1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
// generated source. do not edit.
#![allow(non_upper_case_globals, unused_macros, unused_imports)]
use crate::low::macros::*;
// Copyright Amazon.com, Inc. or its affiliates. All Rights Reserved.
// SPDX-License-Identifier: Apache-2.0 OR ISC OR MIT-0
// ----------------------------------------------------------------------------
// Add modulo p_256, z := (x + y) mod p_256, assuming x and y reduced
// Inputs x[4], y[4]; output z[4]
//
// extern void bignum_add_p256(uint64_t z[static 4], const uint64_t x[static 4],
// const uint64_t y[static 4]);
//
// Standard ARM ABI: X0 = z, X1 = x, X2 = y
// ----------------------------------------------------------------------------
macro_rules! z {
() => {
"x0"
};
}
macro_rules! x {
() => {
"x1"
};
}
macro_rules! y {
() => {
"x2"
};
}
macro_rules! c {
() => {
"x3"
};
}
macro_rules! d0 {
() => {
"x4"
};
}
macro_rules! d1 {
() => {
"x5"
};
}
macro_rules! d2 {
() => {
"x6"
};
}
macro_rules! d3 {
() => {
"x7"
};
}
macro_rules! n0 {
() => {
"x8"
};
}
macro_rules! n1 {
() => {
"x9"
};
}
macro_rules! n2 {
() => {
"x10"
};
}
macro_rules! n3 {
() => {
"x11"
};
}
/// Add modulo p_256, z := (x + y) mod p_256, assuming x and y reduced
///
/// Inputs x[4], y[4]; output z[4]
pub(crate) fn bignum_add_p256(z: &mut [u64; 4], x: &[u64; 4], y: &[u64; 4]) {
// SAFETY: inline assembly. see [crate::low::inline_assembly_safety] for safety info.
unsafe {
core::arch::asm!(
// First just add the numbers as [c;d3;d2;d1;d0]
Q!(" ldp " d0!() ", " d1!() ", [" x!() "]"),
Q!(" ldp " n0!() ", " n1!() ", [" y!() "]"),
Q!(" adds " d0!() ", " d0!() ", " n0!()),
Q!(" adcs " d1!() ", " d1!() ", " n1!()),
Q!(" ldp " d2!() ", " d3!() ", [" x!() ", #16]"),
Q!(" ldp " n2!() ", " n3!() ", [" y!() ", #16]"),
Q!(" adcs " d2!() ", " d2!() ", " n2!()),
Q!(" adcs " d3!() ", " d3!() ", " n3!()),
Q!(" adc " c!() ", xzr, xzr"),
// Now let [c;n3;n2;n1;n0] = [c;d3;d2;d1;d0] - p_256
Q!(" subs " n0!() ", " d0!() ", #0xffffffffffffffff"),
Q!(" mov " n1!() ", #0x00000000ffffffff"),
Q!(" sbcs " n1!() ", " d1!() ", " n1!()),
Q!(" sbcs " n2!() ", " d2!() ", xzr"),
Q!(" mov " n3!() ", #0xffffffff00000001"),
Q!(" sbcs " n3!() ", " d3!() ", " n3!()),
Q!(" sbcs " c!() ", " c!() ", xzr"),
// Select result according to whether (x + y) - p_256 < 0
Q!(" csel " d0!() ", " d0!() ", " n0!() ", cc"),
Q!(" csel " d1!() ", " d1!() ", " n1!() ", cc"),
Q!(" csel " d2!() ", " d2!() ", " n2!() ", cc"),
Q!(" csel " d3!() ", " d3!() ", " n3!() ", cc"),
// Store the result
Q!(" stp " d0!() ", " d1!() ", [" z!() "]"),
Q!(" stp " d2!() ", " d3!() ", [" z!() ", #16]"),
inout("x0") z.as_mut_ptr() => _,
inout("x1") x.as_ptr() => _,
inout("x2") y.as_ptr() => _,
// clobbers
out("x10") _,
out("x11") _,
out("x3") _,
out("x4") _,
out("x5") _,
out("x6") _,
out("x7") _,
out("x8") _,
out("x9") _,
)
};
}