Merge drm/drm-fixes into drm-misc-fixes

Forwarding to v6.6-rc1.

Signed-off-by: Thomas Zimmermann <tzimmermann@suse.de>

7 files changed, 217 insertions, 101 deletions

diff --git a/drivers/gpu/drm/vkms/vkms_composer.c b/drivers/gpu/drm/vkms/vkms_composer.c
index 906d3df40cdb..d5d4f642d367 100644
--- a/drivers/gpu/drm/vkms/vkms_composer.c
+++ b/drivers/gpu/drm/vkms/vkms_composer.c
@@ -6,6 +6,7 @@
 #include <drm/drm_atomic_helper.h>
 #include <drm/drm_blend.h>
 #include <drm/drm_fourcc.h>
+#include <drm/drm_fixed.h>
 #include <drm/drm_gem_framebuffer_helper.h>
 #include <drm/drm_vblank.h>
 #include <linux/minmax.h>
@@ -23,7 +24,7 @@ static u16 pre_mul_blend_channel(u16 src, u16 dst, u16 alpha)
 
 /**
  * pre_mul_alpha_blend - alpha blending equation
- * @src_frame_info: source framebuffer's metadata
+ * @frame_info: Source framebuffer's metadata
  * @stage_buffer: The line with the pixels from src_plane
  * @output_buffer: A line buffer that receives all the blends output
  *
@@ -89,12 +90,81 @@ static void fill_background(const struct pixel_argb_u16 *background_color,
 		output_buffer->pixels[i] = *background_color;
 }
 
+// lerp(a, b, t) = a + (b - a) * t
+static u16 lerp_u16(u16 a, u16 b, s64 t)
+{
+	s64 a_fp = drm_int2fixp(a);
+	s64 b_fp = drm_int2fixp(b);
+
+	s64 delta = drm_fixp_mul(b_fp - a_fp,  t);
+
+	return drm_fixp2int(a_fp + delta);
+}
+
+static s64 get_lut_index(const struct vkms_color_lut *lut, u16 channel_value)
+{
+	s64 color_channel_fp = drm_int2fixp(channel_value);
+
+	return drm_fixp_mul(color_channel_fp, lut->channel_value2index_ratio);
+}
+
+/*
+ * This enum is related to the positions of the variables inside
+ * `struct drm_color_lut`, so the order of both needs to be the same.
+ */
+enum lut_channel {
+	LUT_RED = 0,
+	LUT_GREEN,
+	LUT_BLUE,
+	LUT_RESERVED
+};
+
+static u16 apply_lut_to_channel_value(const struct vkms_color_lut *lut, u16 channel_value,
+				      enum lut_channel channel)
+{
+	s64 lut_index = get_lut_index(lut, channel_value);
+
+	/*
+	 * This checks if `struct drm_color_lut` has any gap added by the compiler
+	 * between the struct fields.
+	 */
+	static_assert(sizeof(struct drm_color_lut) == sizeof(__u16) * 4);
+
+	u16 *floor_lut_value = (__u16 *)&lut->base[drm_fixp2int(lut_index)];
+	u16 *ceil_lut_value = (__u16 *)&lut->base[drm_fixp2int_ceil(lut_index)];
+
+	u16 floor_channel_value = floor_lut_value[channel];
+	u16 ceil_channel_value = ceil_lut_value[channel];
+
+	return lerp_u16(floor_channel_value, ceil_channel_value,
+			lut_index & DRM_FIXED_DECIMAL_MASK);
+}
+
+static void apply_lut(const struct vkms_crtc_state *crtc_state, struct line_buffer *output_buffer)
+{
+	if (!crtc_state->gamma_lut.base)
+		return;
+
+	if (!crtc_state->gamma_lut.lut_length)
+		return;
+
+	for (size_t x = 0; x < output_buffer->n_pixels; x++) {
+		struct pixel_argb_u16 *pixel = &output_buffer->pixels[x];
+
+		pixel->r = apply_lut_to_channel_value(&crtc_state->gamma_lut, pixel->r, LUT_RED);
+		pixel->g = apply_lut_to_channel_value(&crtc_state->gamma_lut, pixel->g, LUT_GREEN);
+		pixel->b = apply_lut_to_channel_value(&crtc_state->gamma_lut, pixel->b, LUT_BLUE);
+	}
+}
+
 /**
- * @wb_frame_info: The writeback frame buffer metadata
+ * blend - blend the pixels from all planes and compute crc
+ * @wb: The writeback frame buffer metadata
  * @crtc_state: The crtc state
  * @crc32: The crc output of the final frame
  * @output_buffer: A buffer of a row that will receive the result of the blend(s)
  * @stage_buffer: The line with the pixels from plane being blend to the output
+ * @row_size: The size, in bytes, of a single row
  *
  * This function blends the pixels (Using the `pre_mul_alpha_blend`)
  * from all planes, calculates the crc32 of the output from the former step,
@@ -128,10 +198,12 @@ static void blend(struct vkms_writeback_job *wb,
 					    output_buffer);
 		}
 
