mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-11-25 03:50:53 +07:00
5a0e3ad6af
percpu.h is included by sched.h and module.h and thus ends up being included when building most .c files. percpu.h includes slab.h which in turn includes gfp.h making everything defined by the two files universally available and complicating inclusion dependencies. percpu.h -> slab.h dependency is about to be removed. Prepare for this change by updating users of gfp and slab facilities include those headers directly instead of assuming availability. As this conversion needs to touch large number of source files, the following script is used as the basis of conversion. http://userweb.kernel.org/~tj/misc/slabh-sweep.py The script does the followings. * Scan files for gfp and slab usages and update includes such that only the necessary includes are there. ie. if only gfp is used, gfp.h, if slab is used, slab.h. * When the script inserts a new include, it looks at the include blocks and try to put the new include such that its order conforms to its surrounding. It's put in the include block which contains core kernel includes, in the same order that the rest are ordered - alphabetical, Christmas tree, rev-Xmas-tree or at the end if there doesn't seem to be any matching order. * If the script can't find a place to put a new include (mostly because the file doesn't have fitting include block), it prints out an error message indicating which .h file needs to be added to the file. The conversion was done in the following steps. 1. The initial automatic conversion of all .c files updated slightly over 4000 files, deleting around 700 includes and adding ~480 gfp.h and ~3000 slab.h inclusions. The script emitted errors for ~400 files. 2. Each error was manually checked. Some didn't need the inclusion, some needed manual addition while adding it to implementation .h or embedding .c file was more appropriate for others. This step added inclusions to around 150 files. 3. The script was run again and the output was compared to the edits from #2 to make sure no file was left behind. 4. Several build tests were done and a couple of problems were fixed. e.g. lib/decompress_*.c used malloc/free() wrappers around slab APIs requiring slab.h to be added manually. 5. The script was run on all .h files but without automatically editing them as sprinkling gfp.h and slab.h inclusions around .h files could easily lead to inclusion dependency hell. Most gfp.h inclusion directives were ignored as stuff from gfp.h was usually wildly available and often used in preprocessor macros. Each slab.h inclusion directive was examined and added manually as necessary. 6. percpu.h was updated not to include slab.h. 7. Build test were done on the following configurations and failures were fixed. CONFIG_GCOV_KERNEL was turned off for all tests (as my distributed build env didn't work with gcov compiles) and a few more options had to be turned off depending on archs to make things build (like ipr on powerpc/64 which failed due to missing writeq). * x86 and x86_64 UP and SMP allmodconfig and a custom test config. * powerpc and powerpc64 SMP allmodconfig * sparc and sparc64 SMP allmodconfig * ia64 SMP allmodconfig * s390 SMP allmodconfig * alpha SMP allmodconfig * um on x86_64 SMP allmodconfig 8. percpu.h modifications were reverted so that it could be applied as a separate patch and serve as bisection point. Given the fact that I had only a couple of failures from tests on step 6, I'm fairly confident about the coverage of this conversion patch. If there is a breakage, it's likely to be something in one of the arch headers which should be easily discoverable easily on most builds of the specific arch. Signed-off-by: Tejun Heo <tj@kernel.org> Guess-its-ok-by: Christoph Lameter <cl@linux-foundation.org> Cc: Ingo Molnar <mingo@redhat.com> Cc: Lee Schermerhorn <Lee.Schermerhorn@hp.com>
432 lines
11 KiB
C
432 lines
11 KiB
C
/*
|
|
* Generic function for frame buffer with packed pixels of any depth.
|
|
*
|
|
* Copyright (C) 1999-2005 James Simmons <jsimmons@www.infradead.org>
|
|
*
|
|
* 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.
|
|
*
|
|
* NOTES:
|
|
*
|
|
* This is for cfb packed pixels. Iplan and such are incorporated in the
|
|
* drivers that need them.
|
|
*
|
|
* FIXME
|
|
*
|
|
* Also need to add code to deal with cards endians that are different than
|
|
* the native cpu endians. I also need to deal with MSB position in the word.
