linux/arch/arm64/include/asm/rwonce.h
Marco Elver bb0c99e08a arm64: Fix non-atomic __READ_ONCE() with CONFIG_LTO=y
The implementation of __READ_ONCE() under CONFIG_LTO=y incorrectly
qualified the fallback "once" access for types larger than 8 bytes,
which are not atomic but should still happen "once" and suppress common
compiler optimizations.

The cast `volatile typeof(__x)` applied the volatile qualifier to the
pointer type itself rather than the pointee. This created a volatile
pointer to a non-volatile type, which violated __READ_ONCE() semantics.

Fix this by casting to `volatile typeof(*__x) *`.

With a defconfig + LTO + debug options build, we see the following
functions to be affected:

	xen_manage_runstate_time (884 -> 944 bytes)
	xen_steal_clock (248 -> 340 bytes)
	  ^-- use __READ_ONCE() to load vcpu_runstate_info structs

Fixes: e35123d83e ("arm64: lto: Strengthen READ_ONCE() to acquire when CONFIG_LTO=y")
Cc: stable@vger.kernel.org
Reviewed-by: Boqun Feng <boqun@kernel.org>
Signed-off-by: Marco Elver <elver@google.com>
Tested-by: David Laight <david.laight.linux@gmail.com>
Signed-off-by: Will Deacon <will@kernel.org>
2026-02-02 15:40:54 +00:00

69 lines
1.8 KiB
C

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2020 Google LLC.
*/
#ifndef __ASM_RWONCE_H
#define __ASM_RWONCE_H
#if defined(CONFIG_LTO) && !defined(__ASSEMBLER__)
#include <linux/compiler_types.h>
#include <asm/alternative-macros.h>
#ifndef BUILD_VDSO
#define __LOAD_RCPC(sfx, regs...) \
ALTERNATIVE( \
"ldar" #sfx "\t" #regs, \
".arch_extension rcpc\n" \
"ldapr" #sfx "\t" #regs, \
ARM64_HAS_LDAPR)
/*
* When building with LTO, there is an increased risk of the compiler
* converting an address dependency headed by a READ_ONCE() invocation
* into a control dependency and consequently allowing for harmful
* reordering by the CPU.
*
* Ensure that such transformations are harmless by overriding the generic
* READ_ONCE() definition with one that provides RCpc acquire semantics
* when building with LTO.
*/
#define __READ_ONCE(x) \
({ \
typeof(&(x)) __x = &(x); \
int atomic = 1; \
union { __unqual_scalar_typeof(*__x) __val; char __c[1]; } __u; \
switch (sizeof(x)) { \
case 1: \
asm volatile(__LOAD_RCPC(b, %w0, %1) \
: "=r" (*(__u8 *)__u.__c) \
: "Q" (*__x) : "memory"); \
break; \
case 2: \
asm volatile(__LOAD_RCPC(h, %w0, %1) \
: "=r" (*(__u16 *)__u.__c) \
: "Q" (*__x) : "memory"); \
break; \
case 4: \
asm volatile(__LOAD_RCPC(, %w0, %1) \
: "=r" (*(__u32 *)__u.__c) \
: "Q" (*__x) : "memory"); \
break; \
case 8: \
asm volatile(__LOAD_RCPC(, %0, %1) \
: "=r" (*(__u64 *)__u.__c) \
: "Q" (*__x) : "memory"); \
break; \
default: \
atomic = 0; \
} \
atomic ? (typeof(*__x))__u.__val : (*(volatile typeof(*__x) *)__x);\
})
#endif /* !BUILD_VDSO */
#endif /* CONFIG_LTO && !__ASSEMBLER__ */
#include <asm-generic/rwonce.h>
#endif /* __ASM_RWONCE_H */