mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-28 01:57:06 +07:00
81d2c6f819
Currently bitops-instrumented.h assumes that the architecture provides atomic, non-atomic and locking bitops (e.g. both set_bit and __set_bit). This is true on x86 and s390, but is not always true: there is a generic bitops/non-atomic.h header that provides generic non-atomic operations, and also a generic bitops/lock.h for locking operations. powerpc uses the generic non-atomic version, so it does not have it's own e.g. __set_bit that could be renamed arch___set_bit. Split up bitops-instrumented.h to mirror the atomic/non-atomic/lock split. This allows arches to only include the headers where they have arch-specific versions to rename. Update x86 and s390. (The generic operations are automatically instrumented because they're written in C, not asm.) Suggested-by: Christophe Leroy <christophe.leroy@c-s.fr> Reviewed-by: Christophe Leroy <christophe.leroy@c-s.fr> Signed-off-by: Daniel Axtens <dja@axtens.net> Acked-by: Marco Elver <elver@google.com> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/20190820024941.12640-1-dja@axtens.net
401 lines
9.9 KiB
C
401 lines
9.9 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _ASM_X86_BITOPS_H
|
|
#define _ASM_X86_BITOPS_H
|
|
|
|
/*
|
|
* Copyright 1992, Linus Torvalds.
|
|
*
|
|
* Note: inlines with more than a single statement should be marked
|
|
* __always_inline to avoid problems with older gcc's inlining heuristics.
|
|
*/
|
|
|
|
#ifndef _LINUX_BITOPS_H
|
|
#error only <linux/bitops.h> can be included directly
|
|
#endif
|
|
|
|
#include <linux/compiler.h>
|
|
#include <asm/alternative.h>
|
|
#include <asm/rmwcc.h>
|
|
#include <asm/barrier.h>
|
|
|
|
#if BITS_PER_LONG == 32
|
|
# define _BITOPS_LONG_SHIFT 5
|
|
#elif BITS_PER_LONG == 64
|
|
# define _BITOPS_LONG_SHIFT 6
|
|
#else
|
|
# error "Unexpected BITS_PER_LONG"
|
|
#endif
|
|
|
|
#define BIT_64(n) (U64_C(1) << (n))
|
|
|
|
/*
|
|
* These have to be done with inline assembly: that way the bit-setting
|
|
* is guaranteed to be atomic. All bit operations return 0 if the bit
|
|
* was cleared before the operation and != 0 if it was not.
|
|
*
|
|
* bit 0 is the LSB of addr; bit 32 is the LSB of (addr+1).
|
|
*/
|
|
|
|
#define RLONG_ADDR(x) "m" (*(volatile long *) (x))
|
|
#define WBYTE_ADDR(x) "+m" (*(volatile char *) (x))
|
|
|
|
#define ADDR RLONG_ADDR(addr)
|
|
|
|
/*
|
|
* We do the locked ops that don't return the old value as
|
|
* a mask operation on a byte.
|
|
*/
|
|
#define CONST_MASK_ADDR(nr, addr) WBYTE_ADDR((void *)(addr) + ((nr)>>3))
|
|
#define CONST_MASK(nr) (1 << ((nr) & 7))
|
|
|
|
static __always_inline void
|
|
arch_set_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
if (__builtin_constant_p(nr)) {
|
|
asm volatile(LOCK_PREFIX "orb %1,%0"
|
|
: CONST_MASK_ADDR(nr, addr)
|
|
: "iq" ((u8)CONST_MASK(nr))
|
|
: "memory");
|
|
} else {
|
|
asm volatile(LOCK_PREFIX __ASM_SIZE(bts) " %1,%0"
|
|
: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
|
|
}
|
|
}
|
|
|
|
static __always_inline void
|
|
arch___set_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
|
|
}
|
|
|
|
static __always_inline void
|
|
arch_clear_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
if (__builtin_constant_p(nr)) {
|
|
asm volatile(LOCK_PREFIX "andb %1,%0"
|
|
: CONST_MASK_ADDR(nr, addr)
|
|
: "iq" ((u8)~CONST_MASK(nr)));
|
|
} else {
|
|
asm volatile(LOCK_PREFIX __ASM_SIZE(btr) " %1,%0"
|
|
: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
|
|
}
|
|
}
|
|
|
|
static __always_inline void
|
|
arch_clear_bit_unlock(long nr, volatile unsigned long *addr)
|
|
{
|
|
barrier();
|
|
arch_clear_bit(nr, addr);
|
|
}
|
|
|
|
static __always_inline void
|
|
arch___clear_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch_clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr)
|
|
{
|
|
bool negative;
|
|
asm volatile(LOCK_PREFIX "andb %2,%1"
|
|
CC_SET(s)
|
|
: CC_OUT(s) (negative), WBYTE_ADDR(addr)
|
|
: "ir" ((char) ~(1 << nr)) : "memory");
|
|
return negative;
|
|
}
|
|
#define arch_clear_bit_unlock_is_negative_byte \
|
|
arch_clear_bit_unlock_is_negative_byte
|
|
|
|
static __always_inline void
|
|
arch___clear_bit_unlock(long nr, volatile unsigned long *addr)
|
|
{
|
|
arch___clear_bit(nr, addr);
|
|
}
|
|
|
|
static __always_inline void
|
|
arch___change_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory");
|
|
}
|
|
|
|
static __always_inline void
|
|
arch_change_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
if (__builtin_constant_p(nr)) {
|
|
asm volatile(LOCK_PREFIX "xorb %1,%0"
|
|
: CONST_MASK_ADDR(nr, addr)
|
|
: "iq" ((u8)CONST_MASK(nr)));
|
|
} else {
|
|
asm volatile(LOCK_PREFIX __ASM_SIZE(btc) " %1,%0"
|
|
: : RLONG_ADDR(addr), "Ir" (nr) : "memory");
|
|
}
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch_test_and_set_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(bts), *addr, c, "Ir", nr);
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr)
|
|
{
|
|
return arch_test_and_set_bit(nr, addr);
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch___test_and_set_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
bool oldbit;
|
|
|
|
asm(__ASM_SIZE(bts) " %2,%1"
|
|
CC_SET(c)
|
|
: CC_OUT(c) (oldbit)
|
|
: ADDR, "Ir" (nr) : "memory");
|
|
return oldbit;
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch_test_and_clear_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btr), *addr, c, "Ir", nr);
|
|
}
|
|
|
|
/*
|
|
* Note: the operation is performed atomically with respect to
|
|
* the local CPU, but not other CPUs. Portable code should not
|
|
* rely on this behaviour.
