crypto: arm/crct10dif - Macroify PMULL asm code

To allow an alternative version to be created of the PMULL based
CRC-T10DIF algorithm, turn the bulk of it into a macro, except for the
final reduction, which will only be used by the existing version.

Reviewed-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

Author: ardbiesheuvel

arch/arm/crypto/crct10dif-ce-core.S

@@ -112,48 +112,42 @@
 	FOLD_CONST_L	.req	q10l
 	FOLD_CONST_H	.req	q10h
 
+        .macro		pmull16x64_p64, v16, v64
+	vmull.p64	q11, \v64\()l, \v16\()_L
+	vmull.p64	\v64, \v64\()h, \v16\()_H
+	veor		\v64, \v64, q11
+	.endm
+
 	// Fold reg1, reg2 into the next 32 data bytes, storing the result back
 	// into reg1, reg2.
-	.macro		fold_32_bytes, reg1, reg2
-	vld1.64		{q11-q12}, [buf]!
+	.macro		fold_32_bytes, reg1, reg2, p
+	vld1.64		{q8-q9}, [buf]!
 
-	vmull.p64	q8, \reg1\()h, FOLD_CONST_H
-	vmull.p64	\reg1, \reg1\()l, FOLD_CONST_L
-	vmull.p64	q9, \reg2\()h, FOLD_CONST_H
-	vmull.p64	\reg2, \reg2\()l, FOLD_CONST_L
+	pmull16x64_\p	FOLD_CONST, \reg1
+	pmull16x64_\p	FOLD_CONST, \reg2
 
-CPU_LE(	vrev64.8	q11, q11	)
-CPU_LE(	vrev64.8	q12, q12	)
-	vswp		q11l, q11h
-	vswp		q12l, q12h
+CPU_LE(	vrev64.8	q8, q8	)
+CPU_LE(	vrev64.8	q9, q9	)
+	vswp		q8l, q8h
+	vswp		q9l, q9h
 
 	veor.8		\reg1, \reg1, q8
 	veor.8		\reg2, \reg2, q9
-	veor.8		\reg1, \reg1, q11
-	veor.8		\reg2, \reg2, q12
 	.endm
 
 	// Fold src_reg into dst_reg, optionally loading the next fold constants
-	.macro		fold_16_bytes, src_reg, dst_reg, load_next_consts
-	vmull.p64	q8, \src_reg\()l, FOLD_CONST_L
-	vmull.p64	\src_reg, \src_reg\()h, FOLD_CONST_H
+	.macro		fold_16_bytes, src_reg, dst_reg, p, load_next_consts
+	pmull16x64_\p	FOLD_CONST, \src_reg
 	.ifnb		\load_next_consts
 	vld1.64		{FOLD_CONSTS}, [fold_consts_ptr, :128]!
 	.endif
-	veor.8		\dst_reg, \dst_reg, q8
 	veor.8		\dst_reg, \dst_reg, \src_reg
 	.endm
 
-//
-// u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
-//
-// Assumes len >= 16.
-//
-ENTRY(crc_t10dif_pmull)
-
+	.macro		crct10dif, p
 	// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
 	cmp		len, #256
-	blt		.Lless_than_256_bytes
+	blt		.Lless_than_256_bytes\@
 
 	mov_l		fold_consts_ptr, .Lfold_across_128_bytes_consts
 
@@ -194,27 +188,27 @@ CPU_LE(	vrev64.8	q7, q7	)
 
 	// While >= 128 data bytes remain (not counting q0-q7), fold the 128
 	// bytes q0-q7 into them, storing the result back into q0-q7.
-.Lfold_128_bytes_loop:
-	fold_32_bytes	q0, q1
-	fold_32_bytes	q2, q3
-	fold_32_bytes	q4, q5
-	fold_32_bytes	q6, q7
+.Lfold_128_bytes_loop\@:
+	fold_32_bytes	q0, q1, \p
+	fold_32_bytes	q2, q3, \p
+	fold_32_bytes	q4, q5, \p
+	fold_32_bytes	q6, q7, \p
 	subs		len, len, #128
-	bge		.Lfold_128_bytes_loop
+	bge		.Lfold_128_bytes_loop\@
 
 	// Now fold the 112 bytes in q0-q6 into the 16 bytes in q7.
 
