1 files changed, 271 insertions, 280 deletions

diff --git a/drivers/gpu/drm/drm_format_helper.c b/drivers/gpu/drm/drm_format_helper.c
index bc0f49773868..a3ccd8bc966f 100644
--- a/drivers/gpu/drm/drm_format_helper.c
+++ b/drivers/gpu/drm/drm_format_helper.c
@@ -40,6 +40,94 @@ unsigned int drm_fb_clip_offset(unsigned int pitch, const struct drm_format_info
 }
 EXPORT_SYMBOL(drm_fb_clip_offset);
 
+/* TODO: Make this functon work with multi-plane formats. */
+static int drm_fb_xfrm(void *dst, unsigned long dst_pitch, unsigned long dst_pixsize,
+		       const void *vaddr, const struct drm_framebuffer *fb,
+		       const struct drm_rect *clip, bool vaddr_cached_hint,
+		       void (*xfrm_line)(void *dbuf, const void *sbuf, unsigned int npixels))
+{
+	unsigned long linepixels = drm_rect_width(clip);
+	unsigned long lines = drm_rect_height(clip);
+	size_t sbuf_len = linepixels * fb->format->cpp[0];
+	void *stmp = NULL;
+	unsigned long i;
+	const void *sbuf;
+
+	/*
+	 * Some source buffers, such as CMA memory, use write-combine
+	 * caching, so reads are uncached. Speed up access by fetching
+	 * one line at a time.
+	 */
+	if (!vaddr_cached_hint) {
+		stmp = kmalloc(sbuf_len, GFP_KERNEL);
+		if (!stmp)
+			return -ENOMEM;
+	}
+
+	if (!dst_pitch)
+		dst_pitch = drm_rect_width(clip) * dst_pixsize;
+	vaddr += clip_offset(clip, fb->pitches[0], fb->format->cpp[0]);
+
+	for (i = 0; i < lines; ++i) {
+		if (stmp)
+			sbuf = memcpy(stmp, vaddr, sbuf_len);
+		else
+			sbuf = vaddr;
+		xfrm_line(dst, sbuf, linepixels);
+		vaddr += fb->pitches[0];
+		dst += dst_pitch;
+	}
+
+	kfree(stmp);
+
+	return 0;
+}
+
+/* TODO: Make this functon work with multi-plane formats. */
+static int drm_fb_xfrm_toio(void __iomem *dst, unsigned long dst_pitch, unsigned long dst_pixsize,
+			    const void *vaddr, const struct drm_framebuffer *fb,
+			    const struct drm_rect *clip, bool vaddr_cached_hint,
+			    void (*xfrm_line)(void *dbuf, const void *sbuf, unsigned int npixels))
+{
+	unsigned long linepixels = drm_rect_width(clip);
+	unsigned long lines = drm_rect_height(clip);
+	size_t dbuf_len = linepixels * dst_pixsize;
+	size_t stmp_off = round_up(dbuf_len, ARCH_KMALLOC_MINALIGN); /* for sbuf alignment */
+	size_t sbuf_len = linepixels * fb->format->cpp[0];
+	void *stmp = NULL;
+	unsigned long i;
+	const void *sbuf;
+	void *dbuf;
+
+	if (vaddr_cached_hint) {
+		dbuf = kmalloc(dbuf_len, GFP_KERNEL);
+	} else {
+		dbuf = kmalloc(stmp_off + sbuf_len, GFP_KERNEL);
+		stmp = dbuf + stmp_off;
+	}
+	if (!dbuf)
+		return -ENOMEM;
+
+	if (!dst_pitch)
+		dst_pitch = linepixels * dst_pixsize;
+	vaddr += clip_offset(clip, fb->pitches[0], fb->format->cpp[0]);
+
+	for (i = 0; i < lines; ++i) {
+		if (stmp)
+			sbuf = memcpy(stmp, vaddr, sbuf_len);
+		else
+			sbuf = vaddr;
+		xfrm_line(dbuf, sbuf, linepixels);
+		memcpy_toio(dst, dbuf, dbuf_len);
+		vaddr += fb->pitches[0];
+		dst += dst_pitch;
+	}
+
+	kfree(dbuf);
+
+	return 0;
+}
+
 /**
  * drm_fb_memcpy - Copy clip buffer
  * @dst: Destination buffer
@@ -100,6 +188,26 @@ void drm_fb_memcpy_toio(void __iomem *dst, unsigned int dst_pitch, const void *v
 }
 EXPORT_SYMBOL(drm_fb_memcpy_toio);
 
