From ba1afa676d0babf99e99f5415db43fdd7ecef104 Mon Sep 17 00:00:00 2001 From: Qu Wenruo Date: Fri, 24 Jun 2022 17:31:47 +0800 Subject: [PATCH 01/26] lib: bitmap: fix the duplicated comments on bitmap_to_arr64() Thanks to the recent commit 0a97953fd221 ("lib: add bitmap_{from,to}_arr64") now we can directly convert a U64 value into a bitmap and vice verse. However when checking the header there is duplicated helper for bitmap_to_arr64(), but no bitmap_from_arr64(). Just fix the copy-n-paste error. Signed-off-by: Qu Wenruo Signed-off-by: Yury Norov --- include/linux/bitmap.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index 2e6cd5681040..f091a1664bf1 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -71,9 +71,9 @@ struct device; * bitmap_release_region(bitmap, pos, order) Free specified bit region * bitmap_allocate_region(bitmap, pos, order) Allocate specified bit region * bitmap_from_arr32(dst, buf, nbits) Copy nbits from u32[] buf to dst + * bitmap_from_arr64(dst, buf, nbits) Copy nbits from u64[] buf to dst * bitmap_to_arr32(buf, src, nbits) Copy nbits from buf to u32[] dst * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst - * bitmap_to_arr64(buf, src, nbits) Copy nbits from buf to u64[] dst * bitmap_get_value8(map, start) Get 8bit value from map at start * bitmap_set_value8(map, value, start) Set 8bit value to map at start * From e5a16a5c4602c119262f350274021f90465f479d Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:05 +0200 Subject: [PATCH 02/26] ia64, processor: fix -Wincompatible-pointer-types in ia64_get_irr() test_bit(), as any other bitmap op, takes `unsigned long *` as a second argument (pointer to the actual bitmap), as any bitmap itself is an array of unsigned longs. However, the ia64_get_irr() code passes a ref to `u64` as a second argument. This works with the ia64 bitops implementation due to that they have `void *` as the second argument and then cast it later on. This works with the bitmap API itself due to that `unsigned long` has the same size on ia64 as `u64` (`unsigned long long`), but from the compiler PoV those two are different. Define @irr as `unsigned long` to fix that. That implies no functional changes. Has been hidden for 16 years! Fixes: a58786917ce2 ("[IA64] avoid broken SAL_CACHE_FLUSH implementations") Cc: stable@vger.kernel.org # 2.6.16+ Reported-by: kernel test robot Signed-off-by: Alexander Lobakin Reviewed-by: Andy Shevchenko Reviewed-by: Yury Norov Signed-off-by: Yury Norov --- arch/ia64/include/asm/processor.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/ia64/include/asm/processor.h b/arch/ia64/include/asm/processor.h index 7cbce290f4e5..757c2f6d8d4b 100644 --- a/arch/ia64/include/asm/processor.h +++ b/arch/ia64/include/asm/processor.h @@ -538,7 +538,7 @@ ia64_get_irr(unsigned int vector) { unsigned int reg = vector / 64; unsigned int bit = vector % 64; - u64 irr; + unsigned long irr; switch (reg) { case 0: irr = ia64_getreg(_IA64_REG_CR_IRR0); break; From 21bb8af513d35c005c401706030f4eb469538d1d Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:06 +0200 Subject: [PATCH 03/26] bitops: always define asm-generic non-atomic bitops Move generic non-atomic bitops from the asm-generic header which gets included only when there are no architecture-specific alternatives, to a separate independent file to make them always available. Almost no actual code changes, only one comment added to generic_test_bit() saying that it's an atomic operation itself and thus `volatile` must always stay there with no cast-aways. Suggested-by: Andy Shevchenko # comment Suggested-by: Marco Elver # reference to kernel-doc Signed-off-by: Alexander Lobakin Reviewed-by: Andy Shevchenko Reviewed-by: Marco Elver Signed-off-by: Yury Norov --- .../asm-generic/bitops/generic-non-atomic.h | 130 ++++++++++++++++++ include/asm-generic/bitops/non-atomic.h | 110 ++------------- 2 files changed, 138 insertions(+), 102 deletions(-) create mode 100644 include/asm-generic/bitops/generic-non-atomic.h diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h new file mode 100644 index 000000000000..7226488810e5 --- /dev/null +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -0,0 +1,130 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H +#define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H + +#include + +#ifndef _LINUX_BITOPS_H +#error only can be included directly +#endif + +/* + * Generic definitions for bit operations, should not be used in regular code + * directly. + */ + +/** + * generic___set_bit - Set a bit in memory + * @nr: the bit to set + * @addr: the address to start counting from + * + * Unlike set_bit(), this function is non-atomic and may be reordered. + * If it's called on the same region of memory simultaneously, the effect + * may be that only one operation succeeds. + */ +static __always_inline void +generic___set_bit(unsigned int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p |= mask; +} + +static __always_inline void +generic___clear_bit(unsigned int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p &= ~mask; +} + +/** + * generic___change_bit - Toggle a bit in memory + * @nr: the bit to change + * @addr: the address to start counting from + * + * Unlike change_bit(), this function is non-atomic and may be reordered. + * If it's called on the same region of memory simultaneously, the effect + * may be that only one operation succeeds. + */ +static __always_inline +void generic___change_bit(unsigned int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + + *p ^= mask; +} + +/** + * generic___test_and_set_bit - Set a bit and return its old value + * @nr: Bit to set + * @addr: Address to count from + * + * This operation is non-atomic and can be reordered. + * If two examples of this operation race, one can appear to succeed + * but actually fail. You must protect multiple accesses with a lock. + */ +static __always_inline int +generic___test_and_set_bit(unsigned int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old = *p; + + *p = old | mask; + return (old & mask) != 0; +} + +/** + * generic___test_and_clear_bit - Clear a bit and return its old value + * @nr: Bit to clear + * @addr: Address to count from + * + * This operation is non-atomic and can be reordered. + * If two examples of this operation race, one can appear to succeed + * but actually fail. You must protect multiple accesses with a lock. + */ +static __always_inline int +generic___test_and_clear_bit(unsigned int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old = *p; + + *p = old & ~mask; + return (old & mask) != 0; +} + +/* WARNING: non atomic and it can be reordered! */ +static __always_inline int +generic___test_and_change_bit(unsigned int nr, volatile unsigned long *addr) +{ + unsigned long mask = BIT_MASK(nr); + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + unsigned long old = *p; + + *p = old ^ mask; + return (old & mask) != 0; +} + +/** + * generic_test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline int +generic_test_bit(unsigned int nr, const volatile unsigned long *addr) +{ + /* + * Unlike the bitops with the '__' prefix above, this one *is* atomic, + * so `volatile` must always stay here with no cast-aways. See + * `Documentation/atomic_bitops.txt` for the details. + */ + return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); +} + +#endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */ diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h index 078cc68be2f1..23d3abc1e10d 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -2,121 +2,27 @@ #ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#include +#include -/** - * arch___set_bit - Set a bit in memory - * @nr: the bit to set - * @addr: the address to start counting from - * - * Unlike set_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static __always_inline void -arch___set_bit(unsigned int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p |= mask; -} +#define arch___set_bit generic___set_bit #define __set_bit arch___set_bit -static __always_inline void -arch___clear_bit(unsigned int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p &= ~mask; -} +#define arch___clear_bit generic___clear_bit #define __clear_bit arch___clear_bit -/** - * arch___change_bit - Toggle a bit in memory - * @nr: the bit to change - * @addr: the address to start counting from - * - * Unlike change_bit(), this function is non-atomic and may be reordered. - * If it's called on the same region of memory simultaneously, the effect - * may be that only one operation succeeds. - */ -static __always_inline -void arch___change_bit(unsigned int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - - *p ^= mask; -} +#define arch___change_bit generic___change_bit #define __change_bit arch___change_bit -/** - * arch___test_and_set_bit - Set a bit and return its old value - * @nr: Bit to set - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static __always_inline int -arch___test_and_set_bit(unsigned int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old | mask; - return (old & mask) != 0; -} +#define arch___test_and_set_bit generic___test_and_set_bit #define __test_and_set_bit arch___test_and_set_bit -/** - * arch___test_and_clear_bit - Clear a bit and return its old value - * @nr: Bit to clear - * @addr: Address to count from - * - * This operation is non-atomic and can be reordered. - * If two examples of this operation race, one can appear to succeed - * but actually fail. You must protect multiple accesses with a lock. - */ -static __always_inline int -arch___test_and_clear_bit(unsigned int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old & ~mask; - return (old & mask) != 0; -} +#define arch___test_and_clear_bit generic___test_and_clear_bit #define __test_and_clear_bit arch___test_and_clear_bit -/* WARNING: non atomic and it can be reordered! */ -static __always_inline int -arch___test_and_change_bit(unsigned int nr, volatile unsigned long *addr) -{ - unsigned long mask = BIT_MASK(nr); - unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); - unsigned long old = *p; - - *p = old ^ mask; - return (old & mask) != 0; -} +#define arch___test_and_change_bit generic___test_and_change_bit #define __test_and_change_bit arch___test_and_change_bit -/** - * arch_test_bit - Determine whether a bit is set - * @nr: bit number to test - * @addr: Address to start counting from - */ -static __always_inline int -arch_test_bit(unsigned int nr, const volatile unsigned long *addr) -{ - return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); -} +#define arch_test_bit generic_test_bit #define test_bit arch_test_bit #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ From 0e862838f290147ea9c16db852d8d494b552d38d Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:07 +0200 Subject: [PATCH 04/26] bitops: unify non-atomic bitops prototypes across architectures Currently, there is a mess with the prototypes of the non-atomic bitops across the different architectures: ret bool, int, unsigned long nr int, long, unsigned int, unsigned long addr volatile unsigned long *, volatile void * Thankfully, it doesn't provoke any bugs, but can sometimes make the compiler angry when it's not handy at all. Adjust all the prototypes to the following standard: ret bool retval can be only 0 or 1 nr unsigned long native; signed makes no sense addr volatile unsigned long * bitmaps are arrays of ulongs Next, some architectures don't define 'arch_' versions as they don't support instrumentation, others do. To make sure there is always the same set of callables present and to ease any potential future changes, make them all follow the rule: * architecture-specific files define only 'arch_' versions; * non-prefixed versions can be defined only in asm-generic files; and place the non-prefixed definitions into a new file in asm-generic to be included by non-instrumented architectures. Finally, add some static assertions in order to prevent people from making a mess in this room again. I also used the %__always_inline attribute consistently, so that they always get resolved to the actual operations. Suggested-by: Andy Shevchenko Signed-off-by: Alexander Lobakin Acked-by: Mark Rutland Reviewed-by: Yury Norov Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- arch/alpha/include/asm/bitops.h | 32 +++++----- arch/hexagon/include/asm/bitops.h | 24 +++++--- arch/ia64/include/asm/bitops.h | 42 +++++++------ arch/m68k/include/asm/bitops.h | 49 ++++++++++----- arch/s390/include/asm/bitops.h | 61 ++++++++++--------- arch/sh/include/asm/bitops-op32.h | 34 +++++++---- arch/x86/include/asm/bitops.h | 22 ++++--- .../asm-generic/bitops/generic-non-atomic.h | 24 ++++---- .../bitops/instrumented-non-atomic.h | 21 ++++--- include/asm-generic/bitops/non-atomic.h | 13 +--- .../bitops/non-instrumented-non-atomic.h | 16 +++++ include/linux/bitops.h | 17 ++++++ tools/include/asm-generic/bitops/non-atomic.h | 24 +++++--- 13 files changed, 229 insertions(+), 150 deletions(-) create mode 100644 include/asm-generic/bitops/non-instrumented-non-atomic.h diff --git a/arch/alpha/include/asm/bitops.h b/arch/alpha/include/asm/bitops.h index e1d8483a45f2..492c7713ddae 100644 --- a/arch/alpha/include/asm/bitops.h +++ b/arch/alpha/include/asm/bitops.h @@ -46,8 +46,8 @@ set_bit(unsigned long nr, volatile void * addr) /* * WARNING: non atomic version. */ -static inline void -__set_bit(unsigned long nr, volatile void * addr) +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) { int *m = ((int *) addr) + (nr >> 5); @@ -82,8 +82,8 @@ clear_bit_unlock(unsigned long nr, volatile void * addr) /* * WARNING: non atomic version. */ -static __inline__ void -__clear_bit(unsigned long nr, volatile void * addr) +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { int *m = ((int *) addr) + (nr >> 5); @@ -94,7 +94,7 @@ static inline void __clear_bit_unlock(unsigned long nr, volatile void * addr) { smp_mb(); - __clear_bit(nr, addr); + arch___clear_bit(nr, addr); } static inline void @@ -118,8 +118,8 @@ change_bit(unsigned long nr, volatile void * addr) /* * WARNING: non atomic version. */ -static __inline__ void -__change_bit(unsigned long nr, volatile void * addr) +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { int *m = ((int *) addr) + (nr >> 5); @@ -186,8 +186,8 @@ test_and_set_bit_lock(unsigned long nr, volatile void *addr) /* * WARNING: non atomic version. */ -static inline int -__test_and_set_bit(unsigned long nr, volatile void * addr) +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = 1 << (nr & 0x1f); int *m = ((int *) addr) + (nr >> 5); @@ -230,8 +230,8 @@ test_and_clear_bit(unsigned long nr, volatile void * addr) /* * WARNING: non atomic version. */ -static inline int -__test_and_clear_bit(unsigned long nr, volatile void * addr) +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = 1 << (nr & 0x1f); int *m = ((int *) addr) + (nr >> 5); @@ -272,8 +272,8 @@ test_and_change_bit(unsigned long nr, volatile void * addr) /* * WARNING: non atomic version. */ -static __inline__ int -__test_and_change_bit(unsigned long nr, volatile void * addr) +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = 1 << (nr & 0x1f); int *m = ((int *) addr) + (nr >> 5); @@ -283,8 +283,8 @@ __test_and_change_bit(unsigned long nr, volatile void * addr) return (old & mask) != 0; } -static inline int -test_bit(int nr, const volatile void * addr) +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { return (1UL & (((const int *) addr)[nr >> 5] >> (nr & 31))) != 0UL; } @@ -450,6 +450,8 @@ sched_find_first_bit(const unsigned long b[2]) return __ffs(tmp) + ofs; } +#include + #include #include diff --git a/arch/hexagon/include/asm/bitops.h b/arch/hexagon/include/asm/bitops.h index 75d6ba3643b8..da500471ac73 100644 --- a/arch/hexagon/include/asm/bitops.h +++ b/arch/hexagon/include/asm/bitops.h @@ -127,38 +127,45 @@ static inline void change_bit(int nr, volatile void *addr) * be atomic, particularly for things like slab_lock and slab_unlock. * */ -static inline void __clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { test_and_clear_bit(nr, addr); } -static inline void __set_bit(int nr, volatile unsigned long *addr) +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) { test_and_set_bit(nr, addr); } -static inline void __change_bit(int nr, volatile unsigned long *addr) +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { test_and_change_bit(nr, addr); } /* Apparently, at least some of these are allowed to be non-atomic */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { return test_and_clear_bit(nr, addr); } -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { return test_and_set_bit(nr, addr); } -static inline int __test_and_change_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { return test_and_change_bit(nr, addr); } -static inline int __test_bit(int nr, const volatile unsigned long *addr) +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { int retval; @@ -172,8 +179,6 @@ static inline int __test_bit(int nr, const volatile unsigned long *addr) return retval; } -#define test_bit(nr, addr) __test_bit(nr, addr) - /* * ffz - find first zero in word. * @word: The word to search @@ -271,6 +276,7 @@ static inline unsigned long __fls(unsigned long word) } #include +#include #include #include diff --git a/arch/ia64/include/asm/bitops.h b/arch/ia64/include/asm/bitops.h index 577be93c0818..9f62af7fd7c4 100644 --- a/arch/ia64/include/asm/bitops.h +++ b/arch/ia64/include/asm/bitops.h @@ -53,7 +53,7 @@ set_bit (int nr, volatile void *addr) } /** - * __set_bit - Set a bit in memory + * arch___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * @@ -61,8 +61,8 @@ set_bit (int nr, volatile void *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static __inline__ void -__set_bit (int nr, volatile void *addr) +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) { *((__u32 *) addr + (nr >> 5)) |= (1 << (nr & 31)); } @@ -135,7 +135,7 @@ __clear_bit_unlock(int nr, void *addr) } /** - * __clear_bit - Clears a bit in memory (non-atomic version) + * arch___clear_bit - Clears a bit in memory (non-atomic version) * @nr: the bit to clear * @addr: the address to start counting from * @@ -143,8 +143,8 @@ __clear_bit_unlock(int nr, void *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static __inline__ void -__clear_bit (int nr, volatile void *addr) +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { *((__u32 *) addr + (nr >> 5)) &= ~(1 << (nr & 31)); } @@ -175,7 +175,7 @@ change_bit (int nr, volatile void *addr) } /** - * __change_bit - Toggle a bit in memory + * arch___change_bit - Toggle a bit in memory * @nr: the bit to toggle * @addr: the address to start counting from * @@ -183,8 +183,8 @@ change_bit (int nr, volatile void *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static __inline__ void -__change_bit (int nr, volatile void *addr) +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { *((__u32 *) addr + (nr >> 5)) ^= (1 << (nr & 31)); } @@ -224,7 +224,7 @@ test_and_set_bit (int nr, volatile void *addr) #define test_and_set_bit_lock test_and_set_bit /** - * __test_and_set_bit - Set a bit and return its old value + * arch___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * @@ -232,8 +232,8 @@ test_and_set_bit (int nr, volatile void *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static __inline__ int -__test_and_set_bit (int nr, volatile void *addr) +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { __u32 *p = (__u32 *) addr + (nr >> 5); __u32 m = 1 << (nr & 31); @@ -269,7 +269,7 @@ test_and_clear_bit (int nr, volatile void *addr) } /** - * __test_and_clear_bit - Clear a bit and return its old value + * arch___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * @@ -277,8 +277,8 @@ test_and_clear_bit (int nr, volatile void *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static __inline__ int -__test_and_clear_bit(int nr, volatile void * addr) +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { __u32 *p = (__u32 *) addr + (nr >> 5); __u32 m = 1 << (nr & 31); @@ -314,14 +314,14 @@ test_and_change_bit (int nr, volatile void *addr) } /** - * __test_and_change_bit - Change a bit and return its old value + * arch___test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * * This operation is non-atomic and can be reordered. */ -static __inline__ int -__test_and_change_bit (int nr, void *addr) +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { __u32 old, bit = (1 << (nr & 31)); __u32 *m = (__u32 *) addr + (nr >> 5); @@ -331,8 +331,8 @@ __test_and_change_bit (int nr, void *addr) return (old & bit) != 0; } -static __inline__ int -test_bit (int nr, const volatile void *addr) +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { return 1 & (((const volatile __u32 *) addr)[nr >> 5] >> (nr & 31)); } @@ -443,6 +443,8 @@ static __inline__ unsigned long __arch_hweight64(unsigned long x) #ifdef __KERNEL__ +#include + #include #include diff --git a/arch/m68k/include/asm/bitops.h b/arch/m68k/include/asm/bitops.h index 51283db53667..71495faf2a90 100644 --- a/arch/m68k/include/asm/bitops.h +++ b/arch/m68k/include/asm/bitops.h @@ -65,8 +65,11 @@ static inline void bfset_mem_set_bit(int nr, volatile unsigned long *vaddr) bfset_mem_set_bit(nr, vaddr)) #endif -#define __set_bit(nr, vaddr) set_bit(nr, vaddr) - +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) +{ + set_bit(nr, addr); +} static inline void bclr_reg_clear_bit(int nr, volatile unsigned long *vaddr) { @@ -105,8 +108,11 @@ static inline void bfclr_mem_clear_bit(int nr, volatile unsigned long *vaddr) bfclr_mem_clear_bit(nr, vaddr)) #endif -#define __clear_bit(nr, vaddr) clear_bit(nr, vaddr) - +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) +{ + clear_bit(nr, addr); +} static inline void bchg_reg_change_bit(int nr, volatile unsigned long *vaddr) { @@ -145,14 +151,17 @@ static inline void bfchg_mem_change_bit(int nr, volatile unsigned long *vaddr) bfchg_mem_change_bit(nr, vaddr)) #endif -#define __change_bit(nr, vaddr) change_bit(nr, vaddr) - - -static inline int test_bit(int nr, const volatile unsigned long *vaddr) +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { - return (vaddr[nr >> 5] & (1UL << (nr & 31))) != 0; + change_bit(nr, addr); } +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) +{ + return (addr[nr >> 5] & (1UL << (nr & 31))) != 0; +} static inline int bset_reg_test_and_set_bit(int nr, volatile unsigned long *vaddr) @@ -201,8 +210,11 @@ static inline int bfset_mem_test_and_set_bit(int nr, bfset_mem_test_and_set_bit(nr, vaddr)) #endif -#define __test_and_set_bit(nr, vaddr) test_and_set_bit(nr, vaddr) - +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) +{ + return test_and_set_bit(nr, addr); +} static inline int bclr_reg_test_and_clear_bit(int nr, volatile unsigned long *vaddr) @@ -251,8 +263,11 @@ static inline int bfclr_mem_test_and_clear_bit(int nr, bfclr_mem_test_and_clear_bit(nr, vaddr)) #endif -#define __test_and_clear_bit(nr, vaddr) test_and_clear_bit(nr, vaddr) - +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) +{ + return test_and_clear_bit(nr, addr); +} static inline int bchg_reg_test_and_change_bit(int nr, volatile unsigned long *vaddr) @@ -301,8 +316,11 @@ static inline int bfchg_mem_test_and_change_bit(int nr, bfchg_mem_test_and_change_bit(nr, vaddr)) #endif -#define __test_and_change_bit(nr, vaddr) test_and_change_bit(nr, vaddr) - +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) +{ + return test_and_change_bit(nr, addr); +} /* * The true 68020 and more advanced processors support the "bfffo" @@ -522,6 +540,7 @@ static inline int __fls(int x) #define clear_bit_unlock clear_bit #define __clear_bit_unlock clear_bit_unlock +#include #include #include #include diff --git a/arch/s390/include/asm/bitops.h b/arch/s390/include/asm/bitops.h index 191dc7898b0f..9a7d15da966e 100644 --- a/arch/s390/include/asm/bitops.h +++ b/arch/s390/include/asm/bitops.h @@ -113,75 +113,76 @@ static inline bool arch_test_and_change_bit(unsigned long nr, return old & mask; } -static inline void arch___set_bit(unsigned long nr, volatile unsigned long *ptr) +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *addr = __bitops_word(nr, ptr); + unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); - *addr |= mask; + *p |= mask; } -static inline void arch___clear_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *addr = __bitops_word(nr, ptr); + unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); - *addr &= ~mask; + *p &= ~mask; } -static inline void arch___change_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *addr = __bitops_word(nr, ptr); + unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); - *addr ^= mask; + *p ^= mask; } -static inline bool arch___test_and_set_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *addr = __bitops_word(nr, ptr); + unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); unsigned long old; - old = *addr; - *addr |= mask; + old = *p; + *p |= mask; return old & mask; } -static inline bool arch___test_and_clear_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *addr = __bitops_word(nr, ptr); + unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); unsigned long old; - old = *addr; - *addr &= ~mask; + old = *p; + *p &= ~mask; return old & mask; } -static inline bool arch___test_and_change_bit(unsigned long nr, - volatile unsigned long *ptr) +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { - unsigned long *addr = __bitops_word(nr, ptr); + unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); unsigned long old; - old = *addr; - *addr ^= mask; + old = *p; + *p ^= mask; return old & mask; } -static inline bool arch_test_bit(unsigned long nr, - const volatile unsigned long *ptr) +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { - const volatile unsigned long *addr = __bitops_word(nr, ptr); + const volatile unsigned long *p = __bitops_word(nr, addr); unsigned long mask = __bitops_mask(nr); - return *addr & mask; + return *p & mask; } static inline bool arch_test_and_set_bit_lock(unsigned long nr, diff --git a/arch/sh/include/asm/bitops-op32.h b/arch/sh/include/asm/bitops-op32.h index cfe5465acce7..565a85d8b7fb 100644 --- a/arch/sh/include/asm/bitops-op32.h +++ b/arch/sh/include/asm/bitops-op32.h @@ -2,6 +2,8 @@ #ifndef __ASM_SH_BITOPS_OP32_H #define __ASM_SH_BITOPS_OP32_H +#include + /* * The bit modifying instructions on SH-2A are only capable of working * with a 3-bit immediate, which signifies the shift position for the bit @@ -16,7 +18,8 @@ #define BYTE_OFFSET(nr) ((nr) % BITS_PER_BYTE) #endif -static inline void __set_bit(int nr, volatile unsigned long *addr) +static __always_inline void +arch___set_bit(unsigned long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { __asm__ __volatile__ ( @@ -33,7 +36,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) } } -static inline void __clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { __asm__ __volatile__ ( @@ -52,7 +56,7 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) } /** - * __change_bit - Toggle a bit in memory + * arch___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * @@ -60,7 +64,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __change_bit(int nr, volatile unsigned long *addr) +static __always_inline void +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { if (__builtin_constant_p(nr)) { __asm__ __volatile__ ( @@ -79,7 +84,7 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) } /** - * __test_and_set_bit - Set a bit and return its old value + * arch___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * @@ -87,7 +92,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -98,7 +104,7 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) } /** - * __test_and_clear_bit - Clear a bit and return its old value + * arch___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * @@ -106,7 +112,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -117,8 +124,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) } /* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) +static __always_inline bool +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -129,13 +136,16 @@ static inline int __test_and_change_bit(int nr, } /** - * test_bit - Determine whether a bit is set + * arch_test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ -static inline int test_bit(int nr, const volatile unsigned long *addr) +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) { return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } +#include + #endif /* __ASM_SH_BITOPS_OP32_H */ diff --git a/arch/x86/include/asm/bitops.h b/arch/x86/include/asm/bitops.h index a288ecd230ab..973c6bd17f98 100644 --- a/arch/x86/include/asm/bitops.h +++ b/arch/x86/include/asm/bitops.h @@ -63,7 +63,7 @@ arch_set_bit(long nr, volatile unsigned long *addr) } static __always_inline void -arch___set_bit(long nr, volatile unsigned long *addr) +arch___set_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(bts) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } @@ -89,7 +89,7 @@ arch_clear_bit_unlock(long nr, volatile unsigned long *addr) } static __always_inline void -arch___clear_bit(long nr, volatile unsigned long *addr) +arch___clear_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btr) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } @@ -114,7 +114,7 @@ arch___clear_bit_unlock(long nr, volatile unsigned long *addr) } static __always_inline void -arch___change_bit(long nr, volatile unsigned long *addr) +arch___change_bit(unsigned long nr, volatile unsigned long *addr) { asm volatile(__ASM_SIZE(btc) " %1,%0" : : ADDR, "Ir" (nr) : "memory"); } @@ -145,7 +145,7 @@ arch_test_and_set_bit_lock(long nr, volatile unsigned long *addr) } static __always_inline bool -arch___test_and_set_bit(long nr, volatile unsigned long *addr) +arch___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; @@ -171,7 +171,7 @@ arch_test_and_clear_bit(long nr, volatile unsigned long *addr) * this without also updating arch/x86/kernel/kvm.c */ static __always_inline bool -arch___test_and_clear_bit(long nr, volatile unsigned long *addr) +arch___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; @@ -183,7 +183,7 @@ arch___test_and_clear_bit(long nr, volatile unsigned long *addr) } static __always_inline bool -arch___test_and_change_bit(long nr, volatile unsigned long *addr) +arch___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { bool oldbit; @@ -219,10 +219,12 @@ static __always_inline bool variable_test_bit(long nr, volatile const unsigned l return oldbit; } -#define arch_test_bit(nr, addr) \ - (__builtin_constant_p((nr)) \ - ? constant_test_bit((nr), (addr)) \ - : variable_test_bit((nr), (addr))) +static __always_inline bool +arch_test_bit(unsigned long nr, const volatile unsigned long *addr) +{ + return __builtin_constant_p(nr) ? constant_test_bit(nr, addr) : + variable_test_bit(nr, addr); +} /** * __ffs - find first set bit in word diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h index 7226488810e5..b85b8a2ac239 100644 --- a/include/asm-generic/bitops/generic-non-atomic.h +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -24,7 +24,7 @@ * may be that only one operation succeeds. */ static __always_inline void -generic___set_bit(unsigned int nr, volatile unsigned long *addr) +generic___set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -33,7 +33,7 @@ generic___set_bit(unsigned int nr, volatile unsigned long *addr) } static __always_inline void -generic___clear_bit(unsigned int nr, volatile unsigned long *addr) +generic___clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -50,8 +50,8 @@ generic___clear_bit(unsigned int nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static __always_inline -void generic___change_bit(unsigned int nr, volatile unsigned long *addr) +static __always_inline void +generic___change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -68,8 +68,8 @@ void generic___change_bit(unsigned int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static __always_inline int -generic___test_and_set_bit(unsigned int nr, volatile unsigned long *addr) +static __always_inline bool +generic___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -88,8 +88,8 @@ generic___test_and_set_bit(unsigned int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static __always_inline int -generic___test_and_clear_bit(unsigned int nr, volatile unsigned long *addr) +static __always_inline bool +generic___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -100,8 +100,8 @@ generic___test_and_clear_bit(unsigned int nr, volatile unsigned long *addr) } /* WARNING: non atomic and it can be reordered! */ -static __always_inline int -generic___test_and_change_bit(unsigned int nr, volatile unsigned long *addr) +static __always_inline bool +generic___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -116,8 +116,8 @@ generic___test_and_change_bit(unsigned int nr, volatile unsigned long *addr) * @nr: bit number to test * @addr: Address to start counting from */ -static __always_inline int -generic_test_bit(unsigned int nr, const volatile unsigned long *addr) +static __always_inline bool +generic_test_bit(unsigned long nr, const volatile unsigned long *addr) { /* * Unlike the bitops with the '__' prefix above, this one *is* atomic, diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 7ab1ecc37782..b019f77ef21c 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -22,7 +22,8 @@ * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static __always_inline void __set_bit(long nr, volatile unsigned long *addr) +static __always_inline void +__set_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); @@ -37,7 +38,8 @@ static __always_inline void __set_bit(long nr, volatile unsigned long *addr) * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void +__clear_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); @@ -52,7 +54,8 @@ static __always_inline void __clear_bit(long nr, volatile unsigned long *addr) * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static __always_inline void __change_bit(long nr, volatile unsigned long *addr) +static __always_inline void +__change_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); @@ -90,7 +93,8 @@ static __always_inline void __instrument_read_write_bitop(long nr, volatile unsi * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ -static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +__test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); @@ -104,7 +108,8 @@ static __always_inline bool __test_and_set_bit(long nr, volatile unsigned long * * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ -static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +__test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); @@ -118,7 +123,8 @@ static __always_inline bool __test_and_clear_bit(long nr, volatile unsigned long * This operation is non-atomic. If two instances of this operation race, one * can appear to succeed but actually fail. */ -static __always_inline bool __test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool +__test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); @@ -129,7 +135,8 @@ static __always_inline bool __test_and_change_bit(long nr, volatile unsigned lon * @nr: bit number to test * @addr: Address to start counting from */ -static __always_inline bool test_bit(long nr, const volatile unsigned long *addr) +static __always_inline bool +test_bit(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h index 23d3abc1e10d..5c37ced343ae 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -5,24 +5,15 @@ #include #define arch___set_bit generic___set_bit -#define __set_bit arch___set_bit - #define arch___clear_bit generic___clear_bit -#define __clear_bit arch___clear_bit - #define arch___change_bit generic___change_bit -#define __change_bit arch___change_bit #define arch___test_and_set_bit generic___test_and_set_bit -#define __test_and_set_bit arch___test_and_set_bit - #define arch___test_and_clear_bit generic___test_and_clear_bit -#define __test_and_clear_bit arch___test_and_clear_bit - #define arch___test_and_change_bit generic___test_and_change_bit -#define __test_and_change_bit arch___test_and_change_bit #define arch_test_bit generic_test_bit -#define test_bit arch_test_bit + +#include #endif /* _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ */ diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h new file mode 100644 index 000000000000..e0fd7bf72a56 --- /dev/null +++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h @@ -0,0 +1,16 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H +#define __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H + +#define __set_bit arch___set_bit +#define __clear_bit arch___clear_bit +#define __change_bit arch___change_bit + +#define __test_and_set_bit arch___test_and_set_bit +#define __test_and_clear_bit arch___test_and_clear_bit +#define __test_and_change_bit arch___test_and_change_bit + +#define test_bit arch_test_bit + +#endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 7aaed501f768..87087454a288 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -26,12 +26,29 @@ extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); +#include + /* * Include this here because some architectures need generic_ffs/fls in * scope */ #include +/* Check that the bitops prototypes are sane */ +#define __check_bitop_pr(name) \ + static_assert(__same_type(arch_##name, generic_##name) && \ + __same_type(name, generic_##name)) + +__check_bitop_pr(__set_bit); +__check_bitop_pr(__clear_bit); +__check_bitop_pr(__change_bit); +__check_bitop_pr(__test_and_set_bit); +__check_bitop_pr(__test_and_clear_bit); +__check_bitop_pr(__test_and_change_bit); +__check_bitop_pr(test_bit); + +#undef __check_bitop_pr + static inline int get_bitmask_order(unsigned int count) { int order; diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h index 7e10c4b50c5d..e5e78e42e57b 100644 --- a/tools/include/asm-generic/bitops/non-atomic.h +++ b/tools/include/asm-generic/bitops/non-atomic.h @@ -2,7 +2,7 @@ #ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#include +#include /** * __set_bit - Set a bit in memory @@ -13,7 +13,8 @@ * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __set_bit(int nr, volatile unsigned long *addr) +static __always_inline void +__set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -21,7 +22,8 @@ static inline void __set_bit(int nr, volatile unsigned long *addr) *p |= mask; } -static inline void __clear_bit(int nr, volatile unsigned long *addr) +static __always_inline void +__clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -38,7 +40,8 @@ static inline void __clear_bit(int nr, volatile unsigned long *addr) * If it's called on the same region of memory simultaneously, the effect * may be that only one operation succeeds. */ -static inline void __change_bit(int nr, volatile unsigned long *addr) +static __always_inline void +__change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -55,7 +58,8 @@ static inline void __change_bit(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +__test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -74,7 +78,8 @@ static inline int __test_and_set_bit(int nr, volatile unsigned long *addr) * If two examples of this operation race, one can appear to succeed * but actually fail. You must protect multiple accesses with a lock. */ -static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) +static __always_inline bool +__test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -85,8 +90,8 @@ static inline int __test_and_clear_bit(int nr, volatile unsigned long *addr) } /* WARNING: non atomic and it can be reordered! */ -static inline int __test_and_change_bit(int nr, - volatile unsigned long *addr) +static __always_inline bool +__test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -101,7 +106,8 @@ static inline int __test_and_change_bit(int nr, * @nr: bit number to test * @addr: Address to start counting from */ -static inline int test_bit(int nr, const volatile unsigned long *addr) +static __always_inline bool +test_bit(unsigned long nr, const volatile unsigned long *addr) { return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } From bb7379bfa680bd48b468e856475778db2ad866c1 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:08 +0200 Subject: [PATCH 05/26] bitops: define const_*() versions of the non-atomics Define const_*() variants of the non-atomic bitops to be used when the input arguments are compile-time constants, so that the compiler will be always able to resolve those to compile-time constants as well. Those are mostly direct aliases for generic_*() with one exception for const_test_bit(): the original one is declared atomic-safe and thus doesn't discard the `volatile` qualifier, so in order to let optimize code, define it separately disregarding the qualifier. Add them to the compile-time type checks as well just in case. Suggested-by: Marco Elver Signed-off-by: Alexander Lobakin Reviewed-by: Marco Elver Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- .../asm-generic/bitops/generic-non-atomic.h | 31 +++++++++++++++++++ include/linux/bitops.h | 1 + 2 files changed, 32 insertions(+) diff --git a/include/asm-generic/bitops/generic-non-atomic.h b/include/asm-generic/bitops/generic-non-atomic.h index b85b8a2ac239..3d5ebd24652b 100644 --- a/include/asm-generic/bitops/generic-non-atomic.h +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -127,4 +127,35 @@ generic_test_bit(unsigned long nr, const volatile unsigned long *addr) return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } +/* + * const_*() definitions provide good compile-time optimizations when + * the passed arguments can be resolved at compile time. + */ +#define const___set_bit generic___set_bit +#define const___clear_bit generic___clear_bit +#define const___change_bit generic___change_bit +#define const___test_and_set_bit generic___test_and_set_bit +#define const___test_and_clear_bit generic___test_and_clear_bit +#define const___test_and_change_bit generic___test_and_change_bit + +/** + * const_test_bit - Determine whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + * + * A version of generic_test_bit() which discards the `volatile` qualifier to + * allow a compiler to optimize code harder. Non-atomic and to be called only + * for testing compile-time constants, e.g. by the corresponding macros, not + * directly from "regular" code. + */ +static __always_inline bool +const_test_bit(unsigned long nr, const volatile unsigned long *addr) +{ + const unsigned long *p = (const unsigned long *)addr + BIT_WORD(nr); + unsigned long mask = BIT_MASK(nr); + unsigned long val = *p; + + return !!(val & mask); +} + #endif /* __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 87087454a288..d393297287d5 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -37,6 +37,7 @@ extern unsigned long __sw_hweight64(__u64 w); /* Check that the bitops prototypes are sane */ #define __check_bitop_pr(name) \ static_assert(__same_type(arch_##name, generic_##name) && \ + __same_type(const_##name, generic_##name) && \ __same_type(name, generic_##name)) __check_bitop_pr(__set_bit); From e69eb9c460f128b71c6b995d75a05244e4b6cc3e Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:09 +0200 Subject: [PATCH 06/26] bitops: wrap non-atomic bitops with a transparent macro In preparation for altering the non-atomic bitops with a macro, wrap them in a transparent definition. This requires prepending one more '_' to their names in order to be able to do that seamlessly. It is a simple change, given that all the non-prefixed definitions are now in asm-generic. sparc32 already has several triple-underscored functions, so I had to rename them ('___' -> 'sp32_'). Signed-off-by: Alexander Lobakin Reviewed-by: Marco Elver Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- arch/sparc/include/asm/bitops_32.h | 18 ++++++------ arch/sparc/lib/atomic32.c | 12 ++++---- .../bitops/instrumented-non-atomic.h | 28 +++++++++---------- .../bitops/non-instrumented-non-atomic.h | 14 +++++----- include/linux/bitops.h | 18 +++++++++++- tools/include/asm-generic/bitops/non-atomic.h | 24 ++++++++-------- tools/include/linux/bitops.h | 16 +++++++++++ 7 files changed, 81 insertions(+), 49 deletions(-) diff --git a/arch/sparc/include/asm/bitops_32.h b/arch/sparc/include/asm/bitops_32.h index 889afa9f990f..3448c191b484 100644 --- a/arch/sparc/include/asm/bitops_32.h +++ b/arch/sparc/include/asm/bitops_32.h @@ -19,9 +19,9 @@ #error only can be included directly #endif -unsigned long ___set_bit(unsigned long *addr, unsigned long mask); -unsigned long ___clear_bit(unsigned long *addr, unsigned long mask); -unsigned long ___change_bit(unsigned long *addr, unsigned long mask); +unsigned long sp32___set_bit(unsigned long *addr, unsigned long mask); +unsigned long sp32___clear_bit(unsigned long *addr, unsigned long mask); +unsigned long sp32___change_bit(unsigned long *addr, unsigned long mask); /* * Set bit 'nr' in 32-bit quantity at address 'addr' where bit '0' @@ -36,7 +36,7 @@ static inline int test_and_set_bit(unsigned long nr, volatile unsigned long *add ADDR = ((unsigned long *) addr) + (nr >> 5); mask = 1 << (nr & 31); - return ___set_bit(ADDR, mask) != 0; + return sp32___set_bit(ADDR, mask) != 0; } static inline void set_bit(unsigned long nr, volatile unsigned long *addr) @@ -46,7 +46,7 @@ static inline void set_bit(unsigned long nr, volatile unsigned long *addr) ADDR = ((unsigned long *) addr) + (nr >> 5); mask = 1 << (nr & 31); - (void) ___set_bit(ADDR, mask); + (void) sp32___set_bit(ADDR, mask); } static inline int test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) @@ -56,7 +56,7 @@ static inline int test_and_clear_bit(unsigned long nr, volatile unsigned long *a ADDR = ((unsigned long *) addr) + (nr >> 5); mask = 1 << (nr & 31); - return ___clear_bit(ADDR, mask) != 0; + return sp32___clear_bit(ADDR, mask) != 0; } static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) @@ -66,7 +66,7 @@ static inline void clear_bit(unsigned long nr, volatile unsigned long *addr) ADDR = ((unsigned long *) addr) + (nr >> 5); mask = 1 << (nr & 31); - (void) ___clear_bit(ADDR, mask); + (void) sp32___clear_bit(ADDR, mask); } static inline int test_and_change_bit(unsigned long nr, volatile unsigned long *addr) @@ -76,7 +76,7 @@ static inline int test_and_change_bit(unsigned long nr, volatile unsigned long * ADDR = ((unsigned long *) addr) + (nr >> 5); mask = 1 << (nr & 31); - return ___change_bit(ADDR, mask) != 0; + return sp32___change_bit(ADDR, mask) != 0; } static inline void change_bit(unsigned long nr, volatile unsigned long *addr) @@ -86,7 +86,7 @@ static inline void change_bit(unsigned long nr, volatile unsigned long *addr) ADDR = ((unsigned long *) addr) + (nr >> 5); mask = 1 << (nr & 31); - (void) ___change_bit(ADDR, mask); + (void) sp32___change_bit(ADDR, mask); } #include diff --git a/arch/sparc/lib/atomic32.c b/arch/sparc/lib/atomic32.c index 8b81d0f00c97..cf80d1ae352b 100644 --- a/arch/sparc/lib/atomic32.c +++ b/arch/sparc/lib/atomic32.c @@ -120,7 +120,7 @@ void arch_atomic_set(atomic_t *v, int i) } EXPORT_SYMBOL(arch_atomic_set); -unsigned long ___set_bit(unsigned long *addr, unsigned long mask) +unsigned long sp32___set_bit(unsigned long *addr, unsigned long mask) { unsigned long old, flags; @@ -131,9 +131,9 @@ unsigned long ___set_bit(unsigned long *addr, unsigned long mask) return old & mask; } -EXPORT_SYMBOL(___set_bit); +EXPORT_SYMBOL(sp32___set_bit); -unsigned long ___clear_bit(unsigned long *addr, unsigned long mask) +unsigned long sp32___clear_bit(unsigned long *addr, unsigned long mask) { unsigned long old, flags; @@ -144,9 +144,9 @@ unsigned long ___clear_bit(unsigned long *addr, unsigned long mask) return old & mask; } -EXPORT_SYMBOL(___clear_bit); +EXPORT_SYMBOL(sp32___clear_bit); -unsigned long ___change_bit(unsigned long *addr, unsigned long mask) +unsigned long sp32___change_bit(unsigned long *addr, unsigned long mask) { unsigned long old, flags; @@ -157,7 +157,7 @@ unsigned long ___change_bit(unsigned long *addr, unsigned long mask) return old & mask; } -EXPORT_SYMBOL(___change_bit); +EXPORT_SYMBOL(sp32___change_bit); unsigned long __cmpxchg_u32(volatile u32 *ptr, u32 old, u32 new) { diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index b019f77ef21c..988a3bbfba34 100644 --- a/include/asm-generic/bitops/instrumented-non-atomic.h +++ b/include/asm-generic/bitops/instrumented-non-atomic.h @@ -14,7 +14,7 @@ #include /** - * __set_bit - Set a bit in memory + * ___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * @@ -23,14 +23,14 @@ * succeeds. */ static __always_inline void -__set_bit(unsigned long nr, volatile unsigned long *addr) +___set_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___set_bit(nr, addr); } /** - * __clear_bit - Clears a bit in memory + * ___clear_bit - Clears a bit in memory * @nr: the bit to clear * @addr: the address to start counting from * @@ -39,14 +39,14 @@ __set_bit(unsigned long nr, volatile unsigned long *addr) * succeeds. */ static __always_inline void -__clear_bit(unsigned long nr, volatile unsigned long *addr) +___clear_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit(nr, addr); } /** - * __change_bit - Toggle a bit in memory + * ___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * @@ -55,7 +55,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *addr) * succeeds. */ static __always_inline void -__change_bit(unsigned long nr, volatile unsigned long *addr) +___change_bit(unsigned long nr, volatile unsigned long *addr) { instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___change_bit(nr, addr); @@ -86,7 +86,7 @@ static __always_inline void __instrument_read_write_bitop(long nr, volatile unsi } /** - * __test_and_set_bit - Set a bit and return its old value + * ___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * @@ -94,14 +94,14 @@ static __always_inline void __instrument_read_write_bitop(long nr, volatile unsi * can appear to succeed but actually fail. */ static __always_inline bool -__test_and_set_bit(unsigned long nr, volatile unsigned long *addr) +___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_set_bit(nr, addr); } /** - * __test_and_clear_bit - Clear a bit and return its old value + * ___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * @@ -109,14 +109,14 @@ __test_and_set_bit(unsigned long nr, volatile unsigned long *addr) * can appear to succeed but actually fail. */ static __always_inline bool -__test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) +___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_clear_bit(nr, addr); } /** - * __test_and_change_bit - Change a bit and return its old value + * ___test_and_change_bit - Change a bit and return its old value * @nr: Bit to change * @addr: Address to count from * @@ -124,19 +124,19 @@ __test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) * can appear to succeed but actually fail. */ static __always_inline bool -__test_and_change_bit(unsigned long nr, volatile unsigned long *addr) +___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { __instrument_read_write_bitop(nr, addr); return arch___test_and_change_bit(nr, addr); } /** - * test_bit - Determine whether a bit is set + * _test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool -test_bit(unsigned long nr, const volatile unsigned long *addr) +_test_bit(unsigned long nr, const volatile unsigned long *addr) { instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); return arch_test_bit(nr, addr); diff --git a/include/asm-generic/bitops/non-instrumented-non-atomic.h b/include/asm-generic/bitops/non-instrumented-non-atomic.h index e0fd7bf72a56..bdb9b1ffaee9 100644 --- a/include/asm-generic/bitops/non-instrumented-non-atomic.h +++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h @@ -3,14 +3,14 @@ #ifndef __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H #define __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H -#define __set_bit arch___set_bit -#define __clear_bit arch___clear_bit -#define __change_bit arch___change_bit +#define ___set_bit arch___set_bit +#define ___clear_bit arch___clear_bit +#define ___change_bit arch___change_bit -#define __test_and_set_bit arch___test_and_set_bit -#define __test_and_clear_bit arch___test_and_clear_bit -#define __test_and_change_bit arch___test_and_change_bit +#define ___test_and_set_bit arch___test_and_set_bit +#define ___test_and_clear_bit arch___test_and_clear_bit +#define ___test_and_change_bit arch___test_and_change_bit -#define test_bit arch_test_bit +#define _test_bit arch_test_bit #endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/linux/bitops.h b/include/linux/bitops.h index d393297287d5..3c3afbae1533 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -26,8 +26,24 @@ extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); +/* + * Defined here because those may be needed by architecture-specific static + * inlines. + */ + #include +#define bitop(op, nr, addr) \ + op(nr, addr) + +#define __set_bit(nr, addr) bitop(___set_bit, nr, addr) +#define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) +#define __change_bit(nr, addr) bitop(___change_bit, nr, addr) +#define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) +#define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) +#define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) +#define test_bit(nr, addr) bitop(_test_bit, nr, addr) + /* * Include this here because some architectures need generic_ffs/fls in * scope @@ -38,7 +54,7 @@ extern unsigned long __sw_hweight64(__u64 w); #define __check_bitop_pr(name) \ static_assert(__same_type(arch_##name, generic_##name) && \ __same_type(const_##name, generic_##name) && \ - __same_type(name, generic_##name)) + __same_type(_##name, generic_##name)) __check_bitop_pr(__set_bit); __check_bitop_pr(__clear_bit); diff --git a/tools/include/asm-generic/bitops/non-atomic.h b/tools/include/asm-generic/bitops/non-atomic.h index e5e78e42e57b..0c472a833408 100644 --- a/tools/include/asm-generic/bitops/non-atomic.h +++ b/tools/include/asm-generic/bitops/non-atomic.h @@ -5,7 +5,7 @@ #include /** - * __set_bit - Set a bit in memory + * ___set_bit - Set a bit in memory * @nr: the bit to set * @addr: the address to start counting from * @@ -14,7 +14,7 @@ * may be that only one operation succeeds. */ static __always_inline void -__set_bit(unsigned long nr, volatile unsigned long *addr) +___set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -23,7 +23,7 @@ __set_bit(unsigned long nr, volatile unsigned long *addr) } static __always_inline void -__clear_bit(unsigned long nr, volatile unsigned long *addr) +___clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -32,7 +32,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *addr) } /** - * __change_bit - Toggle a bit in memory + * ___change_bit - Toggle a bit in memory * @nr: the bit to change * @addr: the address to start counting from * @@ -41,7 +41,7 @@ __clear_bit(unsigned long nr, volatile unsigned long *addr) * may be that only one operation succeeds. */ static __always_inline void -__change_bit(unsigned long nr, volatile unsigned long *addr) +___change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -50,7 +50,7 @@ __change_bit(unsigned long nr, volatile unsigned long *addr) } /** - * __test_and_set_bit - Set a bit and return its old value + * ___test_and_set_bit - Set a bit and return its old value * @nr: Bit to set * @addr: Address to count from * @@ -59,7 +59,7 @@ __change_bit(unsigned long nr, volatile unsigned long *addr) * but actually fail. You must protect multiple accesses with a lock. */ static __always_inline bool -__test_and_set_bit(unsigned long nr, volatile unsigned long *addr) +___test_and_set_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -70,7 +70,7 @@ __test_and_set_bit(unsigned long nr, volatile unsigned long *addr) } /** - * __test_and_clear_bit - Clear a bit and return its old value + * ___test_and_clear_bit - Clear a bit and return its old value * @nr: Bit to clear * @addr: Address to count from * @@ -79,7 +79,7 @@ __test_and_set_bit(unsigned long nr, volatile unsigned long *addr) * but actually fail. You must protect multiple accesses with a lock. */ static __always_inline bool -__test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) +___test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -91,7 +91,7 @@ __test_and_clear_bit(unsigned long nr, volatile unsigned long *addr) /* WARNING: non atomic and it can be reordered! */ static __always_inline bool -__test_and_change_bit(unsigned long nr, volatile unsigned long *addr) +___test_and_change_bit(unsigned long nr, volatile unsigned long *addr) { unsigned long mask = BIT_MASK(nr); unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); @@ -102,12 +102,12 @@ __test_and_change_bit(unsigned long nr, volatile unsigned long *addr) } /** - * test_bit - Determine whether a bit is set + * _test_bit - Determine whether a bit is set * @nr: bit number to test * @addr: Address to start counting from */ static __always_inline bool -test_bit(unsigned long nr, const volatile unsigned long *addr) +_test_bit(unsigned long nr, const volatile unsigned long *addr) { return 1UL & (addr[BIT_WORD(nr)] >> (nr & (BITS_PER_LONG-1))); } diff --git a/tools/include/linux/bitops.h b/tools/include/linux/bitops.h index 5fca38fe1ba8..f18683b95ea6 100644 --- a/tools/include/linux/bitops.h +++ b/tools/include/linux/bitops.h @@ -25,6 +25,22 @@ extern unsigned int __sw_hweight16(unsigned int w); extern unsigned int __sw_hweight32(unsigned int w); extern unsigned long __sw_hweight64(__u64 w); +/* + * Defined here because those may be needed by architecture-specific static + * inlines. + */ + +#define bitop(op, nr, addr) \ + op(nr, addr) + +#define __set_bit(nr, addr) bitop(___set_bit, nr, addr) +#define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) +#define __change_bit(nr, addr) bitop(___change_bit, nr, addr) +#define __test_and_set_bit(nr, addr) bitop(___test_and_set_bit, nr, addr) +#define __test_and_clear_bit(nr, addr) bitop(___test_and_clear_bit, nr, addr) +#define __test_and_change_bit(nr, addr) bitop(___test_and_change_bit, nr, addr) +#define test_bit(nr, addr) bitop(_test_bit, nr, addr) + /* * Include this here because some architectures need generic_ffs/fls in * scope From b03fc1173c0c2bb8fad61902a862985cecdc4b1b Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:10 +0200 Subject: [PATCH 07/26] bitops: let optimize out non-atomic bitops on compile-time constants Currently, many architecture-specific non-atomic bitop implementations use inline asm or other hacks which are faster or more robust when working with "real" variables (i.e. fields from the structures etc.), but the compilers have no clue how to optimize them out when called on compile-time constants. That said, the following code: DECLARE_BITMAP(foo, BITS_PER_LONG) = { }; // -> unsigned long foo[1]; unsigned long bar = BIT(BAR_BIT); unsigned long baz = 0; __set_bit(FOO_BIT, foo); baz |= BIT(BAZ_BIT); BUILD_BUG_ON(!