Merge tag 'drm-misc-next-2022-03-03' of git://anongit.freedesktop.org/drm/drm-misc into drm-next

drm-misc-next for v5.18:

UAPI Changes:

Cross-subsystem Changes:
- Improve performance of some fbdev ops, in some cases up to 6x faster.

Core Changes:
- Some small DP fixes.
- Find panels in subnodes of OF devices, and add of_get_drm_panel_display_mode
  to retrieve mode.
- Add drm_object_property_get_default_value and use it for resetting
  zpos in plane state reset, removing the need for individual drivers
  to do it.
- Same for color encoding and color range props.
- Update panic handling todo doc.
- Add todo that format conversion helpers should be sped up similarly to fbdev ops.

Driver Changes:
- Add panel orientation property to simpledrm for quirked panels.
- Assorted small fixes to tiny/repaper, nouveau, stm, omap, ssd130x.
- Add crc support to stm/ltdc.
- Add MIPI DBI compatible SPI driver
- Assorted small fixes to tiny panels and bridge drivers.
- Add AST2600 support to aspeed.

Signed-off-by: Dave Airlie <airlied@redhat.com>

From: Maarten Lankhorst <maarten.lankhorst@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/48fabd78-ade9-f80b-c724-13726c7be69e@linux.intel.com

3 files changed, 111 insertions, 61 deletions

diff --git a/drivers/video/fbdev/core/cfbimgblt.c b/drivers/video/fbdev/core/cfbimgblt.c
index a2bb276a8b24..7361cfabdd85 100644
--- a/drivers/video/fbdev/core/cfbimgblt.c
+++ b/drivers/video/fbdev/core/cfbimgblt.c
@@ -16,15 +16,15 @@
  *  must be laid out exactly in the same format as the framebuffer. Yes I know
  *  their are cards with hardware that coverts images of various depths to the
  *  framebuffer depth. But not every card has this. All images must be rounded
- *  up to the nearest byte. For example a bitmap 12 bits wide must be two 
- *  bytes width. 
+ *  up to the nearest byte. For example a bitmap 12 bits wide must be two
+ *  bytes width.
  *
- *  Tony: 
- *  Incorporate mask tables similar to fbcon-cfb*.c in 2.4 API.  This speeds 
+ *  Tony:
+ *  Incorporate mask tables similar to fbcon-cfb*.c in 2.4 API.  This speeds
  *  up the code significantly.
- *  
+ *
  *  Code for depths not multiples of BITS_PER_LONG is still kludgy, which is
- *  still processed a bit at a time.   
+ *  still processed a bit at a time.
  *
  *  Also need to add code to deal with cards endians that are different than
  *  the native cpu endians. I also need to deal with MSB position in the word.
@@ -72,8 +72,8 @@ static const u32 cfb_tab32[] = {
 #define FB_WRITEL fb_writel
 #define FB_READL  fb_readl
 
-static inline void color_imageblit(const struct fb_image *image, 
-				   struct fb_info *p, u8 __iomem *dst1, 
+static inline void color_imageblit(const struct fb_image *image,
+				   struct fb_info *p, u8 __iomem *dst1,
 				   u32 start_index,
 				   u32 pitch_index)
 {
@@ -92,7 +92,7 @@ static inline void color_imageblit(const struct fb_image *image,
 		dst = (u32 __iomem *) dst1;
 		shift = 0;
 		val = 0;
-		
+
 		if (start_index) {
 			u32 start_mask = ~fb_shifted_pixels_mask_u32(p,
 						start_index, bswapmask);
@@ -109,8 +109,8 @@ static inline void color_imageblit(const struct fb_image *image,
 			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
 			if (shift >= null_bits) {
 				FB_WRITEL(val, dst++);
-	
-				val = (shift == null_bits) ? 0 : 
+
+				val = (shift == null_bits) ? 0 :
 					FB_SHIFT_LOW(p, color, 32 - shift);
 			}
 			shift += bpp;
@@ -134,9 +134,9 @@ static inline void color_imageblit(const struct fb_image *image,
 	}
 }
 
