This patch series provide an accelerated/optimized Chacha20 and Poly1305
implementation for Power10 or later CPU (ppc64le). This module
implements algorithm specified in RFC7539. The implementation
provides 3.5X better performance than the baseline for Chacha20 and
Poly1305 individually and 1.5X improvement for Chacha20/Poly1305
operation.
This patch has been tested with the kernel crypto module tcrypt.ko and
has passed the selftest. The patch is also tested with
CONFIG_CRYPTO_MANAGER_EXTRA_TESTS enabled.
Danny Tsen (5):
An optimized Chacha20 implementation with 8-way unrolling for ppc64le.
Glue code for optmized Chacha20 implementation for ppc64le.
An optimized Poly1305 implementation with 4-way unrolling for ppc64le.
Glue code for optmized Poly1305 implementation for ppc64le.
Update Kconfig and Makefile.
arch/powerpc/crypto/Kconfig | 26 +
arch/powerpc/crypto/Makefile | 4 +
arch/powerpc/crypto/chacha-p10-glue.c | 221 +++++
arch/powerpc/crypto/chacha-p10le-8x.S | 842 ++++++++++++++++++
arch/powerpc/crypto/poly1305-p10-glue.c | 186 ++++
arch/powerpc/crypto/poly1305-p10le_64.S | 1075 +++++++++++++++++++++++
6 files changed, 2354 insertions(+)
create mode 100644 arch/powerpc/crypto/chacha-p10-glue.c
create mode 100644 arch/powerpc/crypto/chacha-p10le-8x.S
create mode 100644 arch/powerpc/crypto/poly1305-p10-glue.c
create mode 100644 arch/powerpc/crypto/poly1305-p10le_64.S
--
2.31.1
Improve overall performance of Poly1305 for Power10 or later CPU.
Signed-off-by: Danny Tsen <[email protected]>
---
arch/powerpc/crypto/poly1305-p10le_64.S | 1075 +++++++++++++++++++++++
1 file changed, 1075 insertions(+)
create mode 100644 arch/powerpc/crypto/poly1305-p10le_64.S
diff --git a/arch/powerpc/crypto/poly1305-p10le_64.S b/arch/powerpc/crypto/poly1305-p10le_64.S
new file mode 100644
index 000000000000..a3c1987f1ecd
--- /dev/null
+++ b/arch/powerpc/crypto/poly1305-p10le_64.S
@@ -0,0 +1,1075 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+#
+# Accelerated poly1305 implementation for ppc64le.
+#
+# Copyright 2023- IBM Corp. All rights reserved
+#
+#===================================================================================
+# Written by Danny Tsen <[email protected]>
+#
+# Poly1305 - this version mainly using vector/VSX/Scalar
+# - 26 bits limbs
+# - Handle multiple 64 byte blcok.
+#
+# Block size 16 bytes
+# key = (r, s)
+# clamp r &= 0x0FFFFFFC0FFFFFFC 0x0FFFFFFC0FFFFFFF
+# p = 2^130 - 5
+# a += m
+# a = (r + a) % p
+# a += s
+#
+# Improve performance by breaking down polynominal to the sum of products with
+# h4 = m1 * r⁴ + m2 * r³ + m3 * r² + m4 * r
+#
+# 07/22/21 - this revison based on the above sum of products. Setup r^4, r^3, r^2, r and s3, s2, s1, s0
+# to 9 vectors for multiplications.
+#
+# setup r^4, r^3, r^2, r vectors
+# vs [r^1, r^3, r^2, r^4]
+# vs0 = [r0,.....]
+# vs1 = [r1,.....]
+# vs2 = [r2,.....]
+# vs3 = [r3,.....]
+# vs4 = [r4,.....]
+# vs5 = [r1*5,...]
+# vs6 = [r2*5,...]
+# vs7 = [r2*5,...]
+# vs8 = [r4*5,...]
+#
+# Each word in a vector consists a member of a "r/s" in [a * r/s].
+#
+# r0, r4*5, r3*5, r2*5, r1*5;
+# r1, r0, r4*5, r3*5, r2*5;
+# r2, r1, r0, r4*5, r3*5;
+# r3, r2, r1, r0, r4*5;
+# r4, r3, r2, r1, r0 ;
+#
+#
+# poly1305_p10le_4blocks( uint8_t *k, uint32_t mlen, uint8_t *m)
+# k = 32 bytes key
+# r3 = k (r, s)
+# r4 = mlen
+# r5 = m
+#
+#include <asm/ppc_asm.h>
+#include <asm/asm-offsets.h>
+#include <asm/asm-compat.h>
+#include <linux/linkage.h>
+
+.machine "any"
+
+.text
+
+.macro SAVE_GPR GPR OFFSET FRAME
+ std \GPR,\OFFSET(\FRAME)
+.endm
+
+.macro SAVE_VRS VRS OFFSET FRAME
+ li 16, \OFFSET
+ stvx \VRS, 16, \FRAME
+.endm
+
+.macro SAVE_VSX VSX OFFSET FRAME
+ li 16, \OFFSET
+ stxvx \VSX, 16, \FRAME
+.endm
+
+.macro RESTORE_GPR GPR OFFSET FRAME
+ ld \GPR,\OFFSET(\FRAME)
+.endm
+
+.macro RESTORE_VRS VRS OFFSET FRAME
+ li 16, \OFFSET
+ lvx \VRS, 16, \FRAME
+.endm
+
+.macro RESTORE_VSX VSX OFFSET FRAME
+ li 16, \OFFSET
+ lxvx \VSX, 16, \FRAME
+.endm
+
+.macro SAVE_REGS
+ mflr 0
+ std 0, 16(1)
+ stdu 1,-752(1)
+
+ SAVE_GPR 14, 112, 1
+ SAVE_GPR 15, 120, 1
+ SAVE_GPR 16, 128, 1
+ SAVE_GPR 17, 136, 1
+ SAVE_GPR 18, 144, 1
+ SAVE_GPR 19, 152, 1
+ SAVE_GPR 20, 160, 1
+ SAVE_GPR 21, 168, 1
+ SAVE_GPR 22, 176, 1
+ SAVE_GPR 23, 184, 1
+ SAVE_GPR 24, 192, 1
+ SAVE_GPR 25, 200, 1
+ SAVE_GPR 26, 208, 1
+ SAVE_GPR 27, 216, 1
+ SAVE_GPR 28, 224, 1
+ SAVE_GPR 29, 232, 1
+ SAVE_GPR 30, 240, 1
+ SAVE_GPR 31, 248, 1
+
+ addi 9, 1, 256