|
|
*
|
|
* The two functions or copying forward and backward could be split up like
|
|
* the ones for filling, i.e. in aligned and unaligned versions. This would
|
|
* 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/fb.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_readl
|
|
#else
|
|
# define FB_WRITEL fb_writeq
|
|
# define FB_READL fb_readq
|
|
#endif
|
|
|
|
/*
|
|
* Generic bitwise copy algorithm
|
|
*/
|
|
|
|
static void
|
|
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_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
|
|
|
|
if (dst_idx+n <= bits) {
|
|
// Single word
|
|
if (last)
|
|
first &= last;
|
|
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
|
|
} else {
|
|
// Multiple destination words
|
|
|
|
// Leading bits
|
|
if (first != ~0UL) {
|
|
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
|
|
dst++;
|
|
src++;
|
|
n -= bits - dst_idx;
|
|
}
|
|
|
|
// Main chunk
|
|
n /= bits;
|
|
while (n >= 8) {
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
n -= 8;
|
|
}
|
|
while (n--)
|
|
FB_WRITEL(FB_READL(src++), dst++);
|
|
|
|
// Trailing bits
|
|
if (last)
|
|
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
|
|
}
|
|
} else {
|
|
/* Different alignment for source and dest */
|
|
unsigned long d0, d1;
|
|
int m;
|
|
|
|
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
|
|
d0 >>= right;
|
|
} else if (src_idx+n <= bits) {
|
|
// Single source word
|
|
d0 <<= left;
|
|
} else {
|
|
// 2 source words
|
|
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
|
|
SRC and DST overlap bitwise (e.g. when moving just one pixel in
|
|
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'. */
|
|
d0 = FB_READL(src++);
|
|
d0 = fb_rev_pixels_in_long(d0, bswapmask);
|
|
// Leading bits
|
|
if (shift > 0) {
|
|
// Single source word
|
|
d1 = d0;
|
|
d0 >>= right;
|
|
dst++;
|
|
n -= bits - dst_idx;
|
|
} else {
|
|
// 2 source words
|
|
d1 = FB_READL(src++);
|
|
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) && !bswapmask) {
|
|
d1 = FB_READL(src++);
|
|
FB_WRITEL(d0 << left | d1 >> right, dst++);
|
|
d0 = d1;
|
|
d1 = FB_READL(src++);
|
|
FB_WRITEL(d0 << left | d1 >> right, dst++);
|
|
d0 = d1;
|
|
d1 = FB_READL(src++);
|
|
FB_WRITEL(d0 << left | d1 >> right, dst++);
|
|
d0 = d1;
|
|
d1 = FB_READL(src++);
|
|
FB_WRITEL(d0 << left | d1 >> right, dst++);
|
|
d0 = d1;
|
|
n -= 4;
|
|
}
|
|
while (n--) {
|
|
d1 = FB_READL(src++);
|
|
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;
|
|
}
|
|
|
|
// Trailing bits
|
|
if (last) {
|
|
if (m <= right) {
|
|
// Single source word
|
|
d0 <<= left;
|
|
} else {
|
|
// 2 source words
|
|
d1 = FB_READL(src);
|
|
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);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
/*
|
|
* Generic bitwise copy algorithm, operating backward
|
|
*/
|
|
|
|
static void
|
|
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;
|
|
|
|
dst += (n-1)/bits;
|
|
src += (n-1)/bits;
|
|
if ((n-1) % bits) {
|
|
dst_idx += (n-1) % bits;
|
|
dst += dst_idx >> (ffs(bits) - 1);
|
|
dst_idx &= bits - 1;
|
|
src_idx += (n-1) % bits;
|
|
src += src_idx >> (ffs(bits) - 1);
|
|
src_idx &= bits - 1;
|
|
}
|
|
|
|
shift = dst_idx-src_idx;
|
|
|
|
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
|
|
|
|
if ((unsigned long)dst_idx+1 >= n) {
|
|
// Single word
|
|
if (last)
|
|
first &= last;
|
|
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
|
|
} else {
|
|
// Multiple destination words
|
|
|
|
// Leading bits
|
|
if (first != ~0UL) {
|
|
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), first), dst);
|
|
dst--;
|
