Revision 9a9657568bfd89a258db643352e38b5decfd059a authored by Eric Anholt on 20 October 2016, 23:48:12 UTC, committed by popcornmix on 08 January 2017, 11:42:05 UTC
The loop is scanning until the original max_ip (size of the BO), but we want to not examine any code after the PROG_END's delay slots. There was a block trying to do that, except that we had some early continue statements if the signal wasn't a PROG_END or a BRANCH. The failure mode would be that a valid shader is rejected because some undefined memory after the PROG_END slots is parsed as a branch and the rest of its setup is illegal. I haven't seen this in the wild, but valgrind was complaining when about this up in the userland simulator mode. Signed-off-by: Eric Anholt <eric@anholt.net> (cherry picked from commit 457e67a728696c4f8e6423c64e93def50530db9a)
1 parent 2229784
hweight.c
#include <linux/export.h>
#include <linux/bitops.h>
#include <asm/types.h>
/**
* hweightN - returns the hamming weight of a N-bit word
* @x: the word to weigh
*
* The Hamming Weight of a number is the total number of bits set in it.
*/
#ifndef __HAVE_ARCH_SW_HWEIGHT
unsigned int __sw_hweight32(unsigned int w)
{
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x55555555;
w = (w & 0x33333333) + ((w >> 2) & 0x33333333);
w = (w + (w >> 4)) & 0x0f0f0f0f;
return (w * 0x01010101) >> 24;
#else
unsigned int res = w - ((w >> 1) & 0x55555555);
res = (res & 0x33333333) + ((res >> 2) & 0x33333333);
res = (res + (res >> 4)) & 0x0F0F0F0F;
res = res + (res >> 8);
return (res + (res >> 16)) & 0x000000FF;
#endif
}
EXPORT_SYMBOL(__sw_hweight32);
#endif
unsigned int __sw_hweight16(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x5555);
res = (res & 0x3333) + ((res >> 2) & 0x3333);
res = (res + (res >> 4)) & 0x0F0F;
return (res + (res >> 8)) & 0x00FF;
}
EXPORT_SYMBOL(__sw_hweight16);
unsigned int __sw_hweight8(unsigned int w)
{
unsigned int res = w - ((w >> 1) & 0x55);
res = (res & 0x33) + ((res >> 2) & 0x33);
return (res + (res >> 4)) & 0x0F;
}
EXPORT_SYMBOL(__sw_hweight8);
#ifndef __HAVE_ARCH_SW_HWEIGHT
unsigned long __sw_hweight64(__u64 w)
{
#if BITS_PER_LONG == 32
return __sw_hweight32((unsigned int)(w >> 32)) +
__sw_hweight32((unsigned int)w);
#elif BITS_PER_LONG == 64
#ifdef CONFIG_ARCH_HAS_FAST_MULTIPLIER
w -= (w >> 1) & 0x5555555555555555ul;
w = (w & 0x3333333333333333ul) + ((w >> 2) & 0x3333333333333333ul);
w = (w + (w >> 4)) & 0x0f0f0f0f0f0f0f0ful;
return (w * 0x0101010101010101ul) >> 56;
#else
__u64 res = w - ((w >> 1) & 0x5555555555555555ul);
res = (res & 0x3333333333333333ul) + ((res >> 2) & 0x3333333333333333ul);
res = (res + (res >> 4)) & 0x0F0F0F0F0F0F0F0Ful;
res = res + (res >> 8);
res = res + (res >> 16);
return (res + (res >> 32)) & 0x00000000000000FFul;
#endif
#endif
}
EXPORT_SYMBOL(__sw_hweight64);
#endif
Computing file changes ...