+ SAVE_VRS 20, 0, 9
+ SAVE_VRS 21, 16, 9
+ SAVE_VRS 22, 32, 9
+ SAVE_VRS 23, 48, 9
+ SAVE_VRS 24, 64, 9
+ SAVE_VRS 25, 80, 9
+ SAVE_VRS 26, 96, 9
+ SAVE_VRS 27, 112, 9
+ SAVE_VRS 28, 128, 9
+ SAVE_VRS 29, 144, 9
+ SAVE_VRS 30, 160, 9
+ SAVE_VRS 31, 176, 9
+
+ SAVE_VSX 14, 192, 9
+ SAVE_VSX 15, 208, 9
+ SAVE_VSX 16, 224, 9
+ SAVE_VSX 17, 240, 9
+ SAVE_VSX 18, 256, 9
+ SAVE_VSX 19, 272, 9
+ SAVE_VSX 20, 288, 9
+ SAVE_VSX 21, 304, 9
+ SAVE_VSX 22, 320, 9
+ SAVE_VSX 23, 336, 9
+ SAVE_VSX 24, 352, 9
+ SAVE_VSX 25, 368, 9
+ SAVE_VSX 26, 384, 9
+ SAVE_VSX 27, 400, 9
+ SAVE_VSX 28, 416, 9
+ SAVE_VSX 29, 432, 9
+ SAVE_VSX 30, 448, 9
+ SAVE_VSX 31, 464, 9
+.endm # SAVE_REGS
+
+.macro RESTORE_REGS
+ addi 9, 1, 256
+ RESTORE_VRS 20, 0, 9
+ RESTORE_VRS 21, 16, 9
+ RESTORE_VRS 22, 32, 9
+ RESTORE_VRS 23, 48, 9
+ RESTORE_VRS 24, 64, 9
+ RESTORE_VRS 25, 80, 9
+ RESTORE_VRS 26, 96, 9
+ RESTORE_VRS 27, 112, 9
+ RESTORE_VRS 28, 128, 9
+ RESTORE_VRS 29, 144, 9
+ RESTORE_VRS 30, 160, 9
+ RESTORE_VRS 31, 176, 9
+
+ RESTORE_VSX 14, 192, 9
+ RESTORE_VSX 15, 208, 9
+ RESTORE_VSX 16, 224, 9
+ RESTORE_VSX 17, 240, 9
+ RESTORE_VSX 18, 256, 9
+ RESTORE_VSX 19, 272, 9
+ RESTORE_VSX 20, 288, 9
+ RESTORE_VSX 21, 304, 9
+ RESTORE_VSX 22, 320, 9
+ RESTORE_VSX 23, 336, 9
+ RESTORE_VSX 24, 352, 9
+ RESTORE_VSX 25, 368, 9
+ RESTORE_VSX 26, 384, 9
+ RESTORE_VSX 27, 400, 9
+ RESTORE_VSX 28, 416, 9
+ RESTORE_VSX 29, 432, 9
+ RESTORE_VSX 30, 448, 9
+ RESTORE_VSX 31, 464, 9
+
+ RESTORE_GPR 14, 112, 1
+ RESTORE_GPR 15, 120, 1
+ RESTORE_GPR 16, 128, 1
+ RESTORE_GPR 17, 136, 1
+ RESTORE_GPR 18, 144, 1
+ RESTORE_GPR 19, 152, 1
+ RESTORE_GPR 20, 160, 1
+ RESTORE_GPR 21, 168, 1
+ RESTORE_GPR 22, 176, 1
+ RESTORE_GPR 23, 184, 1
+ RESTORE_GPR 24, 192, 1
+ RESTORE_GPR 25, 200, 1
+ RESTORE_GPR 26, 208, 1
+ RESTORE_GPR 27, 216, 1
+ RESTORE_GPR 28, 224, 1
+ RESTORE_GPR 29, 232, 1
+ RESTORE_GPR 30, 240, 1
+ RESTORE_GPR 31, 248, 1
+
+ addi 1, 1, 752
+ ld 0, 16(1)
+ mtlr 0
+.endm # RESTORE_REGS
+
+#
+# p[0] = a0*r0 + a1*r4*5 + a2*r3*5 + a3*r2*5 + a4*r1*5;
+# p[1] = a0*r1 + a1*r0 + a2*r4*5 + a3*r3*5 + a4*r2*5;
+# p[2] = a0*r2 + a1*r1 + a2*r0 + a3*r4*5 + a4*r3*5;
+# p[3] = a0*r3 + a1*r2 + a2*r1 + a3*r0 + a4*r4*5;
+# p[4] = a0*r4 + a1*r3 + a2*r2 + a3*r1 + a4*r0 ;
+#
+# [r^2, r^3, r^1, r^4]
+# [m3, m2, m4, m1]
+#
+# multiply odd and even words
+.macro mul_odd
+ vmulouw 14, 4, 26
+ vmulouw 10, 5, 3
+ vmulouw 11, 6, 2
+ vmulouw 12, 7, 1
+ vmulouw 13, 8, 0
+ vmulouw 15, 4, 27
+ vaddudm 14, 14, 10
+ vaddudm 14, 14, 11
+ vmulouw 10, 5, 26
+ vmulouw 11, 6, 3
+ vaddudm 14, 14, 12
+ vaddudm 14, 14, 13 # x0
+ vaddudm 15, 15, 10
+ vaddudm 15, 15, 11
+ vmulouw 12, 7, 2
+ vmulouw 13, 8, 1
+ vaddudm 15, 15, 12
+ vaddudm 15, 15, 13 # x1
+ vmulouw 16, 4, 28
+ vmulouw 10, 5, 27
+ vmulouw 11, 6, 26
+ vaddudm 16, 16, 10
+ vaddudm 16, 16, 11
+ vmulouw 12, 7, 3
+ vmulouw 13, 8, 2
+ vaddudm 16, 16, 12
+ vaddudm 16, 16, 13 # x2
+ vmulouw 17, 4, 29
+ vmulouw 10, 5, 28
+ vmulouw 11, 6, 27
+ vaddudm 17, 17, 10
+ vaddudm 17, 17, 11
+ vmulouw 12, 7, 26
+ vmulouw 13, 8, 3
+ vaddudm 17, 17, 12
+ vaddudm 17, 17, 13 # x3
+ vmulouw 18, 4, 30
+ vmulouw 10, 5, 29
+ vmulouw 11, 6, 28
+ vaddudm 18, 18, 10
+ vaddudm 18, 18, 11
+ vmulouw 12, 7, 27
+ vmulouw 13, 8, 26
+ vaddudm 18, 18, 12
+ vaddudm 18, 18, 13 # x4
+.endm
+
+.macro mul_even
+ vmuleuw 9, 4, 26
+ vmuleuw 10, 5, 3
+ vmuleuw 11, 6, 2
+ vmuleuw 12, 7, 1
+ vmuleuw 13, 8, 0
+ vaddudm 14, 14, 9
+ vaddudm 14, 14, 10
+ vaddudm 14, 14, 11
+ vaddudm 14, 14, 12
+ vaddudm 14, 14, 13 # x0
+
+ vmuleuw 9, 4, 27
+ vmuleuw 10, 5, 26
+ vmuleuw 11, 6, 3
+ vmuleuw 12, 7, 2
+ vmuleuw 13, 8, 1
+ vaddudm 15, 15, 9
+ vaddudm 15, 15, 10
+ vaddudm 15, 15, 11
+ vaddudm 15, 15, 12
+ vaddudm 15, 15, 13 # x1
+
+ vmuleuw 9, 4, 28
+ vmuleuw 10, 5, 27
+ vmuleuw 11, 6, 26
+ vmuleuw 12, 7, 3
+ vmuleuw 13, 8, 2
+ vaddudm 16, 16, 9
+ vaddudm 16, 16, 10
+ vaddudm 16, 16, 11
+ vaddudm 16, 16, 12
+ vaddudm 16, 16, 13 # x2
+
+ vmuleuw 9, 4, 29
+ vmuleuw 10, 5, 28
+ vmuleuw 11, 6, 27
+ vmuleuw 12, 7, 26
+ vmuleuw 13, 8, 3
+ vaddudm 17, 17, 9
+ vaddudm 17, 17, 10
+ vaddudm 17, 17, 11
+ vaddudm 17, 17, 12
+ vaddudm 17, 17, 13 # x3
+
+ vmuleuw 9, 4, 30
+ vmuleuw 10, 5, 29
+ vmuleuw 11, 6, 28
+ vmuleuw 12, 7, 27
+ vmuleuw 13, 8, 26
+ vaddudm 18, 18, 9
+ vaddudm 18, 18, 10
+ vaddudm 18, 18, 11
+ vaddudm 18, 18, 12
+ vaddudm 18, 18, 13 # x4
+.endm
+
+#
+# poly1305_setup_r
+#
+# setup r^4, r^3, r^2, r vectors
+# [r, r^3, r^2, r^4]
+# vs0 = [r0,...]
