* help moving some redundant computations and branches out of the loop, too.
*/
-
-
#include <linux/module.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/slab.h>
#include <asm/types.h>
#include <asm/io.h>
+#include "fb_draw.h"
#if BITS_PER_LONG == 32
# define FB_WRITEL fb_writel
# define FB_READL fb_readq
#endif
- /*
- * Compose two values, using a bitmask as decision value
- * This is equivalent to (a & mask) | (b & ~mask)
- */
-
-static inline unsigned long
-comp(unsigned long a, unsigned long b, unsigned long mask)
-{
- return ((a ^ b) & mask) ^ b;
-}
-
/*
* Generic bitwise copy algorithm
*/
static void
-bitcpy(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src,
- int src_idx, int bits, unsigned n)
+bitcpy(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
+ const unsigned long __iomem *src, int src_idx, int bits,
+ unsigned n, u32 bswapmask)
{
unsigned long first, last;
int const shift = dst_idx-src_idx;
int left, right;
- first = FB_SHIFT_HIGH(~0UL, dst_idx);
- last = ~(FB_SHIFT_HIGH(~0UL, (dst_idx+n) % bits));
+ first = fb_shifted_pixels_mask_long(p, dst_idx, bswapmask);
+ last = ~fb_shifted_pixels_mask_long(p, (dst_idx+n) % bits, bswapmask);
if (!shift) {
// Same alignment for source and dest
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
}
} else {
+ /* Different alignment for source and dest */
unsigned long d0, d1;
int m;
- // Different alignment for source and dest
right = shift & (bits - 1);
left = -shift & (bits - 1);
+ bswapmask &= shift;
if (dst_idx+n <= bits) {
// Single destination word
if (last)
first &= last;
+ d0 = FB_READL(src);
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
if (shift > 0) {
// Single source word
- FB_WRITEL( comp( FB_READL(src) >> right, FB_READL(dst), first), dst);
+ d0 >>= right;
} else if (src_idx+n <= bits) {
// Single source word
- FB_WRITEL( comp(FB_READL(src) << left, FB_READL(dst), first), dst);
+ d0 <<= left;;
} else {
// 2 source words
- d0 = FB_READL(src++);
- d1 = FB_READL(src);
- FB_WRITEL( comp(d0<<left | d1>>right, FB_READL(dst), first), dst);
+ d1 = FB_READL(src + 1);
+ d1 = fb_rev_pixels_in_long(d1, bswapmask);
+ d0 = d0<<left | d1>>right;
}
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
} else {
// Multiple destination words
/** We must always remember the last value read, because in case
overlap with the current long from SRC. We store this value in
'd0'. */
d0 = FB_READL(src++);
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
// Leading bits
if (shift > 0) {
// Single source word
- FB_WRITEL( comp(d0 >> right, FB_READL(dst), first), dst);
+ d1 = d0;
+ d0 >>= right;
dst++;
n -= bits - dst_idx;
} else {
// 2 source words
d1 = FB_READL(src++);
- FB_WRITEL( comp(d0<<left | d1>>right, FB_READL(dst), first), dst);
- d0 = d1;
+ d1 = fb_rev_pixels_in_long(d1, bswapmask);
+
+ d0 = d0<<left | d1>>right;
dst++;
n -= bits - dst_idx;
}
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+ d0 = d1;
// Main chunk
m = n % bits;
n /= bits;
- while (n >= 4) {
+ while ((n >= 4) && !bswapmask) {
d1 = FB_READL(src++);
FB_WRITEL(d0 << left | d1 >> right, dst++);
d0 = d1;
}
while (n--) {
d1 = FB_READL(src++);
- FB_WRITEL(d0 << left | d1 >> right, dst++);
+ d1 = fb_rev_pixels_in_long(d1, bswapmask);
+ d0 = d0 << left | d1 >> right;
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(d0, dst++);
d0 = d1;
}
if (last) {
if (m <= right) {
// Single source word
- FB_WRITEL( comp(d0 << left, FB_READL(dst), last), dst);
+ d0 <<= left;
} else {
// 2 source words
d1 = FB_READL(src);
- FB_WRITEL( comp(d0<<left | d1>>right, FB_READL(dst), last), dst);
+ d1 = fb_rev_pixels_in_long(d1,
+ bswapmask);
+ d0 = d0<<left | d1>>right;
}
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
}
}
}
*/
static void
-bitcpy_rev(unsigned long __iomem *dst, int dst_idx, const unsigned long __iomem *src,
- int src_idx, int bits, unsigned n)