+		apply_lut(crtc_state, output_buffer);
+
 		*crc32 = crc32_le(*crc32, (void *)output_buffer->pixels, row_size);
 
 		if (wb)
-			wb->wb_write(&wb->wb_frame_info, output_buffer, y_pos);
+			vkms_writeback_row(wb, output_buffer, y_pos);
 	}
 }
 
@@ -145,7 +217,7 @@ static int check_format_funcs(struct vkms_crtc_state *crtc_state,
 		if (!planes[i]->pixel_read)
 			return -1;
 
-	if (active_wb && !active_wb->wb_write)
+	if (active_wb && !active_wb->pixel_write)
 		return -1;
 
 	return 0;
@@ -242,6 +314,22 @@ void vkms_composer_worker(struct work_struct *work)
 	crtc_state->frame_start = 0;
 	crtc_state->frame_end = 0;
 	crtc_state->crc_pending = false;
+
+	if (crtc->state->gamma_lut) {
+		s64 max_lut_index_fp;
+		s64 u16_max_fp = drm_int2fixp(0xffff);
+
+		crtc_state->gamma_lut.base = (struct drm_color_lut *)crtc->state->gamma_lut->data;
+		crtc_state->gamma_lut.lut_length =
+			crtc->state->gamma_lut->length / sizeof(struct drm_color_lut);
+		max_lut_index_fp = drm_int2fixp(crtc_state->gamma_lut.lut_length  - 1);
+		crtc_state->gamma_lut.channel_value2index_ratio = drm_fixp_div(max_lut_index_fp,
+									       u16_max_fp);
+
+	} else {
+		crtc_state->gamma_lut.base = NULL;
+	}
+
 	spin_unlock_irq(&out->composer_lock);
 
 	/*
@@ -320,10 +408,15 @@ void vkms_set_composer(struct vkms_output *out, bool enabled)
 	if (enabled)
 		drm_crtc_vblank_get(&out->crtc);
 
-	spin_lock_irq(&out->lock);
+	mutex_lock(&out->enabled_lock);
 	old_enabled = out->composer_enabled;
 	out->composer_enabled = enabled;
-	spin_unlock_irq(&out->lock);
+
+	/* the composition wasn't enabled, so unlock the lock to make sure the lock
+	 * will be balanced even if we have a failed commit
+	 */
+	if (!out->composer_enabled)
+		mutex_unlock(&out->enabled_lock);
 
 	if (old_enabled)
 		drm_crtc_vblank_put(&out->crtc);
diff --git a/drivers/gpu/drm/vkms/vkms_crtc.c b/drivers/gpu/drm/vkms/vkms_crtc.c
index 515f6772b866..3c5ebf106b66 100644
--- a/drivers/gpu/drm/vkms/vkms_crtc.c
+++ b/drivers/gpu/drm/vkms/vkms_crtc.c
@@ -16,7 +16,7 @@ static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer)
 	struct drm_crtc *crtc = &output->crtc;
 	struct vkms_crtc_state *state;
 	u64 ret_overrun;
-	bool ret, fence_cookie;
+	bool ret, fence_cookie, composer_enabled;
 
 	fence_cookie = dma_fence_begin_signalling();
 
@@ -25,15 +25,15 @@ static enum hrtimer_restart vkms_vblank_simulate(struct hrtimer *timer)
 	if (ret_overrun != 1)
 		pr_warn("%s: vblank timer overrun\n", __func__);
 
-	spin_lock(&output->lock);
 	ret = drm_crtc_handle_vblank(crtc);
 	if (!ret)
 		DRM_ERROR("vkms failure on handling vblank");
 
 	state = output->composer_state;
-	spin_unlock(&output->lock);
+	composer_enabled = output->composer_enabled;
+	mutex_unlock(&output->enabled_lock);
 
-	if (state && output->composer_enabled) {
+	if (state && composer_enabled) {
 		u64 frame = drm_crtc_accurate_vblank_count(crtc);
 
