crypto: x86/chacha20 - refactor to allow varying number of rounds

In preparation for adding XChaCha12 support, rename/refactor the x86_64
SIMD implementations of ChaCha20 to support different numbers of rounds.
Reviewed-by: Martin Willi <martin@strongswan.org>
Signed-off-by: Eric Biggers <ebiggers@google.com>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>

arch/x86/crypto/Makefile

@@ -24,7 +24,7 @@ obj-$(CONFIG_CRYPTO_CAMELLIA_X86_64) += camellia-x86_64.o
 obj-$(CONFIG_CRYPTO_BLOWFISH_X86_64) += blowfish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64) += twofish-x86_64.o
 obj-$(CONFIG_CRYPTO_TWOFISH_X86_64_3WAY) += twofish-x86_64-3way.o
-obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha20-x86_64.o
+obj-$(CONFIG_CRYPTO_CHACHA20_X86_64) += chacha-x86_64.o
 obj-$(CONFIG_CRYPTO_SERPENT_SSE2_X86_64) += serpent-sse2-x86_64.o
 obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o
 obj-$(CONFIG_CRYPTO_GHASH_CLMUL_NI_INTEL) += ghash-clmulni-intel.o
@@ -78,7 +78,7 @@ camellia-x86_64-y := camellia-x86_64-asm_64.o camellia_glue.o
 blowfish-x86_64-y := blowfish-x86_64-asm_64.o blowfish_glue.o
 twofish-x86_64-y := twofish-x86_64-asm_64.o twofish_glue.o
 twofish-x86_64-3way-y := twofish-x86_64-asm_64-3way.o twofish_glue_3way.o
-chacha20-x86_64-y := chacha20-ssse3-x86_64.o chacha20_glue.o
+chacha-x86_64-y := chacha-ssse3-x86_64.o chacha_glue.o
 serpent-sse2-x86_64-y := serpent-sse2-x86_64-asm_64.o serpent_sse2_glue.o
 
 aegis128-aesni-y := aegis128-aesni-asm.o aegis128-aesni-glue.o
@@ -103,7 +103,7 @@ endif
 
 ifeq ($(avx2_supported),yes)
 	camellia-aesni-avx2-y := camellia-aesni-avx2-asm_64.o camellia_aesni_avx2_glue.o
-	chacha20-x86_64-y += chacha20-avx2-x86_64.o
+	chacha-x86_64-y += chacha-avx2-x86_64.o
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 
 	morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o
@@ -112,7 +112,7 @@ ifeq ($(avx2_supported),yes)
 endif
 
 ifeq ($(avx512_supported),yes)
-	chacha20-x86_64-y += chacha20-avx512vl-x86_64.o
+	chacha-x86_64-y += chacha-avx512vl-x86_64.o
 endif
 
 aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o

arch/x86/crypto/chacha20-avx2-x86_64.S → arch/x86/crypto/chacha-avx2-x86_64.S

 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX2 functions
+ * ChaCha 256-bit cipher algorithm, x64 AVX2 functions
  *
  * Copyright (C) 2015 Martin Willi
  *
@@ -38,13 +38,14 @@ CTR4BL:	.octa 0x00000000000000000000000000000002
 
 .text
 
-ENTRY(chacha20_2block_xor_avx2)
+ENTRY(chacha_2block_xor_avx2)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 2 data blocks output, o
 	# %rdx: up to 2 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts two ChaCha20 blocks by loading the state
+	# This function encrypts two ChaCha blocks by loading the state
 	# matrix twice across four AVX registers. It performs matrix operations
 	# on four words in each matrix in parallel, but requires shuffling to
 	# rearrange the words after each round.
@@ -68,7 +69,6 @@ ENTRY(chacha20_2block_xor_avx2)
 	vmovdqa		ROT16(%rip),%ymm5
 
 	mov		%rcx,%rax
-	mov		$10,%ecx
 
 .Ldoubleround:
 
@@ -138,7 +138,7 @@ ENTRY(chacha20_2block_xor_avx2)
 	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
 	vpshufd		$0x39,%ymm3,%ymm3
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround
 
