diff options
Diffstat (limited to 'include/asm-generic')
44 files changed, 1118 insertions, 904 deletions
diff --git a/include/asm-generic/Kbuild b/include/asm-generic/Kbuild index 302506bbc2a4..941be574bbe0 100644 --- a/include/asm-generic/Kbuild +++ b/include/asm-generic/Kbuild @@ -5,6 +5,7 @@ # asm headers from the host architecutre.) mandatory-y += atomic.h +mandatory-y += archrandom.h mandatory-y += barrier.h mandatory-y += bitops.h mandatory-y += bug.h diff --git a/include/asm-generic/access_ok.h b/include/asm-generic/access_ok.h new file mode 100644 index 000000000000..2866ae61b1cd --- /dev/null +++ b/include/asm-generic/access_ok.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_ACCESS_OK_H__ +#define __ASM_GENERIC_ACCESS_OK_H__ + +/* + * Checking whether a pointer is valid for user space access. + * These definitions work on most architectures, but overrides can + * be used where necessary. + */ + +/* + * architectures with compat tasks have a variable TASK_SIZE and should + * override this to a constant. + */ +#ifndef TASK_SIZE_MAX +#define TASK_SIZE_MAX TASK_SIZE +#endif + +#ifndef __access_ok +/* + * 'size' is a compile-time constant for most callers, so optimize for + * this case to turn the check into a single comparison against a constant + * limit and catch all possible overflows. + * On architectures with separate user address space (m68k, s390, parisc, + * sparc64) or those without an MMU, this should always return true. + * + * This version was originally contributed by Jonas Bonn for the + * OpenRISC architecture, and was found to be the most efficient + * for constant 'size' and 'limit' values. + */ +static inline int __access_ok(const void __user *ptr, unsigned long size) +{ + unsigned long limit = TASK_SIZE_MAX; + unsigned long addr = (unsigned long)ptr; + + if (IS_ENABLED(CONFIG_ALTERNATE_USER_ADDRESS_SPACE) || + !IS_ENABLED(CONFIG_MMU)) + return true; + + return (size <= limit) && (addr <= (limit - size)); +} +#endif + +#ifndef access_ok +#define access_ok(addr, size) likely(__access_ok(addr, size)) +#endif + +#endif diff --git a/include/asm-generic/archrandom.h b/include/asm-generic/archrandom.h new file mode 100644 index 000000000000..3cd7f980cfdc --- /dev/null +++ b/include/asm-generic/archrandom.h @@ -0,0 +1,15 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __ASM_GENERIC_ARCHRANDOM_H__ +#define __ASM_GENERIC_ARCHRANDOM_H__ + +static inline size_t __must_check arch_get_random_longs(unsigned long *v, size_t max_longs) +{ + return 0; +} + +static inline size_t __must_check arch_get_random_seed_longs(unsigned long *v, size_t max_longs) +{ + return 0; +} + +#endif diff --git a/include/asm-generic/barrier.h b/include/asm-generic/barrier.h index 640f09479bdf..961f4d88f9ef 100644 --- a/include/asm-generic/barrier.h +++ b/include/asm-generic/barrier.h @@ -14,6 +14,7 @@ #ifndef __ASSEMBLY__ #include <linux/compiler.h> +#include <linux/kcsan-checks.h> #include <asm/rwonce.h> #ifndef nop @@ -21,6 +22,35 @@ #endif /* + * Architectures that want generic instrumentation can define __ prefixed + * variants of all barriers. + */ + +#ifdef __mb +#define mb() do { kcsan_mb(); __mb(); } while (0) +#endif + +#ifdef __rmb +#define rmb() do { kcsan_rmb(); __rmb(); } while (0) +#endif + +#ifdef __wmb +#define wmb() do { kcsan_wmb(); __wmb(); } while (0) +#endif + +#ifdef __dma_mb +#define dma_mb() do { kcsan_mb(); __dma_mb(); } while (0) +#endif + +#ifdef __dma_rmb +#define dma_rmb() do { kcsan_rmb(); __dma_rmb(); } while (0) +#endif + +#ifdef __dma_wmb +#define dma_wmb() do { kcsan_wmb(); __dma_wmb(); } while (0) +#endif + +/* * Force strict CPU ordering. And yes, this is required on UP too when we're * talking to devices. * @@ -39,6 +69,10 @@ #define wmb() mb() #endif +#ifndef dma_mb +#define dma_mb() mb() +#endif + #ifndef dma_rmb #define dma_rmb() rmb() #endif @@ -62,15 +96,15 @@ #ifdef CONFIG_SMP #ifndef smp_mb -#define smp_mb() __smp_mb() +#define smp_mb() do { kcsan_mb(); __smp_mb(); } while (0) #endif #ifndef smp_rmb -#define smp_rmb() __smp_rmb() +#define smp_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0) #endif #ifndef smp_wmb -#define smp_wmb() __smp_wmb() +#define smp_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0) #endif #else /* !CONFIG_SMP */ @@ -123,19 +157,19 @@ do { \ #ifdef CONFIG_SMP #ifndef smp_store_mb -#define smp_store_mb(var, value) __smp_store_mb(var, value) +#define smp_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0) #endif #ifndef smp_mb__before_atomic -#define smp_mb__before_atomic() __smp_mb__before_atomic() +#define smp_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0) #endif #ifndef smp_mb__after_atomic -#define smp_mb__after_atomic() __smp_mb__after_atomic() +#define smp_mb__after_atomic() do { kcsan_mb(); __smp_mb__after_atomic(); } while (0) #endif #ifndef smp_store_release -#define smp_store_release(p, v) __smp_store_release(p, v) +#define smp_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0) #endif #ifndef smp_load_acquire @@ -178,13 +212,13 @@ do { \ #endif /* CONFIG_SMP */ /* Barriers for virtual machine guests when talking to an SMP host */ -#define virt_mb() __smp_mb() -#define virt_rmb() __smp_rmb() -#define virt_wmb() __smp_wmb() -#define virt_store_mb(var, value) __smp_store_mb(var, value) -#define virt_mb__before_atomic() __smp_mb__before_atomic() -#define virt_mb__after_atomic() __smp_mb__after_atomic() -#define virt_store_release(p, v) __smp_store_release(p, v) +#define virt_mb() do { kcsan_mb(); __smp_mb(); } while (0) +#define virt_rmb() do { kcsan_rmb(); __smp_rmb(); } while (0) +#define virt_wmb() do { kcsan_wmb(); __smp_wmb(); } while (0) +#define virt_store_mb(var, value) do { kcsan_mb(); __smp_store_mb(var, value); } while (0) +#define virt_mb__before_atomic() do { kcsan_mb(); __smp_mb__before_atomic(); } while (0) +#define virt_mb__after_atomic() do { kcsan_mb(); __smp_mb__after_atomic(); } while (0) +#define virt_store_release(p, v) do { kcsan_release(); __smp_store_release(p, v); } while (0) #define virt_load_acquire(p) __smp_load_acquire(p) /** @@ -251,5 +285,16 @@ do { \ #define pmem_wmb() wmb() #endif +/* + * ioremap_wc() maps I/O memory as memory with write-combining attributes. For + * this kind of memory accesses, the CPU may wait for prior accesses to be + * merged with subsequent ones. In some situation, such wait is bad for the + * performance. io_stop_wc() can be used to prevent the merging of + * write-combining memory accesses before this macro with those after it. + */ +#ifndef io_stop_wc +#define io_stop_wc() do { } while (0) +#endif + #endif /* !__ASSEMBLY__ */ #endif /* __ASM_GENERIC_BARRIER_H */ diff --git a/include/asm-generic/bitops.h b/include/asm-generic/bitops.h index df9b5bc3d282..a47b8a71d6fe 100644 --- a/include/asm-generic/bitops.h +++ b/include/asm-generic/bitops.h @@ -20,7 +20,6 @@ #include <asm-generic/bitops/fls.h> #include <asm-generic/bitops/__fls.h> #include <asm-generic/bitops/fls64.h> -#include <asm-generic/bitops/find.h> #ifndef _LINUX_BITOPS_H #error only <linux/bitops.h> can be included directly diff --git a/include/asm-generic/bitops/atomic.h b/include/asm-generic/bitops/atomic.h index 3096f086b5a3..71ab4ba9c25d 100644 --- a/include/asm-generic/bitops/atomic.h +++ b/include/asm-generic/bitops/atomic.h @@ -39,9 +39,6 @@ arch_test_and_set_bit(unsigned int nr, volatile unsigned long *p) unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); - if (READ_ONCE(*p) & mask) - return 1; - old = arch_atomic_long_fetch_or(mask, (atomic_long_t *)p); return !!(old & mask); } @@ -53,9 +50,6 @@ arch_test_and_clear_bit(unsigned int nr, volatile unsigned long *p) unsigned long mask = BIT_MASK(nr); p += BIT_WORD(nr); - if (!(READ_ONCE(*p) & mask)) - return 0; - old = arch_atomic_long_fetch_andnot(mask, (atomic_long_t *)p); return !!(old & mask); } diff --git a/include/asm-generic/bitops/find.h b/include/asm-generic/bitops/find.h deleted file mode 100644 index 0d132ee2a291..000000000000 --- a/include/asm-generic/bitops/find.h +++ /dev/null @@ -1,188 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_GENERIC_BITOPS_FIND_H_ -#define _ASM_GENERIC_BITOPS_FIND_H_ - -extern unsigned long _find_next_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long nbits, - unsigned long start, unsigned long invert, unsigned long le); -extern unsigned long _find_first_bit(const unsigned long *addr, unsigned long size); -extern unsigned long _find_first_zero_bit(const unsigned long *addr, unsigned long size); -extern unsigned long _find_last_bit(const unsigned long *addr, unsigned long size); - -#ifndef find_next_bit -/** - * find_next_bit - find the next set bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The bitmap size in bits - * - * Returns the bit number for the next set bit - * If no bits are set, returns @size. - */ -static inline -unsigned long find_next_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val; - - if (unlikely(offset >= size)) - return size; - - val = *addr & GENMASK(size - 1, offset); - return val ? __ffs(val) : size; - } - - return _find_next_bit(addr, NULL, size, offset, 0UL, 0); -} -#endif - -#ifndef find_next_and_bit -/** - * find_next_and_bit - find the next set bit in both memory regions - * @addr1: The first address to base the search on - * @addr2: The second address to base the search on - * @offset: The bitnumber to start searching at - * @size: The bitmap size in bits - * - * Returns the bit number for the next set bit - * If no bits are set, returns @size. - */ -static inline -unsigned long find_next_and_bit(const unsigned long *addr1, - const unsigned long *addr2, unsigned long size, - unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val; - - if (unlikely(offset >= size)) - return size; - - val = *addr1 & *addr2 & GENMASK(size - 1, offset); - return val ? __ffs(val) : size; - } - - return _find_next_bit(addr1, addr2, size, offset, 0UL, 0); -} -#endif - -#ifndef find_next_zero_bit -/** - * find_next_zero_bit - find the next cleared bit in a memory region - * @addr: The address to base the search on - * @offset: The bitnumber to start searching at - * @size: The bitmap size in bits - * - * Returns the bit number of the next zero bit - * If no bits are zero, returns @size. - */ -static inline -unsigned long find_next_zero_bit(const unsigned long *addr, unsigned long size, - unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val; - - if (unlikely(offset >= size)) - return size; - - val = *addr | ~GENMASK(size - 1, offset); - return val == ~0UL ? size : ffz(val); - } - - return _find_next_bit(addr, NULL, size, offset, ~0UL, 0); -} -#endif - -#ifdef CONFIG_GENERIC_FIND_FIRST_BIT - -/** - * find_first_bit - find the first