-static inline void slow_imageblit(const struct fb_image *image, struct fb_info *p, 
+static inline void slow_imageblit(const struct fb_image *image, struct fb_info *p,
 				  u8 __iomem *dst1, u32 fgcolor,
-				  u32 bgcolor, 
+				  u32 bgcolor,
 				  u32 start_index,
 				  u32 pitch_index)
 {
@@ -172,7 +172,7 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 			l--;
 			color = (*s & (1 << l)) ? fgcolor : bgcolor;
 			val |= FB_SHIFT_HIGH(p, color, shift ^ bswapmask);
-			
+
 			/* Did the bitshift spill bits to the next long? */
 			if (shift >= null_bits) {
 				FB_WRITEL(val, dst++);
@@ -191,16 +191,16 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
 
 			FB_WRITEL((FB_READL(dst) & end_mask) | val, dst);
 		}
-		
+
 		dst1 += pitch;
-		src += spitch;	
+		src += spitch;
 		if (pitch_index) {
 			dst2 += pitch;
 			dst1 = (u8 __iomem *)((long __force)dst2 & ~(sizeof(u32) - 1));
 			start_index += pitch_index;
 			start_index &= 32 - 1;
 		}
-		
+
 	}
 }
 
@@ -212,29 +212,35 @@ static inline void slow_imageblit(const struct fb_image *image, struct fb_info *
  *           fix->line_legth is divisible by 4;
  *           beginning and end of a scanline is dword aligned
  */
-static inline void fast_imageblit(const struct fb_image *image, struct fb_info *p, 
-				  u8 __iomem *dst1, u32 fgcolor, 
-				  u32 bgcolor) 
+static inline void fast_imageblit(const struct fb_image *image, struct fb_info *p,
+				  u8 __iomem *dst1, u32 fgcolor,
+				  u32 bgcolor)
 {
 	u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
 	u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
-	u32 bit_mask, end_mask, eorx, shift;
+	u32 bit_mask, eorx;
 	const char *s = image->data, *src;
 	u32 __iomem *dst;
 	const u32 *tab = NULL;
+	size_t tablen;
+	u32 colortab[16];
 	int i, j, k;
 
 	switch (bpp) {
 	case 8:
 		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
+		tablen = 16;
 		break;
 	case 16:
 		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
+		tablen = 4;
 		break;
 	case 32:
-	default:
 		tab = cfb_tab32;
+		tablen = 2;
 		break;
+	default:
+		return;
 	}
 
 	for (i = ppw-1; i--; ) {
@@ -243,25 +249,52 @@ static inline void fast_imageblit(const struct fb_image *image, struct fb_info *
 		fgx |= fgcolor;
 		bgx |= bgcolor;
 	}
-	
+
 	bit_mask = (1 << ppw) - 1;
 	eorx = fgx ^ bgx;
 	k = image->width/ppw;
 
+	for (i = 0; i < tablen; ++i)
+		colortab[i] = (tab[i] & eorx) ^ bgx;
+
 	for (i = image->height; i--; ) {
-		dst = (u32 __iomem *) dst1, shift = 8; src = s;
-		
-		for (j = k; j--; ) {
-			shift -= ppw;
-			end_mask = tab[(*src >> shift) & bit_mask];
-			FB_WRITEL((end_mask & eorx)^bgx, dst++);
-			if (!shift) { shift = 8; src++; }		
+		dst = (u32 __iomem *)dst1;
+		src = s;
+
+		switch (ppw) {
+		case 4: /* 8 bpp */
+			for (j = k; j; j -= 2, ++src) {
+				FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
+			}
+			break;
+		case 2: /* 16 bpp */
+			for (j = k; j; j -= 4, ++src) {
+				FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
+			}
+			break;
+		case 1: /* 32 bpp */
+			for (j = k; j; j -= 8, ++src) {
+				FB_WRITEL(colortab[(*src >> 7) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 6) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 5) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 4) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 3) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 2) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 1) & bit_mask], dst++);
+				FB_WRITEL(colortab[(*src >> 0) & bit_mask], dst++);
+			}
+			break;
 		}
+
 		dst1 += p->fix.line_length;
 		s += spitch;
 	}
-}	
-	
+}
+
 void cfb_imageblit(struct fb_info *p, const struct fb_image *image)
 {
 	u32 fgcolor, bgcolor, start_index, bitstart, pitch_index = 0;
@@ -292,13 +325,13 @@ void cfb_imageblit(struct fb_info *p, const struct fb_image *image)
 		} else {
 			fgcolor = image->fg_color;
 			bgcolor = image->bg_color;
-		}	
-		
-		if (32 % bpp == 0 && !start_index && !pitch_index && 
+		}
+
+		if (32 % bpp == 0 && !start_index && !pitch_index &&
 		    ((width & (32/bpp-1)) == 0) &&
-		    bpp >= 8 && bpp <= 32) 			
+		    bpp >= 8 && bpp <= 32)
 			fast_imageblit(image, p, dst1, fgcolor, bgcolor);
-		else 
+		else
 			slow_imageblit(image, p, dst1, fgcolor, bgcolor,
 					start_index, pitch_index);
 	} else
diff --git a/drivers/video/fbdev/core/sysfillrect.c b/drivers/video/fbdev/core/sysfillrect.c
index 33ee3d34f9d2..bcdcaeae6538 100644
--- a/drivers/video/fbdev/core/sysfillrect.c
+++ b/drivers/video/fbdev/core/sysfillrect.c
@@ -50,19 +50,9 @@ bitfill_aligned(struct fb_info *p, unsigned long *dst, int dst_idx,
 