+# vs1 = [r1,...]
+# vs2 = [r2,...]
+# vs3 = [r3,...]
+# vs4 = [r4,...]
+# vs5 = [r4*5,...]
+# vs6 = [r3*5,...]
+# vs7 = [r2*5,...]
+# vs8 = [r1*5,...]
+#
+# r0, r4*5, r3*5, r2*5, r1*5;
+# r1, r0, r4*5, r3*5, r2*5;
+# r2, r1, r0, r4*5, r3*5;
+# r3, r2, r1, r0, r4*5;
+# r4, r3, r2, r1, r0 ;
+#
+.macro poly1305_setup_r
+
+ # save r
+ xxlor 26, 58, 58
+ xxlor 27, 59, 59
+ xxlor 28, 60, 60
+ xxlor 29, 61, 61
+ xxlor 30, 62, 62
+
+ xxlxor 31, 31, 31
+
+# [r, r^3, r^2, r^4]
+ # compute r^2
+ vmr 4, 26
+ vmr 5, 27
+ vmr 6, 28
+ vmr 7, 29
+ vmr 8, 30
+ bl do_mul # r^2 r^1
+ xxpermdi 58, 58, 36, 0x3 # r0
+ xxpermdi 59, 59, 37, 0x3 # r1
+ xxpermdi 60, 60, 38, 0x3 # r2
+ xxpermdi 61, 61, 39, 0x3 # r3
+ xxpermdi 62, 62, 40, 0x3 # r4
+ xxpermdi 36, 36, 36, 0x3
+ xxpermdi 37, 37, 37, 0x3
+ xxpermdi 38, 38, 38, 0x3
+ xxpermdi 39, 39, 39, 0x3
+ xxpermdi 40, 40, 40, 0x3
+ vspltisb 13, 2
+ vsld 9, 27, 13
+ vsld 10, 28, 13
+ vsld 11, 29, 13
+ vsld 12, 30, 13
+ vaddudm 0, 9, 27
+ vaddudm 1, 10, 28
+ vaddudm 2, 11, 29
+ vaddudm 3, 12, 30
+
+ bl do_mul # r^4 r^3
+ vmrgow 26, 26, 4
+ vmrgow 27, 27, 5
+ vmrgow 28, 28, 6
+ vmrgow 29, 29, 7
+ vmrgow 30, 30, 8
+ vspltisb 13, 2
+ vsld 9, 27, 13
+ vsld 10, 28, 13
+ vsld 11, 29, 13
+ vsld 12, 30, 13
+ vaddudm 0, 9, 27
+ vaddudm 1, 10, 28
+ vaddudm 2, 11, 29
+ vaddudm 3, 12, 30
+
+ # r^2 r^4
+ xxlor 0, 58, 58
+ xxlor 1, 59, 59
+ xxlor 2, 60, 60
+ xxlor 3, 61, 61
+ xxlor 4, 62, 62
+ xxlor 5, 32, 32
+ xxlor 6, 33, 33
+ xxlor 7, 34, 34
+ xxlor 8, 35, 35
+
+ vspltw 9, 26, 3
+ vspltw 10, 26, 2
+ vmrgow 26, 10, 9
+ vspltw 9, 27, 3
+ vspltw 10, 27, 2
+ vmrgow 27, 10, 9
+ vspltw 9, 28, 3
+ vspltw 10, 28, 2
+ vmrgow 28, 10, 9
+ vspltw 9, 29, 3
+ vspltw 10, 29, 2
+ vmrgow 29, 10, 9
+ vspltw 9, 30, 3
+ vspltw 10, 30, 2
+ vmrgow 30, 10, 9
+
+ vsld 9, 27, 13
+ vsld 10, 28, 13
+ vsld 11, 29, 13
+ vsld 12, 30, 13
+ vaddudm 0, 9, 27
+ vaddudm 1, 10, 28
+ vaddudm 2, 11, 29
+ vaddudm 3, 12, 30
+.endm
+
+SYM_FUNC_START_LOCAL(do_mul)
+ mul_odd
+
+ # do reduction ( h %= p )
+ # carry reduction
+ vspltisb 9, 2
+ vsrd 10, 14, 31
+ vsrd 11, 17, 31
+ vand 7, 17, 25
+ vand 4, 14, 25
+ vaddudm 18, 18, 11
+ vsrd 12, 18, 31
+ vaddudm 15, 15, 10
+
+ vsrd 11, 15, 31
+ vand 8, 18, 25
+ vand 5, 15, 25
+ vaddudm 4, 4, 12
+ vsld 10, 12, 9
+ vaddudm 6, 16, 11
+
+ vsrd 13, 6, 31
+ vand 6, 6, 25
+ vaddudm 4, 4, 10
+ vsrd 10, 4, 31
+ vaddudm 7, 7, 13
+
+ vsrd 11, 7, 31
+ vand 7, 7, 25
+ vand 4, 4, 25
+ vaddudm 5, 5, 10
+ vaddudm 8, 8, 11
+ blr
+SYM_FUNC_END(do_mul)
+
+#
+# init key
+#
+.macro do_poly1305_init
+ addis 10, 2, rmask@toc@ha
+ addi 10, 10, rmask@toc@l
+
+ ld 11, 0(10)
+ ld 12, 8(10)
+
+ li 14, 16
+ li 15, 32
+ addis 10, 2, cnum@toc@ha
+ addi 10, 10, cnum@toc@l
+ lvx 25, 0, 10 # v25 - mask
+ lvx 31, 14, 10 # v31 = 1a
+ lvx 19, 15, 10 # v19 = 1 << 24
+ lxv 24, 48(10) # vs24
+ lxv 25, 64(10) # vs25
+
+ # initialize
+ # load key from r3 to vectors
+ ld 9, 24(3)
+ ld 10, 32(3)
+ and. 9, 9, 11
+ and. 10, 10, 12
+
+ # break 26 bits
+ extrdi 14, 9, 26, 38
+ extrdi 15, 9, 26, 12
+ extrdi 16, 9, 12, 0
+ mtvsrdd 58, 0, 14
+ insrdi 16, 10, 14, 38
+ mtvsrdd 59, 0, 15
+ extrdi 17, 10, 26, 24
+ mtvsrdd 60, 0, 16
