crypto: x86_64 optimized XChaCha and NHPoly1305 (for Adiantum)

index ce4e43642984..2a6acb4de373 100644
@@ -47,6 +47,8 @@ obj-$(CONFIG_CRYPTO_MORUS1280_GLUE) += morus1280_glue.o
 obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o
 obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o
 
+obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
+
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)
 	obj-$(CONFIG_CRYPTO_CAMELLIA_AESNI_AVX_X86_64) += \

@@ -85,6 +87,8 @@ aegis256-aesni-y := aegis256-aesni-asm.o aegis256-aesni-glue.o
 morus640-sse2-y := morus640-sse2-asm.o morus640-sse2-glue.o
 morus1280-sse2-y := morus1280-sse2-asm.o morus1280-sse2-glue.o
 
+nhpoly1305-sse2-y := nh-sse2-x86_64.o nhpoly1305-sse2-glue.o
+
 ifeq ($(avx_supported),yes)
 	camellia-aesni-avx-x86_64-y := camellia-aesni-avx-asm_64.o \
 					camellia_aesni_avx_glue.o

123 lines not on this page · raw message

index b6376d5d973e..b85133966d64 100644
@@ -501,6 +501,14 @@ config CRYPTO_NHPOLY1305
 	select CRYPTO_HASH
 	select CRYPTO_POLY1305
 
+config CRYPTO_NHPOLY1305_SSE2
+	tristate "NHPoly1305 hash function (x86_64 SSE2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_NHPOLY1305
+	help
+	  SSE2 optimized implementation of the hash function used by the
+	  Adiantum encryption mode.
+
 config CRYPTO_ADIANTUM
 	tristate "Adiantum support"
 	select CRYPTO_CHACHA20

index 2a6acb4de373..0b31b16f49d8 100644
@@ -48,6 +48,7 @@ obj-$(CONFIG_CRYPTO_MORUS640_SSE2) += morus640-sse2.o
 obj-$(CONFIG_CRYPTO_MORUS1280_SSE2) += morus1280-sse2.o
 
 obj-$(CONFIG_CRYPTO_NHPOLY1305_SSE2) += nhpoly1305-sse2.o
+obj-$(CONFIG_CRYPTO_NHPOLY1305_AVX2) += nhpoly1305-avx2.o
 
 # These modules require assembler to support AVX.
 ifeq ($(avx_supported),yes)

@@ -106,6 +107,8 @@ ifeq ($(avx2_supported),yes)
 	serpent-avx2-y := serpent-avx2-asm_64.o serpent_avx2_glue.o
 
 	morus1280-avx2-y := morus1280-avx2-asm.o morus1280-avx2-glue.o
+
+	nhpoly1305-avx2-y := nh-avx2-x86_64.o nhpoly1305-avx2-glue.o
 endif
 
 ifeq ($(avx512_supported),yes)

157 lines not on this page · raw message

index b85133966d64..e084e2fb6743 100644
@@ -509,6 +509,14 @@ config CRYPTO_NHPOLY1305_SSE2
 	  SSE2 optimized implementation of the hash function used by the
 	  Adiantum encryption mode.
 
+config CRYPTO_NHPOLY1305_AVX2
+	tristate "NHPoly1305 hash function (x86_64 AVX2 implementation)"
+	depends on X86 && 64BIT
+	select CRYPTO_NHPOLY1305
+	help
+	  AVX2 optimized implementation of the hash function used by the
+	  Adiantum encryption mode.
+
 config CRYPTO_ADIANTUM
 	tristate "Adiantum support"
 	select CRYPTO_CHACHA20

index d8ac75bb448f..f6792789f875 100644
@@ -10,6 +10,7 @@
  */
 
 #include <linux/linkage.h>
+#include <asm/frame.h>
 
 .section	.rodata.cst16.ROT8, "aM", @progbits, 16
 .align 16

@@ -23,37 +24,24 @@ CTRINC:	.octa 0x00000003000000020000000100000000
 
 .text
 
-ENTRY(chacha20_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
-
-	# This function encrypts one ChaCha20 block by loading the state matrix
-	# in four SSE registers. It performs matrix operation on four words in
-	# parallel, but requires shuffling to rearrange the words after each
-	# round. 8/16-bit word rotation is done with the slightly better
-	# performing SSSE3 byte shuffling, 7/12-bit word rotation uses
-	# traditional shift+OR.
-
-	# x0..3 = s0..3
-	movdqa		0x00(%rdi),%xmm0
-	movdqa		0x10(%rdi),%xmm1
-	movdqa		0x20(%rdi),%xmm2
-	movdqa		0x30(%rdi),%xmm3
-	movdqa		%xmm0,%xmm8
-	movdqa		%xmm1,%xmm9
-	movdqa		%xmm2,%xmm10
-	movdqa		%xmm3,%xmm11
+/*
+ * chacha20_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
+ * shuffling to rearrange the words after each round.  8/16-bit word rotation is
+ * done with the slightly better performing SSSE3 byte shuffling, 7/12-bit word
+ * rotation uses traditional shift+OR.
+ *
+ * Clobbers: %ecx, %xmm4-%xmm7
+ */
+chacha20_permute:
 
 	movdqa		ROT8(%rip),%xmm4
 	movdqa		ROT16(%rip),%xmm5
-
-	mov		%rcx,%rax
 	mov		$10,%ecx
 
