Clean up and improve ARM/arm64 CRC-T10DIF code

index 5604de61d06d..d2acaa2b5a01 100644
@@ -1,8 +1,11 @@
 //
 // Accelerated CRC-T10DIF using arm64 NEON and Crypto Extensions instructions
 //
-// Copyright (C) 2016 Linaro Ltd <[email protected]>
-// Copyright (C) 2019 Google LLC <[email protected]>
+// Copyright (C) 2016 Linaro Ltd
+// Copyright (C) 2019-2024 Google LLC
+//
+// Authors: Ard Biesheuvel <[email protected]>
+//          Eric Biggers <[email protected]>
 //
 // 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

@@ -122,6 +125,13 @@
 	sli		perm2.2d, perm1.2d, #56
 	sli		perm3.2d, perm1.2d, #48
 	sli		perm4.2d, perm1.2d, #40
+
+	// Compose { 0,0,0,0, 8,8,8,8, 1,1,1,1, 9,9,9,9 }
+	movi		bd1.4h, #8, lsl #8
+	orr		bd1.2s, #1, lsl #16
+	orr		bd1.2s, #1, lsl #24
+	zip1		bd1.16b, bd1.16b, bd1.16b
+	zip1		bd1.16b, bd1.16b, bd1.16b
 	.endm
 
 	.macro		__pmull_pre_p8, bd

@@ -196,6 +206,92 @@ SYM_FUNC_START_LOCAL(__pmull_p8_core)
 	ret
 SYM_FUNC_END(__pmull_p8_core)
 
