fbdev: c2p - Cleanups

- Improve comments and naming
  - Convert macros to static inline functions
  - Remove superfluous `break' after `return'
  - Make sure we get a build-time error (undefined reference to
    'c2p_unsupported') in case of future misuse
  - Replace `unsigned long' by `u32' in comp(), as that's what all callers use
  - Use {get,put}_unaligned_be32() in store_planar{,_masked}()
  - Use void * for arbitrary pointers
  - Use a union to represent pixels/words, to avoid casts

Signed-off-by: Geert Uytterhoeven <geert@linux-m68k.org>
This commit is contained in:
Geert Uytterhoeven 2009-01-04 11:43:00 +01:00
parent 8280eb8a33
commit 1f034456c1
2 changed files with 96 additions and 85 deletions

View File

@ -1,7 +1,7 @@
/*
* Fast C2P (Chunky-to-Planar) Conversion
*
* Copyright (C) 2003 Geert Uytterhoeven
* Copyright (C) 2003-2008 Geert Uytterhoeven
*
* NOTES:
* - This code was inspired by Scout's C2P tutorial
@ -14,6 +14,9 @@
#include <linux/module.h>
#include <linux/string.h>
#include <asm/unaligned.h>
#include "c2p.h"
@ -21,97 +24,100 @@
* Basic transpose step
*/
#define _transp(d, i1, i2, shift, mask) \
do { \
u32 t = (d[i1] ^ (d[i2] >> shift)) & mask; \
d[i1] ^= t; \
d[i2] ^= t << shift; \
} while (0)
static inline void _transp(u32 d[], unsigned int i1, unsigned int i2,
unsigned int shift, u32 mask)
{
u32 t = (d[i1] ^ (d[i2] >> shift)) & mask;
static inline u32 get_mask(int n)
d[i1] ^= t;
d[i2] ^= t << shift;
}
extern void c2p_unsupported(void);
static inline u32 get_mask(unsigned int n)
{
switch (n) {
case 1:
return 0x55555555;
break;
case 2:
return 0x33333333;
break;
case 4:
return 0x0f0f0f0f;
break;
case 8:
return 0x00ff00ff;
break;
case 16:
return 0x0000ffff;
break;
}
c2p_unsupported();
return 0;
}
#define transp_nx1(d, n) \
do { \
u32 mask = get_mask(n); \
/* First block */ \
_transp(d, 0, 1, n, mask); \
/* Second block */ \
_transp(d, 2, 3, n, mask); \
/* Third block */ \
_transp(d, 4, 5, n, mask); \
/* Fourth block */ \
_transp(d, 6, 7, n, mask); \
} while (0)
static inline void transp8(u32 d[], unsigned int n, unsigned int m)
{
u32 mask = get_mask(n);
#define transp_nx2(d, n) \
do { \
u32 mask = get_mask(n); \
/* First block */ \
_transp(d, 0, 2, n, mask); \
_transp(d, 1, 3, n, mask); \
/* Second block */ \
_transp(d, 4, 6, n, mask); \
_transp(d, 5, 7, n, mask); \
} while (0)
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);
/* Third n x 1 block */
_transp(d, 4, 5, n, mask);
/* Fourth n x 1 block */
_transp(d, 6, 7, n, mask);
return;
#define transp_nx4(d, n) \
do { \
u32 mask = get_mask(n); \
_transp(d, 0, 4, n, mask); \
_transp(d, 1, 5, n, mask); \
_transp(d, 2, 6, n, mask); \
_transp(d, 3, 7, n, mask); \
} while (0)
case 2:
/* First n x 2 block */
_transp(d, 0, 2, n, mask);
_transp(d, 1, 3, n, mask);
/* Second n x 2 block */
_transp(d, 4, 6, n, mask);
_transp(d, 5, 7, n, mask);
return;
#define transp(d, n, m) transp_nx ## m(d, n)
case 4:
/* Single n x 4 block */
_transp(d, 0, 4, n, mask);
_transp(d, 1, 5, n, mask);
_transp(d, 2, 6, n, mask);
_transp(d, 3, 7, n, mask);
return;
}
c2p_unsupported();
}
/*
* Perform a full C2P step on 32 8-bit pixels, stored in 8 32-bit words
* containing
* - 32 8-bit chunky pixels on input
* - permuted planar data on output
* - permutated planar data (1 plane per 32-bit word) on output
*/
static void c2p_8bpp(u32 d[8])
static void c2p_32x8(u32 d[8])
{
transp(d, 16, 4);
transp(d, 8, 2);
transp(d, 4, 1);
transp(d, 2, 4);
transp(d, 1, 2);
transp8(d, 16, 4);
transp8(d, 8, 2);
transp8(d, 4, 1);
transp8(d, 2, 4);
transp8(d, 1, 2);
}
/*
* Array containing the permution indices of the planar data after c2p
* Array containing the permutation indices of the planar data after c2p
*/
static const int perm_c2p_8bpp[8] = { 7, 5, 3, 1, 6, 4, 2, 0 };