 	// Fold across 64 bytes.
 	vld1.64		{FOLD_CONSTS}, [fold_consts_ptr, :128]!
-	fold_16_bytes	q0, q4
-	fold_16_bytes	q1, q5
-	fold_16_bytes	q2, q6
-	fold_16_bytes	q3, q7, 1
+	fold_16_bytes	q0, q4, \p
+	fold_16_bytes	q1, q5, \p
+	fold_16_bytes	q2, q6, \p
+	fold_16_bytes	q3, q7, \p, 1
 	// Fold across 32 bytes.
-	fold_16_bytes	q4, q6
-	fold_16_bytes	q5, q7, 1
+	fold_16_bytes	q4, q6, \p
+	fold_16_bytes	q5, q7, \p, 1
 	// Fold across 16 bytes.
-	fold_16_bytes	q6, q7
+	fold_16_bytes	q6, q7, \p
 
 	// Add 128 to get the correct number of data bytes remaining in 0...127
 	// (not counting q7), following the previous extra subtraction by 128.
@@ -224,25 +218,23 @@ CPU_LE(	vrev64.8	q7, q7	)
 
 	// While >= 16 data bytes remain (not counting q7), fold the 16 bytes q7
 	// into them, storing the result back into q7.
-	blt		.Lfold_16_bytes_loop_done
-.Lfold_16_bytes_loop:
-	vmull.p64	q8, q7l, FOLD_CONST_L
-	vmull.p64	q7, q7h, FOLD_CONST_H
-	veor.8		q7, q7, q8
+	blt		.Lfold_16_bytes_loop_done\@
+.Lfold_16_bytes_loop\@:
+	pmull16x64_\p	FOLD_CONST, q7
 	vld1.64		{q0}, [buf]!
 CPU_LE(	vrev64.8	q0, q0	)
 	vswp		q0l, q0h
 	veor.8		q7, q7, q0
 	subs		len, len, #16
-	bge		.Lfold_16_bytes_loop
+	bge		.Lfold_16_bytes_loop\@
 
-.Lfold_16_bytes_loop_done:
+.Lfold_16_bytes_loop_done\@:
 	// Add 16 to get the correct number of data bytes remaining in 0...15
 	// (not counting q7), following the previous extra subtraction by 16.
 	adds		len, len, #16
-	beq		.Lreduce_final_16_bytes
+	beq		.Lreduce_final_16_bytes\@
 
-.Lhandle_partial_segment:
+.Lhandle_partial_segment\@:
 	// Reduce the last '16 + len' bytes where 1 <= len <= 15 and the first
 	// 16 bytes are in q7 and the rest are the remaining data in 'buf'.  To
 	// do this without needing a fold constant for each possible 'len',
@@ -277,12 +269,46 @@ CPU_LE(	vrev64.8	q0, q0	)
 	vbsl.8		q2, q1, q0
 
