crypto: ghash - Add PCLMULQDQ accelerated implementation

PCLMULQDQ is used to accelerate the most time-consuming part of GHASH,
carry-less multiplication. More information about PCLMULQDQ can be
found at:

http://software.intel.com/en-us/articles/carry-less-multiplication-and-its-usage-for-computing-the-gcm-mode/

Because PCLMULQDQ changes XMM state, its usage must be enclosed with
kernel_fpu_begin/end, which can be used only in process context, the
acceleration is implemented as crypto_ahash. That is, request in soft
IRQ context will be defered to the cryptd kernel thread.

Signed-off-by: Huang Ying <ying.huang@intel.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
diff --git a/arch/x86/crypto/ghash-clmulni-intel_asm.S b/arch/x86/crypto/ghash-clmulni-intel_asm.S
new file mode 100644
index 0000000..b9e787a
--- /dev/null
+++ b/arch/x86/crypto/ghash-clmulni-intel_asm.S
@@ -0,0 +1,157 @@
+/*
+ * Accelerated GHASH implementation with Intel PCLMULQDQ-NI
+ * instructions. This file contains accelerated part of ghash
+ * implementation. More information about PCLMULQDQ can be found at:
+ *
+ * http://software.intel.com/en-us/articles/carry-less-multiplication-and-its-usage-for-computing-the-gcm-mode/
+ *
+ * Copyright (c) 2009 Intel Corp.
+ *   Author: Huang Ying <ying.huang@intel.com>
+ *	     Vinodh Gopal
+ *	     Erdinc Ozturk
+ *	     Deniz Karakoyunlu
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms of the GNU General Public License version 2 as published
+ * by the Free Software Foundation.
+ */
+
+#include <linux/linkage.h>
+
+.align 16
+.Lbswap_mask:
+	.octa 0x000102030405060708090a0b0c0d0e0f
+.Lpoly:
+	.octa 0xc2000000000000000000000000000001
+.Ltwo_one:
+	.octa 0x00000001000000000000000000000001
+
+#define DATA	%xmm0
+#define SHASH	%xmm1
+#define T1	%xmm2
+#define T2	%xmm3
+#define T3	%xmm4
+#define BSWAP	%xmm5
+#define IN1	%xmm6
+
+.text
+
+/*
+ * __clmul_gf128mul_ble:	internal ABI
+ * input:
+ *	DATA:			operand1
+ *	SHASH:			operand2, hash_key << 1 mod poly
+ * output:
+ *	DATA:			operand1 * operand2 mod poly
+ * changed:
+ *	T1
+ *	T2
+ *	T3
+ */
+__clmul_gf128mul_ble:
+	movaps DATA, T1
+	pshufd $0b01001110, DATA, T2
+	pshufd $0b01001110, SHASH, T3
+	pxor DATA, T2
+	pxor SHASH, T3
+
+	# pclmulqdq $0x00, SHASH, DATA	# DATA = a0 * b0
+	.byte 0x66, 0x0f, 0x3a, 0x44, 0xc1, 0x00
+	# pclmulqdq $0x11, SHASH, T1	# T1 = a1 * b1
+	.byte 0x66, 0x0f, 0x3a, 0x44, 0xd1, 0x11
+	# pclmulqdq $0x00, T3, T2	# T2 = (a1 + a0) * (b1 + b0)
+	.byte 0x66, 0x0f, 0x3a, 0x44, 0xdc, 0x00
+	pxor DATA, T2
+	pxor T1, T2			# T2 = a0 * b1 + a1 * b0
+
+	movaps T2, T3
+	pslldq $8, T3
+	psrldq $8, T2
+	pxor T3, DATA
+	pxor T2, T1			# <T1:DATA> is result of
+					# carry-less multiplication
+
+	# first phase of the reduction
+	movaps DATA, T3
+	psllq $1, T3
+	pxor DATA, T3
+	psllq $5, T3
+	pxor DATA, T3
+	psllq $57, T3
+	movaps T3, T2
+	pslldq $8, T2
+	psrldq $8, T3
+	pxor T2, DATA
+	pxor T3, T1
+
+	# second phase of the reduction
+	movaps DATA, T2
+	psrlq $5, T2
+	pxor DATA, T2
+	psrlq $1, T2
+	pxor DATA, T2
+	psrlq $1, T2
+	pxor T2, T1
+	pxor T1, DATA
+	ret
+
+/* void clmul_ghash_mul(char *dst, const be128 *shash) */
+ENTRY(clmul_ghash_mul)
+	movups (%rdi), DATA
+	movups (%rsi), SHASH
+	movaps .Lbswap_mask, BSWAP
+	pshufb BSWAP, DATA
+	call __clmul_gf128mul_ble
+	pshufb BSWAP, DATA
+	movups DATA, (%rdi)
+	ret
+
+/*
+ * void clmul_ghash_update(char *dst, const char *src, unsigned int srclen,
+ *			   const be128 *shash);
+ */
+ENTRY(clmul_ghash_update)
+	cmp $16, %rdx
+	jb .Lupdate_just_ret	# check length
+	movaps .Lbswap_mask, BSWAP
+	movups (%rdi), DATA
+	movups (%rcx), SHASH
+	pshufb BSWAP, DATA
+.align 4
+.Lupdate_loop:
+	movups (%rsi), IN1
+	pshufb BSWAP, IN1
+	pxor IN1, DATA
+	call __clmul_gf128mul_ble
+	sub $16, %rdx
+	add $16, %rsi
+	cmp $16, %rdx
+	jge .Lupdate_loop
+	pshufb BSWAP, DATA
+	movups DATA, (%rdi)
+.Lupdate_just_ret:
+	ret
+
+/*
+ * void clmul_ghash_setkey(be128 *shash, const u8 *key);
+ *
+ * Calculate hash_key << 1 mod poly
+ */
+ENTRY(clmul_ghash_setkey)
+	movaps .Lbswap_mask, BSWAP
+	movups (%rsi), %xmm0
+	pshufb BSWAP, %xmm0
+	movaps %xmm0, %xmm1
+	psllq $1, %xmm0
+	psrlq $63, %xmm1
+	movaps %xmm1, %xmm2
+	pslldq $8, %xmm1
+	psrldq $8, %xmm2
+	por %xmm1, %xmm0
+	# reduction
+	pshufd $0b00100100, %xmm2, %xmm1
+	pcmpeqd .Ltwo_one, %xmm1
+	pand .Lpoly, %xmm1
+	pxor %xmm1, %xmm0
+	movups %xmm0, (%rdi)
+	ret