static const int perm_c2p_32x8[8] = { 7, 5, 3, 1, 6, 4, 2, 0 };
/*
@ -119,8 +125,7 @@ static const int perm_c2p_8bpp[8] = { 7, 5, 3, 1, 6, 4, 2, 0 };
* This is equivalent to (a & mask) | (b & ~mask)
*/
static inline unsigned long comp(unsigned long a, unsigned long b,
unsigned long mask)
static inline u32 comp(u32 a, u32 b, u32 mask)
{
return ((a ^ b) & mask) ^ b;
}
@ -130,12 +135,12 @@ static inline unsigned long comp(unsigned long a, unsigned long b,
* Store a full block of planar data after c2p conversion
*/
static inline void store_planar(char *dst, u32 dst_inc, u32 bpp, u32 d[8])
static inline void store_planar(void *dst, u32 dst_inc, u32 bpp, u32 d[8])
{
int i;
for (i = 0; i < bpp; i++, dst += dst_inc)
*(u32 *)dst = d[perm_c2p_8bpp[i]];
put_unaligned_be32(d[perm_c2p_32x8[i]], dst);
}
@ -143,13 +148,15 @@ static inline void store_planar(char *dst, u32 dst_inc, u32 bpp, u32 d[8])
* Store a partial block of planar data after c2p conversion
*/
static inline void store_planar_masked(char *dst, u32 dst_inc, u32 bpp,
static inline void store_planar_masked(void *dst, u32 dst_inc, u32 bpp,
u32 d[8], u32 mask)
{
int i;
for (i = 0; i < bpp; i++, dst += dst_inc)
*(u32 *)dst = comp(d[perm_c2p_8bpp[i]], *(u32 *)dst, mask);
put_unaligned_be32(comp(d[perm_c2p_32x8[i]],
get_unaligned_be32(dst), mask),
dst);
}
@ -166,18 +173,21 @@ static inline void store_planar_masked(char *dst, u32 dst_inc, u32 bpp,
* @bpp: Bits per pixel of the planar frame buffer (1-8)
*/
void c2p(u8 *dst, const u8 *src, u32 dx, u32 dy, u32 width, u32 height,
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)
{
int dst_idx;
u32 d[8], first, last, w;
union {
u8 pixels[32];
u32 words[8];
} d;
u32 dst_idx, first, last, w;
const u8 *c;
u8 *p;
void *p;
dst += dy*dst_nextline+(dx & ~31);
dst_idx = dx % 32;
first = ~0UL >> dst_idx;
last = ~(~0UL >> ((dst_idx+width) % 32));
first = 0xffffffffU >> dst_idx;
last = ~(0xffffffffU >> ((dst_idx+width) % 32));
while (height--) {
c = src;
p = dst;
@ -185,11 +195,12 @@ void c2p(u8 *dst, const u8 *src, u32 dx, u32 dy, u32 width, u32 height,
if (dst_idx+width <= 32) {
/* Single destination word */
first &= last;
memset(d, 0, sizeof(d));
memcpy((u8 *)d+dst_idx, c, width);
memset(d.pixels, 0, sizeof(d));
memcpy(d.pixels+dst_idx, c, width);
c += width;
c2p_8bpp(d);
store_planar_masked(p, dst_nextplane, bpp, d, first);
c2p_32x8(d.words);
store_planar_masked(p, dst_nextplane, bpp, d.words,
first);
p += 4;
} else {
/* Multiple destination words */
@ -197,32 +208,32 @@ void c2p(u8 *dst, const u8 *src, u32 dx, u32 dy, u32 width, u32 height,
/* Leading bits */
if (dst_idx) {
w = 32 - dst_idx;
memset(d, 0, dst_idx);
memcpy((u8 *)d+dst_idx, c, w);
memset(d.pixels, 0, dst_idx);
memcpy(d.pixels+dst_idx, c, w);
c += w;
c2p_8bpp(d);
store_planar_masked(p, dst_nextplane, bpp, d,
first);
c2p_32x8(d.words);
store_planar_masked(p, dst_nextplane, bpp,
d.words, first);
p += 4;
w = width-w;
}
/* Main chunk */
while (w >= 32) {
memcpy(d, c, 32);
memcpy(d.pixels, c, 32);
c += 32;
c2p_8bpp(d);
store_planar(p, dst_nextplane, bpp, d);
c2p_32x8(d.words);
store_planar(p, dst_nextplane, bpp, d.words);
p += 4;
w -= 32;
}
/* Trailing bits */
w %= 32;
if (w > 0) {
memcpy(d, c, w);
memset((u8 *)d+w, 0, 32-w);
c2p_8bpp(d);
store_planar_masked(p, dst_nextplane, bpp, d,
last);
memcpy(d.pixels, c, w);
memset(d.pixels+w, 0, 32-w);
c2p_32x8(d.words);
store_planar_masked(p, dst_nextplane, bpp,
d.words, last);
}
}
src += src_nextline;

View File

@ -10,7 +10,7 @@
#include <linux/types.h>
extern void c2p(u8 *dst, const u8 *src, u32 dx, u32 dy, u32 width, u32 height,
u32 dst_nextline, u32 dst_nextplane, u32 src_nextline,
u32 bpp);
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);