 	# o0 = i0 ^ (x0 + s0)
@@ -228,15 +228,16 @@ ENTRY(chacha20_2block_xor_avx2)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone2
 
-ENDPROC(chacha20_2block_xor_avx2)
+ENDPROC(chacha_2block_xor_avx2)
 
-ENTRY(chacha20_4block_xor_avx2)
+ENTRY(chacha_4block_xor_avx2)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
 	# %rdx: up to 4 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts four ChaCha20 block by loading the state
+	# This function encrypts four ChaCha blocks by loading the state
 	# matrix four times across eight AVX registers. It performs matrix
 	# operations on four words in two matrices in parallel, sequentially
 	# to the operations on the four words of the other two matrices. The
@@ -269,7 +270,6 @@ ENTRY(chacha20_4block_xor_avx2)
 	vmovdqa		ROT16(%rip),%ymm9
 
 	mov		%rcx,%rax
-	mov		$10,%ecx
 
 .Ldoubleround4:
 
@@ -389,7 +389,7 @@ ENTRY(chacha20_4block_xor_avx2)
 	vpshufd		$0x39,%ymm3,%ymm3
 	vpshufd		$0x39,%ymm7,%ymm7
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround4
 
 	# o0 = i0 ^ (x0 + s0), first block
@@ -533,15 +533,16 @@ ENTRY(chacha20_4block_xor_avx2)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone4
 
-ENDPROC(chacha20_4block_xor_avx2)
+ENDPROC(chacha_4block_xor_avx2)
 
-ENTRY(chacha20_8block_xor_avx2)
+ENTRY(chacha_8block_xor_avx2)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 8 data blocks output, o
 	# %rdx: up to 8 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts eight consecutive ChaCha20 blocks by loading
+	# This function encrypts eight consecutive ChaCha blocks by loading
 	# the state matrix in AVX registers eight times. As we need some
 	# scratch registers, we save the first four registers on the stack. The
 	# algorithm performs each operation on the corresponding word of each
@@ -588,8 +589,6 @@ ENTRY(chacha20_8block_xor_avx2)
 	# x12 += counter values 0-3
 	vpaddd		%ymm1,%ymm12,%ymm12
 
-	mov		$10,%ecx
-
 .Ldoubleround8:
 	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
 	vpaddd		0x00(%rsp),%ymm4,%ymm0
@@ -775,7 +774,7 @@ ENTRY(chacha20_8block_xor_avx2)
 	vpsrld		$25,%ymm4,%ymm4
 	vpor		%ymm0,%ymm4,%ymm4
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround8
 
 	# x0..15[0-3] += s[0..15]
@@ -1023,4 +1022,4 @@ ENTRY(chacha20_8block_xor_avx2)
 
 	jmp		.Ldone8
 
-ENDPROC(chacha20_8block_xor_avx2)
+ENDPROC(chacha_8block_xor_avx2)

arch/x86/crypto/chacha20-avx512vl-x86_64.S → arch/x86/crypto/chacha-avx512vl-x86_64.S

 /* SPDX-License-Identifier: GPL-2.0+ */
 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 AVX-512VL functions
+ * ChaCha 256-bit cipher algorithm, x64 AVX-512VL functions
  *
  * Copyright (C) 2018 Martin Willi
  */
@@ -24,13 +24,14 @@ CTR8BL:	.octa 0x00000003000000020000000100000000
 
 .text
 
-ENTRY(chacha20_2block_xor_avx512vl)
+ENTRY(chacha_2block_xor_avx512vl)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 2 data blocks output, o
 	# %rdx: up to 2 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts two ChaCha20 blocks by loading the state
+	# This function encrypts two ChaCha blocks by loading the state
 	# matrix twice across four AVX registers. It performs matrix operations
 	# on four words in each matrix in parallel, but requires shuffling to
 	# rearrange the words after each round.
@@ -50,8 +51,6 @@ ENTRY(chacha20_2block_xor_avx512vl)
 	vmovdqa		%ymm2,%ymm10
 	vmovdqa		%ymm3,%ymm11
 
-	mov		$10,%rax
-
 .Ldoubleround:
 
 	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
@@ -108,7 +107,7 @@ ENTRY(chacha20_2block_xor_avx512vl)
 	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
 	vpshufd		$0x39,%ymm3,%ymm3
 