+static void drm_fb_swab16_line(void *dbuf, const void *sbuf, unsigned int pixels)
+{
+	u16 *dbuf16 = dbuf;
+	const u16 *sbuf16 = sbuf;
+	const u16 *send16 = sbuf16 + pixels;
+
+	while (sbuf16 < send16)
+		*dbuf16++ = swab16(*sbuf16++);
+}
+
+static void drm_fb_swab32_line(void *dbuf, const void *sbuf, unsigned int pixels)
+{
+	u32 *dbuf32 = dbuf;
+	const u32 *sbuf32 = sbuf;
+	const u32 *send32 = sbuf32 + pixels;
+
+	while (sbuf32 < send32)
+		*dbuf32++ = swab32(*sbuf32++);
+}
+
 /**
  * drm_fb_swab - Swap bytes into clip buffer
  * @dst: Destination buffer
@@ -120,63 +228,34 @@ void drm_fb_swab(void *dst, unsigned int dst_pitch, const void *src,
 		 bool cached)
 {
 	u8 cpp = fb->format->cpp[0];
-	size_t len = drm_rect_width(clip) * cpp;
-	const u16 *src16;
-	const u32 *src32;
-	u16 *dst16;
-	u32 *dst32;
-	unsigned int x, y;
-	void *buf = NULL;
-
-	if (WARN_ON_ONCE(cpp != 2 && cpp != 4))
-		return;
-
-	if (!dst_pitch)
-		dst_pitch = len;
 
-	if (!cached)
-		buf = kmalloc(len, GFP_KERNEL);
-
-	src += clip_offset(clip, fb->pitches[0], cpp);
-
-	for (y = clip->y1; y < clip->y2; y++) {
-		if (buf) {
-			memcpy(buf, src, len);
-			src16 = buf;
-			src32 = buf;
-		} else {
-			src16 = src;
-			src32 = src;
-		}
-
-		dst16 = dst;
-		dst32 = dst;
-
-		for (x = clip->x1; x < clip->x2; x++) {
-			if (cpp == 4)
-				*dst32++ = swab32(*src32++);
-			else
-				*dst16++ = swab16(*src16++);
-		}
-
-		src += fb->pitches[0];
-		dst += dst_pitch;
+	switch (cpp) {
+	case 4:
+		drm_fb_xfrm(dst, dst_pitch, cpp, src, fb, clip, cached, drm_fb_swab32_line);
+		break;
+	case 2:
+		drm_fb_xfrm(dst, dst_pitch, cpp, src, fb, clip, cached, drm_fb_swab16_line);
+		break;
+	default:
+		drm_warn_once(fb->dev, "Format %p4cc has unsupported pixel size.\n",
+			      &fb->format->format);
+		break;
 	}
-
-	kfree(buf);
 }
 EXPORT_SYMBOL(drm_fb_swab);
 
-static void drm_fb_xrgb8888_to_rgb332_line(u8 *dbuf, const __le32 *sbuf, unsigned int pixels)
+static void drm_fb_xrgb8888_to_rgb332_line(void *dbuf, const void *sbuf, unsigned int pixels)
 {
+	u8 *dbuf8 = dbuf;
+	const __le32 *sbuf32 = sbuf;
 	unsigned int x;
 	u32 pix;
 
 	for (x = 0; x < pixels; x++) {
-		pix = le32_to_cpu(sbuf[x]);
-		dbuf[x] = ((pix & 0x00e00000) >> 16) |
-			  ((pix & 0x0000e000) >> 11) |
-			  ((pix & 0x000000c0) >> 6);
+		pix = le32_to_cpu(sbuf32[x]);
+		dbuf8[x] = ((pix & 0x00e00000) >> 16) |
+			   ((pix & 0x0000e000) >> 11) |
+			   ((pix & 0x000000c0) >> 6);
 	}
 }
 
