crypto: arm/aes - don't use IV buffer to return final keystream block

The ARM bit sliced AES core code uses the IV buffer to pass the final
keystream block back to the glue code if the input is not a multiple of
the block size, so that the asm code does not have to deal with anything
except 16 byte blocks. This is done under the assumption that the outgoing
IV is meaningless anyway in this case, given that chaining is no longer
possible under these circumstances.

However, as it turns out, the CCM driver does expect the IV to retain
a value that is equal to the original IV except for the counter value,
and even interprets byte zero as a length indicator, which may result
in memory corruption if the IV is overwritten with something else.

So use a separate buffer to return the final keystream block.

Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/arm/crypto/aes-neonbs-core.S

@@ -779,14 +779,15 @@ ENDPROC(aesbs_cbc_decrypt)
 
 	/*
 	 * aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
-	 *		     int rounds, int blocks, u8 ctr[], bool final)
+	 *		     int rounds, int blocks, u8 ctr[], u8 final[])
 	 */
 ENTRY(aesbs_ctr_encrypt)
 	mov		ip, sp
 	push		{r4-r10, lr}
 
 	ldm		ip, {r5-r7}		// load args 4-6
-	add		r5, r5, r7		// one extra block if final == 1
+	teq		r7, #0
+	addne		r5, r5, #1		// one extra block if final != 0
 
 	vld1.8		{q0}, [r6]		// load counter
 	vrev32.8	q1, q0
@@ -865,19 +866,20 @@ ENTRY(aesbs_ctr_encrypt)
 	veor		q2, q2, q14
 	vst1.8		{q2}, [r0]!
 	teq		r4, #0			// skip last block if 'final'
-	W(bne)		4f
+	W(bne)		5f
 3:	veor		q5, q5, q15
 	vst1.8		{q5}, [r0]!
 
-	next_ctr	q0
+4:	next_ctr	q0
 
 	subs		r5, r5, #8
 	bgt		99b
 
-	vmov		q5, q0
-
-4:	vst1.8		{q5}, [r6]
+	vst1.8		{q0}, [r6]
 	pop		{r4-r10, pc}
+
+5:	vst1.8		{q5}, [r4]
+	b		4b
 ENDPROC(aesbs_ctr_encrypt)
 
 	.macro		next_tweak, out, in, const, tmp

arch/arm/crypto/aes-neonbs-glue.c

@@ -35,7 +35,7 @@ asmlinkage void aesbs_cbc_decrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]);
 
 asmlinkage void aesbs_ctr_encrypt(u8 out[], u8 const in[], u8 const rk[],
-				  int rounds, int blocks, u8 ctr[], bool final);
+				  int rounds, int blocks, u8 ctr[], u8 final[]);
 
 asmlinkage void aesbs_xts_encrypt(u8 out[], u8 const in[], u8 const rk[],
 				  int rounds, int blocks, u8 iv[]);
@@ -186,19 +186,20 @@ static int ctr_encrypt(struct skcipher_request *req)
 	struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
 	struct aesbs_ctx *ctx = crypto_skcipher_ctx(tfm);
 	struct skcipher_walk walk;
+	u8 buf[AES_BLOCK_SIZE];
 	int err;
 
 	err = skcipher_walk_virt(&walk, req, true);
 
 	kernel_neon_begin();
 	while (walk.nbytes > 0) {
 		unsigned int blocks = walk.nbytes / AES_BLOCK_SIZE;
-		bool final = (walk.total % AES_BLOCK_SIZE) != 0;
+		u8 *final = (walk.total % AES_BLOCK_SIZE) ? buf : NULL;
 
 		if (walk.nbytes < walk.total) {
 			blocks = round_down(blocks,
 					    walk.stride / AES_BLOCK_SIZE);
-			final = false;
+			final = NULL;
 		}
 
 		aesbs_ctr_encrypt(walk.dst.virt.addr, walk.src.virt.addr,
@@ -210,7 +211,7 @@ static int ctr_encrypt(struct skcipher_request *req)
 
 			if (dst != src)
 				memcpy(dst, src, walk.total % AES_BLOCK_SIZE);
-			crypto_xor(dst, walk.iv, walk.total % AES_BLOCK_SIZE);
+			crypto_xor(dst, final, walk.total % AES_BLOCK_SIZE);
 
 			err = skcipher_walk_done(&walk, 0);
 			break;