set bit in a memory region - * @addr: The address to start the search at - * @size: The maximum number of bits to search - * - * Returns the bit number of the first set bit. - * If no bits are set, returns @size. - */ -static inline -unsigned long find_first_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr & GENMASK(size - 1, 0); - - return val ? __ffs(val) : size; - } - - return _find_first_bit(addr, size); -} - -/** - * find_first_zero_bit - find the first cleared bit in a memory region - * @addr: The address to start the search at - * @size: The maximum number of bits to search - * - * Returns the bit number of the first cleared bit. - * If no bits are zero, returns @size. - */ -static inline -unsigned long find_first_zero_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr | ~GENMASK(size - 1, 0); - - return val == ~0UL ? size : ffz(val); - } - - return _find_first_zero_bit(addr, size); -} -#else /* CONFIG_GENERIC_FIND_FIRST_BIT */ - -#ifndef find_first_bit -#define find_first_bit(addr, size) find_next_bit((addr), (size), 0) -#endif -#ifndef find_first_zero_bit -#define find_first_zero_bit(addr, size) find_next_zero_bit((addr), (size), 0) -#endif - -#endif /* CONFIG_GENERIC_FIND_FIRST_BIT */ - -#ifndef find_last_bit -/** - * find_last_bit - find the last set bit in a memory region - * @addr: The address to start the search at - * @size: The number of bits to search - * - * Returns the bit number of the last set bit, or size. - */ -static inline -unsigned long find_last_bit(const unsigned long *addr, unsigned long size) -{ - if (small_const_nbits(size)) { - unsigned long val = *addr & GENMASK(size - 1, 0); - - return val ? __fls(val) : size; - } - - return _find_last_bit(addr, size); -} -#endif - -/** - * find_next_clump8 - find next 8-bit clump with set bits in a memory region - * @clump: location to store copy of found clump - * @addr: address to base the search on - * @size: bitmap size in number of bits - * @offset: bit offset at which to start searching - * - * Returns the bit offset for the next set clump; the found clump value is - * copied to the location pointed by @clump. If no bits are set, returns @size. - */ -extern unsigned long find_next_clump8(unsigned long *clump, - const unsigned long *addr, - unsigned long size, unsigned long offset); - -#define find_first_clump8(clump, bits, size) \ - find_next_clump8((clump), (bits), (size), 0) - -#endif /*_ASM_GENERIC_BITOPS_FIND_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..564a8c675d85 --- /dev/null +++ b/include/asm-generic/bitops/generic-non-atomic.h @@ -0,0 +1,175 @@ +/* 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> +#include <asm/barrier.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))); +} + +/** + * generic_test_bit_acquire - Determine, with acquire semantics, whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline bool +generic_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + unsigned long *p = ((unsigned long *)addr) + BIT_WORD(nr); + return 1UL & (smp_load_acquire(p) >> (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 +#define const_test_bit_acquire generic_test_bit_acquire + +/** + * 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-atomic.h b/include/asm-generic/bitops/instrumented-atomic.h index 81915dcd4b4e..4225a8ca9c1a 100644 --- a/include/asm-generic/bitops/instrumented-atomic.h +++ b/include/asm-generic/bitops/instrumented-atomic.h @@ -23,7 +23,7 @@ * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void set_bit(long nr, volatile unsigned long *addr) +static __always_inline void set_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_set_bit(nr, addr); @@ -36,7 +36,7 @@ static inline void set_bit(long nr, volatile unsigned long *addr) * * This is a relaxed atomic operation (no implied memory barriers). */ -static inline void clear_bit(long nr, volatile unsigned long *addr) +static __always_inline void clear_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit(nr, addr); @@ -52,7 +52,7 @@ static inline void clear_bit(long nr, volatile unsigned long *addr) * Note that @nr may be almost arbitrarily large; this function is not * restricted to acting on a single-word quantity. */ -static inline void change_bit(long nr, volatile unsigned long *addr) +static __always_inline void change_bit(long nr, volatile unsigned long *addr) { instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_change_bit(nr, addr); @@ -65,8 +65,9 @@ static inline void change_bit(long nr, volatile unsigned long *addr) * * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_set_bit(long nr, volatile unsigned long *addr) { + kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_set_bit(nr, addr); } @@ -78,8 +79,9 @@ static inline bool test_and_set_bit(long nr, volatile unsigned long *addr) * * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) { + kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_clear_bit(nr, addr); } @@ -91,8 +93,9 @@ static inline bool test_and_clear_bit(long nr, volatile unsigned long *addr) * * This is an atomic fully-ordered operation (implied full memory barrier). */ -static inline bool test_and_change_bit(long nr, volatile unsigned long *addr) +static __always_inline bool test_and_change_bit(long nr, volatile unsigned long *addr) { + kcsan_mb(); instrument_atomic_read_write(addr + BIT_WORD(nr), sizeof(long)); return arch_test_and_change_bit(nr, addr); } diff --git a/include/asm-generic/bitops/instrumented-lock.h b/include/asm-generic/bitops/instrumented-lock.h index 75ef606f7145..eb64bd4f11f3 100644 --- a/include/asm-generic/bitops/instrumented-lock.h +++ b/include/asm-generic/bitops/instrumented-lock.h @@ -22,6 +22,7 @@ */ static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) { + kcsan_release(); instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); arch_clear_bit_unlock(nr, addr); } @@ -37,6 +38,7 @@ static inline void clear_bit_unlock(long nr, volatile unsigned long *addr) */ static inline void __clear_bit_unlock(long nr, volatile unsigned long *addr) { + kcsan_release(); instrument_write(addr + BIT_WORD(nr), sizeof(long)); arch___clear_bit_unlock(nr, addr); } @@ -71,6 +73,7 @@ static inline bool test_and_set_bit_lock(long nr, volatile unsigned long *addr) static inline bool clear_bit_unlock_is_negative_byte(long nr, volatile unsigned long *addr) { + kcsan_release(); instrument_atomic_write(addr + BIT_WORD(nr), sizeof(long)); return arch_clear_bit_unlock_is_negative_byte(nr, addr); } diff --git a/include/asm-generic/bitops/instrumented-non-atomic.h b/include/asm-generic/bitops/instrumented-non-atomic.h index 37363d570b9b..2b238b161a62 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 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 inline void __set_bit(long nr, volatile unsigned long *addr) * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static 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 * @@ -52,13 +54,14 @@ static inline void __clear_bit(long nr, volatile unsigned long *addr) * region of memory concurrently, the effect may be that only one operation * succeeds. */ -static 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); } -static inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) +static __always_inline void __instrument_read_write_bitop(long nr, volatile unsigned long *addr) { if (IS_ENABLED(CONFIG_KCSAN_ASSUME_PLAIN_WRITES_ATOMIC)) { /* @@ -83,56 +86,72 @@ static inline void __instrument_read_write_bitop(long nr, volatile unsigned long } /** - * __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 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 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 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 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); } +/** + * _test_bit_acquire - Determine, with acquire semantics, whether a bit is set + * @nr: bit number to test + * @addr: Address to start counting from + */ +static __always_inline bool +_test_bit_acquire(unsigned long nr, const volatile unsigned long *addr) +{ + instrument_atomic_read(addr + BIT_WORD(nr), sizeof(long)); + return arch_test_bit_acquire(nr, addr); +} + #endif /* _ASM_GENERIC_BITOPS_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/asm-generic/bitops/le.h b/include/asm-generic/bitops/le.h index 5a28629cbf4d..d51beff60375 100644 --- a/include/asm-generic/bitops/le.h +++ b/include/asm-generic/bitops/le.h @@ -2,83 +2,19 @@ #ifndef _ASM_GENERIC_BITOPS_LE_H_ #define _ASM_GENERIC_BITOPS_LE_H_ -#include <asm-generic/bitops/find.h> #include <asm/types.h> #include <asm/byteorder.h> -#include <linux/swab.h> #if defined(__LITTLE_ENDIAN) #define BITOP_LE_SWIZZLE 0 -static inline unsigned long find_next_zero_bit_le(const void *addr, - unsigned long size, unsigned long offset) -{ - return find_next_zero_bit(addr, size, offset); -} - -static inline unsigned long find_next_bit_le(const void *addr, - unsigned long size, unsigned long offset) -{ - return find_next_bit(addr, size, offset); -} - -static inline unsigned long find_first_zero_bit_le(const void *addr, - unsigned long size) -{ - return find_first_zero_bit(addr, size); -} - #elif defined(__BIG_ENDIAN) #define BITOP_LE_SWIZZLE ((BITS_PER_LONG-1) & ~0x7) -#ifndef find_next_zero_bit_le -static inline -unsigned long find_next_zero_bit_le(const void *addr, unsigned - long size, unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val = *(const unsigned long *)addr; - - if (unlikely(offset >= size)) - return size; - - val = swab(val) | ~GENMASK(size - 1, offset); - return val == ~0UL ? size : ffz(val); - } - - return _find_next_bit(addr, NULL, size, offset, ~0UL, 1); -} -#endif - -#ifndef find_next_bit_le -static inline -unsigned long find_next_bit_le(const void *addr, unsigned - long size, unsigned long offset) -{ - if (small_const_nbits(size)) { - unsigned long val = *(const unsigned long *)addr; - - if (unlikely(offset >= size)) - return size; - - val = swab(val) & GENMASK(size - 1, offset); - return val ? __ffs(val) : size; - } - - return _find_next_bit(addr, NULL, size, offset, 0UL, 1); -} #endif -#ifndef find_first_zero_bit_le -#define find_first_zero_bit_le(addr, size) \ - find_next_zero_bit_le((addr), (size), 0) -#endif - -#else -#error "Please fix <asm/byteorder.h>" -#endif static inline int test_bit_le(int nr, const void *addr) { diff --git a/include/asm-generic/bitops/non-atomic.h b/include/asm-generic/bitops/non-atomic.h index 078cc68be2f1..71f8d54a5195 100644 --- a/include/asm-generic/bitops/non-atomic.h +++ b/include/asm-generic/bitops/non-atomic.h @@ -2,121 +2,19 @@ #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 +#define arch_test_bit_acquire generic_test_bit_acquire - *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..0ddc78dfc358 --- /dev/null +++ b/include/asm-generic/bitops/non-instrumented-non-atomic.h @@ -0,0 +1,17 @@ +/* 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 +#define _test_bit_acquire arch_test_bit_acquire + +#endif /* __ASM_GENERIC_BITOPS_NON_INSTRUMENTED_NON_ATOMIC_H */ diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h index edb0e2a602a8..4050b191e1a9 100644 --- a/include/asm-generic/bug.h +++ b/include/asm-generic/bug.h @@ -21,6 +21,12 @@ #include <linux/panic.h> #include <linux/printk.h> +struct warn_args; +struct pt_regs; + +void __warn(const char *file, int line, void *caller, unsigned taint, + struct pt_regs *regs, struct warn_args *args); + #ifdef CONFIG_BUG #ifdef CONFIG_GENERIC_BUG @@ -110,11 +116,6 @@ extern __printf(1, 2) void __warn_printk(const char *fmt, ...); #endif /* used internally by panic.c */ -struct warn_args; -struct pt_regs; - -void __warn(const char *file, int line, void *caller, unsigned taint, - struct pt_regs *regs, struct warn_args *args); #ifndef WARN_ON #define WARN_ON(condition) ({ \ @@ -219,22 +220,6 @@ void __warn(const char *file, int line, void *caller, unsigned taint, # define WARN_ON_SMP(x) ({0;}) #endif -/* - * WARN_ON_FUNCTION_MISMATCH() warns if a value doesn't match a - * function address, and can be useful for catching issues with - * callback functions, for example. - * - * With CONFIG_CFI_CLANG, the warning is disabled because the - * compiler replaces function addresses taken in C code with - * local jump table addresses, which breaks cross-module function - * address equality. - */ -#if defined(CONFIG_CFI_CLANG) && defined(CONFIG_MODULES) -# define WARN_ON_FUNCTION_MISMATCH(x, fn) ({ 0; }) -#else -# define WARN_ON_FUNCTION_MISMATCH(x, fn) WARN_ON_ONCE((x) != (fn)) -#endif - #endif /* __ASSEMBLY__ */ #endif diff --git a/include/asm-generic/cacheflush.h b/include/asm-generic/cacheflush.h index 4f07afacbc23..f46258d1a080 100644 --- a/include/asm-generic/cacheflush.h +++ b/include/asm-generic/cacheflush.h @@ -2,6 +2,8 @@ #ifndef _ASM_GENERIC_CACHEFLUSH_H #define _ASM_GENERIC_CACHEFLUSH_H +#include <linux/instrumented.h> + struct mm_struct; struct vm_area_struct; struct page; @@ -105,14 +107,22 @@ static inline void flush_cache_vunmap(unsigned long start, unsigned long end) #ifndef copy_to_user_page #define copy_to_user_page(vma, page, vaddr, dst, src, len) \ do { \ + instrument_copy_to_user((void __user *)dst, src, len); \ memcpy(dst, src, len); \ flush_icache_user_page(vma, page, vaddr, len); \ } while (0) #endif + #ifndef copy_from_user_page -#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ - memcpy(dst, src, len) +#define copy_from_user_page(vma, page, vaddr, dst, src, len) \ + do { \ + instrument_copy_from_user_before(dst, (void __user *)src, \ + len); \ + memcpy(dst, src, len); \ + instrument_copy_from_user_after(dst, (void __user *)src, len, \ + 0); \ + } while (0) #endif #endif /* _ASM_GENERIC_CACHEFLUSH_H */ diff --git a/include/asm-generic/compat.h b/include/asm-generic/compat.h index d46c0201cc34..8392caea398f 100644 --- a/include/asm-generic/compat.h +++ b/include/asm-generic/compat.h @@ -2,6 +2,30 @@ #ifndef __ASM_GENERIC_COMPAT_H #define __ASM_GENERIC_COMPAT_H +#ifndef COMPAT_USER_HZ +#define COMPAT_USER_HZ 100 +#endif + +#ifndef COMPAT_RLIM_INFINITY +#define COMPAT_RLIM_INFINITY 0xffffffff +#endif + +#ifndef COMPAT_OFF_T_MAX +#define COMPAT_OFF_T_MAX 0x7fffffff +#endif + +#ifndef compat_arg_u64 +#ifndef CONFIG_CPU_BIG_ENDIAN +#define compat_arg_u64(name) u32 name##_lo, u32 name##_hi +#define compat_arg_u64_dual(name) u32, name##_lo, u32, name##_hi +#else +#define compat_arg_u64(name) u32 name##_hi, u32 name##_lo +#define compat_arg_u64_dual(name) u32, name##_hi, u32, name##_lo +#endif +#define compat_arg_u64_glue(name) (((u64)name##_lo & 0xffffffffUL) | \ + ((u64)name##_hi << 32)) +#endif /* compat_arg_u64 */ + /* These types are common across all compat ABIs */ typedef u32 compat_size_t; typedef s32 compat_ssize_t; @@ -24,6 +48,11 @@ typedef u32 compat_caddr_t; typedef u32 compat_aio_context_t; typedef u32 compat_old_sigset_t; +#ifndef __compat_uid_t +typedef u32 __compat_uid_t; +typedef u32 __compat_gid_t; +#endif + #ifndef __compat_uid32_t typedef u32 __compat_uid32_t; typedef u32 __compat_gid32_t; @@ -47,4 +76,93 @@ typedef u32 compat_sigset_word; #define _COMPAT_NSIG_BPW 32 #endif +#ifndef compat_dev_t +typedef u32 compat_dev_t; +#endif + +#ifndef compat_ipc_pid_t +typedef s32 compat_ipc_pid_t; +#endif + +#ifndef compat_fsid_t +typedef __kernel_fsid_t compat_fsid_t; +#endif + +#ifndef compat_statfs +struct compat_statfs { + compat_int_t f_type; + compat_int_t f_bsize; + compat_int_t f_blocks; + compat_int_t f_bfree; + compat_int_t f_bavail; + compat_int_t f_files; + compat_int_t f_ffree; + compat_fsid_t f_fsid; + compat_int_t f_namelen; + compat_int_t f_frsize; + compat_int_t f_flags; + compat_int_t f_spare[4]; +}; +#endif + +#ifndef compat_ipc64_perm +struct compat_ipc64_perm { + compat_key_t key; + __compat_uid32_t uid; + __compat_gid32_t gid; + __compat_uid32_t cuid; + __compat_gid32_t cgid; + compat_mode_t mode; + unsigned char __pad1[4 - sizeof(compat_mode_t)]; + compat_ushort_t seq; + compat_ushort_t __pad2; + compat_ulong_t unused1; + compat_ulong_t unused2; +}; + +struct compat_semid64_ds { + struct compat_ipc64_perm sem_perm; + compat_ulong_t sem_otime; + compat_ulong_t sem_otime_high; + compat_ulong_t sem_ctime; + compat_ulong_t sem_ctime_high; + compat_ulong_t sem_nsems; + compat_ulong_t __unused3; + compat_ulong_t __unused4; +}; + +struct compat_msqid64_ds { + struct compat_ipc64_perm msg_perm; + compat_ulong_t msg_stime; + compat_ulong_t msg_stime_high; + compat_ulong_t msg_rtime; + compat_ulong_t msg_rtime_high; + compat_ulong_t msg_ctime; + compat_ulong_t msg_ctime_high; + compat_ulong_t msg_cbytes; + compat_ulong_t msg_qnum; + compat_ulong_t msg_qbytes; + compat_pid_t msg_lspid; + compat_pid_t msg_lrpid; + compat_ulong_t __unused4; + compat_ulong_t __unused5; +}; + +struct compat_shmid64_ds { + struct compat_ipc64_perm shm_perm; + compat_size_t shm_segsz; + compat_ulong_t shm_atime; + compat_ulong_t shm_atime_high; + compat_ulong_t shm_dtime; + compat_ulong_t shm_dtime_high; + compat_ulong_t shm_ctime; + compat_ulong_t shm_ctime_high; + compat_pid_t shm_cpid; + compat_pid_t shm_lpid; + compat_ulong_t shm_nattch; + compat_ulong_t __unused4; + compat_ulong_t __unused5; +}; +#endif + #endif diff --git a/include/asm-generic/error-injection.h b/include/asm-generic/error-injection.h index 7ddd9dc10ce9..fbca56bd9cbc 100644 --- a/include/asm-generic/error-injection.h +++ b/include/asm-generic/error-injection.h @@ -20,7 +20,7 @@ struct pt_regs; #ifdef CONFIG_FUNCTION_ERROR_INJECTION /* - * Whitelist ganerating macro. Specify functions which can be + * Whitelist generating macro. Specify functions which can be * error-injectable using this macro. */ #define ALLOW_ERROR_INJECTION(fname, _etype) \ @@ -29,7 +29,7 @@ static struct error_injection_entry __used \ _eil_addr_##fname = { \ .addr = (unsigned long)fname, \ .etype = EI_ETYPE_##_etype, \ - }; + } void override_function_with_return(struct pt_regs *regs); #else diff --git a/include/asm-generic/export.h b/include/asm-generic/export.h index 07a36a874dca..5e4b1f2369d2 100644 --- a/include/asm-generic/export.h +++ b/include/asm-generic/export.h @@ -2,6 +2,14 @@ #ifndef __ASM_GENERIC_EXPORT_H #define __ASM_GENERIC_EXPORT_H +/* + * This comment block is used by fixdep. Please do not remove. + * + * When CONFIG_MODVERSIONS is changed from n to y, all source files having + * EXPORT_SYMBOL variants must be re-compiled because genksyms is run as a + * side effect of the *.o build rule. + */ + #ifndef KSYM_FUNC #define KSYM_FUNC(x) x #endif @@ -12,9 +20,6 @@ #else #define KSYM_ALIGN 4 #endif -#ifndef KCRC_ALIGN -#define KCRC_ALIGN 4 -#endif .macro __put, val, name #ifdef CONFIG_HAVE_ARCH_PREL32_RELOCATIONS @@ -43,17 +48,6 @@ __ksymtab_\name: __kstrtab_\name: .asciz "\name" .previous -#ifdef CONFIG_MODVERSIONS - .section ___kcrctab\sec+\name,"a" - .balign KCRC_ALIGN -#if defined(CONFIG_MODULE_REL_CRCS) - .long __crc_\name - . -#else - .long __crc_\name -#endif - .weak __crc_\name - .previous -#endif #endif .endm diff --git a/include/asm-generic/hugetlb.h b/include/asm-generic/hugetlb.h index 8e1e6244a89d..a57d667addd2 100644 --- a/include/asm-generic/hugetlb.h +++ b/include/asm-generic/hugetlb.h @@ -2,6 +2,9 @@ #ifndef _ASM_GENERIC_HUGETLB_H #define _ASM_GENERIC_HUGETLB_H +#include <linux/swap.h> +#include <linux/swapops.h> + static inline pte_t mk_huge_pte(struct page *page, pgprot_t pgprot) { return mk_pte(page, pgprot); @@ -32,6 +35,21 @@ static inline pte_t huge_pte_modify(pte_t pte, pgprot_t newprot) return pte_modify(pte, newprot); } +static inline pte_t huge_pte_mkuffd_wp(pte_t pte) +{ + return pte_mkuffd_wp(pte); +} + +static inline pte_t huge_pte_clear_uffd_wp(pte_t pte) +{ + return pte_clear_uffd_wp(pte); +} + +static inline int huge_pte_uffd_wp(pte_t pte) +{ + return pte_uffd_wp(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_CLEAR static inline void huge_pte_clear(struct mm_struct *mm, unsigned long addr, pte_t *ptep, unsigned long sz) @@ -66,10 +84,10 @@ static inline pte_t huge_ptep_get_and_clear(struct mm_struct *mm, #endif #ifndef __HAVE_ARCH_HUGE_PTEP_CLEAR_FLUSH -static inline void huge_ptep_clear_flush(struct vm_area_struct *vma, +static inline pte_t huge_ptep_clear_flush(struct vm_area_struct *vma, unsigned long addr, pte_t *ptep) { - ptep_clear_flush(vma, addr, ptep); + return ptep_clear_flush(vma, addr, ptep); } #endif @@ -80,6 +98,12 @@ static inline int huge_pte_none(pte_t pte) } #endif +/* Please refer to comments above pte_none_mostly() for the usage */ +static inline int huge_pte_none_mostly(pte_t pte) +{ + return huge_pte_none(pte) || is_pte_marker(pte); +} + #ifndef __HAVE_ARCH_HUGE_PTE_WRPROTECT static inline pte_t huge_pte_wrprotect(pte_t pte) { diff --git a/include/asm-generic/hyperv-tlfs.h b/include/asm-generic/hyperv-tlfs.h index 8ed6733d5146..b17c6eeb9afa 100644 --- a/include/asm-generic/hyperv-tlfs.h +++ b/include/asm-generic/hyperv-tlfs.h @@ -102,6 +102,15 @@ struct ms_hyperv_tsc_page { volatile s64 tsc_offset; } __packed; +union hv_reference_tsc_msr { + u64 as_uint64; + struct { + u64 enable:1; + u64 reserved:11; + u64 pfn:52; + } __packed; +}; + /* * The guest OS needs to register the guest ID with the hypervisor. * The guest ID is a 64 bit entity and the structure of this ID is @@ -183,11 +192,18 @@ enum HV_GENERIC_SET_FORMAT { #define HV_HYPERCALL_RESULT_MASK GENMASK_ULL(15, 0) #define HV_HYPERCALL_FAST_BIT BIT(16) #define HV_HYPERCALL_VARHEAD_OFFSET 17 +#define HV_HYPERCALL_VARHEAD_MASK