|
src--;
|
|
n -= dst_idx+1;
|
|
}
|
|
|
|
// Main chunk
|
|
n /= bits;
|
|
while (n >= 8) {
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
n -= 8;
|
|
}
|
|
while (n--)
|
|
FB_WRITEL(FB_READL(src--), dst--);
|
|
|
|
// Trailing bits
|
|
if (last)
|
|
FB_WRITEL( comp( FB_READL(src), FB_READL(dst), last), dst);
|
|
}
|
|
} 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
|
|
d0 <<= left;
|
|
} else if (1+(unsigned long)src_idx >= n) {
|
|
// Single source word
|
|
d0 >>= right;
|
|
} else {
|
|
// 2 source words
|
|
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
|
|
SRC and DST overlap bitwise (e.g. when moving just one pixel in
|
|
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'. */
|
|
|
|
d0 = FB_READL(src--);
|
|
d0 = fb_rev_pixels_in_long(d0, bswapmask);
|
|
// Leading bits
|
|
if (shift < 0) {
|
|
// Single source word
|
|
d1 = d0;
|
|
d0 <<= left;
|
|
} else {
|
|
// 2 source words
|
|
d1 = FB_READL(src--);
|
|
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) && !bswapmask) {
|
|
d1 = FB_READL(src--);
|
|
FB_WRITEL(d0 >> right | d1 << left, dst--);
|
|
d0 = d1;
|
|
d1 = FB_READL(src--);
|
|
FB_WRITEL(d0 >> right | d1 << left, dst--);
|
|
d0 = d1;
|
|
d1 = FB_READL(src--);
|
|
FB_WRITEL(d0 >> right | d1 << left, dst--);
|
|
d0 = d1;
|
|
d1 = FB_READL(src--);
|
|
FB_WRITEL(d0 >> right | d1 << left, dst--);
|
|
d0 = d1;
|
|
n -= 4;
|
|
}
|
|
while (n--) {
|
|
d1 = FB_READL(src--);
|
|
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;
|
|
}
|
|
|
|
// Trailing bits
|
|
if (last) {
|
|
if (m <= left) {
|
|
// Single source word
|
|
d0 >>= right;
|
|
} else {
|
|
// 2 source words
|
|
d1 = FB_READL(src);
|
|
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);
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
void cfb_copyarea(struct fb_info *p, const struct fb_copyarea *area)
|
|
{
|
|
u32 dx = area->dx, dy = area->dy, sx = area->sx, sy = area->sy;
|
|
u32 height = area->height, width = area->width;
|
|
unsigned long const bits_per_line = p->fix.line_length*8u;
|
|
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;
|
|
|
|
/* if the beginning of the target area might overlap with the end of
|
|
the source area, be have to copy the area reverse. */
|
|
if ((dy == sy && dx > sx) || (dy > sy)) {
|
|
dy += height;
|
|
sy += height;
|
|
rev_copy = 1;
|
|
}
|
|
|
|
// split the base of the framebuffer into a long-aligned address and the
|
|
// index of the first bit
|
|
dst = src = (unsigned long __iomem *)((unsigned long)p->screen_base & ~(bytes-1));
|
|
dst_idx = src_idx = 8*((unsigned long)p->screen_base & (bytes-1));
|
|
// add offset of source and target area
|
|
dst_idx += dy*bits_per_line + dx*p->var.bits_per_pixel;
|
|
src_idx += sy*bits_per_line + sx*p->var.bits_per_pixel;
|
|
|
|
if (p->fbops->fb_sync)
|
|
p->fbops->fb_sync(p);
|
|
|
|
if (rev_copy) {
|
|
while (height--) {
|
|
dst_idx -= bits_per_line;
|
|
src_idx -= bits_per_line;
|
|
dst += dst_idx >> (ffs(bits) - 1);
|
|
dst_idx &= (bytes - 1);
|
|
src += src_idx >> (ffs(bits) - 1);
|
|
src_idx &= (bytes - 1);
|
|
bitcpy_rev(p, dst, dst_idx, src, src_idx, bits,
|
|
width*p->var.bits_per_pixel, bswapmask);
|
|
}
|
|
} else {
|
|
while (height--) {
|
|
dst += dst_idx >> (ffs(bits) - 1);
|
|
dst_idx &= (bytes - 1);
|
|
src += src_idx >> (ffs(bits) - 1);
|
|
src_idx &= (bytes - 1);
|
|
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;
|
|
}
|
|
}
|
|
}
|
|
|
|
EXPORT_SYMBOL(cfb_copyarea);
|
|
|
|
MODULE_AUTHOR("James Simmons <jsimmons@users.sf.net>");
|
|
MODULE_DESCRIPTION("Generic software accelerated copyarea");
|
|
MODULE_LICENSE("GPL");
|
|
|