 .Ldoubleround:
-
 	# x0 += x1, x3 = rotl32(x3 ^ x0, 16)
 	paddd		%xmm1,%xmm0
 	pxor		%xmm0,%xmm3

@@ -123,6 +111,29 @@ ENTRY(chacha20_block_xor_ssse3)
 	dec		%ecx
 	jnz		.Ldoubleround
 
+	ret
+ENDPROC(chacha20_permute)
+
+ENTRY(chacha20_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
+	FRAME_BEGIN
+
+	# x0..3 = s0..3
+	movdqa		0x00(%rdi),%xmm0
+	movdqa		0x10(%rdi),%xmm1
+	movdqa		0x20(%rdi),%xmm2
+	movdqa		0x30(%rdi),%xmm3
+	movdqa		%xmm0,%xmm8
+	movdqa		%xmm1,%xmm9
+	movdqa		%xmm2,%xmm10
+	movdqa		%xmm3,%xmm11
+
+	mov		%rcx,%rax
+	call		chacha20_permute
+
 	# o0 = i0 ^ (x0 + s0)
 	paddd		%xmm8,%xmm0
 	cmp		$0x10,%rax

@@ -156,6 +167,7 @@ ENTRY(chacha20_block_xor_ssse3)
 	movdqu		%xmm0,0x30(%rsi)
 
 .Ldone:
+	FRAME_END
 	ret
 
 .Lxorpart:

@@ -189,6 +201,25 @@ ENTRY(chacha20_block_xor_ssse3)
 
 ENDPROC(chacha20_block_xor_ssse3)
 
+ENTRY(hchacha20_block_ssse3)
+	# %rdi: Input state matrix, s
+	# %rsi: output (8 32-bit words)
+	FRAME_BEGIN
+
+	movdqa		0x00(%rdi),%xmm0
+	movdqa		0x10(%rdi),%xmm1
+	movdqa		0x20(%rdi),%xmm2
+	movdqa		0x30(%rdi),%xmm3
+
+	call		chacha20_permute
+
+	movdqu		%xmm0,0x00(%rsi)
+	movdqu		%xmm3,0x10(%rsi)
+
+	FRAME_END
+	ret
+ENDPROC(hchacha20_block_ssse3)
+
 ENTRY(chacha20_4block_xor_ssse3)
 	# %rdi: Input state matrix, s
 	# %rsi: up to 4 data blocks output, o

index e084e2fb6743..df466771e9bf 100644
@@ -1468,19 +1468,13 @@ config CRYPTO_CHACHA20
 	  in some performance-sensitive scenarios.
 
 config CRYPTO_CHACHA20_X86_64
-	tristate "ChaCha20 cipher algorithm (x86_64/SSSE3/AVX2)"
+	tristate "ChaCha stream cipher algorithms (x86_64/SSSE3/AVX2/AVX-512VL)"
 	depends on X86 && 64BIT
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 	help
-	  ChaCha20 cipher algorithm, RFC7539.
-
-	  ChaCha20 is a 256-bit high-speed stream cipher designed by Daniel J.
-	  Bernstein and further specified in RFC7539 for use in IETF protocols.
-	  This is the x86_64 assembler implementation using SIMD instructions.
-
-	  See also:
-	  <http://cr.yp.to/chacha/chacha-20080128.pdf>
+	  SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20
+	  and XChaCha20 stream ciphers.
 
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"

index 0b31b16f49d8..45734e1cf967 100644
@@ -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

similarity index 97%
rename from arch/x86/crypto/chacha20-avx2-x86_64.S
rename to arch/x86/crypto/chacha-avx2-x86_64.S
index b6ab082be657..32903fd450af 100644
@@ -1,5 +1,5 @@
 /*
- * 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)

similarity index 97%
rename from arch/x86/crypto/chacha20-avx512vl-x86_64.S
rename to arch/x86/crypto/chacha-avx512vl-x86_64.S
index 55d34de29e3e..848f9c75fd4f 100644
@@ -1,6 +1,6 @@
 /* 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)

123 lines not on this page · raw message

index df466771e9bf..29865c599b04 100644
@@ -1473,8 +1473,8 @@ config CRYPTO_CHACHA20_X86_64
 	select CRYPTO_BLKCIPHER
 	select CRYPTO_CHACHA20
 	help
-	  SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20
-	  and XChaCha20 stream ciphers.
+	  SSSE3, AVX2, and AVX-512VL optimized implementations of the ChaCha20,
+	  XChaCha20, and XChaCha12 stream ciphers.
 
 config CRYPTO_SEED
 	tristate "SEED cipher algorithm"