GENMASK_ULL(26, 17) +#define HV_HYPERCALL_RSVD0_MASK GENMASK_ULL(31, 27) #define HV_HYPERCALL_REP_COMP_OFFSET 32 #define HV_HYPERCALL_REP_COMP_1 BIT_ULL(32) #define HV_HYPERCALL_REP_COMP_MASK GENMASK_ULL(43, 32) +#define HV_HYPERCALL_RSVD1_MASK GENMASK_ULL(47, 44) #define HV_HYPERCALL_REP_START_OFFSET 48 #define HV_HYPERCALL_REP_START_MASK GENMASK_ULL(59, 48) +#define HV_HYPERCALL_RSVD2_MASK GENMASK_ULL(63, 60) +#define HV_HYPERCALL_RSVD_MASK (HV_HYPERCALL_RSVD0_MASK | \ + HV_HYPERCALL_RSVD1_MASK | \ + HV_HYPERCALL_RSVD2_MASK) /* hypercall status code */ #define HV_STATUS_SUCCESS 0 @@ -540,39 +556,6 @@ enum hv_interrupt_source { HV_INTERRUPT_SOURCE_IOAPIC, }; -union hv_msi_address_register { - u32 as_uint32; - struct { - u32 reserved1:2; - u32 destination_mode:1; - u32 redirection_hint:1; - u32 reserved2:8; - u32 destination_id:8; - u32 msi_base:12; - }; -} __packed; - -union hv_msi_data_register { - u32 as_uint32; - struct { - u32 vector:8; - u32 delivery_mode:3; - u32 reserved1:3; - u32 level_assert:1; - u32 trigger_mode:1; - u32 reserved2:16; - }; -} __packed; - -/* HvRetargetDeviceInterrupt hypercall */ -union hv_msi_entry { - u64 as_uint64; - struct { - union hv_msi_address_register address; - union hv_msi_data_register data; - } __packed; -}; - union hv_ioapic_rte { u64 as_uint64; diff --git a/include/asm-generic/io.h b/include/asm-generic/io.h index 7ce93aaf69f8..a68f8fbf423b 100644 --- a/include/asm-generic/io.h +++ b/include/asm-generic/io.h @@ -10,6 +10,7 @@ #include <asm/page.h> /* I/O is all done through memory accesses */ #include <linux/string.h> /* for memset() and memcpy() */ #include <linux/types.h> +#include <linux/instruction_pointer.h> #ifdef CONFIG_GENERIC_IOMAP #include <asm-generic/iomap.h> @@ -61,6 +62,44 @@ #define __io_par(v) __io_ar(v) #endif +/* + * "__DISABLE_TRACE_MMIO__" flag can be used to disable MMIO tracing for + * specific kernel drivers in case of excessive/unwanted logging. + * + * Usage: Add a #define flag at the beginning of the driver file. + * Ex: #define __DISABLE_TRACE_MMIO__ + * #include <...> + * ... + */ +#if IS_ENABLED(CONFIG_TRACE_MMIO_ACCESS) && !(defined(__DISABLE_TRACE_MMIO__)) +#include <linux/tracepoint-defs.h> + +DECLARE_TRACEPOINT(rwmmio_write); +DECLARE_TRACEPOINT(rwmmio_post_write); +DECLARE_TRACEPOINT(rwmmio_read); +DECLARE_TRACEPOINT(rwmmio_post_read); + +void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr); +void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr); +void log_read_mmio(u8 width, const volatile void __iomem *addr, + unsigned long caller_addr); +void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr, + unsigned long caller_addr); + +#else + +static inline void log_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr) {} +static inline void log_post_write_mmio(u64 val, u8 width, volatile void __iomem *addr, + unsigned long caller_addr) {} +static inline void log_read_mmio(u8 width, const volatile void __iomem *addr, + unsigned long caller_addr) {} +static inline void log_post_read_mmio(u64 val, u8 width, const volatile void __iomem *addr, + unsigned long caller_addr) {} + +#endif /* CONFIG_TRACE_MMIO_ACCESS */ /* * __raw_{read,write}{b,w,l,q}() access memory in native endianness. @@ -149,9 +188,11 @@ static inline u8 readb(const volatile void __iomem *addr) { u8 val; + log_read_mmio(8, addr, _THIS_IP_); __io_br(); val = __raw_readb(addr); __io_ar(val); + log_post_read_mmio(val, 8, addr, _THIS_IP_); return val; } #endif @@ -162,9 +203,11 @@ static inline u16 readw(const volatile void __iomem *addr) { u16 val; + log_read_mmio(16, addr, _THIS_IP_); __io_br(); val = __le16_to_cpu((__le16 __force)__raw_readw(addr)); __io_ar(val); + log_post_read_mmio(val, 16, addr, _THIS_IP_); return val; } #endif @@ -175,9 +218,11 @@ static inline u32 readl(const volatile void __iomem *addr) { u32 val; + log_read_mmio(32, addr, _THIS_IP_); __io_br(); val = __le32_to_cpu((__le32 __force)__raw_readl(addr)); __io_ar(val); + log_post_read_mmio(val, 32, addr, _THIS_IP_); return val; } #endif @@ -189,9 +234,11 @@ static inline u64 readq(const volatile void __iomem *addr) { u64 val; + log_read_mmio(64, addr, _THIS_IP_); __io_br(); val = __le64_to_cpu(__raw_readq(addr)); __io_ar(val); + log_post_read_mmio(val, 64, addr, _THIS_IP_); return val; } #endif @@ -201,9 +248,11 @@ static inline u64 readq(const volatile void __iomem *addr) #define writeb writeb static inline void writeb(u8 value, volatile void __iomem *addr) { + log_write_mmio(value, 8, addr, _THIS_IP_); __io_bw(); __raw_writeb(value, addr); __io_aw(); + log_post_write_mmio(value, 8, addr, _THIS_IP_); } #endif @@ -211,9 +260,11 @@ static inline void writeb(u8 value, volatile void __iomem *addr) #define writew writew static inline void writew(u16 value, volatile void __iomem *addr) { + log_write_mmio(value, 16, addr, _THIS_IP_); __io_bw(); __raw_writew((u16 __force)cpu_to_le16(value), addr); __io_aw(); + log_post_write_mmio(value, 16, addr, _THIS_IP_); } #endif @@ -221,9 +272,11 @@ static inline void writew(u16 value, volatile void __iomem *addr) #define writel writel static inline void writel(u32 value, volatile void __iomem *addr) { + log_write_mmio(value, 32, addr, _THIS_IP_); __io_bw(); __raw_writel((u32 __force)__cpu_to_le32(value), addr); __io_aw(); + log_post_write_mmio(value, 32, addr, _THIS_IP_); } #endif @@ -232,9 +285,11 @@ static inline void writel(u32 value, volatile void __iomem *addr) #define writeq writeq static inline void writeq(u64 value, volatile void __iomem *addr) { + log_write_mmio(value, 64, addr, _THIS_IP_); __io_bw(); __raw_writeq(__cpu_to_le64(value), addr); __io_aw(); + log_post_write_mmio(value, 64, addr, _THIS_IP_); } #endif #endif /* CONFIG_64BIT */ @@ -248,7 +303,12 @@ static inline void writeq(u64 value, volatile void __iomem *addr) #define readb_relaxed readb_relaxed static inline u8 readb_relaxed(const volatile void __iomem *addr) { - return __raw_readb(addr); + u8 val; + + log_read_mmio(8, addr, _THIS_IP_); + val = __raw_readb(addr); + log_post_read_mmio(val, 8, addr, _THIS_IP_); + return val; } #endif @@ -256,7 +316,12 @@ static inline u8 readb_relaxed(const volatile void __iomem *addr) #define readw_relaxed readw_relaxed static inline u16 readw_relaxed(const volatile void __iomem *addr) { - return __le16_to_cpu(__raw_readw(addr)); + u16 val; + + log_read_mmio(16, addr, _THIS_IP_); + val = __le16_to_cpu(__raw_readw(addr)); + log_post_read_mmio(val, 16, addr, _THIS_IP_); + return val; } #endif @@ -264,7 +329,12 @@ static inline u16 readw_relaxed(const volatile void __iomem *addr) #define readl_relaxed readl_relaxed static inline u32 readl_relaxed(const volatile void __iomem *addr) { - return __le32_to_cpu(__raw_readl(addr)); + u32 val; + + log_read_mmio(32, addr, _THIS_IP_); + val = __le32_to_cpu(__raw_readl(addr)); + log_post_read_mmio(val, 32, addr, _THIS_IP_); + return val; } #endif @@ -272,7 +342,12 @@ static inline u32 readl_relaxed(const volatile void __iomem *addr) #define readq_relaxed readq_relaxed static inline u64 readq_relaxed(const volatile void __iomem *addr) { - return __le64_to_cpu(__raw_readq(addr)); + u64 val; + + log_read_mmio(64, addr, _THIS_IP_); + val = __le64_to_cpu(__raw_readq(addr)); + log_post_read_mmio(val, 64, addr, _THIS_IP_); + return val; } #endif @@ -280,7 +355,9 @@ static inline u64 readq_relaxed(const volatile void __iomem *addr) #define writeb_relaxed writeb_relaxed static inline void writeb_relaxed(u8 value, volatile void __iomem *addr) { + log_write_mmio(value, 8, addr, _THIS_IP_); __raw_writeb(value, addr); + log_post_write_mmio(value, 8, addr, _THIS_IP_); } #endif @@ -288,7 +365,9 @@ static inline void writeb_relaxed(u8 value, volatile void __iomem *addr) #define writew_relaxed writew_relaxed static inline void writew_relaxed(u16 value, volatile void __iomem *addr) { + log_write_mmio(value, 16, addr, _THIS_IP_); __raw_writew(cpu_to_le16(value), addr); + log_post_write_mmio(value, 16, addr, _THIS_IP_); } #endif @@ -296,7 +375,9 @@ static inline void writew_relaxed(u16 value, volatile void __iomem *addr) #define writel_relaxed writel_relaxed static inline void writel_relaxed(u32 value, volatile void __iomem *addr) { + log_write_mmio(value, 32, addr, _THIS_IP_); __raw_writel(__cpu_to_le32(value), addr); + log_post_write_mmio(value, 32, addr, _THIS_IP_); } #endif @@ -304,7 +385,9 @@ static inline void writel_relaxed(u32 value, volatile void __iomem *addr) #define writeq_relaxed writeq_relaxed static inline void writeq_relaxed(u64 value, volatile void __iomem *addr) { + log_write_mmio(value, 64, addr, _THIS_IP_); __raw_writeq(__cpu_to_le64(value), addr); + log_post_write_mmio(value, 64, addr, _THIS_IP_); } #endif @@ -964,7 +1047,34 @@ static inline void iounmap(volatile void __iomem *addr) #elif defined(CONFIG_GENERIC_IOREMAP) #include <linux/pgtable.h> -void __iomem *ioremap_prot(phys_addr_t addr, size_t size, unsigned long prot); +/* + * Arch code can implement the following two hooks when using GENERIC_IOREMAP + * ioremap_allowed() return a bool, + * - true means continue to remap + * - false means skip remap and return directly + * iounmap_allowed() return a bool, + * - true means continue to vunmap + * - false means skip vunmap and return directly + */ +#ifndef ioremap_allowed +#define ioremap_allowed ioremap_allowed +static inline bool ioremap_allowed(phys_addr_t phys_addr, size_t size, + unsigned long prot) +{ + return true; +} +#endif + +#ifndef iounmap_allowed +#define iounmap_allowed iounmap_allowed +static inline bool iounmap_allowed(void *addr) +{ + return true; +} +#endif + +void __iomem *ioremap_prot(phys_addr_t phys_addr, size_t size, + unsigned long prot); void iounmap(volatile void __iomem *addr); static inline void __iomem *ioremap(phys_addr_t addr, size_t size) @@ -1059,20 +1169,6 @@ static inline void unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) } #endif -#ifdef CONFIG_VIRT_TO_BUS -#ifndef virt_to_bus -static inline unsigned long virt_to_bus(void *address) -{ - return (unsigned long)address; -} - -static inline void *bus_to_virt(unsigned long address) -{ - return (void *)address; -} -#endif -#endif - #ifndef memset_io #define memset_io memset_io /** @@ -1125,9 +1221,7 @@ static inline void memcpy_toio(volatile void __iomem *addr, const void *buffer, } #endif -#ifndef CONFIG_GENERIC_DEVMEM_IS_ALLOWED extern int devmem_is_allowed(unsigned long pfn); -#endif #endif /* __KERNEL__ */ diff --git a/include/asm-generic/logic_io.h b/include/asm-generic/logic_io.h index a53116b8c57e..8a59b6e567df 100644 --- a/include/asm-generic/logic_io.h +++ b/include/asm-generic/logic_io.h @@ -34,7 +34,7 @@ void __iomem *ioremap(phys_addr_t offset, size_t size); #define iounmap