arm64: lto: Strengthen READ_ONCE() to acquire when CONFIG_LTO=y

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 acquire semantics when
building with LTO.
Acked-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Will Deacon <will@kernel.org>

arch/arm64/include/asm/rwonce.h

+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2020 Google LLC.
+ */
+#ifndef __ASM_RWONCE_H
+#define __ASM_RWONCE_H
+
+#ifdef CONFIG_LTO
+
+#include <linux/compiler_types.h>
+#include <asm/alternative-macros.h>
+
+#ifndef BUILD_VDSO
+
+#ifdef CONFIG_AS_HAS_LDAPR
+#define __LOAD_RCPC(sfx, regs...)					\
+	ALTERNATIVE(							\
+		"ldar"	#sfx "\t" #regs,				\
+		".arch_extension rcpc\n"				\
+		"ldapr"	#sfx "\t" #regs,				\
+	ARM64_HAS_LDAPR)
+#else
+#define __LOAD_RCPC(sfx, regs...)	"ldar" #sfx "\t" #regs
+#endif /* CONFIG_AS_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 */
+
+#include <asm-generic/rwonce.h>
+
+#endif	/* __ASM_RWONCE_H */

arch/arm64/kernel/vdso/Makefile

@@ -28,7 +28,7 @@ ldflags-y := -shared -nostdlib -soname=linux-vdso.so.1 --hash-style=sysv	\
 	     $(btildflags-y) -T
 
 ccflags-y := -fno-common -fno-builtin -fno-stack-protector -ffixed-x18
-ccflags-y += -DDISABLE_BRANCH_PROFILING
+ccflags-y += -DDISABLE_BRANCH_PROFILING -DBUILD_VDSO
 
 CFLAGS_REMOVE_vgettimeofday.o = $(CC_FLAGS_FTRACE) -Os $(CC_FLAGS_SCS) $(GCC_PLUGINS_CFLAGS)
 KASAN_SANITIZE			:= n

arch/arm64/kernel/vdso32/Makefile

@@ -48,7 +48,7 @@ cc32-as-instr = $(call try-run,\
 # As a result we set our own flags here.
 
 # KBUILD_CPPFLAGS and NOSTDINC_FLAGS from top-level Makefile
-VDSO_CPPFLAGS := -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include)
+VDSO_CPPFLAGS := -DBUILD_VDSO -D__KERNEL__ -nostdinc -isystem $(shell $(CC_COMPAT) -print-file-name=include)
 VDSO_CPPFLAGS += $(LINUXINCLUDE)
 
 # Common C and assembly flags

arch/arm64/kernel/vmlinux.lds.S

@@ -201,7 +201,7 @@ SECTIONS
 		INIT_CALLS
 		CON_INITCALL
 		INIT_RAM_FS
-		*(.init.rodata.* .init.bss)	/* from the EFI stub */
+		*(.init.altinstructions .init.rodata.* .init.bss)	/* from the EFI stub */
 	}
 	.exit.data : {
 		EXIT_DATA