fbdev: c2p/atafb - Add support for Atari interleaved bitplanes

The c2p() for normal bitplanes is not suitable for interleaved bitplanes with
2 bytes of interleave, causing a garbled penguin logo. Add c2p_iplan2().

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>

5 files changed, 208 insertions, 14 deletions

diff --git a/drivers/video/Makefile b/drivers/video/Makefile
index e39e33e797da..4fc29eae5152 100644
--- a/drivers/video/Makefile
+++ b/drivers/video/Makefile
@@ -72,7 +72,7 @@ obj-$(CONFIG_FB_TCX)              += tcx.o sbuslib.o
 obj-$(CONFIG_FB_LEO)              += leo.o sbuslib.o
 obj-$(CONFIG_FB_SGIVW)            += sgivwfb.o
 obj-$(CONFIG_FB_ACORN)            += acornfb.o
-obj-$(CONFIG_FB_ATARI)            += atafb.o c2p.o atafb_mfb.o \
+obj-$(CONFIG_FB_ATARI)            += atafb.o c2p_iplan2.o atafb_mfb.o \
                                      atafb_iplan2p2.o atafb_iplan2p4.o atafb_iplan2p8.o
 obj-$(CONFIG_FB_MAC)              += macfb.o
 obj-$(CONFIG_FB_HECUBA)           += hecubafb.o
diff --git a/drivers/video/atafb.c b/drivers/video/atafb.c
index f932c138fe1d..477ce55bbae9 100644
--- a/drivers/video/atafb.c
+++ b/drivers/video/atafb.c
@@ -122,7 +122,6 @@ static struct atafb_par {
         void *screen_base;
         int yres_virtual;
         u_long next_line;
-        u_long next_plane;
 #if defined ATAFB_TT || defined ATAFB_STE
         union {
                 struct {
@@ -1392,14 +1391,7 @@ set_screen_base:
         par->screen_base = screen_base + var->yoffset * linelen;
         par->hw.falcon.xoffset = 0;
 
-        // FIXME!!! sort of works, no crash
-        //par->next_line = linelen;
-        //par->next_plane = yres_virtual * linelen;
         par->next_line = linelen;
-        par->next_plane = 2;
-        // crashes
-        //par->next_plane = linelen;
-        //par->next_line  = yres_virtual * linelen;
 
         return 0;
 }
@@ -2662,10 +2654,9 @@ static void atafb_imageblit(struct fb_info *info, const struct fb_image *image)
                         src += pitch;
                 }
         } else {
-                // only used for logo; broken
-                c2p(info->screen_base, image->data, dx, dy, width, height,
-                    par->next_line, par->next_plane, image->width,
-                    info->var.bits_per_pixel);
+                c2p_iplan2(info->screen_base, image->data, dx, dy, width,
+                           height, par->next_line, image->width,
+                           info->var.bits_per_pixel);
         }
 }
 
diff --git a/drivers/video/c2p.h b/drivers/video/c2p.h
index daafd872601c..53641298b924 100644
--- a/drivers/video/c2p.h
+++ b/drivers/video/c2p.h
@@ -1,7 +1,7 @@
 /*
  *  Fast C2P (Chunky-to-Planar) Conversion
  *
- *  Copyright (C) 2003 Geert Uytterhoeven
+ *  Copyright (C) 2003-2008 Geert Uytterhoeven
  *
  *  This file is subject to the terms and conditions of the GNU General Public
  *  License. See the file COPYING in the main directory of this archive
@@ -14,3 +14,6 @@ extern void c2p(void *dst, const void *src, u32 dx, u32 dy, u32 width,
                 u32 height, u32 dst_nextline, u32 dst_nextplane,
                 u32 src_nextline, u32 bpp);
 
+extern void c2p_iplan2(void *dst, const void *src, u32 dx, u32 dy, u32 width,
+                       u32 height, u32 dst_nextline, u32 src_nextline,
+                       u32 bpp);
diff --git a/drivers/video/c2p_core.h b/drivers/video/c2p_core.h
index 3573cf723e43..e1035a865fb9 100644
--- a/drivers/video/c2p_core.h
+++ b/drivers/video/c2p_core.h
@@ -96,6 +96,53 @@ static inline void transp8(u32 d[], unsigned int n, unsigned int m)
 