@@ -193,46 +272,38 @@ static void drm_fb_xrgb8888_to_rgb332_line(u8 *dbuf, const __le32 *sbuf, unsigne
 void drm_fb_xrgb8888_to_rgb332(void *dst, unsigned int dst_pitch, const void *src,
 			       const struct drm_framebuffer *fb, const struct drm_rect *clip)
 {
-	size_t width = drm_rect_width(clip);
-	size_t src_len = width * sizeof(u32);
-	unsigned int y;
-	void *sbuf;
-
-	if (!dst_pitch)
-		dst_pitch = width;
+	drm_fb_xfrm(dst, dst_pitch, 1, src, fb, clip, false, drm_fb_xrgb8888_to_rgb332_line);
+}
+EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb332);
 
-	/* Use a buffer to speed up access on buffers with uncached read mapping (i.e. WC) */
-	sbuf = kmalloc(src_len, GFP_KERNEL);
-	if (!sbuf)
-		return;
+static void drm_fb_xrgb8888_to_rgb565_line(void *dbuf, const void *sbuf, unsigned int pixels)
+{
+	u16 *dbuf16 = dbuf;
+	const u32 *sbuf32 = sbuf;
+	unsigned int x;
+	u16 val16;
 
-	src += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = 0; y < drm_rect_height(clip); y++) {
-		memcpy(sbuf, src, src_len);
-		drm_fb_xrgb8888_to_rgb332_line(dst, sbuf, width);
-		src += fb->pitches[0];
-		dst += dst_pitch;
+	for (x = 0; x < pixels; x++) {
+		val16 = ((sbuf32[x] & 0x00F80000) >> 8) |
+			((sbuf32[x] & 0x0000FC00) >> 5) |
+			((sbuf32[x] & 0x000000F8) >> 3);
+		dbuf16[x] = val16;
 	}
-
-	kfree(sbuf);
 }
-EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb332);
 
-static void drm_fb_xrgb8888_to_rgb565_line(u16 *dbuf, const u32 *sbuf,
-					   unsigned int pixels,
-					   bool swab)
+static void drm_fb_xrgb8888_to_rgb565_swab_line(void *dbuf, const void *sbuf,
+						unsigned int pixels)
 {
+	u16 *dbuf16 = dbuf;
+	const u32 *sbuf32 = sbuf;
 	unsigned int x;
 	u16 val16;
 
 	for (x = 0; x < pixels; x++) {
-		val16 = ((sbuf[x] & 0x00F80000) >> 8) |
-			((sbuf[x] & 0x0000FC00) >> 5) |
-			((sbuf[x] & 0x000000F8) >> 3);
-		if (swab)
-			dbuf[x] = swab16(val16);
-		else
-			dbuf[x] = val16;
+		val16 = ((sbuf32[x] & 0x00F80000) >> 8) |
+			((sbuf32[x] & 0x0000FC00) >> 5) |
+			((sbuf32[x] & 0x000000F8) >> 3);
+		dbuf16[x] = swab16(val16);
 	}
 }
 
@@ -252,32 +323,12 @@ void drm_fb_xrgb8888_to_rgb565(void *dst, unsigned int dst_pitch, const void *va
 			       const struct drm_framebuffer *fb, const struct drm_rect *clip,
 			       bool swab)
 {
-	size_t linepixels = clip->x2 - clip->x1;
-	size_t src_len = linepixels * sizeof(u32);
-	size_t dst_len = linepixels * sizeof(u16);
-	unsigned y, lines = clip->y2 - clip->y1;
-	void *sbuf;
-
-	if (!dst_pitch)
-		dst_pitch = dst_len;
-
-	/*
-	 * The cma memory is write-combined so reads are uncached.
-	 * Speed up by fetching one line at a time.
-	 */
-	sbuf = kmalloc(src_len, GFP_KERNEL);
-	if (!sbuf)
-		return;
-
-	vaddr += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = 0; y < lines; y++) {
-		memcpy(sbuf, vaddr, src_len);
-		drm_fb_xrgb8888_to_rgb565_line(dst, sbuf, linepixels, swab);
-		vaddr += fb->pitches[0];
-		dst += dst_pitch;
-	}
-
-	kfree(sbuf);
+	if (swab)
+		drm_fb_xfrm(dst, dst_pitch, 2, vaddr, fb, clip, false,
+			    drm_fb_xrgb8888_to_rgb565_swab_line);
+	else
+		drm_fb_xfrm(dst, dst_pitch, 2, vaddr, fb, clip, false,
+			    drm_fb_xrgb8888_to_rgb565_line);
 }
 EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb565);
 