+	.macro		pmull16x64_p64, a16, b64, c64
+	pmull2		\c64\().1q, \a16\().2d, \b64\().2d
+	pmull		\b64\().1q, \a16\().1d, \b64\().1d
+	.endm
+
+	/*
+	 * Pairwise long polynomial multiplication of two 16-bit values
+	 *
+	 *   { w0, w1 }, { y0, y1 }
+	 *
+	 * by two 64-bit values
+	 *
+	 *   { x0, x1, x2, x3, x4, x5, x6, x7 }, { z0, z1, z2, z3, z4, z5, z6, z7 }
+	 *
+	 * where each vector element is a byte, ordered from least to most
+	 * significant.
+	 *
+	 * This can be implemented using 8x8 long polynomial multiplication, by
+	 * reorganizing the input so that each pairwise 8x8 multiplication
+	 * produces one of the terms from the decomposition below, and
+	 * combining the results of each rank and shifting them into place.
+	 *
+	 * Rank
+	 *  0            w0*x0 ^              |        y0*z0 ^
+	 *  1       (w0*x1 ^ w1*x0) <<  8 ^   |   (y0*z1 ^ y1*z0) <<  8 ^
+	 *  2       (w0*x2 ^ w1*x1) << 16 ^   |   (y0*z2 ^ y1*z1) << 16 ^
+	 *  3       (w0*x3 ^ w1*x2) << 24 ^   |   (y0*z3 ^ y1*z2) << 24 ^
+	 *  4       (w0*x4 ^ w1*x3) << 32 ^   |   (y0*z4 ^ y1*z3) << 32 ^
+	 *  5       (w0*x5 ^ w1*x4) << 40 ^   |   (y0*z5 ^ y1*z4) << 40 ^
+	 *  6       (w0*x6 ^ w1*x5) << 48 ^   |   (y0*z6 ^ y1*z5) << 48 ^
+	 *  7       (w0*x7 ^ w1*x6) << 56 ^   |   (y0*z7 ^ y1*z6) << 56 ^
+	 *  8            w1*x7      << 64     |        y1*z7      << 64
+	 *
+	 * The inputs can be reorganized into
+	 *
+	 *   { w0, w0, w0, w0, y0, y0, y0, y0 }, { w1, w1, w1, w1, y1, y1, y1, y1 }
+	 *   { x0, x2, x4, x6, z0, z2, z4, z6 }, { x1, x3, x5, x7, z1, z3, z5, z7 }
+	 *
+	 * and after performing 8x8->16 bit long polynomial multiplication of
+	 * each of the halves of the first vector with those of the second one,
+	 * we obtain the following four vectors of 16-bit elements:
+	 *
+	 *   a := { w0*x0, w0*x2, w0*x4, w0*x6 }, { y0*z0, y0*z2, y0*z4, y0*z6 }
+	 *   b := { w0*x1, w0*x3, w0*x5, w0*x7 }, { y0*z1, y0*z3, y0*z5, y0*z7 }
+	 *   c := { w1*x0, w1*x2, w1*x4, w1*x6 }, { y1*z0, y1*z2, y1*z4, y1*z6 }
+	 *   d := { w1*x1, w1*x3, w1*x5, w1*x7 }, { y1*z1, y1*z3, y1*z5, y1*z7 }
+	 *
+	 * Results b and c can be XORed together, as the vector elements have
+	 * matching ranks. Then, the final XOR (*) can be pulled forward, and
+	 * applied between the halves of each of the remaining three vectors,
+	 * which are then shifted into place, and combined to produce two
+	 * 80-bit results.
+	 *
+	 * (*) NOTE: the 16x64 bit polynomial multiply below is not equivalent
+	 * to the 64x64 bit one above, but XOR'ing the outputs together will
+	 * produce the expected result, and this is sufficient in the context of
+	 * this algorithm.
+	 */
+	.macro		pmull16x64_p8, a16, b64, c64
+	ext		t7.16b, \b64\().16b, \b64\().16b, #1
+	tbl		t5.16b, {\a16\().16b}, bd1.16b
+	uzp1		t7.16b, \b64\().16b, t7.16b
+	bl		__pmull_p8_16x64
+	ext		\b64\().16b, t4.16b, t4.16b, #15
+	eor		\c64\().16b, t8.16b, t5.16b
+	.endm
+
+SYM_FUNC_START_LOCAL(__pmull_p8_16x64)
+	ext		t6.16b, t5.16b, t5.16b, #8
+
+	pmull		t3.8h, t7.8b, t5.8b
+	pmull		t4.8h, t7.8b, t6.8b
+	pmull2		t5.8h, t7.16b, t5.16b
+	pmull2		t6.8h, t7.16b, t6.16b
+
+	ext		t8.16b, t3.16b, t3.16b, #8
+	eor		t4.16b, t4.16b, t6.16b
+	ext		t7.16b, t5.16b, t5.16b, #8
+	ext		t6.16b, t4.16b, t4.16b, #8
+	eor		t8.8b, t8.8b, t3.8b
+	eor		t5.8b, t5.8b, t7.8b
+	eor		t4.8b, t4.8b, t6.8b
+	ext		t5.16b, t5.16b, t5.16b, #14
+	ret
+SYM_FUNC_END(__pmull_p8_16x64)
+
 	.macro		__pmull_p8, rq, ad, bd, i
 	.ifnc		\bd, fold_consts
 	.err

@@ -218,14 +314,12 @@ SYM_FUNC_END(__pmull_p8_core)
 	.macro		fold_32_bytes, p, reg1, reg2
 	ldp		q11, q12, [buf], #0x20
 
-	__pmull_\p	v8, \reg1, fold_consts, 2
-	__pmull_\p	\reg1, \reg1, fold_consts
+	pmull16x64_\p	fold_consts, \reg1, v8
 
 CPU_LE(	rev64		v11.16b, v11.16b		)
 CPU_LE(	rev64		v12.16b, v12.16b		)
 
-	__pmull_\p	v9, \reg2, fold_consts, 2
-	__pmull_\p	\reg2, \reg2, fold_consts
+	pmull16x64_\p	fold_consts, \reg2, v9
 
 CPU_LE(	ext		v11.16b, v11.16b, v11.16b, #8	)
 CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)