-	dec		%rax
+	sub		$2,%r8d
 	jnz		.Ldoubleround
 
 	# o0 = i0 ^ (x0 + s0)
@@ -188,15 +187,16 @@ ENTRY(chacha20_2block_xor_avx512vl)
 
 	jmp		.Ldone2
 
-ENDPROC(chacha20_2block_xor_avx512vl)
+ENDPROC(chacha_2block_xor_avx512vl)
 
-ENTRY(chacha20_4block_xor_avx512vl)
+ENTRY(chacha_4block_xor_avx512vl)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
 	# %rdx: up to 4 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts four ChaCha20 block by loading the state
+	# This function encrypts four ChaCha blocks by loading the state
 	# matrix four times across eight AVX registers. It performs matrix
 	# operations on four words in two matrices in parallel, sequentially
 	# to the operations on the four words of the other two matrices. The
@@ -225,8 +225,6 @@ ENTRY(chacha20_4block_xor_avx512vl)
 	vmovdqa		%ymm3,%ymm14
 	vmovdqa		%ymm7,%ymm15
 
-	mov		$10,%rax
-
 .Ldoubleround4:
 
 	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
@@ -321,7 +319,7 @@ ENTRY(chacha20_4block_xor_avx512vl)
 	vpshufd		$0x39,%ymm3,%ymm3
 	vpshufd		$0x39,%ymm7,%ymm7
 
-	dec		%rax
+	sub		$2,%r8d
 	jnz		.Ldoubleround4
 
 	# o0 = i0 ^ (x0 + s0), first block
@@ -455,15 +453,16 @@ ENTRY(chacha20_4block_xor_avx512vl)
 
 	jmp		.Ldone4
 
-ENDPROC(chacha20_4block_xor_avx512vl)
+ENDPROC(chacha_4block_xor_avx512vl)
 
-ENTRY(chacha20_8block_xor_avx512vl)
+ENTRY(chacha_8block_xor_avx512vl)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 8 data blocks output, o
 	# %rdx: up to 8 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts eight consecutive ChaCha20 blocks by loading
+	# This function encrypts eight consecutive ChaCha blocks by loading
 	# the state matrix in AVX registers eight times. Compared to AVX2, this
 	# mostly benefits from the new rotate instructions in VL and the
 	# additional registers.
@@ -508,8 +507,6 @@ ENTRY(chacha20_8block_xor_avx512vl)
 	vmovdqa64	%ymm14,%ymm30
 	vmovdqa64	%ymm15,%ymm31
 
-	mov		$10,%eax
-
 .Ldoubleround8:
 	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
 	vpaddd		%ymm0,%ymm4,%ymm0
@@ -647,7 +644,7 @@ ENTRY(chacha20_8block_xor_avx512vl)
 	vpxord		%ymm9,%ymm4,%ymm4
 	vprold		$7,%ymm4,%ymm4
 
-	dec		%eax
+	sub		$2,%r8d
 	jnz		.Ldoubleround8
 
 	# x0..15[0-3] += s[0..15]
@@ -836,4 +833,4 @@ ENTRY(chacha20_8block_xor_avx512vl)
 
 	jmp		.Ldone8
 
-ENDPROC(chacha20_8block_xor_avx512vl)
+ENDPROC(chacha_8block_xor_avx512vl)

arch/x86/crypto/chacha20-ssse3-x86_64.S → arch/x86/crypto/chacha-ssse3-x86_64.S

 /*
- * ChaCha20 256-bit cipher algorithm, RFC7539, x64 SSSE3 functions
+ * ChaCha 256-bit cipher algorithm, x64 SSSE3 functions
  *
  * Copyright (C) 2015 Martin Willi
  *
@@ -25,7 +25,7 @@ CTRINC:	.octa 0x00000003000000020000000100000000
 .text
 
