drm: vkms: Refactor the plane composer to accept new formats

Currently the blend function only accepts XRGB_8888 and ARGB_8888
as a color input.

This patch refactors all the functions related to the plane composition
to overcome this limitation.

The pixels blend is done using the new internal format. And new handlers
are being added to convert a specific format to/from this internal format.

So the blend operation depends on these handlers to convert to this common
format. The blended result, if necessary, is converted to the writeback
buffer format.

This patch introduces three major differences to the blend function.
1 - All the planes are blended at once.
2 - The blend calculus is done as per line instead of per pixel.
3 - It is responsible to calculates the CRC and writing the writeback
buffer(if necessary).

These changes allow us to allocate way less memory in the intermediate
buffer to compute these operations. Because now we don't need to
have the entire intermediate image lines at once, just one line is
enough.

| Memory consumption (output dimensions) |
|:--------------------------------------:|
|       Current      |     This patch    |
|:------------------:|:-----------------:|
|   Width * Heigth   |     2 * Width     |

Beyond memory, we also have a minor performance benefit from all
these changes. Results running the IGT[1] test
`igt@kms_cursor_crc@pipe-a-cursor-512x512-onscreen` ten times:

|                 Frametime                  |
|:------------------------------------------:|
|  Implementation |  Current  |  This commit |
|:---------------:|:---------:|:------------:|
| frametime range |  9~22 ms  |    5~17 ms   |
|     Average     |  11.4 ms  |    7.8 ms    |

[1] IGT commit id: bc3f6833a12221a46659535dac06ebb312490eb4

V2: Improves the performance drastically, by performing the operations
    per-line and not per-pixel(Pekka Paalanen).
    Minor improvements(Pekka Paalanen).
V3: Changes the code to blend the planes all at once. This improves
    performance, memory consumption, and removes much of the weirdness
    of the V2(Pekka Paalanen and me).
    Minor improvements(Pekka Paalanen and me).
V4: Rebase the code and adapt it to the new NUM_OVERLAY_PLANES constant.
V5: Minor checkpatch fixes and the removal of TO-DO item(Melissa Wen).
    Several security/robustness improvents(Pekka Paalanen).
    Removes check_planes_x_bounds function and allows partial
    partly off-screen(Pekka Paalanen).
V6: Fix a mismatch of some variable sizes (Pekka Paalanen).
    Several minor improvements (Pekka Paalanen).
Reviewed-by: Melissa Wen <mwen@igalia.com>
Reported-by: kernel test robot <lkp@intel.com>
Signed-off-by: Igor Torrente <igormtorrente@gmail.com>
Signed-off-by: Melissa Wen <melissa.srw@gmail.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220905190811.25024-7-igormtorrente@gmail.com

Documentation/gpu/vkms.rst

@@ -118,10 +118,6 @@ Add Plane Features
 
 There's lots of plane features we could add support for:
 
-- Clearing primary plane: clear primary plane before plane composition (at the
-  start) for correctness of pixel blend ops. It also guarantees alpha channel
-  is cleared in the target buffer for stable crc. [Good to get started]
-
 - ARGB format on primary plane: blend the primary plane into background with
   translucent alpha.
 

drivers/gpu/drm/vkms/Makefile

@@ -3,6 +3,7 @@ vkms-y := \
 	vkms_drv.o \
 	vkms_plane.o \
 	vkms_output.o \
+	vkms_formats.o \
 	vkms_crtc.o \
 	vkms_composer.o \
 	vkms_writeback.o