@@ -238,11 +332,9 @@ CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
 
 	// Fold src_reg into dst_reg, optionally loading the next fold constants
 	.macro		fold_16_bytes, p, src_reg, dst_reg, load_next_consts
-	__pmull_\p	v8, \src_reg, fold_consts
-	__pmull_\p	\src_reg, \src_reg, fold_consts, 2
+	pmull16x64_\p	fold_consts, \src_reg, v8
 	.ifnb		\load_next_consts
 	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
-	__pmull_pre_\p	fold_consts
 	.endif
 	eor		\dst_reg\().16b, \dst_reg\().16b, v8.16b
 	eor		\dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b

@@ -296,7 +388,6 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 
 	// Load the constants for folding across 128 bytes.
 	ld1		{fold_consts.2d}, [fold_consts_ptr]
-	__pmull_pre_\p	fold_consts
 
 	// Subtract 128 for the 128 data bytes just consumed.  Subtract another
 	// 128 to simplify the termination condition of the following loop.

@@ -318,7 +409,6 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 	// Fold across 64 bytes.
 	add		fold_consts_ptr, fold_consts_ptr, #16
 	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
-	__pmull_pre_\p	fold_consts
 	fold_16_bytes	\p, v0, v4
 	fold_16_bytes	\p, v1, v5
 	fold_16_bytes	\p, v2, v6

@@ -339,8 +429,7 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 	// into them, storing the result back into v7.
 	b.lt		.Lfold_16_bytes_loop_done_\@
 .Lfold_16_bytes_loop_\@:
-	__pmull_\p	v8, v7, fold_consts
-	__pmull_\p	v7, v7, fold_consts, 2
+	pmull16x64_\p	fold_consts, v7, v8
 	eor		v7.16b, v7.16b, v8.16b
 	ldr		q0, [buf], #16
 CPU_LE(	rev64		v0.16b, v0.16b			)

@@ -387,9 +476,8 @@ CPU_LE(	ext		v0.16b, v0.16b, v0.16b, #8	)
 	bsl		v2.16b, v1.16b, v0.16b
 
 	// Fold the first chunk into the second chunk, storing the result in v7.
-	__pmull_\p	v0, v3, fold_consts
-	__pmull_\p	v7, v3, fold_consts, 2
-	eor		v7.16b, v7.16b, v0.16b
+	pmull16x64_\p	fold_consts, v3, v0
+	eor		v7.16b, v3.16b, v0.16b
 	eor		v7.16b, v7.16b, v2.16b
 
 .Lreduce_final_16_bytes_\@:

@@ -450,7 +538,6 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 
 	// Load the fold-across-16-bytes constants.
 	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
-	__pmull_pre_\p	fold_consts
 
 	cmp		len, #16
 	b.eq		.Lreduce_final_16_bytes_\@	// len == 16

index d2acaa2b5a01..87dd6d46224d 100644
@@ -74,137 +74,18 @@
 	init_crc	.req	w0
 	buf		.req	x1
 	len		.req	x2
-	fold_consts_ptr	.req	x3
+	fold_consts_ptr	.req	x5
 
 	fold_consts	.req	v10
 
-	ad		.req	v14
-
-	k00_16		.req	v15
-	k32_48		.req	v16
-
 	t3		.req	v17
 	t4		.req	v18
 	t5		.req	v19
 	t6		.req	v20
 	t7		.req	v21
 	t8		.req	v22
-	t9		.req	v23
-
-	perm1		.req	v24
-	perm2		.req	v25
-	perm3		.req	v26
-	perm4		.req	v27
-
-	bd1		.req	v28
-	bd2		.req	v29
-	bd3		.req	v30
-	bd4		.req	v31
-
-	.macro		__pmull_init_p64
-	.endm
 