 		/* Main chunk */
 		n /= bits;
-		while (n >= 8) {
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			*dst++ = pat;
-			n -= 8;
-		}
-		while (n--)
-			*dst++ = pat;
+		memset_l(dst, pat, n);
+		dst += n;
+
 		/* Trailing bits */
 		if (last)
 			*dst = comp(pat, *dst, last);
diff --git a/drivers/video/fbdev/core/sysimgblt.c b/drivers/video/fbdev/core/sysimgblt.c
index a4d05b1b17d7..722c327a381b 100644
--- a/drivers/video/fbdev/core/sysimgblt.c
+++ b/drivers/video/fbdev/core/sysimgblt.c
@@ -188,23 +188,29 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 {
 	u32 fgx = fgcolor, bgx = bgcolor, bpp = p->var.bits_per_pixel;
 	u32 ppw = 32/bpp, spitch = (image->width + 7)/8;
-	u32 bit_mask, end_mask, eorx, shift;
+	u32 bit_mask, eorx;
 	const char *s = image->data, *src;
 	u32 *dst;
-	const u32 *tab = NULL;
+	const u32 *tab;
+	size_t tablen;
+	u32 colortab[16];
 	int i, j, k;
 
 	switch (bpp) {
 	case 8:
 		tab = fb_be_math(p) ? cfb_tab8_be : cfb_tab8_le;
+		tablen = 16;
 		break;
 	case 16:
 		tab = fb_be_math(p) ? cfb_tab16_be : cfb_tab16_le;
+		tablen = 4;
 		break;
 	case 32:
-	default:
 		tab = cfb_tab32;
+		tablen = 2;
 		break;
+	default:
+		return;
 	}
 
 	for (i = ppw-1; i--; ) {
@@ -218,19 +224,40 @@ static void fast_imageblit(const struct fb_image *image, struct fb_info *p,
 	eorx = fgx ^ bgx;
 	k = image->width/ppw;
 
+	for (i = 0; i < tablen; ++i)
+		colortab[i] = (tab[i] & eorx) ^ bgx;
+
 	for (i = image->height; i--; ) {
 		dst = dst1;
-		shift = 8;
 		src = s;
 
-		for (j = k; j--; ) {
-			shift -= ppw;
-			end_mask = tab[(*src >> shift) & bit_mask];
-			*dst++ = (end_mask & eorx) ^ bgx;
-			if (!shift) {
-				shift = 8;
-				src++;
+		switch (ppw) {
+		case 4: /* 8 bpp */
+			for (j = k; j; j -= 2, ++src) {
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
+			}
+			break;
+		case 2: /* 16 bpp */
+			for (j = k; j; j -= 4, ++src) {
+				*dst++ = colortab[(*src >> 6) & bit_mask];
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 2) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
+			}
+			break;
+		case 1: /* 32 bpp */
+			for (j = k; j; j -= 8, ++src) {
+				*dst++ = colortab[(*src >> 7) & bit_mask];
+				*dst++ = colortab[(*src >> 6) & bit_mask];
+				*dst++ = colortab[(*src >> 5) & bit_mask];
+				*dst++ = colortab[(*src >> 4) & bit_mask];
+				*dst++ = colortab[(*src >> 3) & bit_mask];
+				*dst++ = colortab[(*src >> 2) & bit_mask];
+				*dst++ = colortab[(*src >> 1) & bit_mask];
+				*dst++ = colortab[(*src >> 0) & bit_mask];
 			}
+			break;
 		}
 		dst1 += p->fix.line_length;
 		s += spitch;