@@ -297,39 +348,25 @@ void drm_fb_xrgb8888_to_rgb565_toio(void __iomem *dst, unsigned int dst_pitch,
 				    const void *vaddr, const struct drm_framebuffer *fb,
 				    const struct drm_rect *clip, bool swab)
 {
-	size_t linepixels = clip->x2 - clip->x1;
-	size_t dst_len = linepixels * sizeof(u16);
-	unsigned y, lines = clip->y2 - clip->y1;
-	void *dbuf;
-
-	if (!dst_pitch)
-		dst_pitch = dst_len;
-
-	dbuf = kmalloc(dst_len, GFP_KERNEL);
-	if (!dbuf)
-		return;
-
-	vaddr += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = 0; y < lines; y++) {
-		drm_fb_xrgb8888_to_rgb565_line(dbuf, vaddr, linepixels, swab);
-		memcpy_toio(dst, dbuf, dst_len);
-		vaddr += fb->pitches[0];
-		dst += dst_pitch;
-	}
-
-	kfree(dbuf);
+	if (swab)
+		drm_fb_xfrm_toio(dst, dst_pitch, 2, vaddr, fb, clip, false,
+				 drm_fb_xrgb8888_to_rgb565_swab_line);
+	else
+		drm_fb_xfrm_toio(dst, dst_pitch, 2, vaddr, fb, clip, false,
+				 drm_fb_xrgb8888_to_rgb565_line);
 }
 EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb565_toio);
 
-static void drm_fb_xrgb8888_to_rgb888_line(u8 *dbuf, const u32 *sbuf,
-					   unsigned int pixels)
+static void drm_fb_xrgb8888_to_rgb888_line(void *dbuf, const void *sbuf, unsigned int pixels)
 {
+	u8 *dbuf8 = dbuf;
+	const u32 *sbuf32 = sbuf;
 	unsigned int x;
 
 	for (x = 0; x < pixels; x++) {
-		*dbuf++ = (sbuf[x] & 0x000000FF) >>  0;
-		*dbuf++ = (sbuf[x] & 0x0000FF00) >>  8;
-		*dbuf++ = (sbuf[x] & 0x00FF0000) >> 16;
+		*dbuf8++ = (sbuf32[x] & 0x000000FF) >>  0;
+		*dbuf8++ = (sbuf32[x] & 0x0000FF00) >>  8;
+		*dbuf8++ = (sbuf32[x] & 0x00FF0000) >> 16;
 	}
 }
 
@@ -347,28 +384,7 @@ static void drm_fb_xrgb8888_to_rgb888_line(u8 *dbuf, const u32 *sbuf,
 void drm_fb_xrgb8888_to_rgb888(void *dst, unsigned int dst_pitch, const void *src,
 			       const struct drm_framebuffer *fb, const struct drm_rect *clip)
 {
-	size_t width = drm_rect_width(clip);
-	size_t src_len = width * sizeof(u32);
-	unsigned int y;
-	void *sbuf;
-
-	if (!dst_pitch)
-		dst_pitch = width * 3;
-
-	/* Use a buffer to speed up access on buffers with uncached read mapping (i.e. WC) */
-	sbuf = kmalloc(src_len, GFP_KERNEL);
-	if (!sbuf)
-		return;
-
-	src += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = 0; y < drm_rect_height(clip); y++) {
-		memcpy(sbuf, src, src_len);
-		drm_fb_xrgb8888_to_rgb888_line(dst, sbuf, width);
-		src += fb->pitches[0];
-		dst += dst_pitch;
-	}
-
-	kfree(sbuf);
+	drm_fb_xfrm(dst, dst_pitch, 3, src, fb, clip, false, drm_fb_xrgb8888_to_rgb888_line);
 }
 EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888);
 
