xref: /freebsd/share/man/man9/atomic.9 (revision 7e9ed7352231d59b01f8270d35c2b201d3c1c052)
1.\" Copyright (c) 2000-2001 John H. Baldwin <jhb@FreeBSD.org>
2.\" All rights reserved.
3.\"
4.\" Redistribution and use in source and binary forms, with or without
5.\" modification, are permitted provided that the following conditions
6.\" are met:
7.\" 1. Redistributions of source code must retain the above copyright
8.\"    notice, this list of conditions and the following disclaimer.
9.\" 2. Redistributions in binary form must reproduce the above copyright
10.\"    notice, this list of conditions and the following disclaimer in the
11.\"    documentation and/or other materials provided with the distribution.
12.\"
13.\" THIS SOFTWARE IS PROVIDED BY THE DEVELOPERS ``AS IS'' AND ANY EXPRESS OR
14.\" IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES
15.\" OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED.
16.\" IN NO EVENT SHALL THE DEVELOPERS BE LIABLE FOR ANY DIRECT, INDIRECT,
17.\" INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
18.\" NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
19.\" DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
20.\" THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
21.\" (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF
22.\" THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
23.\"
24.\" $FreeBSD$
25.\"
26.Dd August 20, 2013
27.Dt ATOMIC 9
28.Os
29.Sh NAME
30.Nm atomic_add ,
31.Nm atomic_clear ,
32.Nm atomic_cmpset ,
33.Nm atomic_fetchadd ,
34.Nm atomic_load ,
35.Nm atomic_readandclear ,
36.Nm atomic_set ,
37.Nm atomic_subtract ,
38.Nm atomic_store
39.Nd atomic operations
40.Sh SYNOPSIS
41.In sys/types.h
42.In machine/atomic.h
43.Ft void
44.Fn atomic_add_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
45.Ft void
46.Fn atomic_clear_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
47.Ft int
48.Fo atomic_cmpset_[acq_|rel_]<type>
49.Fa "volatile <type> *dst"
50.Fa "<type> old"
51.Fa "<type> new"
52.Fc
53.Ft <type>
54.Fn atomic_fetchadd_<type> "volatile <type> *p" "<type> v"
55.Ft <type>
56.Fn atomic_load_acq_<type> "volatile <type> *p"
57.Ft <type>
58.Fn atomic_readandclear_<type> "volatile <type> *p"
59.Ft void
60.Fn atomic_set_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
61.Ft void
62.Fn atomic_subtract_[acq_|rel_]<type> "volatile <type> *p" "<type> v"
63.Ft void
64.Fn atomic_store_rel_<type> "volatile <type> *p" "<type> v"
65.Ft <type>
66.Fn atomic_swap_<type> "volatile <type> *p" "<type> v"
67.Ft int
68.Fn atomic_testandset_<type> "volatile <type> *p" "u_int v"
69.Sh DESCRIPTION
70Each of the atomic operations is guaranteed to be atomic in the presence of
71interrupts.
72They can be used to implement reference counts or as building blocks for more
73advanced synchronization primitives such as mutexes.
74.Ss Types
75Each atomic operation operates on a specific
76.Fa type .
77The type to use is indicated in the function name.
78The available types that can be used are:
79.Pp
80.Bl -tag -offset indent -width short -compact
81.It Li int
82unsigned integer
83.It Li long
84unsigned long integer
85.It Li ptr
86unsigned integer the size of a pointer
87.It Li 32
88unsigned 32-bit integer
89.It Li 64
90unsigned 64-bit integer
91.El
92.Pp
93For example, the function to atomically add two integers is called
94.Fn atomic_add_int .
95.Pp
96Certain architectures also provide operations for types smaller than
97.Dq Li int .
98.Pp
99.Bl -tag -offset indent -width short -compact
100.It Li char
101unsigned character
102.It Li short
103unsigned short integer
104.It Li 8
105unsigned 8-bit integer
106.It Li 16
107unsigned 16-bit integer
108.El
109.Pp
110These must not be used in MI code because the instructions to implement them
111efficiently may not be available.
112.Ss Memory Barriers
113Memory barriers are used to guarantee the order of data accesses in
114two ways.
115First, they specify hints to the compiler to not re-order or optimize the
116operations.