iounmap -void iounmap(void __iomem *addr); +void iounmap(void volatile __iomem *addr); #define __raw_readb __raw_readb u8 __raw_readb(const volatile void __iomem *addr); diff --git a/include/asm-generic/mshyperv.h b/include/asm-generic/mshyperv.h index 3e2248ac328e..bfb9eb9d7215 100644 --- a/include/asm-generic/mshyperv.h +++ b/include/asm-generic/mshyperv.h @@ -49,8 +49,8 @@ struct ms_hyperv_info { }; extern struct ms_hyperv_info ms_hyperv; -extern void __percpu **hyperv_pcpu_input_arg; -extern void __percpu **hyperv_pcpu_output_arg; +extern void * __percpu *hyperv_pcpu_input_arg; +extern void * __percpu *hyperv_pcpu_output_arg; extern u64 hv_do_hypercall(u64 control, void *inputaddr, void *outputaddr); extern u64 hv_do_fast_hypercall8(u16 control, u64 input8); @@ -105,15 +105,12 @@ static inline u64 hv_do_rep_hypercall(u16 code, u16 rep_count, u16 varhead_size, } /* Generate the guest OS identifier as described in the Hyper-V TLFS */ -static inline __u64 generate_guest_id(__u64 d_info1, __u64 kernel_version, - __u64 d_info2) +static inline u64 hv_generate_guest_id(u64 kernel_version) { - __u64 guest_id = 0; + u64 guest_id; - guest_id = (((__u64)HV_LINUX_VENDOR_ID) << 48); - guest_id |= (d_info1 << 48); + guest_id = (((u64)HV_LINUX_VENDOR_ID) << 48); guest_id |= (kernel_version << 16); - guest_id |= d_info2; return guest_id; } @@ -269,6 +266,9 @@ bool hv_isolation_type_snp(void); u64 hv_ghcb_hypercall(u64 control, void *input, void *output, u32 input_size); void hyperv_cleanup(void); bool hv_query_ext_cap(u64 cap_query); +void hv_setup_dma_ops(struct device *dev, bool coherent); +void *hv_map_memory(void *addr, unsigned long size); +void hv_unmap_memory(void *addr); #else /* CONFIG_HYPERV */ static inline bool hv_is_hyperv_initialized(void) { return false; } static inline bool hv_is_hibernation_supported(void) { return false; } diff --git a/include/asm-generic/pci.h b/include/asm-generic/pci.h index 6bb3cd3d695a..6869f1061528 100644 --- a/include/asm-generic/pci.h +++ b/include/asm-generic/pci.h @@ -1,17 +1,30 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * linux/include/asm-generic/pci.h - * - * Copyright (C) 2003 Russell King - */ -#ifndef _ASM_GENERIC_PCI_H -#define _ASM_GENERIC_PCI_H +/* SPDX-License-Identifier: GPL-2.0-only */ -#ifndef HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ -static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) +#ifndef __ASM_GENERIC_PCI_H +#define __ASM_GENERIC_PCI_H + +#ifndef PCIBIOS_MIN_IO +#define PCIBIOS_MIN_IO 0 +#endif + +#ifndef PCIBIOS_MIN_MEM +#define PCIBIOS_MIN_MEM 0 +#endif + +#ifndef pcibios_assign_all_busses +/* For bootloaders that do not initialize the PCI bus */ +#define pcibios_assign_all_busses() 1 +#endif + +/* Enable generic resource mapping code in drivers/pci/ */ +#define ARCH_GENERIC_PCI_MMAP_RESOURCE + +#ifdef CONFIG_PCI_DOMAINS +static inline int pci_proc_domain(struct pci_bus *bus) { - return channel ? 15 : 14; + /* always show the domain in /proc */ + return 1; } -#endif /* HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ */ +#endif /* CONFIG_PCI_DOMAINS */ -#endif /* _ASM_GENERIC_PCI_H */ +#endif /* __ASM_GENERIC_PCI_H */ diff --git a/include/asm-generic/pci_iomap.h b/include/asm-generic/pci_iomap.h index 5a2f9bf53384..8fbb0a55545d 100644 --- a/include/asm-generic/pci_iomap.h +++ b/include/asm-generic/pci_iomap.h @@ -25,6 +25,8 @@ extern void pci_iounmap(struct pci_dev *dev, void __iomem *); #ifdef CONFIG_NO_GENERIC_PCI_IOPORT_MAP extern void __iomem *__pci_ioport_map(struct pci_dev *dev, unsigned long port, unsigned int nr); +#elif !defined(CONFIG_HAS_IOPORT_MAP) +#define __pci_ioport_map(dev, port, nr) NULL #else #define __pci_ioport_map(dev, port, nr) ioport_map((port), (nr)) #endif diff --git a/include/asm-generic/pgalloc.h b/include/asm-generic/pgalloc.h index 02932efad3ab..977bea16cf1b 100644 --- a/include/asm-generic/pgalloc.h +++ b/include/asm-generic/pgalloc.h @@ -147,6 +147,15 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) #if CONFIG_PGTABLE_LEVELS > 3 +static inline pud_t *__pud_alloc_one(struct mm_struct *mm, unsigned long addr) +{ + gfp_t gfp = GFP_PGTABLE_USER; + + if (mm == &init_mm) + gfp = GFP_PGTABLE_KERNEL; + return (pud_t *)get_zeroed_page(gfp); +} + #ifndef __HAVE_ARCH_PUD_ALLOC_ONE /** * pud_alloc_one - allocate a page for PUD-level page table @@ -159,20 +168,23 @@ static inline void pmd_free(struct mm_struct *mm, pmd_t *pmd) */ static inline pud_t *pud_alloc_one(struct mm_struct *mm, unsigned long addr) { - gfp_t gfp = GFP_PGTABLE_USER; - - if (mm == &init_mm) - gfp = GFP_PGTABLE_KERNEL; - return (pud_t *)get_zeroed_page(gfp); + return __pud_alloc_one(mm, addr); } #endif -static inline void pud_free(struct mm_struct *mm, pud_t *pud) +static inline void __pud_free(struct mm_struct *mm, pud_t *pud) { BUG_ON((unsigned long)pud & (PAGE_SIZE-1)); free_page((unsigned long)pud); } +#ifndef __HAVE_ARCH_PUD_FREE +static inline void pud_free(struct mm_struct *mm, pud_t *pud) +{ + __pud_free(mm, pud); +} +#endif + #endif /* CONFIG_PGTABLE_LEVELS > 3 */ #ifndef __HAVE_ARCH_PGD_FREE diff --git a/include/asm-generic/pgtable-nopmd.h b/include/asm-generic/pgtable-nopmd.h index 10789cf51d16..8ffd64e7a24c 100644 --- a/include/asm-generic/pgtable-nopmd.h +++ b/include/asm-generic/pgtable-nopmd.h @@ -30,6 +30,8 @@ typedef struct { pud_t pud; } pmd_t; static inline int pud_none(pud_t pud) { return 0; } static inline int pud_bad(pud_t pud) { return 0; } static inline int pud_present(pud_t pud) { return 1; } +static inline int pud_user(pud_t pud) { return 0; } +static inline int pud_leaf(pud_t pud) { return 0; } static inline void pud_clear(pud_t *pud) { } #define pmd_ERROR(pmd) (pud_ERROR((pmd).pud)) diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h index 7ae0ece07b4e..75b8f4601b28 100644 --- a/include/asm-generic/qrwlock.h +++ b/include/asm-generic/qrwlock.h @@ -2,6 +2,10 @@ /* * Queue read/write lock * + * These use generic atomic and locking routines, but depend on a fair spinlock + * implementation in order to be fair themselves. The implementation in + * asm-generic/spinlock.h meets these requirements. + * * (C) Copyright 2013-2014 Hewlett-Packard Development Company, L.P. * * Authors: Waiman Long <waiman.long@hp.com> @@ -33,8 +37,8 @@ extern void queued_read_lock_slowpath(struct qrwlock *lock); extern void queued_write_lock_slowpath(struct qrwlock *lock); /** - * queued_read_trylock - try to acquire read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_trylock - try to acquire read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_read_trylock(struct qrwlock *lock) @@ -52,8 +56,8 @@ static inline int queued_read_trylock(struct qrwlock *lock) } /** - * queued_write_trylock - try to acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_trylock - try to acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure * Return: 1 if lock acquired, 0 if failed */ static inline int queued_write_trylock(struct qrwlock *lock) @@ -68,8 +72,8 @@ static inline int queued_write_trylock(struct qrwlock *lock) _QW_LOCKED)); } /** - * queued_read_lock - acquire read lock of a queue rwlock - * @lock: Pointer to queue rwlock structure + * queued_read_lock - acquire read lock of a queued rwlock + * @lock: Pointer to queued rwlock structure */ static inline void queued_read_lock(struct qrwlock *lock) { @@ -84,8 +88,8 @@ static inline void queued_read_lock(struct qrwlock *lock) } /** - * queued_write_lock - acquire write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_lock - acquire write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_lock(struct qrwlock *lock) { @@ -98,8 +102,8 @@ static inline void queued_write_lock(struct qrwlock *lock) } /** - * queued_read_unlock - release read lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_read_unlock - release read lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_read_unlock(struct qrwlock *lock) { @@ -110,8 +114,8 @@ static inline void queued_read_unlock(struct qrwlock *lock) } /** - * queued_write_unlock - release write lock of a queue rwlock - * @lock : Pointer to queue rwlock structure + * queued_write_unlock - release write lock of a queued rwlock + * @lock : Pointer to queued rwlock structure */ static inline void queued_write_unlock(struct qrwlock *lock) { @@ -120,7 +124,7 @@ static inline void queued_write_unlock(struct qrwlock *lock) /** * queued_rwlock_is_contended - check if the lock is contended - * @lock : Pointer to queue rwlock structure + * @lock : Pointer to queued rwlock structure * Return: 1 if lock contended, 0 otherwise */ static inline int queued_rwlock_is_contended(struct qrwlock *lock) @@ -130,7 +134,7 @@ static inline int queued_rwlock_is_contended(struct qrwlock *lock) /* * Remapping rwlock architecture specific functions to the corresponding - * queue rwlock functions. + * queued rwlock functions. */ #define arch_read_lock(l) queued_read_lock(l) #define arch_write_lock(l) queued_write_lock(l) diff --git a/include/asm-generic/qrwlock_types.h b/include/asm-generic/qrwlock_types.h index c36f1d5a2572..12392c14c4d0 100644 --- a/include/asm-generic/qrwlock_types.h +++ b/include/asm-generic/qrwlock_types.h @@ -7,7 +7,7 @@ #include <asm/spinlock_types.h> /* - * The queue read/write lock data structure + * The queued read/write lock data structure */ typedef struct qrwlock { diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h index d74b13825501..995513fa2690 100644 --- a/include/asm-generic/qspinlock.h +++ b/include/asm-generic/qspinlock.h @@ -2,6 +2,35 @@ /* * Queued spinlock * + * A 'generic' spinlock implementation that is based on MCS locks. For an + * architecture that's looking for a 'generic' spinlock, please first consider + * ticket-lock.h and only come looking here when you've considered all the + * constraints below and can show your hardware does actually perform better + * with qspinlock. + * + * qspinlock relies on atomic_*_release()/atomic_*_acquire() to be RCsc (or no + * weaker than RCtso if you're power), where regular code only expects atomic_t + * to be RCpc. + * + * qspinlock relies on a far greater (compared to asm-generic/spinlock.h) set + * of atomic operations to behave well together, please audit them carefully to + * ensure they all have forward progress. Many atomic operations may default to + * cmpxchg() loops which will not have good forward progress properties on + * LL/SC architectures. + * + * One notable example is atomic_fetch_or_acquire(), which x86 cannot (cheaply) + * do. Carefully read the patches that introduced + * queued_fetch_set_pending_acquire(). + * + * qspinlock also heavily relies on mixed size atomic operations, in specific + * it requires architectures to