[PATCH 6/6] crypto: arm/crct10dif - Implement plain NEON variant

[Ard Biesheuvel <ardb+git@google.com>]

From: Ard Biesheuvel <ardb@kernel.org>

The CRC-T10DIF algorithm produces a 16-bit CRC, and this is reflected in
the folding coefficients, which are also only 16 bits wide.

This means that the polynomial multiplications involving these
coefficients can be performed using 8-bit long polynomial multiplication
(8x8 -> 16) in only a few steps, and this is an instruction that is part
of the base NEON ISA, which is all most real ARMv7 cores implement. (The
64-bit PMULL instruction is part of the crypto extensions, which are
only implemented by 64-bit cores)

The final reduction is a bit more involved, but we can delegate that to
the generic CRC-T10DIF implementation after folding the entire input
into a 16 byte vector.

This results in a speedup of around 6.6x on Cortex-A72 running in 32-bit
mode.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
---
 arch/arm/crypto/crct10dif-ce-core.S | 50 ++++++++++++++++++--
 arch/arm/crypto/crct10dif-ce-glue.c | 44 +++++++++++++++--
 2 files changed, 85 insertions(+), 9 deletions(-)

diff --git a/arch/arm/crypto/crct10dif-ce-core.S b/arch/arm/crypto/crct10dif-ce-core.S
index 6b72167574b2..5e103a9a42dd 100644
--- a/arch/arm/crypto/crct10dif-ce-core.S
+++ b/arch/arm/crypto/crct10dif-ce-core.S
@@ -112,6 +112,34 @@
 	FOLD_CONST_L	.req	q10l
 	FOLD_CONST_H	.req	q10h
 
+__pmull16x64_p8:
+	vmull.p8	q13, d23, d24
+	vmull.p8	q14, d23, d25
+	vmull.p8	q15, d22, d24
+	vmull.p8	q12, d22, d25
+
+	veor		q14, q14, q15
+	veor		d24, d24, d25
+	veor		d26, d26, d27
+	veor		d28, d28, d29
+	vmov.i32	d25, #0
+	vmov.i32	d29, #0
+	vext.8		q12, q12, q12, #14
+	vext.8		q14, q14, q14, #15
+	veor		d24, d24, d26
+	bx		lr
+ENDPROC(__pmull16x64_p8)
+
+        .macro		pmull16x64_p8, v16, v64
+	vext.8		q11, \v64, \v64, #1
+	vld1.64		{q12}, [r4, :128]
+	vuzp.8		q11, \v64
+	vtbl.8		d24, {\v16\()_L-\v16\()_H}, d24
+	vtbl.8		d25, {\v16\()_L-\v16\()_H}, d25
+	bl		__pmull16x64_p8
+	veor		\v64, q12, q14
+        .endm
+
         .macro		pmull16x64_p64, v16, v64
 	vmull.p64	q11, \v64\()l, \v16\()_L
 	vmull.p64	\v64, \v64\()h, \v16\()_H
@@ -249,9 +277,9 @@ CPU_LE(	vrev64.8	q0, q0	)
 	vswp		q0l, q0h
 
 	// q1 = high order part of second chunk: q7 left-shifted by 'len' bytes.
-	mov_l		r3, .Lbyteshift_table + 16
-	sub		r3, r3, len
-	vld1.8		{q2}, [r3]
+	mov_l		r1, .Lbyteshift_table + 16
+	sub		r1, r1, len
+	vld1.8		{q2}, [r1]
 	vtbl.8		q1l, {q7l-q7h}, q2l
 	vtbl.8		q1h, {q7l-q7h}, q2h
 
@@ -341,9 +369,20 @@ ENTRY(crc_t10dif_pmull64)
 
 	vmov.u16	r0, q0l[0]
 	bx		lr
-
 ENDPROC(crc_t10dif_pmull64)
 
+ENTRY(crc_t10dif_pmull8)
+	push		{r4, lr}
+	mov_l		r4, .L16x64perm
+
+	crct10dif	p8
+
+CPU_LE(	vrev64.8	q7, q7	)
+	vswp		q7l, q7h
+	vst1.64		{q7}, [r3, :128]
+	pop		{r4, pc}
+ENDPROC(crc_t10dif_pmull8)
+
 	.section	".rodata", "a"
 	.align		4
 
