[PATCH v2] crypto: crypto_xor - use helpers for unaligned accesses

[Ard Biesheuvel <ardb@xxxxxxxxxx>]

Dereferencing a misaligned pointer is undefined behavior in C, and may
result in codegen on architectures such as ARM that trigger alignments
traps and expensive fixups in software.

Instead, use the get_aligned()/put_aligned() accessors, which are cheap
or even completely free when CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS=y.

In the converse case, the prior alignment checks ensure that the casts
are safe, and so no unaligned accessors are necessary.

Signed-off-by: Ard Biesheuvel <ardb@xxxxxxxxxx>
---
v2: fix issue in crypto_xor_cpy()

 crypto/algapi.c         | 24 +++++++++++++++++---
 include/crypto/algapi.h | 10 ++++++--
 2 files changed, 29 insertions(+), 5 deletions(-)

diff --git a/crypto/algapi.c b/crypto/algapi.c
index 9f15e11f5d73..a6a10f2ee0dc 100644
--- a/crypto/algapi.c
+++ b/crypto/algapi.c
@@ -1008,7 +1008,13 @@ void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len)
 	}
 
 	while (IS_ENABLED(CONFIG_64BIT) && len >= 8 && !(relalign & 7)) {
-		*(u64 *)dst = *(u64 *)src1 ^  *(u64 *)src2;
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u64 l = get_unaligned((u64 *)src1) ^
+				get_unaligned((u64 *)src2);
+			put_unaligned(l, (u64 *)dst);
+		} else {
+			*(u64 *)dst = *(u64 *)src1 ^ *(u64 *)src2;
+		}
 		dst += 8;
 		src1 += 8;
 		src2 += 8;
@@ -1016,7 +1022,13 @@ void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len)
 	}
 
 	while (len >= 4 && !(relalign & 3)) {
-		*(u32 *)dst = *(u32 *)src1 ^ *(u32 *)src2;
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u32 l = get_unaligned((u32 *)src1) ^
+				get_unaligned((u32 *)src2);
+			put_unaligned(l, (u32 *)dst);
+		} else {
+			*(u32 *)dst = *(u32 *)src1 ^ *(u32 *)src2;
+		}
 		dst += 4;
 		src1 += 4;
 		src2 += 4;
@@ -1024,7 +1036,13 @@ void __crypto_xor(u8 *dst, const u8 *src1, const u8 *src2, unsigned int len)
 	}
 
 	while (len >= 2 && !(relalign & 1)) {
-		*(u16 *)dst = *(u16 *)src1 ^ *(u16 *)src2;
+		if (IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) {
+			u16 l = get_unaligned((u16 *)src1) ^
+				get_unaligned((u16 *)src2);
+			put_unaligned(l, (u16 *)dst);
+		} else {
+			*(u16 *)dst = *(u16 *)src1 ^ *(u16 *)src2;
+		}
 		dst += 2;
 		src1 += 2;
 		src2 += 2;
diff --git a/include/crypto/algapi.h b/include/crypto/algapi.h
index f76ec723ceae..f50c5d1725da 100644
--- a/include/crypto/algapi.h
+++ b/include/crypto/algapi.h
@@ -13,6 +13,8 @@
 #include <linux/list.h>
 #include <linux/types.h>
 
+#include <asm/unaligned.h>
+
 /*
  * Maximum values for blocksize and alignmask, used to allocate
  * static buffers that are big enough for any combination of
@@ -154,9 +156,11 @@ static inline void crypto_xor(u8 *dst, const u8 *src, unsigned int size)
 	    (size % sizeof(unsigned long)) == 0) {
 		unsigned long *d = (unsigned long *)dst;
 		unsigned long *s = (unsigned long *)src;
+		unsigned long l;
 
 		while (size > 0) {
-			*d++ ^= *s++;
+			l = get_unaligned(d) ^ get_unaligned(s++);
+			put_unaligned(l, d++);
 			size -= sizeof(unsigned long);
 		}
 	} else {
@@ -173,9 +177,11 @@ static inline void crypto_xor_cpy(u8 *dst, const u8 *src1, const u8 *src2,
 		unsigned long *d = (unsigned long *)dst;
 		unsigned long *s1 = (unsigned long *)src1;
 		unsigned long *s2 = (unsigned long *)src2;
+		unsigned long l;
 
 		while (size > 0) {
-			*d++ = *s1++ ^ *s2++;
+			l = get_unaligned(s1++) ^ get_unaligned(s2++);
+			put_unaligned(l, d++);
 			size -= sizeof(unsigned long);
 		}
 	} else {
-- 
2.30.2