have xchg16; something which many LL/SC + * architectures need to implement as a 32bit and+or in order to satisfy the + * forward progress guarantees mentioned above. + * + * Further reading on mixed size atomics that might be relevant: + * + * http://www.cl.cam.ac.uk/~pes20/popl17/mixed-size.pdf + * * (C) Copyright 2013-2015 Hewlett-Packard Development Company, L.P. * (C) Copyright 2015 Hewlett-Packard Enterprise Development LP * diff --git a/include/asm-generic/sections.h b/include/asm-generic/sections.h index 1dfadb2e878d..db13bb620f52 100644 --- a/include/asm-generic/sections.h +++ b/include/asm-generic/sections.h @@ -59,11 +59,24 @@ extern char __noinstr_text_start[], __noinstr_text_end[]; extern __visible const void __nosave_begin, __nosave_end; /* Function descriptor handling (if any). Override in asm/sections.h */ -#ifndef dereference_function_descriptor +#ifdef CONFIG_HAVE_FUNCTION_DESCRIPTORS +void *dereference_function_descriptor(void *ptr); +void *dereference_kernel_function_descriptor(void *ptr); +#else #define dereference_function_descriptor(p) ((void *)(p)) #define dereference_kernel_function_descriptor(p) ((void *)(p)) + +/* An address is simply the address of the function. */ +typedef struct { + unsigned long addr; +} func_desc_t; #endif +static inline bool have_function_descriptors(void) +{ + return IS_ENABLED(CONFIG_HAVE_FUNCTION_DESCRIPTORS); +} + /** * memory_contains - checks if an object is contained within a memory region * @begin: virtual address of the beginning of the memory region @@ -84,7 +97,7 @@ static inline bool memory_contains(void *begin, void *end, void *virt, /** * memory_intersects - checks if the region occupied by an object intersects * with another memory region - * @begin: virtual address of the beginning of the memory regien + * @begin: virtual address of the beginning of the memory region * @end: virtual address of the end of the memory region * @virt: virtual address of the memory object * @size: size of the memory object @@ -97,7 +110,10 @@ static inline bool memory_intersects(void *begin, void *end, void *virt, { void *vend = virt + size; - return (virt >= begin && virt < end) || (vend >= begin && vend < end); + if (virt < end && vend > begin) + return true; + + return false; } /** @@ -130,18 +146,24 @@ static inline bool init_section_intersects(void *virt, size_t size) /** * is_kernel_core_data - checks if the pointer address is located in the - * .data section + * .data or .bss section * * @addr: address to check * - * Returns: true if the address is located in .data, false otherwise. + * Returns: true if the address is located in .data or .bss, false otherwise. * Note: On some archs it may return true for core RODATA, and false * for others. But will always be true for core RW data. */ static inline bool is_kernel_core_data(unsigned long addr) { - return addr >= (unsigned long)_sdata && - addr < (unsigned long)_edata; + if (addr >= (unsigned long)_sdata && addr < (unsigned long)_edata) + return true; + + if (addr >= (unsigned long)__bss_start && + addr < (unsigned long)__bss_stop) + return true; + + return false; } /** @@ -193,12 +215,16 @@ static inline bool __is_kernel_text(unsigned long addr) * @addr: address to check * * Returns: true if the address is located in the kernel range, false otherwise. - * Note: an internal helper, only check the range of _stext to _end. + * Note: an internal helper, check the range of _stext to _end, + * and range from __init_begin to __init_end, which can be outside + * of the _stext to _end range. */ static inline bool __is_kernel(unsigned long addr) { - return addr >= (unsigned long)_stext && - addr < (unsigned long)_end; + return ((addr >= (unsigned long)_stext && + addr < (unsigned long)_end) || + (addr >= (unsigned long)__init_begin && + addr < (unsigned long)__init_end)); } #endif /* _ASM_GENERIC_SECTIONS_H_ */ diff --git a/include/asm-generic/signal.h b/include/asm-generic/signal.h index c53984fa9761..663dd6d0795d 100644 --- a/include/asm-generic/signal.h +++ b/include/asm-generic/signal.h @@ -5,8 +5,6 @@ #include <uapi/asm-generic/signal.h> #ifndef __ASSEMBLY__ -#ifdef SA_RESTORER -#endif #include <asm/sigcontext.h> #undef __HAVE_ARCH_SIG_BITOPS diff --git a/include/asm-generic/softirq_stack.h b/include/asm-generic/softirq_stack.h index eceeecf6a5bd..2a67aed9ac52 100644 --- a/include/asm-generic/softirq_stack.h +++ b/include/asm-generic/softirq_stack.h @@ -2,7 +2,7 @@ #ifndef __ASM_GENERIC_SOFTIRQ_STACK_H #define __ASM_GENERIC_SOFTIRQ_STACK_H -#ifdef CONFIG_HAVE_SOFTIRQ_ON_OWN_STACK +#ifdef CONFIG_SOFTIRQ_ON_OWN_STACK void do_softirq_own_stack(void); #else static inline void do_softirq_own_stack(void) diff --git a/include/asm-generic/spinlock.h b/include/asm-generic/spinlock.h index adaf6acab172..fdfebcb050f4 100644 --- a/include/asm-generic/spinlock.h +++ b/include/asm-generic/spinlock.h @@ -1,12 +1,92 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef __ASM_GENERIC_SPINLOCK_H -#define __ASM_GENERIC_SPINLOCK_H + /* - * You need to implement asm/spinlock.h for SMP support. The generic - * version does not handle SMP. + * 'Generic' ticket-lock implementation. + * + * It relies on atomic_fetch_add() having well defined forward progress + * guarantees under contention. If your architecture cannot provide this, stick + * to a test-and-set lock. + * + * It also relies on atomic_fetch_add() being safe vs smp_store_release() on a + * sub-word of the value. This is generally true for anything LL/SC although + * you'd be hard pressed to find anything useful in architecture specifications + * about this. If your architecture cannot do this you might be better off with + * a test-and-set. + * + * It further assumes atomic_*_release() + atomic_*_acquire() is RCpc and hence + * uses atomic_fetch_add() which is RCsc to create an RCsc hot path, along with + * a full fence after the spin to upgrade the otherwise-RCpc + * atomic_cond_read_acquire(). + * + * The implementation uses smp_cond_load_acquire() to spin, so if the + * architecture has WFE like instructions to sleep instead of poll for word + * modifications be sure to implement that (see ARM64 for example). + * */ -#ifdef CONFIG_SMP -#error need an architecture specific asm/spinlock.h -#endif + +#ifndef __ASM_GENERIC_SPINLOCK_H +#define __ASM_GENERIC_SPINLOCK_H + +#include <linux/atomic.h> +#include <asm-generic/spinlock_types.h> + +static __always_inline void arch_spin_lock(arch_spinlock_t *lock) +{ + u32 val = atomic_fetch_add(1<<16, lock); + u16 ticket = val >> 16; + + if (ticket == (u16)val) + return; + + /* + * atomic_cond_read_acquire() is RCpc, but rather than defining a + * custom cond_read_rcsc() here we just emit a full fence. We only + * need the prior reads before subsequent writes ordering from + * smb_mb(), but as atomic_cond_read_acquire() just emits reads and we + * have no outstanding writes due to the atomic_fetch_add() the extra + * orderings are free. + */ + atomic_cond_read_acquire(lock, ticket == (u16)VAL); + smp_mb(); +} + +static __always_inline bool arch_spin_trylock(arch_spinlock_t *lock) +{ + u32 old = atomic_read(lock); + + if ((old >> 16) != (old & 0xffff)) + return false; + + return atomic_try_cmpxchg(lock, &old, old + (1<<16)); /* SC, for RCsc */ +} + +static __always_inline void arch_spin_unlock(arch_spinlock_t *lock) +{ + u16 *ptr = (u16 *)lock + IS_ENABLED(CONFIG_CPU_BIG_ENDIAN); + u32 val = atomic_read(lock); + + smp_store_release(ptr, (u16)val + 1); +} + +static __always_inline int arch_spin_is_locked(arch_spinlock_t *lock) +{ + u32 val = atomic_read(lock); + + return ((val >> 16) != (val & 0xffff)); +} + +static __always_inline int arch_spin_is_contended(arch_spinlock_t *lock) +{ + u32 val = atomic_read(lock); + + return (s16)((val >> 16) - (val & 0xffff)) > 1; +} + +static __always_inline int arch_spin_value_unlocked(arch_spinlock_t lock) +{ + return !arch_spin_is_locked(&lock); +} + +#include <asm/qrwlock.h> #endif /* __ASM_GENERIC_SPINLOCK_H */ diff --git a/include/asm-generic/spinlock_types.h b/include/asm-generic/spinlock_types.h new file mode 100644 index 000000000000..8962bb730945 --- /dev/null +++ b/include/asm-generic/spinlock_types.h @@ -0,0 +1,17 @@ +/* SPDX-License-Identifier: GPL-2.0 */ + +#ifndef __ASM_GENERIC_SPINLOCK_TYPES_H +#define __ASM_GENERIC_SPINLOCK_TYPES_H + +#include <linux/types.h> +typedef atomic_t arch_spinlock_t; + +/* + * qrwlock_types depends on arch_spinlock_t, so we must typedef that before the + * include. + */ +#include <asm/qrwlock_types.h> + +#define __ARCH_SPIN_LOCK_UNLOCKED ATOMIC_INIT(0) + +#endif /* __ASM_GENERIC_SPINLOCK_TYPES_H */ diff --git a/include/asm-generic/syscall.h b/include/asm-generic/syscall.h index 81695eb02a12..5a80fe728dc8 100644 --- a/include/asm-generic/syscall.h +++ b/include/asm-generic/syscall.h @@ -44,7 +44,7 @@ int syscall_get_nr(struct task_struct *task, struct pt_regs *regs); * * It's only valid to call this when @task is stopped for system * call exit tracing (due to %SYSCALL_WORK_SYSCALL_TRACE or - * %SYSCALL_WORK_SYSCALL_AUDIT), after tracehook_report_syscall_entry() + * %SYSCALL_WORK_SYSCALL_AUDIT), after ptrace_report_syscall_entry() * returned nonzero to prevent the system call from taking place. * * This rolls back the register state in @regs so it's as if the diff --git a/include/asm-generic/termios-base.h b/include/asm-generic/termios-base.h deleted file mode 100644 index 59c5a3bd4a6e..000000000000 --- a/include/asm-generic/termios-base.h +++ /dev/null @@ -1,78 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* termios.h: generic termios/termio user copying/translation - */ - -#ifndef _ASM_GENERIC_TERMIOS_BASE_H -#define _ASM_GENERIC_TERMIOS_BASE_H - -#include <linux/uaccess.h> - -#ifndef __ARCH_TERMIO_GETPUT - -/* - * Translate a "termio" structure into a "termios". Ugh. - */ -static inline int user_termio_to_kernel_termios(struct ktermios *termios, - struct termio __user *termio) -{ - unsigned short tmp; - - if (get_user(tmp, &termio->c_iflag) < 0) - goto fault; - termios->c_iflag = (0xffff0000 & termios->c_iflag) | tmp; - - if (get_user(tmp, &termio->c_oflag) < 0) - goto fault; - termios->c_oflag = (0xffff0000 & termios->c_oflag) | tmp; - - if (get_user(tmp, &termio->c_cflag) < 0) - goto fault; - termios->c_cflag = (0xffff0000 & termios->c_cflag) | tmp; - - if (get_user(tmp, &termio->c_lflag) < 0) - goto fault; - termios->c_lflag = (0xffff0000 & termios->c_lflag) | tmp; - - if (get_user(termios->c_line, &termio->c_line) < 0) - goto fault; - - if (copy_from_user(termios->c_cc, termio->c_cc, NCC) != 0) - goto fault; - - return 0; - - fault: - return -EFAULT; -} - -/* - * Translate a "termios" structure into a "termio". Ugh. - */ -static inline int kernel_termios_to_user_termio(struct termio __user *termio, - struct ktermios *termios) -{ - if (put_user(termios->c_iflag, &termio->c_iflag) < 0 || - put_user(termios->c_oflag, &termio->c_oflag) < 0 || - put_user(termios->c_cflag, &termio->c_cflag) < 0 || - put_user(termios->c_lflag, &termio->c_lflag) < 0 || - put_user(termios->c_line, &termio->c_line) < 0 || - copy_to_user(termio->c_cc, termios->c_cc, NCC) != 0) - return -EFAULT; - - return 0; -} - -#ifndef user_termios_to_kernel_termios -#define user_termios_to_kernel_termios(k, u) copy_from_user(k, u, sizeof(struct termios)) -#endif - -#ifndef kernel_termios_to_user_termios -#define kernel_termios_to_user_termios(u, k) copy_to_user(u, k, sizeof(struct termios)) -#endif - -#define user_termios_to_kernel_termios_1(k, u) copy_from_user(k, u, sizeof(struct termios)) -#define kernel_termios_to_user_termios_1(u, k) copy_to_user(u, k, sizeof(struct termios)) - -#endif /* __ARCH_TERMIO_GETPUT */ - -#endif /* _ASM_GENERIC_TERMIOS_BASE_H */ diff --git a/include/asm-generic/termios.h b/include/asm-generic/termios.h deleted file mode 100644 index b1398d0d4a1d..000000000000 --- a/include/asm-generic/termios.h +++ /dev/null @@ -1,108 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _ASM_GENERIC_TERMIOS_H -#define _ASM_GENERIC_TERMIOS_H - - -#include <linux/uaccess.h> -#include <uapi/asm-generic/termios.h> - -/* intr=^C quit=^\ erase=del kill=^U - eof=^D vtime=\0 vmin=\1 sxtc=\0 - start=^Q stop=^S susp=^Z eol=\0 - reprint=^R discard=^U werase=^W lnext=^V - eol2=\0 -*/ -#define INIT_C_CC "\003\034\177\025\004\0\1\0\021\023\032\0\022\017\027\026\0" - -/* - * Translate a "termio" structure into a "termios". Ugh. - */ -static inline int user_termio_to_kernel_termios(struct ktermios *termios, - const struct termio __user *termio) -{ - unsigned short tmp; - - if (get_user(tmp, &termio->c_iflag) < 0) - goto fault; - termios->c_iflag = (0xffff0000 & termios->c_iflag) | tmp; - - if (get_user(tmp, &termio->c_oflag) < 0) - goto fault; - termios->c_oflag = (0xffff0000 & termios->c_oflag) | tmp; - - if (get_user(tmp, &termio->c_cflag) < 0) - goto fault; - termios->c_cflag = (0xffff0000 & termios->c_cflag) | tmp; - - if (get_user(tmp, &termio->c_lflag) < 0) - goto fault; - termios->c_lflag = (0xffff0000 & termios->c_lflag) | tmp; - - if (get_user(termios->c_line, &termio->c_line) < 0) - goto fault; - - if (copy_from_user(termios->c_cc, termio->c_cc, NCC) != 0) - goto fault; - - return 0; - - fault: - return -EFAULT; -} - -/* - * Translate a "termios" structure into a "termio". Ugh. - */ -static inline int kernel_termios_to_user_termio(struct termio __user *termio, - struct ktermios *termios) -{ - if (put_user(termios->c_iflag, &termio->c_iflag) < 0 || - put_user(termios->c_oflag, &termio->c_oflag) < 0 || - put_user(termios->c_cflag, &termio->c_cflag) < 0 || - put_user(termios->c_lflag, &termio->c_lflag) < 0 || - put_user(termios->c_line, &termio->c_line) < 0 || - copy_to_user(termio->c_cc, termios->c_cc, NCC) != 0) - return -EFAULT; - - return 0; -} - -#ifdef TCGETS2 -static inline int user_termios_to_kernel_termios(struct ktermios *k, - struct termios2 __user *u) -{ - return copy_from_user(k, u, sizeof(struct termios2)); -} - -static inline int kernel_termios_to_user_termios(struct termios2 __user *u, - struct ktermios *k) -{ - return copy_to_user(u, k, sizeof(struct termios2)); -} - -static inline int user_termios_to_kernel_termios_1(struct ktermios *k, - struct termios __user *u) -{ - return copy_from_user(k, u, sizeof(struct termios)); -} - -static inline int kernel_termios_to_user_termios_1(struct termios __user *u, - struct ktermios *k) -{ - return copy_to_user(u, k, sizeof(struct termios)); -} -#else /* TCGETS2 */ -static inline int user_termios_to_kernel_termios(struct ktermios *k, - struct termios __user *u) -{ - return copy_from_user(k, u, sizeof(struct termios)); -} - -static inline int kernel_termios_to_user_termios(struct termios __user *u, - struct ktermios *k) -{ - return copy_to_user(u, k, sizeof(struct termios)); -} -#endif /* TCGETS2 */ - -#endif /* _ASM_GENERIC_TERMIOS_H */ diff --git a/include/asm-generic/tlb.h b/include/asm-generic/tlb.h index 2c68a545ffa7..492dce43236e 100644 --- a/include/asm-generic/tlb.h +++ b/include/asm-generic/tlb.h @@ -158,9 +158,24 @@ * Useful if your architecture doesn't use IPIs for remote TLB invalidates * and therefore doesn't naturally serialize with software page-table walkers. * + * MMU_GATHER_NO_FLUSH_CACHE + * + * Indicates the architecture has flush_cache_range() but it needs *NOT* be called + * before unmapping a VMA. + * + * NOTE: strictly speaking we shouldn't have this knob and instead rely on + * flush_cache_range() being a NOP, except Sparc64 seems to be + * different here. + * + * MMU_GATHER_MERGE_VMAS + * + * Indicates the architecture wants to merge ranges over VMAs; typical when + * multiple range invalidates are more expensive than a full invalidate. + * * MMU_GATHER_NO_RANGE * - * Use this if your architecture lacks an efficient flush_tlb_range(). + * Use this if your architecture lacks an efficient flush_tlb_range(). This + * option implies MMU_GATHER_MERGE_VMAS above. * * MMU_GATHER_NO_GATHER * @@ -180,7 +195,7 @@ struct mmu_table_batch { struct rcu_head rcu; #endif unsigned int nr; - void *tables[0]; + void *tables[]; }; #define MAX_TABLE_BATCH \ @@ -227,7 +242,7 @@ struct mmu_gather_batch { struct mmu_gather_batch *next; unsigned int nr; unsigned int max; - struct page *pages[0]; + struct page *pages[]; }; #define MAX_GATHER_BATCH \ @@ -288,6 +303,7 @@ struct mmu_gather { */ unsigned int vma_exec : 1; unsigned int vma_huge : 1; + unsigned int vma_pfn : 1; unsigned int batch_count; @@ -334,8 +350,8 @@ static inline void __tlb_reset_range(struct mmu_gather *tlb) #ifdef CONFIG_MMU_GATHER_NO_RANGE -#if defined(tlb_flush) || defined(tlb_start_vma) || defined(tlb_end_vma) -#error MMU_GATHER_NO_RANGE relies on default tlb_flush(), tlb_start_vma() and tlb_end_vma() +#if defined(tlb_flush) +#error MMU_GATHER_NO_RANGE relies on default tlb_flush() #endif /* @@ -352,20 +368,9 @@ static inline void tlb_flush(struct mmu_gather *tlb) flush_tlb_mm(tlb->mm); } -static inline void -tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } - -#define tlb_end_vma tlb_end_vma -static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { } - #else /* CONFIG_MMU_GATHER_NO_RANGE */ #ifndef tlb_flush - -#if defined(tlb_start_vma) || defined(tlb_end_vma) -#error Default tlb_flush() relies on default tlb_start_vma() and tlb_end_vma() -#endif - /* * When an architecture does not provide its own tlb_flush() implementation * but does have a reasonably efficient flush_vma_range() implementation @@ -385,6 +390,9 @@ static inline void tlb_flush(struct mmu_gather *tlb) flush_tlb_range(&vma, tlb->start, tlb->end); } } +#endif + +#endif /* CONFIG_MMU_GATHER_NO_RANGE */ static inline void tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) @@ -402,17 +410,9 @@ tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) */ tlb->vma_huge = is_vm_hugetlb_page(vma); tlb->vma_exec = !!(vma->vm_flags & VM_EXEC); + tlb->vma_pfn = !!(vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)); } -#else - -static inline void -tlb_update_vma_flags(struct mmu_gather *tlb, struct vm_area_struct *vma) { } - -#endif - -#endif /* CONFIG_MMU_GATHER_NO_RANGE */ - static inline void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { /* @@ -486,32 +486,36 @@ static inline unsigned long tlb_get_unmap_size(struct mmu_gather *tlb) * case where we're doing a full MM flush. When we're doing a munmap, * the vmas are adjusted to only cover the region to be torn down. */ -#ifndef tlb_start_vma static inline void tlb_start_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; tlb_update_vma_flags(tlb, vma); +#ifndef CONFIG_MMU_GATHER_NO_FLUSH_CACHE flush_cache_range(vma, vma->vm_start, vma->vm_end); -} #endif +} -#ifndef tlb_end_vma static inline void tlb_end_vma(struct mmu_gather *tlb, struct vm_area_struct *vma) { if (tlb->fullmm) return; /* - * Do a TLB flush and reset the range at VMA boundaries; this avoids - * the ranges growing with the unused space between consecutive VMAs, - * but also the mmu_gather::vma_* flags from tlb_start_vma() rely on - * this. + * VM_PFNMAP is more fragile because the core mm will not track the + * page mapcount -- there might not be page-frames for these PFNs after + * all. Force flush TLBs for such ranges to avoid munmap() vs + * unmap_mapping_range() races. */ - tlb_flush_mmu_tlbonly(tlb); + if (tlb->vma_pfn || !IS_ENABLED(CONFIG_MMU_GATHER_MERGE_VMAS)) { + /* + * Do a TLB flush and reset the range at VMA boundaries; this avoids + * the ranges growing with the unused space between consecutive VMAs. + */ + tlb_flush_mmu_tlbonly(tlb); + } } -#endif /* * tlb_flush_{pte|pmd|pud|p4d}_range() adjust the tlb->start and tlb->end, @@ -565,10 +569,14 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, #define tlb_remove_huge_tlb_entry(h, tlb, ptep, address) \ do { \ unsigned long _sz = huge_page_size(h); \ - if (_sz == PMD_SIZE) \ - tlb_flush_pmd_range(tlb, address, _sz); \ - else if (_sz == PUD_SIZE) \ + if (_sz >= P4D_SIZE) \ + tlb_flush_p4d_range(tlb, address, _sz); \ + else if (_sz >= PUD_SIZE) \ tlb_flush_pud_range(tlb, address, _sz); \ + else if (_sz >= PMD_SIZE) \ + tlb_flush_pmd_range(tlb, address, _sz); \ + else \ + tlb_flush_pte_range(tlb, address, _sz); \ __tlb_remove_tlb_entry(tlb, ptep, address); \ } while (0) @@ -654,6 +662,20 @@ static inline void tlb_flush_p4d_range(struct mmu_gather *tlb, } while (0) #endif +#ifndef pte_needs_flush +static inline bool pte_needs_flush(pte_t oldpte, pte_t newpte) +{ + return true; +} +#endif + +#ifndef huge_pmd_needs_flush +static inline bool huge_pmd_needs_flush(pmd_t oldpmd, pmd_t newpmd) +{ + return true; +} +#endif + #endif /* CONFIG_MMU */ #endif /* _ASM_GENERIC__TLB_H */ diff --git a/include/asm-generic/uaccess.h b/include/asm-generic/uaccess.h index 10ffa8b5c117..a5be9e61a2a2 100644 --- a/include/asm-generic/uaccess.h +++ b/include/asm-generic/uaccess.h @@ -8,6 +8,7 @@ * address space, e.g. all NOMMU machines. */ #include <linux/string.h> +#include <asm-generic/access_ok.h> #ifdef CONFIG_UACCESS_MEMCPY #include <asm/unaligned.h> @@ -77,8 +78,6 @@ do { \ goto err_label; \ } while (0) -#define HAVE_GET_KERNEL_NOFAULT 1 - static inline __must_check unsigned long raw_copy_from_user(void *to, const void __user * from, unsigned long n) { @@ -96,49 +95,6 @@ raw_copy_to_user(void __user *to, const void *from, unsigned long n) #define INLINE_COPY_TO_USER #endif /* CONFIG_UACCESS_MEMCPY */ -#ifdef CONFIG_SET_FS -#define MAKE_MM_SEG(s) ((mm_segment_t) { (s) }) - -#ifndef