并行计算之Memory barrier（内存

 1 // test2.cpp
 2 #include <pthread.h>
 3 #include <assert.h>
 4  
 5 // -------------------
 6 int cpu_thread1 = 0;
 7 int cpu_thread2 = 1;
 8  
 9 volatile int x, y, r1, r2;
10  
11 void start()
12 {
13     x = y = r1 = r2 = 0;
14 }
15  
16 void end()
17 {
18     assert(!(r1 == 0 && r2 == 0));
19 }
20  
21 void run1()
22 {
23     x = 1;
24     r1 = y;
25 }
26  
27 void run2()
28 {
29     y = 1;
30     r2 = x;
31 }
32  
33 // -------------------
34 static pthread_barrier_t barrier_start;
35 static pthread_barrier_t barrier_end;
36  
37 static void* thread1(void*)
38 {
39     while (1) {
40         pthread_barrier_wait(&barrier_start);
41         run1();
42         pthread_barrier_wait(&barrier_end);
43     }
44     return NULL;
45 }
46  
47 static void* thread2(void*)
48 {
49     while (1) {
50         pthread_barrier_wait(&barrier_start);
51         run2();
52         pthread_barrier_wait(&barrier_end);
53     }
54     return NULL;
55 }
56  
57 int main()
58 {
59     assert(pthread_barrier_init(&barrier_start, NULL, 3) == 0);
60     assert(pthread_barrier_init(&barrier_end, NULL, 3) == 0);
61  
62     pthread_t t1;
63     pthread_t t2;
64     assert(pthread_create(&t1, NULL, thread1, NULL) == 0);
65     assert(pthread_create(&t2, NULL, thread2, NULL) == 0);
66  
67     cpu_set_t cs;
68     CPU_ZERO(&cs);
69     CPU_SET(cpu_thread1, &cs);
70     assert(pthread_setaffinity_np(t1, sizeof(cs), &cs) == 0);
71     CPU_ZERO(&cs);
72     CPU_SET(cpu_thread2, &cs);
73     assert(pthread_setaffinity_np(t2, sizeof(cs), &cs) == 0);
74  
75     while (1) {
76         start();
77         pthread_barrier_wait(&barrier_start);
78         pthread_barrier_wait(&barrier_end);
79         end();
80     }
81  
82     return 0;
83 } 

  1 /*
  2 * A simple kernel FIFO implementation.
  3 *
  4 * Copyright (C) 2004 Stelian Pop <stelian@popies.net>
  5 *
  6 * This program is free software; you can redistribute it and/or modify
  7 * it under the terms of the GNU General Public License as published by
  8 * the Free Software Foundation; either version 2 of the License, or
  9 * (at your option) any later version.
 10 *
 11 * This program is distributed in the hope that it will be useful,
 12 * but WITHOUT ANY WARRANTY; without even the implied warranty of
 13 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
 14 * GNU General Public License for more details.
 15 *
 16 * You should have received a copy of the GNU General Public License
 17 * along with this program; if not, write to the Free Software
 18 * Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
 19 *
 20 */
 21  
 22 #include <linux/kernel.h>
 23 #include <linux/module.h>
 24 #include <linux/slab.h>
 25 #include <linux/err.h>
 26 #include <linux/kfifo.h>
 27 #include <linux/log2.h>
 28  
 29 /**
 30 * kfifo_init - allocates a new FIFO using a preallocated buffer
 31 * @buffer: the preallocated buffer to be used.
 32 * @size: the size of the internal buffer, this have to be a power of 2.
 33 * @gfp_mask: get_free_pages mask, passed to kmalloc()
 34 * @lock: the lock to be used to protect the fifo buffer
 35 *
 36 * Do NOT pass the kfifo to kfifo_free() after use! Simply free the
 37 * &struct kfifo with kfree().
 38 */
 39 struct kfifo *kfifo_init(unsigned char *buffer, unsigned int size,
 40 gfp_t gfp_mask, spinlock_t *lock)
 41 {
 42     struct kfifo *fifo;
 43  
 44     /* size must be a power of 2 */
 45     BUG_ON(!is_power_of_2(size));
 46  
 47     fifo = kmalloc(sizeof(struct kfifo), gfp_mask);
 48     if (!fifo)
 49         return ERR_PTR(-ENOMEM);
 50  
 51     fifo->buffer = buffer;
 52     fifo->size = size;
 53     fifo->in = fifo->out = 0;
 54     fifo->lock = lock;
 55  
 56     return fifo;
 57 }
 58 EXPORT_SYMBOL(kfifo_init);
 59  
 60 /**
 61 * kfifo_alloc - allocates a new FIFO and its internal buffer
 62 * @size: the size of the internal buffer to be allocated.
