mirror of
https://github.com/AuxXxilium/linux_dsm_epyc7002.git
synced 2024-12-23 05:56:08 +07:00
169c474fb2
Pach series "Introduce the for_each_set_clump8 macro", v18. While adding GPIO get_multiple/set_multiple callback support for various drivers, I noticed a pattern of looping manifesting that would be useful standardized as a macro. This patchset introduces the for_each_set_clump8 macro and utilizes it in several GPIO drivers. The for_each_set_clump macro8 facilitates a for-loop syntax that iterates over a memory region entire groups of set bits at a time. For example, suppose you would like to iterate over a 32-bit integer 8 bits at a time, skipping over 8-bit groups with no set bit, where XXXXXXXX represents the current 8-bit group: Example: 10111110 00000000 11111111 00110011 First loop: 10111110 00000000 11111111 XXXXXXXX Second loop: 10111110 00000000 XXXXXXXX 00110011 Third loop: XXXXXXXX 00000000 11111111 00110011 Each iteration of the loop returns the next 8-bit group that has at least one set bit. The for_each_set_clump8 macro has four parameters: * start: set to the bit offset of the current clump * clump: set to the current clump value * bits: bitmap to search within * size: bitmap size in number of bits In this version of the patchset, the for_each_set_clump macro has been reimplemented and simplified based on the suggestions provided by Rasmus Villemoes and Andy Shevchenko in the version 4 submission. In particular, the function of the for_each_set_clump macro has been restricted to handle only 8-bit clumps; the drivers that use the for_each_set_clump macro only handle 8-bit ports so a generic for_each_set_clump implementation is not necessary. Thus, a solution for large clumps (i.e. those larger than the width of a bitmap word) can be postponed until a driver appears that actually requires such a generic for_each_set_clump implementation. For what it's worth, a semi-generic for_each_set_clump (i.e. for clumps smaller than the width of a bitmap word) can be implemented by simply replacing the hardcoded '8' and '0xFF' instances with respective variables. I have not yet had a need for such an implementation, and since it falls short of a true generic for_each_set_clump function, I have decided to forgo such an implementation for now. In addition, the bitmap_get_value8 and bitmap_set_value8 functions are introduced to get and set 8-bit values respectively. Their use is based on the behavior suggested in the patchset version 4 review. This patch (of 14): This macro iterates for each 8-bit group of bits (clump) with set bits, within a bitmap memory region. For each iteration, "start" is set to the bit offset of the found clump, while the respective clump value is stored to the location pointed by "clump". Additionally, the bitmap_get_value8 and bitmap_set_value8 functions are introduced to respectively get and set an 8-bit value in a bitmap memory region. [gustavo@embeddedor.com: fix potential sign-extension overflow] Link: http://lkml.kernel.org/r/20191015184657.GA26541@embeddedor [akpm@linux-foundation.org: s/ULL/UL/, per Joe] [vilhelm.gray@gmail.com: add for_each_set_clump8 documentation] Link: http://lkml.kernel.org/r/20191016161825.301082-1-vilhelm.gray@gmail.com Link: http://lkml.kernel.org/r/893c3b4f03266c9496137cc98ac2b1bd27f92c73.1570641097.git.vilhelm.gray@gmail.com Signed-off-by: William Breathitt Gray <vilhelm.gray@gmail.com> Signed-off-by: Gustavo A. R. Silva <gustavo@embeddedor.com> Suggested-by: Andy Shevchenko <andy.shevchenko@gmail.com> Suggested-by: Rasmus Villemoes <linux@rasmusvillemoes.dk> Suggested-by: Lukas Wunner <lukas@wunner.de> Tested-by: Andy Shevchenko <andriy.shevchenko@linux.intel.com> Cc: Arnd Bergmann <arnd@arndb.de> Cc: Linus Walleij <linus.walleij@linaro.org> Cc: Bartosz Golaszewski <bgolaszewski@baylibre.com> Cc: Masahiro Yamada <yamada.masahiro@socionext.com> Cc: Geert Uytterhoeven <geert@linux-m68k.org> Cc: Phil Reid <preid@electromag.com.au> Cc: Geert Uytterhoeven <geert+renesas@glider.be> Cc: Mathias Duckeck <m.duckeck@kunbus.de> Cc: Morten Hein Tiljeset <morten.tiljeset@prevas.dk> Cc: Sean Nyekjaer <sean.nyekjaer@prevas.dk> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
302 lines
7.4 KiB
C
302 lines
7.4 KiB
C
/* SPDX-License-Identifier: GPL-2.0 */
|
|
#ifndef _LINUX_BITOPS_H
|
|
#define _LINUX_BITOPS_H
|
|
#include <asm/types.h>
|
|
#include <linux/bits.h>
|
|
|
|
/* Set bits in the first 'n' bytes when loaded from memory */
