTERA_REQUEST_SIZE	1024
+#define ALTERA_BUFFER_SIZE	(MATCH_DATA_LENGTH + ALTERA_REQUEST_SIZE)
+
+static u32 altera_bits_req(u32 n)
+{
+	u32 result = SHORT_BITS;
+
+	if (n == 0)
+		result = 1;
+	else {
+		/* Look for the highest non-zero bit position */
+		while ((n & (1 << (SHORT_BITS - 1))) == 0) {
+			n <<= 1;
+			--result;
+		}
+	}
+
+	return result;
+}
+
+static u32 altera_read_packed(u8 *buffer, u32 bits, u32 *bits_avail,
+							u32 *in_index)
+{
+	u32 result = 0;
+	u32 shift = 0;
+	u32 databyte = 0;
+
+	while (bits > 0) {
+		databyte = buffer[*in_index];
+		result |= (((databyte >> (CHAR_BITS - *bits_avail))
+			& (0xff >> (CHAR_BITS - *bits_avail))) << shift);
+
+		if (bits <= *bits_avail) {
+			result &= (0xffff >> (SHORT_BITS - (bits + shift)));
+			*bits_avail -= bits;
+			bits = 0;
+		} else {
+			++(*in_index);
+			shift += *bits_avail;
+			bits -= *bits_avail;
+			*bits_avail = CHAR_BITS;
+		}
+	}
+
+	return result;
+}
+
+u32 altera_shrink(u8 *in, u32 in_length, u8 *out, u32 out_length, s32 version)
+{
+	u32 i, j, data_length = 0L;
+	u32 offset, length;
+	u32 match_data_length = MATCH_DATA_LENGTH;
+	u32 bits_avail = CHAR_BITS;
+	u32 in_index = 0L;
+
+	if (version > 0)
+		--match_data_length;
+
+	for (i = 0; i < out_length; ++i)
+		out[i] = 0;
+
+	/* Read number of bytes in data. */
+	for (i = 0; i < sizeof(in_length); ++i) {
+		data_length = data_length | (
+			altera_read_packed(in,
+					CHAR_BITS,
+					&bits_avail,
+					&in_index) << (i * CHAR_BITS));
+	}
+
+	if (data_length > out_length) {
+		data_length = 0L;
+		return data_length;
+	}
+
+	i = 0;
+	while (i < data_length) {
+		/* A 0 bit indicates literal data. */
+		if (altera_read_packed(in, 1, &bits_avail,
+						&in_index) == 0) {
+			for (j = 0; j < DATA_BLOB_LENGTH; ++j) {
+				if (i < data_length) {
+					out[i] = (u8)altera_read_packed(in,
+							CHAR_BITS,
+							&bits_avail,
+							&in_index);
+					i++;
+				}
+			}
+		} else {
+			/* A 1 bit indicates offset/length to follow. */
+			offset = altera_read_packed(in, altera_bits_req((s16)
+					(i > match_data_length ?
+						match_data_length : i)),
+					&bits_avail,
+					&in_index);
+			length = altera_read_packed(in, CHAR_BITS,
+					&bits_avail,
+					&in_index);
+			for (j = 0; j < length; ++j) {
+				if (i < data_length) {
+					out[i] = out[i - offset];
+					i++;
+				}
+			}
+		}
+	}
+
+	return data_length;
+}