diff options
Diffstat (limited to 'include/linux/compiler.h')
| -rw-r--r-- | include/linux/compiler.h | 266 |
1 files changed, 160 insertions, 106 deletions
diff --git a/include/linux/compiler.h b/include/linux/compiler.h index cce2c92567b5..f09ebbf16562 100644 --- a/include/linux/compiler.h +++ b/include/linux/compiler.h @@ -120,12 +120,65 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, /* Annotate a C jump table to allow objtool to follow the code flow */ #define __annotate_jump_table __section(.rodata..c_jump_table) +#ifdef CONFIG_DEBUG_ENTRY +/* Begin/end of an instrumentation safe region */ +#define instrumentation_begin() ({ \ + asm volatile("%c0:\n\t" \ + ".pushsection .discard.instr_begin\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) + +/* + * Because instrumentation_{begin,end}() can nest, objtool validation considers + * _begin() a +1 and _end() a -1 and computes a sum over the instructions. + * When the value is greater than 0, we consider instrumentation allowed. + * + * There is a problem with code like: + * + * noinstr void foo() + * { + * instrumentation_begin(); + * ... + * if (cond) { + * instrumentation_begin(); + * ... + * instrumentation_end(); + * } + * bar(); + * instrumentation_end(); + * } + * + * If instrumentation_end() would be an empty label, like all the other + * annotations, the inner _end(), which is at the end of a conditional block, + * would land on the instruction after the block. + * + * If we then consider the sum of the !cond path, we'll see that the call to + * bar() is with a 0-value, even though, we meant it to happen with a positive + * value. + * + * To avoid this, have _end() be a NOP instruction, this ensures it will be + * part of the condition block and does not escape. + */ +#define instrumentation_end() ({ \ + asm volatile("%c0: nop\n\t" \ + ".pushsection .discard.instr_end\n\t" \ + ".long %c0b - .\n\t" \ + ".popsection\n\t" : : "i" (__COUNTER__)); \ +}) +#endif /* CONFIG_DEBUG_ENTRY */ + #else #define annotate_reachable() #define annotate_unreachable() #define __annotate_jump_table #endif +#ifndef instrumentation_begin +#define instrumentation_begin() do { } while(0) +#define instrumentation_end() do { } while(0) +#endif + #ifndef ASM_UNREACHABLE # define ASM_UNREACHABLE #endif @@ -177,28 +230,93 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, # define __UNIQUE_ID(prefix) __PASTE(__PASTE(__UNIQUE_ID_, prefix), __LINE__) #endif -#include <uapi/linux/types.h> +/* + * Prevent the compiler from merging or refetching reads or writes. The + * compiler is also forbidden from reordering successive instances of + * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some + * particular ordering. One way to make the compiler aware of ordering is to + * put the two invocations of READ_ONCE or WRITE_ONCE in different C + * statements. + * + * These two macros will also work on aggregate data types like structs or + * unions. + * + * Their two major use cases are: (1) Mediating communication between + * process-level code and irq/NMI handlers, all running on the same CPU, + * and (2) Ensuring that the compiler does not fold, spindle, or otherwise + * mutilate accesses that either do not require ordering or that interact + * with an explicit memory barrier or atomic instruction that provides the + * required ordering. + */ +#include <asm/barrier.h> +#include <linux/kasan-checks.h> #include <linux/kcsan-checks.h> -#define __READ_ONCE_SIZE \ +/** + * data_race - mark an expression as containing intentional data races + * + * This data_race() macro is useful for situations in which data races + * should be forgiven. One example is diagnostic code that accesses + * shared variables but is not a part of the core