asm-generic: unaligned always use struct helpers

As found by Vineet Gupta and Linus Torvalds, gcc has somewhat unexpected
behavior when faced with overlapping unaligned pointers. The kernel's
unaligned/access-ok.h header technically invokes undefined behavior
that happens to usually work on the architectures using it, but if the
compiler optimizes code based on the assumption that undefined behavior
doesn't happen, it can create output that actually causes data corruption.

A related problem was previously found on 32-bit ARMv7, where most
instructions can be used on unaligned data, but 64-bit ldrd/strd causes
an exception. The workaround was to always use the unaligned/le_struct.h
helper instead of unaligned/access-ok.h, in commit 1cce91df ("ARM:
8715/1: add a private asm/unaligned.h").

The same solution should work on all other architectures as well, so
remove the access-ok.h variant and use the other one unconditionally on
all architectures, picking either the big-endian or little-endian version.

With this, the arm specific header can be removed as well, and the
only file including linux/unaligned/access_ok.h gets moved to including
the normal file.

Fortunately, this made almost no difference to the object code produced
by gcc-11. On x86, s390, powerpc, and arc, the resulting binary appears
to be identical to the previous version, while on arm64 and m68k there
are minimal differences that looks like an optimization pass went into
a different direction, usually using fewer stack spills on the new
version.
Signed-off-by: Arnd Bergmann <arnd@arndb.de>
Link: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100363

arch/arm/include/asm/unaligned.h

-#ifndef __ASM_ARM_UNALIGNED_H
-#define __ASM_ARM_UNALIGNED_H
-
-/*
- * We generally want to set CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS on ARMv6+,
- * but we don't want to use linux/unaligned/access_ok.h since that can lead
- * to traps on unaligned stm/ldm or strd/ldrd.
- */
-#include <asm/byteorder.h>
-
-#if defined(__LITTLE_ENDIAN)
-# include <linux/unaligned/le_struct.h>
-# include <linux/unaligned/generic.h>
-# define get_unaligned	__get_unaligned_le
-# define put_unaligned	__put_unaligned_le
-#elif defined(__BIG_ENDIAN)
-# include <linux/unaligned/be_struct.h>
-# include <linux/unaligned/generic.h>
-# define get_unaligned	__get_unaligned_be
-# define put_unaligned	__put_unaligned_be
-#else
-# error need to define endianess
-#endif
-
-#endif /* __ASM_ARM_UNALIGNED_H */

arch/mips/crypto/crc32-mips.c

@@ -8,13 +8,13 @@
  * Copyright (C) 2018 MIPS Tech, LLC
  */
 
-#include <linux/unaligned/access_ok.h>
 #include <linux/cpufeature.h>
 #include <linux/init.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/string.h>
 #include <asm/mipsregs.h>
+#include <asm/unaligned.h>
 
 #include <crypto/internal/hash.h>
 

include/asm-generic/unaligned.h

@@ -8,22 +8,13 @@
  */
 #include <asm/byteorder.h>
 
-/* Set by the arch if it can handle unaligned accesses in hardware. */
-#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-# include <linux/unaligned/access_ok.h>
-#endif
-
 #if defined(__LITTLE_ENDIAN)
-# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#  include <linux/unaligned/le_struct.h>
-# endif
+# include <linux/unaligned/le_struct.h>
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_le
 # define put_unaligned	__put_unaligned_le
 #elif defined(__BIG_ENDIAN)
-# ifndef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
-#  include <linux/unaligned/be_struct.h>
-# endif
+# include <linux/unaligned/be_struct.h>
 # include <linux/unaligned/generic.h>
 # define get_unaligned	__get_unaligned_be
 # define put_unaligned	__put_unaligned_be

include/linux/unaligned/access_ok.h

-/* SPDX-License-Identifier: GPL-2.0 */
-#ifndef _LINUX_UNALIGNED_ACCESS_OK_H
-#define _LINUX_UNALIGNED_ACCESS_OK_H
-
-#include <linux/kernel.h>
-#include <asm/byteorder.h>
-
-static __always_inline u16 get_unaligned_le16(const void *p)
-{
-	return le16_to_cpup((__le16 *)p);
-}
-
-static __always_inline u32 get_unaligned_le32(const void *p)
-{
-	return le32_to_cpup((__le32 *)p);
-}
-
-static __always_inline u64 get_unaligned_le64(const void *p)
-{
-	return le64_to_cpup((__le64 *)p);
-}
-
-static __always_inline u16 get_unaligned_be16(const void *p)
-{
-	return be16_to_cpup((__be16 *)p);
-}
-
-static __always_inline u32 get_unaligned_be32(const void *p)
-{
-	return be32_to_cpup((__be32 *)p);
-}
-
-static __always_inline u64 get_unaligned_be64(const void *p)
-{
-	return be64_to_cpup((__be64 *)p);
-}
-
-static __always_inline void put_unaligned_le16(u16 val, void *p)
-{
-	*((__le16 *)p) = cpu_to_le16(val);
-}
-
-static __always_inline void put_unaligned_le32(u32 val, void *p)
-{
-	*((__le32 *)p) = cpu_to_le32(val);
-}
-
-static __always_inline void put_unaligned_le64(u64 val, void *p)
-{
-	*((__le64 *)p) = cpu_to_le64(val);
-}
-
-static __always_inline void put_unaligned_be16(u16 val, void *p)
-{
-	*((__be16 *)p) = cpu_to_be16(val);
-}
-
-static __always_inline void put_unaligned_be32(u32 val, void *p)
-{
-	*((__be32 *)p) = cpu_to_be32(val);
-}
-
-static __always_inline void put_unaligned_be64(u64 val, void *p)
-{
-	*((__be64 *)p) = cpu_to_be64(val);
-}
-
-#endif /* _LINUX_UNALIGNED_ACCESS_OK_H */