 		/* update frame_start only if a queued vkms_composer_worker()
@@ -290,8 +290,12 @@ int vkms_crtc_init(struct drm_device *dev, struct drm_crtc *crtc,
 
 	drm_crtc_helper_add(crtc, &vkms_crtc_helper_funcs);
 
+	drm_mode_crtc_set_gamma_size(crtc, VKMS_LUT_SIZE);
+	drm_crtc_enable_color_mgmt(crtc, 0, false, VKMS_LUT_SIZE);
+
 	spin_lock_init(&vkms_out->lock);
 	spin_lock_init(&vkms_out->composer_lock);
+	mutex_init(&vkms_out->enabled_lock);
 
 	vkms_out->composer_workq = alloc_ordered_workqueue("vkms_composer", 0);
 	if (!vkms_out->composer_workq)
diff --git a/drivers/gpu/drm/vkms/vkms_drv.c b/drivers/gpu/drm/vkms/vkms_drv.c
index e3c9c9571c8d..dd0af086e7fa 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.c
+++ b/drivers/gpu/drm/vkms/vkms_drv.c
@@ -120,9 +120,27 @@ static const struct drm_driver vkms_driver = {
 	.minor			= DRIVER_MINOR,
 };
 
+static int vkms_atomic_check(struct drm_device *dev, struct drm_atomic_state *state)
+{
+	struct drm_crtc *crtc;
+	struct drm_crtc_state *new_crtc_state;
+	int i;
+
+	for_each_new_crtc_in_state(state, crtc, new_crtc_state, i) {
+		if (!new_crtc_state->gamma_lut || !new_crtc_state->color_mgmt_changed)
+			continue;
+
+		if (new_crtc_state->gamma_lut->length / sizeof(struct drm_color_lut *)
+		    > VKMS_LUT_SIZE)
+			return -EINVAL;
+	}
+
+	return drm_atomic_helper_check(dev, state);
+}
+
 static const struct drm_mode_config_funcs vkms_mode_funcs = {
 	.fb_create = drm_gem_fb_create,
-	.atomic_check = drm_atomic_helper_check,
+	.atomic_check = vkms_atomic_check,
 	.atomic_commit = drm_atomic_helper_commit,
 };
 
diff --git a/drivers/gpu/drm/vkms/vkms_drv.h b/drivers/gpu/drm/vkms/vkms_drv.h
index 5f1a0a44a78c..c7ae6c2ba1df 100644
--- a/drivers/gpu/drm/vkms/vkms_drv.h
+++ b/drivers/gpu/drm/vkms/vkms_drv.h
@@ -23,6 +23,8 @@
 
 #define NUM_OVERLAY_PLANES 8
 
+#define VKMS_LUT_SIZE 256
+
 struct vkms_frame_info {
 	struct drm_framebuffer *fb;
 	struct drm_rect src, dst;
@@ -46,8 +48,7 @@ struct line_buffer {
 struct vkms_writeback_job {
 	struct iosys_map data[DRM_FORMAT_MAX_PLANES];
 	struct vkms_frame_info wb_frame_info;
-	void (*wb_write)(struct vkms_frame_info *frame_info,
-			 const struct line_buffer *buffer, int y);
+	void (*pixel_write)(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel);
 };
 
 /**
@@ -65,6 +66,12 @@ struct vkms_plane {
 	struct drm_plane base;
 };
 
+struct vkms_color_lut {
+	struct drm_color_lut *base;
+	size_t lut_length;
+	s64 channel_value2index_ratio;
+};
+
 /**
  * vkms_crtc_state - Driver specific CRTC state
  * @base: base CRTC state
@@ -80,6 +87,7 @@ struct vkms_crtc_state {
 	/* stack of active planes for crc computation, should be in z order */
 	struct vkms_plane_state **active_planes;
 	struct vkms_writeback_job *active_writeback;
+	struct vkms_color_lut gamma_lut;
 
 	/* below four are protected by vkms_output.composer_lock */
 	bool crc_pending;
@@ -100,8 +108,10 @@ struct vkms_output {
 	struct workqueue_struct *composer_workq;
 	/* protects concurrent access to composer */
 	spinlock_t lock;
+	/* guarantees that if the composer is enabled, a job will be queued */
+	struct mutex enabled_lock;
 
-	/* protected by @lock */
+	/* protected by @enabled_lock */
 	bool composer_enabled;
 	struct vkms_crtc_state *composer_state;
 