+ extrdi 18, 10, 24, 0
+ mtvsrdd 61, 0, 17
+ mtvsrdd 62, 0, 18
+
+ # r1 = r1 * 5, r2 = r2 * 5, r3 = r3 * 5, r4 = r4 * 5
+ li 9, 5
+ mtvsrdd 36, 0, 9
+ vmulouw 0, 27, 4 # v0 = rr0
+ vmulouw 1, 28, 4 # v1 = rr1
+ vmulouw 2, 29, 4 # v2 = rr2
+ vmulouw 3, 30, 4 # v3 = rr3
+.endm
+
+#
+# poly1305_p10le_4blocks( uint8_t *k, uint32_t mlen, uint8_t *m)
+# k = 32 bytes key
+# r3 = k (r, s)
+# r4 = mlen
+# r5 = m
+#
+SYM_FUNC_START(poly1305_p10le_4blocks)
+.align 5
+ cmpdi 5, 64
+ blt Out_no_poly1305
+
+ SAVE_REGS
+
+ do_poly1305_init
+
+ li 21, 0 # counter to message
+
+ poly1305_setup_r
+
+ # load previous H state
+ # break/convert r6 to 26 bits
+ ld 9, 0(3)
+ ld 10, 8(3)
+ ld 19, 16(3)
+ sldi 19, 19, 24
+ mtvsrdd 41, 0, 19
+ extrdi 14, 9, 26, 38
+ extrdi 15, 9, 26, 12
+ extrdi 16, 9, 12, 0
+ mtvsrdd 36, 0, 14
+ insrdi 16, 10, 14, 38
+ mtvsrdd 37, 0, 15
+ extrdi 17, 10, 26, 24
+ mtvsrdd 38, 0, 16
+ extrdi 18, 10, 24, 0
+ mtvsrdd 39, 0, 17
+ mtvsrdd 40, 0, 18
+ vor 8, 8, 9
+
+ # input m1 m2
+ add 20, 4, 21
+ xxlor 49, 24, 24
+ xxlor 50, 25, 25
+ lxvw4x 43, 0, 20
+ addi 17, 20, 16
+ lxvw4x 44, 0, 17
+ vperm 14, 11, 12, 17
+ vperm 15, 11, 12, 18
+ vand 9, 14, 25 # a0
+ vsrd 10, 14, 31 # >> 26
+ vsrd 11, 10, 31 # 12 bits left
+ vand 10, 10, 25 # a1
+ vspltisb 13, 12
+ vand 16, 15, 25
+ vsld 12, 16, 13
+ vor 11, 11, 12
+ vand 11, 11, 25 # a2
+ vspltisb 13, 14
+ vsrd 12, 15, 13 # >> 14
+ vsrd 13, 12, 31 # >> 26, a4
+ vand 12, 12, 25 # a3
+
+ vaddudm 20, 4, 9
+ vaddudm 21, 5, 10
+ vaddudm 22, 6, 11
+ vaddudm 23, 7, 12
+ vaddudm 24, 8, 13
+
+ # m3 m4
+ addi 17, 17, 16
+ lxvw4x 43, 0, 17
+ addi 17, 17, 16
+ lxvw4x 44, 0, 17
+ vperm 14, 11, 12, 17
+ vperm 15, 11, 12, 18
+ vand 9, 14, 25 # a0
+ vsrd 10, 14, 31 # >> 26
+ vsrd 11, 10, 31 # 12 bits left
+ vand 10, 10, 25 # a1
+ vspltisb 13, 12
+ vand 16, 15, 25
+ vsld 12, 16, 13
+ vspltisb 13, 14
+ vor 11, 11, 12
+ vand 11, 11, 25 # a2
+ vsrd 12, 15, 13 # >> 14
+ vsrd 13, 12, 31 # >> 26, a4
+ vand 12, 12, 25 # a3
+
+ # Smash 4 message blocks into 5 vectors of [m4, m2, m3, m1]
+ vmrgow 4, 9, 20
+ vmrgow 5, 10, 21
+ vmrgow 6, 11, 22
+ vmrgow 7, 12, 23
+ vmrgow 8, 13, 24
+ vaddudm 8, 8, 19
+
+ addi 5, 5, -64 # len -= 64
+ addi 21, 21, 64 # offset += 64
+
+ li 9, 64
+ divdu 31, 5, 9
+
+ cmpdi 31, 0
+ ble Skip_block_loop
+
+ mtctr 31
+
+# h4 = m1 * r⁴ + m2 * r³ + m3 * r² + m4 * r
+# Rewrite the polynominal sum of product as follows,
+# h1 = (h0 + m1) * r^2, h2 = (h0 + m2) * r^2
+# h3 = (h1 + m3) * r^2, h4 = (h2 + m4) * r^2 --> (h0 + m1) r*4 + (h3 + m3) r^2, (h0 + m2) r^4 + (h0 + m4) r^2
+# .... Repeat
+# h5 = (h3 + m5) * r^2, h6 = (h4 + m6) * r^2 -->
+# h7 = (h5 + m7) * r^2, h8 = (h6 + m8) * r^1 --> m5 * r^4 + m6 * r^3 + m7 * r^2 + m8 * r
+#
+loop_4blocks:
+
+ # Multiply odd words and even words
+ mul_odd
+ mul_even
+ # carry reduction
+ vspltisb 9, 2
+ vsrd 10, 14, 31
+ vsrd 11, 17, 31
+ vand 7, 17, 25
+ vand 4, 14, 25
+ vaddudm 18, 18, 11
+ vsrd 12, 18, 31
+ vaddudm 15, 15, 10
+
+ vsrd 11, 15, 31
+ vand 8, 18, 25
+ vand 5, 15, 25
+ vaddudm 4, 4, 12
+ vsld 10, 12, 9
+ vaddudm 6, 16, 11
+
+ vsrd 13, 6, 31
+ vand 6, 6, 25
+ vaddudm 4, 4, 10
+ vsrd 10, 4, 31
+ vaddudm 7, 7, 13