-	.macro		__pmull_pre_p64, bd
-	.endm
-
-	.macro		__pmull_init_p8
-	// k00_16 := 0x0000000000000000_000000000000ffff
-	// k32_48 := 0x00000000ffffffff_0000ffffffffffff
-	movi		k32_48.2d, #0xffffffff
-	mov		k32_48.h[2], k32_48.h[0]
-	ushr		k00_16.2d, k32_48.2d, #32
-
-	// prepare the permutation vectors
-	mov_q		x5, 0x080f0e0d0c0b0a09
-	movi		perm4.8b, #8
-	dup		perm1.2d, x5
-	eor		perm1.16b, perm1.16b, perm4.16b
-	ushr		perm2.2d, perm1.2d, #8
-	ushr		perm3.2d, perm1.2d, #16
-	ushr		perm4.2d, perm1.2d, #24
-	sli		perm2.2d, perm1.2d, #56
-	sli		perm3.2d, perm1.2d, #48
-	sli		perm4.2d, perm1.2d, #40
-
-	// Compose { 0,0,0,0, 8,8,8,8, 1,1,1,1, 9,9,9,9 }
-	movi		bd1.4h, #8, lsl #8
-	orr		bd1.2s, #1, lsl #16
-	orr		bd1.2s, #1, lsl #24
-	zip1		bd1.16b, bd1.16b, bd1.16b
-	zip1		bd1.16b, bd1.16b, bd1.16b
-	.endm
-
-	.macro		__pmull_pre_p8, bd
-	tbl		bd1.16b, {\bd\().16b}, perm1.16b
-	tbl		bd2.16b, {\bd\().16b}, perm2.16b
-	tbl		bd3.16b, {\bd\().16b}, perm3.16b
-	tbl		bd4.16b, {\bd\().16b}, perm4.16b
-	.endm
-
-SYM_FUNC_START_LOCAL(__pmull_p8_core)
-.L__pmull_p8_core:
-	ext		t4.8b, ad.8b, ad.8b, #1			// A1
-	ext		t5.8b, ad.8b, ad.8b, #2			// A2
-	ext		t6.8b, ad.8b, ad.8b, #3			// A3
-
-	pmull		t4.8h, t4.8b, fold_consts.8b		// F = A1*B
-	pmull		t8.8h, ad.8b, bd1.8b			// E = A*B1
-	pmull		t5.8h, t5.8b, fold_consts.8b		// H = A2*B
-	pmull		t7.8h, ad.8b, bd2.8b			// G = A*B2
-	pmull		t6.8h, t6.8b, fold_consts.8b		// J = A3*B
-	pmull		t9.8h, ad.8b, bd3.8b			// I = A*B3
-	pmull		t3.8h, ad.8b, bd4.8b			// K = A*B4
-	b		0f
-
-.L__pmull_p8_core2:
-	tbl		t4.16b, {ad.16b}, perm1.16b		// A1
-	tbl		t5.16b, {ad.16b}, perm2.16b		// A2
-	tbl		t6.16b, {ad.16b}, perm3.16b		// A3
-
-	pmull2		t4.8h, t4.16b, fold_consts.16b		// F = A1*B
-	pmull2		t8.8h, ad.16b, bd1.16b			// E = A*B1
-	pmull2		t5.8h, t5.16b, fold_consts.16b		// H = A2*B
-	pmull2		t7.8h, ad.16b, bd2.16b			// G = A*B2
-	pmull2		t6.8h, t6.16b, fold_consts.16b		// J = A3*B
-	pmull2		t9.8h, ad.16b, bd3.16b			// I = A*B3
-	pmull2		t3.8h, ad.16b, bd4.16b			// K = A*B4
-
-0:	eor		t4.16b, t4.16b, t8.16b			// L = E + F
-	eor		t5.16b, t5.16b, t7.16b			// M = G + H
-	eor		t6.16b, t6.16b, t9.16b			// N = I + J
-
-	uzp1		t8.2d, t4.2d, t5.2d
-	uzp2		t4.2d, t4.2d, t5.2d
-	uzp1		t7.2d, t6.2d, t3.2d
-	uzp2		t6.2d, t6.2d, t3.2d
-
-	// t4 = (L) (P0 + P1) << 8
-	// t5 = (M) (P2 + P3) << 16
-	eor		t8.16b, t8.16b, t4.16b
-	and		t4.16b, t4.16b, k32_48.16b
-
-	// t6 = (N) (P4 + P5) << 24
-	// t7 = (K) (P6 + P7) << 32
-	eor		t7.16b, t7.16b, t6.16b
-	and		t6.16b, t6.16b, k00_16.16b
-
-	eor		t8.16b, t8.16b, t4.16b
-	eor		t7.16b, t7.16b, t6.16b
-
-	zip2		t5.2d, t8.2d, t4.2d
-	zip1		t4.2d, t8.2d, t4.2d
-	zip2		t3.2d, t7.2d, t6.2d
-	zip1		t6.2d, t7.2d, t6.2d
-
-	ext		t4.16b, t4.16b, t4.16b, #15
-	ext		t5.16b, t5.16b, t5.16b, #14
-	ext		t6.16b, t6.16b, t6.16b, #13
-	ext		t3.16b, t3.16b, t3.16b, #12
-
-	eor		t4.16b, t4.16b, t5.16b
-	eor		t6.16b, t6.16b, t3.16b
-	ret
-SYM_FUNC_END(__pmull_p8_core)
+	perm		.req	v27
 
