mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/stable/linux.git
synced 2024-09-03 17:40:04 +00:00
![Christophe Leroy](/assets/img/avatar_default.png)
Building a kernel with CONFIG_CC_OPTIMISE_FOR_SIZE leads to the following functions being copied several times in vmlinux: 31 times __ilog2_u32() 34 times fls() Disassembly follows: c00f476c <fls>: c00f476c: 7c 63 00 34 cntlzw r3,r3 c00f4770: 20 63 00 20 subfic r3,r3,32 c00f4774: 4e 80 00 20 blr c00f4778 <__ilog2_u32>: c00f4778: 94 21 ff f0 stwu r1,-16(r1) c00f477c: 7c 08 02 a6 mflr r0 c00f4780: 90 01 00 14 stw r0,20(r1) c00f4784: 4b ff ff e9 bl c00f476c <fls> c00f4788: 80 01 00 14 lwz r0,20(r1) c00f478c: 38 63 ff ff addi r3,r3,-1 c00f4790: 7c 08 03 a6 mtlr r0 c00f4794: 38 21 00 10 addi r1,r1,16 c00f4798: 4e 80 00 20 blr When forcing inlining of fls(), we get c0008b80 <__ilog2_u32>: c0008b80: 7c 63 00 34 cntlzw r3,r3 c0008b84: 20 63 00 1f subfic r3,r3,31 c0008b88: 4e 80 00 20 blr vmlinux size gets reduced by 1 kbyte with that change. Signed-off-by: Christophe Leroy <christophe.leroy@csgroup.eu> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au> Link: https://lore.kernel.org/r/adc9c9d6378f6b5008246ca717993d7870188efb.1644569473.git.christophe.leroy@csgroup.eu
346 lines
9.4 KiB
C
346 lines
9.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0-or-later */
|
|
/*
|
|
* PowerPC atomic bit operations.
|
|
*
|
|
* Merged version by David Gibson <david@gibson.dropbear.id.au>.
|
|
* Based on ppc64 versions by: Dave Engebretsen, Todd Inglett, Don
|
|
* Reed, Pat McCarthy, Peter Bergner, Anton Blanchard. They
|
|
* originally took it from the ppc32 code.
|
|
*
|
|
* Within a word, bits are numbered LSB first. Lot's of places make
|
|
* this assumption by directly testing bits with (val & (1<<nr)).
|
|
* This can cause confusion for large (> 1 word) bitmaps on a
|
|
* big-endian system because, unlike little endian, the number of each
|
|
* bit depends on the word size.
|
|
*
|
|
* The bitop functions are defined to work on unsigned longs, so for a
|
|
* ppc64 system the bits end up numbered:
|
|
* |63..............0|127............64|191...........128|255...........192|
|
|
* and on ppc32:
|
|
* |31.....0|63....32|95....64|127...96|159..128|191..160|223..192|255..224|
|
|
*
|
|
* There are a few little-endian macros used mostly for filesystem
|
|
* bitmaps, these work on similar bit arrays layouts, but
|
|
* byte-oriented:
|
|
* |7...0|15...8|23...16|31...24|39...32|47...40|55...48|63...56|
|
|
*
|
|
* The main difference is that bit 3-5 (64b) or 3-4 (32b) in the bit
|
|
* number field needs to be reversed compared to the big-endian bit
|
|
* fields. This can be achieved by XOR with 0x38 (64b) or 0x18 (32b).
