linux_dsm_epyc7002/arch/arm/crypto/chacha-scalar-core.S
Ard Biesheuvel b36d8c09e7 crypto: arm/chacha - remove dependency on generic ChaCha driver
Instead of falling back to the generic ChaCha skcipher driver for
non-SIMD cases, use a fast scalar implementation for ARM authored
by Eric Biggers. This removes the module dependency on chacha-generic
altogether, which also simplifies things when we expose the ChaCha
library interface from this module.

Signed-off-by: Ard Biesheuvel <ardb@kernel.org>
Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au>
2019-11-17 09:02:40 +08:00

461 lines
11 KiB
ArmAsm

/* SPDX-License-Identifier: GPL-2.0 */
/*
* Copyright (C) 2018 Google, Inc.
*/
#include <linux/linkage.h>
#include <asm/assembler.h>
/*
* Design notes:
*
* 16 registers would be needed to hold the state matrix, but only 14 are
* available because 'sp' and 'pc' cannot be used. So we spill the elements
* (x8, x9) to the stack and swap them out with (x10, x11). This adds one
* 'ldrd' and one 'strd' instruction per round.
*
* All rotates are performed using the implicit rotate operand accepted by the
* 'add' and 'eor' instructions. This is faster than using explicit rotate
* instructions. To make this work, we allow the values in the second and last
* rows of the ChaCha state matrix (rows 'b' and 'd') to temporarily have the
* wrong rotation amount. The rotation amount is then fixed up just in time
* when the values are used. 'brot' is the number of bits the values in row 'b'
* need to be rotated right to arrive at the correct values, and 'drot'
* similarly for row 'd'. (brot, drot) start out as (0, 0) but we make it such
* that they end up as (25, 24) after every round.
*/
// ChaCha state registers
X0 .req r0
X1 .req r1
X2 .req r2
X3 .req r3
X4 .req r4
X5 .req r5
X6 .req r6
X7 .req r7
X8_X10 .req r8 // shared by x8 and x10
X9_X11 .req r9 // shared by x9 and x11
X12 .req r10
X13 .req r11
X14 .req r12
X15 .req r14
.macro __rev out, in, t0, t1, t2
.if __LINUX_ARM_ARCH__ >= 6
rev \out, \in
.else
lsl \t0, \in, #24
and \t1, \in, #0xff00
and \t2, \in, #0xff0000
orr \out, \t0, \in, lsr #24
orr \out, \out, \t1, lsl #8
orr \out, \out, \t2, lsr #8
.endif
.endm
.macro _le32_bswap x, t0, t1, t2
#ifdef __ARMEB__
__rev \x, \x, \t0, \t1, \t2
#endif
.endm
.macro _le32_bswap_4x a, b, c, d, t0, t1, t2
_le32_bswap \a, \t0, \t1, \t2
_le32_bswap \b, \t0, \t1, \t2
_le32_bswap \c, \t0, \t1, \t2
_le32_bswap \d, \t0, \t1, \t2
.endm
.macro __ldrd a, b, src, offset
#if __LINUX_ARM_ARCH__ >= 6
ldrd \a, \b, [\src, #\offset]
#else
ldr \a, [\src, #\offset]
ldr \b, [\src, #\offset + 4]
#endif
.endm
.macro __strd a, b, dst, offset
