crypto: arm/aes-ce - remove cra_alignmask

Remove the unnecessary alignmask: it is much more efficient to deal with
the misalignment in the core algorithm than relying on the crypto API to
copy the data to a suitably aligned buffer.
Signed-off-by: Ard Biesheuvel <ard.biesheuvel@linaro.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

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

@@ -169,19 +169,19 @@ ENTRY(ce_aes_ecb_encrypt)
 .Lecbencloop3x:
 	subs		r4, r4, #3
 	bmi		.Lecbenc1x
-	vld1.8		{q0-q1}, [r1, :64]!
-	vld1.8		{q2}, [r1, :64]!
+	vld1.8		{q0-q1}, [r1]!
+	vld1.8		{q2}, [r1]!
 	bl		aes_encrypt_3x
-	vst1.8		{q0-q1}, [r0, :64]!
-	vst1.8		{q2}, [r0, :64]!
+	vst1.8		{q0-q1}, [r0]!
+	vst1.8		{q2}, [r0]!
 	b		.Lecbencloop3x
 .Lecbenc1x:
 	adds		r4, r4, #3
 	beq		.Lecbencout
 .Lecbencloop:
-	vld1.8		{q0}, [r1, :64]!
+	vld1.8		{q0}, [r1]!
 	bl		aes_encrypt
-	vst1.8		{q0}, [r0, :64]!
+	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	bne		.Lecbencloop
 .Lecbencout:
@@ -195,19 +195,19 @@ ENTRY(ce_aes_ecb_decrypt)
 .Lecbdecloop3x:
 	subs		r4, r4, #3
 	bmi		.Lecbdec1x
-	vld1.8		{q0-q1}, [r1, :64]!
-	vld1.8		{q2}, [r1, :64]!
+	vld1.8		{q0-q1}, [r1]!
+	vld1.8		{q2}, [r1]!
 	bl		aes_decrypt_3x
-	vst1.8		{q0-q1}, [r0, :64]!
-	vst1.8		{q2}, [r0, :64]!
+	vst1.8		{q0-q1}, [r0]!
+	vst1.8		{q2}, [r0]!
 	b		.Lecbdecloop3x
 .Lecbdec1x:
 	adds		r4, r4, #3
 	beq		.Lecbdecout
 .Lecbdecloop:
-	vld1.8		{q0}, [r1, :64]!
+	vld1.8		{q0}, [r1]!
 	bl		aes_decrypt
-	vst1.8		{q0}, [r0, :64]!
+	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	bne		.Lecbdecloop
 .Lecbdecout:
@@ -226,10 +226,10 @@ ENTRY(ce_aes_cbc_encrypt)
 	vld1.8		{q0}, [r5]
 	prepare_key	r2, r3
 .Lcbcencloop:
-	vld1.8		{q1}, [r1, :64]!	@ get next pt block
+	vld1.8		{q1}, [r1]!		@ get next pt block
 	veor		q0, q0, q1		@ ..and xor with iv
 	bl		aes_encrypt
-	vst1.8		{q0}, [r0, :64]!
+	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	bne		.Lcbcencloop
 	vst1.8		{q0}, [r5]
@@ -244,8 +244,8 @@ ENTRY(ce_aes_cbc_decrypt)
 .Lcbcdecloop3x:
 	subs		r4, r4, #3
 	bmi		.Lcbcdec1x
-	vld1.8		{q0-q1}, [r1, :64]!
-	vld1.8		{q2}, [r1, :64]!
+	vld1.8		{q0-q1}, [r1]!
+	vld1.8		{q2}, [r1]!
 	vmov		q3, q0
 	vmov		q4, q1
 	vmov		q5, q2
@@ -254,19 +254,19 @@ ENTRY(ce_aes_cbc_decrypt)
 	veor		q1, q1, q3
 	veor		q2, q2, q4
 	vmov		q6, q5
-	vst1.8		{q0-q1}, [r0, :64]!
-	vst1.8		{q2}, [r0, :64]!
+	vst1.8		{q0-q1}, [r0]!
+	vst1.8		{q2}, [r0]!
 	b		.Lcbcdecloop3x
 .Lcbcdec1x:
 	adds		r4, r4, #3
 	beq		.Lcbcdecout
 	vmov		q15, q14		@ preserve last round key
 .Lcbcdecloop:
-	vld1.8		{q0}, [r1, :64]!	@ get next ct block
+	vld1.8		{q0}, [r1]!		@ get next ct block
 	veor		q14, q15, q6		@ combine prev ct with last key
 	vmov		q6, q0
 	bl		aes_decrypt
-	vst1.8		{q0}, [r0, :64]!
+	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	bne		.Lcbcdecloop
 .Lcbcdecout:
@@ -300,15 +300,15 @@ ENTRY(ce_aes_ctr_encrypt)
 	rev		ip, r6
 	add		r6, r6, #1
 	vmov		s11, ip
-	vld1.8		{q3-q4}, [r1, :64]!
-	vld1.8		{q5}, [r1, :64]!
+	vld1.8		{q3-q4}, [r1]!
+	vld1.8		{q5}, [r1]!
 	bl		aes_encrypt_3x
 	veor		q0, q0, q3
 	veor		q1, q1, q4
 	veor		q2, q2, q5
 	rev		ip, r6
-	vst1.8		{q0-q1}, [r0, :64]!
-	vst1.8		{q2}, [r0, :64]!
+	vst1.8		{q0-q1}, [r0]!
+	vst1.8		{q2}, [r0]!
 	vmov		s27, ip
 	b		.Lctrloop3x
 .Lctr1x:
@@ -318,10 +318,10 @@ ENTRY(ce_aes_ctr_encrypt)
 	vmov		q0, q6
 	bl		aes_encrypt
 	subs		r4, r4, #1
-	bmi		.Lctrhalfblock		@ blocks < 0 means 1/2 block
-	vld1.8		{q3}, [r1, :64]!
+	bmi		.Lctrtailblock		@ blocks < 0 means tail block
+	vld1.8		{q3}, [r1]!
 	veor		q3, q0, q3
-	vst1.8		{q3}, [r0, :64]!
+	vst1.8		{q3}, [r0]!
 
 	adds		r6, r6, #1		@ increment BE ctr
 	rev		ip, r6
@@ -333,10 +333,8 @@ ENTRY(ce_aes_ctr_encrypt)
 	vst1.8		{q6}, [r5]
 	pop		{r4-r6, pc}
 
-.Lctrhalfblock:
-	vld1.8		{d1}, [r1, :64]
-	veor		d0, d0, d1
-	vst1.8		{d0}, [r0, :64]
+.Lctrtailblock:
+	vst1.8		{q0}, [r0, :64]		@ return just the key stream
 	pop		{r4-r6, pc}
 
 .Lctrcarry:
@@ -405,8 +403,8 @@ ENTRY(ce_aes_xts_encrypt)
 .Lxtsenc3x:
 	subs		r4, r4, #3
 	bmi		.Lxtsenc1x
-	vld1.8		{q0-q1}, [r1, :64]!	@ get 3 pt blocks
-	vld1.8		{q2}, [r1, :64]!
+	vld1.8		{q0-q1}, [r1]!		@ get 3 pt blocks
+	vld1.8		{q2}, [r1]!
 	next_tweak	q4, q3, q7, q6
 	veor		q0, q0, q3
 	next_tweak	q5, q4, q7, q6
@@ -416,8 +414,8 @@ ENTRY(ce_aes_xts_encrypt)
 	veor		q0, q0, q3
 	veor		q1, q1, q4
 	veor		q2, q2, q5
-	vst1.8		{q0-q1}, [r0, :64]!	@ write 3 ct blocks
-	vst1.8		{q2}, [r0, :64]!
+	vst1.8		{q0-q1}, [r0]!		@ write 3 ct blocks
+	vst1.8		{q2}, [r0]!
 	vmov		q3, q5
 	teq		r4, #0
 	beq		.Lxtsencout
@@ -426,11 +424,11 @@ ENTRY(ce_aes_xts_encrypt)
 	adds		r4, r4, #3
 	beq		.Lxtsencout
 .Lxtsencloop:
-	vld1.8		{q0}, [r1, :64]!
+	vld1.8		{q0}, [r1]!
 	veor		q0, q0, q3
 	bl		aes_encrypt
 	veor		q0, q0, q3
-	vst1.8		{q0}, [r0, :64]!
+	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	beq		.Lxtsencout
 	next_tweak	q3, q3, q7, q6
@@ -456,8 +454,8 @@ ENTRY(ce_aes_xts_decrypt)
 .Lxtsdec3x:
 	subs		r4, r4, #3
 	bmi		.Lxtsdec1x
-	vld1.8		{q0-q1}, [r1, :64]!	@ get 3 ct blocks
-	vld1.8		{q2}, [r1, :64]!
+	vld1.8		{q0-q1}, [r1]!		@ get 3 ct blocks
+	vld1.8		{q2}, [r1]!
 	next_tweak	q4, q3, q7, q6
 	veor		q0, q0, q3
 	next_tweak	q5, q4, q7, q6
@@ -467,8 +465,8 @@ ENTRY(ce_aes_xts_decrypt)
 	veor		q0, q0, q3
 	veor		q1, q1, q4
 	veor		q2, q2, q5
-	vst1.8		{q0-q1}, [r0, :64]!	@ write 3 pt blocks
-	vst1.8		{q2}, [r0, :64]!
+	vst1.8		{q0-q1}, [r0]!		@ write 3 pt blocks
+	vst1.8		{q2}, [r0]!
 	vmov		q3, q5
 	teq		r4, #0
 	beq		.Lxtsdecout
@@ -477,12 +475,12 @@ ENTRY(ce_aes_xts_decrypt)
 	adds		r4, r4, #3
 	beq		.Lxtsdecout
 .Lxtsdecloop:
-	vld1.8		{q0}, [r1, :64]!
+	vld1.8		{q0}, [r1]!
 	veor		q0, q0, q3
 	add		ip, r2, #32		@ 3rd round key
 	bl		aes_decrypt
 	veor		q0, q0, q3
-	vst1.8		{q0}, [r0, :64]!
+	vst1.8		{q0}, [r0]!
 	subs		r4, r4, #1
 	beq		.Lxtsdecout
 	next_tweak	q3, q3, q7, q6

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

@@ -278,14 +278,15 @@ static int ctr_encrypt(struct skcipher_request *req)
 		u8 *tsrc = walk.src.virt.addr;
 
 		/*
-		 * Minimum alignment is 8 bytes, so if nbytes is <= 8, we need
-		 * to tell aes_ctr_encrypt() to only read half a block.
+		 * Tell aes_ctr_encrypt() to process a tail block.
 		 */
-		blocks = (nbytes <= 8) ? -1 : 1;
+		blocks = -1;
 
-		ce_aes_ctr_encrypt(tail, tsrc, (u8 *)ctx->key_enc,
+		ce_aes_ctr_encrypt(tail, NULL, (u8 *)ctx->key_enc,
 				   num_rounds(ctx), blocks, walk.iv);
-		memcpy(tdst, tail, nbytes);
+		if (tdst != tsrc)
+			memcpy(tdst, tsrc, nbytes);
+		crypto_xor(tdst, tail, nbytes);
 		err = skcipher_walk_done(&walk, 0);
 	}
 	kernel_neon_end();
@@ -345,7 +346,6 @@ static struct skcipher_alg aes_algs[] = { {
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= AES_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-		.cra_alignmask		= 7,
 		.cra_module		= THIS_MODULE,
 	},
 	.min_keysize	= AES_MIN_KEY_SIZE,
@@ -361,7 +361,6 @@ static struct skcipher_alg aes_algs[] = { {
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= AES_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-		.cra_alignmask		= 7,
 		.cra_module		= THIS_MODULE,
 	},
 	.min_keysize	= AES_MIN_KEY_SIZE,
@@ -378,7 +377,6 @@ static struct skcipher_alg aes_algs[] = { {
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= 1,
 		.cra_ctxsize		= sizeof(struct crypto_aes_ctx),
-		.cra_alignmask		= 7,
 		.cra_module		= THIS_MODULE,
 	},
 	.min_keysize	= AES_MIN_KEY_SIZE,
@@ -396,7 +394,6 @@ static struct skcipher_alg aes_algs[] = { {
 		.cra_flags		= CRYPTO_ALG_INTERNAL,
 		.cra_blocksize		= AES_BLOCK_SIZE,
 		.cra_ctxsize		= sizeof(struct crypto_aes_xts_ctx),
-		.cra_alignmask		= 7,
 		.cra_module		= THIS_MODULE,
 	},
 	.min_keysize	= 2 * AES_MIN_KEY_SIZE,