@@ -387,41 +403,69 @@ void drm_fb_xrgb8888_to_rgb888_toio(void __iomem *dst, unsigned int dst_pitch,
 				    const void *vaddr, const struct drm_framebuffer *fb,
 				    const struct drm_rect *clip)
 {
-	size_t linepixels = clip->x2 - clip->x1;
-	size_t dst_len = linepixels * 3;
-	unsigned y, lines = clip->y2 - clip->y1;
-	void *dbuf;
+	drm_fb_xfrm_toio(dst, dst_pitch, 3, vaddr, fb, clip, false,
+			 drm_fb_xrgb8888_to_rgb888_line);
+}
+EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888_toio);
 
-	if (!dst_pitch)
-		dst_pitch = dst_len;
+static void drm_fb_rgb565_to_xrgb8888_line(void *dbuf, const void *sbuf, unsigned int pixels)
+{
+	u32 *dbuf32 = dbuf;
+	const u16 *sbuf16 = sbuf;
+	unsigned int x;
 
-	dbuf = kmalloc(dst_len, GFP_KERNEL);
-	if (!dbuf)
-		return;
+	for (x = 0; x < pixels; x++, ++sbuf16, ++dbuf32) {
+		u32 val32 = ((*sbuf16 & 0xf800) << 8) |
+			    ((*sbuf16 & 0x07e0) << 5) |
+			    ((*sbuf16 & 0x001f) << 3);
+		*dbuf32 = 0xff000000 | val32 |
+			  ((val32 >> 3) & 0x00070007) |
+			  ((val32 >> 2) & 0x00000300);
+	}
+}
 
-	vaddr += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = 0; y < lines; y++) {
-		drm_fb_xrgb8888_to_rgb888_line(dbuf, vaddr, linepixels);
-		memcpy_toio(dst, dbuf, dst_len);
-		vaddr += fb->pitches[0];
-		dst += dst_pitch;
+static void drm_fb_rgb565_to_xrgb8888_toio(void __iomem *dst, unsigned int dst_pitch,
+					   const void *vaddr, const struct drm_framebuffer *fb,
+					   const struct drm_rect *clip)
+{
+	drm_fb_xfrm_toio(dst, dst_pitch, 4, vaddr, fb, clip, false,
+			 drm_fb_rgb565_to_xrgb8888_line);
+}
+
+static void drm_fb_rgb888_to_xrgb8888_line(void *dbuf, const void *sbuf, unsigned int pixels)
+{
+	u32 *dbuf32 = dbuf;
+	const u8 *sbuf8 = sbuf;
+	unsigned int x;
+
+	for (x = 0; x < pixels; x++) {
+		u8 r = *sbuf8++;
+		u8 g = *sbuf8++;
+		u8 b = *sbuf8++;
+		*dbuf32++ = 0xff000000 | (r << 16) | (g << 8) | b;
 	}
+}
 
-	kfree(dbuf);
+static void drm_fb_rgb888_to_xrgb8888_toio(void __iomem *dst, unsigned int dst_pitch,
+					   const void *vaddr, const struct drm_framebuffer *fb,
+					   const struct drm_rect *clip)
+{
+	drm_fb_xfrm_toio(dst, dst_pitch, 4, vaddr, fb, clip, false,
+			 drm_fb_rgb888_to_xrgb8888_line);
 }
-EXPORT_SYMBOL(drm_fb_xrgb8888_to_rgb888_toio);
 