+
+ vsrd 11, 7, 31
+ vand 7, 7, 25
+ vand 4, 4, 25
+ vaddudm 5, 5, 10
+ vaddudm 8, 8, 11
+
+ # input m1 m2 m3 m4
+ add 20, 4, 21
+ xxlor 49, 24, 24
+ xxlor 50, 25, 25
+ lxvw4x 43, 0, 20
+ addi 17, 20, 16
+ lxvw4x 44, 0, 17
+ vperm 14, 11, 12, 17
+ vperm 15, 11, 12, 18
+ addi 17, 17, 16
+ lxvw4x 43, 0, 17
+ addi 17, 17, 16
+ lxvw4x 44, 0, 17
+ vperm 17, 11, 12, 17
+ vperm 18, 11, 12, 18
+
+ vand 20, 14, 25 # a0
+ vand 9, 17, 25 # a0
+ vsrd 21, 14, 31 # >> 26
+ vsrd 22, 21, 31 # 12 bits left
+ vsrd 10, 17, 31 # >> 26
+ vsrd 11, 10, 31 # 12 bits left
+
+ vand 21, 21, 25 # a1
+ vand 10, 10, 25 # a1
+
+ vspltisb 13, 12
+ vand 16, 15, 25
+ vsld 23, 16, 13
+ vor 22, 22, 23
+ vand 22, 22, 25 # a2
+ vand 16, 18, 25
+ vsld 12, 16, 13
+ vor 11, 11, 12
+ vand 11, 11, 25 # a2
+ vspltisb 13, 14
+ vsrd 23, 15, 13 # >> 14
+ vsrd 24, 23, 31 # >> 26, a4
+ vand 23, 23, 25 # a3
+ vsrd 12, 18, 13 # >> 14
+ vsrd 13, 12, 31 # >> 26, a4
+ vand 12, 12, 25 # a3
+
+ vaddudm 4, 4, 20
+ vaddudm 5, 5, 21
+ vaddudm 6, 6, 22
+ vaddudm 7, 7, 23
+ vaddudm 8, 8, 24
+
+ # Smash 4 message blocks into 5 vectors of [m4, m2, m3, m1]
+ vmrgow 4, 9, 4
+ vmrgow 5, 10, 5
+ vmrgow 6, 11, 6
+ vmrgow 7, 12, 7
+ vmrgow 8, 13, 8
+ vaddudm 8, 8, 19
+
+ addi 5, 5, -64 # len -= 64
+ addi 21, 21, 64 # offset += 64
+
+ bdnz loop_4blocks
+
+Skip_block_loop:
+ xxlor 58, 0, 0
+ xxlor 59, 1, 1
+ xxlor 60, 2, 2
+ xxlor 61, 3, 3
+ xxlor 62, 4, 4
+ xxlor 32, 5, 5
+ xxlor 33, 6, 6
+ xxlor 34, 7, 7
+ xxlor 35, 8, 8
+
+ # Multiply odd words and even words
+ mul_odd
+ mul_even
+
+ # Sum the products.
+ xxpermdi 41, 31, 46, 0
+ xxpermdi 42, 31, 47, 0
+ vaddudm 4, 14, 9
+ xxpermdi 36, 31, 36, 3
+ vaddudm 5, 15, 10
+ xxpermdi 37, 31, 37, 3
+ xxpermdi 43, 31, 48, 0
+ vaddudm 6, 16, 11
+ xxpermdi 38, 31, 38, 3
+ xxpermdi 44, 31, 49, 0
+ vaddudm 7, 17, 12
+ xxpermdi 39, 31, 39, 3
+ xxpermdi 45, 31, 50, 0
+ vaddudm 8, 18, 13
+ xxpermdi 40, 31, 40, 3
+
+ # carry reduction
+ vspltisb 9, 2
+ vsrd 10, 4, 31
+ vsrd 11, 7, 31
+ vand 7, 7, 25
+ vand 4, 4, 25
+ vaddudm 8, 8, 11
+ vsrd 12, 8, 31
+ vaddudm 5, 5, 10
+
+ vsrd 11, 5, 31
+ vand 8, 8, 25
+ vand 5, 5, 25
+ vaddudm 4, 4, 12
+ vsld 10, 12, 9
+ vaddudm 6, 6, 11
+
+ vsrd 13, 6, 31
+ vand 6, 6, 25
+ vaddudm 4, 4, 10
+ vsrd 10, 4, 31
+ vaddudm 7, 7, 13
+
+ vsrd 11, 7, 31
+ vand 7, 7, 25
+ vand 4, 4, 25
+ vaddudm 5, 5, 10
+ vsrd 10, 5, 31
+ vand 5, 5, 25
+ vaddudm 6, 6, 10
+ vaddudm 8, 8, 11
+
+ b do_final_update
+
+do_final_update:
+ # combine 26 bit limbs
+ # v4, v5, v6, v7 and v8 are 26 bit vectors
+ vsld 5, 5, 31
+ vor 20, 4, 5
+ vspltisb 11, 12
+ vsrd 12, 6, 11
+ vsld 6, 6, 31
+ vsld 6, 6, 31
+ vor 20, 20, 6
+ vspltisb 11, 14
+ vsld 7, 7, 11
+ vor 21, 7, 12
+ mfvsrld 16, 40 # save last 2 bytes
+ vsld 8, 8, 11
+ vsld 8, 8, 31
+ vor 21, 21, 8
+ mfvsrld 17, 52
+ mfvsrld 19, 53
+ srdi 16, 16, 24
+
+ std 17, 0(3)
+ std 19, 8(3)
+ stw 16, 16(3)
+
+Out_loop:
+ li 3, 0
+
+ RESTORE_REGS
+
+ blr
+
+Out_no_poly1305:
+ li 3, 0
+ blr
+SYM_FUNC_END(poly1305_p10le_4blocks)
+
+#
+# =======================================================================
+# The following functions implement 64 x 64 bits multiplication poly1305.