#if __LINUX_ARM_ARCH__ >= 6
strd \a, \b, [\dst, #\offset]
#else
str \a, [\dst, #\offset]
str \b, [\dst, #\offset + 4]
#endif
.endm
.macro _halfround a1, b1, c1, d1, a2, b2, c2, d2
// a += b; d ^= a; d = rol(d, 16);
add \a1, \a1, \b1, ror #brot
add \a2, \a2, \b2, ror #brot
eor \d1, \a1, \d1, ror #drot
eor \d2, \a2, \d2, ror #drot
// drot == 32 - 16 == 16
// c += d; b ^= c; b = rol(b, 12);
add \c1, \c1, \d1, ror #16
add \c2, \c2, \d2, ror #16
eor \b1, \c1, \b1, ror #brot
eor \b2, \c2, \b2, ror #brot
// brot == 32 - 12 == 20
// a += b; d ^= a; d = rol(d, 8);
add \a1, \a1, \b1, ror #20
add \a2, \a2, \b2, ror #20
eor \d1, \a1, \d1, ror #16
eor \d2, \a2, \d2, ror #16
// drot == 32 - 8 == 24
// c += d; b ^= c; b = rol(b, 7);
add \c1, \c1, \d1, ror #24
add \c2, \c2, \d2, ror #24
eor \b1, \c1, \b1, ror #20
eor \b2, \c2, \b2, ror #20
// brot == 32 - 7 == 25
.endm
.macro _doubleround
// column round
// quarterrounds: (x0, x4, x8, x12) and (x1, x5, x9, x13)
_halfround X0, X4, X8_X10, X12, X1, X5, X9_X11, X13
// save (x8, x9); restore (x10, x11)
__strd X8_X10, X9_X11, sp, 0
__ldrd X8_X10, X9_X11, sp, 8
// quarterrounds: (x2, x6, x10, x14) and (x3, x7, x11, x15)
_halfround X2, X6, X8_X10, X14, X3, X7, X9_X11, X15
.set brot, 25
.set drot, 24
// diagonal round
// quarterrounds: (x0, x5, x10, x15) and (x1, x6, x11, x12)
_halfround X0, X5, X8_X10, X15, X1, X6, X9_X11, X12
// save (x10, x11); restore (x8, x9)
__strd X8_X10, X9_X11, sp, 8
__ldrd X8_X10, X9_X11, sp, 0
// quarterrounds: (x2, x7, x8, x13) and (x3, x4, x9, x14)
_halfround X2, X7, X8_X10, X13, X3, X4, X9_X11, X14
.endm
.macro _chacha_permute nrounds
.set brot, 0
.set drot, 0
.rept \nrounds / 2
_doubleround
.endr
.endm
.macro _chacha nrounds
.Lnext_block\@:
// Stack: unused0-unused1 x10-x11 x0-x15 OUT IN LEN
// Registers contain x0-x9,x12-x15.
// Do the core ChaCha permutation to update x0-x15.
_chacha_permute \nrounds
add sp, #8
// Stack: x10-x11 orig_x0-orig_x15 OUT IN LEN
// Registers contain x0-x9,x12-x15.
// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
// Free up some registers (r8-r12,r14) by pushing (x8-x9,x12-x15).
push {X8_X10, X9_X11, X12, X13, X14, X15}
// Load (OUT, IN, LEN).
ldr r14, [sp, #96]
ldr r12, [sp, #100]
ldr r11, [sp, #104]
orr r10, r14, r12
// Use slow path if fewer than 64 bytes remain.
cmp r11, #64
blt .Lxor_slowpath\@
// Use slow path if IN and/or OUT isn't 4-byte aligned. Needed even on
// ARMv6+, since ldmia and stmia (used below) still require alignment.
tst r10, #3
bne .Lxor_slowpath\@
// Fast path: XOR 64 bytes of aligned data.
// Stack: x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is OUT.
// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
// x0-x3
__ldrd r8, r9, sp, 32
__ldrd r10, r11, sp, 40
add X0, X0, r8
add X1, X1, r9
add X2, X2, r10
add X3, X3, r11
_le32_bswap_4x X0, X1, X2, X3, r8, r9, r10
ldmia r12!, {r8-r11}
eor X0, X0, r8
eor X1, X1, r9
eor X2, X2, r10
eor X3, X3, r11
stmia r14!, {X0-X3}
// x4-x7
__ldrd r8, r9, sp, 48
__ldrd r10, r11, sp, 56
add X4, r8, X4, ror #brot
add X5, r9, X5, ror #brot
ldmia r12!, {X0-X3}
add X6, r10, X6, ror #brot
add X7, r11, X7, ror #brot
_le32_bswap_4x X4, X5, X6, X7, r8, r9, r10
eor X4, X4, X0
eor X5, X5, X1
eor X6, X6, X2
eor X7, X7, X3
stmia r14!, {X4-X7}
// x8-x15
pop {r0-r7} // (x8-x9,x12-x15,x10-x11)
__ldrd r8, r9, sp, 32
__ldrd r10, r11, sp, 40
add r0, r0, r8 // x8
add r1, r1, r9 // x9
add r6, r6, r10 // x10
add r7, r7, r11 // x11
_le32_bswap_4x r0, r1, r6, r7, r8, r9, r10
ldmia r12!, {r8-r11}
eor r0, r0, r8 // x8
eor r1, r1, r9 // x9
eor r6, r6, r10 // x10
eor r7, r7, r11 // x11
stmia r14!, {r0,r1,r6,r7}
ldmia r12!, {r0,r1,r6,r7}
__ldrd r8, r9, sp, 48
__ldrd r10, r11, sp, 56
add r2, r8, r2, ror #drot // x12
add r3, r9, r3, ror #drot // x13
add r4, r10, r4, ror #drot // x14
add r5, r11, r5, ror #drot // x15
_le32_bswap_4x r2, r3, r4, r5, r9, r10, r11
ldr r9, [sp, #72] // load LEN
eor r2, r2, r0 // x12
eor r3, r3, r1 // x13
eor r4, r4, r6 // x14
eor r5, r5, r7 // x15
subs r9, #64 // decrement and check LEN
stmia r14!, {r2-r5}
beq .Ldone\@
.Lprepare_for_next_block\@:
// Stack: x0-x15 OUT IN LEN
// Increment block counter (x12)
add r8, #1
// Store updated (OUT, IN, LEN)
str r14, [sp, #64]
str r12, [sp, #68]
str r9, [sp, #72]
mov r14, sp
// Store updated block counter (x12)
str r8, [sp, #48]
sub sp, #16
// Reload state and do next block
ldmia r14!, {r0-r11} // load x0-x11
__strd r10, r11, sp, 8 // store x10-x11 before state
ldmia r14, {r10-r12,r14} // load x12-x15
b .Lnext_block\@
.Lxor_slowpath\@:
// Slow path: < 64 bytes remaining, or unaligned input or output buffer.
// We handle it by storing the 64 bytes of keystream to the stack, then
// XOR-ing the needed portion with the data.
// Allocate keystream buffer
sub sp, #64
mov r14, sp
// Stack: ks0-ks15 x8-x9 x12-x15 x10-x11 orig_x0-orig_x15 OUT IN LEN
// Registers: r0-r7 are x0-x7; r8-r11 are free; r12 is IN; r14 is &ks0.
// x4-x7 are rotated by 'brot'; x12-x15 are rotated by 'drot'.
// Save keystream for x0-x3
__ldrd r8, r9, sp, 96
__ldrd r10, r11, sp, 104
add X0, X0, r8
add X1, X1, r9
add X2, X2, r10
add X3, X3, r11
_le32_bswap_4x X0, X1, X2, X3, r8, r9, r10
stmia r14!, {X0-X3}
// Save keystream for x4-x7
__ldrd r8, r9, sp, 112
__ldrd r10, r11, sp, 120
add X4, r8, X4, ror #brot
add X5, r9, X5, ror #brot
add X6, r10, X6, ror #brot
add X7, r11, X7, ror #brot
_le32_bswap_4x X4, X5, X6, X7, r8, r9, r10
add r8, sp, #64
stmia r14!, {X4-X7}
// Save keystream for x8-x15
ldm r8, {r0-r7} // (x8-x9,x12-x15,x10-x11)
__ldrd r8, r9, sp, 128
__ldrd r10, r11, sp, 136
add r0, r0, r8 // x8
add r1, r1, r9 // x9
add r6, r6, r10 // x10
add r7, r7, r11 // x11
_le32_bswap_4x r0, r1, r6, r7, r8, r9, r10
stmia r14!, {r0,r1,r6,r7}
__ldrd r8, r9, sp, 144
__ldrd r10, r11, sp, 152
add r2, r8, r2, ror #drot // x12
add r3, r9, r3, ror #drot // x13
add r4, r10, r4, ror #drot // x14
add r5, r11, r5, ror #drot // x15
_le32_bswap_4x r2, r3, r4, r5, r9, r10, r11
stmia r14, {r2-r5}
// Stack: ks0-ks15 unused0-unused7 x0-x15 OUT IN LEN
// Registers: r8 is block counter, r12 is IN.