|
|
* KVM relies on this behaviour on x86 for modifying memory that is also
|
|
* accessed from a hypervisor on the same CPU if running in a VM: don't change
|
|
* this without also updating arch/x86/kernel/kvm.c
|
|
*/
|
|
static __always_inline bool
|
|
arch___test_and_clear_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
bool oldbit;
|
|
|
|
asm volatile(__ASM_SIZE(btr) " %2,%1"
|
|
CC_SET(c)
|
|
: CC_OUT(c) (oldbit)
|
|
: ADDR, "Ir" (nr) : "memory");
|
|
return oldbit;
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch___test_and_change_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
bool oldbit;
|
|
|
|
asm volatile(__ASM_SIZE(btc) " %2,%1"
|
|
CC_SET(c)
|
|
: CC_OUT(c) (oldbit)
|
|
: ADDR, "Ir" (nr) : "memory");
|
|
|
|
return oldbit;
|
|
}
|
|
|
|
static __always_inline bool
|
|
arch_test_and_change_bit(long nr, volatile unsigned long *addr)
|
|
{
|
|
return GEN_BINARY_RMWcc(LOCK_PREFIX __ASM_SIZE(btc), *addr, c, "Ir", nr);
|
|
}
|
|
|
|
static __always_inline bool constant_test_bit(long nr, const volatile unsigned long *addr)
|
|
{
|
|
return ((1UL << (nr & (BITS_PER_LONG-1))) &
|
|
(addr[nr >> _BITOPS_LONG_SHIFT])) != 0;
|
|
}
|
|
|
|
static __always_inline bool variable_test_bit(long nr, volatile const unsigned long *addr)
|
|
{
|
|
bool oldbit;
|
|
|
|
asm volatile(__ASM_SIZE(bt) " %2,%1"
|
|
CC_SET(c)
|
|
: CC_OUT(c) (oldbit)
|
|
: "m" (*(unsigned long *)addr), "Ir" (nr) : "memory");
|
|
|
|
return oldbit;
|
|
}
|
|
|
|
#define arch_test_bit(nr, addr) \
|
|
(__builtin_constant_p((nr)) \
|
|
? constant_test_bit((nr), (addr)) \
|
|
: variable_test_bit((nr), (addr)))
|
|
|
|
/**
|
|
* __ffs - find first set bit in word
|
|
* @word: The word to search
|
|
*
|
|
* Undefined if no bit exists, so code should check against 0 first.
|
|
*/
|
|
static __always_inline unsigned long __ffs(unsigned long word)
|
|
{
|
|
asm("rep; bsf %1,%0"
|
|
: "=r" (word)
|
|
: "rm" (word));
|
|
return word;
|
|
}
|
|
|
|
/**
|
|
* ffz - find first zero bit in word
|
|
* @word: The word to search
|
|
*
|
|
* Undefined if no zero exists, so code should check against ~0UL first.
|
|
*/
|
|
static __always_inline unsigned long ffz(unsigned long word)
|
|
{
|
|
asm("rep; bsf %1,%0"
|
|
: "=r" (word)
|
|
: "r" (~word));
|
|
return word;
|
|
}
|
|
|
|
/*
|
|
* __fls: find last set bit in word
|
|
* @word: The word to search
|
|
*
|
|
* Undefined if no set bit exists, so code should check against 0 first.
|
|
*/
|
|
static __always_inline unsigned long __fls(unsigned long word)
|
|
{
|
|
asm("bsr %1,%0"
|
|
: "=r" (word)
|
|
: "rm" (word));
|
|
return word;
|
|
}
|
|
|
|
#undef ADDR
|
|
|
|
#ifdef __KERNEL__
|
|
/**
|
|
* ffs - find first set bit in word
|
|
* @x: the word to search
|
|
*
|
|
* This is defined the same way as the libc and compiler builtin ffs
|
|
* routines, therefore differs in spirit from the other bitops.