 /*
- * chacha20_permute - permute one block
+ * chacha_permute - permute one block
  *
  * Permute one 64-byte block where the state matrix is in %xmm0-%xmm3.  This
  * function performs matrix operations on four words in parallel, but requires
@@ -33,13 +33,14 @@ CTRINC:	.octa 0x00000003000000020000000100000000
  * done with the slightly better performing SSSE3 byte shuffling, 7/12-bit word
  * rotation uses traditional shift+OR.
  *
- * Clobbers: %ecx, %xmm4-%xmm7
+ * The round count is given in %r8d.
+ *
+ * Clobbers: %r8d, %xmm4-%xmm7
  */
-chacha20_permute:
+chacha_permute:
 
 	movdqa		ROT8(%rip),%xmm4
 	movdqa		ROT16(%rip),%xmm5
-	mov		$10,%ecx
 
 .Ldoubleround:
 	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
@@ -108,17 +109,18 @@ chacha20_permute:
 	# x3 = shuffle32(x3, MASK(0, 3, 2, 1))
 	pshufd		$0x39,%xmm3,%xmm3
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround
 
 	ret
-ENDPROC(chacha20_permute)
+ENDPROC(chacha_permute)
 
-ENTRY(chacha20_block_xor_ssse3)
+ENTRY(chacha_block_xor_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 1 data block output, o
 	# %rdx: up to 1 data block input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 	FRAME_BEGIN
 
 	# x0..3 = s0..3
@@ -132,7 +134,7 @@ ENTRY(chacha20_block_xor_ssse3)
 	movdqa		%xmm3,%xmm11
 
 	mov		%rcx,%rax
-	call		chacha20_permute
+	call		chacha_permute
 
 	# o0 = i0 ^ (x0 + s0)
 	paddd		%xmm8,%xmm0
@@ -199,11 +201,12 @@ ENTRY(chacha20_block_xor_ssse3)
 	lea		-8(%r10),%rsp
 	jmp		.Ldone
 
-ENDPROC(chacha20_block_xor_ssse3)
+ENDPROC(chacha_block_xor_ssse3)
 
-ENTRY(hchacha20_block_ssse3)
+ENTRY(hchacha_block_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: output (8 32-bit words)
+	# %edx: nrounds
 	FRAME_BEGIN
 
 	movdqa		0x00(%rdi),%xmm0
@@ -211,22 +214,24 @@ ENTRY(hchacha20_block_ssse3)
 	movdqa		0x20(%rdi),%xmm2
 	movdqa		0x30(%rdi),%xmm3
 
-	call		chacha20_permute
+	mov		%edx,%r8d
+	call		chacha_permute
 
 	movdqu		%xmm0,0x00(%rsi)
 	movdqu		%xmm3,0x10(%rsi)
 
 	FRAME_END
 	ret
-ENDPROC(hchacha20_block_ssse3)
+ENDPROC(hchacha_block_ssse3)
 
-ENTRY(chacha20_4block_xor_ssse3)
+ENTRY(chacha_4block_xor_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o
 	# %rdx: up to 4 data blocks input, i
 	# %rcx: input/output length in bytes
+	# %r8d: nrounds
 
-	# This function encrypts four consecutive ChaCha20 blocks by loading the
+	# This function encrypts four consecutive ChaCha blocks by loading the
 	# the state matrix in SSE registers four times. As we need some scratch
 	# registers, we save the first four registers on the stack. The
 	# algorithm performs each operation on the corresponding word of each
@@ -279,8 +284,6 @@ ENTRY(chacha20_4block_xor_ssse3)
 	# x12 += counter values 0-3
 	paddd		%xmm1,%xmm12
 
-	mov		$10,%ecx
-
 .Ldoubleround4:
 	# x0 += x4, x12 = rotl32(x12 ^ x0, 16)
 	movdqa		0x00(%rsp),%xmm0
@@ -498,7 +501,7 @@ ENTRY(chacha20_4block_xor_ssse3)
 	psrld		$25,%xmm4
 	por		%xmm0,%xmm4
 
-	dec		%ecx
+	sub		$2,%r8d
 	jnz		.Ldoubleround4
 
 	# x0[0-3] += s0[0]
@@ -789,4 +792,4 @@ ENTRY(chacha20_4block_xor_ssse3)
 
 	jmp		.Ldone4
 
-ENDPROC(chacha20_4block_xor_ssse3)
+ENDPROC(chacha_4block_xor_ssse3)