|
|
*/
|
|
|
|
#ifndef _ASM_POWERPC_BITOPS_H
|
|
#define _ASM_POWERPC_BITOPS_H
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#ifndef _LINUX_BITOPS_H
|
|
#error only <linux/bitops.h> can be included directly
|
|
#endif
|
|
|
|
#include <linux/compiler.h>
|
|
#include <asm/asm-compat.h>
|
|
#include <asm/synch.h>
|
|
|
|
/* PPC bit number conversion */
|
|
#define PPC_BITLSHIFT(be) (BITS_PER_LONG - 1 - (be))
|
|
#define PPC_BIT(bit) (1UL << PPC_BITLSHIFT(bit))
|
|
#define PPC_BITMASK(bs, be) ((PPC_BIT(bs) - PPC_BIT(be)) | PPC_BIT(bs))
|
|
|
|
/* Put a PPC bit into a "normal" bit position */
|
|
#define PPC_BITEXTRACT(bits, ppc_bit, dst_bit) \
|
|
((((bits) >> PPC_BITLSHIFT(ppc_bit)) & 1) << (dst_bit))
|
|
|
|
#define PPC_BITLSHIFT32(be) (32 - 1 - (be))
|
|
#define PPC_BIT32(bit) (1UL << PPC_BITLSHIFT32(bit))
|
|
#define PPC_BITMASK32(bs, be) ((PPC_BIT32(bs) - PPC_BIT32(be))|PPC_BIT32(bs))
|
|
|
|
#define PPC_BITLSHIFT8(be) (8 - 1 - (be))
|
|
#define PPC_BIT8(bit) (1UL << PPC_BITLSHIFT8(bit))
|
|
#define PPC_BITMASK8(bs, be) ((PPC_BIT8(bs) - PPC_BIT8(be))|PPC_BIT8(bs))
|
|
|
|
#include <asm/barrier.h>
|
|
|
|
/* Macro for generating the ***_bits() functions */
|
|
#define DEFINE_BITOP(fn, op, prefix) \
|
|
static inline void fn(unsigned long mask, \
|
|
volatile unsigned long *_p) \
|
|
{ \
|
|
unsigned long old; \
|
|
unsigned long *p = (unsigned long *)_p; \
|
|
__asm__ __volatile__ ( \
|
|
prefix \
|
|
"1:" PPC_LLARX "%0,0,%3,0\n" \
|
|
#op "%I2 %0,%0,%2\n" \
|
|
PPC_STLCX "%0,0,%3\n" \
|
|
"bne- 1b\n" \
|
|
: "=&r" (old), "+m" (*p) \
|
|
: "rK" (mask), "r" (p) \
|
|
: "cc", "memory"); \
|
|
}
|
|
|
|
DEFINE_BITOP(set_bits, or, "")
|
|
DEFINE_BITOP(change_bits, xor, "")
|
|
|
|
static __always_inline bool is_rlwinm_mask_valid(unsigned long x)
|
|
{
|
|
if (!x)
|
|
return false;
|
|
if (x & 1)
|
|
x = ~x; // make the mask non-wrapping
|
|
x += x & -x; // adding the low set bit results in at most one bit set
|
|
|
|
return !(x & (x - 1));
|
|
}
|
|
|
|
#define DEFINE_CLROP(fn, prefix) \
|
|
static inline void fn(unsigned long mask, volatile unsigned long *_p) \
|
|
{ \
|
|
unsigned long old; \
|
|
unsigned long *p = (unsigned long *)_p; \
|
|
\
|
|
if (IS_ENABLED(CONFIG_PPC32) && \
|
|
__builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) {\
|
|
asm volatile ( \
|
|
prefix \
|
|
"1:" "lwarx %0,0,%3\n" \
|
|
"rlwinm %0,%0,0,%2\n" \
|
|
"stwcx. %0,0,%3\n" \
|
|
"bne- 1b\n" \
|
|
: "=&r" (old), "+m" (*p) \
|
|
: "n" (~mask), "r" (p) \
|
|
: "cc", "memory"); \
|
|
} else { \
|
|
asm volatile ( \
|
|
prefix \
|
|
"1:" PPC_LLARX "%0,0,%3,0\n" \
|
|
"andc %0,%0,%2\n" \
|
|
PPC_STLCX "%0,0,%3\n" \
|
|
"bne- 1b\n" \
|
|
: "=&r" (old), "+m" (*p) \
|
|
: "r" (mask), "r" (p) \
|
|
: "cc", "memory"); \
|
|
} \
|
|
}
|
|
|
|
DEFINE_CLROP(clear_bits, "")
|
|
DEFINE_CLROP(clear_bits_unlock, PPC_RELEASE_BARRIER)
|
|
|
|
static inline void arch_set_bit(int nr, volatile unsigned long *addr)
|
|
{
|
|
set_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
|
|
}
|
|
|
|
static inline void arch_clear_bit(int nr, volatile unsigned long *addr)
|
|
{
|
|
clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
|
|
}
|
|
|
|
static inline void arch_clear_bit_unlock(int nr, volatile unsigned long *addr)
|
|
{
|
|
clear_bits_unlock(BIT_MASK(nr), addr + BIT_WORD(nr));
|
|