 	// Fold the first chunk into the second chunk, storing the result in q7.
-	vmull.p64	q0, q3l, FOLD_CONST_L
-	vmull.p64	q7, q3h, FOLD_CONST_H
-	veor.8		q7, q7, q0
-	veor.8		q7, q7, q2
+	pmull16x64_\p	FOLD_CONST, q3
+	veor.8		q7, q3, q2
+	b		.Lreduce_final_16_bytes\@
+
+.Lless_than_256_bytes\@:
+	// Checksumming a buffer of length 16...255 bytes
+
+	mov_l		fold_consts_ptr, .Lfold_across_16_bytes_consts
+
+	// Load the first 16 data bytes.
+	vld1.64		{q7}, [buf]!
+CPU_LE(	vrev64.8	q7, q7	)
+	vswp		q7l, q7h
+
+	// XOR the first 16 data *bits* with the initial CRC value.
+	vmov.i8		q0h, #0
+	vmov.u16	q0h[3], init_crc
+	veor.8		q7h, q7h, q0h
+
+	// Load the fold-across-16-bytes constants.
+	vld1.64		{FOLD_CONSTS}, [fold_consts_ptr, :128]!
+
+	cmp		len, #16
+	beq		.Lreduce_final_16_bytes\@	// len == 16
+	subs		len, len, #32
+	addlt		len, len, #16
+	blt		.Lhandle_partial_segment\@	// 17 <= len <= 31
+	b		.Lfold_16_bytes_loop\@		// 32 <= len <= 255
+
+.Lreduce_final_16_bytes\@:
+	.endm
+
+//
+// u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
+//
+// Assumes len >= 16.
+//
+ENTRY(crc_t10dif_pmull64)
+	crct10dif	p64
 
-.Lreduce_final_16_bytes:
 	// Reduce the 128-bit value M(x), stored in q7, to the final 16-bit CRC.
 
 	// Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
@@ -316,31 +342,7 @@ CPU_LE(	vrev64.8	q0, q0	)
 	vmov.u16	r0, q0l[0]
 	bx		lr
 
-.Lless_than_256_bytes:
-	// Checksumming a buffer of length 16...255 bytes
-
-	mov_l		fold_consts_ptr, .Lfold_across_16_bytes_consts
-
-	// Load the first 16 data bytes.
-	vld1.64		{q7}, [buf]!
-CPU_LE(	vrev64.8	q7, q7	)
-	vswp		q7l, q7h
-
-	// XOR the first 16 data *bits* with the initial CRC value.
-	vmov.i8		q0h, #0
-	vmov.u16	q0h[3], init_crc
-	veor.8		q7h, q7h, q0h
-
-	// Load the fold-across-16-bytes constants.
-	vld1.64		{FOLD_CONSTS}, [fold_consts_ptr, :128]!
-
-	cmp		len, #16
-	beq		.Lreduce_final_16_bytes		// len == 16
-	subs		len, len, #32
-	addlt		len, len, #16
-	blt		.Lhandle_partial_segment	// 17 <= len <= 31
-	b		.Lfold_16_bytes_loop		// 32 <= len <= 255
-ENDPROC(crc_t10dif_pmull)
+ENDPROC(crc_t10dif_pmull64)
 
 	.section	".rodata", "a"
 	.align		4

arch/arm/crypto/crct10dif-ce-glue.c

@@ -19,7 +19,7 @@
 
 #define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
 
-asmlinkage u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage u16 crc_t10dif_pmull64(u16 init_crc, const u8 *buf, size_t len);
 
 static int crct10dif_init(struct shash_desc *desc)
 {
@@ -29,14 +29,14 @@ static int crct10dif_init(struct shash_desc *desc)
 	return 0;
 }
 
-static int crct10dif_update(struct shash_desc *desc, const u8 *data,
-			    unsigned int length)
+static int crct10dif_update_ce(struct shash_desc *desc, const u8 *data,
+			       unsigned int length)
 {
 	u16 *crc = shash_desc_ctx(desc);
 
 	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
 		kernel_neon_begin();
-		*crc = crc_t10dif_pmull(*crc, data, length);
+		*crc = crc_t10dif_pmull64(*crc, data, length);
 		kernel_neon_end();
 	} else {
 		*crc = crc_t10dif_generic(*crc, data, length);
@@ -56,7 +56,7 @@ static int crct10dif_final(struct shash_desc *desc, u8 *out)
 static struct shash_alg crc_t10dif_alg = {
 	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
 	.init			= crct10dif_init,
-	.update			= crct10dif_update,
+	.update			= crct10dif_update_ce,
 	.final			= crct10dif_final,
 	.descsize		= CRC_T10DIF_DIGEST_SIZE,