drivers/gpu/drm/vkms/vkms_formats.c

+// SPDX-License-Identifier: GPL-2.0+
+
+#include <drm/drm_rect.h>
+#include <linux/minmax.h>
+
+#include "vkms_formats.h"
+
+static size_t pixel_offset(const struct vkms_frame_info *frame_info, int x, int y)
+{
+	return frame_info->offset + (y * frame_info->pitch)
+				  + (x * frame_info->cpp);
+}
+
+/*
+ * packed_pixels_addr - Get the pointer to pixel of a given pair of coordinates
+ *
+ * @frame_info: Buffer metadata
+ * @x: The x(width) coordinate of the 2D buffer
+ * @y: The y(Heigth) coordinate of the 2D buffer
+ *
+ * Takes the information stored in the frame_info, a pair of coordinates, and
+ * returns the address of the first color channel.
+ * This function assumes the channels are packed together, i.e. a color channel
+ * comes immediately after another in the memory. And therefore, this function
+ * doesn't work for YUV with chroma subsampling (e.g. YUV420 and NV21).
+ */
+static void *packed_pixels_addr(const struct vkms_frame_info *frame_info,
+				int x, int y)
+{
+	size_t offset = pixel_offset(frame_info, x, y);
+
+	return (u8 *)frame_info->map[0].vaddr + offset;
+}
+
+static void *get_packed_src_addr(const struct vkms_frame_info *frame_info, int y)
+{
+	int x_src = frame_info->src.x1 >> 16;
+	int y_src = y - frame_info->dst.y1 + (frame_info->src.y1 >> 16);
+
+	return packed_pixels_addr(frame_info, x_src, y_src);
+}
+
+static void ARGB8888_to_argb_u16(struct line_buffer *stage_buffer,
+				 const struct vkms_frame_info *frame_info, int y)
+{
+	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
+	u8 *src_pixels = get_packed_src_addr(frame_info, y);
+	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
+			    stage_buffer->n_pixels);
+
+	for (size_t x = 0; x < x_limit; x++, src_pixels += 4) {
+		/*
+		 * The 257 is the "conversion ratio". This number is obtained by the
+		 * (2^16 - 1) / (2^8 - 1) division. Which, in this case, tries to get
+		 * the best color value in a pixel format with more possibilities.
+		 * A similar idea applies to others RGB color conversions.
+		 */
+		out_pixels[x].a = (u16)src_pixels[3] * 257;
+		out_pixels[x].r = (u16)src_pixels[2] * 257;
+		out_pixels[x].g = (u16)src_pixels[1] * 257;
+		out_pixels[x].b = (u16)src_pixels[0] * 257;
+	}
+}
+
+static void XRGB8888_to_argb_u16(struct line_buffer *stage_buffer,
+				 const struct vkms_frame_info *frame_info, int y)
+{
+	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
+	u8 *src_pixels = get_packed_src_addr(frame_info, y);
+	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
+			    stage_buffer->n_pixels);
+
+	for (size_t x = 0; x < x_limit; x++, src_pixels += 4) {
+		out_pixels[x].a = (u16)0xffff;
+		out_pixels[x].r = (u16)src_pixels[2] * 257;
+		out_pixels[x].g = (u16)src_pixels[1] * 257;
+		out_pixels[x].b = (u16)src_pixels[0] * 257;
+	}
+}
+
+/*
+ * The following  functions take an line of argb_u16 pixels from the
+ * src_buffer, convert them to a specific format, and store them in the
+ * destination.
+ *
+ * They are used in the `compose_active_planes` to convert and store a line
+ * from the src_buffer to the writeback buffer.
+ */
+static void argb_u16_to_ARGB8888(struct vkms_frame_info *frame_info,
+				 const struct line_buffer *src_buffer, int y)
+{
+	int x_dst = frame_info->dst.x1;
+	u8 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
+	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
+	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
+			    src_buffer->n_pixels);
+
+	for (size_t x = 0; x < x_limit; x++, dst_pixels += 4) {
+		/*
+		 * This sequence below is important because the format's byte order is
+		 * in little-endian. In the case of the ARGB8888 the memory is
+		 * organized this way:
+		 *
+		 * | Addr     | = blue channel
+		 * | Addr + 1 | = green channel
+		 * | Addr + 2 | = Red channel
+		 * | Addr + 3 | = Alpha channel
+		 */
+		dst_pixels[3] = DIV_ROUND_CLOSEST(in_pixels[x].a, 257);
+		dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixels[x].r, 257);
+		dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixels[x].g, 257);
+		dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixels[x].b, 257);
+	}
+}
+
+static void argb_u16_to_XRGB8888(struct vkms_frame_info *frame_info,
+				 const struct line_buffer *src_buffer, int y)
+{
+	int x_dst = frame_info->dst.x1;
+	u8 *dst_pixels = packed_pixels_addr(frame_info, x_dst, y);
+	struct pixel_argb_u16 *in_pixels = src_buffer->pixels;
+	int x_limit = min_t(size_t, drm_rect_width(&frame_info->dst),
+			    src_buffer->n_pixels);
+
+	for (size_t x = 0; x < x_limit; x++, dst_pixels += 4) {
+		dst_pixels[3] = 0xff;
+		dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixels[x].r, 257);
+		dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixels[x].g, 257);
+		dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixels[x].b, 257);
+	}
+}
+
+void *get_frame_to_line_function(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_ARGB8888:
+		return &ARGB8888_to_argb_u16;
+	case DRM_FORMAT_XRGB8888:
+		return &XRGB8888_to_argb_u16;
+	default:
+		return NULL;
+	}
+}
+
+void *get_line_to_frame_function(u32 format)
+{
+	switch (format) {
+	case DRM_FORMAT_ARGB8888:
+		return &argb_u16_to_ARGB8888;
+	case DRM_FORMAT_XRGB8888:
+		return &argb_u16_to_XRGB8888;
+	default:
+		return NULL;
+	}
+}

