x86: Prefer TZCNT over BFS
Following a relatively recent compiler change, make use of the fact that for non-zero input BSF and TZCNT produce the same result, and that CPUs not knowing of TZCNT will treat the instruction as BSF (i.e. ignore what looks like a REP prefix to them). The assumption here is that TZCNT would never have worse performance than BSF. For the moment, only do this when the respective generic-CPU option is selected (as there are no specific-CPU options covering the CPUs supporting TZCNT), and don't do that when size optimization was requested. Signed-off-by: Jan Beulich <jbeulich@suse.com> Cc: Linus Torvalds <torvalds@linux-foundation.org> Link: http://lkml.kernel.org/r/504DEA1B020000780009A277@nat28.tlf.novell.com Signed-off-by: Ingo Molnar <mingo@kernel.org>
This commit is contained in:
parent
1edfbb4153
commit
5870661c09
1 changed files with 17 additions and 2 deletions
|
@ -347,6 +347,19 @@ static int test_bit(int nr, const volatile unsigned long *addr);
|
||||||
? constant_test_bit((nr), (addr)) \
|
? constant_test_bit((nr), (addr)) \
|
||||||
: variable_test_bit((nr), (addr)))
|
: variable_test_bit((nr), (addr)))
|
||||||
|
|
||||||
|
#if (defined(CONFIG_X86_GENERIC) || defined(CONFIG_GENERIC_CPU)) \
|
||||||
|
&& !defined(CONFIG_CC_OPTIMIZE_FOR_SIZE)
|
||||||
|
/*
|
||||||
|
* Since BSF and TZCNT have sufficiently similar semantics for the purposes
|
||||||
|
* for which we use them here, BMI-capable hardware will decode the prefixed
|
||||||
|
* variant as 'tzcnt ...' and may execute that faster than 'bsf ...', while
|
||||||
|
* older hardware will ignore the REP prefix and decode it as 'bsf ...'.
|
||||||
|
*/
|
||||||
|
# define BSF_PREFIX "rep;"
|
||||||
|
#else
|
||||||
|
# define BSF_PREFIX
|
||||||
|
#endif
|
||||||
|
|
||||||
/**
|
/**
|
||||||
* __ffs - find first set bit in word
|
* __ffs - find first set bit in word
|
||||||
* @word: The word to search
|
* @word: The word to search
|
||||||
|
@ -355,7 +368,7 @@ static int test_bit(int nr, const volatile unsigned long *addr);
|
||||||
*/
|
*/
|
||||||
static inline unsigned long __ffs(unsigned long word)
|
static inline unsigned long __ffs(unsigned long word)
|
||||||
{
|
{
|
||||||
asm("bsf %1,%0"
|
asm(BSF_PREFIX "bsf %1,%0"
|
||||||
: "=r" (word)
|
: "=r" (word)
|
||||||
: "rm" (word));
|
: "rm" (word));
|
||||||
return word;
|
return word;
|
||||||
|
@ -369,12 +382,14 @@ static inline unsigned long __ffs(unsigned long word)
|
||||||
*/
|
*/
|
||||||
static inline unsigned long ffz(unsigned long word)
|
static inline unsigned long ffz(unsigned long word)
|
||||||
{
|
{
|
||||||
asm("bsf %1,%0"
|
asm(BSF_PREFIX "bsf %1,%0"
|
||||||
: "=r" (word)
|
: "=r" (word)
|
||||||
: "r" (~word));
|
: "r" (~word));
|
||||||
return word;
|
return word;
|
||||||
}
|
}
|
||||||
|
|
||||||
|
#undef BSF_PREFIX
|
||||||
|
|
||||||
/*
|
/*
|
||||||
* __fls: find last set bit in word
|
* __fls: find last set bit in word
|
||||||
* @word: The word to search
|
* @word: The word to search
|
||||||
|
|
Loading…
Reference in a new issue