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:
parent
8280eb8a33
commit
1f034456c1
|
@ -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;
|
||||
|
|
|
@ -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);
|
||||
|
||||
|
|
Loading…
Reference in New Issue