@@ -376,3 +415,6 @@ ENDPROC(crc_t10dif_pmull64)
 	.byte		0x88, 0x89, 0x8a, 0x8b, 0x8c, 0x8d, 0x8e, 0x8f
 	.byte		 0x0,  0x1,  0x2,  0x3,  0x4,  0x5,  0x6,  0x7
 	.byte		 0x8,  0x9,  0xa,  0xb,  0xc,  0xd,  0xe , 0x0
+
+.L16x64perm:
+	.quad		0x808080800000000, 0x909090901010101
diff --git a/arch/arm/crypto/crct10dif-ce-glue.c b/arch/arm/crypto/crct10dif-ce-glue.c
index 60aa79c2fcdb..4431e4ce2dbe 100644
--- a/arch/arm/crypto/crct10dif-ce-glue.c
+++ b/arch/arm/crypto/crct10dif-ce-glue.c
@@ -20,6 +20,7 @@
 #define CRC_T10DIF_PMULL_CHUNK_SIZE	16U
 
 asmlinkage u16 crc_t10dif_pmull64(u16 init_crc, const u8 *buf, size_t len);
+asmlinkage void crc_t10dif_pmull8(u16 init_crc, const u8 *buf, size_t len, u8 *out);
 
 static int crct10dif_init(struct shash_desc *desc)
 {
@@ -45,6 +46,27 @@ static int crct10dif_update_ce(struct shash_desc *desc, const u8 *data,
 	return 0;
 }
 
+static int crct10dif_update_neon(struct shash_desc *desc, const u8 *data,
+			         unsigned int length)
+{
+	u16 *crcp = shash_desc_ctx(desc);
+	u8 buf[16] __aligned(16);
+	u16 crc = *crcp;
+
+	if (length >= CRC_T10DIF_PMULL_CHUNK_SIZE && crypto_simd_usable()) {
+		kernel_neon_begin();
+		crc_t10dif_pmull8(crc, data, length, buf);
+		kernel_neon_end();
+
+		crc = 0;
+		data = buf;
+		length = sizeof(buf);
+	}
+
+	*crcp = crc_t10dif_generic(crc, data, length);
+	return 0;
+}
+
 static int crct10dif_final(struct shash_desc *desc, u8 *out)
 {
 	u16 *crc = shash_desc_ctx(desc);
@@ -53,7 +75,19 @@ static int crct10dif_final(struct shash_desc *desc, u8 *out)
 	return 0;
 }
 
-static struct shash_alg crc_t10dif_alg = {
+static struct shash_alg algs[] = {{
+	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
+	.init			= crct10dif_init,
+	.update			= crct10dif_update_neon,
+	.final			= crct10dif_final,
+	.descsize		= CRC_T10DIF_DIGEST_SIZE,
+
+	.base.cra_name		= "crct10dif",
+	.base.cra_driver_name	= "crct10dif-arm-neon",
+	.base.cra_priority	= 150,
+	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
+	.base.cra_module	= THIS_MODULE,
+}, {
 	.digestsize		= CRC_T10DIF_DIGEST_SIZE,
 	.init			= crct10dif_init,
 	.update			= crct10dif_update_ce,
@@ -65,19 +99,19 @@ static struct shash_alg crc_t10dif_alg = {
 	.base.cra_priority	= 200,
 	.base.cra_blocksize	= CRC_T10DIF_BLOCK_SIZE,
 	.base.cra_module	= THIS_MODULE,
-};
+}};
 
 static int __init crc_t10dif_mod_init(void)
 {
-	if (!(elf_hwcap2 & HWCAP2_PMULL))
+	if (!(elf_hwcap & HWCAP_NEON))
 		return -ENODEV;
 
-	return crypto_register_shash(&crc_t10dif_alg);
+	return crypto_register_shashes(algs, 1 + !!(elf_hwcap2 & HWCAP2_PMULL));
 }
 
 static void __exit crc_t10dif_mod_exit(void)
 {
-	crypto_unregister_shash(&crc_t10dif_alg);
+	crypto_unregister_shashes(algs, 1 + !!(elf_hwcap2 & HWCAP2_PMULL));
 }
 
 module_init(crc_t10dif_mod_init);
-- 
2.47.0.163.g1226f6d8fa-goog