 
     /*
+     *  Transpose operations on 4 32-bit words
+     */
+
+static inline void transp4(u32 d[], unsigned int n, unsigned int m)
+{
+        u32 mask = get_mask(n);
+
+        switch (m) {
+        case 1:
+                /* First n x 1 block */
+                _transp(d, 0, 1, n, mask);
+                /* Second n x 1 block */
+                _transp(d, 2, 3, n, mask);
+                return;
+
+        case 2:
+                /* Single n x 2 block */
+                _transp(d, 0, 2, n, mask);
+                _transp(d, 1, 3, n, mask);
+                return;
+        }
+
+        c2p_unsupported();
+}
+
+
+    /*
+     *  Transpose operations on 4 32-bit words (reverse order)
+     */
+
+static inline void transp4x(u32 d[], unsigned int n, unsigned int m)
+{
+        u32 mask = get_mask(n);
+
+        switch (m) {
+        case 2:
+                /* Single n x 2 block */
+                _transp(d, 2, 0, n, mask);
+                _transp(d, 3, 1, n, mask);
+                return;
+        }
+
+        c2p_unsupported();
+}
+
+
+    /*
      *  Compose two values, using a bitmask as decision value
      *  This is equivalent to (a & mask) | (b & ~mask)
      */
diff --git a/drivers/video/c2p_iplan2.c b/drivers/video/c2p_iplan2.c
new file mode 100644
index 000000000000..19156dc6158c
--- /dev/null
+++ b/drivers/video/c2p_iplan2.c
@@ -0,0 +1,153 @@
+/*
+ *  Fast C2P (Chunky-to-Planar) Conversion
+ *
+ *  Copyright (C) 2003-2008 Geert Uytterhoeven
+ *
+ *  This file is subject to the terms and conditions of the GNU General Public
+ *  License. See the file COPYING in the main directory of this archive
+ *  for more details.
+ */
+
+#include <linux/module.h>
+#include <linux/string.h>
+
+#include <asm/unaligned.h>
+
+#include "c2p.h"
+#include "c2p_core.h"
+
+
+    /*
+     *  Perform a full C2P step on 16 8-bit pixels, stored in 4 32-bit words
+     *  containing
+     *    - 16 8-bit chunky pixels on input
+     *    - permutated planar data (2 planes per 32-bit word) on output
+     */
+
+static void c2p_16x8(u32 d[4])
+{
+        transp4(d, 8, 2);
+        transp4(d, 1, 2);
+        transp4x(d, 16, 2);
+        transp4x(d, 2, 2);
+        transp4(d, 4, 1);
+}
+
+
+    /*
+     *  Array containing the permutation indices of the planar data after c2p
+     */
+
+static const int perm_c2p_16x8[4] = { 1, 3, 0, 2 };
+
+
+    /*
+     *  Store a full block of iplan2 data after c2p conversion
+     */
+
+static inline void store_iplan2(void *dst, u32 bpp, u32 d[4])
+{
+        int i;
+
+        for (i = 0; i < bpp/2; i++, dst += 4)
+                put_unaligned_be32(d[perm_c2p_16x8[i]], dst);
+}
+
+
+    /*
+     *  Store a partial block of iplan2 data after c2p conversion
+     */
+
+static inline void store_iplan2_masked(void *dst, u32 bpp, u32 d[4], u32 mask)
+{
+        int i;
+
+        for (i = 0; i < bpp/2; i++, dst += 4)
+                put_unaligned_be32(comp(d[perm_c2p_16x8[i]],
+                                        get_unaligned_be32(dst), mask),
+                                   dst);
+}
+
+
+    /*
+     *  c2p_iplan2 - Copy 8-bit chunky image data to an interleaved planar
+     *  frame buffer with 2 bytes of interleave
+     *  @dst: Starting address of the planar frame buffer
+     *  @dx: Horizontal destination offset (in pixels)
+     *  @dy: Vertical destination offset (in pixels)
+     *  @width: Image width (in pixels)
+     *  @height: Image height (in pixels)
+     *  @dst_nextline: Frame buffer offset to the next line (in bytes)
+     *  @src_nextline: Image offset to the next line (in bytes)
+     *  @bpp: Bits per pixel of the planar frame buffer (2, 4, or 8)
+     */
+
+void c2p_iplan2(void *dst, const void *src, u32 dx, u32 dy, u32 width,
+                u32 height, u32 dst_nextline, u32 src_nextline, u32 bpp)
+{
+        union {
+                u8 pixels[16];
+                u32 words[4];
+        } d;
+        u32 dst_idx, first, last, w;
+        const u8 *c;
+        void *p;
+
+        dst += dy*dst_nextline+(dx & ~15)*bpp;
+        dst_idx = dx % 16;
+        first = 0xffffU >> dst_idx;
+        first |= first << 16;
+        last = 0xffffU ^ (0xffffU >> ((dst_idx+width) % 16));
+        last |= last << 16;
+        while (height--) {
+                c = src;
+                p = dst;
+                w = width;
+                if (dst_idx+width <= 16) {
+                        /* Single destination word */
+                        first &= last;
+                        memset(d.pixels, 0, sizeof(d));
+                        memcpy(d.pixels+dst_idx, c, width);
+                        c += width;
+                        c2p_16x8(d.words);
+                        store_iplan2_masked(p, bpp, d.words, first);
+                        p += bpp*2;
+                } else {
+                        /* Multiple destination words */
+                        w = width;
+                        /* Leading bits */
+                        if (dst_idx) {
+                                w = 16 - dst_idx;
+                                memset(d.pixels, 0, dst_idx);
+                                memcpy(d.pixels+dst_idx, c, w);
+                                c += w;
+                                c2p_16x8(d.words);
+                                store_iplan2_masked(p, bpp, d.words, first);
+                                p += bpp*2;
+                                w = width-w;
+                        }
+                        /* Main chunk */
+                        while (w >= 16) {
+                                memcpy(d.pixels, c, 16);
+                                c += 16;
+                                c2p_16x8(d.words);
+                                store_iplan2(p, bpp, d.words);
+                                p += bpp*2;
+                                w -= 16;
+                        }
+                        /* Trailing bits */
+                        w %= 16;
+                        if (w > 0) {
+                                memcpy(d.pixels, c, w);
+                                memset(d.pixels+w, 0, 16-w);
+                                c2p_16x8(d.words);
+                                store_iplan2_masked(p, bpp, d.words, last);
+                        }
+                }
+                src += src_nextline;
+                dst += dst_nextline;
+        }
+}
+EXPORT_SYMBOL_GPL(c2p_iplan2);
+
+MODULE_LICENSE("GPL");