 	.macro		pmull16x64_p64, a16, b64, c64
 	pmull2		\c64\().1q, \a16\().2d, \b64\().2d

@@ -266,7 +147,7 @@ SYM_FUNC_END(__pmull_p8_core)
 	 */
 	.macro		pmull16x64_p8, a16, b64, c64
 	ext		t7.16b, \b64\().16b, \b64\().16b, #1
-	tbl		t5.16b, {\a16\().16b}, bd1.16b
+	tbl		t5.16b, {\a16\().16b}, perm.16b
 	uzp1		t7.16b, \b64\().16b, t7.16b
 	bl		__pmull_p8_16x64
 	ext		\b64\().16b, t4.16b, t4.16b, #15

@@ -292,22 +173,6 @@ SYM_FUNC_START_LOCAL(__pmull_p8_16x64)
 	ret
 SYM_FUNC_END(__pmull_p8_16x64)
 
-	.macro		__pmull_p8, rq, ad, bd, i
-	.ifnc		\bd, fold_consts
-	.err
-	.endif
-	mov		ad.16b, \ad\().16b
-	.ifb		\i
-	pmull		\rq\().8h, \ad\().8b, \bd\().8b		// D = A*B
-	.else
-	pmull2		\rq\().8h, \ad\().16b, \bd\().16b	// D = A*B
-	.endif
-
-	bl		.L__pmull_p8_core\i
-
-	eor		\rq\().16b, \rq\().16b, t4.16b
-	eor		\rq\().16b, \rq\().16b, t6.16b
-	.endm
 
 	// Fold reg1, reg2 into the next 32 data bytes, storing the result back
 	// into reg1, reg2.

@@ -340,16 +205,7 @@ CPU_LE(	ext		v12.16b, v12.16b, v12.16b, #8	)
 	eor		\dst_reg\().16b, \dst_reg\().16b, \src_reg\().16b
 	.endm
 
-	.macro		__pmull_p64, rd, rn, rm, n
-	.ifb		\n
-	pmull		\rd\().1q, \rn\().1d, \rm\().1d
-	.else
-	pmull2		\rd\().1q, \rn\().2d, \rm\().2d
-	.endif
-	.endm
-
 	.macro		crc_t10dif_pmull, p
-	__pmull_init_\p
 
 	// For sizes less than 256 bytes, we can't fold 128 bytes at a time.
 	cmp		len, #256