-static void drm_fb_xrgb8888_to_xrgb2101010_line(u32 *dbuf, const u32 *sbuf,
-						unsigned int pixels)
+static void drm_fb_xrgb8888_to_xrgb2101010_line(void *dbuf, const void *sbuf, unsigned int pixels)
 {
+	u32 *dbuf32 = dbuf;
+	const u32 *sbuf32 = sbuf;
 	unsigned int x;
 	u32 val32;
 
 	for (x = 0; x < pixels; x++) {
-		val32 = ((sbuf[x] & 0x000000FF) << 2) |
-			((sbuf[x] & 0x0000FF00) << 4) |
-			((sbuf[x] & 0x00FF0000) << 6);
-		*dbuf++ = val32 | ((val32 >> 8) & 0x00300C03);
+		val32 = ((sbuf32[x] & 0x000000FF) << 2) |
+			((sbuf32[x] & 0x0000FF00) << 4) |
+			((sbuf32[x] & 0x00FF0000) << 6);
+		*dbuf32++ = val32 | ((val32 >> 8) & 0x00300C03);
 	}
 }
 
@@ -442,42 +486,25 @@ void drm_fb_xrgb8888_to_xrgb2101010_toio(void __iomem *dst,
 					 const struct drm_framebuffer *fb,
 					 const struct drm_rect *clip)
 {
-	size_t linepixels = clip->x2 - clip->x1;
-	size_t dst_len = linepixels * sizeof(u32);
-	unsigned int y, lines = clip->y2 - clip->y1;
-	void *dbuf;
-
-	if (!dst_pitch)
-		dst_pitch = dst_len;
-
-	dbuf = kmalloc(dst_len, GFP_KERNEL);
-	if (!dbuf)
-		return;
-
-	vaddr += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = 0; y < lines; y++) {
-		drm_fb_xrgb8888_to_xrgb2101010_line(dbuf, vaddr, linepixels);
-		memcpy_toio(dst, dbuf, dst_len);
-		vaddr += fb->pitches[0];
-		dst += dst_pitch;
-	}
-
-	kfree(dbuf);
+	drm_fb_xfrm_toio(dst, dst_pitch, 4, vaddr, fb, clip, false,
+			 drm_fb_xrgb8888_to_xrgb2101010_line);
 }
 EXPORT_SYMBOL(drm_fb_xrgb8888_to_xrgb2101010_toio);
 
-static void drm_fb_xrgb8888_to_gray8_line(u8 *dst, const u32 *src, unsigned int pixels)
+static void drm_fb_xrgb8888_to_gray8_line(void *dbuf, const void *sbuf, unsigned int pixels)
 {
+	u8 *dbuf8 = dbuf;
+	const u32 *sbuf32 = sbuf;
 	unsigned int x;
 
 	for (x = 0; x < pixels; x++) {
-		u8 r = (*src & 0x00ff0000) >> 16;
-		u8 g = (*src & 0x0000ff00) >> 8;
-		u8 b =  *src & 0x000000ff;
+		u8 r = (*sbuf32 & 0x00ff0000) >> 16;
+		u8 g = (*sbuf32 & 0x0000ff00) >> 8;
+		u8 b =  *sbuf32 & 0x000000ff;
 
 		/* ITU BT.601: Y = 0.299 R + 0.587 G + 0.114 B */
-		*dst++ = (3 * r + 6 * g + b) / 10;
-		src++;
+		*dbuf8++ = (3 * r + 6 * g + b) / 10;
+		sbuf32++;
 	}
 }
 
@@ -501,37 +528,7 @@ static void drm_fb_xrgb8888_to_gray8_line(u8 *dst, const u32 *src, unsigned int
 void drm_fb_xrgb8888_to_gray8(void *dst, unsigned int dst_pitch, const void *vaddr,
 			      const struct drm_framebuffer *fb, const struct drm_rect *clip)
 {
-	unsigned int linepixels = clip->x2 - clip->x1;
-	unsigned int len = linepixels * sizeof(u32);
-	unsigned int y;
-	void *buf;
-	u8 *dst8;
-	u32 *src32;
-
-	if (WARN_ON(fb->format->format != DRM_FORMAT_XRGB8888))
-		return;
-
-	if (!dst_pitch)
-		dst_pitch = drm_rect_width(clip);
-
-	/*
-	 * The cma memory is write-combined so reads are uncached.
-	 * Speed up by fetching one line at a time.
-	 */
-	buf = kmalloc(len, GFP_KERNEL);
-	if (!buf)
-		return;
-
-	vaddr += clip_offset(clip, fb->pitches[0], sizeof(u32));
-	for (y = clip->y1; y < clip->y2; y++) {
-		dst8 = dst;
-		src32 = memcpy(buf, vaddr, len);
-		drm_fb_xrgb8888_to_gray8_line(dst8, src32, linepixels);
-		vaddr += fb->pitches[0];
-		dst += dst_pitch;
-	}
-
-	kfree(buf);
+	drm_fb_xfrm(dst, dst_pitch, 1, vaddr, fb, clip, false, drm_fb_xrgb8888_to_gray8_line);
 }
 EXPORT_SYMBOL(drm_fb_xrgb8888_to_gray8);
 
