main.h 4.72 KB
Newer Older
1
2
3
4
5
6
7
8
9
10
11
12
/*
 * Copyright (C) 2016 Red Hat, Inc.
 * Author: Michael S. Tsirkin <mst@redhat.com>
 * This work is licensed under the terms of the GNU GPL, version 2.
 *
 * Common macros and functions for ring benchmarking.
 */
#ifndef MAIN_H
#define MAIN_H

#include <stdbool.h>

13
14
extern int param;

15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
extern bool do_exit;

#if defined(__x86_64__) || defined(__i386__)
#include "x86intrin.h"

static inline void wait_cycles(unsigned long long cycles)
{
	unsigned long long t;

	t = __rdtsc();
	while (__rdtsc() - t < cycles) {}
}

#define VMEXIT_CYCLES 500
#define VMENTRY_CYCLES 500

31
32
33
34
35
36
37
38
39
40
#elif defined(__s390x__)
static inline void wait_cycles(unsigned long long cycles)
{
	asm volatile("0: brctg %0,0b" : : "d" (cycles));
}

/* tweak me */
#define VMEXIT_CYCLES 200
#define VMENTRY_CYCLES 200

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
#else
static inline void wait_cycles(unsigned long long cycles)
{
	_Exit(5);
}
#define VMEXIT_CYCLES 0
#define VMENTRY_CYCLES 0
#endif

static inline void vmexit(void)
{
	if (!do_exit)
		return;
	
	wait_cycles(VMEXIT_CYCLES);
}
static inline void vmentry(void)
{
	if (!do_exit)
		return;
	
	wait_cycles(VMENTRY_CYCLES);
}

/* implemented by ring */
void alloc_ring(void);
/* guest side */
int add_inbuf(unsigned, void *, void *);
void *get_buf(unsigned *, void **);
void disable_call();
71
bool used_empty();
72
73
74
75
bool enable_call();
void kick_available();
/* host side */
void disable_kick();
76
bool avail_empty();
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
bool enable_kick();
bool use_buf(unsigned *, void **);
void call_used();

/* implemented by main */
extern bool do_sleep;
void kick(void);
void wait_for_kick(void);
void call(void);
void wait_for_call(void);

extern unsigned ring_size;

/* Compiler barrier - similar to what Linux uses */
#define barrier() asm volatile("" ::: "memory")

/* Is there a portable way to do this? */
#if defined(__x86_64__) || defined(__i386__)
#define cpu_relax() asm ("rep; nop" ::: "memory")
96
97
#elif defined(__s390x__)
#define cpu_relax() barrier()
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
#else
#define cpu_relax() assert(0)
#endif

extern bool do_relax;

static inline void busy_wait(void)
{
	if (do_relax)
		cpu_relax();
	else
		/* prevent compiler from removing busy loops */
		barrier();
} 

113
#if defined(__x86_64__) || defined(__i386__)
114
#define smp_mb()     asm volatile("lock; addl $0,-132(%%rsp)" ::: "memory", "cc")
115
#else
116
117
118
119
120
/*
 * Not using __ATOMIC_SEQ_CST since gcc docs say they are only synchronized
 * with other __ATOMIC_SEQ_CST calls.
 */
#define smp_mb() __sync_synchronize()
121
#endif
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136

/*
 * This abuses the atomic builtins for thread fences, and
 * adds a compiler barrier.
 */
#define smp_release() do { \
    barrier(); \
    __atomic_thread_fence(__ATOMIC_RELEASE); \
} while (0)

#define smp_acquire() do { \
    __atomic_thread_fence(__ATOMIC_ACQUIRE); \
    barrier(); \
} while (0)

137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
#if defined(__i386__) || defined(__x86_64__) || defined(__s390x__)
#define smp_wmb() barrier()
#else
#define smp_wmb() smp_release()
#endif

#ifdef __alpha__
#define smp_read_barrier_depends() smp_acquire()
#else
#define smp_read_barrier_depends() do {} while(0)
#endif

static __always_inline
void __read_once_size(const volatile void *p, void *res, int size)
{
        switch (size) {                                                 \
        case 1: *(unsigned char *)res = *(volatile unsigned char *)p; break;              \
        case 2: *(unsigned short *)res = *(volatile unsigned short *)p; break;            \
        case 4: *(unsigned int *)res = *(volatile unsigned int *)p; break;            \
        case 8: *(unsigned long long *)res = *(volatile unsigned long long *)p; break;            \
        default:                                                        \
                barrier();                                              \
                __builtin_memcpy((void *)res, (const void *)p, size);   \
                barrier();                                              \
        }                                                               \
}

static __always_inline void __write_once_size(volatile void *p, void *res, int size)
{
	switch (size) {
	case 1: *(volatile unsigned char *)p = *(unsigned char *)res; break;
	case 2: *(volatile unsigned short *)p = *(unsigned short *)res; break;
	case 4: *(volatile unsigned int *)p = *(unsigned int *)res; break;
	case 8: *(volatile unsigned long long *)p = *(unsigned long long *)res; break;
	default:
		barrier();
		__builtin_memcpy((void *)p, (const void *)res, size);
		barrier();
	}
}

#define READ_ONCE(x) \
({									\
	union { typeof(x) __val; char __c[1]; } __u;			\
	__read_once_size(&(x), __u.__c, sizeof(x));		\
	smp_read_barrier_depends(); /* Enforce dependency ordering from x */ \
	__u.__val;							\
})

#define WRITE_ONCE(x, val) \
({							\
	union { typeof(x) __val; char __c[1]; } __u =	\
		{ .__val = (typeof(x)) (val) }; \
	__write_once_size(&(x), __u.__c, sizeof(x));	\
	__u.__val;					\
})

194
#endif