@@ -479,47 +335,7 @@ CPU_LE(	ext		v0.16b, v0.16b, v0.16b, #8	)
 	pmull16x64_\p	fold_consts, v3, v0
 	eor		v7.16b, v3.16b, v0.16b
 	eor		v7.16b, v7.16b, v2.16b
-
-.Lreduce_final_16_bytes_\@:
-	// Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC.
-
-	movi		v2.16b, #0		// init zero register
-
-	// Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
-	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
-	__pmull_pre_\p	fold_consts
-
-	// Fold the high 64 bits into the low 64 bits, while also multiplying by
-	// x^64.  This produces a 128-bit value congruent to x^64 * M(x) and
-	// whose low 48 bits are 0.
-	ext		v0.16b, v2.16b, v7.16b, #8
-	__pmull_\p	v7, v7, fold_consts, 2	// high bits * x^48 * (x^80 mod G(x))
-	eor		v0.16b, v0.16b, v7.16b	// + low bits * x^64
-
-	// Fold the high 32 bits into the low 96 bits.  This produces a 96-bit
-	// value congruent to x^64 * M(x) and whose low 48 bits are 0.
-	ext		v1.16b, v0.16b, v2.16b, #12	// extract high 32 bits
-	mov		v0.s[3], v2.s[0]	// zero high 32 bits
-	__pmull_\p	v1, v1, fold_consts	// high 32 bits * x^48 * (x^48 mod G(x))
-	eor		v0.16b, v0.16b, v1.16b	// + low bits
-
-	// Load G(x) and floor(x^48 / G(x)).
-	ld1		{fold_consts.2d}, [fold_consts_ptr]
-	__pmull_pre_\p	fold_consts
-
-	// Use Barrett reduction to compute the final CRC value.
-	__pmull_\p	v1, v0, fold_consts, 2	// high 32 bits * floor(x^48 / G(x))
-	ushr		v1.2d, v1.2d, #32	// /= x^32
-	__pmull_\p	v1, v1, fold_consts	// *= G(x)
-	ushr		v0.2d, v0.2d, #48
-	eor		v0.16b, v0.16b, v1.16b	// + low 16 nonzero bits
-	// Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
-
-	umov		w0, v0.h[0]
-	.ifc		\p, p8
-	frame_pop
-	.endif
-	ret
+	b		.Lreduce_final_16_bytes_\@
 
 .Lless_than_256_bytes_\@:
 	// Checksumming a buffer of length 16...255 bytes

@@ -545,6 +361,8 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 	b.ge		.Lfold_16_bytes_loop_\@		// 32 <= len <= 255
 	add		len, len, #16
 	b		.Lhandle_partial_segment_\@	// 17 <= len <= 31
+
+.Lreduce_final_16_bytes_\@:
 	.endm
 
 //

@@ -554,7 +372,22 @@ CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
 //
 SYM_FUNC_START(crc_t10dif_pmull_p8)
 	frame_push	1
+
+	// Compose { 0,0,0,0, 8,8,8,8, 1,1,1,1, 9,9,9,9 }
+	movi		perm.4h, #8, lsl #8
+	orr		perm.2s, #1, lsl #16
+	orr		perm.2s, #1, lsl #24
+	zip1		perm.16b, perm.16b, perm.16b
+	zip1		perm.16b, perm.16b, perm.16b
+
 	crc_t10dif_pmull p8
+
+CPU_LE(	rev64		v7.16b, v7.16b			)
+CPU_LE(	ext		v7.16b, v7.16b, v7.16b, #8	)
+	str		q7, [x3]
+
+	frame_pop
+	ret
 SYM_FUNC_END(crc_t10dif_pmull_p8)
 