synchronization design. + * + * This macro *does not* affect normal code generation, but is a hint + * to tooling that data races here are to be ignored. + */ +#define data_race(expr) \ ({ \ - switch (size) { \ - case 1: *(__u8 *)res = *(volatile __u8 *)p; break; \ - case 2: *(__u16 *)res = *(volatile __u16 *)p; break; \ - case 4: *(__u32 *)res = *(volatile __u32 *)p; break; \ - case 8: *(__u64 *)res = *(volatile __u64 *)p; break; \ - default: \ - barrier(); \ - __builtin_memcpy((void *)res, (const void *)p, size); \ - barrier(); \ - } \ + __kcsan_disable_current(); \ + ({ \ + __unqual_scalar_typeof(({ expr; })) __v = ({ expr; }); \ + __kcsan_enable_current(); \ + __v; \ + }); \ }) +/* + * Use __READ_ONCE() instead of READ_ONCE() if you do not require any + * atomicity or dependency ordering guarantees. Note that this may result + * in tears! + */ +#define __READ_ONCE(x) (*(const volatile __unqual_scalar_typeof(x) *)&(x)) + +#define __READ_ONCE_SCALAR(x) \ +({ \ + typeof(x) *__xp = &(x); \ + __unqual_scalar_typeof(x) __x = data_race(__READ_ONCE(*__xp)); \ + kcsan_check_atomic_read(__xp, sizeof(*__xp)); \ + smp_read_barrier_depends(); \ + (typeof(x))__x; \ +}) + +#define READ_ONCE(x) \ +({ \ + compiletime_assert_rwonce_type(x); \ + __READ_ONCE_SCALAR(x); \ +}) + +#define __WRITE_ONCE(x, val) \ +do { \ + *(volatile typeof(x) *)&(x) = (val); \ +} while (0) + +#define __WRITE_ONCE_SCALAR(x, val) \ +do { \ + typeof(x) *__xp = &(x); \ + kcsan_check_atomic_write(__xp, sizeof(*__xp)); \ + data_race(({ __WRITE_ONCE(*__xp, val); 0; })); \ +} while (0) + +#define WRITE_ONCE(x, val) \ +do { \ + compiletime_assert_rwonce_type(x); \ + __WRITE_ONCE_SCALAR(x, val); \ +} while (0) + #ifdef CONFIG_KASAN /* - * We can't declare function 'inline' because __no_sanitize_address confilcts + * We can't declare function 'inline' because __no_sanitize_address conflicts * with inlining. Attempt to inline it may cause a build failure. - * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 + * https://gcc.gnu.org/bugzilla/show_bug.cgi?id=67368 * '__maybe_unused' allows us to avoid defined-but-not-used warnings. */ # define __no_kasan_or_inline __no_sanitize_address notrace __maybe_unused @@ -225,78 +343,26 @@ void ftrace_likely_update(struct ftrace_likely_data *f, int val, #define __no_sanitize_or_inline __always_inline #endif -static __no_kcsan_or_inline -void __read_once_size(const volatile void *p, void *res, int size) -{ - kcsan_check_atomic_read(p, size); - __READ_ONCE_SIZE; -} - static __no_sanitize_or_inline -void __read_once_size_nocheck(const volatile void *p, void *res, int size) +unsigned long __read_once_word_nocheck(const void *addr) { - __READ_ONCE_SIZE; -} - -static __no_kcsan_or_inline -void __write_once_size(volatile void *p, void *res, int size) -{ - kcsan_check_atomic_write(p, size); - - switch (size) { - case 1: *(volatile __u8 *)p = *(__u8 *)res; break; - case 2: *(volatile __u16 *)p = *(__u16 *)res; break; - case 4: *(volatile __u32 *)p = *(__u32 *)res; break; - case 8: *(volatile __u64 *)p = *(__u64 *)res; break; - default: - barrier(); - __builtin_memcpy((void *)p, (const void *)res, size); - barrier(); - } + return __READ_ONCE(*(unsigned long *)addr); } /* - * Prevent the compiler from merging or refetching reads or writes. The - * compiler is also forbidden from reordering successive instances of - * READ_ONCE and WRITE_ONCE, but only when the compiler is aware of some - * particular ordering. One way to make the compiler aware of ordering is to - * put the two invocations of READ_ONCE or WRITE_ONCE in different C - * statements. - * - * These two macros will also work on aggregate data types like structs or - * unions. If the size of the accessed data type exceeds