crypto: memneq - avoid implicit unaligned accesses

The C standard does not support dereferencing pointers that are not
aligned with respect to the pointed-to type, and doing so is technically
undefined behavior, even if the underlying hardware supports it.

This means that conditionally dereferencing such pointers based on
whether CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y is not the right thing
to do, and actually results in alignment faults on ARM, which are fixed
up on a slow path. Instead, we should use the unaligned accessors in
such cases: on architectures that don't care about alignment, they will
result in identical codegen whereas, e.g., codegen on ARM will avoid
doubleword loads and stores but use ordinary ones, which are able to
tolerate misalignment.

Link: https://lore.kernel.org/linux-crypto/CAHk-=wiKkdYLY0bv+nXrcJz3NH9mAqPAafX7PpW5EwVtxsEu7Q@mail.gmail.com/Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Reviewed-by: Arnd Bergmann <arnd@arndb.de>
Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

crypto/memneq.c

@@ -60,6 +60,7 @@
  */
 
 #include <crypto/algapi.h>
+#include <asm/unaligned.h>
 
 #ifndef __HAVE_ARCH_CRYPTO_MEMNEQ
 
@@ -71,7 +72,8 @@ __crypto_memneq_generic(const void *a, const void *b, size_t size)
 
 #if defined(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)
 	while (size >= sizeof(unsigned long)) {
-		neq |= *(unsigned long *)a ^ *(unsigned long *)b;
+		neq |= get_unaligned((unsigned long *)a) ^
+		       get_unaligned((unsigned long *)b);
 		OPTIMIZER_HIDE_VAR(neq);
 		a += sizeof(unsigned long);
 		b += sizeof(unsigned long);
@@ -95,18 +97,24 @@ static inline unsigned long __crypto_memneq_16(const void *a, const void *b)
 
 #ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
 	if (sizeof(unsigned long) == 8) {
-		neq |= *(unsigned long *)(a)   ^ *(unsigned long *)(b);
+		neq |= get_unaligned((unsigned long *)a) ^
+		       get_unaligned((unsigned long *)b);
 		OPTIMIZER_HIDE_VAR(neq);
-		neq |= *(unsigned long *)(a+8) ^ *(unsigned long *)(b+8);
+		neq |= get_unaligned((unsigned long *)(a + 8)) ^
+		       get_unaligned((unsigned long *)(b + 8));
 		OPTIMIZER_HIDE_VAR(neq);
 	} else if (sizeof(unsigned int) == 4) {
-		neq |= *(unsigned int *)(a)    ^ *(unsigned int *)(b);
+		neq |= get_unaligned((unsigned int *)a) ^
+		       get_unaligned((unsigned int *)b);
 		OPTIMIZER_HIDE_VAR(neq);
-		neq |= *(unsigned int *)(a+4)  ^ *(unsigned int *)(b+4);
+		neq |= get_unaligned((unsigned int *)(a + 4)) ^
+		       get_unaligned((unsigned int *)(b + 4));
 		OPTIMIZER_HIDE_VAR(neq);
-		neq |= *(unsigned int *)(a+8)  ^ *(unsigned int *)(b+8);
+		neq |= get_unaligned((unsigned int *)(a + 8)) ^
+		       get_unaligned((unsigned int *)(b + 8));
 		OPTIMIZER_HIDE_VAR(neq);
-		neq |= *(unsigned int *)(a+12) ^ *(unsigned int *)(b+12);
+		neq |= get_unaligned((unsigned int *)(a + 12)) ^
+		       get_unaligned((unsigned int *)(b + 12));
 		OPTIMIZER_HIDE_VAR(neq);
 	} else
 #endif /* CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS */