crypto: arm64/aes-ce - Simplify round key load sequence

Tweak the round key logic so that they can be loaded using a single
branchless sequence using overlapping loads. This is shorter and
simpler, and puts the conditional branches based on the key size further
apart, which might benefit microarchitectures that cannot record taken
branches at every instruction. For these branches, use test-bit-branch
instructions that don't clobber the condition flags.

Note that none of this has any impact on performance, positive or
otherwise (and the branch prediction benefit would only benefit AES-192
which nobody uses). It does make for nicer code, though.

While at it, use \@ to generate the labels inside the macros, which is
more robust than using fixed numbers, which could clash inadvertently.
Also, bring aes-neon.S in line with these changes, including the switch
to test-and-branch instructions, to avoid surprises in the future when
we might start relying on the condition flags being preserved in the
chaining mode wrappers in aes-modes.S

Signed-off-by: Ard Biesheuvel <[e-mail]>
Reviewed-by: Eric Biggers <[e-mail]>
Signed-off-by: Herbert Xu <[e-mail]>

arch/arm64/crypto/aes-ce.S

···
 	.endm
 
 	/* preload all round keys */
-	.macro		load_round_keys, rounds, rk
-	cmp		\rounds, #12
-	blo		2222f		/* 128 bits */
-	beq		1111f		/* 192 bits */
-	ld1		{v17.4s-v18.4s}, [\rk], #32
-1111:	ld1		{v19.4s-v20.4s}, [\rk], #32
-2222:	ld1		{v21.4s-v24.4s}, [\rk], #64
-	ld1		{v25.4s-v28.4s}, [\rk], #64
-	ld1		{v29.4s-v31.4s}, [\rk]
+	.macro		load_round_keys, rk, nr, tmp
+	add		\tmp, \rk, \nr, sxtw #4
+	sub		\tmp, \tmp, #160
+	ld1		{v17.4s-v20.4s}, [\rk]
+	ld1		{v21.4s-v24.4s}, [\tmp], #64
+	ld1		{v25.4s-v28.4s}, [\tmp], #64
+	ld1		{v29.4s-v31.4s}, [\tmp]
 	.endm
 
 	/* prepare for encryption with key in rk[] */
 	.macro		enc_prepare, rounds, rk, temp
-	mov		\temp, \rk
-	load_round_keys	\rounds, \temp
+	load_round_keys	\rk, \rounds, \temp
 	.endm
 
 	/* prepare for encryption (again) but with new key in rk[] */
 	.macro		enc_switch_key, rounds, rk, temp
-	mov		\temp, \rk
-	load_round_keys	\rounds, \temp
+	load_round_keys	\rk, \rounds, \temp
 	.endm
 
 	/* prepare for decryption with key in rk[] */
 	.macro		dec_prepare, rounds, rk, temp
-	mov		\temp, \rk
-	load_round_keys	\rounds, \temp
+	load_round_keys	\rk, \rounds, \temp
 	.endm
 
 	.macro		do_enc_Nx, de, mc, k, i0, i1, i2, i3, i4
···
 
 	/* up to 5 interleaved blocks */
 	.macro		do_block_Nx, enc, rounds, i0, i1, i2, i3, i4
-	cmp		\rounds, #12
-	blo		2222f		/* 128 bits */
-	beq		1111f		/* 192 bits */
+	tbz		\rounds, #2, .L\@	/* 128 bits */
 	round_Nx	\enc, v17, \i0, \i1, \i2, \i3, \i4
 	round_Nx	\enc, v18, \i0, \i1, \i2, \i3, \i4
-1111:	round_Nx	\enc, v19, \i0, \i1, \i2, \i3, \i4
+	tbz		\rounds, #1, .L\@	/* 192 bits */
+	round_Nx	\enc, v19, \i0, \i1, \i2, \i3, \i4
 	round_Nx	\enc, v20, \i0, \i1, \i2, \i3, \i4
-2222:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
+.L\@:	.irp		key, v21, v22, v23, v24, v25, v26, v27, v28, v29
 	round_Nx	\enc, \key, \i0, \i1, \i2, \i3, \i4
 	.endr
 	fin_round_Nx	\enc, v30, v31, \i0, \i1, \i2, \i3, \i4

arch/arm64/crypto/aes-neon.S

···
 	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
-1111:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+.La\@:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
 	movi		v15.16b, #0x40
 	tbl		\in\().16b, {\in\().16b}, v13.16b	/* ShiftRows */
 	sub_bytes	\in
-	subs		\i, \i, #1
+	sub		\i, \i, #1
 	ld1		{v15.4s}, [\rkp], #16
-	beq		2222f
+	cbz		\i, .Lb\@
 	mix_columns	\in, \enc
-	b		1111b
-2222:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
+	b		.La\@
+.Lb\@:	eor		\in\().16b, \in\().16b, v15.16b		/* ^round key */
 	.endm
 
 	.macro		encrypt_block, in, rounds, rk, rkp, i
···
 	ld1		{v15.4s}, [\rk]
 	add		\rkp, \rk, #16
 	mov		\i, \rounds
-1111:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+.La\@:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
 	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
 	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
 	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */
···
 	tbl		\in2\().16b, {\in2\().16b}, v13.16b	/* ShiftRows */
 	tbl		\in3\().16b, {\in3\().16b}, v13.16b	/* ShiftRows */
 	sub_bytes_4x	\in0, \in1, \in2, \in3
-	subs		\i, \i, #1
+	sub		\i, \i, #1
 	ld1		{v15.4s}, [\rkp], #16
-	beq		2222f
+	cbz		\i, .Lb\@
 	mix_columns_2x	\in0, \in1, \enc
 	mix_columns_2x	\in2, \in3, \enc
-	b		1111b
-2222:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
+	b		.La\@
+.Lb\@:	eor		\in0\().16b, \in0\().16b, v15.16b	/* ^round key */
 	eor		\in1\().16b, \in1\().16b, v15.16b	/* ^round key */
 	eor		\in2\().16b, \in2\().16b, v15.16b	/* ^round key */
 	eor		\in3\().16b, \in3\().16b, v15.16b	/* ^round key */