the word size of - * the machine (e.g., 32 bits or 64 bits) READ_ONCE() and WRITE_ONCE() will - * fall back to memcpy(). There's at least two memcpy()s: one for the - * __builtin_memcpy() and then one for the macro doing the copy of variable - * - '__u' allocated on the stack. - * - * Their two major use cases are: (1) Mediating communication between - * process-level code and irq/NMI handlers, all running on the same CPU, - * and (2) Ensuring that the compiler does not fold, spindle, or otherwise - * mutilate accesses that either do not require ordering or that interact - * with an explicit memory barrier or atomic instruction that provides the - * required ordering. + * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need to load a + * word from memory atomically but without telling KASAN/KCSAN. This is + * usually used by unwinding code when walking the stack of a running process. */ -#include <asm/barrier.h> -#include <linux/kasan-checks.h> - -#define __READ_ONCE(x, check) \ +#define READ_ONCE_NOCHECK(x) \ ({ \ - union { typeof(x) __val; char __c[1]; } __u; \ - if (check) \ - __read_once_size(&(x), __u.__c, sizeof(x)); \ - else \ - __read_once_size_nocheck(&(x), __u.__c, sizeof(x)); \ - smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \ - __u.__val; \ + unsigned long __x; \ + compiletime_assert(sizeof(x) == sizeof(__x), \ + "Unsupported access size for READ_ONCE_NOCHECK()."); \ + __x = __read_once_word_nocheck(&(x)); \ + smp_read_barrier_depends(); \ + (typeof(x))__x; \ }) -#define READ_ONCE(x) __READ_ONCE(x, 1) - -/* - * Use READ_ONCE_NOCHECK() instead of READ_ONCE() if you need - * to hide memory access from KASAN. - */ -#define READ_ONCE_NOCHECK(x) __READ_ONCE(x, 0) static __no_kasan_or_inline unsigned long read_word_at_a_time(const void *addr) @@ -305,34 +371,6 @@ unsigned long read_word_at_a_time(const void *addr) return *(unsigned long *)addr; } -#define WRITE_ONCE(x, val) \ -({ \ - union { typeof(x) __val; char __c[1]; } __u = \ - { .__val = (__force typeof(x)) (val) }; \ - __write_once_size(&(x), __u.__c, sizeof(x)); \ - __u.__val; \ -}) - -/** - * data_race - mark an expression as containing intentional data races - * - * This data_race() macro is useful for situations in which data races - * should be forgiven. One example is diagnostic code that accesses - * shared variables but is not a part of the core synchronization design. - * - * This macro *does not* affect normal code generation, but is a hint - * to tooling that data races here are to be ignored. - */ -#define data_race(expr) \ - ({ \ - typeof(({ expr; })) __val; \ - kcsan_disable_current(); \ - __val = ({ expr; }); \ - kcsan_enable_current(); \ - __val; \ - }) -#else - #endif /* __KERNEL__ */ /* @@ -397,7 +435,23 @@ static inline void *offset_to_ptr(const int *off) compiletime_assert(__native_word(t), \ "Need native word sized stores/loads for atomicity.") +/* + * Yes, this permits 64-bit accesses on 32-bit architectures. These will + * actually be atomic in some cases (namely Armv7 + LPAE), but for others we + * rely on the access being split into 2x32-bit accesses for a 32-bit quantity + * (e.g. a virtual address) and a strong prevailing wind. + */ +#define compiletime_assert_rwonce_type(t) \ + compiletime_assert(__native_word(t) || sizeof(t) == sizeof(long long), \ + "Unsupported access size for {READ,WRITE}_ONCE().") + /* &a[0] degrades to a pointer: a different type from an array */ #define __must_be_array(a) BUILD_BUG_ON_ZERO(__same_type((a), &(a)[0])) +/* + * This is needed in functions which generate the stack canary, see + * arch/x86/kernel/smpboot.c::start_secondary() for an example. + */ +#define prevent_tail_call_optimization() mb() + #endif /* __LINUX_COMPILER_H */ |