@@ -583,6 +580,14 @@ int drm_fb_blit_toio(void __iomem *dst, unsigned int dst_pitch, uint32_t dst_for
 			drm_fb_xrgb8888_to_rgb888_toio(dst, dst_pitch, vmap, fb, clip);
 			return 0;
 		}
+	} else if (dst_format == DRM_FORMAT_XRGB8888) {
+		if (fb_format == DRM_FORMAT_RGB888) {
+			drm_fb_rgb888_to_xrgb8888_toio(dst, dst_pitch, vmap, fb, clip);
+			return 0;
+		} else if (fb_format == DRM_FORMAT_RGB565) {
+			drm_fb_rgb565_to_xrgb8888_toio(dst, dst_pitch, vmap, fb, clip);
+			return 0;
+		}
 	} else if (dst_format == DRM_FORMAT_XRGB2101010) {
 		if (fb_format == DRM_FORMAT_XRGB8888) {
 			drm_fb_xrgb8888_to_xrgb2101010_toio(dst, dst_pitch, vmap, fb, clip);
@@ -590,41 +595,36 @@ int drm_fb_blit_toio(void __iomem *dst, unsigned int dst_pitch, uint32_t dst_for
 		}
 	}
 
+	drm_warn_once(fb->dev, "No conversion helper from %p4cc to %p4cc found.\n",
+		      &fb_format, &dst_format);
+
 	return -EINVAL;
 }
 EXPORT_SYMBOL(drm_fb_blit_toio);
 
-static void drm_fb_gray8_to_mono_reversed_line(u8 *dst, const u8 *src, unsigned int pixels,
-					       unsigned int start_offset, unsigned int end_len)
-{
-	unsigned int xb, i;
-
-	for (xb = 0; xb < pixels; xb++) {
-		unsigned int start = 0, end = 8;
-		u8 byte = 0x00;
-
-		if (xb == 0 && start_offset)
-			start = start_offset;
 
-		if (xb == pixels - 1 && end_len)
-			end = end_len;
+static void drm_fb_gray8_to_mono_line(void *dbuf, const void *sbuf, unsigned int pixels)
+{
+	u8 *dbuf8 = dbuf;
+	const u8 *sbuf8 = sbuf;
 
-		for (i = start; i < end; i++) {
-			unsigned int x = xb * 8 + i;
+	while (pixels) {
+		unsigned int i, bits = min(pixels, 8U);
+		u8 byte = 0;
 
-			byte >>= 1;
-			if (src[x] >> 7)
-				byte |= BIT(7);
+		for (i = 0; i < bits; i++, pixels--) {
+			if (*sbuf8++ >= 128)
+				byte |= BIT(i);
 		}
-		*dst++ = byte;
+		*dbuf8++ = byte;
 	}
 }
 