|
|
#ifdef __LITTLE_ENDIAN
|
|
# define aligned_byte_mask(n) ((1UL << 8*(n))-1)
|
|
#else
|
|
# define aligned_byte_mask(n) (~0xffUL << (BITS_PER_LONG - 8 - 8*(n)))
|
|
#endif
|
|
|
|
#define BITS_PER_TYPE(type) (sizeof(type) * BITS_PER_BYTE)
|
|
#define BITS_TO_LONGS(nr) DIV_ROUND_UP(nr, BITS_PER_TYPE(long))
|
|
|
|
extern unsigned int __sw_hweight8(unsigned int w);
|
|
extern unsigned int __sw_hweight16(unsigned int w);
|
|
extern unsigned int __sw_hweight32(unsigned int w);
|
|
extern unsigned long __sw_hweight64(__u64 w);
|
|
|
|
/*
|
|
* Include this here because some architectures need generic_ffs/fls in
|
|
* scope
|
|
*/
|
|
#include <asm/bitops.h>
|
|
|
|
#define for_each_set_bit(bit, addr, size) \
|
|
for ((bit) = find_first_bit((addr), (size)); \
|
|
(bit) < (size); \
|
|
(bit) = find_next_bit((addr), (size), (bit) + 1))
|
|
|
|
/* same as for_each_set_bit() but use bit as value to start with */
|
|
#define for_each_set_bit_from(bit, addr, size) \
|
|
for ((bit) = find_next_bit((addr), (size), (bit)); \
|
|
(bit) < (size); \
|
|
(bit) = find_next_bit((addr), (size), (bit) + 1))
|
|
|
|
#define for_each_clear_bit(bit, addr, size) \
|
|
for ((bit) = find_first_zero_bit((addr), (size)); \
|
|
(bit) < (size); \
|
|
(bit) = find_next_zero_bit((addr), (size), (bit) + 1))
|
|
|
|
/* same as for_each_clear_bit() but use bit as value to start with */
|
|
#define for_each_clear_bit_from(bit, addr, size) \
|
|
for ((bit) = find_next_zero_bit((addr), (size), (bit)); \
|
|
(bit) < (size); \
|
|
(bit) = find_next_zero_bit((addr), (size), (bit) + 1))
|
|
|
|
/**
|
|
* for_each_set_clump8 - iterate over bitmap for each 8-bit clump with set bits
|
|
* @start: bit offset to start search and to store the current iteration offset
|
|
* @clump: location to store copy of current 8-bit clump
|
|
* @bits: bitmap address to base the search on
|
|
* @size: bitmap size in number of bits
|
|
*/
|
|
#define for_each_set_clump8(start, clump, bits, size) \
|
|
for ((start) = find_first_clump8(&(clump), (bits), (size)); \
|
|
(start) < (size); \
|
|
(start) = find_next_clump8(&(clump), (bits), (size), (start) + 8))
|
|
|
|
static inline int get_bitmask_order(unsigned int count)
|
|
{
|
|
int order;
|
|
|
|
order = fls(count);
|
|
return order; /* We could be slightly more clever with -1 here... */
|
|
}
|
|
|
|
static __always_inline unsigned long hweight_long(unsigned long w)
|
|
{
|
|
return sizeof(w) == 4 ? hweight32(w) : hweight64(w);
|
|
}
|
|
|
|
/**
|
|
* rol64 - rotate a 64-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u64 rol64(__u64 word, unsigned int shift)
|
|
{
|
|
return (word << (shift & 63)) | (word >> ((-shift) & 63));
|
|
}
|
|
|
|
/**
|
|
* ror64 - rotate a 64-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u64 ror64(__u64 word, unsigned int shift)
|
|
{
|
|
return (word >> (shift & 63)) | (word << ((-shift) & 63));
|
|
}
|
|
|
|
/**
|
|
* rol32 - rotate a 32-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u32 rol32(__u32 word, unsigned int shift)
|
|
{
|
|
return (word << (shift & 31)) | (word >> ((-shift) & 31));
|
|
}
|
|
|
|
/**
|
|
* ror32 - rotate a 32-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u32 ror32(__u32 word, unsigned int shift)
|
|
{
|
|
return (word >> (shift & 31)) | (word << ((-shift) & 31));
|
|
}
|
|
|
|
/**
|
|
* rol16 - rotate a 16-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u16 rol16(__u16 word, unsigned int shift)
|
|
{
|
|
return (word << (shift & 15)) | (word >> ((-shift) & 15));
|
|
}
|
|
|
|
/**
|
|
* ror16 - rotate a 16-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u16 ror16(__u16 word, unsigned int shift)
|
|
{
|
|
return (word >> (shift & 15)) | (word << ((-shift) & 15));
|
|
}
|
|
|
|
/**
|
|
* rol8 - rotate an 8-bit value left
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u8 rol8(__u8 word, unsigned int shift)
|
|
{
|
|
return (word << (shift & 7)) | (word >> ((-shift) & 7));
|
|
}
|
|
|
|
/**
|
|
* ror8 - rotate an 8-bit value right
|
|
* @word: value to rotate
|
|
* @shift: bits to roll
|
|
*/
|
|
static inline __u8 ror8(__u8 word, unsigned int shift)
|
|
{
|
|
return (word >> (shift & 7)) | (word << ((-shift) & 7));
|
|
}
|
|
|
|
/**
|
|
* sign_extend32 - sign extend a 32-bit value using specified bit as sign-bit
|
|
* @value: value to sign extend
|
|
* @index: 0 based bit index (0<=index<32) to sign bit
|
|
*
|
|
* This is safe to use for 16- and 8-bit types as well.