drivers/gpu/drm/vkms/vkms_formats.h

+/* SPDX-License-Identifier: GPL-2.0+ */
+
+#ifndef _VKMS_FORMATS_H_
+#define _VKMS_FORMATS_H_
+
+#include "vkms_drv.h"
+
+void *get_frame_to_line_function(u32 format);
+
+void *get_line_to_frame_function(u32 format);
+
+#endif /* _VKMS_FORMATS_H_ */

drivers/gpu/drm/vkms/vkms_plane.c

@@ -9,6 +9,7 @@
 #include <drm/drm_gem_framebuffer_helper.h>
 
 #include "vkms_drv.h"
+#include "vkms_formats.h"
 
 static const u32 vkms_formats[] = {
 	DRM_FORMAT_XRGB8888,
@@ -99,6 +100,7 @@ static void vkms_plane_atomic_update(struct drm_plane *plane,
 	struct drm_shadow_plane_state *shadow_plane_state;
 	struct drm_framebuffer *fb = new_state->fb;
 	struct vkms_frame_info *frame_info;
+	u32 fmt = fb->format->format;
 
 	if (!new_state->crtc || !fb)
 		return;
@@ -115,6 +117,7 @@ static void vkms_plane_atomic_update(struct drm_plane *plane,
 	frame_info->offset = fb->offsets[0];
 	frame_info->pitch = fb->pitches[0];
 	frame_info->cpp = fb->format->cpp[0];
+	vkms_plane_state->plane_read = get_frame_to_line_function(fmt);
 }
 
 static int vkms_plane_atomic_check(struct drm_plane *plane,

drivers/gpu/drm/vkms/vkms_writeback.c

@@ -12,6 +12,7 @@
 #include <drm/drm_gem_shmem_helper.h>
 
 #include "vkms_drv.h"
+#include "vkms_formats.h"
 
 static const u32 vkms_wb_formats[] = {
 	DRM_FORMAT_XRGB8888,
@@ -124,6 +125,7 @@ static void vkms_wb_atomic_commit(struct drm_connector *conn,
 	struct drm_framebuffer *fb = connector_state->writeback_job->fb;
 	struct vkms_writeback_job *active_wb;
 	struct vkms_frame_info *wb_frame_info;
+	u32 wb_format = fb->format->format;
 
 	if (!conn_state)
 		return;
@@ -141,6 +143,7 @@ static void vkms_wb_atomic_commit(struct drm_connector *conn,
 	crtc_state->wb_pending = true;
 	spin_unlock_irq(&output->composer_lock);
 	drm_writeback_queue_job(wb_conn, connector_state);
+	active_wb->wb_write = get_line_to_frame_function(wb_format);
 }
 
 static const struct drm_connector_helper_funcs vkms_wb_conn_helper_funcs = {