+#
+SYM_FUNC_START_LOCAL(Poly1305_init_64)
+ # mask 0x0FFFFFFC0FFFFFFC
+ # mask 0x0FFFFFFC0FFFFFFF
+ addis 10, 2, rmask@toc@ha
+ addi 10, 10, rmask@toc@l
+ ld 11, 0(10)
+ ld 12, 8(10)
+
+ # initialize
+ # load key from r3
+ ld 9, 24(3)
+ ld 10, 32(3)
+ and. 9, 9, 11 # cramp mask r0
+ and. 10, 10, 12 # cramp mask r1
+
+ srdi 21, 10, 2
+ add 19, 21, 10 # s1: r19 - (r1 >> 2) *5
+
+ # setup r and s
+ li 25, 0
+ mtvsrdd 32+0, 9, 19 # r0, s1
+ mtvsrdd 32+1, 10, 9 # r1, r0
+ mtvsrdd 32+2, 19, 25 # s1
+ mtvsrdd 32+3, 9, 25 # r0
+
+ blr
+SYM_FUNC_END(Poly1305_init_64)
+
+# Poly1305_mult
+# v6 = (h0, h1), v8 = h2
+# v0 = (r0, s1), v1 = (r1, r0), v2 = s1, v3 = r0
+#
+# Output: v7, v10, v11
+#
+SYM_FUNC_START_LOCAL(Poly1305_mult)
+ #
+ # d0 = h0 * r0 + h1 * s1
+ vmsumudm 7, 6, 0, 9 # h0 * r0, h1 * s1
+
+ # d1 = h0 * r1 + h1 * r0 + h2 * s1
+ vmsumudm 11, 6, 1, 9 # h0 * r1, h1 * r0
+ vmsumudm 10, 8, 2, 11 # d1 += h2 * s1
+
+ # d2 = r0
+ vmsumudm 11, 8, 3, 9 # d2 = h2 * r0
+ blr
+SYM_FUNC_END(Poly1305_mult)
+
+#
+# carry reduction
+# h %=p
+#
+# Input: v7, v10, v11
+# Output: r27, r28, r29
+#
+SYM_FUNC_START_LOCAL(Carry_reduction)
+ mfvsrld 27, 32+7
+ mfvsrld 28, 32+10
+ mfvsrld 29, 32+11
+ mfvsrd 20, 32+7 # h0.h
+ mfvsrd 21, 32+10 # h1.h
+
+ addc 28, 28, 20
+ adde 29, 29, 21
+ srdi 22, 29, 0x2
+ sldi 23, 22, 0x2
+ add 23, 23, 22 # (h2 & 3) * 5
+ addc 27, 27, 23 # h0
+ addze 28, 28 # h1
+ andi. 29, 29, 0x3 # h2
+ blr
+SYM_FUNC_END(Carry_reduction)
+
+#
+# poly1305 multiplication
+# h *= r, h %= p
+# d0 = h0 * r0 + h1 * s1
+# d1 = h0 * r1 + h1 * r0 + h2 * s1
+# d2 = h0 * r0
+#
+#
+# unsigned int poly1305_test_64s(unisgned char *state, const byte *src, size_t len, highbit)
+# - no highbit if final leftover block (highbit = 0)
+#
+SYM_FUNC_START(poly1305_64s)
+ cmpdi 5, 0
+ ble Out_no_poly1305_64
+
+ mflr 0
+ std 0, 16(1)
+ stdu 1,-400(1)
+
+ SAVE_GPR 14, 112, 1
+ SAVE_GPR 15, 120, 1
+ SAVE_GPR 16, 128, 1
+ SAVE_GPR 17, 136, 1
+ SAVE_GPR 18, 144, 1
+ SAVE_GPR 19, 152, 1
+ SAVE_GPR 20, 160, 1
+ SAVE_GPR 21, 168, 1
+ SAVE_GPR 22, 176, 1
+ SAVE_GPR 23, 184, 1
+ SAVE_GPR 24, 192, 1
+ SAVE_GPR 25, 200, 1
+ SAVE_GPR 26, 208, 1
+ SAVE_GPR 27, 216, 1
+ SAVE_GPR 28, 224, 1
+ SAVE_GPR 29, 232, 1
+ SAVE_GPR 30, 240, 1
+ SAVE_GPR 31, 248, 1
+
+ # Init poly1305
+ bl Poly1305_init_64
+
+ li 25, 0 # offset to inp and outp
+
+ add 11, 25, 4
+
+ # load h
+ # h0, h1, h2?
+ ld 27, 0(3)
+ ld 28, 8(3)
+ lwz 29, 16(3)
+
+ li 30, 16
+ divdu 31, 5, 30
+
+ mtctr 31
+
+ mr 24, 6 # highbit
+
+Loop_block_64:
+ vxor 9, 9, 9
+
+ ld 20, 0(11)
+ ld 21, 8(11)
+ addi 11, 11, 16
+
+ addc 27, 27, 20
+ adde 28, 28, 21
+ adde 29, 29, 24
+
+ li 22, 0
+ mtvsrdd 32+6, 27, 28 # h0, h1
+ mtvsrdd 32+8, 29, 22 # h2
+
+ bl Poly1305_mult
+
+ bl Carry_reduction
+
+ bdnz Loop_block_64
+
+ std 27, 0(3)
+ std 28, 8(3)
+ stw 29, 16(3)
+
+ li 3, 0
+
+ RESTORE_GPR 14, 112, 1
+ RESTORE_GPR 15, 120, 1
+ RESTORE_GPR 16, 128, 1
+ RESTORE_GPR 17, 136, 1
+ RESTORE_GPR 18, 144, 1
+ RESTORE_GPR 19, 152, 1
+ RESTORE_GPR 20, 160, 1
+ RESTORE_GPR 21, 168, 1
+ RESTORE_GPR 22, 176, 1
+ RESTORE_GPR 23, 184, 1
+ RESTORE_GPR 24, 192, 1
+ RESTORE_GPR 25, 200, 1
+ RESTORE_GPR 26, 208, 1
+ RESTORE_GPR 27, 216, 1
+ RESTORE_GPR 28, 224, 1
+ RESTORE_GPR 29, 232, 1
+ RESTORE_GPR 30, 240, 1
+ RESTORE_GPR 31, 248, 1
+
+ addi 1, 1, 400
+ ld 0, 16(1)
+ mtlr 0
+
+ blr
+
+Out_no_poly1305_64:
+ li 3, 0
+ blr
+SYM_FUNC_END(poly1305_64s)
+
+#
+# Input: r3 = h, r4 = s, r5 = mac
+# mac = h + s
+#
+SYM_FUNC_START(poly1305_emit_64)
+ ld 10, 0(3)
+ ld 11, 8(3)
+ ld 12, 16(3)
+
+ # compare modulus
+ # h + 5 + (-p)
+ mr 6, 10
+ mr 7, 11
+ mr 8, 12
+ addic. 6, 6, 5
+ addze 7, 7
+ addze 8, 8
+ srdi 9, 8, 2 # overflow?
+ cmpdi 9, 0
+ beq Skip_h64
+ mr 10, 6
+ mr 11, 7
+ mr 12, 8
+
+Skip_h64:
+ ld 6, 0(4)
+ ld 7, 8(4)
+ addc 10, 10, 6
+ adde 11, 11, 7
+ addze 12, 12
+
+ std 10, 0(5)
+ std 11, 8(5)
+ blr
+SYM_FUNC_END(poly1305_emit_64)
+
+SYM_DATA_START_LOCAL(RMASK)
+.align 5
+rmask:
+.byte 0xff, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f, 0xfc, 0xff, 0xff, 0x0f
+cnum:
+.long 0x03ffffff, 0x00000000, 0x03ffffff, 0x00000000
+.long 0x1a, 0x00, 0x1a, 0x00
+.long 0x01000000, 0x01000000, 0x01000000, 0x01000000
+.long 0x00010203, 0x04050607, 0x10111213, 0x14151617
+.long 0x08090a0b, 0x0c0d0e0f, 0x18191a1b, 0x1c1d1e1f
+SYM_DATA_END(RMASK)
--
2.31.1
Defined CRYPTO_CHACHA20_P10 and CRYPTO POLY1305_P10 in Kconfig to
support optimized implementation for Power10 and later CPU.
