linux_dsm_epyc7002/arch/powerpc/include/asm/bitops.h
Christophe Leroy f83647d642 powerpc: Discard ffs()/__ffs() function and use builtin functions instead
With the ffs() function as defined in arch/powerpc/include/asm/bitops.h
GCC will not optimise the code in case of constant parameter, as shown
by the small exemple below.

int ffs_test(void)
{
	return 4 << ffs(31);
}

c0012334 <ffs_test>:
c0012334:       39 20 00 01     li      r9,1
c0012338:       38 60 00 04     li      r3,4
c001233c:       7d 29 00 34     cntlzw  r9,r9
c0012340:       21 29 00 20     subfic  r9,r9,32
c0012344:       7c 63 48 30     slw     r3,r3,r9
c0012348:       4e 80 00 20     blr

With this patch, the same function will compile as follows:

c0012334 <ffs_test>:
c0012334:       38 60 00 08     li      r3,8
c0012338:       4e 80 00 20     blr

The same happens with __ffs()

For non constant calls, the generated code is doing the same,
allthought it is slightly different on 64 bits for ffs():

unsigned long test__ffs(unsigned long x)
{
	return __ffs(x);
}

int testffs(int x)
{
	return ffs(x);
}

On PPC32, before the patch:
0000003c <test__ffs>:
  3c:	7d 23 00 d0 	neg     r9,r3
  40:	7d 23 18 38 	and     r3,r9,r3
  44:	7c 63 00 34 	cntlzw  r3,r3
  48:	20 63 00 1f 	subfic  r3,r3,31
  4c:	4e 80 00 20 	blr

00000050 <testffs>:
  50:	7d 23 00 d0 	neg     r9,r3
  54:	7d 23 18 38 	and     r3,r9,r3
  58:	7c 63 00 34 	cntlzw  r3,r3
  5c:	20 63 00 20 	subfic  r3,r3,32
  60:	4e 80 00 20 	blr

On PPC32, after the patch:
0000002c <test__ffs>:
  2c:	7d 23 00 d0 	neg     r9,r3
  30:	7d 23 18 38 	and     r3,r9,r3
  34:	7c 63 00 34 	cntlzw  r3,r3
  38:	20 63 00 1f 	subfic  r3,r3,31
  3c:	4e 80 00 20 	blr

00000040 <testffs>:
  40:	7d 23 00 d0 	neg     r9,r3
  44:	7d 23 18 38 	and     r3,r9,r3
  48:	7c 63 00 34 	cntlzw  r3,r3
  4c:	20 63 00 20 	subfic  r3,r3,32
  50:	4e 80 00 20 	blr

On PPC64, before the patch:
0000000000000060 <.test__ffs>:
  60:	7c 03 00 d0 	neg     r0,r3
  64:	7c 03 18 38 	and     r3,r0,r3
  68:	7c 63 00 74 	cntlzd  r3,r3
  6c:	20 63 00 3f 	subfic  r3,r3,63
  70:	7c 63 07 b4 	extsw   r3,r3
  74:	4e 80 00 20 	blr

0000000000000080 <.testffs>:
  80:	7c 03 00 d0 	neg     r0,r3
  84:	7c 03 18 38 	and     r3,r0,r3
  88:	7c 63 00 74 	cntlzd  r3,r3
  8c:	20 63 00 40 	subfic  r3,r3,64
  90:	7c 63 07 b4 	extsw   r3,r3
  94:	4e 80 00 20 	blr

On PPC64, after the patch:
0000000000000050 <.test__ffs>:
  50:	7c 03 00 d0 	neg     r0,r3
  54:	7c 03 18 38 	and     r3,r0,r3
  58:	7c 63 00 74 	cntlzd  r3,r3
  5c:	20 63 00 3f 	subfic  r3,r3,63
  60:	4e 80 00 20 	blr

0000000000000070 <.testffs>:
  70:	7c 03 00 d0 	neg     r0,r3
  74:	7c 03 18 38 	and     r3,r0,r3
  78:	7c 63 00 34 	cntlzw  r3,r3
  7c:	20 63 00 20 	subfic  r3,r3,32
  80:	7c 63 07 b4 	extsw   r3,r3
  84:	4e 80 00 20 	blr
(ffs() operates on an int so cntlzw is equivalent to cntlzd)

In addition, when reading the generated vmlinux, we can observe
that with the builtin functions, GCC sometimes efficiently spreads
the instructions within the generated functions while the inline
assembly force them to remain grouped together.

