* 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)
+#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 u32 get_mask(int n)
{
- switch (n) {
+ switch (n) {
case 1:
- return 0x55555555;
- break;
+ return 0x55555555;
+ break;
case 2:
- return 0x33333333;
- break;
+ return 0x33333333;
+ break;
case 4:
- return 0x0f0f0f0f;
- break;
+ return 0x0f0f0f0f;
+ break;
case 8:
- return 0x00ff00ff;
- break;
+ return 0x00ff00ff;
+ break;
case 16:
- return 0x0000ffff;
- break;
- }
- return 0;
+ return 0x0000ffff;
+ break;
+ }
+ 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)
-
-#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)
-
-#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)
+#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)
+
+#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)
+
+#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)
#define transp(d, n, m) transp_nx ## m(d, n)
static void c2p_8bpp(u32 d[8])
{
- transp(d, 16, 4);
- transp(d, 8, 2);
- transp(d, 4, 1);
- transp(d, 2, 4);
- transp(d, 1, 2);
+ transp(d, 16, 4);
+ transp(d, 8, 2);
+ transp(d, 4, 1);
+ transp(d, 2, 4);
+ transp(d, 1, 2);
}
static inline void store_planar(char *dst, u32 dst_inc, u32 bpp, u32 d[8])
{
- int i;
+ int i;
- for (i = 0; i < bpp; i++, dst += dst_inc)
- *(u32 *)dst = d[perm_c2p_8bpp[i]];
+ for (i = 0; i < bpp; i++, dst += dst_inc)
+ *(u32 *)dst = d[perm_c2p_8bpp[i]];
}
static inline void store_planar_masked(char *dst, u32 dst_inc, u32 bpp,
u32 d[8], u32 mask)
{
- int i;
+ int i;
- for (i = 0; i < bpp; i++, dst += dst_inc)
- *(u32 *)dst = comp(d[perm_c2p_8bpp[i]], *(u32 *)dst, mask);
+ for (i = 0; i < bpp; i++, dst += dst_inc)
+ *(u32 *)dst = comp(d[perm_c2p_8bpp[i]], *(u32 *)dst, mask);
}
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)
{
- int dst_idx;
- u32 d[8], first, last, w;
- const u8 *c;
- u8 *p;
-
- dst += dy*dst_nextline+(dx & ~31);
- dst_idx = dx % 32;
- first = ~0UL >> dst_idx;
- last = ~(~0UL >> ((dst_idx+width) % 32));
- while (height--) {
- c = src;
- p = dst;
- w = width;
- if (dst_idx+width <= 32) {
- /* Single destination word */
- first &= last;
- memset(d, 0, sizeof(d));
- memcpy((u8 *)d+dst_idx, c, width);
- c += width;
- c2p_8bpp(d);
- store_planar_masked(p, dst_nextplane, bpp, d, first);
- p += 4;
- } else {
- /* Multiple destination words */
- w = width;
- /* Leading bits */
- if (dst_idx) {
- w = 32 - dst_idx;
- memset(d, 0, dst_idx);
- memcpy((u8 *)d+dst_idx, c, w);
- c += w;
- c2p_8bpp(d);
- store_planar_masked(p, dst_nextplane, bpp, d, first);
- p += 4;
- w = width-w;
- }
- /* Main chunk */
- while (w >= 32) {
- memcpy(d, c, 32);
- c += 32;
- c2p_8bpp(d);
- store_planar(p, dst_nextplane, bpp, d);
- 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);
- }
+ int dst_idx;
+ u32 d[8], first, last, w;
+ const u8 *c;
+ u8 *p;
+
+ dst += dy*dst_nextline+(dx & ~31);
+ dst_idx = dx % 32;
+ first = ~0UL >> dst_idx;
+ last = ~(~0UL >> ((dst_idx+width) % 32));
+ while (height--) {
+ c = src;
+ p = dst;
+ w = width;
+ if (dst_idx+width <= 32) {
+ /* Single destination word */
+ first &= last;
+ memset(d, 0, sizeof(d));
+ memcpy((u8 *)d+dst_idx, c, width);
+ c += width;
+ c2p_8bpp(d);
+ store_planar_masked(p, dst_nextplane, bpp, d, first);
+ p += 4;
+ } else {
+ /* Multiple destination words */
+ w = width;
+ /* Leading bits */
+ if (dst_idx) {
+ w = 32 - dst_idx;
+ memset(d, 0, dst_idx);
+ memcpy((u8 *)d+dst_idx, c, w);
+ c += w;
+ c2p_8bpp(d);
+ store_planar_masked(p, dst_nextplane, bpp, d,
+ first);
+ p += 4;
+ w = width-w;
+ }
+ /* Main chunk */
+ while (w >= 32) {
+ memcpy(d, c, 32);
+ c += 32;
+ c2p_8bpp(d);
+ store_planar(p, dst_nextplane, bpp, d);
+ 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);
+ }
+ }
+ src += src_nextline;
+ dst += dst_nextline;
}
- src += src_nextline;
- dst += dst_nextline;
- }
}
EXPORT_SYMBOL_GPL(c2p);