Added new module driver chacha-p10-crypto and poly1305-p10-crypto.
Signed-off-by: Danny Tsen <[email protected]>
---
arch/powerpc/crypto/Kconfig | 26 ++++++++++++++++++++++++++
arch/powerpc/crypto/Makefile | 4 ++++
2 files changed, 30 insertions(+)
diff --git a/arch/powerpc/crypto/Kconfig b/arch/powerpc/crypto/Kconfig
index 7113f9355165..f74d9dd6574b 100644
--- a/arch/powerpc/crypto/Kconfig
+++ b/arch/powerpc/crypto/Kconfig
@@ -111,4 +111,30 @@ config CRYPTO_AES_GCM_P10
Support for cryptographic acceleration instructions on Power10 or
later CPU. This module supports stitched acceleration for AES/GCM.
+config CRYPTO_CHACHA20_P10
+ tristate "Ciphers: ChaCha20, XChacha20, XChacha12 (P10 or later)"
+ depends on PPC64 && CPU_LITTLE_ENDIAN
+ select CRYPTO_SKCIPHER
+ select CRYPTO_LIB_CHACHA_GENERIC
+ select CRYPTO_ARCH_HAVE_LIB_CHACHA
+ help
+ Length-preserving ciphers: ChaCha20, XChaCha20, and XChaCha12
+ stream cipher algorithms
+
+ Architecture: PowerPC64
+ - Power10 or later
+ - Little-endian
+
+config CRYPTO_POLY1305_P10
+ tristate "Hash functions: Poly1305 (P10 or later)"
+ depends on PPC64 && CPU_LITTLE_ENDIAN
+ select CRYPTO_HASH
+ select CRYPTO_LIB_POLY1305_GENERIC
+ help
+ Poly1305 authenticator algorithm (RFC7539)
+
+ Architecture: PowerPC64
+ - Power10 or later
+ - Little-endian
+
endmenu
diff --git a/arch/powerpc/crypto/Makefile b/arch/powerpc/crypto/Makefile
index 05c7486f42c5..cd5282eff451 100644
--- a/arch/powerpc/crypto/Makefile
+++ b/arch/powerpc/crypto/Makefile
@@ -14,6 +14,8 @@ obj-$(CONFIG_CRYPTO_CRC32C_VPMSUM) += crc32c-vpmsum.o
obj-$(CONFIG_CRYPTO_CRCT10DIF_VPMSUM) += crct10dif-vpmsum.o
obj-$(CONFIG_CRYPTO_VPMSUM_TESTER) += crc-vpmsum_test.o
obj-$(CONFIG_CRYPTO_AES_GCM_P10) += aes-gcm-p10-crypto.o
+obj-$(CONFIG_CRYPTO_CHACHA20_P10) += chacha-p10-crypto.o
+obj-$(CONFIG_CRYPTO_POLY1305_P10) += poly1305-p10-crypto.o
aes-ppc-spe-y := aes-spe-core.o aes-spe-keys.o aes-tab-4k.o aes-spe-modes.o aes-spe-glue.o
md5-ppc-y := md5-asm.o md5-glue.o
@@ -23,6 +25,8 @@ sha256-ppc-spe-y := sha256-spe-asm.o sha256-spe-glue.o
crc32c-vpmsum-y := crc32c-vpmsum_asm.o crc32c-vpmsum_glue.o
crct10dif-vpmsum-y := crct10dif-vpmsum_asm.o crct10dif-vpmsum_glue.o
aes-gcm-p10-crypto-y := aes-gcm-p10-glue.o aes-gcm-p10.o ghashp8-ppc.o aesp8-ppc.o
+chacha-p10-crypto-y := chacha-p10-glue.o chacha-p10le-8x.o
+poly1305-p10-crypto-y := poly1305-p10-glue.o poly1305-p10le_64.o
quiet_cmd_perl = PERL $@
cmd_perl = $(PERL) $< $(if $(CONFIG_CPU_LITTLE_ENDIAN), linux-ppc64le, linux-ppc64) > $@
--
2.31.1
Signed-off-by: Danny Tsen <[email protected]>
---
arch/powerpc/crypto/chacha-p10-glue.c | 221 ++++++++++++++++++++++++++
1 file changed, 221 insertions(+)
create mode 100644 arch/powerpc/crypto/chacha-p10-glue.c
diff --git a/arch/powerpc/crypto/chacha-p10-glue.c b/arch/powerpc/crypto/chacha-p10-glue.c
new file mode 100644
index 000000000000..74fb86b0d209
--- /dev/null
+++ b/arch/powerpc/crypto/chacha-p10-glue.c
@@ -0,0 +1,221 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * PowerPC P10 (ppc64le) accelerated ChaCha and XChaCha stream ciphers,
+ * including ChaCha20 (RFC7539)
+ *
+ * Copyright 2023- IBM Corp. All rights reserved.
