xref: /freebsd/share/man/man9/atomic.9 (revision 6b129086dcee14496517fae085b448e3edc69bc7)
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.
172.Ss Semantics
173This section describes the semantics of each operation using a C like notation.
174.Bl -hang
175.It Fn atomic_add p v
176.Bd -literal -compact
177*p += v;
178.Ed
179.It Fn atomic_clear p v
180.Bd -literal -compact
181*p &= ~v;
182.Ed
183.It Fn atomic_cmpset dst old new
184.Bd -literal -compact
185if (*dst == old) {
186	*dst = new;
187	return (1);
188} else
189	return (0);
190.Ed
191.El
192.Pp
193The
194.Fn atomic_cmpset
195functions are not implemented for the types
196.Dq Li char ,
197.Dq Li short ,
198.Dq Li 8 ,
199and
200.Dq Li 16 .
201.Bl -hang
202.It Fn atomic_fetchadd p v
203.Bd -literal -compact
204tmp = *p;
205*p += v;
206return (tmp);
207.Ed
208.El
209.Pp
210The
211.Fn atomic_fetchadd
212functions are only implemented for the types
213.Dq Li int ,
214.Dq Li long
215and
216.Dq Li 32
217and do not have any variants with memory barriers at this time.
218.Bl -hang
219.It Fn atomic_load p
220.Bd -literal -compact
221return (*p);
222.Ed
223.El
224.Pp
225The
226.Fn atomic_load
227functions are only provided with acquire memory barriers.
228.Bl -hang
229.It Fn atomic_readandclear p
230.Bd -literal -compact
231tmp = *p;
232*p = 0;
233return (tmp);
234.Ed
235.El
236.Pp
237The
238.Fn atomic_readandclear
239functions are not implemented for the types
240.Dq Li char ,
241.Dq Li short ,
242.Dq Li ptr ,
243.Dq Li 8 ,
244and
245.Dq Li 16
246and do not have any variants with memory barriers at this time.
247.Bl -hang
248.It Fn atomic_set p v
249.Bd -literal -compact
250*p |= v;
251.Ed
252.It Fn atomic_subtract p v
253.Bd -literal -compact
254*p -= v;
255.Ed
256.It Fn atomic_store p v
257.Bd -literal -compact
258*p = v;
259.Ed
260.El
261.Pp
262The
263.Fn atomic_store
264functions are only provided with release memory barriers.
265.Bl -hang
266.It Fn atomic_swap p v
267.Bd -literal -compact
268tmp = *p;
269*p = v;
270return (tmp);
271.Ed
272.El
273.Pp
274The
275.Fn atomic_swap
276functions are not implemented for the types
277.Dq Li char ,
278.Dq Li short ,
279.Dq Li ptr ,
280.Dq Li 8 ,
281and
282.Dq Li 16
283and do not have any variants with memory barriers at this time.
284.Bl -hang
285.It Fn atomic_testandset p v
286.Bd -literal -compact
287bit = 1 << (v % (sizeof(*p) * NBBY));
288tmp = (*p & bit) != 0;
289*p |= bit;
290return (tmp);
291.Ed
292.El
293.Pp
294The
295.Fn atomic_testandset
296functions are only implemented for the types
297.Dq Li int ,
298.Dq Li long
299and
300.Dq Li 32
301and do not have any variants with memory barriers at this time.
302.Pp
303The type
304.Dq Li 64
305is currently not implemented for any of the atomic operations on the
306.Tn arm ,
307.Tn i386 ,
308and
309.Tn powerpc
310architectures.
311.Sh RETURN VALUES
312The
313.Fn atomic_cmpset
314function returns the result of the compare operation.
315The
316.Fn atomic_fetchadd ,
317.Fn atomic_load ,
318.Fn atomic_readandclear ,
319and
320.Fn atomic_swap
321functions return the value at the specified address.
322The
323.Fn atomic_testandset
324function returns the result of the test operation.
325.Sh EXAMPLES
326This example uses the
327.Fn atomic_cmpset_acq_ptr
328and
329.Fn atomic_set_ptr
330functions to obtain a sleep mutex and handle recursion.
331Since the
332.Va mtx_lock
333member of a
334.Vt "struct mtx"
335is a pointer, the
336.Dq Li ptr
337type is used.
338.Bd -literal
339/* Try to obtain mtx_lock once. */
340#define _obtain_lock(mp, tid)						\\
341	atomic_cmpset_acq_ptr(&(mp)->mtx_lock, MTX_UNOWNED, (tid))
342
343/* Get a sleep lock, deal with recursion inline. */
344#define _get_sleep_lock(mp, tid, opts, file, line) do {			\\
345	uintptr_t _tid = (uintptr_t)(tid);				\\
346									\\
347	if (!_obtain_lock(mp, tid)) {					\\
348		if (((mp)->mtx_lock & MTX_FLAGMASK) != _tid)		\\
349			_mtx_lock_sleep((mp), _tid, (opts), (file), (line));\\
350		else {							\\
351			atomic_set_ptr(&(mp)->mtx_lock, MTX_RECURSE);	\\
352			(mp)->mtx_recurse++;				\\
353		}							\\
354	}								\\
355} while (0)
356.Ed
357.Sh HISTORY
358The
359.Fn atomic_add ,
360.Fn atomic_clear ,
361.Fn atomic_set ,
362and
363.Fn atomic_subtract
364operations were first introduced in
365.Fx 3.0 .
366This first set only supported the types
367.Dq Li char ,
368.Dq Li short ,
369.Dq Li int ,
370and
371.Dq Li long .
372The
373.Fn atomic_cmpset ,
374.Fn atomic_load ,
375.Fn atomic_readandclear ,
376and
377.Fn atomic_store
378operations were added in
379.Fx 5.0 .
380The types
381.Dq Li 8 ,
382.Dq Li 16 ,
383.Dq Li 32 ,
384.Dq Li 64 ,
385and
386.Dq Li ptr
387and all of the acquire and release variants
388were added in
389.Fx 5.0
390as well.
391The
392.Fn atomic_fetchadd
393operations were added in
394.Fx 6.0 .
395The
396.Fn atomic_swap
397and
398.Fn atomic_testandset
399operations were added in
400.Fx 10.0 .
401