mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-22 15:45:09 +07:00
f5967101e9
People complained about ARCH_HWEIGHT_CFLAGS and how it throws a wrench
into kcov, lto, etc, experimentations.
Add asm versions for __sw_hweight{32,64}() and do explicit saving and
restoring of clobbered registers. This gets rid of the special calling
convention. We get to call those functions on !X86_FEATURE_POPCNT CPUs.
We still need to hardcode POPCNT and register operands as some old gas
versions which we support, do not know about POPCNT.
Btw, remove redundant REX prefix from 32-bit POPCNT because alternatives
can do padding now.
Suggested-by: H. Peter Anvin <hpa@zytor.com>
Signed-off-by: Borislav Petkov <bp@suse.de>
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Andy Lutomirski <luto@amacapital.net>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Link: http://lkml.kernel.org/r/1464605787-20603-1-git-send-email-bp@alien8.de
Signed-off-by: Ingo Molnar <mingo@kernel.org>
63 lines
1.2 KiB
C
63 lines
1.2 KiB
C
#ifndef _ASM_X86_HWEIGHT_H
|
|
#define _ASM_X86_HWEIGHT_H
|
|
|
|
#include <asm/cpufeatures.h>
|
|
|
|
#ifdef CONFIG_64BIT
|
|
/* popcnt %edi, %eax */
|
|
#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc7"
|
|
/* popcnt %rdi, %rax */
|
|
#define POPCNT64 ".byte 0xf3,0x48,0x0f,0xb8,0xc7"
|
|
#define REG_IN "D"
|
|
#define REG_OUT "a"
|
|
#else
|
|
/* popcnt %eax, %eax */
|
|
#define POPCNT32 ".byte 0xf3,0x0f,0xb8,0xc0"
|
|
#define REG_IN "a"
|
|
#define REG_OUT "a"
|
|
#endif
|
|
|
|
#define __HAVE_ARCH_SW_HWEIGHT
|
|
|
|
static __always_inline unsigned int __arch_hweight32(unsigned int w)
|
|
{
|
|
unsigned int res;
|
|
|
|
asm (ALTERNATIVE("call __sw_hweight32", POPCNT32, X86_FEATURE_POPCNT)
|
|
: "="REG_OUT (res)
|
|
: REG_IN (w));
|
|
|
|
return res;
|
|
}
|
|
|
|
static inline unsigned int __arch_hweight16(unsigned int w)
|
|
{
|
|
return __arch_hweight32(w & 0xffff);
|
|
}
|
|
|
|
static inline unsigned int __arch_hweight8(unsigned int w)
|
|
{
|
|
return __arch_hweight32(w & 0xff);
|
|
}
|
|
|
|
#ifdef CONFIG_X86_32
|
|
static inline unsigned long __arch_hweight64(__u64 w)
|
|
{
|
|
return __arch_hweight32((u32)w) +
|
|
__arch_hweight32((u32)(w >> 32));
|
|
}
|
|
#else
|
|
static __always_inline unsigned long __arch_hweight64(__u64 w)
|
|
{
|
|
unsigned long res;
|
|
|
|
asm (ALTERNATIVE("call __sw_hweight64", POPCNT64, X86_FEATURE_POPCNT)
|
|
: "="REG_OUT (res)
|
|
: REG_IN (w));
|
|
|
|
return res;
|
|
}
|
|
#endif /* CONFIG_X86_32 */
|
|
|
|
#endif
|