+ */
+
+#include <crypto/algapi.h>
+#include <crypto/internal/chacha.h>
+#include <crypto/internal/simd.h>
+#include <crypto/internal/skcipher.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cpufeature.h>
+#include <linux/sizes.h>
+#include <asm/simd.h>
+#include <asm/switch_to.h>
+
+asmlinkage void chacha_p10le_8x(u32 *state, u8 *dst, const u8 *src,
+ unsigned int len, int nrounds);
+
+static __ro_after_init DEFINE_STATIC_KEY_FALSE(have_p10);
+
+static void vsx_begin(void)
+{
+ preempt_disable();
+ enable_kernel_vsx();
+}
+
+static void vsx_end(void)
+{
+ disable_kernel_vsx();
+ preempt_enable();
+}
+
+static void chacha_p10_do_8x(u32 *state, u8 *dst, const u8 *src,
+ unsigned int bytes, int nrounds)
+{
+ unsigned int l = bytes & ~0x0FF;
+
+ if (l > 0) {
+ chacha_p10le_8x(state, dst, src, l, nrounds);
+ bytes -= l;
+ src += l;
+ dst += l;
+ state[12] += l / CHACHA_BLOCK_SIZE;
+ }
+
+ if (bytes > 0)
+ chacha_crypt_generic(state, dst, src, bytes, nrounds);
+}
+
+void hchacha_block_arch(const u32 *state, u32 *stream, int nrounds)
+{
+ hchacha_block_generic(state, stream, nrounds);
+}
+EXPORT_SYMBOL(hchacha_block_arch);
+
+void chacha_init_arch(u32 *state, const u32 *key, const u8 *iv)
+{
+ chacha_init_generic(state, key, iv);
+}
+EXPORT_SYMBOL(chacha_init_arch);
+
+void chacha_crypt_arch(u32 *state, u8 *dst, const u8 *src, unsigned int bytes,
+ int nrounds)
+{
+ if (!static_branch_likely(&have_p10) || bytes <= CHACHA_BLOCK_SIZE ||
+ !crypto_simd_usable())
+ return chacha_crypt_generic(state, dst, src, bytes, nrounds);
+
+ do {
+ unsigned int todo = min_t(unsigned int, bytes, SZ_4K);
+
+ vsx_begin();
+ chacha_p10_do_8x(state, dst, src, todo, nrounds);
+ vsx_end();
+
+ bytes -= todo;
+ src += todo;
+ dst += todo;
+ } while (bytes);
+}
+EXPORT_SYMBOL(chacha_crypt_arch);
+
+static int chacha_p10_stream_xor(struct skcipher_request *req,
+ const struct chacha_ctx *ctx, const u8 *iv)
+{
+ struct skcipher_walk walk;
+ u32 state[16];
+ int err;
+
+ err = skcipher_walk_virt(&walk, req, false);
+ if (err)
+ return err;
+
+ chacha_init_generic(state, ctx->key, iv);
+
+ while (walk.nbytes > 0) {
+ unsigned int nbytes = walk.nbytes;
+
+ if (nbytes < walk.total)
+ nbytes = rounddown(nbytes, walk.stride);
+
+ if (!crypto_simd_usable()) {
+ chacha_crypt_generic(state, walk.dst.virt.addr,
+ walk.src.virt.addr, nbytes,
+ ctx->nrounds);
+ } else {
+ vsx_begin();
+ chacha_p10_do_8x(state, walk.dst.virt.addr,
+ walk.src.virt.addr, nbytes, ctx->nrounds);
+ vsx_end();
+ }
+ err = skcipher_walk_done(&walk, walk.nbytes - nbytes);
+ if (err)
+ break;
+ }
+
+ return err;
+}
+
+static int chacha_p10(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+
+ return chacha_p10_stream_xor(req, ctx, req->iv);
+}
+
+static int xchacha_p10(struct skcipher_request *req)
+{
+ struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req);
+ struct chacha_ctx *ctx = crypto_skcipher_ctx(tfm);
+ struct chacha_ctx subctx;
+ u32 state[16];
+ u8 real_iv[16];
+
+ chacha_init_generic(state, ctx->key, req->iv);
+ hchacha_block_arch(state, subctx.key, ctx->nrounds);
+ subctx.nrounds = ctx->nrounds;
+
+ memcpy(&real_iv[0], req->iv + 24, 8);
+ memcpy(&real_iv[8], req->iv + 16, 8);
+ return chacha_p10_stream_xor(req, &subctx, real_iv);
+}
+
+static struct skcipher_alg algs[] = {
+ {
+ .base.cra_name = "chacha20",
+ .base.cra_driver_name = "chacha20-p10",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = CHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .setkey = chacha20_setkey,
+ .encrypt = chacha_p10,
+ .decrypt = chacha_p10,
+ }, {
+ .base.cra_name = "xchacha20",
+ .base.cra_driver_name = "xchacha20-p10",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .setkey = chacha20_setkey,
+ .encrypt = xchacha_p10,
+ .decrypt = xchacha_p10,
+ }, {
+ .base.cra_name = "xchacha12",
+ .base.cra_driver_name = "xchacha12-p10",
+ .base.cra_priority = 300,
+ .base.cra_blocksize = 1,
+ .base.cra_ctxsize = sizeof(struct chacha_ctx),
+ .base.cra_module = THIS_MODULE,
+
+ .min_keysize = CHACHA_KEY_SIZE,
+ .max_keysize = CHACHA_KEY_SIZE,
+ .ivsize = XCHACHA_IV_SIZE,
+ .chunksize = CHACHA_BLOCK_SIZE,
+ .setkey = chacha12_setkey,
+ .encrypt = xchacha_p10,
+ .decrypt = xchacha_p10,
+ }
+};
+
+static int __init chacha_p10_init(void)
+{
+ static_branch_enable(&have_p10);
+
+ return crypto_register_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+static void __exit chacha_p10_exit(void)
+{
+ crypto_unregister_skciphers(algs, ARRAY_SIZE(algs));
+}
+
+module_cpu_feature_match(PPC_MODULE_FEATURE_P10, chacha_p10_init);
+module_exit(chacha_p10_exit);
+
+MODULE_DESCRIPTION("ChaCha and XChaCha stream ciphers (P10 accelerated)");
+MODULE_AUTHOR("Danny Tsen <[email protected]>");
+MODULE_LICENSE("GPL v2");
+MODULE_ALIAS_CRYPTO("chacha20");
+MODULE_ALIAS_CRYPTO("chacha20-p10");
+MODULE_ALIAS_CRYPTO("xchacha20");
+MODULE_ALIAS_CRYPTO("xchacha20-p10");
+MODULE_ALIAS_CRYPTO("xchacha12");
+MODULE_ALIAS_CRYPTO("xchacha12-p10");
--
2.31.1
On Wed, Apr 26, 2023 at 03:11:42PM -0400, Danny Tsen wrote:
> This patch series provide an accelerated/optimized Chacha20 and Poly1305
> implementation for Power10 or later CPU (ppc64le). This module
> implements algorithm specified in RFC7539. The implementation
> provides 3.5X better performance than the baseline for Chacha20 and
> Poly1305 individually and 1.5X improvement for Chacha20/Poly1305
> operation.
>
> This patch has been tested with the kernel crypto module tcrypt.ko and
> has passed the selftest. The patch is also tested with
> CONFIG_CRYPTO_MANAGER_EXTRA_TESTS enabled.
>
>
> Danny Tsen (5):
> An optimized Chacha20 implementation with 8-way unrolling for ppc64le.
> Glue code for optmized Chacha20 implementation for ppc64le.
> An optimized Poly1305 implementation with 4-way unrolling for ppc64le.
> Glue code for optmized Poly1305 implementation for ppc64le.
> Update Kconfig and Makefile.
>
> arch/powerpc/crypto/Kconfig | 26 +
> arch/powerpc/crypto/Makefile | 4 +
> arch/powerpc/crypto/chacha-p10-glue.c | 221 +++++
> arch/powerpc/crypto/chacha-p10le-8x.S | 842 ++++++++++++++++++
> arch/powerpc/crypto/poly1305-p10-glue.c | 186 ++++
> arch/powerpc/crypto/poly1305-p10le_64.S | 1075 +++++++++++++++++++++++
> 6 files changed, 2354 insertions(+)
> create mode 100644 arch/powerpc/crypto/chacha-p10-glue.c
> create mode 100644 arch/powerpc/crypto/chacha-p10le-8x.S
> create mode 100644 arch/powerpc/crypto/poly1305-p10-glue.c
> create mode 100644 arch/powerpc/crypto/poly1305-p10le_64.S
>
> --
> 2.31.1
All applied. Thanks.
--
Email: Herbert Xu <[email protected]>
Home Page: http://gondor.apana.org.au/~herbert/
PGP Key: http://gondor.apana.org.au/~herbert/pubkey.txt