 	.align		5

@@ -565,6 +398,41 @@ SYM_FUNC_END(crc_t10dif_pmull_p8)
 //
 SYM_FUNC_START(crc_t10dif_pmull_p64)
 	crc_t10dif_pmull	p64
+
+	// Reduce the 128-bit value M(x), stored in v7, to the final 16-bit CRC.
+
+	movi		v2.16b, #0		// init zero register
+
+	// Load 'x^48 * (x^48 mod G(x))' and 'x^48 * (x^80 mod G(x))'.
+	ld1		{fold_consts.2d}, [fold_consts_ptr], #16
+
+	// Fold the high 64 bits into the low 64 bits, while also multiplying by
+	// x^64.  This produces a 128-bit value congruent to x^64 * M(x) and
+	// whose low 48 bits are 0.
+	ext		v0.16b, v2.16b, v7.16b, #8
+	pmull2		v7.1q, v7.2d, fold_consts.2d	// high bits * x^48 * (x^80 mod G(x))
+	eor		v0.16b, v0.16b, v7.16b		// + low bits * x^64
+
+	// Fold the high 32 bits into the low 96 bits.  This produces a 96-bit
+	// value congruent to x^64 * M(x) and whose low 48 bits are 0.
+	ext		v1.16b, v0.16b, v2.16b, #12	// extract high 32 bits
+	mov		v0.s[3], v2.s[0]		// zero high 32 bits
+	pmull		v1.1q, v1.1d, fold_consts.1d	// high 32 bits * x^48 * (x^48 mod G(x))
+	eor		v0.16b, v0.16b, v1.16b		// + low bits
+
+	// Load G(x) and floor(x^48 / G(x)).
+	ld1		{fold_consts.2d}, [fold_consts_ptr]
+
+	// Use Barrett reduction to compute the final CRC value.
+	pmull2		v1.1q, v0.2d, fold_consts.2d	// high 32 bits * floor(x^48 / G(x))
+	ushr		v1.2d, v1.2d, #32		// /= x^32
+	pmull		v1.1q, v1.1d, fold_consts.1d	// *= G(x)
+	ushr		v0.2d, v0.2d, #48
+	eor		v0.16b, v0.16b, v1.16b		// + low 16 nonzero bits
+	// Final CRC value (x^16 * M(x)) mod G(x) is in low 16 bits of v0.
+
+	umov		w0, v0.h[0]
+	ret
 SYM_FUNC_END(crc_t10dif_pmull_p64)
 
 	.section	".rodata", "a"

index 46c02c518a30..4dac32e020de 100644
@@ -144,11 +144,6 @@ CPU_LE(	vrev64.8	q12, q12	)
 	veor.8		\dst_reg, \dst_reg, \src_reg
 	.endm
 
-	.macro		__adrl, out, sym
-	movw		\out, #:lower16:\sym
-	movt		\out, #:upper16:\sym
-	.endm
-
 //
 // u16 crc_t10dif_pmull(u16 init_crc, const u8 *buf, size_t len);
 //

@@ -160,7 +155,7 @@ ENTRY(crc_t10dif_pmull)
 	cmp		len, #256
 	blt		.Lless_than_256_bytes
 
-	__adrl		fold_consts_ptr, .Lfold_across_128_bytes_consts
+	mov_l		fold_consts_ptr, .Lfold_across_128_bytes_consts
 
 	// Load the first 128 data bytes.  Byte swapping is necessary to make
 	// the bit order match the polynomial coefficient order.

@@ -262,7 +257,7 @@ CPU_LE(	vrev64.8	q0, q0	)
 	vswp		q0l, q0h
 
 	// q1 = high order part of second chunk: q7 left-shifted by 'len' bytes.
-	__adrl		r3, .Lbyteshift_table + 16
+	mov_l		r3, .Lbyteshift_table + 16
 	sub		r3, r3, len
 	vld1.8		{q2}, [r3]
 	vtbl.8		q1l, {q7l-q7h}, q2l

@@ -324,7 +319,7 @@ CPU_LE(	vrev64.8	q0, q0	)
 .Lless_than_256_bytes:
 	// Checksumming a buffer of length 16...255 bytes
 
-	__adrl		fold_consts_ptr, .Lfold_across_16_bytes_consts
+	mov_l		fold_consts_ptr, .Lfold_across_16_bytes_consts
 
 	// Load the first 16 data bytes.
 	vld1.64		{q7}, [buf]!