}
|
|
|
|
static inline void arch_change_bit(int nr, volatile unsigned long *addr)
|
|
{
|
|
change_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
|
|
}
|
|
|
|
/* Like DEFINE_BITOP(), with changes to the arguments to 'op' and the output
|
|
* operands. */
|
|
#define DEFINE_TESTOP(fn, op, prefix, postfix, eh) \
|
|
static inline unsigned long fn( \
|
|
unsigned long mask, \
|
|
volatile unsigned long *_p) \
|
|
{ \
|
|
unsigned long old, t; \
|
|
unsigned long *p = (unsigned long *)_p; \
|
|
__asm__ __volatile__ ( \
|
|
prefix \
|
|
"1:" PPC_LLARX "%0,0,%3,%4\n" \
|
|
#op "%I2 %1,%0,%2\n" \
|
|
PPC_STLCX "%1,0,%3\n" \
|
|
"bne- 1b\n" \
|
|
postfix \
|
|
: "=&r" (old), "=&r" (t) \
|
|
: "rK" (mask), "r" (p), "i" (IS_ENABLED(CONFIG_PPC64) ? eh : 0) \
|
|
: "cc", "memory"); \
|
|
return (old & mask); \
|
|
}
|
|
|
|
DEFINE_TESTOP(test_and_set_bits, or, PPC_ATOMIC_ENTRY_BARRIER,
|
|
PPC_ATOMIC_EXIT_BARRIER, 0)
|
|
DEFINE_TESTOP(test_and_set_bits_lock, or, "",
|
|
PPC_ACQUIRE_BARRIER, 1)
|
|
DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
|
|
PPC_ATOMIC_EXIT_BARRIER, 0)
|
|
|
|
static inline unsigned long test_and_clear_bits(unsigned long mask, volatile unsigned long *_p)
|
|
{
|
|
unsigned long old, t;
|
|
unsigned long *p = (unsigned long *)_p;
|
|
|
|
if (IS_ENABLED(CONFIG_PPC32) &&
|
|
__builtin_constant_p(mask) && is_rlwinm_mask_valid(~mask)) {
|
|
asm volatile (
|
|
PPC_ATOMIC_ENTRY_BARRIER
|
|
"1:" "lwarx %0,0,%3\n"
|
|
"rlwinm %1,%0,0,%2\n"
|
|
"stwcx. %1,0,%3\n"
|
|
"bne- 1b\n"
|
|
PPC_ATOMIC_EXIT_BARRIER
|
|
: "=&r" (old), "=&r" (t)
|
|
: "n" (~mask), "r" (p)
|
|
: "cc", "memory");
|
|
} else {
|
|
asm volatile (
|
|
PPC_ATOMIC_ENTRY_BARRIER
|
|
"1:" PPC_LLARX "%0,0,%3,0\n"
|
|
"andc %1,%0,%2\n"
|
|
PPC_STLCX "%1,0,%3\n"
|
|
"bne- 1b\n"
|
|
PPC_ATOMIC_EXIT_BARRIER
|
|
: "=&r" (old), "=&r" (t)
|
|
: "r" (mask), "r" (p)
|
|
: "cc", "memory");
|
|
}
|
|
|
|
return (old & mask);
|
|
}
|
|
|
|
static inline int arch_test_and_set_bit(unsigned long nr,
|
|
volatile unsigned long *addr)
|
|
{
|
|
return test_and_set_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
|
|
}
|
|
|
|
static inline int arch_test_and_set_bit_lock(unsigned long nr,
|
|
volatile unsigned long *addr)
|
|
{
|
|
return test_and_set_bits_lock(BIT_MASK(nr),
|
|
addr + BIT_WORD(nr)) != 0;
|
|
}
|
|
|
|
static inline int arch_test_and_clear_bit(unsigned long nr,
|
|
volatile unsigned long *addr)
|
|
{
|
|
return test_and_clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
|
|
}
|
|
|
|
static inline int arch_test_and_change_bit(unsigned long nr,
|
|
volatile unsigned long *addr)
|
|
{
|
|
return test_and_change_bits(BIT_MASK(nr), addr + BIT_WORD(nr)) != 0;
|
|
}
|
|
|
|
#ifdef CONFIG_PPC64
|
|
static inline unsigned long
|
|
clear_bit_unlock_return_word(int nr, volatile unsigned long *addr)
|
|
{
|
|
unsigned long old, t;
|
|
unsigned long *p = (unsigned long *)addr + BIT_WORD(nr);
|
|
unsigned long mask = BIT_MASK(nr);
|
|
|
|
__asm__ __volatile__ (
|
|
PPC_RELEASE_BARRIER
|
|
"1:" PPC_LLARX "%0,0,%3,0\n"
|
|
"andc %1,%0,%2\n"
|
|
PPC_STLCX "%1,0,%3\n"
|
|
"bne- 1b\n"
|
|
: "=&r" (old), "=&r" (t)
|
|
: "r" (mask), "r" (p)
|
|
: "cc", "memory");
|
|
|
|
return old;
|
|
}
|
|
|
|
/*
|
|
* This is a special function for mm/filemap.c
|
|
* Bit 7 corresponds to PG_waiters.