__builtin_constant_p(test_bit(FOO_BIT, foo)); BUILD_BUG_ON(!__builtin_constant_p(bar & BAR_BIT)); BUILD_BUG_ON(!__builtin_constant_p(baz & BAZ_BIT)); triggers the first assertion on x86_64, which means that the compiler is unable to evaluate it to a compile-time initializer when the architecture-specific bitop is used even if it's obvious. In order to let the compiler optimize out such cases, expand the bitop() macro to use the "constant" C non-atomic bitop implementations when all of the arguments passed are compile-time constants, which means that the result will be a compile-time constant as well, so that it produces more efficient and simple code in 100% cases, comparing to the architecture-specific counterparts. The savings are architecture, compiler and compiler flags dependent, for example, on x86_64 -O2: GCC 12: add/remove: 78/29 grow/shrink: 332/525 up/down: 31325/-61560 (-30235) LLVM 13: add/remove: 79/76 grow/shrink: 184/537 up/down: 55076/-141892 (-86816) LLVM 14: add/remove: 10/3 grow/shrink: 93/138 up/down: 3705/-6992 (-3287) and ARM64 (courtesy of Mark): GCC 11: add/remove: 92/29 grow/shrink: 933/2766 up/down: 39340/-82580 (-43240) LLVM 14: add/remove: 21/11 grow/shrink: 620/651 up/down: 12060/-15824 (-3764) Cc: Mark Rutland Signed-off-by: Alexander Lobakin Reviewed-by: Marco Elver Signed-off-by: Yury Norov --- include/linux/bitops.h | 18 +++++++++++++++++- 1 file changed, 17 insertions(+), 1 deletion(-) diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 3c3afbae1533..cf9bf65039f2 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -33,8 +33,24 @@ extern unsigned long __sw_hweight64(__u64 w); #include +/* + * Many architecture-specific non-atomic bitops contain inline asm code and due + * to that the compiler can't optimize them to compile-time expressions or + * constants. In contrary, generic_*() helpers are defined in pure C and + * compilers optimize them just well. + * Therefore, to make `unsigned long foo = 0; __set_bit(BAR, &foo)` effectively + * equal to `unsigned long foo = BIT(BAR)`, pick the generic C alternative when + * the arguments can be resolved at compile time. That expression itself is a + * constant and doesn't bring any functional changes to the rest of cases. + * The casts to `uintptr_t` are needed to mitigate `-Waddress` warnings when + * passing a bitmap from .bss or .data (-> `!!addr` is always true). + */ #define bitop(op, nr, addr) \ - op(nr, addr) + ((__builtin_constant_p(nr) && \ + __builtin_constant_p((uintptr_t)(addr) != (uintptr_t)NULL) && \ + (uintptr_t)(addr) != (uintptr_t)NULL && \ + __builtin_constant_p(*(const unsigned long *)(addr))) ? \ + const##op(nr, addr) : op(nr, addr)) #define __set_bit(nr, addr) bitop(___set_bit, nr, addr) #define __clear_bit(nr, addr) bitop(___clear_bit, nr, addr) From 2f7ee2a72ccec8b85a05c4644d7ec9f40c1c50c8 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:11 +0200 Subject: [PATCH 08/26] net/ice: fix initializing the bitmap in the switch code Kbuild spotted the following bug during the testing of one of the optimizations: In file included from include/linux/cpumask.h:12, [...] from drivers/net/ethernet/intel/ice/ice_switch.c:4: drivers/net/ethernet/intel/ice/ice_switch.c: In function 'ice_find_free_recp_res_idx.constprop': include/linux/bitmap.h:447:22: warning: 'possible_idx[0]' is used uninitialized [-Wuninitialized] 447 | *map |= GENMASK(start + nbits - 1, start); | ^~ In file included from drivers/net/ethernet/intel/ice/ice.h:7, from drivers/net/ethernet/intel/ice/ice_lib.h:7, from drivers/net/ethernet/intel/ice/ice_switch.c:4: drivers/net/ethernet/intel/ice/ice_switch.c:4929:24: note: 'possible_idx[0]' was declared here 4929 | DECLARE_BITMAP(possible_idx, ICE_MAX_FV_WORDS); | ^~~~~~~~~~~~ include/linux/types.h:11:23: note: in definition of macro 'DECLARE_BITMAP' 11 | unsigned long name[BITS_TO_LONGS(bits)] | ^~~~ %ICE_MAX_FV_WORDS is 48, so bitmap_set() here was initializing only 48 bits, leaving a junk in the rest 16. It was previously hidden due to that filling 48 bits makes bitmap_set() call external __bitmap_set(), but after making it use plain bit arithmetics on small bitmaps, compilers started seeing the issue. It was still working because those 16 weren't used anywhere anyhow. bitmap_{clear,set}() are not really intended to initialize bitmaps, rather to modify already initialized ones, as they don't do anything past the passed number of bits. The correct function to do this in that particular case is bitmap_fill(), so use it here. It will do `*possible_idx = ~0UL` instead of `*possible_idx |= GENMASK(47, 0)`, not leaving anything in an undefined state. Fixes: fd2a6b71e300 ("ice: create advanced switch recipe") Reported-by: kernel test robot Signed-off-by: Alexander Lobakin Signed-off-by: Yury Norov --- drivers/net/ethernet/intel/ice/ice_switch.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/ethernet/intel/ice/ice_switch.c b/drivers/net/ethernet/intel/ice/ice_switch.c index 8d8f3eec79ee..9b2872e89151 100644 --- a/drivers/net/ethernet/intel/ice/ice_switch.c +++ b/drivers/net/ethernet/intel/ice/ice_switch.c @@ -4934,7 +4934,7 @@ ice_find_free_recp_res_idx(struct ice_hw *hw, const unsigned long *profiles, bitmap_zero(recipes, ICE_MAX_NUM_RECIPES); bitmap_zero(used_idx, ICE_MAX_FV_WORDS); - bitmap_set(possible_idx, 0, ICE_MAX_FV_WORDS); + bitmap_fill(possible_idx, ICE_MAX_FV_WORDS); /* For each profile we are going to associate the recipe with, add the * recipes that are associated with that profile. This will give us From 3e7e5baaaba78075a7f3a57432609e363bf2a486 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:12 +0200 Subject: [PATCH 09/26] bitmap: don't assume compiler evaluates small mem*() builtins calls Intel kernel bot triggered the build bug on ARC architecture that in fact is as follows: DECLARE_BITMAP(bitmap, BITS_PER_LONG); bitmap_clear(bitmap, 0, BITS_PER_LONG); BUILD_BUG_ON(!__builtin_constant_p(*bitmap)); which can be expanded to: unsigned long bitmap[1]; memset(bitmap, 0, sizeof(*bitmap)); BUILD_BUG_ON(!__builtin_constant_p(*bitmap)); In most cases, a compiler is able to expand small/simple mem*() calls to simple assignments or bitops, in this case that would mean: unsigned long bitmap[1] = { 0 }; BUILD_BUG_ON(!__builtin_constant_p(*bitmap)); and on most architectures this works, but not on ARC, despite having -O3 for every build. So, to make this work, in case when the last bit to modify is still within the first long (small_const_nbits()), just use plain assignments for the rest of bitmap_*() functions which still use mem*(), but didn't receive such compile-time optimizations yet. This doesn't have the same coverage as compilers provide, but at least something to start: text: add/remove: 3/7 grow/shrink: 43/78 up/down: 1848/-3370 (-1546) data: add/remove: 1/11 grow/shrink: 0/8 up/down: 4/-356 (-352) notably cpumask_*() family when NR_CPUS <= BITS_PER_LONG: netif_get_num_default_rss_queues 38 4 -34 cpumask_copy 90 - -90 cpumask_clear 146 - -146 and the abovementioned assertion started passing. Signed-off-by: Alexander Lobakin Signed-off-by: Yury Norov --- include/linux/bitmap.h | 22 +++++++++++++++++++--- 1 file changed, 19 insertions(+), 3 deletions(-) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index f091a1664bf1..c91638e507f2 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -238,20 +238,32 @@ extern int bitmap_print_list_to_buf(char *buf, const unsigned long *maskp, static inline void bitmap_zero(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0, len); + + if (small_const_nbits(nbits)) + *dst = 0; + else + memset(dst, 0, len); } static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memset(dst, 0xff, len); + + if (small_const_nbits(nbits)) + *dst = ~0UL; + else + memset(dst, 0xff, len); } static inline void bitmap_copy(unsigned long *dst, const unsigned long *src, unsigned int nbits) { unsigned int len = BITS_TO_LONGS(nbits) * sizeof(unsigned long); - memcpy(dst, src, len); + + if (small_const_nbits(nbits)) + *dst = *src; + else + memcpy(dst, src, len); } /* @@ -431,6 +443,8 @@ static __always_inline void bitmap_set(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __set_bit(start, map); + else if (small_const_nbits(start + nbits)) + *map |= GENMASK(start + nbits - 1, start); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && @@ -445,6 +459,8 @@ static __always_inline void bitmap_clear(unsigned long *map, unsigned int start, { if (__builtin_constant_p(nbits) && nbits == 1) __clear_bit(start, map); + else if (small_const_nbits(start + nbits)) + *map &= ~GENMASK(start + nbits - 1, start); else if (__builtin_constant_p(start & BITMAP_MEM_MASK) && IS_ALIGNED(start, BITMAP_MEM_ALIGNMENT) && __builtin_constant_p(nbits & BITMAP_MEM_MASK) && From dc34d5036692c614eef23c1130ee42a201c316bf Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 24 Jun 2022 14:13:13 +0200 Subject: [PATCH 10/26] lib: test_bitmap: add compile-time optimization/evaluations assertions Add a function to the bitmap test suite, which will ensure that compilers are able to evaluate operations performed by the bitops/bitmap helpers to compile-time constants when all of the arguments are compile-time constants as well, or trigger a build bug otherwise. This should work on all architectures and all the optimization levels supported by Kbuild. The function doesn't perform any runtime tests and gets optimized out to nothing after passing the build assertions. Unfortunately, Clang for s390 is currently broken (up to the latest Git snapshots) -- see the comment in the code -- so for now there's a small workaround for it which doesn't alter the logics. Hope we'll be able to remove it one day (bugreport is on its way). Suggested-by: Yury Norov Signed-off-by: Alexander Lobakin Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- lib/test_bitmap.c | 62 +++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 62 insertions(+) diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index d5923a640457..25967cfa4ab2 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -869,6 +869,67 @@ static void __init test_bitmap_print_buf(void) } } +static void __init test_bitmap_const_eval(void) +{ + DECLARE_BITMAP(bitmap, BITS_PER_LONG); + unsigned long initvar = BIT(2); + unsigned long bitopvar = 0; + unsigned long var = 0; + int res; + + /* + * Compilers must be able to optimize all of those to compile-time + * constants on any supported optimization level (-O2, -Os) and any + * architecture. Otherwise, trigger a build bug. + * The whole function gets optimized out then, there's nothing to do + * in runtime. + */ + + /* + * Equals to `unsigned long bitmap[1] = { GENMASK(6, 5), }`. + * Clang on s390 optimizes bitops at compile-time as intended, but at + * the same time stops treating @bitmap and @bitopvar as compile-time + * constants after regular test_bit() is executed, thus triggering the + * build bugs below. So, call const_test_bit() there directly until + * the compiler is fixed. + */ + bitmap_clear(bitmap, 0, BITS_PER_LONG); +#if defined(__s390__) && defined(__clang__) + if (!const_test_bit(7, bitmap)) +#else + if (!test_bit(7, bitmap)) +#endif + bitmap_set(bitmap, 5, 2); + + /* Equals to `unsigned long bitopvar = BIT(20)` */ + __change_bit(31, &bitopvar); + bitmap_shift_right(&bitopvar, &bitopvar, 11, BITS_PER_LONG); + + /* Equals to `unsigned long var = BIT(25)` */ + var |= BIT(25); + if (var & BIT(0)) + var ^= GENMASK(9, 6); + + /* __const_hweight<32|64>(GENMASK(6, 5)) == 2 */ + res = bitmap_weight(bitmap, 20); + BUILD_BUG_ON(!__builtin_constant_p(res)); + BUILD_BUG_ON(res != 2); + + /* !(BIT(31) & BIT(18)) == 1 */ + res = !test_bit(18, &bitopvar); + BUILD_BUG_ON(!__builtin_constant_p(res)); + BUILD_BUG_ON(!res); + + /* BIT(2) & GENMASK(14, 8) == 0 */ + res = initvar & GENMASK(14, 8); + BUILD_BUG_ON(!__builtin_constant_p(res)); + BUILD_BUG_ON(res); + + /* ~BIT(25) */ + BUILD_BUG_ON(!__builtin_constant_p(~var)); + BUILD_BUG_ON(~var != ~BIT(25)); +} + static void __init selftest(void) { test_zero_clear(); @@ -884,6 +945,7 @@ static void __init selftest(void) test_for_each_set_clump8(); test_bitmap_cut(); test_bitmap_print_buf(); + test_bitmap_const_eval(); } KSTM_MODULE_LOADERS(test_bitmap); From 428bc098635680a664779f26f24fe9197d186172 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 11 Jul 2022 20:09:29 +0200 Subject: [PATCH 11/26] lib/bitmap: fix off-by-one in bitmap_to_arr64() GENMASK*() family takes the first and the last bits of the mask *including* them. So, with the current code bitmap_to_arr64() doesn't clear the tail properly: nbits % exp mask must be 1 GENMASK(1, 0) 0x3 0x1 ... 63 GENMASK(63, 0) 0xffffffffffffffff 0x7fffffffffffffff This was found by making the function always available instead of 32-bit BE systems only (for reusing in some new functionality). Turn the number of bits into the last bit set by subtracting 1. @nbits is already checked to be positive beforehand. Fixes: 0a97953fd221 ("lib: add bitmap_{from,to}_arr64") Signed-off-by: Alexander Lobakin Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- lib/bitmap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/lib/bitmap.c b/lib/bitmap.c index b18e31ea6e66..e903e13c62e1 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -1564,7 +1564,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits) /* Clear tail bits in the last element of array beyond nbits. */ if (nbits % 64) - buf[-1] &= GENMASK_ULL(nbits % 64, 0); + buf[-1] &= GENMASK_ULL((nbits - 1) % 64, 0); } EXPORT_SYMBOL(bitmap_to_arr64); #endif From 30fd8cdf53a02b54b199043fcf1857db76e8badc Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Mon, 11 Jul 2022 20:09:30 +0200 Subject: [PATCH 12/26] lib/test_bitmap: test the tail after bitmap_to_arr64() Currently, test_bitmap_arr64() only tests bitmap_to_arr64()'s sanity by comparing the result of double-conversion (bm -> arr64 -> bm2) with the input bitmap. However, this may be not enough when one side hides bugs of the second one (e.g. tail clearing, which is being performed by both). Expand the tests and check the tail of the actual arr64 used as a temporary buffer for double-converting. Signed-off-by: Alexander Lobakin Reviewed-by: Andy Shevchenko Signed-off-by: Yury Norov --- lib/test_bitmap.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/lib/test_bitmap.c b/lib/test_bitmap.c index 25967cfa4ab2..98754ff9fe68 100644 --- a/lib/test_bitmap.c +++ b/lib/test_bitmap.c @@ -604,6 +604,12 @@ static void __init test_bitmap_arr64(void) pr_err("bitmap_copy_arr64(nbits == %d:" " tail is not safely cleared: %d\n", nbits, next_bit); + if ((nbits % 64) && + (arr[(nbits - 1) / 64] & ~GENMASK_ULL((nbits - 1) % 64, 0))) + pr_err("bitmap_to_arr64(nbits == %d): tail is not safely cleared: 0x%016llx (must be 0x%016llx)\n", + nbits, arr[(nbits - 1) / 64], + GENMASK_ULL((nbits - 1) % 64, 0)); + if (nbits < EXP1_IN_BITS - 64) expect_eq_uint(arr[DIV_ROUND_UP(nbits, 64)], 0xa5a5a5a5); } From b0b0b77ea611e3088e9523e60860f4f41b62b235 Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Tue, 12 Jul 2022 17:38:36 +0200 Subject: [PATCH 13/26] iommu/vt-d: avoid invalid memory access via node_online(NUMA_NO_NODE) KASAN reports: [ 4.668325][ T0] BUG: KASAN: wild-memory-access in dmar_parse_one_rhsa (arch/x86/include/asm/bitops.h:214 arch/x86/include/asm/bitops.h:226 include/asm-generic/bitops/instrumented-non-atomic.h:142 include/linux/nodemask.h:415 drivers/iommu/intel/dmar.c:497) [ 4.676149][ T0] Read of size 8 at addr 1fffffff85115558 by task swapper/0/0 [ 4.683454][ T0] [ 4.685638][ T0] CPU: 0 PID: 0 Comm: swapper/0 Not tainted 5.19.0-rc3-00004-g0e862838f290 #1 [ 4.694331][ T0] Hardware name: Supermicro SYS-5018D-FN4T/X10SDV-8C-TLN4F, BIOS 1.1 03/02/2016 [ 4.703196][ T0] Call Trace: [ 4.706334][ T0] [ 4.709133][ T0] ? dmar_parse_one_rhsa (arch/x86/include/asm/bitops.h:214 arch/x86/include/asm/bitops.h:226 include/asm-generic/bitops/instrumented-non-atomic.h:142 include/linux/nodemask.h:415 drivers/iommu/intel/dmar.c:497) after converting the type of the first argument (@nr, bit number) of arch_test_bit() from `long` to `unsigned long`[0]. Under certain conditions (for example, when ACPI NUMA is disabled via command line), pxm_to_node() can return %NUMA_NO_NODE (-1). It is valid 'magic' number of NUMA node, but not valid bit number to use in bitops. node_online() eventually descends to test_bit() without checking for the input, assuming it's on caller side (which might be good for perf-critical tasks). There, -1 becomes %ULONG_MAX which leads to an insane array index when calculating bit position in memory. For now, add an explicit check for @node being not %NUMA_NO_NODE before calling test_bit(). The actual logics didn't change here at all. [0] https://github.com/norov/linux/commit/0e862838f290147ea9c16db852d8d494b552d38d Fixes: ee34b32d8c29 ("dmar: support for parsing Remapping Hardware Static Affinity structure") Cc: stable@vger.kernel.org # 2.6.33+ Reported-by: kernel test robot Signed-off-by: Alexander Lobakin Reviewed-by: Andy Shevchenko Reviewed-by: Lu Baolu Signed-off-by: Yury Norov --- drivers/iommu/intel/dmar.