ldr r9, [sp, #168] // LEN
ldr r14, [sp, #160] // OUT
cmp r9, #64
mov r0, sp
movle r1, r9
movgt r1, #64
// r1 is number of bytes to XOR, in range [1, 64]
.if __LINUX_ARM_ARCH__ < 6
orr r2, r12, r14
tst r2, #3 // IN or OUT misaligned?
bne .Lxor_next_byte\@
.endif
// XOR a word at a time
.rept 16
subs r1, #4
blt .Lxor_words_done\@
ldr r2, [r12], #4
ldr r3, [r0], #4
eor r2, r2, r3
str r2, [r14], #4
.endr
b .Lxor_slowpath_done\@
.Lxor_words_done\@:
ands r1, r1, #3
beq .Lxor_slowpath_done\@
// XOR a byte at a time
.Lxor_next_byte\@:
ldrb r2, [r12], #1
ldrb r3, [r0], #1
eor r2, r2, r3
strb r2, [r14], #1
subs r1, #1
bne .Lxor_next_byte\@
.Lxor_slowpath_done\@:
subs r9, #64
add sp, #96
bgt .Lprepare_for_next_block\@
.Ldone\@:
.endm // _chacha
/*
* void chacha_doarm(u8 *dst, const u8 *src, unsigned int bytes,
* const u32 *state, int nrounds);
*/
ENTRY(chacha_doarm)
cmp r2, #0 // len == 0?
reteq lr
ldr ip, [sp]
cmp ip, #12
push {r0-r2,r4-r11,lr}
// Push state x0-x15 onto stack.
// Also store an extra copy of x10-x11 just before the state.
add X12, r3, #48
ldm X12, {X12,X13,X14,X15}
push {X12,X13,X14,X15}
sub sp, sp, #64
__ldrd X8_X10, X9_X11, r3, 40
__strd X8_X10, X9_X11, sp, 8
__strd X8_X10, X9_X11, sp, 56
ldm r3, {X0-X9_X11}
__strd X0, X1, sp, 16
__strd X2, X3, sp, 24
__strd X4, X5, sp, 32
__strd X6, X7, sp, 40
__strd X8_X10, X9_X11, sp, 48
beq 1f
_chacha 20
0: add sp, #76
pop {r4-r11, pc}
1: _chacha 12
b 0b
ENDPROC(chacha_doarm)
/*
* void hchacha_block_arm(const u32 state[16], u32 out[8], int nrounds);
*/
ENTRY(hchacha_block_arm)
push {r1,r4-r11,lr}
cmp r2, #12 // ChaCha12 ?
mov r14, r0
ldmia r14!, {r0-r11} // load x0-x11
push {r10-r11} // store x10-x11 to stack
ldm r14, {r10-r12,r14} // load x12-x15
sub sp, #8
beq 1f
_chacha_permute 20
// Skip over (unused0-unused1, x10-x11)
0: add sp, #16
// Fix up rotations of x12-x15
ror X12, X12, #drot
ror X13, X13, #drot
pop {r4} // load 'out'
ror X14, X14, #drot
ror X15, X15, #drot
// Store (x0-x3,x12-x15) to 'out'
stm r4, {X0,X1,X2,X3,X12,X13,X14,X15}
pop {r4-r11,pc}
1: _chacha_permute 12
b 0b
ENDPROC(hchacha_block_arm)