__builtin_ffs() is already used in arch/powerpc/include/asm/page_32.h

Those builtins have been in GCC since at least 3.4.6 (see
https://gcc.gnu.org/onlinedocs/gcc-3.4.6/gcc/Other-Builtins.html )

Signed-off-by: Christophe Leroy <christophe.leroy@c-s.fr>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
2017-06-02 19:23:54 +10:00

318 lines
8.8 KiB
C

/*
* 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).
*
* This program is free software; you can redistribute it and/or
* modify it under the terms of the GNU General Public License
* as published by the Free Software Foundation; either version
* 2 of the License, or (at your option) any later version.
*/
#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" \
stringify_in_c(op) "%0,%0,%2\n" \
PPC405_ERR77(0,%3) \
PPC_STLCX "%0,0,%3\n" \
"bne- 1b\n" \
: "=&r" (old), "+m" (*p) \
: "r" (mask), "r" (p) \
: "cc", "memory"); \
}
DEFINE_BITOP(set_bits, or, "")
DEFINE_BITOP(clear_bits, andc, "")
DEFINE_BITOP(clear_bits_unlock, andc, PPC_RELEASE_BARRIER)
DEFINE_BITOP(change_bits, xor, "")
static __inline__ void set_bit(int nr, volatile unsigned long *addr)
{
set_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
}
static __inline__ void clear_bit(int nr, volatile unsigned long *addr)
{
clear_bits(BIT_MASK(nr), addr + BIT_WORD(nr));
}
static __inline__ void clear_bit_unlock(int nr, volatile unsigned long *addr)
{
clear_bits_unlock(BIT_MASK(nr), addr + BIT_WORD(nr));
}
static __inline__ void 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,eh) "\n" \
stringify_in_c(op) "%1,%0,%2\n" \
PPC405_ERR77(0,%3) \
PPC_STLCX "%1,0,%3\n" \
"bne- 1b\n" \
postfix \
: "=&r" (old), "=&r" (t) \
: "r" (mask), "r" (p) \
: "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_clear_bits, andc, PPC_ATOMIC_ENTRY_BARRIER,
PPC_ATOMIC_EXIT_BARRIER, 0)
DEFINE_TESTOP(test_and_change_bits, xor, PPC_ATOMIC_ENTRY_BARRIER,
PPC_ATOMIC_EXIT_BARRIER, 0)
static __inline__ int 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 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 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 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"
PPC405_ERR77(0,%3)
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 */
#define clear_bit_unlock_is_negative_byte(nr, addr) \
(clear_bit_unlock_return_word(nr, addr) & BIT_MASK(PG_waiters))
#endif /* CONFIG_PPC64 */
#include <asm-generic/bitops/non-atomic.h>
static __inline__ void __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.
*/
static __inline__ __attribute__((const))
int __ilog2(unsigned long x)
{
int lz;
asm (PPC_CNTLZL "%0,%1" : "=r" (lz) : "r" (x));
return BITS_PER_LONG - 1 - lz;
}
static inline __attribute__((const))
int __ilog2_u32(u32 n)
{
int bit;
asm ("cntlzw %0,%1" : "=r" (bit) : "r" (n));
return 31 - bit;
}
#ifdef __powerpc64__
static inline __attribute__((const))
int __ilog2_u64(u64 n)
{
int bit;
asm ("cntlzd %0,%1" : "=r" (bit) : "r" (n));
return 63 - bit;
}
#endif
/*
* Determines the bit position of the least significant 0 bit in the
* specified double word. The returned bit position will be
* zero-based, starting from the right side (63/31 - 0).
*/
static __inline__ unsigned long ffz(unsigned long x)
{
/* no zero exists anywhere in the 8 byte area. */
if ((x = ~x) == 0)
return BITS_PER_LONG;
/*
* Calculate the bit position of the least significant '1' bit in x
* (since x has been changed this will actually be the least significant
* '0' bit in * the original x). Note: (x & -x) gives us a mask that
* is the least significant * (RIGHT-most) 1-bit of the value in x.
*/
return __ilog2(x & -x);
}
#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 __inline__ int fls(unsigned int x)
{
int lz;
asm ("cntlzw %0,%1" : "=r" (lz) : "r" (x));
return 32 - lz;
}
static __inline__ unsigned long __fls(unsigned long x)
{
return __ilog2(x);
}
/*
* 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 __powerpc64__
static __inline__ int fls64(__u64 x)
{
int lz;
asm ("cntlzd %0,%1" : "=r" (lz) : "r" (x));
return 64 - lz;
}
#else
#include <asm-generic/bitops/fls64.h>
#endif /* __powerpc64__ */
#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
#include <asm-generic/bitops/find.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 */