+bitcpy_rev(struct fb_info *p, unsigned long __iomem *dst, int dst_idx,
+ const unsigned long __iomem *src, int src_idx, int bits,
+ unsigned n, u32 bswapmask)
{
unsigned long first, last;
int shift;
shift = dst_idx-src_idx;
- first = FB_SHIFT_LOW(~0UL, bits - 1 - dst_idx);
- last = ~(FB_SHIFT_LOW(~0UL, bits - 1 - ((dst_idx-n) % bits)));
+ first = fb_shifted_pixels_mask_long(p, bits - 1 - dst_idx, bswapmask);
+ last = ~fb_shifted_pixels_mask_long(p, bits - 1 - ((dst_idx-n) % bits),
+ bswapmask);
if (!shift) {
// Same alignment for source and dest
}
} else {
// Different alignment for source and dest
+ unsigned long d0, d1;
+ int m;
int const left = -shift & (bits-1);
int const right = shift & (bits-1);
+ bswapmask &= shift;
if ((unsigned long)dst_idx+1 >= n) {
// Single destination word
if (last)
first &= last;
+ d0 = FB_READL(src);
if (shift < 0) {
// Single source word
- FB_WRITEL( comp( FB_READL(src)<<left, FB_READL(dst), first), dst);
+ d0 <<= left;
} else if (1+(unsigned long)src_idx >= n) {
// Single source word
- FB_WRITEL( comp( FB_READL(src)>>right, FB_READL(dst), first), dst);
+ d0 >>= right;
} else {
// 2 source words
- FB_WRITEL( comp( (FB_READL(src)>>right | FB_READL(src-1)<<left), FB_READL(dst), first), dst);
+ d1 = FB_READL(src - 1);
+ d1 = fb_rev_pixels_in_long(d1, bswapmask);
+ d0 = d0>>right | d1<<left;
}
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
} else {
// Multiple destination words
/** We must always remember the last value read, because in case
1bpp), we always collect one full long for DST and that might
overlap with the current long from SRC. We store this value in
'd0'. */
- unsigned long d0, d1;
- int m;
d0 = FB_READL(src--);
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
// Leading bits
if (shift < 0) {
// Single source word
- FB_WRITEL( comp( (d0 << left), FB_READL(dst), first), dst);
+ d1 = d0;
+ d0 <<= left;
} else {
// 2 source words
d1 = FB_READL(src--);
- FB_WRITEL( comp( (d0>>right | d1<<left), FB_READL(dst), first), dst);
- d0 = d1;
+ d1 = fb_rev_pixels_in_long(d1, bswapmask);
+ d0 = d0>>right | d1<<left;
}
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(comp(d0, FB_READL(dst), first), dst);
+ d0 = d1;
dst--;
n -= dst_idx+1;
// Main chunk
m = n % bits;
n /= bits;
- while (n >= 4) {
+ while ((n >= 4) && !bswapmask) {
d1 = FB_READL(src--);
FB_WRITEL(d0 >> right | d1 << left, dst--);
d0 = d1;
}
while (n--) {
d1 = FB_READL(src--);
- FB_WRITEL(d0 >> right | d1 << left, dst--);
+ d1 = fb_rev_pixels_in_long(d1, bswapmask);
+ d0 = d0 >> right | d1 << left;
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(d0, dst--);
d0 = d1;
}
if (last) {
if (m <= left) {
// Single source word
- FB_WRITEL( comp(d0 >> right, FB_READL(dst), last), dst);
+ d0 >>= right;
} else {
// 2 source words
d1 = FB_READL(src);
- FB_WRITEL( comp(d0>>right | d1<<left, FB_READL(dst), last), dst);
+ d1 = fb_rev_pixels_in_long(d1,
+ bswapmask);
+ d0 = d0>>right | d1<<left;
}
+ d0 = fb_rev_pixels_in_long(d0, bswapmask);
+ FB_WRITEL(comp(d0, FB_READL(dst), last), dst);
}
}
}
unsigned long __iomem *dst = NULL, *src = NULL;
int bits = BITS_PER_LONG, bytes = bits >> 3;
int dst_idx = 0, src_idx = 0, rev_copy = 0;
+ u32 bswapmask = fb_compute_bswapmask(p);
if (p->state != FBINFO_STATE_RUNNING)
return;
dst_idx &= (bytes - 1);
src += src_idx >> (ffs(bits) - 1);
src_idx &= (bytes - 1);
- bitcpy_rev(dst, dst_idx, src, src_idx, bits,
- width*p->var.bits_per_pixel);
+ bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
+ width*p->var.bits_per_pixel, bswapmask);
}
} else {
while (height--) {
dst_idx &= (bytes - 1);
src += src_idx >> (ffs(bits) - 1);
src_idx &= (bytes - 1);
- bitcpy(dst, dst_idx, src, src_idx, bits,
- width*p->var.bits_per_pixel);
+ bitcpy(p, dst, dst_idx, src, src_idx, bits,
+ width*p->var.bits_per_pixel, bswapmask);
dst_idx += bits_per_line;
src_idx += bits_per_line;
}
git.openpandora.org / pandora-kernel.git / blobdiff