117Second, on architectures that do not guarantee ordered data accesses,
118special instructions or special variants of instructions are used to indicate
119to the processor that data accesses need to occur in a certain order.
120As a result, most of the atomic operations have three variants in order to
121include optional memory barriers.
122The first form just performs the operation without any explicit barriers.
123The second form uses a read memory barrier, and the third variant uses a write
124memory barrier.
125.Pp
126The second variant of each operation includes a read memory barrier.
127This barrier ensures that the effects of this operation are completed before the
128effects of any later data accesses.
129As a result, the operation is said to have acquire semantics as it acquires a
130pseudo-lock requiring further operations to wait until it has completed.
131To denote this, the suffix
132.Dq Li _acq
133is inserted into the function name immediately prior to the
134.Dq Li _ Ns Aq Fa type
135suffix.
136For example, to subtract two integers ensuring that any later writes will
137happen after the subtraction is performed, use
138.Fn atomic_subtract_acq_int .
139.Pp
140The third variant of each operation includes a write memory barrier.
141This ensures that all effects of all previous data accesses are completed
142before this operation takes place.
143As a result, the operation is said to have release semantics as it releases
144any pending data accesses to be completed before its operation is performed.
145To denote this, the suffix
146.Dq Li _rel
147is inserted into the function name immediately prior to the
148.Dq Li _ Ns Aq Fa type
149suffix.
150For example, to add two long integers ensuring that all previous
151writes will happen first, use
152.Fn atomic_add_rel_long .
153.Pp
154A practical example of using memory barriers is to ensure that data accesses
155that are protected by a lock are all performed while the lock is held.
156To achieve this, one would use a read barrier when acquiring the lock to
157guarantee that the lock is held before any protected operations are performed.
158Finally, one would use a write barrier when releasing the lock to ensure that
159all of the protected operations are completed before the lock is released.
160.Ss Multiple Processors
161The current set of atomic operations do not necessarily guarantee atomicity
162across multiple processors.
163To guarantee atomicity across processors, not only does the individual
164operation need to be atomic on the processor performing the operation, but
165the result of the operation needs to be pushed out to stable storage and the
166caches of all other processors on the system need to invalidate any cache
167lines that include the affected memory region.
168On the
169.Tn i386
170architecture, the cache coherency model requires that the hardware perform
171this task, thus the atomic operations are atomic across multiple processors.
172On the
173.Tn ia64
174architecture, coherency is only guaranteed for pages that are configured to
175using a caching policy of either uncached or write back.
176.Ss Semantics
177This section describes the semantics of each operation using a C like notation.
178.Bl -hang
179.It Fn atomic_add p v
180.Bd -literal -compact
181*p += v;
182.Ed
183.It Fn atomic_clear p v
184.Bd -literal -compact
185*p &= ~v;
186.Ed
187.It Fn atomic_cmpset dst old new
188.Bd -literal -compact
189if (*dst == old) {
190	*dst = new;
191	return (1);
192} else
193	return (0);
194.Ed
195.El
196.Pp
197The
198.Fn atomic_cmpset
199functions are not implemented for the types
200.Dq Li char ,
201.Dq Li short ,
202.Dq Li 8 ,
203and
204.Dq Li 16 .
205.Bl -hang
206.It Fn atomic_fetchadd p v
207.Bd -literal -compact
208tmp = *p;
209*p += v;
210return (tmp);
211.Ed
212.El
213.Pp
214The
215.Fn atomic_fetchadd
216functions are only implemented for the types
217.Dq Li int ,
218.Dq Li long
219and
220.Dq Li 32
221and do not have any variants with memory barriers at this time.
222.Bl -hang
223.It Fn atomic_load p
224.Bd -literal -compact
225return (*p);
226.Ed
227.El
228.Pp
229The
230.Fn atomic_load
231functions are only provided with acquire memory barriers.
232.Bl -hang
233.It Fn atomic_readandclear p
234.Bd -literal -compact
235tmp = *p;
236*p = 0;
237return (tmp);
238.Ed
239.El
240.Pp
241The
242.Fn atomic_readandclear
243functions are not implemented for the types
244.Dq Li char ,
245.Dq Li short ,
246.Dq Li ptr ,
247.Dq Li 8 ,
248and
249.Dq Li 16
250and do not have any variants with memory barriers at this time.