 63 * @gfp_mask: get_free_pages mask, passed to kmalloc()
 64 * @lock: the lock to be used to protect the fifo buffer
 65 *
 66 * The size will be rounded-up to a power of 2.
 67 */
 68 struct kfifo *kfifo_alloc(unsigned int size, gfp_t gfp_mask, spinlock_t *lock)
 69 {
 70     unsigned char *buffer;
 71     struct kfifo *ret;
 72  
 73     /*
 74     * round up to the next power of 2, since our ‘let the indices
 75     * wrap‘ technique works only in this case.
 76     */
 77     if (!is_power_of_2(size)) {
 78         BUG_ON(size > 0x80000000);
 79         size = roundup_pow_of_two(size);
 80     }
 81  
 82     buffer = kmalloc(size, gfp_mask);
 83     if (!buffer)
 84         return ERR_PTR(-ENOMEM);
 85  
 86     ret = kfifo_init(buffer, size, gfp_mask, lock);
 87  
 88     if (IS_ERR(ret))
 89         kfree(buffer);
 90  
 91     return ret;
 92 }
 93 EXPORT_SYMBOL(kfifo_alloc);
 94  
 95 /**
 96 * kfifo_free - frees the FIFO
 97 * @fifo: the fifo to be freed.
 98 */
 99 void kfifo_free(struct kfifo *fifo)
100 {
101     kfree(fifo->buffer);
102     kfree(fifo);
103 }
104 EXPORT_SYMBOL(kfifo_free);
105  
106 /**
107 * __kfifo_put - puts some data into the FIFO, no locking version
108 * @fifo: the fifo to be used.
109 * @buffer: the data to be added.
110 * @len: the length of the data to be added.
111 *
112 * This function copies at most @len bytes from the @buffer into
113 * the FIFO depending on the free space, and returns the number of
114 * bytes copied.
115 *
116 * Note that with only one concurrent reader and one concurrent
117 * writer, you don‘t need extra locking to use these functions.
118 */
119 unsigned int __kfifo_put(struct kfifo *fifo,
120 const unsigned char *buffer, unsigned int len)
121 {
122     unsigned int l;
123  
124     len = min(len, fifo->size - fifo->in + fifo->out);
125  
126     /*
127     * Ensure that we sample the fifo->out index -before- we
128     * start putting bytes into the kfifo.
129     */
130     smp_mb();
131  
132     /* first put the data starting from fifo->in to buffer end */
133     l = min(len, fifo->size - (fifo->in & (fifo->size - 1)));
134     memcpy(fifo->buffer + (fifo->in & (fifo->size - 1)), buffer, l);
135  
136     /* then put the rest (if any) at the beginning of the buffer */
137     memcpy(fifo->buffer, buffer + l, len - l);
138  
139     /*
140     * Ensure that we add the bytes to the kfifo -before-
141     * we update the fifo->in index.
142     */
143     smp_wmb();
144     fifo->in += len;
145  
146     return len;
147 }
148 EXPORT_SYMBOL(__kfifo_put);
149  
150 /**
151 * __kfifo_get - gets some data from the FIFO, no locking version
152 * @fifo: the fifo to be used.
153 * @buffer: where the data must be copied.
154 * @len: the size of the destination buffer.
155 *
156 * This function copies at most @len bytes from the FIFO into the
157 * @buffer and returns the number of copied bytes.
158 *
159 * Note that with only one concurrent reader and one concurrent
160 * writer, you don‘t need extra locking to use these functions.
161 */
162 unsigned int __kfifo_get(struct kfifo *fifo,
163 unsigned char *buffer, unsigned int len)
164 {
165     unsigned int l;
166  
167     len = min(len, fifo->in - fifo->out);
168  
169     /*
170     * Ensure that we sample the fifo->in index -before- we
171     * start removing bytes from the kfifo.
172     */
173  
174     smp_rmb();
175  
176     /* first get the data from fifo->out until the end of the buffer */
177     l = min(len, fifo->size - (fifo->out & (fifo->size - 1)));
178     memcpy(buffer, fifo->buffer + (fifo->out & (fifo->size - 1)), l);
179  
180     /* then get the rest (if any) from the beginning of the buffer */
181     memcpy(buffer + l, fifo->buffer, len - l);
182  
183     /*
184     * Ensure that we remove the bytes from the kfifo -before-
185     * we update the fifo->out index.
186     */
187  
188     smp_mb();
189  
190     fifo->out += len;
191  
192     return len;
193 }
194 EXPORT_SYMBOL(__kfifo_get);