index 4dac32e020de..6b72167574b2 100644
@@ -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

index 6b72167574b2..2bbf2df9c1e2 100644
@@ -112,6 +112,82 @@
 	FOLD_CONST_L	.req	q10l
 	FOLD_CONST_H	.req	q10h
 
+	/*
+	 * Pairwise long polynomial multiplication of two 16-bit values
+	 *
+	 *   { w0, w1 }, { y0, y1 }
+	 *
+	 * by two 64-bit values
+	 *
+	 *   { x0, x1, x2, x3, x4, x5, x6, x7 }, { z0, z1, z2, z3, z4, z5, z6, z7 }
+	 *
+	 * where each vector element is a byte, ordered from least to most
+	 * significant. The resulting 80-bit vectors are XOR'ed together.
+	 *
+	 * This can be implemented using 8x8 long polynomial multiplication, by
+	 * reorganizing the input so that each pairwise 8x8 multiplication
+	 * produces one of the terms from the decomposition below, and
+	 * combining the results of each rank and shifting them into place.
+	 *
+	 * Rank
+	 *  0            w0*x0 ^              |        y0*z0 ^
+	 *  1       (w0*x1 ^ w1*x0) <<  8 ^   |   (y0*z1 ^ y1*z0) <<  8 ^
+	 *  2       (w0*x2 ^ w1*x1) << 16 ^   |   (y0*z2 ^ y1*z1) << 16 ^
+	 *  3       (w0*x3 ^ w1*x2) << 24 ^   |   (y0*z3 ^ y1*z2) << 24 ^
+	 *  4       (w0*x4 ^ w1*x3) << 32 ^   |   (y0*z4 ^ y1*z3) << 32 ^
+	 *  5       (w0*x5 ^ w1*x4) << 40 ^   |   (y0*z5 ^ y1*z4) << 40 ^
+	 *  6       (w0*x6 ^ w1*x5) << 48 ^   |   (y0*z6 ^ y1*z5) << 48 ^
+	 *  7       (w0*x7 ^ w1*x6) << 56 ^   |   (y0*z7 ^ y1*z6) << 56 ^
+	 *  8            w1*x7      << 64     |        y1*z7      << 64
+	 *
+	 * The inputs can be reorganized into
+	 *
+	 *   { w0, w0, w0, w0, y0, y0, y0, y0 }, { w1, w1, w1, w1, y1, y1, y1, y1 }
+	 *   { x0, x2, x4, x6, z0, z2, z4, z6 }, { x1, x3, x5, x7, z1, z3, z5, z7 }
+	 *
+	 * and after performing 8x8->16 bit long polynomial multiplication of
+	 * each of the halves of the first vector with those of the second one,
+	 * we obtain the following four vectors of 16-bit elements:
+	 *
+	 *   a := { w0*x0, w0*x2, w0*x4, w0*x6 }, { y0*z0, y0*z2, y0*z4, y0*z6 }
+	 *   b := { w0*x1, w0*x3, w0*x5, w0*x7 }, { y0*z1, y0*z3, y0*z5, y0*z7 }
+	 *   c := { w1*x0, w1*x2, w1*x4, w1*x6 }, { y1*z0, y1*z2, y1*z4, y1*z6 }
+	 *   d := { w1*x1, w1*x3, w1*x5, w1*x7 }, { y1*z1, y1*z3, y1*z5, y1*z7 }
+	 *
+	 * Results b and c can be XORed together, as the vector elements have
+	 * matching ranks. Then, the final XOR can be pulled forward, and
+	 * applied between the halves of each of the remaining three vectors,
+	 * which are then shifted into place, and XORed together to produce the
+	 * final 80-bit result.
+	 */
+        .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
+
+__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_p64, v16, v64
 	vmull.p64	q11, \v64\()l, \v16\()_L
 	vmull.p64	\v64, \v64\()h, \v16\()_H

@@ -249,9 +325,9 @@ 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 +417,20 @@ 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 +463,6 @@ 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