251.Bl -hang
252.It Fn atomic_set p v
253.Bd -literal -compact
254*p |= v;
255.Ed
256.It Fn atomic_subtract p v
257.Bd -literal -compact
258*p -= v;
259.Ed
260.It Fn atomic_store p v
261.Bd -literal -compact
262*p = v;
263.Ed
264.El
265.Pp
266The
267.Fn atomic_store
268functions are only provided with release memory barriers.
269.Bl -hang
270.It Fn atomic_swap p v
271.Bd -literal -compact
272tmp = *p;
273*p = v;
274return (tmp);
275.Ed
276.El
277.Pp
278The
279.Fn atomic_swap
280functions are not implemented for the types
281.Dq Li char ,
282.Dq Li short ,
283.Dq Li ptr ,
284.Dq Li 8 ,
285and
286.Dq Li 16
287and do not have any variants with memory barriers at this time.
288.Bl -hang
289.It Fn atomic_testandset p v
290.Bd -literal -compact
291bit = 1 << (v % (sizeof(*p) * NBBY));
292tmp = (*p & bit) != 0;
293*p |= bit;
294return (tmp);
295.Ed
296.El
297.Pp
298The
299.Fn atomic_testandset
300functions are only implemented for the types
301.Dq Li int ,
302.Dq Li long
303and
304.Dq Li 32
305and do not have any variants with memory barriers at this time.
306.Pp
307The type
308.Dq Li 64
309is currently not implemented for any of the atomic operations on the
310.Tn arm ,
311.Tn i386 ,
312and
313.Tn powerpc
314architectures.
315.Sh RETURN VALUES
316The
317.Fn atomic_cmpset
318function returns the result of the compare operation.
319The
320.Fn atomic_fetchadd ,
321.Fn atomic_load ,
322.Fn atomic_readandclear ,
323and
324.Fn atomic_swap
325functions return the value at the specified address.
326The
327.Fn atomic_testandset
328function returns the result of the test operation.
329.Sh EXAMPLES
330This example uses the
331.Fn atomic_cmpset_acq_ptr
332and
333.Fn atomic_set_ptr
334functions to obtain a sleep mutex and handle recursion.
335Since the
336.Va mtx_lock
337member of a
338.Vt "struct mtx"
339is a pointer, the
340.Dq Li ptr
341type is used.
342.Bd -literal
343/* Try to obtain mtx_lock once. */
344#define _obtain_lock(mp, tid)						\\
345	atomic_cmpset_acq_ptr(&(mp)->mtx_lock, MTX_UNOWNED, (tid))
346
347/* Get a sleep lock, deal with recursion inline. */
348#define _get_sleep_lock(mp, tid, opts, file, line) do {			\\
349	uintptr_t _tid = (uintptr_t)(tid);				\\
350									\\
351	if (!_obtain_lock(mp, tid)) {					\\
352		if (((mp)->mtx_lock & MTX_FLAGMASK) != _tid)		\\
353			_mtx_lock_sleep((mp), _tid, (opts), (file), (line));\\
354		else {							\\
355			atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE);	\\
356			(mp)->mtx_recurse++;				\\
357		}							\\
358	}								\\
359} while (0)
360.Ed
361.Sh HISTORY
362The
363.Fn atomic_add ,
364.Fn atomic_clear ,
365.Fn atomic_set ,
366and
367.Fn atomic_subtract
368operations were first introduced in
369.Fx 3.0 .
370This first set only supported the types
371.Dq Li char ,
372.Dq Li short ,
373.Dq Li int ,
374and
375.Dq Li long .
376The
377.Fn atomic_cmpset ,
378.Fn atomic_load ,
379.Fn atomic_readandclear ,
380and
381.Fn atomic_store
382operations were added in
383.Fx 5.0 .
384The types
385.Dq Li 8 ,
386.Dq Li 16 ,
387.Dq Li 32 ,
388.Dq Li 64 ,
389and
390.Dq Li ptr
391and all of the acquire and release variants
392were added in
393.Fx 5.0
394as well.
395The
396.Fn atomic_fetchadd
397operations were added in
398.Fx 6.0 .
399The
400.Fn atomic_swap
401and
402.Fn atomic_testandset
403operations were added in
404.Fx 10.0 .
405