KERNEL_DS -#define KERNEL_DS MAKE_MM_SEG(~0UL) -#endif - -#ifndef USER_DS -#define USER_DS MAKE_MM_SEG(TASK_SIZE - 1) -#endif - -#ifndef get_fs -#define get_fs() (current_thread_info()->addr_limit) - -static inline void set_fs(mm_segment_t fs) -{ - current_thread_info()->addr_limit = fs; -} -#endif - -#ifndef uaccess_kernel -#define uaccess_kernel() (get_fs().seg == KERNEL_DS.seg) -#endif - -#ifndef user_addr_max -#define user_addr_max() (uaccess_kernel() ? ~0UL : TASK_SIZE) -#endif - -#endif /* CONFIG_SET_FS */ - -#define access_ok(addr, size) __access_ok((unsigned long)(addr),(size)) - -/* - * The architecture should really override this if possible, at least - * doing a check on the get_fs() - */ -#ifndef __access_ok -static inline int __access_ok(unsigned long addr, unsigned long size) -{ - return 1; -} -#endif - /* * These are the main single-value transfer routines. They automatically * use the right size if we just have the right pointer type. diff --git a/include/asm-generic/unaligned.h b/include/asm-generic/unaligned.h index 1c4242416c9f..699650f81970 100644 --- a/include/asm-generic/unaligned.h +++ b/include/asm-generic/unaligned.h @@ -126,4 +126,30 @@ static inline void put_unaligned_le24(const u32 val, void *p) __put_unaligned_le24(val, p); } +static inline void __put_unaligned_be48(const u64 val, u8 *p) +{ + *p++ = val >> 40; + *p++ = val >> 32; + *p++ = val >> 24; + *p++ = val >> 16; + *p++ = val >> 8; + *p++ = val; +} + +static inline void put_unaligned_be48(const u64 val, void *p) +{ + __put_unaligned_be48(val, p); +} + +static inline u64 __get_unaligned_be48(const u8 *p) +{ + return (u64)p[0] << 40 | (u64)p[1] << 32 | (u64)p[2] << 24 | + p[3] << 16 | p[4] << 8 | p[5]; +} + +static inline u64 get_unaligned_be48(const void *p) +{ + return __get_unaligned_be48(p); +} + #endif /* __ASM_GENERIC_UNALIGNED_H */ diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h index 42f3866bca69..3dc5824141cd 100644 --- a/include/asm-generic/vmlinux.lds.h +++ b/include/asm-generic/vmlinux.lds.h @@ -126,13 +126,13 @@ */ #define SCHED_DATA \ STRUCT_ALIGN(); \ - __begin_sched_classes = .; \ - *(__idle_sched_class) \ - *(__fair_sched_class) \ - *(__rt_sched_class) \ - *(__dl_sched_class) \ + __sched_class_highest = .; \ *(__stop_sched_class) \ - __end_sched_classes = .; + *(__dl_sched_class) \ + *(__rt_sched_class) \ + *(__fair_sched_class) \ + *(__idle_sched_class) \ + __sched_class_lowest = .; /* The actual configuration determine if the init/exit sections * are handled as text/data or they can be discarded (which @@ -154,6 +154,24 @@ #define MEM_DISCARD(sec) *(.mem##sec) #endif +#ifndef CONFIG_HAVE_DYNAMIC_FTRACE_NO_PATCHABLE +#define KEEP_PATCHABLE KEEP(*(__patchable_function_entries)) +#define PATCHABLE_DISCARDS +#else +#define KEEP_PATCHABLE +#define PATCHABLE_DISCARDS *(__patchable_function_entries) +#endif + +#ifndef CONFIG_ARCH_SUPPORTS_CFI_CLANG +/* + * Simply points to ftrace_stub, but with the proper protocol. + * Defined by the linker script in linux/vmlinux.lds.h + */ +#define FTRACE_STUB_HACK ftrace_stub_graph = ftrace_stub; +#else +#define FTRACE_STUB_HACK +#endif + #ifdef CONFIG_FTRACE_MCOUNT_RECORD /* * The ftrace call sites are logged to a section whose name depends on the @@ -161,10 +179,6 @@ * FTRACE_CALLSITE_SECTION. We capture all of them here to avoid header * dependencies for FTRACE_CALLSITE_SECTION's definition. * - * Need to also make ftrace_stub_graph point to ftrace_stub - * so that the same stub location may have different protocols - * and not mess up with C verifiers. - * * ftrace_ops_list_func will be defined as arch_ftrace_ops_list_func * as some archs will have a different prototype for that function * but ftrace_ops_list_func() will have a single prototype. @@ -172,13 +186,13 @@ #define MCOUNT_REC() . = ALIGN(8); \ __start_mcount_loc = .; \ KEEP(*(__mcount_loc)) \ - KEEP(*(__patchable_function_entries)) \ + KEEP_PATCHABLE \ __stop_mcount_loc = .; \ - ftrace_stub_graph = ftrace_stub; \ + FTRACE_STUB_HACK \ ftrace_ops_list_func = arch_ftrace_ops_list_func; #else # ifdef CONFIG_FUNCTION_TRACER -# define MCOUNT_REC() ftrace_stub_graph = ftrace_stub; \ +# define MCOUNT_REC() FTRACE_STUB_HACK \ ftrace_ops_list_func = arch_ftrace_ops_list_func; # else # define MCOUNT_REC() @@ -321,16 +335,6 @@ #define THERMAL_TABLE(name) #endif -#ifdef CONFIG_DTPM -#define DTPM_TABLE() \ - . = ALIGN(8); \ - __dtpm_table = .; \ - KEEP(*(__dtpm_table)) \ - __dtpm_table_end = .; -#else -#define DTPM_TABLE() -#endif - #define KERNEL_DTB() \ STRUCT_ALIGN(); \ __dtb_start = .; \ @@ -343,6 +347,7 @@ #define DATA_DATA \ *(.xiptext) \ *(DATA_MAIN) \ + *(.data..decrypted) \ *(.ref.data) \ *(.data..shared_aligned) /* percpu related */ \ MEM_KEEP(init.data*) \ @@ -355,6 +360,9 @@ *(__tracepoints) \ /* implement dynamic printk debug */ \ . = ALIGN(8); \ + __start___dyndbg_classes = .; \ + KEEP(*(__dyndbg_classes)) \ + __stop___dyndbg_classes = .; \ __start___dyndbg = .; \ KEEP(*(__dyndbg)) \ __stop___dyndbg = .; \ @@ -404,6 +412,7 @@ KEEP(*(__jump_table)) \ __stop___jump_table = .; +#ifdef CONFIG_HAVE_STATIC_CALL_INLINE #define STATIC_CALL_DATA \ . = ALIGN(8); \ __start_static_call_sites = .; \ @@ -412,6 +421,9 @@ __start_static_call_tramp_key = .; \ KEEP(*(.static_call_tramp_key)) \ __stop_static_call_tramp_key = .; +#else +#define STATIC_CALL_DATA +#endif /* * Allow architectures to handle ro_after_init data on their @@ -428,6 +440,22 @@ #endif /* + * .kcfi_traps contains a list KCFI trap locations. + */ +#ifndef KCFI_TRAPS +#ifdef CONFIG_ARCH_USES_CFI_TRAPS +#define KCFI_TRAPS \ + __kcfi_traps : AT(ADDR(__kcfi_traps) - LOAD_OFFSET) { \ + __start___kcfi_traps = .; \ + KEEP(*(.kcfi_traps)) \ + __stop___kcfi_traps = .; \ + } +#else +#define KCFI_TRAPS +#endif +#endif + +/* * Read only Data */ #define RO_DATA(align) \ @@ -535,6 +563,8 @@ __stop___modver = .; \ } \ \ + KCFI_TRAPS \ + \ RO_EXCEPTION_TABLE \ NOTES \ BTF \ @@ -544,21 +574,6 @@ /* - * .text..L.cfi.jumptable.* contain Control-Flow Integrity (CFI) - * jump table entries. - */ -#ifdef CONFIG_CFI_CLANG -#define TEXT_CFI_JT \ - . = ALIGN(PMD_SIZE); \ - __cfi_jt_start = .; \ - *(.text..L.cfi.jumptable .text..L.cfi.jumptable.*) \ - . = ALIGN(PMD_SIZE); \ - __cfi_jt_end = .; -#else -#define TEXT_CFI_JT -#endif - -/* * Non-instrumentable text section */ #define NOINSTR_TEXT \ @@ -585,7 +600,6 @@ *(.text..refcount) \ *(.ref.text) \ *(.text.asan.* .text.tsan.*) \ - TEXT_CFI_JT \ MEM_KEEP(init.text*) \ MEM_KEEP(exit.text*) \ @@ -723,7 +737,6 @@ ACPI_PROBE_TABLE(irqchip) \ ACPI_PROBE_TABLE(timer) \ THERMAL_TABLE(governor) \ - DTPM_TABLE() \ EARLYCON_TABLE() \ LSM_TABLE() \ EARLY_LSM_TABLE() \ @@ -983,7 +996,6 @@ #ifdef CONFIG_AMD_MEM_ENCRYPT #define PERCPU_DECRYPTED_SECTION \ . = ALIGN(PAGE_SIZE); \ - *(.data..decrypted) \ *(.data..percpu..decrypted) \ . = ALIGN(PAGE_SIZE); #else @@ -1015,8 +1027,7 @@ * keep any .init_array.* sections. * https://bugs.llvm.org/show_bug.cgi?id=46478 */ -#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) || \ - defined(CONFIG_CFI_CLANG) +#if defined(CONFIG_GCOV_KERNEL) || defined(CONFIG_KASAN_GENERIC) || defined(CONFIG_KCSAN) # ifdef CONFIG_CONSTRUCTORS # define SANITIZER_DISCARDS \ *(.eh_frame) @@ -1031,6 +1042,7 @@ #define COMMON_DISCARDS \ SANITIZER_DISCARDS \ + PATCHABLE_DISCARDS \ *(.discard) \ *(.discard.*) \ *(.modinfo) \ diff --git a/include/asm-generic/xor.h b/include/asm-generic/xor.h index b62a2a56a4d4..44509d48fca2 100644 --- a/include/asm-generic/xor.h +++ b/include/asm-generic/xor.h @@ -8,7 +8,8 @@ #include <linux/prefetch.h> static void -xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_8regs_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8; @@ -27,8 +28,9 @@ xor_8regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_8regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_8regs_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8; @@ -48,8 +50,10 @@ xor_8regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_8regs_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8; @@ -70,8 +74,11 @@ xor_8regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_8regs_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8; @@ -93,7 +100,8 @@ xor_8regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_32regs_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8; @@ -129,8 +137,9 @@ xor_32regs_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_32regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_32regs_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8; @@ -175,8 +184,10 @@ xor_32regs_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_32regs_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8; @@ -230,8 +241,11 @@ xor_32regs_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_32regs_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8; @@ -294,7 +308,8 @@ xor_32regs_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_8regs_p_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8 - 1; prefetchw(p1); @@ -320,8 +335,9 @@ xor_8regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_8regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_8regs_p_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8 - 1; prefetchw(p1); @@ -350,8 +366,10 @@ xor_8regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_8regs_p_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -384,8 +402,11 @@ xor_8regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_8regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_8regs_p_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -421,7 +442,8 @@ xor_8regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) +xor_32regs_p_2(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -466,8 +488,9 @@ xor_32regs_p_2(unsigned long bytes, unsigned long *p1, unsigned long *p2) } static void -xor_32regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3) +xor_32regs_p_3(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -523,8 +546,10 @@ xor_32regs_p_3(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4) +xor_32regs_p_4(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4) { long lines = bytes / (sizeof (long)) / 8 - 1; @@ -591,8 +616,11 @@ xor_32regs_p_4(unsigned long bytes, unsigned long *p1, unsigned long *p2, } static void -xor_32regs_p_5(unsigned long bytes, unsigned long *p1, unsigned long *p2, - unsigned long *p3, unsigned long *p4, unsigned long *p5) +xor_32regs_p_5(unsigned long bytes, unsigned long * __restrict p1, + const unsigned long * __restrict p2, + const unsigned long * __restrict p3, + const unsigned long * __restrict p4, + const unsigned long * __restrict p5) { long lines = bytes / (sizeof (long)) / 8 - 1; |