|
|
*
|
|
* ffs(value) returns 0 if value is 0 or the position of the first
|
|
* set bit if value is nonzero. The first (least significant) bit
|
|
* is at position 1.
|
|
*/
|
|
static __always_inline int ffs(int x)
|
|
{
|
|
int r;
|
|
|
|
#ifdef CONFIG_X86_64
|
|
/*
|
|
* AMD64 says BSFL won't clobber the dest reg if x==0; Intel64 says the
|
|
* dest reg is undefined if x==0, but their CPU architect says its
|
|
* value is written to set it to the same as before, except that the
|
|
* top 32 bits will be cleared.
|
|
*
|
|
* We cannot do this on 32 bits because at the very least some
|
|
* 486 CPUs did not behave this way.
|
|
*/
|
|
asm("bsfl %1,%0"
|
|
: "=r" (r)
|
|
: "rm" (x), "0" (-1));
|
|
#elif defined(CONFIG_X86_CMOV)
|
|
asm("bsfl %1,%0\n\t"
|
|
"cmovzl %2,%0"
|
|
: "=&r" (r) : "rm" (x), "r" (-1));
|
|
#else
|
|
asm("bsfl %1,%0\n\t"
|
|
"jnz 1f\n\t"
|
|
"movl $-1,%0\n"
|
|
"1:" : "=r" (r) : "rm" (x));
|
|
#endif
|
|
return r + 1;
|
|
}
|
|
|
|
/**
|
|
* fls - find last set bit in word
|
|
* @x: the word to search
|
|
*
|
|
* This is defined in a similar way as the libc and compiler builtin
|
|
* ffs, but returns the position of the most significant set bit.
|
|
*
|
|
* fls(value) returns 0 if value is 0 or the position of the last
|
|
* set bit if value is nonzero. The last (most significant) bit is
|
|
* at position 32.
|
|
*/
|
|
static __always_inline int fls(unsigned int x)
|
|
{
|
|
int r;
|
|
|
|
#ifdef CONFIG_X86_64
|
|
/*
|
|
* AMD64 says BSRL won't clobber the dest reg if x==0; Intel64 says the
|
|
* dest reg is undefined if x==0, but their CPU architect says its
|
|
* value is written to set it to the same as before, except that the
|
|
* top 32 bits will be cleared.
|
|
*
|
|
* We cannot do this on 32 bits because at the very least some
|
|
* 486 CPUs did not behave this way.
|
|
*/
|
|
asm("bsrl %1,%0"
|
|
: "=r" (r)
|
|
: "rm" (x), "0" (-1));
|
|
#elif defined(CONFIG_X86_CMOV)
|
|
asm("bsrl %1,%0\n\t"
|
|
"cmovzl %2,%0"
|
|
: "=&r" (r) : "rm" (x), "rm" (-1));
|
|
#else
|
|
asm("bsrl %1,%0\n\t"
|
|
"jnz 1f\n\t"
|
|
"movl $-1,%0\n"
|
|
"1:" : "=r" (r) : "rm" (x));
|
|
#endif
|
|
return r + 1;
|
|
}
|
|
|
|
/**
|
|
* fls64 - find last set bit in a 64-bit word
|
|
* @x: the word to search
|
|
*
|
|
* This is defined in a similar way as the libc and compiler builtin
|
|
* ffsll, but returns the position of the most significant set bit.
|
|
*
|
|
* fls64(value) returns 0 if value is 0 or the position of the last
|
|
* set bit if value is nonzero. The last (most significant) bit is
|
|
* at position 64.
|
|
*/
|
|
#ifdef CONFIG_X86_64
|
|
static __always_inline int fls64(__u64 x)
|
|
{
|
|
int bitpos = -1;
|
|
/*
|
|
* AMD64 says BSRQ won't clobber the dest reg if x==0; Intel64 says the
|
|
* dest reg is undefined if x==0, but their CPU architect says its
|
|
* value is written to set it to the same as before.
|
|
*/
|
|
asm("bsrq %1,%q0"
|
|
: "+r" (bitpos)
|
|
: "rm" (x));
|
|
return bitpos + 1;
|
|
}
|
|
#else
|
|
#include <asm-generic/bitops/fls64.h>
|
|
#endif
|
|
|
|
#include <asm-generic/bitops/find.h>
|
|
|
|
#include <asm-generic/bitops/sched.h>
|
|
|
|
#include <asm/arch_hweight.h>
|
|
|
|
#include <asm-generic/bitops/const_hweight.h>
|
|
|
|
#include <asm-generic/bitops/instrumented-atomic.h>
|
|
#include <asm-generic/bitops/instrumented-non-atomic.h>
|
|
#include <asm-generic/bitops/instrumented-lock.h>
|
|
|
|
#include <asm-generic/bitops/le.h>
|
|
|
|
#include <asm-generic/bitops/ext2-atomic-setbit.h>
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif /* _ASM_X86_BITOPS_H */
|