summaryrefslogtreecommitdiffstats
path: root/arch/arm/include/asm/div64.h
blob: 898e9c78a7e75714ae53d6dd4987f6a9791bd8d8 (plain)
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
/* SPDX-License-Identifier: GPL-2.0 */
#ifndef __ASM_ARM_DIV64
#define __ASM_ARM_DIV64

#include <linux/types.h>
#include <asm/compiler.h>

/*
 * The semantics of __div64_32() are:
 *
 * uint32_t __div64_32(uint64_t *n, uint32_t base)
 * {
 * 	uint32_t remainder = *n % base;
 * 	*n = *n / base;
 * 	return remainder;
 * }
 *
 * In other words, a 64-bit dividend with a 32-bit divisor producing
 * a 64-bit result and a 32-bit remainder.  To accomplish this optimally
 * we override the generic version in lib/div64.c to call our __do_div64
 * assembly implementation with completely non standard calling convention
 * for arguments and results (beware).
 */

#ifdef __ARMEB__
#define __xh "r0"
#define __xl "r1"
#else
#define __xl "r0"
#define __xh "r1"
#endif

static inline uint32_t __div64_32(uint64_t *n, uint32_t base)
{
	register unsigned int __base      asm("r4") = base;
	register unsigned long long __n   asm("r0") = *n;
	register unsigned long long __res asm("r2");
	register unsigned int __rem       asm(__xh);
	asm(	__asmeq("%0", __xh)
		__asmeq("%1", "r2")
		__asmeq("%2", "r0")
		__asmeq("%3", "r4")
		"bl	__do_div64"
		: "=r" (__rem), "=r" (__res)
		: "r" (__n), "r" (__base)
		: "ip", "lr", "cc");
	*n = __res;
	return __rem;
}
#define __div64_32 __div64_32

#if !defined(CONFIG_AEABI)

/*
 * In OABI configurations, some uses of the do_div function
 * cause gcc to run out of registers. To work around that,
 * we can force the use of the out-of-line version for
 * configurations that build a OABI kernel.
 */
#define do_div(n, base) __div64_32(&(n), base)

#else

/*
 * gcc versions earlier than 4.0 are simply too problematic for the
 * __div64_const32() code in asm-generic/div64.h. First there is
 * gcc PR 15089 that tend to trig on more complex constructs, spurious
 * .global __udivsi3 are inserted even if none of those symbols are
 * referenced in the generated code, and those gcc versions are not able
 * to do constant propagation on long long values anyway.
 */

#define __div64_const32_is_OK (__GNUC__ >= 4)

static inline uint64_t __arch_xprod_64(uint64_t m, uint64_t n, bool bias)
{
	unsigned long long res;
	register unsigned int tmp asm("ip") = 0;

	if (!bias) {
		asm (	"umull	%Q0, %R0, %Q1, %Q2\n\t"
			"mov	%Q0, #0"
			: "=&r" (res)
			: "r" (m), "r" (n)
			: "cc");
	} else if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
		res = m;
		asm (	"umlal	%Q0, %R0, %Q1, %Q2\n\t"
			"mov	%Q0, #0"
			: "+&r" (res)
			: "r" (m), "r" (n)
			: "cc");
	} else {
		asm (	"umull	%Q0, %R0, %Q2, %Q3\n\t"
			"cmn	%Q0, %Q2\n\t"
			"adcs	%R0, %R0, %R2\n\t"
			"adc	%Q0, %1, #0"
			: "=&r" (res), "+&r" (tmp)
			: "r" (m), "r" (n)
			: "cc");
	}

	if (!(m & ((1ULL << 63) | (1ULL << 31)))) {
		asm (	"umlal	%R0, %Q0, %R1, %Q2\n\t"
			"umlal	%R0, %Q0, %Q1, %R2\n\t"
			"mov	%R0, #0\n\t"
			"umlal	%Q0, %R0, %R1, %R2"
			: "+&r" (res)
			: "r" (m), "r" (n)
			: "cc");
	} else {
		asm (	"umlal	%R0, %Q0, %R2, %Q3\n\t"
			"umlal	%R0, %1, %Q2, %R3\n\t"
			"mov	%R0, #0\n\t"
			"adds	%Q0, %1, %Q0\n\t"
			"adc	%R0, %R0, #0\n\t"
			"umlal	%Q0, %R0, %R2, %R3"
			: "+&r" (res), "+&r" (tmp)
			: "r" (m), "r" (n)
			: "cc");
	}

	return res;
}
#define __arch_xprod_64 __arch_xprod_64

#include <asm-generic/div64.h>

#endif

#endif