@@ -157,6 +167,7 @@ int vkms_verify_crc_source(struct drm_crtc *crtc, const char *source_name,
 void vkms_composer_worker(struct work_struct *work);
 void vkms_set_composer(struct vkms_output *out, bool enabled);
 void vkms_compose_row(struct line_buffer *stage_buffer, struct vkms_plane_state *plane, int y);
+void vkms_writeback_row(struct vkms_writeback_job *wb, const struct line_buffer *src_buffer, int y);
 
 /* Writeback */
 int vkms_enable_writeback_connector(struct vkms_device *vkmsdev);
diff --git a/drivers/gpu/drm/vkms/vkms_formats.c b/drivers/gpu/drm/vkms/vkms_formats.c
index 5945da0beba6..36046b12f296 100644
--- a/drivers/gpu/drm/vkms/vkms_formats.c
+++ b/drivers/gpu/drm/vkms/vkms_formats.c
@@ -111,6 +111,19 @@ static void RGB565_to_argb_u16(u8 *src_pixels, struct pixel_argb_u16 *out_pixel)
 	out_pixel->b = drm_fixp2int_round(drm_fixp_mul(fp_b, fp_rb_ratio));
 }
 
+/**
+ * vkms_compose_row - compose a single row of a plane
+ * @stage_buffer: output line with the composed pixels
+ * @plane: state of the plane that is being composed
+ * @y: y coordinate of the row
+ *
+ * This function composes a single row of a plane. It gets the source pixels
+ * through the y coordinate (see get_packed_src_addr()) and goes linearly
+ * through the source pixel, reading the pixels and converting it to
+ * ARGB16161616 (see the pixel_read() callback). For rotate-90 and rotate-270,
+ * the source pixels are not traversed linearly. The source pixels are queried
+ * on each iteration in order to traverse the pixels vertically.
+ */
 void vkms_compose_row(struct line_buffer *stage_buffer, struct vkms_plane_state *plane, int y)
 {
 	struct pixel_argb_u16 *out_pixels = stage_buffer->pixels;
@@ -137,107 +150,81 @@ void vkms_compose_row(struct line_buffer *stage_buffer, struct vkms_plane_state
  * 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)
+static void argb_u16_to_ARGB8888(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	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);
-	}
+	/*
+	 * 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_pixel->a, 257);
+	dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixel->r, 257);
+	dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixel->g, 257);
+	dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixel->b, 257);
 }
 
-static void argb_u16_to_XRGB8888(struct vkms_frame_info *frame_info,
-				 const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_XRGB8888(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	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);
-	}
+	dst_pixels[3] = 0xff;
+	dst_pixels[2] = DIV_ROUND_CLOSEST(in_pixel->r, 257);
+	dst_pixels[1] = DIV_ROUND_CLOSEST(in_pixel->g, 257);
+	dst_pixels[0] = DIV_ROUND_CLOSEST(in_pixel->b, 257);
 }
 
-static void argb_u16_to_ARGB16161616(struct vkms_frame_info *frame_info,
-				     const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_ARGB16161616(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u16 *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] = cpu_to_le16(in_pixels[x].a);
-		dst_pixels[2] = cpu_to_le16(in_pixels[x].r);
-		dst_pixels[1] = cpu_to_le16(in_pixels[x].g);
-		dst_pixels[0] = cpu_to_le16(in_pixels[x].b);
-	}
+	u16 *pixels = (u16 *)dst_pixels;
+
+	pixels[3] = cpu_to_le16(in_pixel->a);
+	pixels[2] = cpu_to_le16(in_pixel->r);
+	pixels[1] = cpu_to_le16(in_pixel->g);
+	pixels[0] = cpu_to_le16(in_pixel->b);
 }
 
-static void argb_u16_to_XRGB16161616(struct vkms_frame_info *frame_info,
-				     const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_XRGB16161616(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u16 *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] = 0xffff;
-		dst_pixels[2] = cpu_to_le16(in_pixels[x].r);
-		dst_pixels[1] = cpu_to_le16(in_pixels[x].g);
-		dst_pixels[0] = cpu_to_le16(in_pixels[x].b);
-	}
+	u16 *pixels = (u16 *)dst_pixels;
+
+	pixels[3] = 0xffff;
+	pixels[2] = cpu_to_le16(in_pixel->r);
+	pixels[1] = cpu_to_le16(in_pixel->g);
+	pixels[0] = cpu_to_le16(in_pixel->b);
 }
 