|
|
*/
|
|
static inline __s32 sign_extend32(__u32 value, int index)
|
|
{
|
|
__u8 shift = 31 - index;
|
|
return (__s32)(value << shift) >> shift;
|
|
}
|
|
|
|
/**
|
|
* sign_extend64 - sign extend a 64-bit value using specified bit as sign-bit
|
|
* @value: value to sign extend
|
|
* @index: 0 based bit index (0<=index<64) to sign bit
|
|
*/
|
|
static inline __s64 sign_extend64(__u64 value, int index)
|
|
{
|
|
__u8 shift = 63 - index;
|
|
return (__s64)(value << shift) >> shift;
|
|
}
|
|
|
|
static inline unsigned fls_long(unsigned long l)
|
|
{
|
|
if (sizeof(l) == 4)
|
|
return fls(l);
|
|
return fls64(l);
|
|
}
|
|
|
|
static inline int get_count_order(unsigned int count)
|
|
{
|
|
int order;
|
|
|
|
order = fls(count) - 1;
|
|
if (count & (count - 1))
|
|
order++;
|
|
return order;
|
|
}
|
|
|
|
/**
|
|
* get_count_order_long - get order after rounding @l up to power of 2
|
|
* @l: parameter
|
|
*
|
|
* it is same as get_count_order() but with long type parameter
|
|
*/
|
|
static inline int get_count_order_long(unsigned long l)
|
|
{
|
|
if (l == 0UL)
|
|
return -1;
|
|
else if (l & (l - 1UL))
|
|
return (int)fls_long(l);
|
|
else
|
|
return (int)fls_long(l) - 1;
|
|
}
|
|
|
|
/**
|
|
* __ffs64 - find first set bit in a 64 bit word
|
|
* @word: The 64 bit word
|
|
*
|
|
* On 64 bit arches this is a synomyn for __ffs
|
|
* The result is not defined if no bits are set, so check that @word
|
|
* is non-zero before calling this.
|
|
*/
|
|
static inline unsigned long __ffs64(u64 word)
|
|
{
|
|
#if BITS_PER_LONG == 32
|
|
if (((u32)word) == 0UL)
|
|
return __ffs((u32)(word >> 32)) + 32;
|
|
#elif BITS_PER_LONG != 64
|
|
#error BITS_PER_LONG not 32 or 64
|
|
#endif
|
|
return __ffs((unsigned long)word);
|
|
}
|
|
|
|
/**
|
|
* assign_bit - Assign value to a bit in memory
|
|
* @nr: the bit to set
|
|
* @addr: the address to start counting from
|
|
* @value: the value to assign
|
|
*/
|
|
static __always_inline void assign_bit(long nr, volatile unsigned long *addr,
|
|
bool value)
|
|
{
|
|
if (value)
|
|
set_bit(nr, addr);
|
|
else
|
|
clear_bit(nr, addr);
|
|
}
|
|
|
|
static __always_inline void __assign_bit(long nr, volatile unsigned long *addr,
|
|
bool value)
|
|
{
|
|
if (value)
|
|
__set_bit(nr, addr);
|
|
else
|
|
__clear_bit(nr, addr);
|
|
}
|
|
|
|
#ifdef __KERNEL__
|
|
|
|
#ifndef set_mask_bits
|
|
#define set_mask_bits(ptr, mask, bits) \
|
|
({ \
|
|
const typeof(*(ptr)) mask__ = (mask), bits__ = (bits); \
|
|
typeof(*(ptr)) old__, new__; \
|
|
\
|
|
do { \
|
|
old__ = READ_ONCE(*(ptr)); \
|
|
new__ = (old__ & ~mask__) | bits__; \
|
|
} while (cmpxchg(ptr, old__, new__) != old__); \
|
|
\
|
|
old__; \
|
|
})
|
|
#endif
|
|
|
|
#ifndef bit_clear_unless
|
|
#define bit_clear_unless(ptr, clear, test) \
|
|
({ \
|
|
const typeof(*(ptr)) clear__ = (clear), test__ = (test);\
|
|
typeof(*(ptr)) old__, new__; \
|
|
\
|
|
do { \
|
|
old__ = READ_ONCE(*(ptr)); \
|
|
new__ = old__ & ~clear__; \
|
|
} while (!(old__ & test__) && \
|
|
cmpxchg(ptr, old__, new__) != old__); \
|
|
\
|
|
!(old__ & test__); \
|
|
})
|
|
#endif
|
|
|
|
#ifndef find_last_bit
|
|
/**
|
|
* find_last_bit - find the last set bit in a memory region
|
|
* @addr: The address to start the search at
|
|
* @size: The number of bits to search
|
|
*
|
|
* Returns the bit number of the last set bit, or size.
|
|
*/
|
|
extern unsigned long find_last_bit(const unsigned long *addr,
|
|
unsigned long size);
|
|
#endif
|
|
|
|
#endif /* __KERNEL__ */
|
|
#endif
|