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c index 592c1e1a5d4b..70d324c9894a 100644 --- a/drivers/iommu/intel/dmar.c +++ b/drivers/iommu/intel/dmar.c @@ -494,7 +494,7 @@ static int dmar_parse_one_rhsa(struct acpi_dmar_header *header, void *arg) if (drhd->reg_base_addr == rhsa->base_address) { int node = pxm_to_node(rhsa->proximity_domain); - if (!node_online(node)) + if (node != NUMA_NO_NODE && !node_online(node)) node = NUMA_NO_NODE; drhd->iommu->node = node; return 0; From 0b4736a424a1358d613057a24ff97813305513e2 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:23 -0700 Subject: [PATCH 14/26] arm: align find_bit declarations with generic kernel ARM has their own implementation for find_bit functions, and function declarations are different with those in generic headers. Fix it. Signed-off-by: Yury Norov --- arch/arm/include/asm/bitops.h | 18 ++++++++++-------- 1 file changed, 10 insertions(+), 8 deletions(-) diff --git a/arch/arm/include/asm/bitops.h b/arch/arm/include/asm/bitops.h index 8e94fe7ab5eb..714440fa2fc6 100644 --- a/arch/arm/include/asm/bitops.h +++ b/arch/arm/include/asm/bitops.h @@ -160,18 +160,20 @@ extern int _test_and_change_bit(int nr, volatile unsigned long * p); /* * Little endian assembly bitops. nr = 0 -> byte 0 bit 0. */ -extern int _find_first_zero_bit_le(const unsigned long *p, unsigned size); -extern int _find_next_zero_bit_le(const unsigned long *p, int size, int offset); -extern int _find_first_bit_le(const unsigned long *p, unsigned size); -extern int _find_next_bit_le(const unsigned long *p, int size, int offset); +unsigned long _find_first_zero_bit_le(const unsigned long *p, unsigned long size); +unsigned long _find_next_zero_bit_le(const unsigned long *p, + unsigned long size, unsigned long offset); +unsigned long _find_first_bit_le(const unsigned long *p, unsigned long size); +unsigned long _find_next_bit_le(const unsigned long *p, unsigned long size, unsigned long offset); /* * Big endian assembly bitops. nr = 0 -> byte 3 bit 0. */ -extern int _find_first_zero_bit_be(const unsigned long *p, unsigned size); -extern int _find_next_zero_bit_be(const unsigned long *p, int size, int offset); -extern int _find_first_bit_be(const unsigned long *p, unsigned size); -extern int _find_next_bit_be(const unsigned long *p, int size, int offset); +unsigned long _find_first_zero_bit_be(const unsigned long *p, unsigned long size); +unsigned long _find_next_zero_bit_be(const unsigned long *p, + unsigned long size, unsigned long offset); +unsigned long _find_first_bit_be(const unsigned long *p, unsigned long size); +unsigned long _find_next_bit_be(const unsigned long *p, unsigned long size, unsigned long offset); #ifndef CONFIG_SMP /* From e2863a78593d638d3924a6f67900c4820034f349 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:24 -0700 Subject: [PATCH 15/26] lib/bitmap: change return types to bool where appropriate Some bitmap functions return boolean results in int variables. Fix it by changing return types to bool. Signed-off-by: Yury Norov --- include/linux/bitmap.h | 8 ++++---- lib/bitmap.c | 4 ++-- tools/include/linux/bitmap.h | 8 ++++---- tools/lib/bitmap.c | 2 +- 4 files changed, 11 insertions(+), 11 deletions(-) diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index c91638e507f2..e1a438bdda52 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -148,13 +148,13 @@ void __bitmap_shift_left(unsigned long *dst, const unsigned long *src, unsigned int shift, unsigned int nbits); void bitmap_cut(unsigned long *dst, const unsigned long *src, unsigned int first, unsigned int cut, unsigned int nbits); -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); void __bitmap_replace(unsigned long *dst, const unsigned long *old, const unsigned long *new, @@ -315,7 +315,7 @@ void bitmap_to_arr64(u64 *buf, const unsigned long *bitmap, unsigned int nbits); bitmap_copy_clear_tail((unsigned long *)(buf), (const unsigned long *)(bitmap), (nbits)) #endif -static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, +static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) @@ -341,7 +341,7 @@ static inline void bitmap_xor(unsigned long *dst, const unsigned long *src1, __bitmap_xor(dst, src1, src2, nbits); } -static inline int bitmap_andnot(unsigned long *dst, const unsigned long *src1, +static inline bool bitmap_andnot(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) diff --git a/lib/bitmap.c b/lib/bitmap.c index e903e13c62e1..9bc80f5bf149 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -237,7 +237,7 @@ void bitmap_cut(unsigned long *dst, const unsigned long *src, } EXPORT_SYMBOL(bitmap_cut); -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; @@ -275,7 +275,7 @@ void __bitmap_xor(unsigned long *dst, const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_xor); -int __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_andnot(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index afdf93bebaaf..2ae7ab8ed7d1 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -14,7 +14,7 @@ int __bitmap_weight(const unsigned long *bitmap, int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); bool __bitmap_equal(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits); @@ -45,7 +45,7 @@ static inline void bitmap_fill(unsigned long *dst, unsigned int nbits) dst[nlongs - 1] = BITMAP_LAST_WORD_MASK(nbits); } -static inline int bitmap_empty(const unsigned long *src, unsigned nbits) +static inline bool bitmap_empty(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -53,7 +53,7 @@ static inline int bitmap_empty(const unsigned long *src, unsigned nbits) return find_first_bit(src, nbits) == nbits; } -static inline int bitmap_full(const unsigned long *src, unsigned int nbits) +static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return ! (~(*src) & BITMAP_LAST_WORD_MASK(nbits)); @@ -146,7 +146,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, * @src2: operand 2 * @nbits: size of bitmap */ -static inline int bitmap_and(unsigned long *dst, const unsigned long *src1, +static inline bool bitmap_and(unsigned long *dst, const unsigned long *src1, const unsigned long *src2, unsigned int nbits) { if (small_const_nbits(nbits)) diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 354f8cdc0880..2e351d63fdba 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -57,7 +57,7 @@ size_t bitmap_scnprintf(unsigned long *bitmap, unsigned int nbits, return ret; } -int __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, +bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int bits) { unsigned int k; From 4dea97f8636d0514befc9fc5cf342b351b7d0e20 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:25 -0700 Subject: [PATCH 16/26] lib/bitmap: change type of bitmap_weight to unsigned long bitmap_weight() doesn't return negative values, so change it's type to unsigned long. It may help compiler to generate better code and catch bugs. Signed-off-by: Yury Norov --- drivers/dma/ti/k3-udma.c | 6 +++--- drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c | 2 +- drivers/gpu/drm/i915/display/intel_display_power.c | 2 +- drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c | 2 +- drivers/iommu/intel/iommu.c | 2 +- drivers/net/ethernet/mellanox/mlx4/fw.c | 2 +- drivers/net/wireless/ath/ath9k/htc_drv_debug.c | 2 +- drivers/net/wireless/ath/carl9170/debug.c | 2 +- include/linux/bitmap.h | 5 +++-- lib/bitmap.c | 5 ++--- tools/include/linux/bitmap.h | 4 ++-- tools/lib/bitmap.c | 4 ++-- 12 files changed, 19 insertions(+), 19 deletions(-) diff --git a/drivers/dma/ti/k3-udma.c b/drivers/dma/ti/k3-udma.c index 2f0d2c68c93c..07cb48db76ba 100644 --- a/drivers/dma/ti/k3-udma.c +++ b/drivers/dma/ti/k3-udma.c @@ -4997,7 +4997,7 @@ static int setup_resources(struct udma_dev *ud) switch (ud->match_data->type) { case DMA_TYPE_UDMA: dev_info(dev, - "Channels: %d (tchan: %u, rchan: %u, gp-rflow: %u)\n", + "Channels: %d (tchan: %lu, rchan: %lu, gp-rflow: %lu)\n", ch_count, ud->tchan_cnt - bitmap_weight(ud->tchan_map, ud->tchan_cnt), @@ -5008,7 +5008,7 @@ static int setup_resources(struct udma_dev *ud) break; case DMA_TYPE_BCDMA: dev_info(dev, - "Channels: %d (bchan: %u, tchan: %u, rchan: %u)\n", + "Channels: %d (bchan: %lu, tchan: %lu, rchan: %lu)\n", ch_count, ud->bchan_cnt - bitmap_weight(ud->bchan_map, ud->bchan_cnt), @@ -5019,7 +5019,7 @@ static int setup_resources(struct udma_dev *ud) break; case DMA_TYPE_PKTDMA: dev_info(dev, - "Channels: %d (tchan: %u, rchan: %u)\n", + "Channels: %d (tchan: %lu, rchan: %lu)\n", ch_count, ud->tchan_cnt - bitmap_weight(ud->tchan_map, ud->tchan_cnt), diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c index 16699158e00d..1098506ba1aa 100644 --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_gfx.c @@ -195,7 +195,7 @@ void amdgpu_gfx_compute_queue_acquire(struct amdgpu_device *adev) set_bit(i, adev->gfx.mec.queue_bitmap); } - dev_dbg(adev->dev, "mec queue bitmap weight=%d\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES)); + dev_dbg(adev->dev, "mec queue bitmap weight=%ld\n", bitmap_weight(adev->gfx.mec.queue_bitmap, AMDGPU_MAX_COMPUTE_QUEUES)); } void amdgpu_gfx_graphics_queue_acquire(struct amdgpu_device *adev) diff --git a/drivers/gpu/drm/i915/display/intel_display_power.c b/drivers/gpu/drm/i915/display/intel_display_power.c index 949edc983a16..4204e8a0e1a6 100644 --- a/drivers/gpu/drm/i915/display/intel_display_power.c +++ b/drivers/gpu/drm/i915/display/intel_display_power.c @@ -378,7 +378,7 @@ static void print_power_domains(struct i915_power_domains *power_domains, power_domains); enum intel_display_power_domain domain; - drm_dbg(&i915->drm, "%s (%d):\n", prefix, bitmap_weight(mask->bits, POWER_DOMAIN_NUM)); + drm_dbg(&i915->drm, "%s (%ld):\n", prefix, bitmap_weight(mask->bits, POWER_DOMAIN_NUM)); for_each_power_domain(domain, mask) drm_dbg(&i915->drm, "%s use_count %d\n", intel_display_power_domain_str(domain), diff --git a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c index 56a3063545ec..3d35b3982a60 100644 --- a/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c +++ b/drivers/gpu/drm/msm/disp/mdp5/mdp5_smp.c @@ -363,7 +363,7 @@ void mdp5_smp_dump(struct mdp5_smp *smp, struct drm_printer *p) } drm_printf(p, "TOTAL:\t%d\t(of %d)\n", total, smp->blk_cnt); - drm_printf(p, "AVAIL:\t%d\n", smp->blk_cnt - + drm_printf(p, "AVAIL:\t%ld\n", smp->blk_cnt - bitmap_weight(state->state, smp->blk_cnt)); if (drm_can_sleep()) diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c index 44016594831d..2f1b09f34706 100644 --- a/drivers/iommu/intel/iommu.c +++ b/drivers/iommu/intel/iommu.c @@ -3946,7 +3946,7 @@ static ssize_t domains_used_show(struct device *dev, struct device_attribute *attr, char *buf) { struct intel_iommu *iommu = dev_to_intel_iommu(dev); - return sprintf(buf, "%d\n", bitmap_weight(iommu->domain_ids, + return sprintf(buf, "%ld\n", bitmap_weight(iommu->domain_ids, cap_ndoms(iommu->cap))); } static DEVICE_ATTR_RO(domains_used); diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index 42c96c9d7fb1..af054a3808ca 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -463,7 +463,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave, field = min( bitmap_weight(actv_ports.ports, dev->caps.num_ports), - dev->caps.num_ports); + (unsigned long)dev->caps.num_ports); MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_NUM_PORTS_OFFSET); size = dev->caps.function_caps; /* set PF behaviours */ diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c index b3ed65e5c4da..d32056c4ee1d 100644 --- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c +++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c @@ -296,7 +296,7 @@ static ssize_t read_file_slot(struct file *file, char __user *user_buf, spin_lock_bh(&priv->tx.tx_lock); len = scnprintf(buf, sizeof(buf), "TX slot bitmap : %*pb\n" - "Used slots : %d\n", + "Used slots : %ld\n", MAX_TX_BUF_NUM, priv->tx.tx_slot, bitmap_weight(priv->tx.tx_slot, MAX_TX_BUF_NUM)); spin_unlock_bh(&priv->tx.tx_lock); diff --git a/drivers/net/wireless/ath/carl9170/debug.c b/drivers/net/wireless/ath/carl9170/debug.c index bb40889d7c72..7e88882b87d9 100644 --- a/drivers/net/wireless/ath/carl9170/debug.c +++ b/drivers/net/wireless/ath/carl9170/debug.c @@ -221,7 +221,7 @@ static char *carl9170_debugfs_mem_usage_read(struct ar9170 *ar, char *buf, ADD(buf, *len, bufsize, "jar: [%*pb]\n", ar->fw.mem_blocks, ar->mem_bitmap); - ADD(buf, *len, bufsize, "cookies: used:%3d / total:%3d, allocs:%d\n", + ADD(buf, *len, bufsize, "cookies: used:%3ld / total:%3d, allocs:%d\n", bitmap_weight(ar->mem_bitmap, ar->fw.mem_blocks), ar->fw.mem_blocks, atomic_read(&ar->mem_allocs)); diff --git a/include/linux/bitmap.h b/include/linux/bitmap.h index e1a438bdda52..035d4ac66641 100644 --- a/include/linux/bitmap.h +++ b/include/linux/bitmap.h @@ -163,7 +163,7 @@ bool __bitmap_intersects(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); bool __bitmap_subset(const unsigned long *bitmap1, const unsigned long *bitmap2, unsigned int nbits); -int __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); +unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int nbits); void __bitmap_set(unsigned long *map, unsigned int start, int len); void __bitmap_clear(unsigned long *map, unsigned int start, int len); @@ -431,7 +431,8 @@ static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) return find_first_zero_bit(src, nbits) == nbits; } -static __always_inline int bitmap_weight(const unsigned long *src, unsigned int nbits) +static __always_inline +unsigned long bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); diff --git a/lib/bitmap.c b/lib/bitmap.c index 9bc80f5bf149..2b67cd657692 100644 --- a/lib/bitmap.c +++ b/lib/bitmap.c @@ -333,10 +333,9 @@ bool __bitmap_subset(const unsigned long *bitmap1, } EXPORT_SYMBOL(__bitmap_subset); -int __bitmap_weight(const unsigned long *bitmap, unsigned int bits) +unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { - unsigned int k, lim = bits/BITS_PER_LONG; - int w = 0; + unsigned long k, w = 0, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; k++) w += hweight_long(bitmap[k]); diff --git a/tools/include/linux/bitmap.h b/tools/include/linux/bitmap.h index 2ae7ab8ed7d1..ae1852e39142 100644 --- a/tools/include/linux/bitmap.h +++ b/tools/include/linux/bitmap.h @@ -11,7 +11,7 @@ #define DECLARE_BITMAP(name,bits) \ unsigned long name[BITS_TO_LONGS(bits)] -int __bitmap_weight(const unsigned long *bitmap, int bits); +unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits); void __bitmap_or(unsigned long *dst, const unsigned long *bitmap1, const unsigned long *bitmap2, int bits); bool __bitmap_and(unsigned long *dst, const unsigned long *bitmap1, @@ -61,7 +61,7 @@ static inline bool bitmap_full(const unsigned long *src, unsigned int nbits) return find_first_zero_bit(src, nbits) == nbits; } -static inline int bitmap_weight(const unsigned long *src, unsigned int nbits) +static inline unsigned long bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); diff --git a/tools/lib/bitmap.c b/tools/lib/bitmap.c index 2e351d63fdba..e1fafc131a49 100644 --- a/tools/lib/bitmap.c +++ b/tools/lib/bitmap.c @@ -5,9 +5,9 @@ */ #include -int __bitmap_weight(const unsigned long *bitmap, int bits) +unsigned long __bitmap_weight(const unsigned long *bitmap, unsigned int bits) { - int k, w = 0, lim = bits/BITS_PER_LONG; + unsigned long k, w = 0, lim = bits/BITS_PER_LONG; for (k = 0; k < lim; k++) w += hweight_long(bitmap[k]); From cb32c285cc10e428589194e30233d673e7c23c72 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:26 -0700 Subject: [PATCH 17/26] cpumask: change return types to bool where appropriate Some cpumask functions have integer return types where return values are naturally booleans. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index fe29ac7cc469..b54e27d9da6b 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -372,9 +372,9 @@ static __always_inline void __cpumask_clear_cpu(int cpu, struct cpumask *dstp) * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns 1 if @cpu is set in @cpumask, else returns 0 + * Returns true if @cpu is set in @cpumask, else returns false */ -static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpumask) +static __always_inline bool cpumask_test_cpu(int cpu, const struct cpumask *cpumask) { return test_bit(cpumask_check(cpu), cpumask_bits((cpumask))); } @@ -384,11 +384,11 @@ static __always_inline int cpumask_test_cpu(int cpu, const struct cpumask *cpuma * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 + * Returns true if @cpu is set in old bitmap of @cpumask, else returns false * * test_and_set_bit wrapper for cpumasks. */ -static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) +static __always_inline bool cpumask_test_and_set_cpu(int cpu, struct cpumask *cpumask) { return test_and_set_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -398,11 +398,11 @@ static __always_inline int cpumask_test_and_set_cpu(int cpu, struct cpumask *cpu * @cpu: cpu number (< nr_cpu_ids) * @cpumask: the cpumask pointer * - * Returns 1 if @cpu is set in old bitmap of @cpumask, else returns 0 + * Returns true if @cpu is set in old bitmap of @cpumask, else returns false * * test_and_clear_bit wrapper for cpumasks. */ -static __always_inline int cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) +static __always_inline bool cpumask_test_and_clear_cpu(int cpu, struct cpumask *cpumask) { return test_and_clear_bit(cpumask_check(cpu), cpumask_bits(cpumask)); } @@ -431,9 +431,9 @@ static inline void cpumask_clear(struct cpumask *dstp) * @src1p: the first input * @src2p: the second input * - * If *@dstp is empty, returns 0, else returns 1 + * If *@dstp is empty, returns false, else returns true */ -static inline int cpumask_and(struct cpumask *dstp, +static inline bool cpumask_and(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { @@ -474,9 +474,9 @@ static inline void cpumask_xor(struct cpumask *dstp, * @src1p: the first input * @src2p: the second input * - * If *@dstp is empty, returns 0, else returns 1 + * If *@dstp is empty, returns false, else returns true */ -static inline int cpumask_andnot(struct cpumask *dstp, +static inline bool cpumask_andnot(struct cpumask *dstp, const struct cpumask *src1p, const struct cpumask *src2p) { @@ -539,9 +539,9 @@ static inline bool cpumask_intersects(const struct cpumask *src1p, * @src1p: the first input * @src2p: the second input * - * Returns 1 if *@src1p is a subset of *@src2p, else returns 0 + * Returns true if *@src1p is a subset of *@src2p, else returns false */ -static inline int cpumask_subset(const struct cpumask *src1p, +static inline bool cpumask_subset(const struct cpumask *src1p, const struct cpumask *src2p) { return bitmap_subset(cpumask_bits(src1p), cpumask_bits(src2p), From 8b6b795d9bfc031a8953c40fac8d3cf67e1a4d3d Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:27 -0700 Subject: [PATCH 18/26] lib/cpumask: change return types to unsigned where appropriate Switch return types to unsigned int where return values cannot be negative. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 14 +++++++------- lib/cpumask.c | 18 +++++++++--------- 2 files changed, 16 insertions(+), 16 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index b54e27d9da6b..760022bcb925 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -176,12 +176,12 @@ static inline unsigned int cpumask_local_spread(unsigned int i, int node) return 0; } -static inline int cpumask_any_and_distribute(const struct cpumask *src1p, +static inline unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { return cpumask_first_and(src1p, src2p); } -static inline int cpumask_any_distribute(const struct cpumask *srcp) +static inline unsigned int cpumask_any_distribute(const struct cpumask *srcp) { return cpumask_first(srcp); } @@ -258,12 +258,12 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } -int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); -int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu); +unsigned int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); +unsigned int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu); unsigned int cpumask_local_spread(unsigned int i, int node); -int cpumask_any_and_distribute(const struct cpumask *src1p, +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); -int cpumask_any_distribute(const struct cpumask *srcp); +unsigned int cpumask_any_distribute(const struct cpumask *srcp); /** * for_each_cpu - iterate over every cpu in a mask @@ -289,7 +289,7 @@ int cpumask_any_distribute(const struct cpumask *srcp); (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) -extern int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); +unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); /** * for_each_cpu_wrap - iterate over every cpu in a mask, starting at a specified location diff --git a/lib/cpumask.c b/lib/cpumask.c index a971a82d2f43..da68f6bbde44 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -31,7 +31,7 @@ EXPORT_SYMBOL(cpumask_next); * * Returns >= nr_cpu_ids if no further cpus set in both. */ -int cpumask_next_and(int n, const struct cpumask *src1p, +unsigned int cpumask_next_and(int n, const struct cpumask *src1p, const struct cpumask *src2p) { /* -1 is a legal arg here. */ @@ -50,7 +50,7 @@ EXPORT_SYMBOL(cpumask_next_and); * Often used to find any cpu but smp_processor_id() in a mask. * Returns >= nr_cpu_ids if no cpus set. */ -int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) +unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) { unsigned int i; @@ -74,9 +74,9 @@ EXPORT_SYMBOL(cpumask_any_but); * Note: the @wrap argument is required for the start condition when * we cannot assume @start is set in @mask. */ -int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) +unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap) { - int next; + unsigned int next; again: next = cpumask_next(n, mask); @@ -205,7 +205,7 @@ void __init free_bootmem_cpumask_var(cpumask_var_t mask) */ unsigned int cpumask_local_spread(unsigned int i, int node) { - int cpu; + unsigned int cpu; /* Wrap: we always want a cpu. */ i %= num_online_cpus(); @@ -243,10 +243,10 @@ static DEFINE_PER_CPU(int, distribute_cpu_mask_prev); * * Returns >= nr_cpu_ids if the intersection is empty. */ -int cpumask_any_and_distribute(const struct cpumask *src1p, +unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p) { - int next, prev; + unsigned int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); @@ -262,9 +262,9 @@ int cpumask_any_and_distribute(const struct cpumask *src1p, } EXPORT_SYMBOL(cpumask_any_and_distribute); -int cpumask_any_distribute(const struct cpumask *srcp) +unsigned int cpumask_any_distribute(const struct cpumask *srcp) { - int next, prev; + unsigned int next, prev; /* NOTE: our first selection will skip 0. */ prev = __this_cpu_read(distribute_cpu_mask_prev); From 9b2e70860ef2f0d74b6d9e57929d57b14481b9c9 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:28 -0700 Subject: [PATCH 19/26] lib/cpumask: move trivial wrappers around find_bit to the header To avoid circular dependencies, cpumask keeps simple (almost) one-line wrappers around find_bit() in a c-file. Commit 47d8c15615c0a2 ("include: move find.h from asm_generic to linux") moved find.h header out of asm_generic include path, and it helped to fix many circular dependencies, including some in cpumask.h. This patch moves those one-liners to header files. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 57 ++++++++++++++++++++++++++++++++++++++--- lib/cpumask.c | 55 --------------------------------------- 2 files changed, 54 insertions(+), 58 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index 760022bcb925..ea3de2c2c180 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -241,7 +241,21 @@ static inline unsigned int cpumask_last(const struct cpumask *srcp) return find_last_bit(cpumask_bits(srcp), nr_cpumask_bits); } -unsigned int __pure cpumask_next(int n, const struct cpumask *srcp); +/** + * cpumask_next - get the next cpu in a cpumask + * @n: the cpu prior to the place to search (ie. return will be > @n) + * @srcp: the cpumask pointer + * + * Returns >= nr_cpu_ids if no further cpus set. + */ +static inline +unsigned int cpumask_next(int n, const struct cpumask *srcp) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); +} /** * cpumask_next_zero - get the next unset cpu in a cpumask @@ -258,8 +272,25 @@ static inline unsigned int cpumask_next_zero(int n, const struct cpumask *srcp) return find_next_zero_bit(cpumask_bits(srcp), nr_cpumask_bits, n+1); } -unsigned int __pure cpumask_next_and(int n, const struct cpumask *, const struct cpumask *); -unsigned int __pure cpumask_any_but(const struct cpumask *mask, unsigned int cpu); +/** + * cpumask_next_and - get the next cpu in *src1p & *src2p + * @n: the cpu prior to the place to search (ie. return will be > @n) + * @src1p: the first cpumask pointer + * @src2p: the second cpumask pointer + * + * Returns >= nr_cpu_ids if no further cpus set in both. + */ +static inline +unsigned int cpumask_next_and(int n, const struct cpumask *src1p, + const struct cpumask *src2p) +{ + /* -1 is a legal arg here. */ + if (n != -1) + cpumask_check(n); + return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), + nr_cpumask_bits, n + 1); +} + unsigned int cpumask_local_spread(unsigned int i, int node); unsigned int cpumask_any_and_distribute(const struct cpumask *src1p, const struct cpumask *src2p); @@ -324,6 +355,26 @@ unsigned int cpumask_next_wrap(int n, const struct cpumask *mask, int start, boo for ((cpu) = -1; \ (cpu) = cpumask_next_and((cpu), (mask1), (mask2)), \ (cpu) < nr_cpu_ids;) + +/** + * cpumask_any_but - return a "random" in a cpumask, but not this one. + * @mask: the cpumask to search + * @cpu: the cpu to ignore. + * + * Often used to find any cpu but smp_processor_id() in a mask. + * Returns >= nr_cpu_ids if no cpus set. + */ +static inline +unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) +{ + unsigned int i; + + cpumask_check(cpu); + for_each_cpu(i, mask) + if (i != cpu) + break; + return i; +} #endif /* SMP */ #define CPU_BITS_NONE \ diff --git a/lib/cpumask.c b/lib/cpumask.c index da68f6bbde44..cb7262ff8633 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -7,61 +7,6 @@ #include #include -/** - * cpumask_next - get the next cpu in a cpumask - * @n: the cpu prior to the place to search (ie. return will be > @n) - * @srcp: the cpumask pointer - * - * Returns >= nr_cpu_ids if no further cpus set. - */ -unsigned int cpumask_next(int n, const struct cpumask *srcp) -{ - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); - return find_next_bit(cpumask_bits(srcp), nr_cpumask_bits, n + 1); -} -EXPORT_SYMBOL(cpumask_next); - -/** - * cpumask_next_and - get the next cpu in *src1p & *src2p - * @n: the cpu prior to the place to search (ie. return will be > @n) - * @src1p: the first cpumask pointer - * @src2p: the second cpumask pointer - * - * Returns >= nr_cpu_ids if no further cpus set in both. - */ -unsigned int cpumask_next_and(int n, const struct cpumask *src1p, - const struct cpumask *src2p) -{ - /* -1 is a legal arg here. */ - if (n != -1) - cpumask_check(n); - return find_next_and_bit(cpumask_bits(src1p), cpumask_bits(src2p), - nr_cpumask_bits, n + 1); -} -EXPORT_SYMBOL(cpumask_next_and); - -/** - * cpumask_any_but - return a "random" in a cpumask, but not this one. - * @mask: the cpumask to search - * @cpu: the cpu to ignore. - * - * Often used to find any cpu but smp_processor_id() in a mask. - * Returns >= nr_cpu_ids if no cpus set. - */ -unsigned int cpumask_any_but(const struct cpumask *mask, unsigned int cpu) -{ - unsigned int i; - - cpumask_check(cpu); - for_each_cpu(i, mask) - if (i != cpu) - break; - return i; -} -EXPORT_SYMBOL(cpumask_any_but); - /** * cpumask_next_wrap - helper to implement for_each_cpu_wrap * @n: the cpu prior to the place to search From db96b0c5f9db22d908ab5f7cd75904adba4b28ca Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 10 Jun 2021 10:56:49 +0200 Subject: [PATCH 20/26] headers/deps: mm: Optimize header dependencies There's a couple of superfluous inclusions here - remove them before doing bigger changes. Signed-off-by: Ingo Molnar Signed-off-by: Yury Norov --- include/linux/gfp.h | 3 --- 1 file changed, 3 deletions(-) diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 2d2ccae933c2..52f2c873a7d4 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -2,10 +2,7 @@ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H -#include #include -#include -#include #include /* The typedef is in types.h but we want the documentation here */ From cb5a065b4ea9c062a18143c8a14e831179687f54 Mon Sep 17 00:00:00 2001 From: Ingo Molnar Date: Thu, 14 Apr 2022 18:42:28 +0200 Subject: [PATCH 21/26] headers/deps: mm: Split out of This is a much smaller header. Signed-off-by: Ingo Molnar Signed-off-by: Yury Norov --- include/linux/gfp.h | 345 +------------------------------------ include/linux/gfp_types.h | 348 ++++++++++++++++++++++++++++++++++++++ 2 files changed, 350 insertions(+), 343 deletions(-) create mode 100644 include/linux/gfp_types.h diff --git a/include/linux/gfp.h b/include/linux/gfp.h index 52f2c873a7d4..f314be58fa77 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -2,354 +2,13 @@ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H +#include + #include #include -/* The typedef is in types.h but we want the documentation here */ -#if 0 -/** - * typedef gfp_t - Memory allocation flags. - * - * GFP flags are commonly used throughout Linux to indicate how memory - * should be allocated. The GFP acronym stands for get_free_pages(), - * the underlying memory allocation function. Not every GFP flag is - * supported by every function which may allocate memory. Most users - * will want to use a plain ``GFP_KERNEL``. - */ -typedef unsigned int __bitwise gfp_t; -#endif - struct vm_area_struct; -/* - * In case of changes, please don't forget to update - * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c - */ - -/* Plain integer GFP bitmasks. Do not use this directly. */ -#define ___GFP_DMA 0x01u -#define ___GFP_HIGHMEM 0x02u -#define ___GFP_DMA32 0x04u -#define ___GFP_MOVABLE 0x08u -#define ___GFP_RECLAIMABLE 0x10u -#define ___GFP_HIGH 0x20u -#define ___GFP_IO 0x40u -#define ___GFP_FS 0x80u -#define ___GFP_ZERO 0x100u -#define ___GFP_ATOMIC 0x200u -#define ___GFP_DIRECT_RECLAIM 0x400u -#define ___GFP_KSWAPD_RECLAIM 0x800u -#define ___GFP_WRITE 0x1000u -#define ___GFP_NOWARN 0x2000u -#define ___GFP_RETRY_MAYFAIL 0x4000u -#define ___GFP_NOFAIL 0x8000u -#define ___GFP_NORETRY 0x10000u -#define ___GFP_MEMALLOC 0x20000u -#define ___GFP_COMP 0x40000u -#define ___GFP_NOMEMALLOC 0x80000u -#define ___GFP_HARDWALL 0x100000u -#define ___GFP_THISNODE 0x200000u -#define ___GFP_ACCOUNT 0x400000u -#define ___GFP_ZEROTAGS 0x800000u -#ifdef CONFIG_KASAN_HW_TAGS -#define ___GFP_SKIP_ZERO 0x1000000u -#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u -#define ___GFP_SKIP_KASAN_POISON 0x4000000u -#else -#define ___GFP_SKIP_ZERO 0 -#define ___GFP_SKIP_KASAN_UNPOISON 0 -#define ___GFP_SKIP_KASAN_POISON 0 -#endif -#ifdef CONFIG_LOCKDEP -#define ___GFP_NOLOCKDEP 0x8000000u -#else -#define ___GFP_NOLOCKDEP 0 -#endif -/* If the above are modified, __GFP_BITS_SHIFT may need updating */ - -/* - * Physical address zone modifiers (see linux/mmzone.h - low four bits) - * - * Do not put any conditional on these. If necessary modify the definitions - * without the underscores and use them consistently. The definitions here may - * be used in bit comparisons. - */ -#define __GFP_DMA ((__force gfp_t)___GFP_DMA) -#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) -#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) -#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ -#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) - -/** - * DOC: Page mobility and placement hints - * - * Page mobility and placement hints - * --------------------------------- - * - * These flags provide hints about how mobile the page is. Pages with similar - * mobility are placed within the same pageblocks to minimise problems due - * to external fragmentation. - * - * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be - * moved by page migration during memory compaction or can be reclaimed. - * - * %__GFP_RECLAIMABLE is used for slab allocations that specify - * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. - * - * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, - * these pages will be spread between local zones to avoid all the dirty - * pages being in one zone (fair zone allocation policy). - * - * %__GFP_HARDWALL enforces the cpuset memory allocation policy. - * - * %__GFP_THISNODE forces the allocation to be satisfied from the requested - * node with no fallbacks or placement policy enforcements. - * - * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. - */ -#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) -#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) -#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) -#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) -#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) - -/** - * DOC: Watermark modifiers - * - * Watermark modifiers -- controls access to emergency reserves - * ------------------------------------------------------------ - * - * %__GFP_HIGH indicates that the caller is high-priority and that granting - * the request is necessary before the system can make forward progress. - * For example, creating an IO context to clean pages. - * - * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is - * high priority. Users are typically interrupt handlers. This may be - * used in conjunction with %__GFP_HIGH - * - * %__GFP_MEMALLOC allows access to all memory. This should only be used when - * the caller guarantees the allocation will allow more memory to be freed - * very shortly e.g. process exiting or swapping. Users either should - * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). - * Users of this flag have to be extremely careful to not deplete the reserve - * completely and implement a throttling mechanism which controls the - * consumption of the reserve based on the amount of freed memory. - * Usage of a pre-allocated pool (e.g. mempool) should be always considered - * before using this flag. - * - * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. - * This takes precedence over the %__GFP_MEMALLOC flag if both are set. - */ -#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) -#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) -#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) -#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) - -/** - * DOC: Reclaim modifiers - * - * Reclaim modifiers - * ----------------- - * Please note that all the following flags are only applicable to sleepable - * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). - * - * %__GFP_IO can start physical IO. - * - * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the - * allocator recursing into the filesystem which might already be holding - * locks. - * - * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. - * This flag can be cleared to avoid unnecessary delays when a fallback - * option is available. - * - * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when - * the low watermark is reached and have it reclaim pages until the high - * watermark is reached. A caller may wish to clear this flag when fallback - * options are available and the reclaim is likely to disrupt the system. The - * canonical example is THP allocation where a fallback is cheap but - * reclaim/compaction may cause indirect stalls. - * - * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. - * - * The default allocator behavior depends on the request size. We have a concept - * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). - * !costly allocations are too essential to fail so they are implicitly - * non-failing by default (with some exceptions like OOM victims might fail so - * the caller still has to check for failures) while costly requests try to be - * not disruptive and back off even without invoking the OOM killer. - * The following three modifiers might be used to override some of these - * implicit rules - * - * %__GFP_NORETRY: The VM implementation will try only very lightweight - * memory direct reclaim to get some memory under memory pressure (thus - * it can sleep). It will avoid disruptive actions like OOM killer. The - * caller must handle the failure which is quite likely to happen under - * heavy memory pressure. The flag is suitable when failure