-static void argb_u16_to_RGB565(struct vkms_frame_info *frame_info,
-			       const struct line_buffer *src_buffer, int y)
+static void argb_u16_to_RGB565(u8 *dst_pixels, struct pixel_argb_u16 *in_pixel)
 {
-	int x_dst = frame_info->dst.x1;
-	u16 *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);
+	u16 *pixels = (u16 *)dst_pixels;
 
 	s64 fp_rb_ratio = drm_fixp_div(drm_int2fixp(65535), drm_int2fixp(31));
 	s64 fp_g_ratio = drm_fixp_div(drm_int2fixp(65535), drm_int2fixp(63));
 
-	for (size_t x = 0; x < x_limit; x++, dst_pixels++) {
-		s64 fp_r = drm_int2fixp(in_pixels[x].r);
-		s64 fp_g = drm_int2fixp(in_pixels[x].g);
-		s64 fp_b = drm_int2fixp(in_pixels[x].b);
+	s64 fp_r = drm_int2fixp(in_pixel->r);
+	s64 fp_g = drm_int2fixp(in_pixel->g);
+	s64 fp_b = drm_int2fixp(in_pixel->b);
 
-		u16 r = drm_fixp2int_round(drm_fixp_div(fp_r, fp_rb_ratio));
-		u16 g = drm_fixp2int_round(drm_fixp_div(fp_g, fp_g_ratio));
-		u16 b = drm_fixp2int_round(drm_fixp_div(fp_b, fp_rb_ratio));
+	u16 r = drm_fixp2int(drm_fixp_div(fp_r, fp_rb_ratio));
+	u16 g = drm_fixp2int(drm_fixp_div(fp_g, fp_g_ratio));
+	u16 b = drm_fixp2int(drm_fixp_div(fp_b, fp_rb_ratio));
 
-		*dst_pixels = cpu_to_le16(r << 11 | g << 5 | b);
-	}
+	*pixels = cpu_to_le16(r << 11 | g << 5 | b);
+}
+
+void vkms_writeback_row(struct vkms_writeback_job *wb,
+			const struct line_buffer *src_buffer, int y)
+{
+	struct vkms_frame_info *frame_info = &wb->wb_frame_info;
+	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 += frame_info->cpp)
+		wb->pixel_write(dst_pixels, &in_pixels[x]);
 }
 
 void *get_pixel_conversion_function(u32 format)
@@ -258,7 +245,7 @@ void *get_pixel_conversion_function(u32 format)
 	}
 }
 
-void *get_line_to_frame_function(u32 format)
+void *get_pixel_write_function(u32 format)
 {
 	switch (format) {
 	case DRM_FORMAT_ARGB8888:
diff --git a/drivers/gpu/drm/vkms/vkms_formats.h b/drivers/gpu/drm/vkms/vkms_formats.h
index c5b113495d0c..cf59c2ed8e9a 100644
--- a/drivers/gpu/drm/vkms/vkms_formats.h
+++ b/drivers/gpu/drm/vkms/vkms_formats.h
@@ -7,6 +7,6 @@
 
 void *get_pixel_conversion_function(u32 format);
 
-void *get_line_to_frame_function(u32 format);
+void *get_pixel_write_function(u32 format);
 
 #endif /* _VKMS_FORMATS_H_ */
diff --git a/drivers/gpu/drm/vkms/vkms_writeback.c b/drivers/gpu/drm/vkms/vkms_writeback.c
index 84a51cd281b9..d7e63aa14663 100644
--- a/drivers/gpu/drm/vkms/vkms_writeback.c
+++ b/drivers/gpu/drm/vkms/vkms_writeback.c
@@ -15,6 +15,7 @@
 #include "vkms_formats.h"
 
 static const u32 vkms_wb_formats[] = {
+	DRM_FORMAT_ARGB8888,
 	DRM_FORMAT_XRGB8888,
 	DRM_FORMAT_XRGB16161616,
 	DRM_FORMAT_ARGB16161616,
@@ -142,13 +143,15 @@ static void vkms_wb_atomic_commit(struct drm_connector *conn,
 
 	spin_lock_irq(&output->composer_lock);
 	crtc_state->active_writeback = active_wb;
+	crtc_state->wb_pending = true;
+	spin_unlock_irq(&output->composer_lock);
+
 	wb_frame_info->offset = fb->offsets[0];
 	wb_frame_info->pitch = fb->pitches[0];
 	wb_frame_info->cpp = fb->format->cpp[0];
-	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);
+	active_wb->pixel_write = get_pixel_write_function(wb_format);
 	drm_rect_init(&wb_frame_info->src, 0, 0, crtc_width, crtc_height);
 	drm_rect_init(&wb_frame_info->dst, 0, 0, crtc_width, crtc_height);
 }