 /**
- * drm_fb_xrgb8888_to_mono_reversed - Convert XRGB8888 to reversed monochrome
- * @dst: reversed monochrome destination buffer
+ * drm_fb_xrgb8888_to_mono - Convert XRGB8888 to monochrome
+ * @dst: monochrome destination buffer (0=black, 1=white)
  * @dst_pitch: Number of bytes between two consecutive scanlines within dst
- * @src: XRGB8888 source buffer
+ * @vaddr: XRGB8888 source buffer
  * @fb: DRM framebuffer
  * @clip: Clip rectangle area to copy
  *
@@ -633,17 +633,23 @@ static void drm_fb_gray8_to_mono_reversed_line(u8 *dst, const u8 *src, unsigned
  * and use this function to convert to the native format.
  *
  * This function uses drm_fb_xrgb8888_to_gray8() to convert to grayscale and
- * then the result is converted from grayscale to reversed monohrome.
+ * then the result is converted from grayscale to monochrome.
+ *
+ * The first pixel (upper left corner of the clip rectangle) will be converted
+ * and copied to the first bit (LSB) in the first byte of the monochrome
+ * destination buffer.
+ * If the caller requires that the first pixel in a byte must be located at an
+ * x-coordinate that is a multiple of 8, then the caller must take care itself
+ * of supplying a suitable clip rectangle.
  */
-void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const void *vaddr,
-				      const struct drm_framebuffer *fb, const struct drm_rect *clip)
+void drm_fb_xrgb8888_to_mono(void *dst, unsigned int dst_pitch, const void *vaddr,
+			     const struct drm_framebuffer *fb, const struct drm_rect *clip)
 {
 	unsigned int linepixels = drm_rect_width(clip);
-	unsigned int lines = clip->y2 - clip->y1;
+	unsigned int lines = drm_rect_height(clip);
 	unsigned int cpp = fb->format->cpp[0];
 	unsigned int len_src32 = linepixels * cpp;
 	struct drm_device *dev = fb->dev;
-	unsigned int start_offset, end_len;
 	unsigned int y;
 	u8 *mono = dst, *gray8;
 	u32 *src32;
@@ -652,21 +658,18 @@ void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const v
 		return;
 
 	/*
-	 * The reversed mono destination buffer contains 1 bit per pixel
-	 * and destination scanlines have to be in multiple of 8 pixels.
+	 * The mono destination buffer contains 1 bit per pixel
 	 */
 	if (!dst_pitch)
 		dst_pitch = DIV_ROUND_UP(linepixels, 8);
 
-	drm_WARN_ONCE(dev, dst_pitch % 8 != 0, "dst_pitch is not a multiple of 8\n");
-
 	/*
 	 * The cma memory is write-combined so reads are uncached.
 	 * Speed up by fetching one line at a time.
 	 *
-	 * Also, format conversion from XR24 to reversed monochrome
-	 * are done line-by-line but are converted to 8-bit grayscale
-	 * as an intermediate step.
+	 * Also, format conversion from XR24 to monochrome are done
+	 * line-by-line but are converted to 8-bit grayscale as an
+	 * intermediate step.
 	 *
 	 * Allocate a buffer to be used for both copying from the cma
 	 * memory and to store the intermediate grayscale line pixels.
@@ -677,27 +680,15 @@ void drm_fb_xrgb8888_to_mono_reversed(void *dst, unsigned int dst_pitch, const v
 
 	gray8 = (u8 *)src32 + len_src32;
 
-	/*
-	 * For damage handling, it is possible that only parts of the source
-	 * buffer is copied and this could lead to start and end pixels that
-	 * are not aligned to multiple of 8.
-	 *
-	 * Calculate if the start and end pixels are not aligned and set the
-	 * offsets for the reversed mono line conversion function to adjust.
-	 */
-	start_offset = clip->x1 % 8;
-	end_len = clip->x2 % 8;
-
 	vaddr += clip_offset(clip, fb->pitches[0], cpp);
 	for (y = 0; y < lines; y++) {
 		src32 = memcpy(src32, vaddr, len_src32);
 		drm_fb_xrgb8888_to_gray8_line(gray8, src32, linepixels);
-		drm_fb_gray8_to_mono_reversed_line(mono, gray8, dst_pitch,
-						   start_offset, end_len);
+		drm_fb_gray8_to_mono_line(mono, gray8, linepixels);
 		vaddr += fb->pitches[0];
 		mono += dst_pitch;
 	}
 
 	kfree(src32);
 }
-EXPORT_SYMBOL(drm_fb_xrgb8888_to_mono_reversed);
+EXPORT_SYMBOL(drm_fb_xrgb8888_to_mono);