can easily be - * handled at small cost, such as reduced throughput - * - * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim - * procedures that have previously failed if there is some indication - * that progress has been made else where. It can wait for other - * tasks to attempt high level approaches to freeing memory such as - * compaction (which removes fragmentation) and page-out. - * There is still a definite limit to the number of retries, but it is - * a larger limit than with %__GFP_NORETRY. - * Allocations with this flag may fail, but only when there is - * genuinely little unused memory. While these allocations do not - * directly trigger the OOM killer, their failure indicates that - * the system is likely to need to use the OOM killer soon. The - * caller must handle failure, but can reasonably do so by failing - * a higher-level request, or completing it only in a much less - * efficient manner. - * If the allocation does fail, and the caller is in a position to - * free some non-essential memory, doing so could benefit the system - * as a whole. - * - * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller - * cannot handle allocation failures. The allocation could block - * indefinitely but will never return with failure. Testing for - * failure is pointless. - * New users should be evaluated carefully (and the flag should be - * used only when there is no reasonable failure policy) but it is - * definitely preferable to use the flag rather than opencode endless - * loop around allocator. - * Using this flag for costly allocations is _highly_ discouraged. - */ -#define __GFP_IO ((__force gfp_t)___GFP_IO) -#define __GFP_FS ((__force gfp_t)___GFP_FS) -#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ -#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ -#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) -#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) -#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) -#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) - -/** - * DOC: Action modifiers - * - * Action modifiers - * ---------------- - * - * %__GFP_NOWARN suppresses allocation failure reports. - * - * %__GFP_COMP address compound page metadata. - * - * %__GFP_ZERO returns a zeroed page on success. - * - * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself - * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that - * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting - * memory tags at the same time as zeroing memory has minimal additional - * performace impact. - * - * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. - * Only effective in HW_TAGS mode. - * - * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. - * Typically, used for userspace pages. Only effective in HW_TAGS mode. - */ -#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) -#define __GFP_COMP ((__force gfp_t)___GFP_COMP) -#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) -#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) -#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) -#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) -#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) - -/* Disable lockdep for GFP context tracking */ -#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) - -/* Room for N __GFP_FOO bits */ -#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) -#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) - -/** - * DOC: Useful GFP flag combinations - * - * Useful GFP flag combinations - * ---------------------------- - * - * Useful GFP flag combinations that are commonly used. It is recommended - * that subsystems start with one of these combinations and then set/clear - * %__GFP_FOO flags as necessary. - * - * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower - * watermark is applied to allow access to "atomic reserves". - * The current implementation doesn't support NMI and few other strict - * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. - * - * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires - * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. - * - * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is - * accounted to kmemcg. - * - * %GFP_NOWAIT is for kernel allocations that should not stall for direct - * reclaim, start physical IO or use any filesystem callback. - * - * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages - * that do not require the starting of any physical IO. - * Please try to avoid using this flag directly and instead use - * memalloc_noio_{save,restore} to mark the whole scope which cannot - * perform any IO with a short explanation why. All allocation requests - * will inherit GFP_NOIO implicitly. - * - * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. - * Please try to avoid using this flag directly and instead use - * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't - * recurse into the FS layer with a short explanation why. All allocation - * requests will inherit GFP_NOFS implicitly. - * - * %GFP_USER is for userspace allocations that also need to be directly - * accessibly by the kernel or hardware. It is typically used by hardware - * for buffers that are mapped to userspace (e.g. graphics) that hardware - * still must DMA to. cpuset limits are enforced for these allocations. - * - * %GFP_DMA exists for historical reasons and should be avoided where possible. - * The flags indicates that the caller requires that the lowest zone be - * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but - * it would require careful auditing as some users really require it and - * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the - * lowest zone as a type of emergency reserve. - * - * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit - * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory - * because the DMA32 kmalloc cache array is not implemented. - * (Reason: there is no such user in kernel). - * - * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, - * do not need to be directly accessible by the kernel but that cannot - * move once in use. An example may be a hardware allocation that maps - * data directly into userspace but has no addressing limitations. - * - * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not - * need direct access to but can use kmap() when access is required. They - * are expected to be movable via page reclaim or page migration. Typically, - * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. - * - * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They - * are compound allocations that will generally fail quickly if memory is not - * available and will not wake kswapd/kcompactd on failure. The _LIGHT - * version does not attempt reclaim/compaction at all and is by default used - * in page fault path, while the non-light is used by khugepaged. - */ -#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) -#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) -#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) -#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) -#define GFP_NOIO (__GFP_RECLAIM) -#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) -#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) -#define GFP_DMA __GFP_DMA -#define GFP_DMA32 __GFP_DMA32 -#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) -#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ - __GFP_SKIP_KASAN_POISON) -#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ - __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) -#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) - /* Convert GFP flags to their corresponding migrate type */ #define GFP_MOVABLE_MASK (__GFP_RECLAIMABLE|__GFP_MOVABLE) #define GFP_MOVABLE_SHIFT 3 diff --git a/include/linux/gfp_types.h b/include/linux/gfp_types.h new file mode 100644 index 000000000000..06fc85cee23f --- /dev/null +++ b/include/linux/gfp_types.h @@ -0,0 +1,348 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_GFP_TYPES_H +#define __LINUX_GFP_TYPES_H + +/* The typedef is in types.h but we want the documentation here */ +#if 0 +/** + * typedef gfp_t - Memory allocation flags. + * + * GFP flags are commonly used throughout Linux to indicate how memory + * should be allocated. The GFP acronym stands for get_free_pages(), + * the underlying memory allocation function. Not every GFP flag is + * supported by every function which may allocate memory. Most users + * will want to use a plain ``GFP_KERNEL``. + */ +typedef unsigned int __bitwise gfp_t; +#endif + +/* + * In case of changes, please don't forget to update + * include/trace/events/mmflags.h and tools/perf/builtin-kmem.c + */ + +/* Plain integer GFP bitmasks. Do not use this directly. */ +#define ___GFP_DMA 0x01u +#define ___GFP_HIGHMEM 0x02u +#define ___GFP_DMA32 0x04u +#define ___GFP_MOVABLE 0x08u +#define ___GFP_RECLAIMABLE 0x10u +#define ___GFP_HIGH 0x20u +#define ___GFP_IO 0x40u +#define ___GFP_FS 0x80u +#define ___GFP_ZERO 0x100u +#define ___GFP_ATOMIC 0x200u +#define ___GFP_DIRECT_RECLAIM 0x400u +#define ___GFP_KSWAPD_RECLAIM 0x800u +#define ___GFP_WRITE 0x1000u +#define ___GFP_NOWARN 0x2000u +#define ___GFP_RETRY_MAYFAIL 0x4000u +#define ___GFP_NOFAIL 0x8000u +#define ___GFP_NORETRY 0x10000u +#define ___GFP_MEMALLOC 0x20000u +#define ___GFP_COMP 0x40000u +#define ___GFP_NOMEMALLOC 0x80000u +#define ___GFP_HARDWALL 0x100000u +#define ___GFP_THISNODE 0x200000u +#define ___GFP_ACCOUNT 0x400000u +#define ___GFP_ZEROTAGS 0x800000u +#ifdef CONFIG_KASAN_HW_TAGS +#define ___GFP_SKIP_ZERO 0x1000000u +#define ___GFP_SKIP_KASAN_UNPOISON 0x2000000u +#define ___GFP_SKIP_KASAN_POISON 0x4000000u +#else +#define ___GFP_SKIP_ZERO 0 +#define ___GFP_SKIP_KASAN_UNPOISON 0 +#define ___GFP_SKIP_KASAN_POISON 0 +#endif +#ifdef CONFIG_LOCKDEP +#define ___GFP_NOLOCKDEP 0x8000000u +#else +#define ___GFP_NOLOCKDEP 0 +#endif +/* If the above are modified, __GFP_BITS_SHIFT may need updating */ + +/* + * Physical address zone modifiers (see linux/mmzone.h - low four bits) + * + * Do not put any conditional on these. If necessary modify the definitions + * without the underscores and use them consistently. The definitions here may + * be used in bit comparisons. + */ +#define __GFP_DMA ((__force gfp_t)___GFP_DMA) +#define __GFP_HIGHMEM ((__force gfp_t)___GFP_HIGHMEM) +#define __GFP_DMA32 ((__force gfp_t)___GFP_DMA32) +#define __GFP_MOVABLE ((__force gfp_t)___GFP_MOVABLE) /* ZONE_MOVABLE allowed */ +#define GFP_ZONEMASK (__GFP_DMA|__GFP_HIGHMEM|__GFP_DMA32|__GFP_MOVABLE) + +/** + * DOC: Page mobility and placement hints + * + * Page mobility and placement hints + * --------------------------------- + * + * These flags provide hints about how mobile the page is. Pages with similar + * mobility are placed within the same pageblocks to minimise problems due + * to external fragmentation. + * + * %__GFP_MOVABLE (also a zone modifier) indicates that the page can be + * moved by page migration during memory compaction or can be reclaimed. + * + * %__GFP_RECLAIMABLE is used for slab allocations that specify + * SLAB_RECLAIM_ACCOUNT and whose pages can be freed via shrinkers. + * + * %__GFP_WRITE indicates the caller intends to dirty the page. Where possible, + * these pages will be spread between local zones to avoid all the dirty + * pages being in one zone (fair zone allocation policy). + * + * %__GFP_HARDWALL enforces the cpuset memory allocation policy. + * + * %__GFP_THISNODE forces the allocation to be satisfied from the requested + * node with no fallbacks or placement policy enforcements. + * + * %__GFP_ACCOUNT causes the allocation to be accounted to kmemcg. + */ +#define __GFP_RECLAIMABLE ((__force gfp_t)___GFP_RECLAIMABLE) +#define __GFP_WRITE ((__force gfp_t)___GFP_WRITE) +#define __GFP_HARDWALL ((__force gfp_t)___GFP_HARDWALL) +#define __GFP_THISNODE ((__force gfp_t)___GFP_THISNODE) +#define __GFP_ACCOUNT ((__force gfp_t)___GFP_ACCOUNT) + +/** + * DOC: Watermark modifiers + * + * Watermark modifiers -- controls access to emergency reserves + * ------------------------------------------------------------ + * + * %__GFP_HIGH indicates that the caller is high-priority and that granting + * the request is necessary before the system can make forward progress. + * For example, creating an IO context to clean pages. + * + * %__GFP_ATOMIC indicates that the caller cannot reclaim or sleep and is + * high priority. Users are typically interrupt handlers. This may be + * used in conjunction with %__GFP_HIGH + * + * %__GFP_MEMALLOC allows access to all memory. This should only be used when + * the caller guarantees the allocation will allow more memory to be freed + * very shortly e.g. process exiting or swapping. Users either should + * be the MM or co-ordinating closely with the VM (e.g. swap over NFS). + * Users of this flag have to be extremely careful to not deplete the reserve + * completely and implement a throttling mechanism which controls the + * consumption of the reserve based on the amount of freed memory. + * Usage of a pre-allocated pool (e.g. mempool) should be always considered + * before using this flag. + * + * %__GFP_NOMEMALLOC is used to explicitly forbid access to emergency reserves. + * This takes precedence over the %__GFP_MEMALLOC flag if both are set. + */ +#define __GFP_ATOMIC ((__force gfp_t)___GFP_ATOMIC) +#define __GFP_HIGH ((__force gfp_t)___GFP_HIGH) +#define __GFP_MEMALLOC ((__force gfp_t)___GFP_MEMALLOC) +#define __GFP_NOMEMALLOC ((__force gfp_t)___GFP_NOMEMALLOC) + +/** + * DOC: Reclaim modifiers + * + * Reclaim modifiers + * ----------------- + * Please note that all the following flags are only applicable to sleepable + * allocations (e.g. %GFP_NOWAIT and %GFP_ATOMIC will ignore them). + * + * %__GFP_IO can start physical IO. + * + * %__GFP_FS can call down to the low-level FS. Clearing the flag avoids the + * allocator recursing into the filesystem which might already be holding + * locks. + * + * %__GFP_DIRECT_RECLAIM indicates that the caller may enter direct reclaim. + * This flag can be cleared to avoid unnecessary delays when a fallback + * option is available. + * + * %__GFP_KSWAPD_RECLAIM indicates that the caller wants to wake kswapd when + * the low watermark is reached and have it reclaim pages until the high + * watermark is reached. A caller may wish to clear this flag when fallback + * options are available and the reclaim is likely to disrupt the system. The + * canonical example is THP allocation where a fallback is cheap but + * reclaim/compaction may cause indirect stalls. + * + * %__GFP_RECLAIM is shorthand to allow/forbid both direct and kswapd reclaim. + * + * The default allocator behavior depends on the request size. We have a concept + * of so called costly allocations (with order > %PAGE_ALLOC_COSTLY_ORDER). + * !costly allocations are too essential to fail so they are implicitly + * non-failing by default (with some exceptions like OOM victims might fail so + * the caller still has to check for failures) while costly requests try to be + * not disruptive and back off even without invoking the OOM killer. + * The following three modifiers might be used to override some of these + * implicit rules + * + * %__GFP_NORETRY: The VM implementation will try only very lightweight + * memory direct reclaim to get some memory under memory pressure (thus + * it can sleep). It will avoid disruptive actions like OOM killer. The + * caller must handle the failure which is quite likely to happen under + * heavy memory pressure. The flag is suitable when failure can easily be + * handled at small cost, such as reduced throughput + * + * %__GFP_RETRY_MAYFAIL: The VM implementation will retry memory reclaim + * procedures that have previously failed if there is some indication + * that progress has been made else where. It can wait for other + * tasks to attempt high level approaches to freeing memory such as + * compaction (which removes fragmentation) and page-out. + * There is still a definite limit to the number of retries, but it is + * a larger limit than with %__GFP_NORETRY. + * Allocations with this flag may fail, but only when there is + * genuinely little unused memory. While these allocations do not + * directly trigger the OOM killer, their failure indicates that + * the system is likely to need to use the OOM killer soon. The + * caller must handle failure, but can reasonably do so by failing + * a higher-level request, or completing it only in a much less + * efficient manner. + * If the allocation does fail, and the caller is in a position to + * free some non-essential memory, doing so could benefit the system + * as a whole. + * + * %__GFP_NOFAIL: The VM implementation _must_ retry infinitely: the caller + * cannot handle allocation failures. The allocation could block + * indefinitely but will never return with failure. Testing for + * failure is pointless. + * New users should be evaluated carefully (and the flag should be + * used only when there is no reasonable failure policy) but it is + * definitely preferable to use the flag rather than opencode endless + * loop around allocator. + * Using this flag for costly allocations is _highly_ discouraged. + */ +#define __GFP_IO ((__force gfp_t)___GFP_IO) +#define __GFP_FS ((__force gfp_t)___GFP_FS) +#define __GFP_DIRECT_RECLAIM ((__force gfp_t)___GFP_DIRECT_RECLAIM) /* Caller can reclaim */ +#define __GFP_KSWAPD_RECLAIM ((__force gfp_t)___GFP_KSWAPD_RECLAIM) /* kswapd can wake */ +#define __GFP_RECLAIM ((__force gfp_t)(___GFP_DIRECT_RECLAIM|___GFP_KSWAPD_RECLAIM)) +#define __GFP_RETRY_MAYFAIL ((__force gfp_t)___GFP_RETRY_MAYFAIL) +#define __GFP_NOFAIL ((__force gfp_t)___GFP_NOFAIL) +#define __GFP_NORETRY ((__force gfp_t)___GFP_NORETRY) + +/** + * DOC: Action modifiers + * + * Action modifiers + * ---------------- + * + * %__GFP_NOWARN suppresses allocation failure reports. + * + * %__GFP_COMP address compound page metadata. + * + * %__GFP_ZERO returns a zeroed page on success. + * + * %__GFP_ZEROTAGS zeroes memory tags at allocation time if the memory itself + * is being zeroed (either via __GFP_ZERO or via init_on_alloc, provided that + * __GFP_SKIP_ZERO is not set). This flag is intended for optimization: setting + * memory tags at the same time as zeroing memory has minimal additional + * performace impact. + * + * %__GFP_SKIP_KASAN_UNPOISON makes KASAN skip unpoisoning on page allocation. + * Only effective in HW_TAGS mode. + * + * %__GFP_SKIP_KASAN_POISON makes KASAN skip poisoning on page deallocation. + * Typically, used for userspace pages. Only effective in HW_TAGS mode. + */ +#define __GFP_NOWARN ((__force gfp_t)___GFP_NOWARN) +#define __GFP_COMP ((__force gfp_t)___GFP_COMP) +#define __GFP_ZERO ((__force gfp_t)___GFP_ZERO) +#define __GFP_ZEROTAGS ((__force gfp_t)___GFP_ZEROTAGS) +#define __GFP_SKIP_ZERO ((__force gfp_t)___GFP_SKIP_ZERO) +#define __GFP_SKIP_KASAN_UNPOISON ((__force gfp_t)___GFP_SKIP_KASAN_UNPOISON) +#define __GFP_SKIP_KASAN_POISON ((__force gfp_t)___GFP_SKIP_KASAN_POISON) + +/* Disable lockdep for GFP context tracking */ +#define __GFP_NOLOCKDEP ((__force gfp_t)___GFP_NOLOCKDEP) + +/* Room for N __GFP_FOO bits */ +#define __GFP_BITS_SHIFT (27 + IS_ENABLED(CONFIG_LOCKDEP)) +#define __GFP_BITS_MASK ((__force gfp_t)((1 << __GFP_BITS_SHIFT) - 1)) + +/** + * DOC: Useful GFP flag combinations + * + * Useful GFP flag combinations + * ---------------------------- + * + * Useful GFP flag combinations that are commonly used. It is recommended + * that subsystems start with one of these combinations and then set/clear + * %__GFP_FOO flags as necessary. + * + * %GFP_ATOMIC users can not sleep and need the allocation to succeed. A lower + * watermark is applied to allow access to "atomic reserves". + * The current implementation doesn't support NMI and few other strict + * non-preemptive contexts (e.g. raw_spin_lock). The same applies to %GFP_NOWAIT. + * + * %GFP_KERNEL is typical for kernel-internal allocations. The caller requires + * %ZONE_NORMAL or a lower zone for direct access but can direct reclaim. + * + * %GFP_KERNEL_ACCOUNT is the same as GFP_KERNEL, except the allocation is + * accounted to kmemcg. + * + * %GFP_NOWAIT is for kernel allocations that should not stall for direct + * reclaim, start physical IO or use any filesystem callback. + * + * %GFP_NOIO will use direct reclaim to discard clean pages or slab pages + * that do not require the starting of any physical IO. + * Please try to avoid using this flag directly and instead use + * memalloc_noio_{save,restore} to mark the whole scope which cannot + * perform any IO with a short explanation why. All allocation requests + * will inherit GFP_NOIO implicitly. + * + * %GFP_NOFS will use direct reclaim but will not use any filesystem interfaces. + * Please try to avoid using this flag directly and instead use + * memalloc_nofs_{save,restore} to mark the whole scope which cannot/shouldn't + * recurse into the FS layer with a short explanation why. All allocation + * requests will inherit GFP_NOFS implicitly. + * + * %GFP_USER is for userspace allocations that also need to be directly + * accessibly by the kernel or hardware. It is typically used by hardware + * for buffers that are mapped to userspace (e.g. graphics) that hardware + * still must DMA to. cpuset limits are enforced for these allocations. + * + * %GFP_DMA exists for historical reasons and should be avoided where possible. + * The flags indicates that the caller requires that the lowest zone be + * used (%ZONE_DMA or 16M on x86-64). Ideally, this would be removed but + * it would require careful auditing as some users really require it and + * others use the flag to avoid lowmem reserves in %ZONE_DMA and treat the + * lowest zone as a type of emergency reserve. + * + * %GFP_DMA32 is similar to %GFP_DMA except that the caller requires a 32-bit + * address. Note that kmalloc(..., GFP_DMA32) does not return DMA32 memory + * because the DMA32 kmalloc cache array is not implemented. + * (Reason: there is no such user in kernel). + * + * %GFP_HIGHUSER is for userspace allocations that may be mapped to userspace, + * do not need to be directly accessible by the kernel but that cannot + * move once in use. An example may be a hardware allocation that maps + * data directly into userspace but has no addressing limitations. + * + * %GFP_HIGHUSER_MOVABLE is for userspace allocations that the kernel does not + * need direct access to but can use kmap() when access is required. They + * are expected to be movable via page reclaim or page migration. Typically, + * pages on the LRU would also be allocated with %GFP_HIGHUSER_MOVABLE. + * + * %GFP_TRANSHUGE and %GFP_TRANSHUGE_LIGHT are used for THP allocations. They + * are compound allocations that will generally fail quickly if memory is not + * available and will not wake kswapd/kcompactd on failure. The _LIGHT + * version does not attempt reclaim/compaction at all and is by default used + * in page fault path, while the non-light is used by khugepaged. + */ +#define GFP_ATOMIC (__GFP_HIGH|__GFP_ATOMIC|__GFP_KSWAPD_RECLAIM) +#define GFP_KERNEL (__GFP_RECLAIM | __GFP_IO | __GFP_FS) +#define GFP_KERNEL_ACCOUNT (GFP_KERNEL | __GFP_ACCOUNT) +#define GFP_NOWAIT (__GFP_KSWAPD_RECLAIM) +#define GFP_NOIO (__GFP_RECLAIM) +#define GFP_NOFS (__GFP_RECLAIM | __GFP_IO) +#define GFP_USER (__GFP_RECLAIM | __GFP_IO | __GFP_FS | __GFP_HARDWALL) +#define GFP_DMA __GFP_DMA +#define GFP_DMA32 __GFP_DMA32 +#define GFP_HIGHUSER (GFP_USER | __GFP_HIGHMEM) +#define GFP_HIGHUSER_MOVABLE (GFP_HIGHUSER | __GFP_MOVABLE | \ + __GFP_SKIP_KASAN_POISON) +#define GFP_TRANSHUGE_LIGHT ((GFP_HIGHUSER_MOVABLE | __GFP_COMP | \ + __GFP_NOMEMALLOC | __GFP_NOWARN) & ~__GFP_RECLAIM) +#define GFP_TRANSHUGE (GFP_TRANSHUGE_LIGHT | __GFP_DIRECT_RECLAIM) + +#endif /* __LINUX_GFP_TYPES_H */ From 7343f2b0db4961d9f386e685e651c663dc763d0c Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Wed, 6 Jul 2022 08:52:24 -0700 Subject: [PATCH 22/26] headers/deps: mm: align MANITAINERS and Docs with new gfp.h structure After moving gfp types out of gfp.h, we have to align MAINTAINERS and Docs, to avoid warnings like this: >> include/linux/gfp.h:1: warning: 'Page mobility and placement hints' not found >> include/linux/gfp.h:1: warning: 'Watermark modifiers' not found >> include/linux/gfp.h:1: warning: 'Reclaim modifiers' not found >> include/linux/gfp.h:1: warning: 'Useful GFP flag combinations' not found Signed-off-by: Yury Norov --- Documentation/core-api/mm-api.rst | 8 ++++---- MAINTAINERS | 1 + 2 files changed, 5 insertions(+), 4 deletions(-) diff --git a/Documentation/core-api/mm-api.rst b/Documentation/core-api/mm-api.rst index f5b2f92822c8..1ebcc6c3fafe 100644 --- a/Documentation/core-api/mm-api.rst +++ b/Documentation/core-api/mm-api.rst @@ -22,16 +22,16 @@ Memory Allocation Controls .. kernel-doc:: include/linux/gfp.h :internal: -.. kernel-doc:: include/linux/gfp.h +.. kernel-doc:: include/linux/gfp_types.h :doc: Page mobility and placement hints -.. kernel-doc:: include/linux/gfp.h +.. kernel-doc:: include/linux/gfp_types.h :doc: Watermark modifiers -.. kernel-doc:: include/linux/gfp.h +.. kernel-doc:: include/linux/gfp_types.h :doc: Reclaim modifiers -.. kernel-doc:: include/linux/gfp.h +.. kernel-doc:: include/linux/gfp_types.h :doc: Useful GFP flag combinations The Slab Cache diff --git a/MAINTAINERS b/MAINTAINERS index 3cf9842d9233..7c0b8f28aa25 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -12850,6 +12850,7 @@ T: quilt https://ozlabs.org/~akpm/mmotm/ T: quilt https://ozlabs.org/~akpm/mmots/ T: git git://github.com/hnaz/linux-mm.git F: include/linux/gfp.h +F: include/linux/gfp_types.h F: include/linux/memory_hotplug.h F: include/linux/mm.h F: include/linux/mmzone.h From f0dd891dd5a1d6dc6c9d486333aac4f433f17d17 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Fri, 1 Jul 2022 05:54:30 -0700 Subject: [PATCH 23/26] lib/cpumask: move some one-line wrappers to header file After moving gfp flags to a separate header, it's possible to move some cpumask allocators into headers, and avoid creating real functions. Signed-off-by: Yury Norov --- include/linux/cpumask.h | 34 +++++++++++++++++++++++++++++++--- lib/cpumask.c | 28 ---------------------------- 2 files changed, 31 insertions(+), 31 deletions(-) diff --git a/include/linux/cpumask.h b/include/linux/cpumask.h index ea3de2c2c180..80627362c774 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -12,6 +12,8 @@ #include #include #include +#include +#include /* Don't assign or return these: may not be this big! */ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; @@ -794,9 +796,35 @@ typedef struct cpumask *cpumask_var_t; #define __cpumask_var_read_mostly __read_mostly bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); -bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node); -bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags); + +static inline +bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) +{ + return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); +} + +/** + * alloc_cpumask_var - allocate a struct cpumask + * @mask: pointer to cpumask_var_t where the cpumask is returned + * @flags: GFP_ flags + * + * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is + * a nop returning a constant 1 (in ). + * + * See alloc_cpumask_var_node. + */ +static inline +bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +{ + return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); +} + +static inline +bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) +{ + return alloc_cpumask_var(mask, flags | __GFP_ZERO); +} + void alloc_bootmem_cpumask_var(cpumask_var_t *mask); void free_cpumask_var(cpumask_var_t mask); void free_bootmem_cpumask_var(cpumask_var_t mask); diff --git a/lib/cpumask.c b/lib/cpumask.c index cb7262ff8633..f0ae119be8c4 100644 --- a/lib/cpumask.c +++ b/lib/cpumask.c @@ -70,34 +70,6 @@ bool alloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) } EXPORT_SYMBOL(alloc_cpumask_var_node); -bool zalloc_cpumask_var_node(cpumask_var_t *mask, gfp_t flags, int node) -{ - return alloc_cpumask_var_node(mask, flags | __GFP_ZERO, node); -} -EXPORT_SYMBOL(zalloc_cpumask_var_node); - -/** - * alloc_cpumask_var - allocate a struct cpumask - * @mask: pointer to cpumask_var_t where the cpumask is returned - * @flags: GFP_ flags - * - * Only defined when CONFIG_CPUMASK_OFFSTACK=y, otherwise is - * a nop returning a constant 1 (in ). - * - * See alloc_cpumask_var_node. - */ -bool alloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) -{ - return alloc_cpumask_var_node(mask, flags, NUMA_NO_NODE); -} -EXPORT_SYMBOL(alloc_cpumask_var); - -bool zalloc_cpumask_var(cpumask_var_t *mask, gfp_t flags) -{ - return alloc_cpumask_var(mask, flags | __GFP_ZERO); -} -EXPORT_SYMBOL(zalloc_cpumask_var); - /** * alloc_bootmem_cpumask_var - allocate a struct cpumask from the bootmem arena. * @mask: pointer to cpumask_var_t where the cpumask is returned From 3a2ba42cbd0b669ce3837ba400905f93dd06c79f Mon Sep 17 00:00:00 2001 From: Alexander Lobakin Date: Fri, 15 Jul 2022 17:15:36 +0200 Subject: [PATCH 24/26] x86/olpc: fix 'logical not is only applied to the left hand side' The bitops compile-time optimization series revealed one more problem in olpc-xo1-sci.c:send_ebook_state(), resulted in GCC warnings: arch/x86/platform/olpc/olpc-xo1-sci.c: In function 'send_ebook_state': arch/x86/platform/olpc/olpc-xo1-sci.c:83:63: warning: logical not is only applied to the left hand side of comparison [-Wlogical-not-parentheses] 83 | if (!!test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == state) | ^~ arch/x86/platform/olpc/olpc-xo1-sci.c:83:13: note: add parentheses around left hand side expression to silence this warning Despite this code working as intended, this redundant double negation of boolean value, together with comparing to `char` with no explicit conversion to bool, makes compilers think the author made some unintentional logical mistakes here. Make it the other way around and negate the char instead to silence the warnings. Fixes: d2aa37411b8e ("x86/olpc/xo1/sci: Produce wakeup events for buttons and switches") Cc: stable@vger.kernel.org # 3.5+ Reported-by: Guenter Roeck Reported-by: kernel test robot Reviewed-and-tested-by: Guenter Roeck Signed-off-by: Alexander Lobakin Signed-off-by: Yury Norov --- arch/x86/platform/olpc/olpc-xo1-sci.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/arch/x86/platform/olpc/olpc-xo1-sci.c b/arch/x86/platform/olpc/olpc-xo1-sci.c index f03a6883dcc6..89f25af4b3c3 100644 --- a/arch/x86/platform/olpc/olpc-xo1-sci.c +++ b/arch/x86/platform/olpc/olpc-xo1-sci.c @@ -80,7 +80,7 @@ static void send_ebook_state(void) return; } - if (!!test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == state) + if (test_bit(SW_TABLET_MODE, ebook_switch_idev->sw) == !!state) return; /* Nothing new to report. */ input_report_switch(ebook_switch_idev, SW_TABLET_MODE, state); From 3e731203153de1c06a8b7a4f15061e9051c09a6f Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Sat, 23 Jul 2022 14:45:36 -0700 Subject: [PATCH 25/26] powerpc: drop dependency on in archrandom.h archrandom.h includes to refer ppc_md. This causes circular header dependency, if generic nodemask.h includes random.h: In file included from include/linux/cred.h:16, from include/linux/seq_file.h:13, from arch/powerpc/include/asm/machdep.h:6, from arch/powerpc/include/asm/archrandom.h:5, from include/linux/random.h:109, from include/linux/nodemask.h:97, from include/linux/list_lru.h:12, from include/linux/fs.h:13, from include/linux/compat.h:17, from arch/powerpc/kernel/asm-offsets.c:12: include/linux/sched.h:1203:9: error: unknown type name 'nodemask_t' 1203 | nodemask_t mems_allowed; | ^~~~~~~~~~ Fix it by removing dependency from archrandom.h Now as arch_get_random_seed_long() moved to c-file, and not exported, it's not available for modules. As Michael Ellerman says: I think we actually don't need it exported to modules, I think it's a private detail of the RNG <-> architecture interface, not something that modules should be calling. CC: Andy Shevchenko CC: Benjamin Herrenschmidt CC: Michael Ellerman CC: Paul Mackerras CC: Rasmus Villemoes CC: Stephen Rothwell CC: linuxppc-dev@lists.ozlabs.org Suggested-by: Michael Ellerman (for non-exporting) Acked-by: Michael Ellerman Acked-by: Michael Ellerman Signed-off-by: Yury Norov --- arch/powerpc/include/asm/archrandom.h | 9 +-------- arch/powerpc/kernel/setup-common.c | 12 ++++++++++++ 2 files changed, 13 insertions(+), 8 deletions(-) diff --git a/arch/powerpc/include/asm/archrandom.h b/arch/powerpc/include/asm/archrandom.h index 9a53e29680f4..21def59ef1a6 100644 --- a/arch/powerpc/include/asm/archrandom.h +++ b/arch/powerpc/include/asm/archrandom.h @@ -4,7 +4,7 @@ #ifdef CONFIG_ARCH_RANDOM -#include +bool __must_check arch_get_random_seed_long(unsigned long *v); static inline bool __must_check arch_get_random_long(unsigned long *v) { @@ -16,13 +16,6 @@ static inline bool __must_check arch_get_random_int(unsigned int *v) return false; } -static inline bool __must_check arch_get_random_seed_long(unsigned long *v) -{ - if (ppc_md.get_random_seed) - return ppc_md.get_random_seed(v); - - return false; -} static inline bool __must_check arch_get_random_seed_int(unsigned int *v) { diff --git a/arch/powerpc/kernel/setup-common.c b/arch/powerpc/kernel/setup-common.c index eb0077b302e2..5175726c703d 100644 --- a/arch/powerpc/kernel/setup-common.c +++ b/arch/powerpc/kernel/setup-common.c @@ -171,6 +171,18 @@ EXPORT_SYMBOL_GPL(machine_power_off); void (*pm_power_off)(void); EXPORT_SYMBOL_GPL(pm_power_off); +#ifdef CONFIG_ARCH_RANDOM +bool __must_check arch_get_random_seed_long(unsigned long *v) +{ + if (ppc_md.get_random_seed) + return ppc_md.get_random_seed(v); + + return false; +} +EXPORT_SYMBOL(arch_get_random_seed_long); + +#endif + void machine_halt(void) { machine_shutdown(); From 36d4b36b69590fed99356a4426c940a253a93800 Mon Sep 17 00:00:00 2001 From: Yury Norov Date: Mon, 25 Jul 2022 09:39:17 -0700 Subject: [PATCH 26/26] lib/nodemask: inline next_node_in() and node_random() The functions are pretty thin wrappers around find_bit engine, and keeping them in c-file prevents compiler from small_const_nbits() optimization, which must take place for all systems with MAX_NUMNODES less than BITS_PER_LONG (default is 16 for me). Moving them to header file doesn't blow up the kernel size: add/remove: 1/2 grow/shrink: 9/5 up/down: 968/-88 (880) CC: Andy Shevchenko CC: Benjamin Herrenschmidt CC: Michael Ellerman CC: Paul Mackerras CC: Rasmus Villemoes CC: Stephen Rothwell CC: linuxppc-dev@lists.ozlabs.org Signed-off-by: Yury Norov --- MAINTAINERS | 1 - include/linux/nodemask.h | 26 ++++++++++++++++++++------ lib/Makefile | 2 +- lib/nodemask.c | 8 -------- 4 files changed, 21 insertions(+), 16 deletions(-) diff --git a/MAINTAINERS b/MAINTAINERS index 7c0b8f28aa25..19c8d0ef1177 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -3540,7 +3540,6 @@ F: lib/bitmap.c F: lib/cpumask.c F: lib/find_bit.c F: lib/find_bit_benchmark.c -F: lib/nodemask.c F: lib/test_bitmap.c F: tools/include/linux/bitmap.h F: tools/include/linux/find.h diff --git a/include/linux/nodemask.h b/include/linux/nodemask.h index 0f233b76c9ce..4b71a96190a8 100644 --- a/include/linux/nodemask.h +++ b/include/linux/nodemask.h @@ -94,6 +94,7 @@ #include #include #include +#include typedef struct { DECLARE_BITMAP(bits, MAX_NUMNODES); } nodemask_t; extern nodemask_t _unused_nodemask_arg_; @@ -276,7 +277,14 @@ static inline unsigned int __next_node(int n, const nodemask_t *srcp) * the first node in src if needed. Returns MAX_NUMNODES if src is empty. */ #define next_node_in(n, src) __next_node_in((n), &(src)) -unsigned int __next_node_in(int node, const nodemask_t *srcp); +static inline unsigned int __next_node_in(int node, const nodemask_t *srcp) +{ + unsigned int ret = __next_node(node, srcp); + + if (ret == MAX_NUMNODES) + ret = __first_node(srcp); + return ret; +} static inline void init_nodemask_of_node(nodemask_t *mask, int node) { @@ -493,14 +501,20 @@ static inline int num_node_state(enum node_states state) #endif -#if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) -extern int node_random(const nodemask_t *maskp); -#else -static inline int node_random(const nodemask_t *mask) +static inline int node_random(const nodemask_t *maskp) { +#if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) + int w, bit = NUMA_NO_NODE; + + w = nodes_weight(*maskp); + if (w) + bit = bitmap_ord_to_pos(maskp->bits, + get_random_int() % w, MAX_NUMNODES); + return bit; +#else return 0; -} #endif +} #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] diff --git a/lib/Makefile b/lib/Makefile index f99bf61f8bbc..731cea0342d1 100644 --- a/lib/Makefile +++ b/lib/Makefile @@ -33,7 +33,7 @@ lib-y := ctype.o string.o vsprintf.o cmdline.o \ flex_proportions.o ratelimit.o show_mem.o \ is_single_threaded.o plist.o decompress.o kobject_uevent.o \ earlycpio.o seq_buf.o siphash.o dec_and_lock.o \ - nmi_backtrace.o nodemask.o win_minmax.o memcat_p.o \ + nmi_backtrace.o win_minmax.o memcat_p.o \ buildid.o lib-$(CONFIG_PRINTK) += dump_stack.o diff --git a/lib/nodemask.c b/lib/nodemask.c index e22647f5181b..b8a433d16b51 100644 --- a/lib/nodemask.c +++ b/lib/nodemask.c @@ -3,14 +3,6 @@ #include #include -unsigned int __next_node_in(int node, const nodemask_t *srcp) -{ - unsigned int ret = __next_node(node, srcp); - - if (ret == MAX_NUMNODES) - ret = __first_node(srcp); - return ret; -} EXPORT_SYMBOL(__next_node_in); #ifdef CONFIG_NUMA