diff options
Diffstat (limited to 'include')
| -rw-r--r-- | include/asm-generic/bitops/generic-non-atomic.h | 161 | ||||
| -rw-r--r-- | include/asm-generic/bitops/instrumented-non-atomic.h | 35 | ||||
| -rw-r--r-- | include/asm-generic/bitops/non-atomic.h | 121 | ||||
| -rw-r--r-- | include/asm-generic/bitops/non-instrumented-non-atomic.h | 16 | ||||
| -rw-r--r-- | include/linux/bitmap.h | 37 | ||||
| -rw-r--r-- | include/linux/bitops.h | 50 | ||||
| -rw-r--r-- | include/linux/cpumask.h | 122 | ||||
| -rw-r--r-- | include/linux/gfp.h | 348 | ||||
| -rw-r--r-- | include/linux/gfp_types.h | 348 | ||||
| -rw-r--r-- | include/linux/nodemask.h | 24 |
10 files changed, 753 insertions, 509 deletions
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..3d5ebd24652b --- /dev/null +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -0,0 +1,161 @@ +/* SPDX-License-Identifier: GPL-2.0-only */ + +#ifndef __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H +#define __ASM_GENERIC_BITOPS_GENERIC_NON_ATOMIC_H + +#include <linux/bits.h> + +#ifndef _LINUX_BITOPS_H +#error only <linux/bitops.h> 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 long 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 long 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 long 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 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); + 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 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); + unsigned long old = *p; + + *p = old & ~mask; + return (old & mask) != 0; +} + +/* WARNING: non atomic and it can be reordered! */ +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); + 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 bool +generic_test_bit(unsigned long 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))); +} + +/* + * 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/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 7ab1ecc37782..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 <linux/instrumented.h> /** - * __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 * @@ -22,14 +22,15 @@ * 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); } /** - * __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 * @@ -37,14 +38,15 @@ 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); } /** - * __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 * @@ -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); @@ -83,53 +86,57 @@ 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 * * 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); } /** - * __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 * * 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); } /** - * __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 * * 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); } /** - * 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(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 078cc68be2f1..5c37ced343ae 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -2,121 +2,18 @@ #ifndef _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ #define _ASM_GENERIC_BITOPS_NON_ATOMIC_H_ -#include <asm/types.h> +#include <asm-generic/bitops/generic-non-atomic.h> -/** - * 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); +#define arch___set_bit generic___set_bit +#define arch___clear_bit generic___clear_bit +#define arch___change_bit generic___change_bit - *p |= mask; -} -#define __set_bit arch___set_bit +#define arch___test_and_set_bit generic___test_and_set_bit +#define arch___test_and_clear_bit generic___test_and_clear_bit +#define arch___test_and_change_bit generic___test_and_change_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); +#define arch_test_bit generic_test_bit - *p &= ~mask; -} -#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 __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 __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 __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 __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 test_bit arch_test_bit +#include <asm-generic/bitops/non-instrumented-non-atomic.h> #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..bdb9b1ffaee9 --- /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/bitmap.h b/include/linux/bitmap.h index 2e6cd5681040..f65410a49fda 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 * @@ -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, @@ -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 int __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); @@ -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); } /* @@ -303,7 +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)) @@ -329,7 +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)) @@ -419,7 +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 int bitmap_weight(const unsigned long *src, unsigned int nbits) { if (small_const_nbits(nbits)) return hweight_long(*src & BITMAP_LAST_WORD_MASK(nbits)); @@ -431,6 +444,8 @@ 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 +460,8 @@ 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) && diff --git a/include/linux/bitops.h b/include/linux/bitops.h index 7aaed501f768..cf9bf65039f2 100644 --- a/include/linux/bitops.h +++ b/include/linux/bitops.h @@ -27,11 +27,61 @@ 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 <asm-generic/bitops/generic-non-atomic.h> + +/* + * 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) \ + ((__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) +#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 */ #include <asm/bitops.h> +/* 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); +__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/include/linux/cpumask.h b/include/linux/cpumask.h index 707387323862..0d435d0edbcb 100644 --- a/include/linux/cpumask.h +++ b/include/linux/cpumask.h @@ -12,6 +12,8 @@ #include <linux/bitmap.h> #include <linux/atomic.h> #include <linux/bug.h> +#include <linux/gfp_types.h> +#include <linux/numa.h> /* Don't assign or return these: may not be this big! */ typedef struct cpumask { DECLARE_BITMAP(bits, NR_CPUS); } cpumask_t; @@ -162,7 +164,21 @@ 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 @@ -179,9 +195,6 @@ 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); - #if NR_CPUS == 1 /* Uniprocessor: there is only one valid CPU */ static inline unsigned int cpumask_local_spread(unsigned int i, int node) @@ -200,12 +213,31 @@ static inline int cpumask_any_distribute(const struct cpumask *srcp) } #else 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); #endif /* NR_CPUS */ /** + * 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); +} + +/** * for_each_cpu - iterate over every cpu in a mask * @cpu: the (optionally unsigned) integer iterator * @mask: the cpumask pointer @@ -229,7 +261,7 @@ int cpumask_any_distribute(const struct cpumask *srcp); (cpu) = cpumask_next_zero((cpu), (mask)), \ (cpu) < nr_cpu_ids;) -int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool wrap); +unsigned int __pure 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 @@ -265,6 +297,26 @@ int __pure cpumask_next_wrap(int n, const struct cpumask *mask, int start, bool (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; +} + #define CPU_BITS_NONE \ { \ [0 ... BITS_TO_LONGS(NR_CPUS)-1] = 0UL \ @@ -311,9 +363,9 @@ 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))); } @@ -323,11 +375,11 @@ 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)); } @@ -337,11 +389,11 @@ 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)); } @@ -370,9 +422,9 @@ 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) { @@ -413,9 +465,9 @@ 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) { @@ -478,9 +530,9 @@ 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), @@ -682,9 +734,35 @@ 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 <linux/cpumask.h>). + * + * 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/include/linux/gfp.h b/include/linux/gfp.h index 0ace7759acd2..f314be58fa77 100644 --- a/include/linux/gfp.h +++ b/include/linux/gfp.h @@ -2,357 +2,13 @@ #ifndef __LINUX_GFP_H #define __LINUX_GFP_H -#include <linux/mmdebug.h> +#include <linux/gfp_types.h> + #include <linux/mmzone.h> -#include <linux/stddef.h> -#include <linux/linkage.h> #include <linux/topology.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 - 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 | __GFP_SKIP_KASAN_UNPOISON) -#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..d88c46ca82e1 --- /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 | __GFP_SKIP_KASAN_UNPOISON) +#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 */ 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 <linux/bitmap.h> #include <linux/minmax.h> #include <linux/numa.h> +#include <linux/random.h> 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 +static inline int node_random(const nodemask_t *maskp) +{ #if defined(CONFIG_NUMA) && (MAX_NUMNODES > 1) -extern int node_random(const nodemask_t *maskp); + 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 -static inline int node_random(const nodemask_t *mask) -{ return 0; -} #endif +} #define node_online_map node_states[N_ONLINE] #define node_possible_map node_states[N_POSSIBLE] |