|
|
*/
|
|
#define arch_clear_bit_unlock_is_negative_byte(nr, addr) \
|
|
(clear_bit_unlock_return_word(nr, addr) & BIT_MASK(7))
|
|
|
|
#endif /* CONFIG_PPC64 */
|
|
|
|
#include <asm-generic/bitops/non-atomic.h>
|
|
|
|
static inline void arch___clear_bit_unlock(int nr, volatile unsigned long *addr)
|
|
{
|
|
__asm__ __volatile__(PPC_RELEASE_BARRIER "" ::: "memory");
|
|
__clear_bit(nr, addr);
|
|
}
|
|
|
|
/*
|
|
* Return the zero-based bit position (LE, not IBM bit numbering) of
|
|
* the most significant 1-bit in a double word.
|
|
*/
|
|
#define __ilog2(x) ilog2(x)
|
|
|
|
#include <asm-generic/bitops/ffz.h>
|
|
|
|
#include <asm-generic/bitops/builtin-__ffs.h>
|
|
|
|
#include <asm-generic/bitops/builtin-ffs.h>
|
|
|
|
/*
|
|
* fls: find last (most-significant) bit set.
|
|
* Note fls(0) = 0, fls(1) = 1, fls(0x80000000) = 32.
|
|
*/
|
|
static __always_inline int fls(unsigned int x)
|
|
{
|
|
int lz;
|
|
|
|
if (__builtin_constant_p(x))
|
|
return x ? 32 - __builtin_clz(x) : 0;
|
|
asm("cntlzw %0,%1" : "=r" (lz) : "r" (x));
|
|
return 32 - lz;
|
|
}
|
|
|
|
#include <asm-generic/bitops/builtin-__fls.h>
|
|
|
|
/*
|
|
* 64-bit can do this using one cntlzd (count leading zeroes doubleword)
|
|
* instruction; for 32-bit we use the generic version, which does two
|
|
* 32-bit fls calls.
|
|
*/
|
|
#ifdef CONFIG_PPC64
|
|
static __always_inline int fls64(__u64 x)
|
|
{
|
|
int lz;
|
|
|
|
if (__builtin_constant_p(x))
|
|
return x ? 64 - __builtin_clzll(x) : 0;
|
|
asm("cntlzd %0,%1" : "=r" (lz) : "r" (x));
|
|
return 64 - lz;
|
|
}
|
|
#else
|
|
#include <asm-generic/bitops/fls64.h>
|
|
#endif
|
|
|
|
#ifdef CONFIG_PPC64
|
|
unsigned int __arch_hweight8(unsigned int w);
|
|
unsigned int __arch_hweight16(unsigned int w);
|
|
unsigned int __arch_hweight32(unsigned int w);
|
|
unsigned long __arch_hweight64(__u64 w);
|
|
#include <asm-generic/bitops/const_hweight.h>
|
|
#else
|
|
#include <asm-generic/bitops/hweight.h>
|
|
#endif
|
|
|
|
/* wrappers that deal with KASAN instrumentation */
|
|
#include <asm-generic/bitops/instrumented-atomic.h>
|
|
#include <asm-generic/bitops/instrumented-lock.h>
|
|
|
|
/* Little-endian versions */
|
|
#include <asm-generic/bitops/le.h>
|
|
|
|
/* Bitmap functions for the ext2 filesystem */
|
|
|
|
#include <asm-generic/bitops/ext2-atomic-setbit.h>
|
|
|
|
#include <asm-generic/bitops/sched.h>
|
|
|
|
#endif /* __KERNEL__ */
|
|
|
|
#endif /* _ASM_POWERPC_BITOPS_H */
|