diff options
| author |   Patrick Steuer <patrick.steuer@de.ibm.com> | 2021-11-04 15:58:51 +0100 |
|---|---|---|
| committer |   Heiko Carstens <hca@linux.ibm.com> | 2021-12-06 14:42:24 +0100 |
| commit | b087dfab4d3902681550fd1f5ff9c3e942059478 (patch) | |
| tree | acc95523edb8e6eac15e296eaf9ecb5b5ac889b5 /arch/s390/include/asm | |
| parent | Linux 5.16-rc4 (diff) | |
| download | linux-dev-b087dfab4d3902681550fd1f5ff9c3e942059478.tar.xz linux-dev-b087dfab4d3902681550fd1f5ff9c3e942059478.zip | |
s390/crypto: add SIMD implementation for ChaCha20
Add an implementation of the ChaCha20 stream cipher (see e.g. RFC 7539)
that makes use of z13's vector instruction set extension.
The original implementation is by Andy Polyakov which is
adapted for kernel use.
Four to six blocks are processed in parallel resulting in a performance
gain for inputs >= 256 bytes.
chacha20-generic
1 operation in 622 cycles (256 bytes)
1 operation in 2346 cycles (1024 bytes)
chacha20-s390
1 operation in 218 cycles (256 bytes)
1 operation in 647 cycles (1024 bytes)
Cc: Andy Polyakov <appro@openssl.org>
Reviewed-by: Harald Freudenberger <freude@de.ibm.com>
Signed-off-by: Patrick Steuer <patrick.steuer@de.ibm.com>
Signed-off-by: Heiko Carstens <hca@linux.ibm.com>
Diffstat (limited to 'arch/s390/include/asm')
| -rw-r--r-- | arch/s390/include/asm/vx-insn.h | 117 |
1 files changed, 117 insertions, 0 deletions
diff --git a/arch/s390/include/asm/vx-insn.h b/arch/s390/include/asm/vx-insn.h index 0c05a673811c..87e6cc2aeba4 100644 --- a/arch/s390/include/asm/vx-insn.h +++ b/arch/s390/include/asm/vx-insn.h @@ -372,6 +372,16 @@ MRXBOPC \hint, 0x36, v1, v3 .endm +/* VECTOR STORE */ +.macro VST vr1, disp, index="%r0", base + VX_NUM v1, \vr1 + GR_NUM x2, \index + GR_NUM b2, \base /* Base register */ + .word 0xE700 | ((v1&15) << 4) | (x2&15) + .word (b2 << 12) | (\disp) + MRXBOPC 0, 0x0E, v1 +.endm + /* VECTOR STORE MULTIPLE */ .macro VSTM vfrom, vto, disp, base, hint=3 VX_NUM v1, \vfrom @@ -411,6 +421,81 @@ VUPLL \vr1, \vr2, 2 .endm +/* VECTOR PERMUTE DOUBLEWORD IMMEDIATE */ +.macro VPDI vr1, vr2, vr3, m4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC \m4, 0x84, v1, v2, v3 +.endm + +/* VECTOR REPLICATE */ +.macro VREP vr1, vr3, imm2, m4 + VX_NUM v1, \vr1 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v3&15) + .word \imm2 + MRXBOPC \m4, 0x4D, v1, v3 +.endm +.macro VREPB vr1, vr3, imm2 + VREP \vr1, \vr3, \imm2, 0 +.endm +.macro VREPH vr1, vr3, imm2 + VREP \vr1, \vr3, \imm2, 1 +.endm +.macro VREPF vr1, vr3, imm2 + VREP \vr1, \vr3, \imm2, 2 +.endm +.macro VREPG vr1, vr3, imm2 + VREP \vr1, \vr3, \imm2, 3 +.endm + +/* VECTOR MERGE HIGH */ +.macro VMRH vr1, vr2, vr3, m4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC \m4, 0x61, v1, v2, v3 +.endm +.macro VMRHB vr1, vr2, vr3 + VMRH \vr1, \vr2, \vr3, 0 +.endm +.macro VMRHH vr1, vr2, vr3 + VMRH \vr1, \vr2, \vr3, 1 +.endm +.macro VMRHF vr1, vr2, vr3 + VMRH \vr1, \vr2, \vr3, 2 +.endm +.macro VMRHG vr1, vr2, vr3 + VMRH \vr1, \vr2, \vr3, 3 +.endm + +/* VECTOR MERGE LOW */ +.macro VMRL vr1, vr2, vr3, m4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) + MRXBOPC \m4, 0x60, v1, v2, v3 +.endm +.macro VMRLB vr1, vr2, vr3 + VMRL \vr1, \vr2, \vr3, 0 +.endm +.macro VMRLH vr1, vr2, vr3 + VMRL \vr1, \vr2, \vr3, 1 +.endm +.macro VMRLF vr1, vr2, vr3 + VMRL \vr1, \vr2, \vr3, 2 +.endm +.macro VMRLG vr1, vr2, vr3 + VMRL \vr1, \vr2, \vr3, 3 +.endm + /* Vector integer instructions */ @@ -557,5 +642,37 @@ VESRAV \vr1, \vr2, \vr3, 3 .endm +/* VECTOR ELEMENT ROTATE LEFT LOGICAL */ +.macro VERLL vr1, vr3, disp, base="%r0", m4 + VX_NUM v1, \vr1 + VX_NUM v3, \vr3 + GR_NUM b2, \base + .word 0xE700 | ((v1&15) << 4) | (v3&15) + .word (b2 << 12) | (\disp) + MRXBOPC \m4, 0x33, v1, v3 +.endm +.macro VERLLB vr1, vr3, disp, base="%r0" + VERLL \vr1, \vr3, \disp, \base, 0 +.endm +.macro VERLLH vr1, vr3, disp, base="%r0" + VERLL \vr1, \vr3, \disp, \base, 1 +.endm +.macro VERLLF vr1, vr3, disp, base="%r0" + VERLL \vr1, \vr3, \disp, \base, 2 +.endm +.macro VERLLG vr1, vr3, disp, base="%r0" + VERLL \vr1, \vr3, \disp, \base, 3 +.endm + +/* VECTOR SHIFT LEFT DOUBLE BY BYTE */ +.macro VSLDB vr1, vr2, vr3, imm4 + VX_NUM v1, \vr1 + VX_NUM v2, \vr2 + VX_NUM v3, \vr3 + .word 0xE700 | ((v1&15) << 4) | (v2&15) + .word ((v3&15) << 12) | (\imm4) + MRXBOPC 0, 0x77, v1, v2, v3 +.endm + #endif /* __ASSEMBLY__ */ #endif /* __ASM_S390_VX_INSN_H */ |